dp-di is an open-weight model from Ean. Its published files total 296.3 GB.
Parameters—
Context—
Weights290.7 GB
License—
AccessOpen weights
Monthly Downloads—
Model Card
The publisher has not written a card for this model.
Identity and Version
- Repository
- eantropix/dp-di
- Publisher
- Ean
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 5f63b32577def14354cecc0a737cea4153adffbd
- First published
- 2026-09-04
- Last updated
- 2026-10-15
Files and Weights
3,703 files, 296.3 GB in total. The weights are 1156 files totalling 290.7 GB in bin, pt, pth, safetensors.
Weights1156 files · 290.7 GB
Configuration964 files · 43.2 MB
Tokenizer39 files · 344.2 MB
Documentation316 files · 1.3 MB
Other524 files · 135.1 MB
Repository1 file · 37.1 KB
Every file (first 3,000)
| File | Type | Size | SHA-256 |
|---|---|---|---|
| Llama-3.2-1B_full_fastdp/model.safetensors | Weights | 2.5 GB | b2b078f5d5ac |
| Llama-3.2-1B_full_fastdp/training_args.bin | Weights | 5.6 KB | 5c3bb67f3765 |
| Llama-3.2-1B_full_lr0.001_e3/model.safetensors | Weights | 2.5 GB | ff3026517773 |
| Llama-3.2-1B_full_lr0.001_e3/training_args.bin | Weights | 5.6 KB | 03442af61554 |
| Llama-3.2-1B_full_nodp/model.safetensors | Weights | 2.5 GB | 9f126fc713cf |
| Llama-3.2-1B_full_nodp/training_args.bin | Weights | 5.6 KB | 5c3bb67f3765 |
| Llama-3.2-1B_lora_fastdp/adapter_model.safetensors | Weights | 45.1 MB | 1c2e0ced3c82 |
| Llama-3.2-1B_lora_fastdp/training_args.bin | Weights | 5.6 KB | 5c3bb67f3765 |
| Llama-3.2-1B_lora_nodp/adapter_model.safetensors | Weights | 45.1 MB | ba4773995e43 |
| Llama-3.2-1B_lora_nodp/training_args.bin | Weights | 5.6 KB | 5c3bb67f3765 |
| Llama-3.2-1B_lora_r16_a32_lr0.001_e3/adapter_model.safetensors | Weights | 45.1 MB | 574bb1df9b08 |
| Llama-3.2-1B_lora_r16_a32_lr0.001_e3/training_args.bin | Weights | 5.6 KB | 03442af61554 |
| Llama-3.2-1B_qlora_fastdp/adapter_model.safetensors | Weights | 45.1 MB | f2f18e82fa32 |
| Llama-3.2-1B_qlora_fastdp/training_args.bin | Weights | 5.6 KB | 5c3bb67f3765 |
| Llama-3.2-1B_qlora_nodp/adapter_model.safetensors | Weights | 45.1 MB | 53ca785fd522 |
| Llama-3.2-1B_qlora_nodp/training_args.bin | Weights | 5.6 KB | 5c3bb67f3765 |
| Llama-3.2-3B_full_lr0.001_e3/model.safetensors | Weights | 6.4 GB | 283b345c7eb9 |
| Llama-3.2-3B_full_lr0.001_e3/training_args.bin | Weights | 5.6 KB | 03442af61554 |
| Llama-3.2-3B_full_nodp/model.safetensors | Weights | 6.4 GB | 0a66b75949bf |
| Llama-3.2-3B_full_nodp/training_args.bin | Weights | 5.6 KB | 5c3bb67f3765 |
| Llama-3.2-3B_lora_nodp/adapter_model.safetensors | Weights | 97.3 MB | e90dc41e70b0 |
| Llama-3.2-3B_lora_nodp/training_args.bin | Weights | 5.6 KB | 5c3bb67f3765 |
| Llama-3.2-3B_lora_r16_a32_lr0.001_e3/adapter_model.safetensors | Weights | 97.3 MB | bc9608d6c6b6 |
| Llama-3.2-3B_lora_r16_a32_lr0.001_e3/training_args.bin | Weights | 5.6 KB | 03442af61554 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/adapter_model.safetensors | Weights | 180.4 MB | 1859f648380e |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-173/adapter_model.safetensors | Weights | 90.2 MB | 98dcbbc90479 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-173/optimizer.pt | Weights | 180.5 MB | f66e50ae214f |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-173/rng_state.pth | Weights | 14.6 KB | 6c56778bbd09 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-173/scheduler.pt | Weights | 1.4 KB | be6fd9c20c17 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-173/training_args.bin | Weights | 5.7 KB | 6b278657c62a |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-692/adapter_model.safetensors | Weights | 90.2 MB | bf890fdf0ef8 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-692/optimizer.pt | Weights | 180.5 MB | bd65784a719d |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-692/rng_state.pth | Weights | 14.6 KB | 2a2baff5f9dd |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-692/scheduler.pt | Weights | 1.5 KB | d1fd62670aa1 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-692/training_args.bin | Weights | 5.7 KB | 6b278657c62a |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/training_args.bin | Weights | 5.7 KB | 6b278657c62a |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/adapter_model.safetensors | Weights | 180.4 MB | 9a106fbb1a86 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-173/adapter_model.safetensors | Weights | 90.2 MB | 9726f6228573 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-173/optimizer.pt | Weights | 180.5 MB | 9684397c7c2c |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-173/rng_state.pth | Weights | 14.6 KB | 6c56778bbd09 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-173/scheduler.pt | Weights | 1.4 KB | be6fd9c20c17 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-173/training_args.bin | Weights | 5.7 KB | 147c502033ce |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-692/adapter_model.safetensors | Weights | 90.2 MB | 5f8e3b8c7042 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-692/optimizer.pt | Weights | 180.5 MB | abcd64d13ba2 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-692/rng_state.pth | Weights | 14.6 KB | 2a2baff5f9dd |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-692/scheduler.pt | Weights | 1.5 KB | d1fd62670aa1 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-692/training_args.bin | Weights | 5.7 KB | 147c502033ce |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/training_args.bin | Weights | 5.7 KB | 147c502033ce |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/adapter_model.safetensors | Weights | 180.4 MB | bce4cd7a4d3f |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/checkpoint-173/adapter_model.safetensors | Weights | 90.2 MB | 67925ddc0404 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/checkpoint-173/optimizer.pt | Weights | 180.5 MB | 9684397c7c2c |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/checkpoint-173/rng_state.pth | Weights | 14.6 KB | 6c56778bbd09 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/checkpoint-173/scheduler.pt | Weights | 1.4 KB | be6fd9c20c17 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/checkpoint-173/training_args.bin | Weights | 5.7 KB | cfb6e7bf357f |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/checkpoint-692/adapter_model.safetensors | Weights | 90.2 MB | ddd62a51b8da |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/checkpoint-692/optimizer.pt | Weights | 180.5 MB | fbc193b249b5 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/checkpoint-692/rng_state.pth | Weights | 14.6 KB | 2a2baff5f9dd |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/checkpoint-692/scheduler.pt | Weights | 1.5 KB | d1fd62670aa1 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/checkpoint-692/training_args.bin | Weights | 5.7 KB | cfb6e7bf357f |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/training_args.bin | Weights | 5.7 KB | cfb6e7bf357f |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/adapter_model.safetensors | Weights | 180.4 MB | 34835a529771 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/checkpoint-173/adapter_model.safetensors | Weights | 90.2 MB | dfdca5d53c4b |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/checkpoint-173/optimizer.pt | Weights | 180.5 MB | 94b261971e8b |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/checkpoint-173/rng_state.pth | Weights | 14.6 KB | 6c56778bbd09 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/checkpoint-173/scheduler.pt | Weights | 1.4 KB | be6fd9c20c17 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/checkpoint-173/training_args.bin | Weights | 5.7 KB | 5a02b8387d7f |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/checkpoint-692/adapter_model.safetensors | Weights | 90.2 MB | f2620f89c401 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/checkpoint-692/optimizer.pt | Weights | 180.5 MB | 85b1810ed666 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/checkpoint-692/rng_state.pth | Weights | 14.6 KB | 2a2baff5f9dd |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/checkpoint-692/scheduler.pt | Weights | 1.5 KB | d1fd62670aa1 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/checkpoint-692/training_args.bin | Weights | 5.7 KB | 5a02b8387d7f |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/training_args.bin | Weights | 5.7 KB | 5a02b8387d7f |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/adapter_model.safetensors | Weights | 180.4 MB | 6db6309d59cf |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/checkpoint-173/adapter_model.safetensors | Weights | 90.2 MB | 8e845847c9b0 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/checkpoint-173/optimizer.pt | Weights | 180.5 MB | bc79ff93d257 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/checkpoint-173/rng_state.pth | Weights | 14.6 KB | 6c56778bbd09 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/checkpoint-173/scheduler.pt | Weights | 1.4 KB | be6fd9c20c17 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/checkpoint-173/training_args.bin | Weights | 5.7 KB | d8fee2016f78 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/checkpoint-692/adapter_model.safetensors | Weights | 90.2 MB | 11bc6047f966 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/checkpoint-692/optimizer.pt | Weights | 180.5 MB | 792f7eea7b4d |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/checkpoint-692/rng_state.pth | Weights | 14.6 KB | 2a2baff5f9dd |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/checkpoint-692/scheduler.pt | Weights | 1.5 KB | d1fd62670aa1 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/checkpoint-692/training_args.bin | Weights | 5.7 KB | d8fee2016f78 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/training_args.bin | Weights | 5.7 KB | d8fee2016f78 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/adapter_model.safetensors | Weights | 180.4 MB | 01b59022f5ea |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/checkpoint-173/adapter_model.safetensors | Weights | 90.2 MB | da59529b688d |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/checkpoint-173/optimizer.pt | Weights | 180.5 MB | 40b9f159a4a8 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/checkpoint-173/rng_state.pth | Weights | 14.6 KB | 6c56778bbd09 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/checkpoint-173/scheduler.pt | Weights | 1.4 KB | be6fd9c20c17 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/checkpoint-173/training_args.bin | Weights | 5.7 KB | 488c8e405498 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/checkpoint-692/adapter_model.safetensors | Weights | 90.2 MB | c52baf41f93e |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/checkpoint-692/optimizer.pt | Weights | 180.5 MB | 8bdbc804bd44 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/checkpoint-692/rng_state.pth | Weights | 14.6 KB | 2a2baff5f9dd |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/checkpoint-692/scheduler.pt | Weights | 1.5 KB | d1fd62670aa1 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/checkpoint-692/training_args.bin | Weights | 5.7 KB | 488c8e405498 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/training_args.bin | Weights | 5.7 KB | 488c8e405498 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/adapter_model.safetensors | Weights | 180.4 MB | c8c0cb70a293 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/checkpoint-173/adapter_model.safetensors | Weights | 90.2 MB | 60132fe17966 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/checkpoint-173/optimizer.pt | Weights | 180.5 MB | aeb34debcecc |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/checkpoint-173/rng_state.pth | Weights | 14.6 KB | 6c56778bbd09 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/checkpoint-173/scheduler.pt | Weights | 1.4 KB | be6fd9c20c17 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/checkpoint-173/training_args.bin | Weights | 5.7 KB | e5162310d524 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/checkpoint-692/adapter_model.safetensors | Weights | 90.2 MB | 10b476c649ef |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/checkpoint-692/optimizer.pt | Weights | 180.5 MB | 5c2ef38fb878 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/checkpoint-692/rng_state.pth | Weights | 14.6 KB | 2a2baff5f9dd |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/checkpoint-692/scheduler.pt | Weights | 1.5 KB | d1fd62670aa1 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/checkpoint-692/training_args.bin | Weights | 5.7 KB | e5162310d524 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/training_args.bin | Weights | 5.7 KB | e5162310d524 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/adapter_model.safetensors | Weights | 180.4 MB | e9009c58add7 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/checkpoint-173/adapter_model.safetensors | Weights | 90.2 MB | 8675ef1c7384 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/checkpoint-173/optimizer.pt | Weights | 180.5 MB | 08e7a16fe76e |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/checkpoint-173/rng_state.pth | Weights | 14.6 KB | 6c56778bbd09 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/checkpoint-173/scheduler.pt | Weights | 1.4 KB | be6fd9c20c17 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/checkpoint-173/training_args.bin | Weights | 5.7 KB | 1dc49e259d68 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/checkpoint-692/adapter_model.safetensors | Weights | 90.2 MB | 21fa3e194301 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/checkpoint-692/optimizer.pt | Weights | 180.5 MB | 9ab315be8bf4 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/checkpoint-692/rng_state.pth | Weights | 14.6 KB | 2a2baff5f9dd |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/checkpoint-692/scheduler.pt | Weights | 1.5 KB | d1fd62670aa1 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/checkpoint-692/training_args.bin | Weights | 5.7 KB | 1dc49e259d68 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/training_args.bin | Weights | 5.7 KB | 1dc49e259d68 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/adapter_model.safetensors | Weights | 180.4 MB | a9a030aeed3b |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/checkpoint-173/adapter_model.safetensors | Weights | 90.2 MB | 4a8653c76ea3 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/checkpoint-173/optimizer.pt | Weights | 180.5 MB | c66c8db3ccba |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/checkpoint-173/rng_state.pth | Weights | 14.6 KB | 6c56778bbd09 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/checkpoint-173/scheduler.pt | Weights | 1.4 KB | be6fd9c20c17 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/checkpoint-173/training_args.bin | Weights | 5.7 KB | a1b824b1948b |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/checkpoint-692/adapter_model.safetensors | Weights | 90.2 MB | 15b6583eb041 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/checkpoint-692/optimizer.pt | Weights | 180.5 MB | e0bb61bed77b |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/checkpoint-692/rng_state.pth | Weights | 14.6 KB | 2a2baff5f9dd |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/checkpoint-692/scheduler.pt | Weights | 1.5 KB | d1fd62670aa1 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/checkpoint-692/training_args.bin | Weights | 5.7 KB | a1b824b1948b |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/training_args.bin | Weights | 5.7 KB | a1b824b1948b |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/adapter_model.safetensors | Weights | 180.4 MB | fcc22ee33ba6 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/checkpoint-173/adapter_model.safetensors | Weights | 90.2 MB | 862c25a36560 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/checkpoint-173/optimizer.pt | Weights | 180.5 MB | c64671e2b928 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/checkpoint-173/rng_state.pth | Weights | 14.6 KB | 6c56778bbd09 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/checkpoint-173/scheduler.pt | Weights | 1.4 KB | be6fd9c20c17 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/checkpoint-173/training_args.bin | Weights | 5.7 KB | b2298bc3b5cc |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/checkpoint-692/adapter_model.safetensors | Weights | 90.2 MB | d3586a4e77ec |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/checkpoint-692/optimizer.pt | Weights | 180.5 MB | 4f6a85f50f74 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/checkpoint-692/rng_state.pth | Weights | 14.6 KB | 2a2baff5f9dd |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/checkpoint-692/scheduler.pt | Weights | 1.5 KB | d1fd62670aa1 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/checkpoint-692/training_args.bin | Weights | 5.7 KB | b2298bc3b5cc |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/training_args.bin | Weights | 5.7 KB | b2298bc3b5cc |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/adapter_model.safetensors | Weights | 180.4 MB | 35f202eccfd7 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/checkpoint-173/adapter_model.safetensors | Weights | 90.2 MB | a74a4a781b5f |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/checkpoint-173/optimizer.pt | Weights | 180.5 MB | 5ef9c2d90b88 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/checkpoint-173/rng_state.pth | Weights | 14.6 KB | 6c56778bbd09 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/checkpoint-173/scheduler.pt | Weights | 1.4 KB | be6fd9c20c17 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/checkpoint-173/training_args.bin | Weights | 5.7 KB | c0bdb6a5b7df |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/checkpoint-692/adapter_model.safetensors | Weights | 90.2 MB | 2b41b927e3d6 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/checkpoint-692/optimizer.pt | Weights | 180.5 MB | c8df22b3d0b6 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/checkpoint-692/rng_state.pth | Weights | 14.6 KB | 2a2baff5f9dd |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/checkpoint-692/scheduler.pt | Weights | 1.5 KB | d1fd62670aa1 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/checkpoint-692/training_args.bin | Weights | 5.7 KB | c0bdb6a5b7df |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/training_args.bin | Weights | 5.7 KB | c0bdb6a5b7df |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/adapter_model.safetensors | Weights | 180.4 MB | 4fa4bf1633e0 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/checkpoint-173/adapter_model.safetensors | Weights | 90.2 MB | ad9a2d3a424c |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/checkpoint-173/optimizer.pt | Weights | 180.5 MB | 69aca4091d1d |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/checkpoint-173/rng_state.pth | Weights | 14.6 KB | 6c56778bbd09 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/checkpoint-173/scheduler.pt | Weights | 1.4 KB | be6fd9c20c17 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/checkpoint-173/training_args.bin | Weights | 5.7 KB | 38bc4df56a61 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/checkpoint-692/adapter_model.safetensors | Weights | 90.2 MB | 88a1b4bf5a43 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/checkpoint-692/optimizer.pt | Weights | 180.5 MB | e465e29fd45f |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/checkpoint-692/rng_state.pth | Weights | 14.6 KB | 2a2baff5f9dd |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/checkpoint-692/scheduler.pt | Weights | 1.5 KB | d1fd62670aa1 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/checkpoint-692/training_args.bin | Weights | 5.7 KB | 38bc4df56a61 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/training_args.bin | Weights | 5.7 KB | 38bc4df56a61 |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1730/model.safetensors | Weights | 2.5 GB | 9e59a7420cd6 |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1730/optimizer.pt | Weights | 4.9 GB | 435e764d1138 |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1730/rng_state.pth | Weights | 14.6 KB | d233ab4262c4 |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1730/scheduler.pt | Weights | 1.5 KB | c032df8b3c15 |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1730/training_args.bin | Weights | 5.7 KB | 583496fe5ef6 |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1734/model.safetensors | Weights | 2.5 GB | e87206d7fce2 |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1734/optimizer.pt | Weights | 4.9 GB | 3948e01d43b2 |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1734/rng_state.pth | Weights | 14.6 KB | beae152c63fd |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1734/scheduler.pt | Weights | 1.5 KB | 485ae713f246 |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1734/training_args.bin | Weights | 5.7 KB | 583496fe5ef6 |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/model.safetensors | Weights | 2.5 GB | 9e59a7420cd6 |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/training_args.bin | Weights | 5.7 KB | 583496fe5ef6 |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1730/model.safetensors | Weights | 2.5 GB | 8b4c9d2653e2 |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1730/optimizer.pt | Weights | 4.9 GB | 3e991cf49002 |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1730/rng_state.pth | Weights | 14.6 KB | d233ab4262c4 |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1730/scheduler.pt | Weights | 1.5 KB | 167650c76738 |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1730/training_args.bin | Weights | 5.7 KB | 0db9f4519d12 |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1734/model.safetensors | Weights | 2.5 GB | 2a4029a5e601 |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1734/optimizer.pt | Weights | 4.9 GB | 93635df098d5 |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1734/rng_state.pth | Weights | 14.6 KB | beae152c63fd |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1734/scheduler.pt | Weights | 1.5 KB | 363a8a601eb9 |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1734/training_args.bin | Weights | 5.7 KB | 0db9f4519d12 |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/model.safetensors | Weights | 2.5 GB | 8b4c9d2653e2 |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/training_args.bin | Weights | 5.7 KB | 0db9f4519d12 |
| fft/fastdp/llama-3.2-1b_eps0.1_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 2.5 GB | b7721aacc754 |
| fft/fastdp/llama-3.2-1b_eps0.1_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 7c6e70433f20 |
| fft/fastdp/llama-3.2-1b_eps0.5_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 2.5 GB | 4c600455cb61 |
| fft/fastdp/llama-3.2-1b_eps0.5_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 5c9e499a37ee |
| fft/fastdp/llama-3.2-1b_eps1.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 2.5 GB | 1f17a64bf14b |
| fft/fastdp/llama-3.2-1b_eps1.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | a3879bb60a78 |
| fft/fastdp/llama-3.2-1b_eps100.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 2.5 GB | b7c280016f54 |
| fft/fastdp/llama-3.2-1b_eps100.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | e0cf7ebbc6a3 |
| fft/fastdp/llama-3.2-1b_eps1000.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 2.5 GB | 8f3b882b596e |
| fft/fastdp/llama-3.2-1b_eps1000.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 78c5beb0395e |
| fft/fastdp/llama-3.2-1b_eps16.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 2.5 GB | 860ab1330864 |
| fft/fastdp/llama-3.2-1b_eps16.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 28816717bb5a |
| fft/fastdp/llama-3.2-1b_eps2.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 2.5 GB | 45ec82ef0325 |
| fft/fastdp/llama-3.2-1b_eps2.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 56de19f1955f |
| fft/fastdp/llama-3.2-1b_eps32.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 2.5 GB | d378cdbbe0e2 |
| fft/fastdp/llama-3.2-1b_eps32.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 9ef54340f282 |
| fft/fastdp/llama-3.2-1b_eps4.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 2.5 GB | 99007a58b200 |
| fft/fastdp/llama-3.2-1b_eps4.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | b90ba0f47dae |
| fft/fastdp/llama-3.2-1b_eps500.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 2.5 GB | 9933bdc73e47 |
| fft/fastdp/llama-3.2-1b_eps500.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 084544af86c0 |
| fft/fastdp/llama-3.2-1b_eps64.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 2.5 GB | 2cb5d347f8d2 |
| fft/fastdp/llama-3.2-1b_eps64.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | b56276145f0f |
| fft/fastdp/llama-3.2-1b_eps8.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 2.5 GB | 0db10bc7e277 |
| fft/fastdp/llama-3.2-1b_eps8.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | fbc8707d6eac |
| fft/fastdp/qwen2.5-0.5b_eps0.1_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 988.1 MB | f19b11138f12 |
| fft/fastdp/qwen2.5-0.5b_eps0.1_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 6f3f1e545eeb |
| fft/fastdp/qwen2.5-0.5b_eps0.5_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 988.1 MB | 10774f90a90b |
| fft/fastdp/qwen2.5-0.5b_eps0.5_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 20035d8b94b2 |
| fft/fastdp/qwen2.5-0.5b_eps1.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 988.1 MB | 264942e41393 |
| fft/fastdp/qwen2.5-0.5b_eps1.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | e914c9ea47d6 |
| fft/fastdp/qwen2.5-0.5b_eps100.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 988.1 MB | ebd33b14fe41 |
| fft/fastdp/qwen2.5-0.5b_eps100.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 89f422c1b419 |
| fft/fastdp/qwen2.5-0.5b_eps1000.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 988.1 MB | b7cac376ff51 |
| fft/fastdp/qwen2.5-0.5b_eps1000.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 65f52e1d9302 |
| fft/fastdp/qwen2.5-0.5b_eps16.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 988.1 MB | ba9cdca780cb |
| fft/fastdp/qwen2.5-0.5b_eps16.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 4755f73c9dd7 |
| fft/fastdp/qwen2.5-0.5b_eps2.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 988.1 MB | ab0067e95cc7 |
| fft/fastdp/qwen2.5-0.5b_eps2.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 6ab9f032ac87 |
| fft/fastdp/qwen2.5-0.5b_eps32.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 988.1 MB | 79b0c79cbae0 |
| fft/fastdp/qwen2.5-0.5b_eps32.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 535538a96117 |
| fft/fastdp/qwen2.5-0.5b_eps4.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 988.1 MB | 684e86e2bf33 |
| fft/fastdp/qwen2.5-0.5b_eps4.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 2fa42261e03f |
| fft/fastdp/qwen2.5-0.5b_eps500.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 988.1 MB | 78e4743b477b |
| fft/fastdp/qwen2.5-0.5b_eps500.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 30ce55ef5452 |
| fft/fastdp/qwen2.5-0.5b_eps64.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 988.1 MB | a26ce48f895a |
| fft/fastdp/qwen2.5-0.5b_eps64.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 416e8c18d107 |
| fft/fastdp/qwen2.5-0.5b_eps8.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 988.1 MB | c3dcdfa8aaa4 |
| fft/fastdp/qwen2.5-0.5b_eps8.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 8bd2618df282 |
| fft/fastdp/smollm-1.7b_eps0.1_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 3.4 GB | 096bb5c34ffe |
| fft/fastdp/smollm-1.7b_eps0.1_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | b4ab5f15667e |
| fft/fastdp/smollm-1.7b_eps0.5_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 3.4 GB | 26c863cd126e |
| fft/fastdp/smollm-1.7b_eps0.5_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 8bf9b4477c4f |
| fft/fastdp/smollm-1.7b_eps1.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 3.4 GB | b0e08aeac79e |
| fft/fastdp/smollm-1.7b_eps1.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 94746b6bd5c5 |
| fft/fastdp/smollm-1.7b_eps100.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 3.4 GB | b58f7a602338 |
| fft/fastdp/smollm-1.7b_eps100.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 365684e58db1 |
| fft/fastdp/smollm-1.7b_eps1000.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 3.4 GB | 3530e5940c91 |
| fft/fastdp/smollm-1.7b_eps1000.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 8e874b94ed47 |
| fft/fastdp/smollm-1.7b_eps16.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 3.4 GB | 3ef7ab38be3d |
| fft/fastdp/smollm-1.7b_eps16.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 5cf7f984f596 |
| fft/fastdp/smollm-1.7b_eps2.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 3.4 GB | c2e3a52784fa |
| fft/fastdp/smollm-1.7b_eps2.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | b96883ddfc38 |
| fft/fastdp/smollm-1.7b_eps32.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 3.4 GB | 6ccca8c195f5 |
| fft/fastdp/smollm-1.7b_eps32.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 03dc0207ef4f |
| fft/fastdp/smollm-1.7b_eps4.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 3.4 GB | f431a8da563c |
| fft/fastdp/smollm-1.7b_eps4.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | bc2b3155394a |
| fft/fastdp/smollm-1.7b_eps500.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 3.4 GB | 8ebbe84188e7 |
| fft/fastdp/smollm-1.7b_eps500.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 321f6f93f586 |
| fft/fastdp/smollm-1.7b_eps64.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 3.4 GB | ecd556108d4a |
| fft/fastdp/smollm-1.7b_eps64.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 7e78abe04424 |
| fft/fastdp/smollm-1.7b_eps8.0_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 3.4 GB | df9b6096d7e4 |
| fft/fastdp/smollm-1.7b_eps8.0_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 091d56bd8d13 |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1730/model.safetensors | Weights | 2.5 GB | 38dd05ffafd6 |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1730/optimizer.pt | Weights | 2.5 GB | 48d54ec9cfb5 |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1730/rng_state.pth | Weights | 14.6 KB | 236304ae89e4 |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1730/scheduler.pt | Weights | 1.5 KB | c032df8b3c15 |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1730/training_args.bin | Weights | 5.7 KB | 4fe579522a1d |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1734/model.safetensors | Weights | 2.5 GB | f13eb1e27f39 |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1734/optimizer.pt | Weights | 2.5 GB | b097fbdb2d01 |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1734/rng_state.pth | Weights | 14.6 KB | 236304ae89e4 |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1734/scheduler.pt | Weights | 1.5 KB | 485ae713f246 |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1734/training_args.bin | Weights | 5.7 KB | 4fe579522a1d |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/model.safetensors | Weights | 2.5 GB | 38dd05ffafd6 |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/training_args.bin | Weights | 5.7 KB | 4fe579522a1d |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1038/model.safetensors | Weights | 2.5 GB | 52145896c131 |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1038/optimizer.pt | Weights | 2.5 GB | c19858cbb69d |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | fdc37bbd2e97 |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | d5d386d0ed97 |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 5661aedae92a |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/checkpoint-519/model.safetensors | Weights | 2.5 GB | 4b9fbd260873 |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/checkpoint-519/optimizer.pt | Weights | 2.5 GB | 3e31efd0fee4 |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/checkpoint-519/rng_state.pth | Weights | 14.6 KB | a8e2011629d8 |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/checkpoint-519/scheduler.pt | Weights | 1.5 KB | 98ae58e0a386 |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/checkpoint-519/training_args.bin | Weights | 5.7 KB | 5661aedae92a |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/model.safetensors | Weights | 2.5 GB | 4b9fbd260873 |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/training_args.bin | Weights | 5.7 KB | 5661aedae92a |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 2.5 GB | 18d67303926e |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | bfa8219e73af |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/checkpoint-1730/model.safetensors | Weights | 6.4 GB | 4fac673a8576 |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/checkpoint-1730/optimizer.pt | Weights | 6.5 GB | e07340791352 |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/checkpoint-1730/rng_state.pth | Weights | 14.6 KB | 236304ae89e4 |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/checkpoint-1730/scheduler.pt | Weights | 1.5 KB | c032df8b3c15 |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/checkpoint-1730/training_args.bin | Weights | 5.7 KB | b96b7d3e682f |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/checkpoint-1734/model.safetensors | Weights | 6.4 GB | 4cfd684e7e61 |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/checkpoint-1734/optimizer.pt | Weights | 6.5 GB | 2adf2144d09d |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/checkpoint-1734/rng_state.pth | Weights | 14.6 KB | 236304ae89e4 |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/checkpoint-1734/scheduler.pt | Weights | 1.5 KB | 485ae713f246 |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/checkpoint-1734/training_args.bin | Weights | 5.7 KB | b96b7d3e682f |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/model.safetensors | Weights | 6.4 GB | 4fac673a8576 |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/training_args.bin | Weights | 5.7 KB | b96b7d3e682f |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/checkpoint-1038/model.safetensors | Weights | 6.4 GB | 98a4c61248ed |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/checkpoint-1038/optimizer.pt | Weights | 6.5 GB | 6cbd10e99f75 |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | fdc37bbd2e97 |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | d5d386d0ed97 |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 40ffaf0dd475 |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/checkpoint-519/model.safetensors | Weights | 6.4 GB | 1d77946e9b0e |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/checkpoint-519/optimizer.pt | Weights | 6.5 GB | 30ee7f30deeb |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/checkpoint-519/rng_state.pth | Weights | 14.6 KB | a8e2011629d8 |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/checkpoint-519/scheduler.pt | Weights | 1.5 KB | 98ae58e0a386 |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/checkpoint-519/training_args.bin | Weights | 5.7 KB | 40ffaf0dd475 |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/model.safetensors | Weights | 6.4 GB | 1d77946e9b0e |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/training_args.bin | Weights | 5.7 KB | 40ffaf0dd475 |
| fft/nodp/qwen2.5-0.5b_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 988.1 MB | 842a3f10f692 |
| fft/nodp/qwen2.5-0.5b_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | bb13a5d07e29 |
| fft/nodp/qwen2.5-1.5b_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 3.1 GB | 8e4030af5f1c |
| fft/nodp/qwen2.5-1.5b_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 8026dee342f7 |
| fft/nodp/smollm-1.7b_lr5e-5_ep3_bs8_seq4096/model.safetensors | Weights | 3.4 GB | 280e7be39acf |
| fft/nodp/smollm-1.7b_lr5e-5_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 0ff3dd69e12a |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/adapter_model.safetensors | Weights | 11.3 MB | bd043fb40026 |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/adapter_model.safetensors | Weights | 5.7 MB | eea59966afe8 |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/optimizer.pt | Weights | 11.5 MB | 40feb395bc1a |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/rng_state.pth | Weights | 14.6 KB | ca715e1bef1b |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/scheduler.pt | Weights | 1.5 KB | 9b528c414cbd |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/training_args.bin | Weights | 5.7 KB | b73d8d889ec5 |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/adapter_model.safetensors | Weights | 5.7 MB | 39991b942deb |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/optimizer.pt | Weights | 11.5 MB | 24b47d88cef2 |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/rng_state.pth | Weights | 14.6 KB | 882674f40fc9 |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/scheduler.pt | Weights | 1.5 KB | f86c1fb05bc7 |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/training_args.bin | Weights | 5.7 KB | b73d8d889ec5 |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/training_args.bin | Weights | 5.7 KB | b73d8d889ec5 |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/adapter_model.safetensors | Weights | 180.4 MB | 9c97e47862a8 |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-173/adapter_model.safetensors | Weights | 90.2 MB | 1698e57e1f33 |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-173/optimizer.pt | Weights | 180.5 MB | 5af19c9ffca1 |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-173/rng_state.pth | Weights | 14.6 KB | 6c56778bbd09 |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-173/scheduler.pt | Weights | 1.4 KB | be6fd9c20c17 |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-173/training_args.bin | Weights | 5.7 KB | c6fdc16f108c |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-692/adapter_model.safetensors | Weights | 90.2 MB | e4f6c5d19821 |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-692/optimizer.pt | Weights | 180.5 MB | 5126021e2db3 |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-692/rng_state.pth | Weights | 14.6 KB | 2a2baff5f9dd |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-692/scheduler.pt | Weights | 1.5 KB | d1fd62670aa1 |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-692/training_args.bin | Weights | 5.7 KB | c6fdc16f108c |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/training_args.bin | Weights | 5.7 KB | c6fdc16f108c |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/adapter_model.safetensors | Weights | 97.3 MB | 754ee4c62db5 |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-173/adapter_model.safetensors | Weights | 48.7 MB | 09272dbd4094 |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-173/optimizer.pt | Weights | 97.6 MB | 6f4c32d9eb1c |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-173/rng_state.pth | Weights | 14.6 KB | dedaa0d0b472 |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-173/scheduler.pt | Weights | 1.4 KB | 11f7e18638fd |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-173/training_args.bin | Weights | 5.7 KB | ab525ffc1bdf |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-692/adapter_model.safetensors | Weights | 48.7 MB | 41c096d71419 |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-692/optimizer.pt | Weights | 97.6 MB | bb1593c17f4f |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-692/rng_state.pth | Weights | 14.6 KB | fa5f43044ac4 |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-692/scheduler.pt | Weights | 1.5 KB | 9441e9faaf23 |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-692/training_args.bin | Weights | 5.7 KB | ab525ffc1bdf |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | ab525ffc1bdf |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/adapter_model.safetensors | Weights | 24.4 MB | 1bca690e1fc6 |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1730/adapter_model.safetensors | Weights | 12.2 MB | f47430664f6e |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1730/optimizer.pt | Weights | 24.6 MB | c56655e5d012 |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1730/rng_state.pth | Weights | 14.6 KB | ed4cdd620832 |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1730/scheduler.pt | Weights | 1.5 KB | f38ed2d9f855 |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1730/training_args.bin | Weights | 5.7 KB | 54462d77a5b9 |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1734/adapter_model.safetensors | Weights | 12.2 MB | 70685b6b9fa4 |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1734/optimizer.pt | Weights | 24.6 MB | 4e834187ceaf |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1734/rng_state.pth | Weights | 14.6 KB | b803b92aca96 |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1734/scheduler.pt | Weights | 1.5 KB | bb2b18636584 |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1734/training_args.bin | Weights | 5.7 KB | 54462d77a5b9 |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/training_args.bin | Weights | 5.7 KB | 54462d77a5b9 |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/adapter_model.safetensors | Weights | 389.1 MB | d1b64d7ad154 |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-173/adapter_model.safetensors | Weights | 194.6 MB | 4872cda2810f |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-173/optimizer.pt | Weights | 389.4 MB | af5df6ba31ed |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-173/rng_state.pth | Weights | 14.6 KB | dedaa0d0b472 |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-173/scheduler.pt | Weights | 1.4 KB | be6fd9c20c17 |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-173/training_args.bin | Weights | 5.7 KB | be060928813d |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-692/adapter_model.safetensors | Weights | 194.6 MB | e01f4ea455fe |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-692/optimizer.pt | Weights | 389.4 MB | 97ab38d825ce |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-692/rng_state.pth | Weights | 14.6 KB | fa5f43044ac4 |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-692/scheduler.pt | Weights | 1.5 KB | d1fd62670aa1 |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-692/training_args.bin | Weights | 5.7 KB | be060928813d |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/training_args.bin | Weights | 5.7 KB | be060928813d |
| lora/fastdp/llama-3.2-1b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 90.2 MB | 01a1aad7d5f3 |
| lora/fastdp/llama-3.2-1b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | fae0896e8b6d |
| lora/fastdp/llama-3.2-1b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 90.2 MB | 5e96a06a3c59 |
| lora/fastdp/llama-3.2-1b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | acba0d3f5105 |
| lora/fastdp/llama-3.2-1b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 90.2 MB | 9976c444cbc1 |
| lora/fastdp/llama-3.2-1b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 07b3cb323f60 |
| lora/fastdp/llama-3.2-1b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 90.2 MB | 507b0379590f |
| lora/fastdp/llama-3.2-1b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 9a5f32605fd0 |
| lora/fastdp/llama-3.2-1b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 90.2 MB | 0405b97b6961 |
| lora/fastdp/llama-3.2-1b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 5a7aa3b23eb5 |
| lora/fastdp/llama-3.2-1b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 90.2 MB | a27d3cab835a |
| lora/fastdp/llama-3.2-1b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 31504fcceaa1 |
| lora/fastdp/llama-3.2-1b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 90.2 MB | 932e062e5b76 |
| lora/fastdp/llama-3.2-1b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | d6f46aafa354 |
| lora/fastdp/llama-3.2-1b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 90.2 MB | 61860e166eed |
| lora/fastdp/llama-3.2-1b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 864fd47fbdf5 |
| lora/fastdp/llama-3.2-1b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 90.2 MB | 40c3e4487c1d |
| lora/fastdp/llama-3.2-1b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 45b334d2e663 |
| lora/fastdp/llama-3.2-1b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 90.2 MB | 5ebed057198e |
| lora/fastdp/llama-3.2-1b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 9b765b300c90 |
| lora/fastdp/llama-3.2-1b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 90.2 MB | bda8a0f25670 |
| lora/fastdp/llama-3.2-1b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | b13da57e7756 |
| lora/fastdp/llama-3.2-1b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 90.2 MB | 3b032c062671 |
| lora/fastdp/llama-3.2-1b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 63b0ffd3448a |
| lora/fastdp/qwen2.5-0.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | 188ed1723842 |
| lora/fastdp/qwen2.5-0.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | c6106ae7760f |
| lora/fastdp/qwen2.5-0.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | b7679c54a23b |
| lora/fastdp/qwen2.5-0.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 436953d851f0 |
| lora/fastdp/qwen2.5-0.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | 012a8d636bc4 |
| lora/fastdp/qwen2.5-0.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | c2dc56739b34 |
| lora/fastdp/qwen2.5-0.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | b840a9e33e20 |
| lora/fastdp/qwen2.5-0.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | ade6b8e5906f |
| lora/fastdp/qwen2.5-0.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | 14023e550324 |
| lora/fastdp/qwen2.5-0.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 8d6814076c0e |
| lora/fastdp/qwen2.5-0.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | 6cb384c1ef9e |
| lora/fastdp/qwen2.5-0.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 3c9216c9d716 |
| lora/fastdp/qwen2.5-0.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | d5c182fa8d00 |
| lora/fastdp/qwen2.5-0.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 44af097e76ca |
| lora/fastdp/qwen2.5-0.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | a28d1d2d4e68 |
| lora/fastdp/qwen2.5-0.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 81abea8ecd37 |
| lora/fastdp/qwen2.5-0.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | 085e6366a4c2 |
| lora/fastdp/qwen2.5-0.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | c8441cded0fe |
| lora/fastdp/qwen2.5-0.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | 268adfbc95d1 |
| lora/fastdp/qwen2.5-0.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 9873de9b612b |
| lora/fastdp/qwen2.5-0.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | 476eaeca055b |
| lora/fastdp/qwen2.5-0.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | aa0b68d0233d |
| lora/fastdp/qwen2.5-0.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | cafece9e563a |
| lora/fastdp/qwen2.5-0.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | c014aa93db2c |
| lora/fastdp/qwen2.5-1.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | 5a7d78a65f5e |
| lora/fastdp/qwen2.5-1.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | d5f0c300f63f |
| lora/fastdp/qwen2.5-1.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | 8cf327d61ca7 |
| lora/fastdp/qwen2.5-1.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 24e078c91d3a |
| lora/fastdp/qwen2.5-1.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | 97021676e9dc |
| lora/fastdp/qwen2.5-1.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 36c3d2a45e48 |
| lora/fastdp/qwen2.5-1.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | 14de3bfcb624 |
| lora/fastdp/qwen2.5-1.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 2c330eaa2fca |
| lora/fastdp/qwen2.5-1.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | a5d082cbc927 |
| lora/fastdp/qwen2.5-1.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 51de1583c8f5 |
| lora/fastdp/qwen2.5-1.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | 83344b46d270 |
| lora/fastdp/qwen2.5-1.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | f2519af12a81 |
| lora/fastdp/qwen2.5-1.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | 4517c47d8ec2 |
| lora/fastdp/qwen2.5-1.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 1ee29bcd645c |
| lora/fastdp/qwen2.5-1.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | 4b2e5fb19ee9 |
| lora/fastdp/qwen2.5-1.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | d754cc6a4d44 |
| lora/fastdp/qwen2.5-1.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | 81240ee64978 |
| lora/fastdp/qwen2.5-1.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 5a99f640d620 |
| lora/fastdp/qwen2.5-1.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | 4d4116cf84bf |
| lora/fastdp/qwen2.5-1.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 494165a13696 |
| lora/fastdp/qwen2.5-1.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | b83aa2977e40 |
| lora/fastdp/qwen2.5-1.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 98cab0bac080 |
| lora/fastdp/qwen2.5-1.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | a861c7c892e4 |
| lora/fastdp/qwen2.5-1.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | d4f2fe63a815 |
| lora/fastdp/smollm-1.7b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | 2ebb1dfd8f3a |
| lora/fastdp/smollm-1.7b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 0d5ce4bb37b1 |
| lora/fastdp/smollm-1.7b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | 1650d30149d6 |
| lora/fastdp/smollm-1.7b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | c1d8ddf0fa9d |
| lora/fastdp/smollm-1.7b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | ad5331ecf0da |
| lora/fastdp/smollm-1.7b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 983adb980684 |
| lora/fastdp/smollm-1.7b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | dc0a4fb7ed6b |
| lora/fastdp/smollm-1.7b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 9ed4c7740273 |
| lora/fastdp/smollm-1.7b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | c336a2ce6dcb |
| lora/fastdp/smollm-1.7b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 04488d053519 |
| lora/fastdp/smollm-1.7b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | 7ee173de0a90 |
| lora/fastdp/smollm-1.7b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | c178af5b634d |
| lora/fastdp/smollm-1.7b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | 3a34da40b5d2 |
| lora/fastdp/smollm-1.7b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 6e7a42bbcb05 |
| lora/fastdp/smollm-1.7b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | bf1d87ac1d85 |
| lora/fastdp/smollm-1.7b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 78b05d29edeb |
| lora/fastdp/smollm-1.7b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | fd244c49548c |
| lora/fastdp/smollm-1.7b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 7cd01167ddc8 |
| lora/fastdp/smollm-1.7b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | 2228bb14f72e |
| lora/fastdp/smollm-1.7b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | c4c6e775cfb3 |
| lora/fastdp/smollm-1.7b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | dea1857dafa3 |
| lora/fastdp/smollm-1.7b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 618dcf830252 |
| lora/fastdp/smollm-1.7b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | 5724b9a0ad67 |
| lora/fastdp/smollm-1.7b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 35c9d0030b9a |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/adapter_model.safetensors | Weights | 45.1 MB | 4af93f84b099 |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 45.1 MB | 4af93f84b099 |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1038/optimizer.pt | Weights | 90.4 MB | 3e59ae324c2a |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | df582693e9f5 |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 35f888de7a93 |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 5fbabc49040e |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 45.1 MB | 0a5682124e04 |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1557/optimizer.pt | Weights | 90.4 MB | f17ce74fcf68 |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 49084a834931 |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | 92f82ed2a404 |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | 5fbabc49040e |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | 5fbabc49040e |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/adapter_model.safetensors | Weights | 45.1 MB | a7d689f5c1b4 |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1730/adapter_model.safetensors | Weights | 45.1 MB | a7d689f5c1b4 |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1730/optimizer.pt | Weights | 90.4 MB | 5454b0720d74 |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1730/rng_state.pth | Weights | 14.6 KB | 4dc72868f8d2 |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1730/scheduler.pt | Weights | 1.5 KB | 9b528c414cbd |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1730/training_args.bin | Weights | 5.7 KB | c67aca56d923 |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1734/adapter_model.safetensors | Weights | 45.1 MB | 5f8af6b53bec |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1734/optimizer.pt | Weights | 90.4 MB | 3279a33f52c5 |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1734/rng_state.pth | Weights | 14.6 KB | 7c7548e5e343 |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1734/scheduler.pt | Weights | 1.5 KB | f86c1fb05bc7 |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1734/training_args.bin | Weights | 5.7 KB | c67aca56d923 |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/training_args.bin | Weights | 5.7 KB | c67aca56d923 |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/adapter_model.safetensors | Weights | 45.1 MB | 631e6d058e6c |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 45.1 MB | 631e6d058e6c |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1038/optimizer.pt | Weights | 90.4 MB | cf189bf35d90 |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | df582693e9f5 |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 18eebf06b5a7 |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 325f75fa98b1 |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 45.1 MB | f66c153689ea |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1557/optimizer.pt | Weights | 90.4 MB | 555f37fe89fb |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 49084a834931 |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | 4fad5b216a5f |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | 325f75fa98b1 |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/training_args.bin | Weights | 5.7 KB | 325f75fa98b1 |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/adapter_model.safetensors | Weights | 11.3 MB | a4f10ae639ef |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 11.3 MB | a4f10ae639ef |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1038/optimizer.pt | Weights | 22.7 MB | 1a0da69287ea |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | df582693e9f5 |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 35f888de7a93 |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 457f46b4cbc3 |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 11.3 MB | ce7af2b7e86e |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1557/optimizer.pt | Weights | 22.7 MB | 6aa8b730e684 |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 49084a834931 |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | 92f82ed2a404 |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | 457f46b4cbc3 |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | 457f46b4cbc3 |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/adapter_model.safetensors | Weights | 11.3 MB | 0a59139936db |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/adapter_model.safetensors | Weights | 11.3 MB | 0a59139936db |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/optimizer.pt | Weights | 22.7 MB | 7a5f906c05e7 |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/rng_state.pth | Weights | 14.6 KB | 4dc72868f8d2 |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/scheduler.pt | Weights | 1.5 KB | 9b528c414cbd |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/training_args.bin | Weights | 5.7 KB | b5d69d7f2503 |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/adapter_model.safetensors | Weights | 11.3 MB | afac44c00b0e |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/optimizer.pt | Weights | 22.7 MB | 7d366d904798 |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/rng_state.pth | Weights | 14.6 KB | 7c7548e5e343 |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/scheduler.pt | Weights | 1.5 KB | f86c1fb05bc7 |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/training_args.bin | Weights | 5.7 KB | b5d69d7f2503 |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/training_args.bin | Weights | 5.7 KB | b5d69d7f2503 |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/adapter_model.safetensors | Weights | 11.3 MB | b9f22b406e82 |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 11.3 MB | b9f22b406e82 |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1038/optimizer.pt | Weights | 22.7 MB | dcf1af15b14b |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | df582693e9f5 |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 18eebf06b5a7 |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 6b201d10cbd3 |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 11.3 MB | 85fa5cbc766a |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1557/optimizer.pt | Weights | 22.7 MB | a9d0eac2ffae |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 49084a834931 |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | 4fad5b216a5f |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | 6b201d10cbd3 |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/training_args.bin | Weights | 5.7 KB | 6b201d10cbd3 |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/adapter_model.safetensors | Weights | 180.4 MB | a62ec4e73d7d |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 180.4 MB | a62ec4e73d7d |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1038/optimizer.pt | Weights | 360.9 MB | 54409068d65a |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | df582693e9f5 |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 35f888de7a93 |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | f7271680f0d0 |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 180.4 MB | b3cb7c3d9492 |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1557/optimizer.pt | Weights | 360.9 MB | 9c553809af9d |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 49084a834931 |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | 92f82ed2a404 |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | f7271680f0d0 |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | f7271680f0d0 |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/adapter_model.safetensors | Weights | 180.4 MB | a44466dbca56 |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 180.4 MB | a44466dbca56 |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1038/optimizer.pt | Weights | 360.9 MB | 5f12dbe1774a |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | df582693e9f5 |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 586b296eac29 |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 8acb6ea85bd7 |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 180.4 MB | 5ab196f2681b |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1557/optimizer.pt | Weights | 360.9 MB | 3d546a16fcab |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 49084a834931 |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | df6594421845 |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | 8acb6ea85bd7 |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/training_args.bin | Weights | 5.7 KB | 8acb6ea85bd7 |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/adapter_model.safetensors | Weights | 180.4 MB | 0b5a3ef76e43 |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 180.4 MB | 0b5a3ef76e43 |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1038/optimizer.pt | Weights | 360.9 MB | 32cd69517817 |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | df582693e9f5 |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 18eebf06b5a7 |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 32f63dcde98d |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 180.4 MB | 3d953b384f84 |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1557/optimizer.pt | Weights | 360.9 MB | 973bab2dbeee |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 49084a834931 |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | 4fad5b216a5f |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | 32f63dcde98d |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/training_args.bin | Weights | 5.7 KB | 32f63dcde98d |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 180.4 MB | 592a1edd9384 |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 1be561014184 |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/adapter_model.safetensors | Weights | 97.3 MB | 028bbafb6686 |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 97.3 MB | 028bbafb6686 |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1038/optimizer.pt | Weights | 194.8 MB | cf345d68c6ca |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | c9600caae10b |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 35f888de7a93 |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 165dce8e5ef7 |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 97.3 MB | 9b4613755a6b |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1557/optimizer.pt | Weights | 194.8 MB | d262ca201754 |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | db9b087f1a12 |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | 92f82ed2a404 |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | 165dce8e5ef7 |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | 165dce8e5ef7 |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/adapter_model.safetensors | Weights | 97.3 MB | 2bb4011280a2 |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 97.3 MB | 2bb4011280a2 |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1038/optimizer.pt | Weights | 194.8 MB | d84017b9e1ba |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | c9600caae10b |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 586b296eac29 |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 5593763aa5dc |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 97.3 MB | c725326f2842 |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1557/optimizer.pt | Weights | 194.8 MB | 91d2d516c425 |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | db9b087f1a12 |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | df6594421845 |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | 5593763aa5dc |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/training_args.bin | Weights | 5.7 KB | 5593763aa5dc |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/adapter_model.safetensors | Weights | 97.3 MB | 586393a9f9dc |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 97.3 MB | 692a3503b4a9 |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-1038/optimizer.pt | Weights | 194.8 MB | b6d259037b5e |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | c9600caae10b |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 18eebf06b5a7 |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | ff886c25999a |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-519/adapter_model.safetensors | Weights | 97.3 MB | 586393a9f9dc |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-519/optimizer.pt | Weights | 194.8 MB | 2e1956717c57 |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-519/rng_state.pth | Weights | 14.6 KB | 247757a21a30 |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-519/scheduler.pt | Weights | 1.5 KB | 5da2569f055f |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-519/training_args.bin | Weights | 5.7 KB | ff886c25999a |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/training_args.bin | Weights | 5.7 KB | ff886c25999a |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 97.3 MB | 8c1e08ab2216 |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | bd79784131a4 |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/adapter_model.safetensors | Weights | 24.4 MB | 3500f3470ece |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 24.4 MB | 04bee97a961b |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1038/optimizer.pt | Weights | 49.0 MB | 48e99da7713e |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | c9600caae10b |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 35f888de7a93 |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 059424ed65f8 |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-519/adapter_model.safetensors | Weights | 24.4 MB | 3500f3470ece |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-519/optimizer.pt | Weights | 49.0 MB | 8d2cf0ed176b |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-519/rng_state.pth | Weights | 14.6 KB | 247757a21a30 |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-519/scheduler.pt | Weights | 1.5 KB | 88b92ec6d906 |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-519/training_args.bin | Weights | 5.7 KB | 059424ed65f8 |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | 059424ed65f8 |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/adapter_model.safetensors | Weights | 24.4 MB | ea7500bcaafd |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1730/adapter_model.safetensors | Weights | 24.4 MB | ea7500bcaafd |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1730/optimizer.pt | Weights | 49.0 MB | 9f4ea08030fa |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1730/rng_state.pth | Weights | 14.6 KB | 96dc7cbb57c6 |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1730/scheduler.pt | Weights | 1.5 KB | 9b528c414cbd |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1730/training_args.bin | Weights | 5.7 KB | 54b569a8850a |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1734/adapter_model.safetensors | Weights | 24.4 MB | 7f41923f708a |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1734/optimizer.pt | Weights | 49.0 MB | 03c4313a4e61 |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1734/rng_state.pth | Weights | 14.6 KB | a5adf31f82ec |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1734/scheduler.pt | Weights | 1.5 KB | f86c1fb05bc7 |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1734/training_args.bin | Weights | 5.7 KB | 54b569a8850a |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/training_args.bin | Weights | 5.7 KB | 54b569a8850a |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/adapter_model.safetensors | Weights | 24.4 MB | 0987d6ea4198 |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 24.4 MB | 0987d6ea4198 |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1038/optimizer.pt | Weights | 49.0 MB | 357fa26601a8 |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | c9600caae10b |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 18eebf06b5a7 |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | f96a877fd55c |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 24.4 MB | 370d38173121 |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1557/optimizer.pt | Weights | 49.0 MB | 527dfe1cd9d9 |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | db9b087f1a12 |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | 4fad5b216a5f |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | f96a877fd55c |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/training_args.bin | Weights | 5.7 KB | f96a877fd55c |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/adapter_model.safetensors | Weights | 389.1 MB | 3aa1b0f6899a |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-173/adapter_model.safetensors | Weights | 389.1 MB | 3aa1b0f6899a |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-173/optimizer.pt | Weights | 778.4 MB | 882c75bb68b7 |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-173/rng_state.pth | Weights | 14.6 KB | 6f60b1d11783 |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-173/scheduler.pt | Weights | 1.4 KB | 11f7e18638fd |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-173/training_args.bin | Weights | 5.7 KB | d697cf17f0c3 |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-692/adapter_model.safetensors | Weights | 389.1 MB | 7500f798d57e |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-692/optimizer.pt | Weights | 778.4 MB | e929f3013667 |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-692/rng_state.pth | Weights | 14.6 KB | 94cbd1d0d646 |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-692/scheduler.pt | Weights | 1.5 KB | 9441e9faaf23 |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-692/training_args.bin | Weights | 5.7 KB | d697cf17f0c3 |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | d697cf17f0c3 |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/adapter_model.safetensors | Weights | 389.1 MB | fb422ee927e7 |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 389.1 MB | fb422ee927e7 |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1038/optimizer.pt | Weights | 778.4 MB | c12d228fd078 |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | c9600caae10b |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 586b296eac29 |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | d088fe5421a7 |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 389.1 MB | d7f291177c3f |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1557/optimizer.pt | Weights | 778.4 MB | ae230695fe9c |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | db9b087f1a12 |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | df6594421845 |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | d088fe5421a7 |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/training_args.bin | Weights | 5.7 KB | d088fe5421a7 |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/adapter_model.safetensors | Weights | 389.1 MB | a22f488cbe37 |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 389.1 MB | d8520f51e516 |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-1038/optimizer.pt | Weights | 778.4 MB | 23e63734a915 |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | c9600caae10b |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 18eebf06b5a7 |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 52ab759b347f |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-519/adapter_model.safetensors | Weights | 389.1 MB | a22f488cbe37 |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-519/optimizer.pt | Weights | 778.4 MB | 74bceb09cd36 |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-519/rng_state.pth | Weights | 14.6 KB | 247757a21a30 |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-519/scheduler.pt | Weights | 1.5 KB | 5da2569f055f |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-519/training_args.bin | Weights | 5.7 KB | 52ab759b347f |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/training_args.bin | Weights | 5.7 KB | 52ab759b347f |
| lora/nodp/qwen2.5-0.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 140.8 MB | a4e010f005f8 |
| lora/nodp/qwen2.5-0.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 6bbe766bd346 |
| lora/nodp/qwen2.5-1.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 295.5 MB | 041800252f3b |
| lora/nodp/qwen2.5-1.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | a83b2d9501c3 |
| lora/nodp/smollm-1.7b_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 289.5 MB | c2502d638185 |
| lora/nodp/smollm-1.7b_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 392425e873da |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/adapter_model.safetensors | Weights | 97.3 MB | 752eaf23c8ea |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/checkpoint-173/adapter_model.safetensors | Weights | 48.7 MB | 7f7af6eaa526 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/checkpoint-173/optimizer.pt | Weights | 97.6 MB | 8d435fe617aa |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/checkpoint-173/rng_state.pth | Weights | 14.6 KB | dedaa0d0b472 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/checkpoint-173/scheduler.pt | Weights | 1.4 KB | 11f7e18638fd |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/checkpoint-173/training_args.bin | Weights | 5.7 KB | 496f2ee9efed |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/checkpoint-692/adapter_model.safetensors | Weights | 48.7 MB | c7e6c5cf5274 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/checkpoint-692/optimizer.pt | Weights | 97.6 MB | cdc54bb7de10 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/checkpoint-692/rng_state.pth | Weights | 14.6 KB | fa5f43044ac4 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/checkpoint-692/scheduler.pt | Weights | 1.5 KB | 9441e9faaf23 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/checkpoint-692/training_args.bin | Weights | 5.7 KB | 496f2ee9efed |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | 496f2ee9efed |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/adapter_model.safetensors | Weights | 97.3 MB | caebb0b827ca |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/checkpoint-173/adapter_model.safetensors | Weights | 48.7 MB | 98cabf97474e |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/checkpoint-173/optimizer.pt | Weights | 97.6 MB | 276ea57ddf72 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/checkpoint-173/rng_state.pth | Weights | 14.6 KB | dedaa0d0b472 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/checkpoint-173/scheduler.pt | Weights | 1.4 KB | 11f7e18638fd |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/checkpoint-173/training_args.bin | Weights | 5.7 KB | 229b19b0b084 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/checkpoint-692/adapter_model.safetensors | Weights | 48.7 MB | 470769af79d0 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/checkpoint-692/optimizer.pt | Weights | 97.6 MB | 90743e7e5505 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/checkpoint-692/rng_state.pth | Weights | 14.6 KB | fa5f43044ac4 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/checkpoint-692/scheduler.pt | Weights | 1.5 KB | 9441e9faaf23 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/checkpoint-692/training_args.bin | Weights | 5.7 KB | 229b19b0b084 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | 229b19b0b084 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/adapter_model.safetensors | Weights | 97.3 MB | 28f7caccc5da |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/checkpoint-173/adapter_model.safetensors | Weights | 48.7 MB | 22c49eae8f74 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/checkpoint-173/optimizer.pt | Weights | 97.6 MB | 47e0e36f1157 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/checkpoint-173/rng_state.pth | Weights | 14.6 KB | dedaa0d0b472 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/checkpoint-173/scheduler.pt | Weights | 1.4 KB | 11f7e18638fd |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/checkpoint-173/training_args.bin | Weights | 5.7 KB | e4d605d215e1 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/checkpoint-692/adapter_model.safetensors | Weights | 48.7 MB | 136559050518 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/checkpoint-692/optimizer.pt | Weights | 97.6 MB | 180126b7a711 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/checkpoint-692/rng_state.pth | Weights | 14.6 KB | fa5f43044ac4 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/checkpoint-692/scheduler.pt | Weights | 1.5 KB | 9441e9faaf23 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/checkpoint-692/training_args.bin | Weights | 5.7 KB | e4d605d215e1 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | e4d605d215e1 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/adapter_model.safetensors | Weights | 97.3 MB | 958fe40d913c |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/checkpoint-173/adapter_model.safetensors | Weights | 48.7 MB | ce75ef04ff16 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/checkpoint-173/optimizer.pt | Weights | 97.6 MB | fe0bc4291d71 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/checkpoint-173/rng_state.pth | Weights | 14.6 KB | dedaa0d0b472 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/checkpoint-173/scheduler.pt | Weights | 1.4 KB | 11f7e18638fd |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/checkpoint-173/training_args.bin | Weights | 5.7 KB | ee879eeb03cf |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/checkpoint-692/adapter_model.safetensors | Weights | 48.7 MB | f63996b150f0 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/checkpoint-692/optimizer.pt | Weights | 97.6 MB | f8b832261475 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/checkpoint-692/rng_state.pth | Weights | 14.6 KB | fa5f43044ac4 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/checkpoint-692/scheduler.pt | Weights | 1.5 KB | 9441e9faaf23 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/checkpoint-692/training_args.bin | Weights | 5.7 KB | ee879eeb03cf |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | ee879eeb03cf |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/adapter_model.safetensors | Weights | 97.3 MB | 60b6b9968173 |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/checkpoint-173/adapter_model.safetensors | Weights | 48.7 MB | 227c6cd7d750 |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/checkpoint-173/optimizer.pt | Weights | 97.6 MB | f29b096d8e80 |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/checkpoint-173/rng_state.pth | Weights | 14.6 KB | dedaa0d0b472 |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/checkpoint-173/scheduler.pt | Weights | 1.4 KB | 11f7e18638fd |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/checkpoint-173/training_args.bin | Weights | 5.7 KB | 1543be3ab238 |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/checkpoint-692/adapter_model.safetensors | Weights | 48.7 MB | 85303d6b091e |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/checkpoint-692/optimizer.pt | Weights | 97.6 MB | 16bcf8a6779f |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/checkpoint-692/rng_state.pth | Weights | 14.6 KB | fa5f43044ac4 |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/checkpoint-692/scheduler.pt | Weights | 1.5 KB | 9441e9faaf23 |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/checkpoint-692/training_args.bin | Weights | 5.7 KB | 1543be3ab238 |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | 1543be3ab238 |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/adapter_model.safetensors | Weights | 11.3 MB | b0217e80cc10 |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 5.7 MB | 0a47375debda |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1557/optimizer.pt | Weights | 11.5 MB | 1be7b3386fe5 |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 82688b2d2486 |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | df6594421845 |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | 8fde522ae2bf |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/adapter_model.safetensors | Weights | 5.7 MB | 0e5a3bb9f1bd |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/optimizer.pt | Weights | 11.5 MB | 15ae4bc97dfd |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/rng_state.pth | Weights | 14.6 KB | 882674f40fc9 |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/scheduler.pt | Weights | 1.5 KB | f86c1fb05bc7 |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/training_args.bin | Weights | 5.7 KB | 8fde522ae2bf |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/training_args.bin | Weights | 5.7 KB | 8fde522ae2bf |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/adapter_model.safetensors | Weights | 180.4 MB | 0839fd74b9b4 |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-173/adapter_model.safetensors | Weights | 90.2 MB | 4b15c5d0cbe1 |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-173/optimizer.pt | Weights | 180.5 MB | c194ff576531 |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-173/rng_state.pth | Weights | 14.6 KB | 6c56778bbd09 |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-173/scheduler.pt | Weights | 1.4 KB | be6fd9c20c17 |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-173/training_args.bin | Weights | 5.7 KB | f8856c72a6c8 |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-692/adapter_model.safetensors | Weights | 90.2 MB | b398af9d4ca9 |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-692/optimizer.pt | Weights | 180.5 MB | 5d019da731ba |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-692/rng_state.pth | Weights | 14.6 KB | 2a2baff5f9dd |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-692/scheduler.pt | Weights | 1.5 KB | d1fd62670aa1 |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-692/training_args.bin | Weights | 5.7 KB | f8856c72a6c8 |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/training_args.bin | Weights | 5.7 KB | f8856c72a6c8 |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/adapter_model.safetensors | Weights | 97.3 MB | 9bc23efece0b |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-173/adapter_model.safetensors | Weights | 48.7 MB | af892421d9e5 |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-173/optimizer.pt | Weights | 97.6 MB | 872fe73dabf8 |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-173/rng_state.pth | Weights | 14.6 KB | dedaa0d0b472 |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-173/scheduler.pt | Weights | 1.4 KB | 11f7e18638fd |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-173/training_args.bin | Weights | 5.7 KB | a0a7a80e00c4 |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-692/adapter_model.safetensors | Weights | 48.7 MB | 7750d7200040 |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-692/optimizer.pt | Weights | 97.6 MB | d1314c49eff2 |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-692/rng_state.pth | Weights | 14.6 KB | fa5f43044ac4 |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-692/scheduler.pt | Weights | 1.5 KB | 9441e9faaf23 |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-692/training_args.bin | Weights | 5.7 KB | a0a7a80e00c4 |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | a0a7a80e00c4 |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/adapter_model.safetensors | Weights | 24.4 MB | 3c2c0c1c97e9 |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1730/adapter_model.safetensors | Weights | 12.2 MB | 21283c5caedf |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1730/optimizer.pt | Weights | 24.6 MB | 6c866ec26118 |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1730/rng_state.pth | Weights | 14.6 KB | ed4cdd620832 |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1730/scheduler.pt | Weights | 1.5 KB | d16a4d18e324 |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1730/training_args.bin | Weights | 5.7 KB | fd1cc4bcfe8c |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1734/adapter_model.safetensors | Weights | 12.2 MB | 95ec2b72ebf1 |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1734/optimizer.pt | Weights | 24.6 MB | 77f32e9cc262 |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1734/rng_state.pth | Weights | 14.6 KB | b803b92aca96 |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1734/scheduler.pt | Weights | 1.5 KB | 4aca76f744a1 |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1734/training_args.bin | Weights | 5.7 KB | fd1cc4bcfe8c |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | fd1cc4bcfe8c |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/adapter_model.safetensors | Weights | 389.1 MB | 11357c051250 |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-173/adapter_model.safetensors | Weights | 194.6 MB | 835786148c01 |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-173/optimizer.pt | Weights | 389.4 MB | ae0d416a0fd0 |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-173/rng_state.pth | Weights | 14.6 KB | dedaa0d0b472 |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-173/scheduler.pt | Weights | 1.4 KB | 11f7e18638fd |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-173/training_args.bin | Weights | 5.7 KB | 2b936a1533d2 |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-692/adapter_model.safetensors | Weights | 194.6 MB | eb47a9d1489a |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-692/optimizer.pt | Weights | 389.4 MB | b72fd3f3981e |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-692/rng_state.pth | Weights | 14.6 KB | fa5f43044ac4 |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-692/scheduler.pt | Weights | 1.5 KB | 9441e9faaf23 |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-692/training_args.bin | Weights | 5.7 KB | 2b936a1533d2 |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | 2b936a1533d2 |
| qlora/fastdp/llama-3.2-3b_eps0.1_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 48.7 MB | e910e97d1f79 |
| qlora/fastdp/llama-3.2-3b_eps0.1_r16_a32_lr1e-3_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | bb0fc34070bb |
| qlora/fastdp/llama-3.2-3b_eps0.5_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 48.7 MB | a23e9610573f |
| qlora/fastdp/llama-3.2-3b_eps0.5_r16_a32_lr1e-3_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | d0aaf633e2cd |
| qlora/fastdp/llama-3.2-3b_eps1.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 48.7 MB | f437bbf8eb02 |
| qlora/fastdp/llama-3.2-3b_eps1.0_r16_a32_lr1e-3_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 77965841664d |
| qlora/fastdp/llama-3.2-3b_eps100.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 48.7 MB | e6134eeb9fb4 |
| qlora/fastdp/llama-3.2-3b_eps100.0_r16_a32_lr1e-3_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 95cf40078719 |
| qlora/fastdp/llama-3.2-3b_eps1000.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 48.7 MB | 04065c0cf6d3 |
| qlora/fastdp/llama-3.2-3b_eps1000.0_r16_a32_lr1e-3_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 902ebdf8f77d |
| qlora/fastdp/llama-3.2-3b_eps16.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 48.7 MB | 6df1b47586ec |
| qlora/fastdp/llama-3.2-3b_eps16.0_r16_a32_lr1e-3_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 98b1967ba188 |
| qlora/fastdp/llama-3.2-3b_eps2.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 48.7 MB | ca86ba58415a |
| qlora/fastdp/llama-3.2-3b_eps2.0_r16_a32_lr1e-3_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | f4748cd1ec64 |
| qlora/fastdp/llama-3.2-3b_eps32.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 48.7 MB | ec29635cd122 |
| qlora/fastdp/llama-3.2-3b_eps32.0_r16_a32_lr1e-3_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 18ec103caa83 |
| qlora/fastdp/llama-3.2-3b_eps4.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 48.7 MB | 5aecb1f7389a |
| qlora/fastdp/llama-3.2-3b_eps4.0_r16_a32_lr1e-3_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | afdf4f8b108c |
| qlora/fastdp/llama-3.2-3b_eps500.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 48.7 MB | 3df3212f1456 |
| qlora/fastdp/llama-3.2-3b_eps500.0_r16_a32_lr1e-3_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 571fb935a369 |
| qlora/fastdp/llama-3.2-3b_eps64.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 48.7 MB | d2a484c7cb9a |
| qlora/fastdp/llama-3.2-3b_eps64.0_r16_a32_lr1e-3_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | b12361a0f191 |
| qlora/fastdp/llama-3.2-3b_eps8.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 48.7 MB | 1a78e494741d |
| qlora/fastdp/llama-3.2-3b_eps8.0_r16_a32_lr1e-3_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 0430b2e89333 |
| qlora/fastdp/qwen2.5-0.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | f7b9987f8cc4 |
| qlora/fastdp/qwen2.5-0.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | aba1d2e821a3 |
| qlora/fastdp/qwen2.5-0.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | c59ce3bc4682 |
| qlora/fastdp/qwen2.5-0.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 308727ce82fe |
| qlora/fastdp/qwen2.5-0.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | 5082b1973afd |
| qlora/fastdp/qwen2.5-0.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 62a5fda79ff1 |
| qlora/fastdp/qwen2.5-0.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | b76116331ea1 |
| qlora/fastdp/qwen2.5-0.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 215a5323b56c |
| qlora/fastdp/qwen2.5-0.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | 2e380d4d7838 |
| qlora/fastdp/qwen2.5-0.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 1544d9365c36 |
| qlora/fastdp/qwen2.5-0.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | 3d4bf4f7abda |
| qlora/fastdp/qwen2.5-0.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 8f9015fee1cb |
| qlora/fastdp/qwen2.5-0.5b_eps16000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | a4a0fd9fe843 |
| qlora/fastdp/qwen2.5-0.5b_eps16000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 8ea6b5539ab1 |
| qlora/fastdp/qwen2.5-0.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | 044e159a7d55 |
| qlora/fastdp/qwen2.5-0.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 494bdbdcf1b3 |
| qlora/fastdp/qwen2.5-0.5b_eps2000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | a0f37fbb8b7f |
| qlora/fastdp/qwen2.5-0.5b_eps2000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 31dcf2517efd |
| qlora/fastdp/qwen2.5-0.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | 416923218b67 |
| qlora/fastdp/qwen2.5-0.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | adbe6bf5ab4e |
| qlora/fastdp/qwen2.5-0.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | 6b8df14d6beb |
| qlora/fastdp/qwen2.5-0.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | f668fdb57e8b |
| qlora/fastdp/qwen2.5-0.5b_eps4000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | f3857aae1f33 |
| qlora/fastdp/qwen2.5-0.5b_eps4000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 9a49f5925f36 |
| qlora/fastdp/qwen2.5-0.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | 4cac452b9b62 |
| qlora/fastdp/qwen2.5-0.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | a9cd98a8479e |
| qlora/fastdp/qwen2.5-0.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | 7a0731842b7d |
| qlora/fastdp/qwen2.5-0.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 6635d801b1b3 |
| qlora/fastdp/qwen2.5-0.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | 8b5546e5b7d5 |
| qlora/fastdp/qwen2.5-0.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 094e27a65271 |
| qlora/fastdp/qwen2.5-0.5b_eps8000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | 972db7a329cc |
| qlora/fastdp/qwen2.5-0.5b_eps8000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 48a9a2b4d88b |
| qlora/fastdp/qwen2.5-1.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | f3d217e9a354 |
| qlora/fastdp/qwen2.5-1.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 2e844b86fe33 |
| qlora/fastdp/qwen2.5-1.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | 6de96a9f2982 |
| qlora/fastdp/qwen2.5-1.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 8e1a86854a38 |
| qlora/fastdp/qwen2.5-1.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | e5a1e38febaa |
| qlora/fastdp/qwen2.5-1.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 0c2575a76336 |
| qlora/fastdp/qwen2.5-1.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | 28a67bbb6f1c |
| qlora/fastdp/qwen2.5-1.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 8cdd21699796 |
| qlora/fastdp/qwen2.5-1.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | f4f9f511accc |
| qlora/fastdp/qwen2.5-1.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 70af7e1efad9 |
| qlora/fastdp/qwen2.5-1.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | 3ee7fc4f1b58 |
| qlora/fastdp/qwen2.5-1.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 1d2f56bf75a3 |
| qlora/fastdp/qwen2.5-1.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | bea16af59f30 |
| qlora/fastdp/qwen2.5-1.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | d7fa1d9cdc02 |
| qlora/fastdp/qwen2.5-1.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | fd32cd40e9ee |
| qlora/fastdp/qwen2.5-1.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 78ec6be29e01 |
| qlora/fastdp/qwen2.5-1.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | 03ddf7e50e9a |
| qlora/fastdp/qwen2.5-1.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 5d19d4355c20 |
| qlora/fastdp/qwen2.5-1.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | 5f0f613b4b23 |
| qlora/fastdp/qwen2.5-1.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 67977e0fe04e |
| qlora/fastdp/qwen2.5-1.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | 04f3229b7b97 |
| qlora/fastdp/qwen2.5-1.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 6df1eec7be2e |
| qlora/fastdp/qwen2.5-1.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | f08fcee53d68 |
| qlora/fastdp/qwen2.5-1.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 76cccf1de8dc |
| qlora/fastdp/smollm-1.7b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | bb42b2ceec47 |
| qlora/fastdp/smollm-1.7b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 3c75afda660d |
| qlora/fastdp/smollm-1.7b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | d0cadcc6a562 |
| qlora/fastdp/smollm-1.7b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 08f3218a5b29 |
| qlora/fastdp/smollm-1.7b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | 8546b20a2ddf |
| qlora/fastdp/smollm-1.7b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 9778501970c5 |
| qlora/fastdp/smollm-1.7b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | 8862e37bc57e |
| qlora/fastdp/smollm-1.7b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 9801b42c53bf |
| qlora/fastdp/smollm-1.7b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | bc1dd8b2adbe |
| qlora/fastdp/smollm-1.7b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 018add67de5f |
| qlora/fastdp/smollm-1.7b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | 7507ee41d27d |
| qlora/fastdp/smollm-1.7b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 0826fd785cff |
| qlora/fastdp/smollm-1.7b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | da1f4393fa3f |
| qlora/fastdp/smollm-1.7b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | c6de17169902 |
| qlora/fastdp/smollm-1.7b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | 9f7e298e24e3 |
| qlora/fastdp/smollm-1.7b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 58223090dc9f |
| qlora/fastdp/smollm-1.7b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | b9eef0bea55f |
| qlora/fastdp/smollm-1.7b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | f72211cfad49 |
| qlora/fastdp/smollm-1.7b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | 665b7e07fd67 |
| qlora/fastdp/smollm-1.7b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | ba469f53051a |
| qlora/fastdp/smollm-1.7b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | 0c530c83e9a1 |
| qlora/fastdp/smollm-1.7b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 5b95b3d42d99 |
| qlora/fastdp/smollm-1.7b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | 6c8d5c4ff492 |
| qlora/fastdp/smollm-1.7b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | c54df3e1d10b |
| qlora/fastdp/stablelm-2-1.6b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 121.2 MB | 9fb2322ce841 |
| qlora/fastdp/stablelm-2-1.6b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 98894ce5d8b8 |
| qlora/fastdp/stablelm-2-1.6b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 121.2 MB | f6f0ce3c118c |
| qlora/fastdp/stablelm-2-1.6b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 17aded85fbdc |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/adapter_model.safetensors | Weights | 45.1 MB | ff71d5229136 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 22.6 MB | 2bc8f1c6ebfd |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1038/optimizer.pt | Weights | 45.3 MB | 478e75b60822 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | 8bf263f068b2 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 35f888de7a93 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 67449235caf2 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 22.6 MB | c92c5207ee48 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1557/optimizer.pt | Weights | 45.3 MB | c3a0e1090dbf |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 3216af4d0ba7 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | 92f82ed2a404 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | 67449235caf2 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | 67449235caf2 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/adapter_model.safetensors | Weights | 45.1 MB | df472adc591d |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1730/adapter_model.safetensors | Weights | 22.6 MB | da1c7aab2c21 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1730/optimizer.pt | Weights | 45.3 MB | 2bee8e959ca9 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1730/rng_state.pth | Weights | 14.6 KB | 2d74ce1538c0 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1730/scheduler.pt | Weights | 1.5 KB | 9b528c414cbd |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1730/training_args.bin | Weights | 5.7 KB | 3b1cf56bfb3c |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1734/adapter_model.safetensors | Weights | 22.6 MB | 27e4af0c5904 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1734/optimizer.pt | Weights | 45.3 MB | 6f7e1aaa876f |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1734/rng_state.pth | Weights | 14.6 KB | b2cc68be781d |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1734/scheduler.pt | Weights | 1.5 KB | f86c1fb05bc7 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1734/training_args.bin | Weights | 5.7 KB | 3b1cf56bfb3c |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/training_args.bin | Weights | 5.7 KB | 3b1cf56bfb3c |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/adapter_model.safetensors | Weights | 45.1 MB | 5ccb7cfe6774 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 22.6 MB | 7c518ae7ded3 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1038/optimizer.pt | Weights | 45.3 MB | 6e6fbab39d1e |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | 8bf263f068b2 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 18eebf06b5a7 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 20b7b691d262 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 22.6 MB | bd13ed8b034e |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1557/optimizer.pt | Weights | 45.3 MB | dc485a2b225e |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 3216af4d0ba7 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | 4fad5b216a5f |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | 20b7b691d262 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/training_args.bin | Weights | 5.7 KB | 20b7b691d262 |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/adapter_model.safetensors | Weights | 11.3 MB | dc971af8e2a8 |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 5.7 MB | 58b8809481ab |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1038/optimizer.pt | Weights | 11.5 MB | 7feb1fe95d16 |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | 8bf263f068b2 |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 35f888de7a93 |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 4011f4b4b7fa |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 5.7 MB | 1d77b9ba1de2 |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1557/optimizer.pt | Weights | 11.5 MB | cefa4ec58054 |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 3216af4d0ba7 |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | 92f82ed2a404 |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | 4011f4b4b7fa |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | 4011f4b4b7fa |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/adapter_model.safetensors | Weights | 11.3 MB | 7d35f53667a0 |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/adapter_model.safetensors | Weights | 5.7 MB | 6dbd0cbe2870 |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/optimizer.pt | Weights | 11.5 MB | 018a67a4b876 |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/rng_state.pth | Weights | 14.6 KB | 2d74ce1538c0 |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/scheduler.pt | Weights | 1.5 KB | 9b528c414cbd |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/training_args.bin | Weights | 5.7 KB | 9dd7a911cdfd |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/adapter_model.safetensors | Weights | 5.7 MB | b9382a065fda |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/optimizer.pt | Weights | 11.5 MB | d909e89a1a8a |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/rng_state.pth | Weights | 14.6 KB | b2cc68be781d |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/scheduler.pt | Weights | 1.5 KB | f86c1fb05bc7 |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/training_args.bin | Weights | 5.7 KB | 9dd7a911cdfd |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/training_args.bin | Weights | 5.7 KB | 9dd7a911cdfd |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/adapter_model.safetensors | Weights | 11.3 MB | bfc679778fdb |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 5.7 MB | 8d005257da1c |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1038/optimizer.pt | Weights | 11.5 MB | 914b26eba05e |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | 8bf263f068b2 |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 18eebf06b5a7 |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | b52482b0125b |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 5.7 MB | dcf690fc3939 |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1557/optimizer.pt | Weights | 11.5 MB | cdcba4ce6eea |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 3216af4d0ba7 |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | 4fad5b216a5f |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | b52482b0125b |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/training_args.bin | Weights | 5.7 KB | b52482b0125b |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/adapter_model.safetensors | Weights | 180.4 MB | 085389153a5f |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 90.2 MB | 6b848ecc60fd |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1038/optimizer.pt | Weights | 180.5 MB | a0d4517717d5 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | 8bf263f068b2 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 35f888de7a93 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 1bdd417dd4c0 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 90.2 MB | c4d6f41b28d2 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1557/optimizer.pt | Weights | 180.5 MB | a15a708b9de5 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 3216af4d0ba7 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | 92f82ed2a404 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | 1bdd417dd4c0 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | 1bdd417dd4c0 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/adapter_model.safetensors | Weights | 180.4 MB | 8b9056524d0a |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 90.2 MB | ac29c951ff96 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1038/optimizer.pt | Weights | 180.5 MB | 291173d059ab |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | 8bf263f068b2 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 586b296eac29 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | bb88d3cf47ac |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 90.2 MB | 9621f52c084b |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1557/optimizer.pt | Weights | 180.5 MB | 25899e8ab0cd |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 3216af4d0ba7 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | df6594421845 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | bb88d3cf47ac |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/training_args.bin | Weights | 5.7 KB | bb88d3cf47ac |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/adapter_model.safetensors | Weights | 180.4 MB | 9d6d49d2a00c |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 90.2 MB | 4ab79e415c50 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1038/optimizer.pt | Weights | 180.5 MB | 8409e3281558 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | 8bf263f068b2 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 18eebf06b5a7 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | b5bfa0020609 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 90.2 MB | 345907382bc0 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1557/optimizer.pt | Weights | 180.5 MB | b0f0fa41bef3 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 3216af4d0ba7 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | 4fad5b216a5f |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | b5bfa0020609 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/training_args.bin | Weights | 5.7 KB | b5bfa0020609 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/adapter_model.safetensors | Weights | 97.3 MB | ff13ecb4772f |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 48.7 MB | 1ef0521f946d |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1038/optimizer.pt | Weights | 97.6 MB | 35a1bd2e5284 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | 5178088021a2 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 35f888de7a93 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 674ce89ee693 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 48.7 MB | b9c0a830c2b1 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1557/optimizer.pt | Weights | 97.6 MB | 5452cd3344f2 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 4b726fcaff44 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | 92f82ed2a404 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | 674ce89ee693 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | 674ce89ee693 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 48.7 MB | 71b37d968f99 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 40abfa29dfbe |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/adapter_model.safetensors | Weights | 97.3 MB | 3a149d994d90 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1730/adapter_model.safetensors | Weights | 48.7 MB | 79d30063f16e |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1730/optimizer.pt | Weights | 97.6 MB | eb29be0895a3 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1730/rng_state.pth | Weights | 14.6 KB | 75fe3296e373 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1730/scheduler.pt | Weights | 1.5 KB | 9b528c414cbd |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1730/training_args.bin | Weights | 5.7 KB | 6db670f0ccc1 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1734/adapter_model.safetensors | Weights | 48.7 MB | 944b962c8dc5 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1734/optimizer.pt | Weights | 97.6 MB | f4aeb8e53eb8 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1734/rng_state.pth | Weights | 14.6 KB | 7185567ed70c |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1734/scheduler.pt | Weights | 1.5 KB | f86c1fb05bc7 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1734/training_args.bin | Weights | 5.7 KB | 6db670f0ccc1 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/training_args.bin | Weights | 5.7 KB | 6db670f0ccc1 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/adapter_model.safetensors | Weights | 97.3 MB | a78e920300be |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 48.7 MB | 55563bf2379f |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-1038/optimizer.pt | Weights | 97.6 MB | a83cb6cfdb31 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | 5178088021a2 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 18eebf06b5a7 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 0b6f373d8e2a |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-519/adapter_model.safetensors | Weights | 48.7 MB | e48f6fa541b8 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-519/optimizer.pt | Weights | 97.6 MB | 5395a3011002 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-519/rng_state.pth | Weights | 14.6 KB | 4af52c27f279 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-519/scheduler.pt | Weights | 1.5 KB | 5da2569f055f |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-519/training_args.bin | Weights | 5.7 KB | 0b6f373d8e2a |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/training_args.bin | Weights | 5.7 KB | 0b6f373d8e2a |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/adapter_model.safetensors | Weights | 24.4 MB | 655a58e3fb24 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 12.2 MB | b9a2dd86e19f |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1038/optimizer.pt | Weights | 24.6 MB | ae206c2797d4 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | 5178088021a2 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 35f888de7a93 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | afacfe6e12cf |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 12.2 MB | eedec16a5090 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1557/optimizer.pt | Weights | 24.6 MB | a7313f6beb09 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 4b726fcaff44 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | 92f82ed2a404 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | afacfe6e12cf |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | afacfe6e12cf |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/adapter_model.safetensors | Weights | 24.4 MB | d04fac0719b1 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1730/adapter_model.safetensors | Weights | 12.2 MB | 6b8dee4ca871 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1730/optimizer.pt | Weights | 24.6 MB | 3451783f0833 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1730/rng_state.pth | Weights | 14.6 KB | 75fe3296e373 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1730/scheduler.pt | Weights | 1.5 KB | 9b528c414cbd |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1730/training_args.bin | Weights | 5.7 KB | c8eaf34ce3cf |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1734/adapter_model.safetensors | Weights | 12.2 MB | b3b9116a48a6 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1734/optimizer.pt | Weights | 24.6 MB | 2f54f1a1f2c9 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1734/rng_state.pth | Weights | 14.6 KB | 7185567ed70c |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1734/scheduler.pt | Weights | 1.5 KB | f86c1fb05bc7 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1734/training_args.bin | Weights | 5.7 KB | c8eaf34ce3cf |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/training_args.bin | Weights | 5.7 KB | c8eaf34ce3cf |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/adapter_model.safetensors | Weights | 24.4 MB | 2535e6a90876 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 12.2 MB | 471f4058b975 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1038/optimizer.pt | Weights | 24.6 MB | afc3aa8b3453 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | 5178088021a2 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 18eebf06b5a7 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | f59871abfc7b |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 12.2 MB | 9e956ce5a3e6 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1557/optimizer.pt | Weights | 24.6 MB | 35432c45bdc7 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 4b726fcaff44 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | 4fad5b216a5f |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | f59871abfc7b |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/training_args.bin | Weights | 5.7 KB | f59871abfc7b |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/adapter_model.safetensors | Weights | 389.1 MB | 6124dc4360d6 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 194.6 MB | d365496f2af8 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-1038/optimizer.pt | Weights | 389.4 MB | 7972d12caad0 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | 5178088021a2 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 35f888de7a93 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 1e57d97cc70e |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 194.6 MB | 6a7df0a64404 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-1557/optimizer.pt | Weights | 389.4 MB | f9f9dd6dd506 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 4b726fcaff44 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | 92f82ed2a404 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | 1e57d97cc70e |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/training_args.bin | Weights | 5.7 KB | 1e57d97cc70e |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/adapter_model.safetensors | Weights | 389.1 MB | 6e95c3beb59f |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 194.6 MB | 128419db1a5d |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1038/optimizer.pt | Weights | 389.4 MB | 58d606dd6f43 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | 5178088021a2 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 586b296eac29 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | 400f194af9ec |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1557/adapter_model.safetensors | Weights | 194.6 MB | ea14e3e3c81a |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1557/optimizer.pt | Weights | 389.4 MB | a91116062f31 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1557/rng_state.pth | Weights | 14.6 KB | 4b726fcaff44 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1557/scheduler.pt | Weights | 1.5 KB | df6594421845 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1557/training_args.bin | Weights | 5.7 KB | 400f194af9ec |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/training_args.bin | Weights | 5.7 KB | 400f194af9ec |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/adapter_model.safetensors | Weights | 389.1 MB | 4e2fbe80a950 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-1038/adapter_model.safetensors | Weights | 194.6 MB | 1ba97ce54c94 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-1038/optimizer.pt | Weights | 389.4 MB | 0c49536732d7 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-1038/rng_state.pth | Weights | 14.6 KB | 5178088021a2 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-1038/scheduler.pt | Weights | 1.5 KB | 18eebf06b5a7 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-1038/training_args.bin | Weights | 5.7 KB | b6cd894af503 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-519/adapter_model.safetensors | Weights | 194.6 MB | 3fe0d9754b56 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-519/optimizer.pt | Weights | 389.4 MB | 01ed7b4ef222 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-519/rng_state.pth | Weights | 14.6 KB | 4af52c27f279 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-519/scheduler.pt | Weights | 1.5 KB | 5da2569f055f |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-519/training_args.bin | Weights | 5.7 KB | b6cd894af503 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/training_args.bin | Weights | 5.7 KB | b6cd894af503 |
| qlora/nodp/qwen2.5-0.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 70.4 MB | f82247c5805b |
| qlora/nodp/qwen2.5-0.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 5686f4fe53f2 |
| qlora/nodp/qwen2.5-1.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 147.8 MB | bde027eb57bf |
| qlora/nodp/qwen2.5-1.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 28c55c4d0f8e |
| qlora/nodp/smollm-1.7b_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 144.7 MB | 3627aef7fad9 |
| qlora/nodp/smollm-1.7b_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 41b1b36a958e |
| qlora/nodp/stablelm-2-1.6b_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_model.safetensors | Weights | 121.2 MB | 05d96471b223 |
| qlora/nodp/stablelm-2-1.6b_r64_a128_lr5e-4_ep3_bs8_seq4096/training_args.bin | Weights | 5.7 KB | 8785e22d3419 |
| Llama-3.2-1B_full_fastdp/config.json | Configuration | 863 B | — |
| Llama-3.2-1B_full_fastdp/generation_config.json | Configuration | 215 B | — |
| Llama-3.2-1B_full_lr0.001_e3/config.json | Configuration | 863 B | — |
| Llama-3.2-1B_full_lr0.001_e3/generation_config.json | Configuration | 215 B | — |
| Llama-3.2-1B_full_lr0.001_e3/hyperparameters.json | Configuration | 476 B | — |
| Llama-3.2-1B_full_nodp/config.json | Configuration | 863 B | — |
| Llama-3.2-1B_full_nodp/generation_config.json | Configuration | 215 B | — |
| Llama-3.2-1B_lora_fastdp/adapter_config.json | Configuration | 797 B | — |
| Llama-3.2-1B_lora_nodp/adapter_config.json | Configuration | 797 B | — |
| Llama-3.2-1B_lora_r16_a32_lr0.001_e3/adapter_config.json | Configuration | 797 B | — |
| Llama-3.2-1B_lora_r16_a32_lr0.001_e3/hyperparameters.json | Configuration | 667 B | — |
| Llama-3.2-1B_qlora_fastdp/adapter_config.json | Configuration | 797 B | — |
| Llama-3.2-1B_qlora_nodp/adapter_config.json | Configuration | 797 B | — |
| Llama-3.2-3B_full_lr0.001_e3/config.json | Configuration | 864 B | — |
| Llama-3.2-3B_full_lr0.001_e3/generation_config.json | Configuration | 215 B | — |
| Llama-3.2-3B_full_lr0.001_e3/hyperparameters.json | Configuration | 476 B | — |
| Llama-3.2-3B_full_nodp/config.json | Configuration | 864 B | — |
| Llama-3.2-3B_full_nodp/generation_config.json | Configuration | 215 B | — |
| Llama-3.2-3B_lora_nodp/adapter_config.json | Configuration | 797 B | — |
| Llama-3.2-3B_lora_r16_a32_lr0.001_e3/adapter_config.json | Configuration | 797 B | — |
| Llama-3.2-3B_lora_r16_a32_lr0.001_e3/hyperparameters.json | Configuration | 667 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-173/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-173/trainer_state.json | Configuration | 51.4 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-692/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-692/trainer_state.json | Configuration | 202.4 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/dp_privacy_spent.json | Configuration | 170 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/experiment_metadata.json | Configuration | 689 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-173/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-173/trainer_state.json | Configuration | 51.4 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-692/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-692/trainer_state.json | Configuration | 202.0 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/dp_privacy_spent.json | Configuration | 161 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/experiment_metadata.json | Configuration | 677 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/checkpoint-173/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/checkpoint-173/trainer_state.json | Configuration | 51.3 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/checkpoint-692/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/checkpoint-692/trainer_state.json | Configuration | 202.0 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/dp_privacy_spent.json | Configuration | 162 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/experiment_metadata.json | Configuration | 678 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/checkpoint-173/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/checkpoint-173/trainer_state.json | Configuration | 51.4 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/checkpoint-692/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/checkpoint-692/trainer_state.json | Configuration | 202.4 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/dp_privacy_spent.json | Configuration | 174 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/experiment_metadata.json | Configuration | 686 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/checkpoint-173/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/checkpoint-173/trainer_state.json | Configuration | 51.4 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/checkpoint-692/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/checkpoint-692/trainer_state.json | Configuration | 202.5 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/dp_privacy_spent.json | Configuration | 174 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/experiment_metadata.json | Configuration | 687 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/checkpoint-173/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/checkpoint-173/trainer_state.json | Configuration | 51.4 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/checkpoint-692/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/checkpoint-692/trainer_state.json | Configuration | 202.5 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/dp_privacy_spent.json | Configuration | 180 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/experiment_metadata.json | Configuration | 692 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/checkpoint-173/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/checkpoint-173/trainer_state.json | Configuration | 51.4 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/checkpoint-692/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/checkpoint-692/trainer_state.json | Configuration | 202.4 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/dp_privacy_spent.json | Configuration | 173 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/experiment_metadata.json | Configuration | 686 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/checkpoint-173/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/checkpoint-173/trainer_state.json | Configuration | 51.4 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/checkpoint-692/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/checkpoint-692/trainer_state.json | Configuration | 202.4 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/dp_privacy_spent.json | Configuration | 175 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/experiment_metadata.json | Configuration | 694 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/checkpoint-173/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/checkpoint-173/trainer_state.json | Configuration | 51.4 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/checkpoint-692/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/checkpoint-692/trainer_state.json | Configuration | 202.4 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/dp_privacy_spent.json | Configuration | 170 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/experiment_metadata.json | Configuration | 683 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/checkpoint-173/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/checkpoint-173/trainer_state.json | Configuration | 51.4 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/checkpoint-692/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/checkpoint-692/trainer_state.json | Configuration | 202.3 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/dp_privacy_spent.json | Configuration | 178 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/experiment_metadata.json | Configuration | 693 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/checkpoint-173/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/checkpoint-173/trainer_state.json | Configuration | 51.4 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/checkpoint-692/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/checkpoint-692/trainer_state.json | Configuration | 202.6 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/dp_privacy_spent.json | Configuration | 179 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/experiment_metadata.json | Configuration | 692 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/checkpoint-173/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/checkpoint-173/trainer_state.json | Configuration | 51.4 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/checkpoint-692/adapter_config.json | Configuration | 798 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/checkpoint-692/trainer_state.json | Configuration | 202.5 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/dp_privacy_spent.json | Configuration | 178 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/experiment_metadata.json | Configuration | 697 B | — |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1730/config.json | Configuration | 863 B | — |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1730/generation_config.json | Configuration | 215 B | — |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1730/trainer_state.json | Configuration | 503.2 KB | — |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1734/config.json | Configuration | 863 B | — |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1734/generation_config.json | Configuration | 215 B | — |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1734/trainer_state.json | Configuration | 504.3 KB | — |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/config.json | Configuration | 863 B | — |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/dp_privacy_spent.json | Configuration | 135 B | — |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/experiment_metadata.json | Configuration | 826 B | — |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/generation_config.json | Configuration | 215 B | — |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1730/config.json | Configuration | 863 B | — |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1730/generation_config.json | Configuration | 215 B | — |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1730/trainer_state.json | Configuration | 503.4 KB | — |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1734/config.json | Configuration | 863 B | — |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1734/generation_config.json | Configuration | 215 B | — |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1734/trainer_state.json | Configuration | 504.5 KB | — |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/config.json | Configuration | 863 B | — |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/dp_privacy_spent.json | Configuration | 135 B | — |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/experiment_metadata.json | Configuration | 826 B | — |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/generation_config.json | Configuration | 215 B | — |
| fft/fastdp/llama-3.2-1b_eps0.1_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 863 B | — |
| fft/fastdp/llama-3.2-1b_eps0.1_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 119 B | — |
| fft/fastdp/llama-3.2-1b_eps0.1_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 419 B | — |
| fft/fastdp/llama-3.2-1b_eps0.1_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 215 B | — |
| fft/fastdp/llama-3.2-1b_eps0.5_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 863 B | — |
| fft/fastdp/llama-3.2-1b_eps0.5_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 137 B | — |
| fft/fastdp/llama-3.2-1b_eps0.5_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 419 B | — |
| fft/fastdp/llama-3.2-1b_eps0.5_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 215 B | — |
| fft/fastdp/llama-3.2-1b_eps1.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 863 B | — |
| fft/fastdp/llama-3.2-1b_eps1.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 136 B | — |
| fft/fastdp/llama-3.2-1b_eps1.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 419 B | — |
| fft/fastdp/llama-3.2-1b_eps1.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 215 B | — |
| fft/fastdp/llama-3.2-1b_eps100.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 863 B | — |
| fft/fastdp/llama-3.2-1b_eps100.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 137 B | — |
| fft/fastdp/llama-3.2-1b_eps100.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 423 B | — |
| fft/fastdp/llama-3.2-1b_eps100.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 215 B | — |
| fft/fastdp/llama-3.2-1b_eps1000.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 863 B | — |
| fft/fastdp/llama-3.2-1b_eps1000.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 138 B | — |
| fft/fastdp/llama-3.2-1b_eps1000.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 429 B | — |
| fft/fastdp/llama-3.2-1b_eps1000.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 215 B | — |
| fft/fastdp/llama-3.2-1b_eps16.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 863 B | — |
| fft/fastdp/llama-3.2-1b_eps16.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 137 B | — |
| fft/fastdp/llama-3.2-1b_eps16.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 435 B | — |
| fft/fastdp/llama-3.2-1b_eps16.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 215 B | — |
| fft/fastdp/llama-3.2-1b_eps2.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 863 B | — |
| fft/fastdp/llama-3.2-1b_eps2.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 136 B | — |
| fft/fastdp/llama-3.2-1b_eps2.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 419 B | — |
| fft/fastdp/llama-3.2-1b_eps2.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 215 B | — |
| fft/fastdp/llama-3.2-1b_eps32.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 863 B | — |
| fft/fastdp/llama-3.2-1b_eps32.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 137 B | — |
| fft/fastdp/llama-3.2-1b_eps32.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 435 B | — |
| fft/fastdp/llama-3.2-1b_eps32.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 215 B | — |
| fft/fastdp/llama-3.2-1b_eps4.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 863 B | — |
| fft/fastdp/llama-3.2-1b_eps4.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 135 B | — |
| fft/fastdp/llama-3.2-1b_eps4.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 420 B | — |
| fft/fastdp/llama-3.2-1b_eps4.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 215 B | — |
| fft/fastdp/llama-3.2-1b_eps500.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 863 B | — |
| fft/fastdp/llama-3.2-1b_eps500.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 138 B | — |
| fft/fastdp/llama-3.2-1b_eps500.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 424 B | — |
| fft/fastdp/llama-3.2-1b_eps500.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 215 B | — |
| fft/fastdp/llama-3.2-1b_eps64.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 863 B | — |
| fft/fastdp/llama-3.2-1b_eps64.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 136 B | — |
| fft/fastdp/llama-3.2-1b_eps64.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 424 B | — |
| fft/fastdp/llama-3.2-1b_eps64.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 215 B | — |
| fft/fastdp/llama-3.2-1b_eps8.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 863 B | — |
| fft/fastdp/llama-3.2-1b_eps8.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 135 B | — |
| fft/fastdp/llama-3.2-1b_eps8.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 418 B | — |
| fft/fastdp/llama-3.2-1b_eps8.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 215 B | — |
| fft/fastdp/qwen2.5-0.5b_eps0.1_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 1.3 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps0.1_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 119 B | — |
| fft/fastdp/qwen2.5-0.5b_eps0.1_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 421 B | — |
| fft/fastdp/qwen2.5-0.5b_eps0.1_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 148 B | — |
| fft/fastdp/qwen2.5-0.5b_eps0.5_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 1.3 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps0.5_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 137 B | — |
| fft/fastdp/qwen2.5-0.5b_eps0.5_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 422 B | — |
| fft/fastdp/qwen2.5-0.5b_eps0.5_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 148 B | — |
| fft/fastdp/qwen2.5-0.5b_eps1.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 1.3 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps1.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 136 B | — |
| fft/fastdp/qwen2.5-0.5b_eps1.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 413 B | — |
| fft/fastdp/qwen2.5-0.5b_eps1.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 148 B | — |
| fft/fastdp/qwen2.5-0.5b_eps100.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 1.3 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps100.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 137 B | — |
| fft/fastdp/qwen2.5-0.5b_eps100.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 419 B | — |
| fft/fastdp/qwen2.5-0.5b_eps100.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 148 B | — |
| fft/fastdp/qwen2.5-0.5b_eps1000.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 1.3 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps1000.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 138 B | — |
| fft/fastdp/qwen2.5-0.5b_eps1000.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 422 B | — |
| fft/fastdp/qwen2.5-0.5b_eps1000.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 148 B | — |
| fft/fastdp/qwen2.5-0.5b_eps16.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 1.3 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps16.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 137 B | — |
| fft/fastdp/qwen2.5-0.5b_eps16.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 429 B | — |
| fft/fastdp/qwen2.5-0.5b_eps16.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 148 B | — |
| fft/fastdp/qwen2.5-0.5b_eps2.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 1.3 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps2.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 136 B | — |
| fft/fastdp/qwen2.5-0.5b_eps2.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 413 B | — |
| fft/fastdp/qwen2.5-0.5b_eps2.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 148 B | — |
| fft/fastdp/qwen2.5-0.5b_eps32.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 1.3 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps32.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 137 B | — |
| fft/fastdp/qwen2.5-0.5b_eps32.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 418 B | — |
| fft/fastdp/qwen2.5-0.5b_eps32.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 148 B | — |
| fft/fastdp/qwen2.5-0.5b_eps4.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 1.3 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps4.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 135 B | — |
| fft/fastdp/qwen2.5-0.5b_eps4.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 413 B | — |
| fft/fastdp/qwen2.5-0.5b_eps4.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 148 B | — |
| fft/fastdp/qwen2.5-0.5b_eps500.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 1.3 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps500.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 138 B | — |
| fft/fastdp/qwen2.5-0.5b_eps500.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 418 B | — |
| fft/fastdp/qwen2.5-0.5b_eps500.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 148 B | — |
| fft/fastdp/qwen2.5-0.5b_eps64.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 1.3 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps64.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 136 B | — |
| fft/fastdp/qwen2.5-0.5b_eps64.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 418 B | — |
| fft/fastdp/qwen2.5-0.5b_eps64.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 148 B | — |
| fft/fastdp/qwen2.5-0.5b_eps8.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 1.3 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps8.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 135 B | — |
| fft/fastdp/qwen2.5-0.5b_eps8.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 413 B | — |
| fft/fastdp/qwen2.5-0.5b_eps8.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 148 B | — |
| fft/fastdp/smollm-1.7b_eps0.1_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 723 B | — |
| fft/fastdp/smollm-1.7b_eps0.1_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 119 B | — |
| fft/fastdp/smollm-1.7b_eps0.1_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 416 B | — |
| fft/fastdp/smollm-1.7b_eps0.1_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 141 B | — |
| fft/fastdp/smollm-1.7b_eps0.5_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 723 B | — |
| fft/fastdp/smollm-1.7b_eps0.5_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 137 B | — |
| fft/fastdp/smollm-1.7b_eps0.5_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 419 B | — |
| fft/fastdp/smollm-1.7b_eps0.5_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 141 B | — |
| fft/fastdp/smollm-1.7b_eps1.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 723 B | — |
| fft/fastdp/smollm-1.7b_eps1.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 136 B | — |
| fft/fastdp/smollm-1.7b_eps1.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 430 B | — |
| fft/fastdp/smollm-1.7b_eps1.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 141 B | — |
| fft/fastdp/smollm-1.7b_eps100.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 723 B | — |
| fft/fastdp/smollm-1.7b_eps100.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 137 B | — |
| fft/fastdp/smollm-1.7b_eps100.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 425 B | — |
| fft/fastdp/smollm-1.7b_eps100.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 141 B | — |
| fft/fastdp/smollm-1.7b_eps1000.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 723 B | — |
| fft/fastdp/smollm-1.7b_eps1000.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 138 B | — |
| fft/fastdp/smollm-1.7b_eps1000.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 438 B | — |
| fft/fastdp/smollm-1.7b_eps1000.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 141 B | — |
| fft/fastdp/smollm-1.7b_eps16.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 723 B | — |
| fft/fastdp/smollm-1.7b_eps16.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 137 B | — |
| fft/fastdp/smollm-1.7b_eps16.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 424 B | — |
| fft/fastdp/smollm-1.7b_eps16.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 141 B | — |
| fft/fastdp/smollm-1.7b_eps2.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 723 B | — |
| fft/fastdp/smollm-1.7b_eps2.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 136 B | — |
| fft/fastdp/smollm-1.7b_eps2.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 419 B | — |
| fft/fastdp/smollm-1.7b_eps2.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 141 B | — |
| fft/fastdp/smollm-1.7b_eps32.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 723 B | — |
| fft/fastdp/smollm-1.7b_eps32.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 137 B | — |
| fft/fastdp/smollm-1.7b_eps32.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 423 B | — |
| fft/fastdp/smollm-1.7b_eps32.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 141 B | — |
| fft/fastdp/smollm-1.7b_eps4.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 723 B | — |
| fft/fastdp/smollm-1.7b_eps4.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 135 B | — |
| fft/fastdp/smollm-1.7b_eps4.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 418 B | — |
| fft/fastdp/smollm-1.7b_eps4.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 141 B | — |
| fft/fastdp/smollm-1.7b_eps500.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 723 B | — |
| fft/fastdp/smollm-1.7b_eps500.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 138 B | — |
| fft/fastdp/smollm-1.7b_eps500.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 435 B | — |
| fft/fastdp/smollm-1.7b_eps500.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 141 B | — |
| fft/fastdp/smollm-1.7b_eps64.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 723 B | — |
| fft/fastdp/smollm-1.7b_eps64.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 136 B | — |
| fft/fastdp/smollm-1.7b_eps64.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 424 B | — |
| fft/fastdp/smollm-1.7b_eps64.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 141 B | — |
| fft/fastdp/smollm-1.7b_eps8.0_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 723 B | — |
| fft/fastdp/smollm-1.7b_eps8.0_lr5e-5_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 135 B | — |
| fft/fastdp/smollm-1.7b_eps8.0_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 419 B | — |
| fft/fastdp/smollm-1.7b_eps8.0_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 141 B | — |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1730/config.json | Configuration | 863 B | — |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1730/generation_config.json | Configuration | 215 B | — |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1730/trainer_state.json | Configuration | 511.3 KB | — |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1734/config.json | Configuration | 863 B | — |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1734/generation_config.json | Configuration | 215 B | — |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/checkpoint-1734/trainer_state.json | Configuration | 512.5 KB | — |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/config.json | Configuration | 863 B | — |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/experiment_metadata.json | Configuration | 565 B | — |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/generation_config.json | Configuration | 215 B | — |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1038/config.json | Configuration | 863 B | — |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1038/generation_config.json | Configuration | 215 B | — |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/checkpoint-1038/trainer_state.json | Configuration | 307.1 KB | — |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/checkpoint-519/config.json | Configuration | 863 B | — |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/checkpoint-519/generation_config.json | Configuration | 215 B | — |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/checkpoint-519/trainer_state.json | Configuration | 154.0 KB | — |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/config.json | Configuration | 863 B | — |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/experiment_metadata.json | Configuration | 565 B | — |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/generation_config.json | Configuration | 215 B | — |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 863 B | — |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 363 B | — |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 215 B | — |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/checkpoint-1730/config.json | Configuration | 864 B | — |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/checkpoint-1730/generation_config.json | Configuration | 215 B | — |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/checkpoint-1730/trainer_state.json | Configuration | 512.2 KB | — |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/checkpoint-1734/config.json | Configuration | 864 B | — |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/checkpoint-1734/generation_config.json | Configuration | 215 B | — |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/checkpoint-1734/trainer_state.json | Configuration | 513.4 KB | — |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/config.json | Configuration | 864 B | — |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/experiment_metadata.json | Configuration | 565 B | — |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/generation_config.json | Configuration | 215 B | — |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/checkpoint-1038/config.json | Configuration | 864 B | — |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/checkpoint-1038/generation_config.json | Configuration | 215 B | — |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/checkpoint-1038/trainer_state.json | Configuration | 307.7 KB | — |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/checkpoint-519/config.json | Configuration | 864 B | — |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/checkpoint-519/generation_config.json | Configuration | 215 B | — |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/checkpoint-519/trainer_state.json | Configuration | 154.3 KB | — |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/config.json | Configuration | 864 B | — |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/experiment_metadata.json | Configuration | 565 B | — |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/generation_config.json | Configuration | 215 B | — |
| fft/nodp/qwen2.5-0.5b_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 1.3 KB | — |
| fft/nodp/qwen2.5-0.5b_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 348 B | — |
| fft/nodp/qwen2.5-0.5b_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 148 B | — |
| fft/nodp/qwen2.5-1.5b_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 1.4 KB | — |
| fft/nodp/qwen2.5-1.5b_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 358 B | — |
| fft/nodp/qwen2.5-1.5b_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 148 B | — |
| fft/nodp/smollm-1.7b_lr5e-5_ep3_bs8_seq4096/config.json | Configuration | 723 B | — |
| fft/nodp/smollm-1.7b_lr5e-5_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 365 B | — |
| fft/nodp/smollm-1.7b_lr5e-5_ep3_bs8_seq4096/generation_config.json | Configuration | 141 B | — |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/adapter_config.json | Configuration | 795 B | — |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/adapter_config.json | Configuration | 795 B | — |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/trainer_state.json | Configuration | 506.2 KB | — |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/adapter_config.json | Configuration | 795 B | — |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/trainer_state.json | Configuration | 507.4 KB | — |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/dp_privacy_spent.json | Configuration | 135 B | — |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/experiment_metadata.json | Configuration | 831 B | — |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/adapter_config.json | Configuration | 798 B | — |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-173/adapter_config.json | Configuration | 798 B | — |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-173/trainer_state.json | Configuration | 51.4 KB | — |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-692/adapter_config.json | Configuration | 798 B | — |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-692/trainer_state.json | Configuration | 202.5 KB | — |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/dp_privacy_spent.json | Configuration | 136 B | — |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/experiment_metadata.json | Configuration | 854 B | — |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/adapter_config.json | Configuration | 797 B | — |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-173/adapter_config.json | Configuration | 797 B | — |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-173/trainer_state.json | Configuration | 51.3 KB | — |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-692/adapter_config.json | Configuration | 797 B | — |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-692/trainer_state.json | Configuration | 202.3 KB | — |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/dp_privacy_spent.json | Configuration | 136 B | — |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/experiment_metadata.json | Configuration | 849 B | — |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/adapter_config.json | Configuration | 795 B | — |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1730/adapter_config.json | Configuration | 795 B | — |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1730/trainer_state.json | Configuration | 506.3 KB | — |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1734/adapter_config.json | Configuration | 795 B | — |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1734/trainer_state.json | Configuration | 507.5 KB | — |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/dp_privacy_spent.json | Configuration | 135 B | — |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/experiment_metadata.json | Configuration | 831 B | — |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/adapter_config.json | Configuration | 798 B | — |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-173/adapter_config.json | Configuration | 798 B | — |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-173/trainer_state.json | Configuration | 51.4 KB | — |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-692/adapter_config.json | Configuration | 798 B | — |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-692/trainer_state.json | Configuration | 202.6 KB | — |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/dp_privacy_spent.json | Configuration | 136 B | — |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/experiment_metadata.json | Configuration | 844 B | — |
| lora/fastdp/llama-3.2-1b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 798 B | — |
| lora/fastdp/llama-3.2-1b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 161 B | — |
| lora/fastdp/llama-3.2-1b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 441 B | — |
| lora/fastdp/llama-3.2-1b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 798 B | — |
| lora/fastdp/llama-3.2-1b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 178 B | — |
| lora/fastdp/llama-3.2-1b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 431 B | — |
| lora/fastdp/llama-3.2-1b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 798 B | — |
| lora/fastdp/llama-3.2-1b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 174 B | — |
| lora/fastdp/llama-3.2-1b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 431 B | — |
| lora/fastdp/llama-3.2-1b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 798 B | — |
| lora/fastdp/llama-3.2-1b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 174 B | — |
| lora/fastdp/llama-3.2-1b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 435 B | — |
| lora/fastdp/llama-3.2-1b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 798 B | — |
| lora/fastdp/llama-3.2-1b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 180 B | — |
| lora/fastdp/llama-3.2-1b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 436 B | — |
| lora/fastdp/llama-3.2-1b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 798 B | — |
| lora/fastdp/llama-3.2-1b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 170 B | — |
| lora/fastdp/llama-3.2-1b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 445 B | — |
| lora/fastdp/llama-3.2-1b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 798 B | — |
| lora/fastdp/llama-3.2-1b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 173 B | — |
| lora/fastdp/llama-3.2-1b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 431 B | — |
| lora/fastdp/llama-3.2-1b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 798 B | — |
| lora/fastdp/llama-3.2-1b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 175 B | — |
| lora/fastdp/llama-3.2-1b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 434 B | — |
| lora/fastdp/llama-3.2-1b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 798 B | — |
| lora/fastdp/llama-3.2-1b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 170 B | — |
| lora/fastdp/llama-3.2-1b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 430 B | — |
| lora/fastdp/llama-3.2-1b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 798 B | — |
| lora/fastdp/llama-3.2-1b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 180 B | — |
| lora/fastdp/llama-3.2-1b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 445 B | — |
| lora/fastdp/llama-3.2-1b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 798 B | — |
| lora/fastdp/llama-3.2-1b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 178 B | — |
| lora/fastdp/llama-3.2-1b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 435 B | — |
| lora/fastdp/llama-3.2-1b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 798 B | — |
| lora/fastdp/llama-3.2-1b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 173 B | — |
| lora/fastdp/llama-3.2-1b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 431 B | — |
| lora/fastdp/qwen2.5-0.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-0.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 161 B | — |
| lora/fastdp/qwen2.5-0.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 425 B | — |
| lora/fastdp/qwen2.5-0.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-0.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 178 B | — |
| lora/fastdp/qwen2.5-0.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 424 B | — |
| lora/fastdp/qwen2.5-0.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-0.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 174 B | — |
| lora/fastdp/qwen2.5-0.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 425 B | — |
| lora/fastdp/qwen2.5-0.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-0.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 174 B | — |
| lora/fastdp/qwen2.5-0.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 439 B | — |
| lora/fastdp/qwen2.5-0.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-0.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 180 B | — |
| lora/fastdp/qwen2.5-0.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 441 B | — |
| lora/fastdp/qwen2.5-0.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-0.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 170 B | — |
| lora/fastdp/qwen2.5-0.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 440 B | — |
| lora/fastdp/qwen2.5-0.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-0.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 173 B | — |
| lora/fastdp/qwen2.5-0.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 436 B | — |
| lora/fastdp/qwen2.5-0.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-0.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 175 B | — |
| lora/fastdp/qwen2.5-0.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 429 B | — |
| lora/fastdp/qwen2.5-0.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-0.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 170 B | — |
| lora/fastdp/qwen2.5-0.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 434 B | — |
| lora/fastdp/qwen2.5-0.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-0.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 180 B | — |
| lora/fastdp/qwen2.5-0.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 429 B | — |
| lora/fastdp/qwen2.5-0.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-0.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 178 B | — |
| lora/fastdp/qwen2.5-0.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 429 B | — |
| lora/fastdp/qwen2.5-0.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-0.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 173 B | — |
| lora/fastdp/qwen2.5-0.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 425 B | — |
| lora/fastdp/qwen2.5-1.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-1.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 161 B | — |
| lora/fastdp/qwen2.5-1.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 425 B | — |
| lora/fastdp/qwen2.5-1.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-1.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 178 B | — |
| lora/fastdp/qwen2.5-1.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 436 B | — |
| lora/fastdp/qwen2.5-1.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-1.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 174 B | — |
| lora/fastdp/qwen2.5-1.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 435 B | — |
| lora/fastdp/qwen2.5-1.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-1.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 174 B | — |
| lora/fastdp/qwen2.5-1.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 427 B | — |
| lora/fastdp/qwen2.5-1.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-1.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 180 B | — |
| lora/fastdp/qwen2.5-1.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 431 B | — |
| lora/fastdp/qwen2.5-1.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-1.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 170 B | — |
| lora/fastdp/qwen2.5-1.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 429 B | — |
| lora/fastdp/qwen2.5-1.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-1.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 173 B | — |
| lora/fastdp/qwen2.5-1.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 435 B | — |
| lora/fastdp/qwen2.5-1.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-1.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 175 B | — |
| lora/fastdp/qwen2.5-1.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 428 B | — |
| lora/fastdp/qwen2.5-1.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-1.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 170 B | — |
| lora/fastdp/qwen2.5-1.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 425 B | — |
| lora/fastdp/qwen2.5-1.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-1.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 180 B | — |
| lora/fastdp/qwen2.5-1.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 429 B | — |
| lora/fastdp/qwen2.5-1.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-1.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 178 B | — |
| lora/fastdp/qwen2.5-1.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 429 B | — |
| lora/fastdp/qwen2.5-1.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/fastdp/qwen2.5-1.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 173 B | — |
| lora/fastdp/qwen2.5-1.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 425 B | — |
| lora/fastdp/smollm-1.7b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| lora/fastdp/smollm-1.7b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 161 B | — |
| lora/fastdp/smollm-1.7b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 430 B | — |
| lora/fastdp/smollm-1.7b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| lora/fastdp/smollm-1.7b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 178 B | — |
| lora/fastdp/smollm-1.7b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 431 B | — |
| lora/fastdp/smollm-1.7b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| lora/fastdp/smollm-1.7b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 174 B | — |
| lora/fastdp/smollm-1.7b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 431 B | — |
| lora/fastdp/smollm-1.7b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| lora/fastdp/smollm-1.7b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 174 B | — |
| lora/fastdp/smollm-1.7b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 446 B | — |
| lora/fastdp/smollm-1.7b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| lora/fastdp/smollm-1.7b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 180 B | — |
| lora/fastdp/smollm-1.7b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 436 B | — |
| lora/fastdp/smollm-1.7b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| lora/fastdp/smollm-1.7b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 170 B | — |
| lora/fastdp/smollm-1.7b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 445 B | — |
| lora/fastdp/smollm-1.7b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| lora/fastdp/smollm-1.7b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 173 B | — |
| lora/fastdp/smollm-1.7b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 441 B | — |
| lora/fastdp/smollm-1.7b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| lora/fastdp/smollm-1.7b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 175 B | — |
| lora/fastdp/smollm-1.7b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 435 B | — |
| lora/fastdp/smollm-1.7b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| lora/fastdp/smollm-1.7b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 170 B | — |
| lora/fastdp/smollm-1.7b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 430 B | — |
| lora/fastdp/smollm-1.7b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| lora/fastdp/smollm-1.7b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 180 B | — |
| lora/fastdp/smollm-1.7b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 445 B | — |
| lora/fastdp/smollm-1.7b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| lora/fastdp/smollm-1.7b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 178 B | — |
| lora/fastdp/smollm-1.7b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 446 B | — |
| lora/fastdp/smollm-1.7b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| lora/fastdp/smollm-1.7b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 173 B | — |
| lora/fastdp/smollm-1.7b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 431 B | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/adapter_config.json | Configuration | 797 B | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1038/adapter_config.json | Configuration | 797 B | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1038/trainer_state.json | Configuration | 316.4 KB | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1557/adapter_config.json | Configuration | 797 B | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1557/trainer_state.json | Configuration | 475.0 KB | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/experiment_metadata.json | Configuration | 578 B | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/adapter_config.json | Configuration | 797 B | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1730/adapter_config.json | Configuration | 797 B | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1730/trainer_state.json | Configuration | 528.1 KB | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1734/adapter_config.json | Configuration | 797 B | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1734/trainer_state.json | Configuration | 529.3 KB | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/experiment_metadata.json | Configuration | 579 B | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/adapter_config.json | Configuration | 797 B | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1038/adapter_config.json | Configuration | 797 B | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1038/trainer_state.json | Configuration | 316.9 KB | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1557/adapter_config.json | Configuration | 797 B | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1557/trainer_state.json | Configuration | 475.5 KB | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/experiment_metadata.json | Configuration | 579 B | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/adapter_config.json | Configuration | 795 B | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1038/adapter_config.json | Configuration | 795 B | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1038/trainer_state.json | Configuration | 316.7 KB | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1557/adapter_config.json | Configuration | 795 B | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1557/trainer_state.json | Configuration | 475.3 KB | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/experiment_metadata.json | Configuration | 572 B | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/adapter_config.json | Configuration | 795 B | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/adapter_config.json | Configuration | 795 B | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/trainer_state.json | Configuration | 528.1 KB | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/adapter_config.json | Configuration | 795 B | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/trainer_state.json | Configuration | 529.3 KB | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/experiment_metadata.json | Configuration | 573 B | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/adapter_config.json | Configuration | 795 B | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1038/adapter_config.json | Configuration | 795 B | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1038/trainer_state.json | Configuration | 317.3 KB | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1557/adapter_config.json | Configuration | 795 B | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1557/trainer_state.json | Configuration | 475.9 KB | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/experiment_metadata.json | Configuration | 573 B | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/adapter_config.json | Configuration | 798 B | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1038/adapter_config.json | Configuration | 798 B | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1038/trainer_state.json | Configuration | 316.4 KB | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1557/adapter_config.json | Configuration | 798 B | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1557/trainer_state.json | Configuration | 475.0 KB | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/experiment_metadata.json | Configuration | 581 B | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/adapter_config.json | Configuration | 798 B | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1038/adapter_config.json | Configuration | 798 B | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1038/trainer_state.json | Configuration | 316.4 KB | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1557/adapter_config.json | Configuration | 798 B | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1557/trainer_state.json | Configuration | 474.9 KB | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/experiment_metadata.json | Configuration | 581 B | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/adapter_config.json | Configuration | 798 B | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1038/adapter_config.json | Configuration | 798 B | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1038/trainer_state.json | Configuration | 316.9 KB | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1557/adapter_config.json | Configuration | 798 B | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1557/trainer_state.json | Configuration | 475.4 KB | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/experiment_metadata.json | Configuration | 582 B | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 798 B | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 365 B | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/adapter_config.json | Configuration | 797 B | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1038/adapter_config.json | Configuration | 797 B | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1038/trainer_state.json | Configuration | 316.5 KB | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1557/adapter_config.json | Configuration | 797 B | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1557/trainer_state.json | Configuration | 475.1 KB | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/experiment_metadata.json | Configuration | 578 B | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/adapter_config.json | Configuration | 797 B | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1038/adapter_config.json | Configuration | 797 B | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1038/trainer_state.json | Configuration | 316.8 KB | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1557/adapter_config.json | Configuration | 797 B | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1557/trainer_state.json | Configuration | 475.4 KB | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/experiment_metadata.json | Configuration | 578 B | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/adapter_config.json | Configuration | 797 B | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-1038/adapter_config.json | Configuration | 797 B | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-1038/trainer_state.json | Configuration | 317.2 KB | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-519/adapter_config.json | Configuration | 797 B | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-519/trainer_state.json | Configuration | 159.2 KB | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/experiment_metadata.json | Configuration | 578 B | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 797 B | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 374 B | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/adapter_config.json | Configuration | 795 B | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1038/adapter_config.json | Configuration | 795 B | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1038/trainer_state.json | Configuration | 316.9 KB | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-519/adapter_config.json | Configuration | 795 B | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-519/trainer_state.json | Configuration | 158.9 KB | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/experiment_metadata.json | Configuration | 571 B | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/adapter_config.json | Configuration | 795 B | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1730/adapter_config.json | Configuration | 795 B | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1730/trainer_state.json | Configuration | 528.2 KB | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1734/adapter_config.json | Configuration | 795 B | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1734/trainer_state.json | Configuration | 529.4 KB | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/experiment_metadata.json | Configuration | 573 B | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/adapter_config.json | Configuration | 795 B | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1038/adapter_config.json | Configuration | 795 B | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1038/trainer_state.json | Configuration | 317.5 KB | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1557/adapter_config.json | Configuration | 795 B | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1557/trainer_state.json | Configuration | 476.2 KB | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/experiment_metadata.json | Configuration | 573 B | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/adapter_config.json | Configuration | 798 B | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-173/adapter_config.json | Configuration | 798 B | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-173/trainer_state.json | Configuration | 53.6 KB | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-692/adapter_config.json | Configuration | 798 B | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-692/trainer_state.json | Configuration | 211.2 KB | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/experiment_metadata.json | Configuration | 581 B | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/adapter_config.json | Configuration | 798 B | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1038/adapter_config.json | Configuration | 798 B | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1038/trainer_state.json | Configuration | 316.8 KB | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1557/adapter_config.json | Configuration | 798 B | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1557/trainer_state.json | Configuration | 475.4 KB | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/experiment_metadata.json | Configuration | 582 B | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/adapter_config.json | Configuration | 798 B | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-1038/adapter_config.json | Configuration | 798 B | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-1038/trainer_state.json | Configuration | 317.0 KB | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-519/adapter_config.json | Configuration | 798 B | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-519/trainer_state.json | Configuration | 159.0 KB | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/experiment_metadata.json | Configuration | 581 B | — |
| lora/nodp/qwen2.5-0.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/nodp/qwen2.5-0.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 369 B | — |
| lora/nodp/qwen2.5-1.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| lora/nodp/qwen2.5-1.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 357 B | — |
| lora/nodp/smollm-1.7b_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| lora/nodp/smollm-1.7b_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 365 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/adapter_config.json | Configuration | 797 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/checkpoint-173/adapter_config.json | Configuration | 797 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/checkpoint-173/trainer_state.json | Configuration | 51.4 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/checkpoint-692/adapter_config.json | Configuration | 797 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/checkpoint-692/trainer_state.json | Configuration | 202.4 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/dp_privacy_spent.json | Configuration | 170 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/experiment_metadata.json | Configuration | 637 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/adapter_config.json | Configuration | 797 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/checkpoint-173/adapter_config.json | Configuration | 797 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/checkpoint-173/trainer_state.json | Configuration | 51.4 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/checkpoint-692/adapter_config.json | Configuration | 797 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/checkpoint-692/trainer_state.json | Configuration | 202.3 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/dp_privacy_spent.json | Configuration | 173 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/experiment_metadata.json | Configuration | 638 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/adapter_config.json | Configuration | 797 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/checkpoint-173/adapter_config.json | Configuration | 797 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/checkpoint-173/trainer_state.json | Configuration | 51.3 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/checkpoint-692/adapter_config.json | Configuration | 797 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/checkpoint-692/trainer_state.json | Configuration | 202.3 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/dp_privacy_spent.json | Configuration | 175 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/experiment_metadata.json | Configuration | 642 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/adapter_config.json | Configuration | 797 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/checkpoint-173/adapter_config.json | Configuration | 797 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/checkpoint-173/trainer_state.json | Configuration | 51.4 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/checkpoint-692/adapter_config.json | Configuration | 797 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/checkpoint-692/trainer_state.json | Configuration | 202.3 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/dp_privacy_spent.json | Configuration | 170 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/experiment_metadata.json | Configuration | 635 B | — |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/adapter_config.json | Configuration | 797 B | — |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/checkpoint-173/adapter_config.json | Configuration | 797 B | — |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/checkpoint-173/trainer_state.json | Configuration | 51.3 KB | — |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/checkpoint-692/adapter_config.json | Configuration | 797 B | — |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/checkpoint-692/trainer_state.json | Configuration | 202.2 KB | — |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/dp_privacy_spent.json | Configuration | 162 B | — |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/experiment_metadata.json | Configuration | 595 B | — |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/adapter_config.json | Configuration | 795 B | — |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1557/adapter_config.json | Configuration | 795 B | — |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1557/trainer_state.json | Configuration | 455.3 KB | — |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/adapter_config.json | Configuration | 795 B | — |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/trainer_state.json | Configuration | 507.1 KB | — |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/dp_privacy_spent.json | Configuration | 135 B | — |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/experiment_metadata.json | Configuration | 846 B | — |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/adapter_config.json | Configuration | 798 B | — |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-173/adapter_config.json | Configuration | 798 B | — |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-173/trainer_state.json | Configuration | 51.4 KB | — |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-692/adapter_config.json | Configuration | 798 B | — |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-692/trainer_state.json | Configuration | 202.4 KB | — |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/dp_privacy_spent.json | Configuration | 136 B | — |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/experiment_metadata.json | Configuration | 857 B | — |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/adapter_config.json | Configuration | 797 B | — |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-173/adapter_config.json | Configuration | 797 B | — |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-173/trainer_state.json | Configuration | 51.4 KB | — |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-692/adapter_config.json | Configuration | 797 B | — |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-692/trainer_state.json | Configuration | 202.3 KB | — |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/dp_privacy_spent.json | Configuration | 136 B | — |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/experiment_metadata.json | Configuration | 843 B | — |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/adapter_config.json | Configuration | 795 B | — |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1730/adapter_config.json | Configuration | 795 B | — |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1730/trainer_state.json | Configuration | 505.8 KB | — |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1734/adapter_config.json | Configuration | 795 B | — |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1734/trainer_state.json | Configuration | 506.9 KB | — |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/dp_privacy_spent.json | Configuration | 135 B | — |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/experiment_metadata.json | Configuration | 844 B | — |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/adapter_config.json | Configuration | 798 B | — |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-173/adapter_config.json | Configuration | 798 B | — |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-173/trainer_state.json | Configuration | 51.3 KB | — |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-692/adapter_config.json | Configuration | 798 B | — |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-692/trainer_state.json | Configuration | 201.6 KB | — |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/dp_privacy_spent.json | Configuration | 136 B | — |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/experiment_metadata.json | Configuration | 847 B | — |
| qlora/fastdp/llama-3.2-3b_eps0.1_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_config.json | Configuration | 797 B | — |
| qlora/fastdp/llama-3.2-3b_eps0.1_r16_a32_lr1e-3_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 161 B | — |
| qlora/fastdp/llama-3.2-3b_eps0.1_r16_a32_lr1e-3_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 433 B | — |
| qlora/fastdp/llama-3.2-3b_eps0.5_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_config.json | Configuration | 797 B | — |
| qlora/fastdp/llama-3.2-3b_eps0.5_r16_a32_lr1e-3_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 178 B | — |
| qlora/fastdp/llama-3.2-3b_eps0.5_r16_a32_lr1e-3_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 432 B | — |
| qlora/fastdp/llama-3.2-3b_eps1.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_config.json | Configuration | 797 B | — |
| qlora/fastdp/llama-3.2-3b_eps1.0_r16_a32_lr1e-3_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 174 B | — |
| qlora/fastdp/llama-3.2-3b_eps1.0_r16_a32_lr1e-3_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 433 B | — |
| qlora/fastdp/llama-3.2-3b_eps100.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_config.json | Configuration | 797 B | — |
| qlora/fastdp/llama-3.2-3b_eps100.0_r16_a32_lr1e-3_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 174 B | — |
| qlora/fastdp/llama-3.2-3b_eps100.0_r16_a32_lr1e-3_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 437 B | — |
| qlora/fastdp/llama-3.2-3b_eps1000.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_config.json | Configuration | 797 B | — |
| qlora/fastdp/llama-3.2-3b_eps1000.0_r16_a32_lr1e-3_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 180 B | — |
| qlora/fastdp/llama-3.2-3b_eps1000.0_r16_a32_lr1e-3_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 438 B | — |
| qlora/fastdp/llama-3.2-3b_eps16.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_config.json | Configuration | 797 B | — |
| qlora/fastdp/llama-3.2-3b_eps16.0_r16_a32_lr1e-3_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 170 B | — |
| qlora/fastdp/llama-3.2-3b_eps16.0_r16_a32_lr1e-3_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 447 B | — |
| qlora/fastdp/llama-3.2-3b_eps2.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_config.json | Configuration | 797 B | — |
| qlora/fastdp/llama-3.2-3b_eps2.0_r16_a32_lr1e-3_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 173 B | — |
| qlora/fastdp/llama-3.2-3b_eps2.0_r16_a32_lr1e-3_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 433 B | — |
| qlora/fastdp/llama-3.2-3b_eps32.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_config.json | Configuration | 797 B | — |
| qlora/fastdp/llama-3.2-3b_eps32.0_r16_a32_lr1e-3_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 175 B | — |
| qlora/fastdp/llama-3.2-3b_eps32.0_r16_a32_lr1e-3_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 437 B | — |
| qlora/fastdp/llama-3.2-3b_eps4.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_config.json | Configuration | 797 B | — |
| qlora/fastdp/llama-3.2-3b_eps4.0_r16_a32_lr1e-3_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 170 B | — |
| qlora/fastdp/llama-3.2-3b_eps4.0_r16_a32_lr1e-3_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 444 B | — |
| qlora/fastdp/llama-3.2-3b_eps500.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_config.json | Configuration | 797 B | — |
| qlora/fastdp/llama-3.2-3b_eps500.0_r16_a32_lr1e-3_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 180 B | — |
| qlora/fastdp/llama-3.2-3b_eps500.0_r16_a32_lr1e-3_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 447 B | — |
| qlora/fastdp/llama-3.2-3b_eps64.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_config.json | Configuration | 797 B | — |
| qlora/fastdp/llama-3.2-3b_eps64.0_r16_a32_lr1e-3_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 178 B | — |
| qlora/fastdp/llama-3.2-3b_eps64.0_r16_a32_lr1e-3_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 447 B | — |
| qlora/fastdp/llama-3.2-3b_eps8.0_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_config.json | Configuration | 797 B | — |
| qlora/fastdp/llama-3.2-3b_eps8.0_r16_a32_lr1e-3_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 173 B | — |
| qlora/fastdp/llama-3.2-3b_eps8.0_r16_a32_lr1e-3_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 433 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 161 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 438 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 178 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 439 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 174 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 428 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 174 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 432 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 180 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 435 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 170 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 432 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps16000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps16000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 182 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps16000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 448 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 173 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 427 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps2000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps2000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 181 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps2000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 444 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 175 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 433 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 170 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 428 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps4000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps4000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 181 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps4000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 434 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 180 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 432 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 178 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 433 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 173 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 428 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps8000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps8000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 175 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps8000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 444 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 161 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 428 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 178 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 428 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 174 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 427 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 174 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 431 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 180 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 445 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 170 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 442 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 173 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 439 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 175 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 442 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 170 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 428 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 180 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 443 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 178 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 442 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 173 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 428 B | — |
| qlora/fastdp/smollm-1.7b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| qlora/fastdp/smollm-1.7b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 161 B | — |
| qlora/fastdp/smollm-1.7b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 445 B | — |
| qlora/fastdp/smollm-1.7b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| qlora/fastdp/smollm-1.7b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 178 B | — |
| qlora/fastdp/smollm-1.7b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 444 B | — |
| qlora/fastdp/smollm-1.7b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| qlora/fastdp/smollm-1.7b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 174 B | — |
| qlora/fastdp/smollm-1.7b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 444 B | — |
| qlora/fastdp/smollm-1.7b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| qlora/fastdp/smollm-1.7b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 174 B | — |
| qlora/fastdp/smollm-1.7b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 437 B | — |
| qlora/fastdp/smollm-1.7b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| qlora/fastdp/smollm-1.7b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 180 B | — |
| qlora/fastdp/smollm-1.7b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 440 B | — |
| qlora/fastdp/smollm-1.7b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| qlora/fastdp/smollm-1.7b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 170 B | — |
| qlora/fastdp/smollm-1.7b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 449 B | — |
| qlora/fastdp/smollm-1.7b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| qlora/fastdp/smollm-1.7b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 173 B | — |
| qlora/fastdp/smollm-1.7b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 445 B | — |
| qlora/fastdp/smollm-1.7b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| qlora/fastdp/smollm-1.7b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 175 B | — |
| qlora/fastdp/smollm-1.7b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 448 B | — |
| qlora/fastdp/smollm-1.7b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| qlora/fastdp/smollm-1.7b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 170 B | — |
| qlora/fastdp/smollm-1.7b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 434 B | — |
| qlora/fastdp/smollm-1.7b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| qlora/fastdp/smollm-1.7b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 180 B | — |
| qlora/fastdp/smollm-1.7b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 437 B | — |
| qlora/fastdp/smollm-1.7b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| qlora/fastdp/smollm-1.7b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 178 B | — |
| qlora/fastdp/smollm-1.7b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 437 B | — |
| qlora/fastdp/smollm-1.7b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| qlora/fastdp/smollm-1.7b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 173 B | — |
| qlora/fastdp/smollm-1.7b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 432 B | — |
| qlora/fastdp/stablelm-2-1.6b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 802 B | — |
| qlora/fastdp/stablelm-2-1.6b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 161 B | — |
| qlora/fastdp/stablelm-2-1.6b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 455 B | — |
| qlora/fastdp/stablelm-2-1.6b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 802 B | — |
| qlora/fastdp/stablelm-2-1.6b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/dp_privacy_spent.json | Configuration | 178 B | — |
| qlora/fastdp/stablelm-2-1.6b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 443 B | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/adapter_config.json | Configuration | 797 B | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1038/adapter_config.json | Configuration | 797 B | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1038/trainer_state.json | Configuration | 307.3 KB | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1557/adapter_config.json | Configuration | 797 B | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1557/trainer_state.json | Configuration | 461.2 KB | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/experiment_metadata.json | Configuration | 581 B | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/adapter_config.json | Configuration | 797 B | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1730/adapter_config.json | Configuration | 797 B | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1730/trainer_state.json | Configuration | 513.2 KB | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1734/adapter_config.json | Configuration | 797 B | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1734/trainer_state.json | Configuration | 514.4 KB | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/experiment_metadata.json | Configuration | 582 B | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/adapter_config.json | Configuration | 797 B | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1038/adapter_config.json | Configuration | 797 B | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1038/trainer_state.json | Configuration | 308.1 KB | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1557/adapter_config.json | Configuration | 797 B | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1557/trainer_state.json | Configuration | 462.0 KB | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/experiment_metadata.json | Configuration | 582 B | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/adapter_config.json | Configuration | 795 B | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1038/adapter_config.json | Configuration | 795 B | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1038/trainer_state.json | Configuration | 308.0 KB | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1557/adapter_config.json | Configuration | 795 B | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1557/trainer_state.json | Configuration | 462.2 KB | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/experiment_metadata.json | Configuration | 574 B | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/adapter_config.json | Configuration | 795 B | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/adapter_config.json | Configuration | 795 B | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/trainer_state.json | Configuration | 513.3 KB | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/adapter_config.json | Configuration | 795 B | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/trainer_state.json | Configuration | 514.4 KB | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/experiment_metadata.json | Configuration | 576 B | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/adapter_config.json | Configuration | 795 B | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1038/adapter_config.json | Configuration | 795 B | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1038/trainer_state.json | Configuration | 308.8 KB | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1557/adapter_config.json | Configuration | 795 B | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1557/trainer_state.json | Configuration | 463.0 KB | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/experiment_metadata.json | Configuration | 576 B | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/adapter_config.json | Configuration | 798 B | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1038/adapter_config.json | Configuration | 798 B | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1038/trainer_state.json | Configuration | 306.5 KB | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1557/adapter_config.json | Configuration | 798 B | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1557/trainer_state.json | Configuration | 460.1 KB | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/experiment_metadata.json | Configuration | 584 B | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/adapter_config.json | Configuration | 798 B | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1038/adapter_config.json | Configuration | 798 B | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1038/trainer_state.json | Configuration | 307.4 KB | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1557/adapter_config.json | Configuration | 798 B | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1557/trainer_state.json | Configuration | 461.2 KB | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/experiment_metadata.json | Configuration | 585 B | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/adapter_config.json | Configuration | 798 B | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1038/adapter_config.json | Configuration | 798 B | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1038/trainer_state.json | Configuration | 307.5 KB | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1557/adapter_config.json | Configuration | 798 B | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1557/trainer_state.json | Configuration | 461.1 KB | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/experiment_metadata.json | Configuration | 585 B | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/adapter_config.json | Configuration | 797 B | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1038/adapter_config.json | Configuration | 797 B | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1038/trainer_state.json | Configuration | 308.5 KB | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1557/adapter_config.json | Configuration | 797 B | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1557/trainer_state.json | Configuration | 463.1 KB | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/experiment_metadata.json | Configuration | 581 B | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3_bs8_seq4096/adapter_config.json | Configuration | 797 B | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 376 B | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/adapter_config.json | Configuration | 797 B | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1730/adapter_config.json | Configuration | 797 B | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1730/trainer_state.json | Configuration | 515.7 KB | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1734/adapter_config.json | Configuration | 797 B | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1734/trainer_state.json | Configuration | 516.9 KB | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/experiment_metadata.json | Configuration | 582 B | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/adapter_config.json | Configuration | 797 B | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-1038/adapter_config.json | Configuration | 797 B | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-1038/trainer_state.json | Configuration | 309.6 KB | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-519/adapter_config.json | Configuration | 797 B | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-519/trainer_state.json | Configuration | 155.4 KB | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/experiment_metadata.json | Configuration | 582 B | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/adapter_config.json | Configuration | 795 B | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1038/adapter_config.json | Configuration | 795 B | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1038/trainer_state.json | Configuration | 309.3 KB | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1557/adapter_config.json | Configuration | 795 B | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1557/trainer_state.json | Configuration | 464.3 KB | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/experiment_metadata.json | Configuration | 575 B | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/adapter_config.json | Configuration | 795 B | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1730/adapter_config.json | Configuration | 795 B | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1730/trainer_state.json | Configuration | 515.6 KB | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1734/adapter_config.json | Configuration | 795 B | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1734/trainer_state.json | Configuration | 516.8 KB | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/experiment_metadata.json | Configuration | 576 B | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/adapter_config.json | Configuration | 795 B | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1038/adapter_config.json | Configuration | 795 B | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1038/trainer_state.json | Configuration | 310.2 KB | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1557/adapter_config.json | Configuration | 795 B | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1557/trainer_state.json | Configuration | 465.1 KB | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/experiment_metadata.json | Configuration | 576 B | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/adapter_config.json | Configuration | 798 B | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-1038/adapter_config.json | Configuration | 798 B | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-1038/trainer_state.json | Configuration | 307.9 KB | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-1557/adapter_config.json | Configuration | 798 B | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-1557/trainer_state.json | Configuration | 462.1 KB | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/experiment_metadata.json | Configuration | 584 B | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/adapter_config.json | Configuration | 798 B | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1038/adapter_config.json | Configuration | 798 B | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1038/trainer_state.json | Configuration | 309.0 KB | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1557/adapter_config.json | Configuration | 798 B | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1557/trainer_state.json | Configuration | 463.8 KB | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/experiment_metadata.json | Configuration | 585 B | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/adapter_config.json | Configuration | 798 B | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-1038/adapter_config.json | Configuration | 798 B | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-1038/trainer_state.json | Configuration | 308.9 KB | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-519/adapter_config.json | Configuration | 798 B | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-519/trainer_state.json | Configuration | 155.0 KB | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/experiment_metadata.json | Configuration | 585 B | — |
| qlora/nodp/qwen2.5-0.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/nodp/qwen2.5-0.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 372 B | — |
| qlora/nodp/qwen2.5-1.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 792 B | — |
| qlora/nodp/qwen2.5-1.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 362 B | — |
| qlora/nodp/smollm-1.7b_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 800 B | — |
| qlora/nodp/smollm-1.7b_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 367 B | — |
| qlora/nodp/stablelm-2-1.6b_r64_a128_lr5e-4_ep3_bs8_seq4096/adapter_config.json | Configuration | 802 B | — |
| qlora/nodp/stablelm-2-1.6b_r64_a128_lr5e-4_ep3_bs8_seq4096/experiment_metadata.json | Configuration | 378 B | — |
| Llama-3.2-1B_full_lr0.001_e3/README.md | Documentation | 1.2 KB | — |
| Llama-3.2-1B_lora_fastdp/README.md | Documentation | 5.1 KB | — |
| Llama-3.2-1B_lora_nodp/README.md | Documentation | 5.1 KB | — |
| Llama-3.2-1B_lora_r16_a32_lr0.001_e3/README.md | Documentation | 1.4 KB | — |
| Llama-3.2-1B_qlora_fastdp/README.md | Documentation | 5.1 KB | — |
| Llama-3.2-1B_qlora_nodp/README.md | Documentation | 5.1 KB | — |
| Llama-3.2-3B_full_lr0.001_e3/README.md | Documentation | 1.2 KB | — |
| Llama-3.2-3B_lora_nodp/README.md | Documentation | 5.1 KB | — |
| Llama-3.2-3B_lora_r16_a32_lr0.001_e3/README.md | Documentation | 1.4 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/README.md | Documentation | 1.5 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/README.md | Documentation | 1.5 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/README.md | Documentation | 1.5 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/README.md | Documentation | 1.5 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/README.md | Documentation | 1.5 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/README.md | Documentation | 1.5 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/README.md | Documentation | 1.5 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/README.md | Documentation | 1.5 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/README.md | Documentation | 1.5 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/README.md | Documentation | 1.5 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/README.md | Documentation | 1.5 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/README.md | Documentation | 1.5 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/README.md | Documentation | 1.4 KB | — |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/README.md | Documentation | 1.4 KB | — |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/README.md | Documentation | 1.5 KB | — |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/README.md | Documentation | 1.5 KB | — |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/README.md | Documentation | 1.5 KB | — |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/README.md | Documentation | 1.5 KB | — |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/README.md | Documentation | 1.5 KB | — |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/README.md | Documentation | 5.1 KB | — |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/README.md | Documentation | 5.1 KB | — |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/README.md | Documentation | 1.5 KB | — |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/README.md | Documentation | 1.5 KB | — |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1730/README.md | Documentation | 5.1 KB | — |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1734/README.md | Documentation | 5.1 KB | — |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/README.md | Documentation | 1.5 KB | — |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/llama-3.2-1b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/llama-3.2-1b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/llama-3.2-1b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/llama-3.2-1b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/llama-3.2-1b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/llama-3.2-1b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/llama-3.2-1b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/llama-3.2-1b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/llama-3.2-1b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/llama-3.2-1b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/llama-3.2-1b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/llama-3.2-1b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/smollm-1.7b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/smollm-1.7b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/smollm-1.7b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/smollm-1.7b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/smollm-1.7b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/smollm-1.7b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/smollm-1.7b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/smollm-1.7b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/smollm-1.7b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/smollm-1.7b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/smollm-1.7b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/fastdp/smollm-1.7b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/README.md | Documentation | 1.5 KB | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1730/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1734/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/README.md | Documentation | 1.5 KB | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/README.md | Documentation | 1.5 KB | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/README.md | Documentation | 1.5 KB | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/README.md | Documentation | 1.5 KB | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/README.md | Documentation | 1.5 KB | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/README.md | Documentation | 1.5 KB | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/README.md | Documentation | 1.5 KB | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-519/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-519/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/README.md | Documentation | 1.5 KB | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1730/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1734/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/README.md | Documentation | 1.5 KB | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/README.md | Documentation | 1.5 KB | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/README.md | Documentation | 1.5 KB | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-519/README.md | Documentation | 5.1 KB | — |
| lora/nodp/qwen2.5-0.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/nodp/qwen2.5-1.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| lora/nodp/smollm-1.7b_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/README.md | Documentation | 5.1 KB | — |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1730/README.md | Documentation | 5.1 KB | — |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1734/README.md | Documentation | 5.1 KB | — |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-173/README.md | Documentation | 5.1 KB | — |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-692/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/llama-3.2-3b_eps0.1_r16_a32_lr1e-3_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/llama-3.2-3b_eps0.5_r16_a32_lr1e-3_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/llama-3.2-3b_eps1.0_r16_a32_lr1e-3_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/llama-3.2-3b_eps100.0_r16_a32_lr1e-3_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/llama-3.2-3b_eps1000.0_r16_a32_lr1e-3_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/llama-3.2-3b_eps16.0_r16_a32_lr1e-3_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/llama-3.2-3b_eps2.0_r16_a32_lr1e-3_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/llama-3.2-3b_eps32.0_r16_a32_lr1e-3_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/llama-3.2-3b_eps4.0_r16_a32_lr1e-3_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/llama-3.2-3b_eps500.0_r16_a32_lr1e-3_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/llama-3.2-3b_eps64.0_r16_a32_lr1e-3_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/llama-3.2-3b_eps8.0_r16_a32_lr1e-3_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps16000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps2000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps4000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps8000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/smollm-1.7b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/smollm-1.7b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/smollm-1.7b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/smollm-1.7b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/smollm-1.7b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/smollm-1.7b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/smollm-1.7b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/smollm-1.7b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/smollm-1.7b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/smollm-1.7b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/smollm-1.7b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/smollm-1.7b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/stablelm-2-1.6b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/fastdp/stablelm-2-1.6b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1730/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/checkpoint-1734/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1730/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/checkpoint-1734/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1730/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/checkpoint-1734/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/checkpoint-519/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1730/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/checkpoint-1734/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/checkpoint-1557/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/README.md | Documentation | 1.5 KB | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-1038/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/checkpoint-519/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/qwen2.5-0.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/qwen2.5-1.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/smollm-1.7b_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| qlora/nodp/stablelm-2-1.6b_r64_a128_lr5e-4_ep3_bs8_seq4096/README.md | Documentation | 5.1 KB | — |
| Llama-3.2-1B_full_fastdp/loss_scores.log | Other | 957 B | — |
| Llama-3.2-1B_full_lr0.001_e3/loss_scores.log | Other | 916 B | — |
| Llama-3.2-1B_full_nodp/loss_scores.log | Other | 776 B | — |
| Llama-3.2-1B_lora_fastdp/loss_scores.log | Other | 1.0 KB | — |
| Llama-3.2-1B_lora_nodp/loss_scores.log | Other | 967 B | — |
| Llama-3.2-1B_lora_r16_a32_lr0.001_e3/loss_scores.log | Other | 867 B | — |
| Llama-3.2-1B_qlora_fastdp/loss_scores.log | Other | 1.0 KB | — |
| Llama-3.2-1B_qlora_nodp/loss_scores.log | Other | 967 B | — |
| Llama-3.2-3B_full_lr0.001_e3/loss_scores.log | Other | 917 B | — |
| Llama-3.2-3B_full_nodp/loss_scores.log | Other | 777 B | — |
| Llama-3.2-3B_lora_nodp/loss_scores.log | Other | 967 B | — |
| Llama-3.2-3B_lora_r16_a32_lr0.001_e3/loss_scores.log | Other | 868 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/loss_scores.log | Other | 976 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/runs/Sep21_03-49-24_a5058d49a437/events.out.tfevents.1789962564.a5058d49a437.83167.0 | Other | 271.2 KB | 9c0b21c8359e |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/loss_scores.log | Other | 973 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/runs/Sep21_01-21-15_a5058d49a437/events.out.tfevents.1789953675.a5058d49a437.4135014.0 | Other | 271.2 KB | 2b9161d6c9c0 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/loss_scores.log | Other | 974 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/runs/Sep21_00-51-18_a5058d49a437/events.out.tfevents.1789951878.a5058d49a437.4105949.0 | Other | 271.2 KB | 3570ae953477 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/loss_scores.log | Other | 971 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e0)/runs/Sep21_02-20-14_a5058d49a437/events.out.tfevents.1789957214.a5058d49a437.4191567.0 | Other | 271.2 KB | f811eaa66865 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/loss_scores.log | Other | 975 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e2)/runs/Sep21_05-17-38_a5058d49a437/events.out.tfevents.1789967858.a5058d49a437.167759.0 | Other | 271.2 KB | 573ff3b3868d |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/loss_scores.log | Other | 976 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e3)/runs/Sep21_06-16-35_a5058d49a437/events.out.tfevents.1789971395.a5058d49a437.224250.0 | Other | 271.2 KB | 631489f6de89 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/loss_scores.log | Other | 972 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(2e0)/runs/Sep21_02-49-49_a5058d49a437/events.out.tfevents.1789958989.a5058d49a437.26039.0 | Other | 271.2 KB | 5c229a2ee809 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/loss_scores.log | Other | 976 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(3.2e1)/runs/Sep21_04-18-54_a5058d49a437/events.out.tfevents.1789964334.a5058d49a437.111445.0 | Other | 271.2 KB | 73ed15cfed6d |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/loss_scores.log | Other | 972 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(4e0)/runs/Sep21_03-20-00_a5058d49a437/events.out.tfevents.1789960800.a5058d49a437.54982.0 | Other | 271.2 KB | 6225cea268fb |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/loss_scores.log | Other | 973 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e-1)/runs/Sep21_01-50-45_a5058d49a437/events.out.tfevents.1789955445.a5058d49a437.4163308.0 | Other | 271.2 KB | 074f16e3376f |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/loss_scores.log | Other | 975 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(5e2)/runs/Sep21_05-47-08_a5058d49a437/events.out.tfevents.1789969628.a5058d49a437.196037.0 | Other | 271.2 KB | 96d01fb7d4f1 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/loss_scores.log | Other | 976 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(6.4e1)/runs/Sep21_04-48-10_a5058d49a437/events.out.tfevents.1789966090.a5058d49a437.139500.0 | Other | 271.2 KB | 0de9eb69da67 |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/loss_scores.log | Other | 1.0 KB | — |
| fft/dp/llama-3.2-1b_lr1e-5_ep3/runs/Sep13_01-35-29_a5058d49a437/events.out.tfevents.1789263329.a5058d49a437.1518672.0 | Other | 671.3 KB | 7b1ac0baad6b |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/loss_scores.log | Other | 1.0 KB | — |
| fft/dp/llama-3.2-1b_lr5e-5_ep3/runs/Sep13_09-47-52_a5058d49a437/events.out.tfevents.1789292872.a5058d49a437.1990569.0 | Other | 671.3 KB | 7375dd294a35 |
| fft/fastdp/llama-3.2-1b_eps0.1_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 693 B | — |
| fft/fastdp/llama-3.2-1b_eps0.1_lr5e-5_ep3_bs8_seq4096/runs/Oct10_14-40-23_06d06940cb84/events.out.tfevents.1791643223.06d06940cb84.7591.0 | Other | 666.9 KB | 07b888f07582 |
| fft/fastdp/llama-3.2-1b_eps0.5_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 693 B | — |
| fft/fastdp/llama-3.2-1b_eps0.5_lr5e-5_ep3_bs8_seq4096/runs/Oct10_15-17-13_06d06940cb84/events.out.tfevents.1791645433.06d06940cb84.7654.0 | Other | 666.9 KB | 1dc808549689 |
| fft/fastdp/llama-3.2-1b_eps1.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 693 B | — |
| fft/fastdp/llama-3.2-1b_eps1.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_15-54-04_06d06940cb84/events.out.tfevents.1791647644.06d06940cb84.7701.0 | Other | 666.9 KB | 81e5d1df0d90 |
| fft/fastdp/llama-3.2-1b_eps100.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 695 B | — |
| fft/fastdp/llama-3.2-1b_eps100.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_20-12-48_06d06940cb84/events.out.tfevents.1791663168.06d06940cb84.8030.0 | Other | 666.9 KB | fdc9b6d3d4de |
| fft/fastdp/llama-3.2-1b_eps1000.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 696 B | — |
| fft/fastdp/llama-3.2-1b_eps1000.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_21-26-46_06d06940cb84/events.out.tfevents.1791667606.06d06940cb84.8125.0 | Other | 666.9 KB | c98bdf4b28ce |
| fft/fastdp/llama-3.2-1b_eps16.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 696 B | — |
| fft/fastdp/llama-3.2-1b_eps16.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_18-21-50_06d06940cb84/events.out.tfevents.1791656510.06d06940cb84.7889.0 | Other | 666.9 KB | bed099e55fba |
| fft/fastdp/llama-3.2-1b_eps2.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 693 B | — |
| fft/fastdp/llama-3.2-1b_eps2.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_16-31-00_06d06940cb84/events.out.tfevents.1791649860.06d06940cb84.7748.0 | Other | 666.9 KB | defee0eb106e |
| fft/fastdp/llama-3.2-1b_eps32.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 696 B | — |
| fft/fastdp/llama-3.2-1b_eps32.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_18-58-47_06d06940cb84/events.out.tfevents.1791658727.06d06940cb84.7936.0 | Other | 666.9 KB | 8fe0b83214af |
| fft/fastdp/llama-3.2-1b_eps4.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 693 B | — |
| fft/fastdp/llama-3.2-1b_eps4.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_17-07-56_06d06940cb84/events.out.tfevents.1791652076.06d06940cb84.7795.0 | Other | 666.9 KB | 6865d28ca3be |
| fft/fastdp/llama-3.2-1b_eps500.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 695 B | — |
| fft/fastdp/llama-3.2-1b_eps500.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_20-49-46_06d06940cb84/events.out.tfevents.1791665386.06d06940cb84.8078.0 | Other | 666.9 KB | 6371905ec672 |
| fft/fastdp/llama-3.2-1b_eps64.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 696 B | — |
| fft/fastdp/llama-3.2-1b_eps64.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_19-35-47_06d06940cb84/events.out.tfevents.1791660947.06d06940cb84.7983.0 | Other | 666.9 KB | f6638c430b9d |
| fft/fastdp/llama-3.2-1b_eps8.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 693 B | — |
| fft/fastdp/llama-3.2-1b_eps8.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_17-44-56_06d06940cb84/events.out.tfevents.1791654296.06d06940cb84.7842.0 | Other | 666.9 KB | 2dbc22457898 |
| fft/fastdp/qwen2.5-0.5b_eps0.1_lr5e-5_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps0.1_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 687 B | — |
| fft/fastdp/qwen2.5-0.5b_eps0.1_lr5e-5_ep3_bs8_seq4096/runs/Oct10_01-10-34_06d06940cb84/events.out.tfevents.1791594634.06d06940cb84.6065.0 | Other | 667.4 KB | bf1377ee18f5 |
| fft/fastdp/qwen2.5-0.5b_eps0.5_lr5e-5_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps0.5_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 687 B | — |
| fft/fastdp/qwen2.5-0.5b_eps0.5_lr5e-5_ep3_bs8_seq4096/runs/Oct10_01-44-10_06d06940cb84/events.out.tfevents.1791596650.06d06940cb84.6128.0 | Other | 667.4 KB | 682a2857cb69 |
| fft/fastdp/qwen2.5-0.5b_eps1.0_lr5e-5_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps1.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 687 B | — |
| fft/fastdp/qwen2.5-0.5b_eps1.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_02-17-48_06d06940cb84/events.out.tfevents.1791598668.06d06940cb84.6175.0 | Other | 667.4 KB | a64b89775257 |
| fft/fastdp/qwen2.5-0.5b_eps100.0_lr5e-5_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps100.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 689 B | — |
| fft/fastdp/qwen2.5-0.5b_eps100.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_06-13-05_06d06940cb84/events.out.tfevents.1791612785.06d06940cb84.6506.0 | Other | 667.4 KB | aec0110bc341 |
| fft/fastdp/qwen2.5-0.5b_eps1000.0_lr5e-5_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps1000.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 690 B | — |
| fft/fastdp/qwen2.5-0.5b_eps1000.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_07-20-20_06d06940cb84/events.out.tfevents.1791616820.06d06940cb84.6601.0 | Other | 667.4 KB | 6beb2dddd0f1 |
| fft/fastdp/qwen2.5-0.5b_eps16.0_lr5e-5_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps16.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 690 B | — |
| fft/fastdp/qwen2.5-0.5b_eps16.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_04-32-05_06d06940cb84/events.out.tfevents.1791606725.06d06940cb84.6365.0 | Other | 667.4 KB | 2d0ab27f4f34 |
| fft/fastdp/qwen2.5-0.5b_eps2.0_lr5e-5_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps2.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 687 B | — |
| fft/fastdp/qwen2.5-0.5b_eps2.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_02-51-21_06d06940cb84/events.out.tfevents.1791600681.06d06940cb84.6222.0 | Other | 667.4 KB | 702e6ec4e9ca |
| fft/fastdp/qwen2.5-0.5b_eps32.0_lr5e-5_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps32.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 690 B | — |
| fft/fastdp/qwen2.5-0.5b_eps32.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_05-05-43_06d06940cb84/events.out.tfevents.1791608743.06d06940cb84.6412.0 | Other | 667.4 KB | 81f90d6f5346 |
| fft/fastdp/qwen2.5-0.5b_eps4.0_lr5e-5_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps4.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 687 B | — |
| fft/fastdp/qwen2.5-0.5b_eps4.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_03-24-59_06d06940cb84/events.out.tfevents.1791602699.06d06940cb84.6269.0 | Other | 667.4 KB | 50cbdf819bbb |
| fft/fastdp/qwen2.5-0.5b_eps500.0_lr5e-5_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps500.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 689 B | — |
| fft/fastdp/qwen2.5-0.5b_eps500.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_06-46-40_06d06940cb84/events.out.tfevents.1791614800.06d06940cb84.6554.0 | Other | 667.4 KB | 082c165f8945 |
| fft/fastdp/qwen2.5-0.5b_eps64.0_lr5e-5_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps64.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 690 B | — |
| fft/fastdp/qwen2.5-0.5b_eps64.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_05-39-26_06d06940cb84/events.out.tfevents.1791610766.06d06940cb84.6459.0 | Other | 667.4 KB | 304c8b7e71c7 |
| fft/fastdp/qwen2.5-0.5b_eps8.0_lr5e-5_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| fft/fastdp/qwen2.5-0.5b_eps8.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 687 B | — |
| fft/fastdp/qwen2.5-0.5b_eps8.0_lr5e-5_ep3_bs8_seq4096/runs/Oct10_03-58-32_06d06940cb84/events.out.tfevents.1791604712.06d06940cb84.6318.0 | Other | 667.4 KB | 419241767bc2 |
| fft/fastdp/smollm-1.7b_eps0.1_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 694 B | — |
| fft/fastdp/smollm-1.7b_eps0.1_lr5e-5_ep3_bs8_seq4096/runs/Oct14_15-05-03_06d06940cb84/events.out.tfevents.1791990303.06d06940cb84.17568.0 | Other | 666.8 KB | ff81a60ffc5c |
| fft/fastdp/smollm-1.7b_eps0.5_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 694 B | — |
| fft/fastdp/smollm-1.7b_eps0.5_lr5e-5_ep3_bs8_seq4096/runs/Oct14_15-53-05_06d06940cb84/events.out.tfevents.1791993185.06d06940cb84.17629.0 | Other | 666.8 KB | 24c5094710ca |
| fft/fastdp/smollm-1.7b_eps1.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 694 B | — |
| fft/fastdp/smollm-1.7b_eps1.0_lr5e-5_ep3_bs8_seq4096/runs/Oct14_16-41-06_06d06940cb84/events.out.tfevents.1791996066.06d06940cb84.17690.0 | Other | 666.8 KB | e7122dd439cb |
| fft/fastdp/smollm-1.7b_eps100.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 696 B | — |
| fft/fastdp/smollm-1.7b_eps100.0_lr5e-5_ep3_bs8_seq4096/runs/Oct14_22-18-53_06d06940cb84/events.out.tfevents.1792016333.06d06940cb84.18006.0 | Other | 666.8 KB | 637fae41eba0 |
| fft/fastdp/smollm-1.7b_eps1000.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 697 B | — |
| fft/fastdp/smollm-1.7b_eps1000.0_lr5e-5_ep3_bs8_seq4096/runs/Oct14_23-55-51_06d06940cb84/events.out.tfevents.1792022151.06d06940cb84.18156.0 | Other | 666.8 KB | 8d8947ce5aaa |
| fft/fastdp/smollm-1.7b_eps16.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 697 B | — |
| fft/fastdp/smollm-1.7b_eps16.0_lr5e-5_ep3_bs8_seq4096/runs/Oct14_19-53-54_06d06940cb84/events.out.tfevents.1792007634.06d06940cb84.17871.0 | Other | 666.8 KB | b85c10200af9 |
| fft/fastdp/smollm-1.7b_eps2.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 694 B | — |
| fft/fastdp/smollm-1.7b_eps2.0_lr5e-5_ep3_bs8_seq4096/runs/Oct14_17-29-10_06d06940cb84/events.out.tfevents.1791998950.06d06940cb84.17735.0 | Other | 666.8 KB | 2bf913723693 |
| fft/fastdp/smollm-1.7b_eps32.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 697 B | — |
| fft/fastdp/smollm-1.7b_eps32.0_lr5e-5_ep3_bs8_seq4096/runs/Oct14_20-42-12_06d06940cb84/events.out.tfevents.1792010532.06d06940cb84.17916.0 | Other | 666.8 KB | c5da2a095bde |
| fft/fastdp/smollm-1.7b_eps4.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 694 B | — |
| fft/fastdp/smollm-1.7b_eps4.0_lr5e-5_ep3_bs8_seq4096/runs/Oct14_18-17-16_06d06940cb84/events.out.tfevents.1792001836.06d06940cb84.17781.0 | Other | 666.8 KB | 8291cc665000 |
| fft/fastdp/smollm-1.7b_eps500.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 696 B | — |
| fft/fastdp/smollm-1.7b_eps500.0_lr5e-5_ep3_bs8_seq4096/runs/Oct14_23-07-15_06d06940cb84/events.out.tfevents.1792019235.06d06940cb84.18051.0 | Other | 666.8 KB | be9b92342659 |
| fft/fastdp/smollm-1.7b_eps64.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 697 B | — |
| fft/fastdp/smollm-1.7b_eps64.0_lr5e-5_ep3_bs8_seq4096/runs/Oct14_21-30-36_06d06940cb84/events.out.tfevents.1792013436.06d06940cb84.17961.0 | Other | 666.8 KB | f34873322c46 |
| fft/fastdp/smollm-1.7b_eps8.0_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 694 B | — |
| fft/fastdp/smollm-1.7b_eps8.0_lr5e-5_ep3_bs8_seq4096/runs/Oct14_19-05-36_06d06940cb84/events.out.tfevents.1792004736.06d06940cb84.17826.0 | Other | 666.8 KB | 305c57aa883e |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/loss_scores.log | Other | 961 B | — |
| fft/nodp/llama-3.2-1b_lr1e-5_ep3/runs/Sep09_21-14-25_a5058d49a437/events.out.tfevents.1788988465.a5058d49a437.1312458.0 | Other | 671.3 KB | c8ad57063a28 |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/loss_scores.log | Other | 849 B | — |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3/runs/Sep09_21-51-52_a5058d49a437/events.out.tfevents.1788990712.a5058d49a437.1348280.0 | Other | 403.7 KB | 3fc673e052cb |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 628 B | — |
| fft/nodp/llama-3.2-1b_lr5e-5_ep3_bs8_seq4096/runs/Oct10_14-17-14_06d06940cb84/events.out.tfevents.1791641834.06d06940cb84.7511.0 | Other | 666.9 KB | d802e14ea6b3 |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/loss_scores.log | Other | 961 B | — |
| fft/nodp/llama-3.2-3b_lr1e-5_ep3/runs/Sep09_22-15-56_a5058d49a437/events.out.tfevents.1788992156.a5058d49a437.1371589.0 | Other | 671.3 KB | 325f6848bea4 |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/loss_scores.log | Other | 851 B | — |
| fft/nodp/llama-3.2-3b_lr5e-5_ep3/runs/Sep09_23-37-06_a5058d49a437/events.out.tfevents.1788997026.a5058d49a437.1449203.0 | Other | 403.7 KB | c1d47b0da271 |
| fft/nodp/qwen2.5-0.5b_lr5e-5_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| fft/nodp/qwen2.5-0.5b_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 622 B | — |
| fft/nodp/qwen2.5-0.5b_lr5e-5_ep3_bs8_seq4096/runs/Oct10_00-50-03_06d06940cb84/events.out.tfevents.1791593403.06d06940cb84.5985.0 | Other | 667.3 KB | bf068f2cda90 |
| fft/nodp/qwen2.5-1.5b_lr5e-5_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| fft/nodp/qwen2.5-1.5b_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 622 B | — |
| fft/nodp/qwen2.5-1.5b_lr5e-5_ep3_bs8_seq4096/runs/Oct13_14-12-12_06d06940cb84/events.out.tfevents.1791900732.06d06940cb84.12901.0 | Other | 667.4 KB | 506b6e0794ee |
| fft/nodp/smollm-1.7b_lr5e-5_ep3_bs8_seq4096/loss_scores.log | Other | 629 B | — |
| fft/nodp/smollm-1.7b_lr5e-5_ep3_bs8_seq4096/runs/Oct14_14-34-39_06d06940cb84/events.out.tfevents.1791988479.06d06940cb84.17490.0 | Other | 666.8 KB | 83507941ca49 |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/loss_scores.log | Other | 1.1 KB | — |
| lora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/runs/Sep13_03-33-54_a5058d49a437/events.out.tfevents.1789270434.a5058d49a437.1632309.0 | Other | 671.3 KB | 4f5feb709224 |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/loss_scores.log | Other | 923 B | — |
| lora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/runs/Sep13_03-12-15_a5058d49a437/events.out.tfevents.1789269135.a5058d49a437.1611284.0 | Other | 270.7 KB | 4ef2fee7c097 |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/loss_scores.log | Other | 919 B | — |
| lora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/runs/Sep13_10-37-46_a5058d49a437/events.out.tfevents.1789295866.a5058d49a437.2038158.0 | Other | 270.7 KB | 55745098391e |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/loss_scores.log | Other | 1.1 KB | — |
| lora/dp/llama-3.2-3b_r4_a8_lr5e-4_ep3/runs/Sep13_12-02-45_a5058d49a437/events.out.tfevents.1789300965.a5058d49a437.2119524.0 | Other | 671.3 KB | e3a646d2822e |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/loss_scores.log | Other | 922 B | — |
| lora/dp/llama-3.2-3b_r64_a128_lr5e-4_ep3/runs/Sep13_11-19-27_a5058d49a437/events.out.tfevents.1789298367.a5058d49a437.2078051.0 | Other | 270.7 KB | bd03fd7c42c8 |
| lora/fastdp/llama-3.2-1b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 784 B | — |
| lora/fastdp/llama-3.2-1b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct10_08-23-39_06d06940cb84/events.out.tfevents.1791620619.06d06940cb84.6738.0 | Other | 666.9 KB | 8942d47af451 |
| lora/fastdp/llama-3.2-1b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 784 B | — |
| lora/fastdp/llama-3.2-1b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct10_08-52-57_06d06940cb84/events.out.tfevents.1791622377.06d06940cb84.6802.0 | Other | 666.9 KB | 7e7feda2c101 |
| lora/fastdp/llama-3.2-1b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 784 B | — |
| lora/fastdp/llama-3.2-1b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct10_09-22-24_06d06940cb84/events.out.tfevents.1791624144.06d06940cb84.6867.0 | Other | 666.9 KB | 720940dd63dd |
| lora/fastdp/llama-3.2-1b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 786 B | — |
| lora/fastdp/llama-3.2-1b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct10_12-48-43_06d06940cb84/events.out.tfevents.1791636523.06d06940cb84.7314.0 | Other | 666.9 KB | 20008d9de01d |
| lora/fastdp/llama-3.2-1b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 787 B | — |
| lora/fastdp/llama-3.2-1b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct10_13-47-34_06d06940cb84/events.out.tfevents.1791640054.06d06940cb84.7443.0 | Other | 666.9 KB | 1aa8eb322dd7 |
| lora/fastdp/llama-3.2-1b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 787 B | — |
| lora/fastdp/llama-3.2-1b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct10_11-19-57_06d06940cb84/events.out.tfevents.1791631197.06d06940cb84.7123.0 | Other | 666.9 KB | 374fe3a3e6d2 |
| lora/fastdp/llama-3.2-1b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 784 B | — |
| lora/fastdp/llama-3.2-1b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct10_09-51-47_06d06940cb84/events.out.tfevents.1791625907.06d06940cb84.6932.0 | Other | 666.9 KB | 70f266282a59 |
| lora/fastdp/llama-3.2-1b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 787 B | — |
| lora/fastdp/llama-3.2-1b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct10_11-49-26_06d06940cb84/events.out.tfevents.1791632966.06d06940cb84.7186.0 | Other | 666.9 KB | ce36bccfee40 |
| lora/fastdp/llama-3.2-1b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 784 B | — |
| lora/fastdp/llama-3.2-1b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct10_10-21-09_06d06940cb84/events.out.tfevents.1791627669.06d06940cb84.6995.0 | Other | 666.9 KB | a69b7b87db76 |
| lora/fastdp/llama-3.2-1b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 786 B | — |
| lora/fastdp/llama-3.2-1b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct10_13-18-08_06d06940cb84/events.out.tfevents.1791638288.06d06940cb84.7379.0 | Other | 666.9 KB | bda71e9242f8 |
| lora/fastdp/llama-3.2-1b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 787 B | — |
| lora/fastdp/llama-3.2-1b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct10_12-18-51_06d06940cb84/events.out.tfevents.1791634731.06d06940cb84.7250.0 | Other | 666.9 KB | a83eb7e7b434 |
| lora/fastdp/llama-3.2-1b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 784 B | — |
| lora/fastdp/llama-3.2-1b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct10_10-50-35_06d06940cb84/events.out.tfevents.1791629435.06d06940cb84.7059.0 | Other | 666.9 KB | 0deafd537458 |
| lora/fastdp/qwen2.5-0.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 778 B | — |
| lora/fastdp/qwen2.5-0.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_18-00-56_06d06940cb84/events.out.tfevents.1791568856.06d06940cb84.5212.0 | Other | 667.4 KB | b1ac664576db |
| lora/fastdp/qwen2.5-0.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 778 B | — |
| lora/fastdp/qwen2.5-0.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_18-34-46_06d06940cb84/events.out.tfevents.1791570886.06d06940cb84.5277.0 | Other | 667.4 KB | 5583645c7d8a |
| lora/fastdp/qwen2.5-0.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 778 B | — |
| lora/fastdp/qwen2.5-0.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_19-08-33_06d06940cb84/events.out.tfevents.1791572913.06d06940cb84.5340.0 | Other | 667.4 KB | 0b38c2695f8e |
| lora/fastdp/qwen2.5-0.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 780 B | — |
| lora/fastdp/qwen2.5-0.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_23-07-24_06d06940cb84/events.out.tfevents.1791587244.06d06940cb84.5790.0 | Other | 667.4 KB | 12a2acf21a80 |
| lora/fastdp/qwen2.5-0.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 781 B | — |
| lora/fastdp/qwen2.5-0.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct10_00-15-38_06d06940cb84/events.out.tfevents.1791591338.06d06940cb84.5918.0 | Other | 667.4 KB | 79828b5f84f9 |
| lora/fastdp/qwen2.5-0.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 781 B | — |
| lora/fastdp/qwen2.5-0.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_21-24-46_06d06940cb84/events.out.tfevents.1791581086.06d06940cb84.5598.0 | Other | 667.4 KB | 4f7fd60d5444 |
| lora/fastdp/qwen2.5-0.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 778 B | — |
| lora/fastdp/qwen2.5-0.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_19-42-26_06d06940cb84/events.out.tfevents.1791574946.06d06940cb84.5406.0 | Other | 667.4 KB | e0d7a4e7e8f9 |
| lora/fastdp/qwen2.5-0.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 781 B | — |
| lora/fastdp/qwen2.5-0.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_21-59-15_06d06940cb84/events.out.tfevents.1791583155.06d06940cb84.5662.0 | Other | 667.4 KB | bd4fb2c3bccf |
| lora/fastdp/qwen2.5-0.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 778 B | — |
| lora/fastdp/qwen2.5-0.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_20-16-25_06d06940cb84/events.out.tfevents.1791576985.06d06940cb84.5470.0 | Other | 667.4 KB | 34ccc4d0e1b7 |
| lora/fastdp/qwen2.5-0.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 780 B | — |
| lora/fastdp/qwen2.5-0.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_23-41-30_06d06940cb84/events.out.tfevents.1791589290.06d06940cb84.5853.0 | Other | 667.4 KB | 1da09bc498fe |
| lora/fastdp/qwen2.5-0.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 781 B | — |
| lora/fastdp/qwen2.5-0.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_22-33-16_06d06940cb84/events.out.tfevents.1791585196.06d06940cb84.5726.0 | Other | 667.4 KB | df0302a15e6d |
| lora/fastdp/qwen2.5-0.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-0.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 778 B | — |
| lora/fastdp/qwen2.5-0.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_20-50-20_06d06940cb84/events.out.tfevents.1791579020.06d06940cb84.5534.0 | Other | 667.4 KB | 5b1c93c001d9 |
| lora/fastdp/qwen2.5-1.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 778 B | — |
| lora/fastdp/qwen2.5-1.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_05-10-56_06d06940cb84/events.out.tfevents.1791868256.06d06940cb84.12138.0 | Other | 667.4 KB | 90e7f27f3d44 |
| lora/fastdp/qwen2.5-1.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 778 B | — |
| lora/fastdp/qwen2.5-1.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_05-56-03_06d06940cb84/events.out.tfevents.1791870963.06d06940cb84.12202.0 | Other | 667.4 KB | 088a63dd459d |
| lora/fastdp/qwen2.5-1.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 778 B | — |
| lora/fastdp/qwen2.5-1.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_06-40-59_06d06940cb84/events.out.tfevents.1791873659.06d06940cb84.12265.0 | Other | 667.4 KB | 32ba553770a5 |
| lora/fastdp/qwen2.5-1.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 780 B | — |
| lora/fastdp/qwen2.5-1.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_11-56-51_06d06940cb84/events.out.tfevents.1791892611.06d06940cb84.12710.0 | Other | 667.4 KB | 2e39cf240ac8 |
| lora/fastdp/qwen2.5-1.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 781 B | — |
| lora/fastdp/qwen2.5-1.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_13-26-54_06d06940cb84/events.out.tfevents.1791898014.06d06940cb84.12837.0 | Other | 667.4 KB | 3fa7c3212e98 |
| lora/fastdp/qwen2.5-1.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 781 B | — |
| lora/fastdp/qwen2.5-1.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_09-41-35_06d06940cb84/events.out.tfevents.1791884495.06d06940cb84.12518.0 | Other | 667.4 KB | 65b1cfcb04c7 |
| lora/fastdp/qwen2.5-1.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 778 B | — |
| lora/fastdp/qwen2.5-1.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_07-26-05_06d06940cb84/events.out.tfevents.1791876365.06d06940cb84.12328.0 | Other | 667.4 KB | c900d0db688b |
| lora/fastdp/qwen2.5-1.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 781 B | — |
| lora/fastdp/qwen2.5-1.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_10-26-42_06d06940cb84/events.out.tfevents.1791887202.06d06940cb84.12581.0 | Other | 667.4 KB | 36bbdd9309c7 |
| lora/fastdp/qwen2.5-1.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 778 B | — |
| lora/fastdp/qwen2.5-1.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_08-11-13_06d06940cb84/events.out.tfevents.1791879073.06d06940cb84.12391.0 | Other | 667.4 KB | 8ad1df064751 |
| lora/fastdp/qwen2.5-1.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 780 B | — |
| lora/fastdp/qwen2.5-1.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_12-41-53_06d06940cb84/events.out.tfevents.1791895313.06d06940cb84.12774.0 | Other | 667.4 KB | 2738d2c71ef2 |
| lora/fastdp/qwen2.5-1.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 781 B | — |
| lora/fastdp/qwen2.5-1.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_11-11-43_06d06940cb84/events.out.tfevents.1791889903.06d06940cb84.12645.0 | Other | 667.4 KB | f62b90f36fec |
| lora/fastdp/qwen2.5-1.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/fastdp/qwen2.5-1.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 778 B | — |
| lora/fastdp/qwen2.5-1.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_08-56-28_06d06940cb84/events.out.tfevents.1791881788.06d06940cb84.12455.0 | Other | 667.4 KB | 9dcdadbf8bda |
| lora/fastdp/smollm-1.7b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 785 B | — |
| lora/fastdp/smollm-1.7b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct14_06-21-41_06d06940cb84/events.out.tfevents.1791958901.06d06940cb84.15156.0 | Other | 666.8 KB | 7a5da471a90f |
| lora/fastdp/smollm-1.7b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 785 B | — |
| lora/fastdp/smollm-1.7b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct14_07-02-34_06d06940cb84/events.out.tfevents.1791961354.06d06940cb84.15274.0 | Other | 666.8 KB | a4826e8f9fb4 |
| lora/fastdp/smollm-1.7b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 785 B | — |
| lora/fastdp/smollm-1.7b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct14_07-43-30_06d06940cb84/events.out.tfevents.1791963810.06d06940cb84.15393.0 | Other | 666.8 KB | d295d9e54d56 |
| lora/fastdp/smollm-1.7b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 787 B | — |
| lora/fastdp/smollm-1.7b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct14_12-30-33_06d06940cb84/events.out.tfevents.1791981033.06d06940cb84.16844.0 | Other | 666.8 KB | 70508ef8e2a9 |
| lora/fastdp/smollm-1.7b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 788 B | — |
| lora/fastdp/smollm-1.7b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct14_13-53-33_06d06940cb84/events.out.tfevents.1791986013.06d06940cb84.17372.0 | Other | 666.8 KB | 40d35929b0b7 |
| lora/fastdp/smollm-1.7b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 788 B | — |
| lora/fastdp/smollm-1.7b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct14_10-26-57_06d06940cb84/events.out.tfevents.1791973617.06d06940cb84.15866.0 | Other | 666.8 KB | 48e9f0e534d2 |
| lora/fastdp/smollm-1.7b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 785 B | — |
| lora/fastdp/smollm-1.7b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct14_08-24-19_06d06940cb84/events.out.tfevents.1791966259.06d06940cb84.15511.0 | Other | 666.8 KB | 884d773913a7 |
| lora/fastdp/smollm-1.7b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 788 B | — |
| lora/fastdp/smollm-1.7b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct14_11-07-54_06d06940cb84/events.out.tfevents.1791976074.06d06940cb84.15984.0 | Other | 666.8 KB | da663c578a74 |
| lora/fastdp/smollm-1.7b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 785 B | — |
| lora/fastdp/smollm-1.7b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct14_09-05-13_06d06940cb84/events.out.tfevents.1791968713.06d06940cb84.15630.0 | Other | 666.8 KB | 42aac581da6b |
| lora/fastdp/smollm-1.7b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 787 B | — |
| lora/fastdp/smollm-1.7b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct14_13-12-42_06d06940cb84/events.out.tfevents.1791983562.06d06940cb84.17254.0 | Other | 666.8 KB | 97e1c0bef8d7 |
| lora/fastdp/smollm-1.7b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 788 B | — |
| lora/fastdp/smollm-1.7b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct14_11-48-42_06d06940cb84/events.out.tfevents.1791978522.06d06940cb84.16102.0 | Other | 666.8 KB | b95f1d92d94f |
| lora/fastdp/smollm-1.7b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 785 B | — |
| lora/fastdp/smollm-1.7b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct14_09-46-04_06d06940cb84/events.out.tfevents.1791971164.06d06940cb84.15748.0 | Other | 666.8 KB | 8dd53015258b |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/loss_scores.log | Other | 1.0 KB | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/runs/Sep11_08-26-55_a5058d49a437/events.out.tfevents.1789115215.a5058d49a437.3331035.0 | Other | 603.3 KB | b9a38b464544 |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/loss_scores.log | Other | 1.0 KB | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/runs/Sep11_03-24-11_a5058d49a437/events.out.tfevents.1789097051.a5058d49a437.3042645.0 | Other | 671.3 KB | aec6b7a0f813 |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/loss_scores.log | Other | 1.0 KB | — |
| lora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/runs/Sep11_05-56-31_a5058d49a437/events.out.tfevents.1789106191.a5058d49a437.3187786.0 | Other | 603.3 KB | dcef6fa787cb |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/loss_scores.log | Other | 1.0 KB | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/runs/Sep11_07-37-52_a5058d49a437/events.out.tfevents.1789112272.a5058d49a437.3284347.0 | Other | 603.3 KB | 936d9d2ef1bb |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/loss_scores.log | Other | 1.0 KB | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/runs/Sep11_02-30-22_a5058d49a437/events.out.tfevents.1789093822.a5058d49a437.2991221.0 | Other | 671.3 KB | a70e77e4cc62 |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/loss_scores.log | Other | 1.0 KB | — |
| lora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/runs/Sep11_05-08-05_a5058d49a437/events.out.tfevents.1789103285.a5058d49a437.3141665.0 | Other | 603.3 KB | 4cccaee9ed08 |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/loss_scores.log | Other | 1.0 KB | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/runs/Sep11_09-16-31_a5058d49a437/events.out.tfevents.1789118191.a5058d49a437.3378164.0 | Other | 603.3 KB | 1594ca0f6b37 |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/loss_scores.log | Other | 1.0 KB | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/runs/Sep11_04-16-44_a5058d49a437/events.out.tfevents.1789100204.a5058d49a437.3092699.0 | Other | 603.3 KB | a611971114c9 |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/loss_scores.log | Other | 1.0 KB | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/runs/Sep11_06-46-19_a5058d49a437/events.out.tfevents.1789109179.a5058d49a437.3235236.0 | Other | 603.3 KB | e90cbaa2a775 |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 695 B | — |
| lora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct10_07-54-17_06d06940cb84/events.out.tfevents.1791618857.06d06940cb84.6657.0 | Other | 666.9 KB | c19c45dcca34 |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/loss_scores.log | Other | 1.0 KB | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/runs/Sep11_18-21-11_a5058d49a437/events.out.tfevents.1789150871.a5058d49a437.3911654.0 | Other | 603.3 KB | d8463e949e09 |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/loss_scores.log | Other | 1.0 KB | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/runs/Sep11_11-43-56_a5058d49a437/events.out.tfevents.1789127036.a5058d49a437.3518415.0 | Other | 603.3 KB | ee3ac97df739 |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/loss_scores.log | Other | 930 B | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/runs/Sep11_15-41-04_a5058d49a437/events.out.tfevents.1789141264.a5058d49a437.3753772.0 | Other | 403.7 KB | ce3a1dd6f2df |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 694 B | — |
| lora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3_bs8_seq4096/runs/Oct11_16-12-39_06d06940cb84/events.out.tfevents.1791735159.06d06940cb84.9165.0 | Other | 666.9 KB | a7c1764f0c49 |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/loss_scores.log | Other | 924 B | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/runs/Sep11_17-29-08_a5058d49a437/events.out.tfevents.1789147748.a5058d49a437.3860295.0 | Other | 403.7 KB | a74ed547b22c |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/loss_scores.log | Other | 1.0 KB | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/runs/Sep11_10-09-05_a5058d49a437/events.out.tfevents.1789121345.a5058d49a437.3428178.0 | Other | 671.3 KB | 1a79f19b9fad |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/loss_scores.log | Other | 1.0 KB | — |
| lora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/runs/Sep11_14-24-49_a5058d49a437/events.out.tfevents.1789136689.a5058d49a437.3678483.0 | Other | 603.3 KB | dda90fc01f2e |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/loss_scores.log | Other | 863 B | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/runs/Sep11_19-37-48_a5058d49a437/events.out.tfevents.1789155468.a5058d49a437.3987280.0 | Other | 270.7 KB | 868aab151e50 |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/loss_scores.log | Other | 1.0 KB | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/runs/Sep11_13-04-10_a5058d49a437/events.out.tfevents.1789131850.a5058d49a437.3599001.0 | Other | 603.3 KB | 07701fe8e997 |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/loss_scores.log | Other | 933 B | — |
| lora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/runs/Sep11_16-33-35_a5058d49a437/events.out.tfevents.1789144415.a5058d49a437.3805584.0 | Other | 403.7 KB | d2b2764a7ca7 |
| lora/nodp/qwen2.5-0.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/nodp/qwen2.5-0.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 689 B | — |
| lora/nodp/qwen2.5-0.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_17-25-03_06d06940cb84/events.out.tfevents.1791566703.06d06940cb84.5079.0 | Other | 667.4 KB | f57f7ca31045 |
| lora/nodp/qwen2.5-1.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| lora/nodp/qwen2.5-1.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 689 B | — |
| lora/nodp/qwen2.5-1.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_04-23-21_06d06940cb84/events.out.tfevents.1791865401.06d06940cb84.12074.0 | Other | 667.4 KB | 9f28778f51e3 |
| lora/nodp/smollm-1.7b_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 696 B | — |
| lora/nodp/smollm-1.7b_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct14_05-40-53_06d06940cb84/events.out.tfevents.1791956453.06d06940cb84.15019.0 | Other | 666.8 KB | c1f5b7de89c1 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/loss_scores.log | Other | 954 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps16.0_lr1e-3_ep3/runs/Sep17_18-40-17_a5058d49a437/events.out.tfevents.1789670417.a5058d49a437.3813481.0 | Other | 271.2 KB | 868eeafbf2e8 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/loss_scores.log | Other | 952 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps2.0_lr1e-3_ep3/runs/Sep17_16-56-13_a5058d49a437/events.out.tfevents.1789664173.a5058d49a437.3713472.0 | Other | 271.2 KB | fc68337cdc0e |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/loss_scores.log | Other | 950 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps32.0_lr1e-3_ep3/runs/Sep17_19-32-13_a5058d49a437/events.out.tfevents.1789673533.a5058d49a437.3863225.0 | Other | 271.2 KB | c1fd0e0cfe22 |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/loss_scores.log | Other | 952 B | — |
| pilot_epsilon/llama-3.2-3b_r16_a32_eps4.0_lr1e-3_ep3/runs/Sep17_17-48-35_a5058d49a437/events.out.tfevents.1789667315.a5058d49a437.3764010.0 | Other | 271.2 KB | df4234b1192d |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/loss_scores.log | Other | 955 B | — |
| pilot_sigma/llama-3.2-3b_r16_a32_sigma0.15_lr1e-3_ep3/runs/Sep17_15-35-34_a5058d49a437/events.out.tfevents.1789659334.a5058d49a437.3635988.0 | Other | 271.2 KB | 470e18c1de98 |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/loss_scores.log | Other | 1.1 KB | — |
| qlora/dp/llama-3.2-1b_r4_a8_lr1e-4_ep3/runs/Sep13_08-35-29_a5058d49a437/events.out.tfevents.1789288529.a5058d49a437.1920894.0 | Other | 671.8 KB | e67c37b0f494 |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/loss_scores.log | Other | 924 B | — |
| qlora/dp/llama-3.2-1b_r64_a128_lr5e-4_ep3/runs/Sep13_05-10-27_a5058d49a437/events.out.tfevents.1789276227.a5058d49a437.1724679.0 | Other | 271.1 KB | 01f2e5759902 |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/loss_scores.log | Other | 916 B | — |
| qlora/dp/llama-3.2-3b_r16_a32_lr1e-3_ep3/runs/Sep13_05-41-05_a5058d49a437/events.out.tfevents.1789278065.a5058d49a437.1754033.0 | Other | 271.1 KB | b9b539a60185 |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/loss_scores.log | Other | 1.1 KB | — |
| qlora/dp/llama-3.2-3b_r4_a8_lr1e-3_ep3/runs/Sep13_06-34-08_a5058d49a437/events.out.tfevents.1789281248.a5058d49a437.1804821.0 | Other | 671.8 KB | 2db13b8cd920 |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/loss_scores.log | Other | 924 B | — |
| qlora/dp/llama-3.2-3b_r64_a128_lr1e-3_ep3/runs/Sep13_04-15-22_a5058d49a437/events.out.tfevents.1789272922.a5058d49a437.1671971.0 | Other | 271.1 KB | 127ea98b9e91 |
| qlora/fastdp/llama-3.2-3b_eps0.1_r16_a32_lr1e-3_ep3_bs8_seq4096/loss_scores.log | Other | 783 B | — |
| qlora/fastdp/llama-3.2-3b_eps0.1_r16_a32_lr1e-3_ep3_bs8_seq4096/runs/Oct10_23-14-38_06d06940cb84/events.out.tfevents.1791674078.06d06940cb84.8280.0 | Other | 667.4 KB | 814b02a37b51 |
| qlora/fastdp/llama-3.2-3b_eps0.5_r16_a32_lr1e-3_ep3_bs8_seq4096/loss_scores.log | Other | 783 B | — |
| qlora/fastdp/llama-3.2-3b_eps0.5_r16_a32_lr1e-3_ep3_bs8_seq4096/runs/Oct11_00-39-26_06d06940cb84/events.out.tfevents.1791679166.06d06940cb84.8359.0 | Other | 667.4 KB | 57283190632e |
| qlora/fastdp/llama-3.2-3b_eps1.0_r16_a32_lr1e-3_ep3_bs8_seq4096/loss_scores.log | Other | 783 B | — |
| qlora/fastdp/llama-3.2-3b_eps1.0_r16_a32_lr1e-3_ep3_bs8_seq4096/runs/Oct11_02-04-15_06d06940cb84/events.out.tfevents.1791684255.06d06940cb84.8423.0 | Other | 667.4 KB | c01f43066b76 |
| qlora/fastdp/llama-3.2-3b_eps100.0_r16_a32_lr1e-3_ep3_bs8_seq4096/loss_scores.log | Other | 785 B | — |
| qlora/fastdp/llama-3.2-3b_eps100.0_r16_a32_lr1e-3_ep3_bs8_seq4096/runs/Oct11_11-57-22_06d06940cb84/events.out.tfevents.1791719842.06d06940cb84.8874.0 | Other | 667.4 KB | 837a19f43a58 |
| qlora/fastdp/llama-3.2-3b_eps1000.0_r16_a32_lr1e-3_ep3_bs8_seq4096/loss_scores.log | Other | 786 B | — |
| qlora/fastdp/llama-3.2-3b_eps1000.0_r16_a32_lr1e-3_ep3_bs8_seq4096/runs/Oct11_14-48-00_06d06940cb84/events.out.tfevents.1791730080.06d06940cb84.9098.0 | Other | 667.4 KB | 7b6d114be787 |
| qlora/fastdp/llama-3.2-3b_eps16.0_r16_a32_lr1e-3_ep3_bs8_seq4096/loss_scores.log | Other | 786 B | — |
| qlora/fastdp/llama-3.2-3b_eps16.0_r16_a32_lr1e-3_ep3_bs8_seq4096/runs/Oct11_07-42-57_06d06940cb84/events.out.tfevents.1791704577.06d06940cb84.8683.0 | Other | 667.4 KB | a91cf3d9782d |
| qlora/fastdp/llama-3.2-3b_eps2.0_r16_a32_lr1e-3_ep3_bs8_seq4096/loss_scores.log | Other | 783 B | — |
| qlora/fastdp/llama-3.2-3b_eps2.0_r16_a32_lr1e-3_ep3_bs8_seq4096/runs/Oct11_03-28-56_06d06940cb84/events.out.tfevents.1791689336.06d06940cb84.8487.0 | Other | 667.4 KB | b82d3014bb6a |
| qlora/fastdp/llama-3.2-3b_eps32.0_r16_a32_lr1e-3_ep3_bs8_seq4096/loss_scores.log | Other | 786 B | — |
| qlora/fastdp/llama-3.2-3b_eps32.0_r16_a32_lr1e-3_ep3_bs8_seq4096/runs/Oct11_09-07-46_06d06940cb84/events.out.tfevents.1791709666.06d06940cb84.8747.0 | Other | 667.4 KB | a6e0da3c2589 |
| qlora/fastdp/llama-3.2-3b_eps4.0_r16_a32_lr1e-3_ep3_bs8_seq4096/loss_scores.log | Other | 783 B | — |
| qlora/fastdp/llama-3.2-3b_eps4.0_r16_a32_lr1e-3_ep3_bs8_seq4096/runs/Oct11_04-53-45_06d06940cb84/events.out.tfevents.1791694425.06d06940cb84.8551.0 | Other | 667.4 KB | 730f74124c02 |
| qlora/fastdp/llama-3.2-3b_eps500.0_r16_a32_lr1e-3_ep3_bs8_seq4096/loss_scores.log | Other | 785 B | — |
| qlora/fastdp/llama-3.2-3b_eps500.0_r16_a32_lr1e-3_ep3_bs8_seq4096/runs/Oct11_13-22-44_06d06940cb84/events.out.tfevents.1791724964.06d06940cb84.9034.0 | Other | 667.4 KB | e1555276a599 |
| qlora/fastdp/llama-3.2-3b_eps64.0_r16_a32_lr1e-3_ep3_bs8_seq4096/loss_scores.log | Other | 786 B | — |
| qlora/fastdp/llama-3.2-3b_eps64.0_r16_a32_lr1e-3_ep3_bs8_seq4096/runs/Oct11_10-32-29_06d06940cb84/events.out.tfevents.1791714749.06d06940cb84.8811.0 | Other | 667.4 KB | 1c8b6741a8c9 |
| qlora/fastdp/llama-3.2-3b_eps8.0_r16_a32_lr1e-3_ep3_bs8_seq4096/loss_scores.log | Other | 783 B | — |
| qlora/fastdp/llama-3.2-3b_eps8.0_r16_a32_lr1e-3_ep3_bs8_seq4096/runs/Oct11_06-18-30_06d06940cb84/events.out.tfevents.1791699510.06d06940cb84.8618.0 | Other | 667.4 KB | f17a785e4752 |
| qlora/fastdp/qwen2.5-0.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 779 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct08_23-09-20_06d06940cb84/events.out.tfevents.1791500960.06d06940cb84.2611.0 | Other | 667.8 KB | 0414b448ca56 |
| qlora/fastdp/qwen2.5-0.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 779 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_00-07-41_06d06940cb84/events.out.tfevents.1791504461.06d06940cb84.2757.0 | Other | 667.8 KB | 39cf6c8a7859 |
| qlora/fastdp/qwen2.5-0.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 779 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_01-06-04_06d06940cb84/events.out.tfevents.1791507964.06d06940cb84.2908.0 | Other | 667.8 KB | 3ecd6cd07768 |
| qlora/fastdp/qwen2.5-0.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 781 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_09-58-05_06d06940cb84/events.out.tfevents.1791539885.06d06940cb84.3718.0 | Other | 667.8 KB | 4d6033279e4a |
| qlora/fastdp/qwen2.5-0.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 782 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_11-55-50_06d06940cb84/events.out.tfevents.1791546950.06d06940cb84.3920.0 | Other | 667.8 KB | c20052c6ed3d |
| qlora/fastdp/qwen2.5-0.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 782 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_07-02-19_06d06940cb84/events.out.tfevents.1791529339.06d06940cb84.3418.0 | Other | 667.8 KB | 613aebfe9872 |
| qlora/fastdp/qwen2.5-0.5b_eps16000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps16000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 785 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps16000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_15-48-32_06d06940cb84/events.out.tfevents.1791560912.06d06940cb84.4245.0 | Other | 667.8 KB | 020a1d24103f |
| qlora/fastdp/qwen2.5-0.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 779 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_04-07-29_06d06940cb84/events.out.tfevents.1791518849.06d06940cb84.3118.0 | Other | 667.8 KB | 4a8381cab211 |
| qlora/fastdp/qwen2.5-0.5b_eps2000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps2000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 782 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps2000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_12-54-52_06d06940cb84/events.out.tfevents.1791550492.06d06940cb84.4020.0 | Other | 667.8 KB | 5c1f3ed6ae7d |
| qlora/fastdp/qwen2.5-0.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 782 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_08-00-58_06d06940cb84/events.out.tfevents.1791532858.06d06940cb84.3518.0 | Other | 667.8 KB | dc5d5bdddaac |
| qlora/fastdp/qwen2.5-0.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 779 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_05-05-42_06d06940cb84/events.out.tfevents.1791522342.06d06940cb84.3218.0 | Other | 667.8 KB | b461db330b88 |
| qlora/fastdp/qwen2.5-0.5b_eps4000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps4000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 782 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps4000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_13-52-39_06d06940cb84/events.out.tfevents.1791553959.06d06940cb84.4119.0 | Other | 667.8 KB | f17a268fe455 |
| qlora/fastdp/qwen2.5-0.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 781 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_10-56-19_06d06940cb84/events.out.tfevents.1791543379.06d06940cb84.3818.0 | Other | 667.8 KB | 07388348fa59 |
| qlora/fastdp/qwen2.5-0.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 782 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_08-59-33_06d06940cb84/events.out.tfevents.1791536373.06d06940cb84.3618.0 | Other | 667.8 KB | 8918b3e7c6da |
| qlora/fastdp/qwen2.5-0.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 779 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_06-04-19_06d06940cb84/events.out.tfevents.1791525859.06d06940cb84.3318.0 | Other | 667.8 KB | 47d531b32447 |
| qlora/fastdp/qwen2.5-0.5b_eps8000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-0.5b_eps8000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 782 B | — |
| qlora/fastdp/qwen2.5-0.5b_eps8000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct09_14-50-36_06d06940cb84/events.out.tfevents.1791557436.06d06940cb84.4181.0 | Other | 667.8 KB | 5586c5a9ddf7 |
| qlora/fastdp/qwen2.5-1.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 779 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct12_13-05-05_06d06940cb84/events.out.tfevents.1791810305.06d06940cb84.11292.0 | Other | 667.9 KB | c8163e5d9b76 |
| qlora/fastdp/qwen2.5-1.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 779 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct12_14-21-57_06d06940cb84/events.out.tfevents.1791814917.06d06940cb84.11372.0 | Other | 667.9 KB | 2e29f56ebeaf |
| qlora/fastdp/qwen2.5-1.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 779 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct12_15-38-16_06d06940cb84/events.out.tfevents.1791819496.06d06940cb84.11436.0 | Other | 667.9 KB | 4e507ba69c7e |
| qlora/fastdp/qwen2.5-1.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 781 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_00-33-58_06d06940cb84/events.out.tfevents.1791851638.06d06940cb84.11882.0 | Other | 667.9 KB | 615fc902cd85 |
| qlora/fastdp/qwen2.5-1.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 782 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_03-07-04_06d06940cb84/events.out.tfevents.1791860824.06d06940cb84.12010.0 | Other | 667.9 KB | b804acb4e90f |
| qlora/fastdp/qwen2.5-1.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 782 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct12_20-44-49_06d06940cb84/events.out.tfevents.1791837889.06d06940cb84.11692.0 | Other | 667.9 KB | 027b9a4978f9 |
| qlora/fastdp/qwen2.5-1.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 779 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct12_16-55-05_06d06940cb84/events.out.tfevents.1791824105.06d06940cb84.11500.0 | Other | 667.9 KB | 7a7f222f9801 |
| qlora/fastdp/qwen2.5-1.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 782 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct12_22-01-18_06d06940cb84/events.out.tfevents.1791842478.06d06940cb84.11755.0 | Other | 667.9 KB | 0d82b5b0f8d5 |
| qlora/fastdp/qwen2.5-1.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 779 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct12_18-11-13_06d06940cb84/events.out.tfevents.1791828673.06d06940cb84.11564.0 | Other | 667.9 KB | a907fa4981bb |
| qlora/fastdp/qwen2.5-1.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 781 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_01-50-43_06d06940cb84/events.out.tfevents.1791856243.06d06940cb84.11946.0 | Other | 667.9 KB | 2e0c331c0e47 |
| qlora/fastdp/qwen2.5-1.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 782 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct12_23-17-26_06d06940cb84/events.out.tfevents.1791847046.06d06940cb84.11819.0 | Other | 667.9 KB | d7f7fb29deb8 |
| qlora/fastdp/qwen2.5-1.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/fastdp/qwen2.5-1.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 779 B | — |
| qlora/fastdp/qwen2.5-1.5b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct12_19-28-07_06d06940cb84/events.out.tfevents.1791833287.06d06940cb84.11628.0 | Other | 667.9 KB | 1929a5623576 |
| qlora/fastdp/smollm-1.7b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 786 B | — |
| qlora/fastdp/smollm-1.7b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_15-40-05_06d06940cb84/events.out.tfevents.1791906005.06d06940cb84.13444.0 | Other | 667.3 KB | 7463dcaf07cd |
| qlora/fastdp/smollm-1.7b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 786 B | — |
| qlora/fastdp/smollm-1.7b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_16-50-56_06d06940cb84/events.out.tfevents.1791910256.06d06940cb84.13579.0 | Other | 667.3 KB | 8c0edda20631 |
| qlora/fastdp/smollm-1.7b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 786 B | — |
| qlora/fastdp/smollm-1.7b_eps1.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_18-01-39_06d06940cb84/events.out.tfevents.1791914499.06d06940cb84.13714.0 | Other | 667.3 KB | 19ea3b541805 |
| qlora/fastdp/smollm-1.7b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 788 B | — |
| qlora/fastdp/smollm-1.7b_eps100.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct14_02-13-44_06d06940cb84/events.out.tfevents.1791944024.06d06940cb84.14665.0 | Other | 667.3 KB | 998b058d3261 |
| qlora/fastdp/smollm-1.7b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 789 B | — |
| qlora/fastdp/smollm-1.7b_eps1000.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct14_04-31-39_06d06940cb84/events.out.tfevents.1791952299.06d06940cb84.14901.0 | Other | 667.3 KB | 867e67d43138 |
| qlora/fastdp/smollm-1.7b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 789 B | — |
| qlora/fastdp/smollm-1.7b_eps16.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_22-43-55_06d06940cb84/events.out.tfevents.1791931435.06d06940cb84.14186.0 | Other | 667.3 KB | fa9a69a3c1ba |
| qlora/fastdp/smollm-1.7b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 786 B | — |
| qlora/fastdp/smollm-1.7b_eps2.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_19-12-13_06d06940cb84/events.out.tfevents.1791918733.06d06940cb84.13832.0 | Other | 667.3 KB | 1f4dc4a8e2c8 |
| qlora/fastdp/smollm-1.7b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 789 B | — |
| qlora/fastdp/smollm-1.7b_eps32.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_23-54-00_06d06940cb84/events.out.tfevents.1791935640.06d06940cb84.14304.0 | Other | 667.3 KB | a53ec382f22b |
| qlora/fastdp/smollm-1.7b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 786 B | — |
| qlora/fastdp/smollm-1.7b_eps4.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_20-22-34_06d06940cb84/events.out.tfevents.1791922954.06d06940cb84.13950.0 | Other | 667.3 KB | c28b3d272dc5 |
| qlora/fastdp/smollm-1.7b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 788 B | — |
| qlora/fastdp/smollm-1.7b_eps500.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct14_03-22-43_06d06940cb84/events.out.tfevents.1791948163.06d06940cb84.14783.0 | Other | 667.3 KB | 74b215f568f1 |
| qlora/fastdp/smollm-1.7b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 789 B | — |
| qlora/fastdp/smollm-1.7b_eps64.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct14_01-03-46_06d06940cb84/events.out.tfevents.1791939826.06d06940cb84.14547.0 | Other | 667.3 KB | 619deaecbbbc |
| qlora/fastdp/smollm-1.7b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 786 B | — |
| qlora/fastdp/smollm-1.7b_eps8.0_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_21-33-08_06d06940cb84/events.out.tfevents.1791927188.06d06940cb84.14068.0 | Other | 667.3 KB | d5a214d3dc1d |
| qlora/fastdp/stablelm-2-1.6b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 792 B | — |
| qlora/fastdp/stablelm-2-1.6b_eps0.1_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct15_01-32-20_06d06940cb84/events.out.tfevents.1792027940.06d06940cb84.18363.0 | Other | 667.4 KB | 0c327d81013e |
| qlora/fastdp/stablelm-2-1.6b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 792 B | — |
| qlora/fastdp/stablelm-2-1.6b_eps0.5_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct15_02-37-55_06d06940cb84/events.out.tfevents.1792031875.06d06940cb84.18441.0 | Other | 667.4 KB | a182c12848e1 |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/loss_scores.log | Other | 1.0 KB | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-3_ep3/runs/Sep10_06-42-57_a5058d49a437/events.out.tfevents.1789022577.a5058d49a437.1856809.0 | Other | 603.8 KB | 100ee059738a |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/loss_scores.log | Other | 1.1 KB | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr1e-4_ep3/runs/Sep10_01-52-04_a5058d49a437/events.out.tfevents.1789005124.a5058d49a437.1578890.0 | Other | 671.8 KB | 95128d0ef49e |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/loss_scores.log | Other | 1.0 KB | — |
| qlora/nodp/llama-3.2-1b_r16_a32_lr5e-4_ep3/runs/Sep10_03-11-44_a5058d49a437/events.out.tfevents.1789009904.a5058d49a437.1654550.0 | Other | 603.8 KB | f83aa67ecbf4 |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/loss_scores.log | Other | 1.0 KB | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-3_ep3/runs/Sep10_05-32-44_a5058d49a437/events.out.tfevents.1789018364.a5058d49a437.1789729.0 | Other | 603.8 KB | c330f74ccb8d |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/loss_scores.log | Other | 1.0 KB | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr1e-4_ep3/runs/Sep10_00-34-23_a5058d49a437/events.out.tfevents.1789000463.a5058d49a437.1504643.0 | Other | 671.8 KB | bb65439fcc5d |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/loss_scores.log | Other | 1.0 KB | — |
| qlora/nodp/llama-3.2-1b_r4_a8_lr5e-4_ep3/runs/Sep11_21-23-26_a5058d49a437/events.out.tfevents.1789161806.a5058d49a437.4091646.0 | Other | 603.8 KB | 46c330bf3df4 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/loss_scores.log | Other | 1.0 KB | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-3_ep3/runs/Sep10_07-53-09_a5058d49a437/events.out.tfevents.1789026789.a5058d49a437.1923864.0 | Other | 603.8 KB | 1982e517a764 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/loss_scores.log | Other | 1.0 KB | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr1e-4_ep3/runs/Sep11_20-16-35_a5058d49a437/events.out.tfevents.1789157795.a5058d49a437.4025463.0 | Other | 603.8 KB | f64a93bd99c4 |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/loss_scores.log | Other | 1.0 KB | — |
| qlora/nodp/llama-3.2-1b_r64_a128_lr5e-4_ep3/runs/Sep10_04-21-46_a5058d49a437/events.out.tfevents.1789014106.a5058d49a437.1721920.0 | Other | 603.8 KB | 28f0e5ee79d3 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/loss_scores.log | Other | 1.0 KB | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3/runs/Sep10_22-24-29_a5058d49a437/events.out.tfevents.1789079069.a5058d49a437.2755947.0 | Other | 603.8 KB | 64938ad2e6f4 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3_bs8_seq4096/loss_scores.log | Other | 695 B | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-3_ep3_bs8_seq4096/runs/Oct10_22-08-59_06d06940cb84/events.out.tfevents.1791670139.06d06940cb84.8200.0 | Other | 667.4 KB | 4d33631746d8 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/loss_scores.log | Other | 1.0 KB | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr1e-4_ep3/runs/Sep10_11-19-12_a5058d49a437/events.out.tfevents.1789039152.a5058d49a437.2120665.0 | Other | 671.8 KB | f2a6f2ec5c75 |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/loss_scores.log | Other | 932 B | — |
| qlora/nodp/llama-3.2-3b_r16_a32_lr5e-4_ep3/runs/Sep10_17-36-29_a5058d49a437/events.out.tfevents.1789061789.a5058d49a437.2480973.0 | Other | 404.2 KB | 705baa61601b |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/loss_scores.log | Other | 1.0 KB | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-3_ep3/runs/Sep10_20-21-54_a5058d49a437/events.out.tfevents.1789071714.a5058d49a437.2638965.0 | Other | 603.8 KB | 9e0204445b18 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/loss_scores.log | Other | 1.0 KB | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr1e-4_ep3/runs/Sep10_09-04-17_a5058d49a437/events.out.tfevents.1789031057.a5058d49a437.1991773.0 | Other | 671.8 KB | d3b955f1c281 |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/loss_scores.log | Other | 1.0 KB | — |
| qlora/nodp/llama-3.2-3b_r4_a8_lr5e-4_ep3/runs/Sep10_15-35-03_a5058d49a437/events.out.tfevents.1789054503.a5058d49a437.2365009.0 | Other | 603.8 KB | b149b60029df |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/loss_scores.log | Other | 1.0 KB | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-3_ep3/runs/Sep11_00-25-56_a5058d49a437/events.out.tfevents.1789086356.a5058d49a437.2872002.0 | Other | 603.8 KB | a05885fd6044 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/loss_scores.log | Other | 1.0 KB | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr1e-4_ep3/runs/Sep10_13-33-24_a5058d49a437/events.out.tfevents.1789047204.a5058d49a437.2248823.0 | Other | 603.8 KB | 09a8e8b89997 |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/loss_scores.log | Other | 933 B | — |
| qlora/nodp/llama-3.2-3b_r64_a128_lr5e-4_ep3/runs/Sep10_18-59-13_a5058d49a437/events.out.tfevents.1789066753.a5058d49a437.2560002.0 | Other | 404.2 KB | 96d3876c9bce |
| qlora/nodp/qwen2.5-0.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/nodp/qwen2.5-0.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 691 B | — |
| qlora/nodp/qwen2.5-0.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct08_22-28-40_06d06940cb84/events.out.tfevents.1791498520.06d06940cb84.2467.0 | Other | 667.8 KB | 6d71dc4c6435 |
| qlora/nodp/qwen2.5-1.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/chat_template.jinja | Other | 2.4 KB | — |
| qlora/nodp/qwen2.5-1.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 691 B | — |
| qlora/nodp/qwen2.5-1.5b_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct12_12-10-06_06d06940cb84/events.out.tfevents.1791807006.06d06940cb84.11195.0 | Other | 667.9 KB | 89037c4cc693 |
| qlora/nodp/smollm-1.7b_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 698 B | — |
| qlora/nodp/smollm-1.7b_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct13_14-51-30_06d06940cb84/events.out.tfevents.1791903090.06d06940cb84.13310.0 | Other | 667.2 KB | 2edb32aea532 |
| qlora/nodp/stablelm-2-1.6b_r64_a128_lr5e-4_ep3_bs8_seq4096/loss_scores.log | Other | 704 B | — |
| qlora/nodp/stablelm-2-1.6b_r64_a128_lr5e-4_ep3_bs8_seq4096/runs/Oct15_00-47-26_06d06940cb84/events.out.tfevents.1792025246.06d06940cb84.18284.0 | Other | 667.4 KB | 9d16c90fa9f5 |
| .gitattributes | Repository | 37.1 KB | — |
| Llama-3.2-1B_full_fastdp/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| Llama-3.2-1B_full_fastdp/tokenizer_config.json | Tokenizer | 335 B | — |
| Llama-3.2-1B_full_lr0.001_e3/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| Llama-3.2-1B_full_lr0.001_e3/tokenizer_config.json | Tokenizer | 335 B | — |
| Llama-3.2-1B_full_nodp/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| Llama-3.2-1B_full_nodp/tokenizer_config.json | Tokenizer | 335 B | — |
| Llama-3.2-1B_lora_fastdp/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| Llama-3.2-1B_lora_fastdp/tokenizer_config.json | Tokenizer | 335 B | — |
| Llama-3.2-1B_lora_nodp/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| Llama-3.2-1B_lora_nodp/tokenizer_config.json | Tokenizer | 335 B | — |
| Llama-3.2-1B_lora_r16_a32_lr0.001_e3/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| Llama-3.2-1B_lora_r16_a32_lr0.001_e3/tokenizer_config.json | Tokenizer | 335 B | — |
| Llama-3.2-1B_qlora_fastdp/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| Llama-3.2-1B_qlora_fastdp/tokenizer_config.json | Tokenizer | 335 B | — |
| Llama-3.2-1B_qlora_nodp/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| Llama-3.2-1B_qlora_nodp/tokenizer_config.json | Tokenizer | 335 B | — |
| Llama-3.2-3B_full_lr0.001_e3/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| Llama-3.2-3B_full_lr0.001_e3/tokenizer_config.json | Tokenizer | 335 B | — |
| Llama-3.2-3B_full_nodp/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| Llama-3.2-3B_full_nodp/tokenizer_config.json | Tokenizer | 335 B | — |
| Llama-3.2-3B_lora_nodp/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| Llama-3.2-3B_lora_nodp/tokenizer_config.json | Tokenizer | 335 B | — |
| Llama-3.2-3B_lora_r16_a32_lr0.001_e3/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| Llama-3.2-3B_lora_r16_a32_lr0.001_e3/tokenizer_config.json | Tokenizer | 335 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-173/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-173/tokenizer_config.json | Tokenizer | 335 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-692/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/checkpoint-692/tokenizer_config.json | Tokenizer | 335 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1.6e1)/tokenizer_config.json | Tokenizer | 335 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-173/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-173/tokenizer_config.json | Tokenizer | 335 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-692/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/checkpoint-692/tokenizer_config.json | Tokenizer | 335 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-1)/tokenizer_config.json | Tokenizer | 335 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/checkpoint-173/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/checkpoint-173/tokenizer_config.json | Tokenizer | 335 B | — |
| epsilon_sweep_1b_qlora/llama-3.2-1b_r64_a128_lr5e-4_ep3_eps(1e-2)/checkpoint-692/tokenizer.json | Tokenizer | 17.2 MB | 6b9e4e7fb171 |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 290.7 GB
Download from Ean
Released by Ean through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 290.7 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.