Audio-Text-to-Text
Transformers
TensorBoard
Safetensors
qwen2-audio
audio
dcase
sft
grpo
lora
checkpoints
Instructions to use darkraider42/dcase-paper-checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use darkraider42/dcase-paper-checkpoints with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("darkraider42/dcase-paper-checkpoints", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +46 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1006/adapter_model.safetensors +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1006/optimizer.pt +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1006/rng_state.pth +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1006/scheduler.pt +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1006/tokenizer.json +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1006/training_args.bin +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1509/adapter_model.safetensors +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1509/optimizer.pt +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1509/rng_state.pth +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1509/scheduler.pt +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1509/tokenizer.json +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1509/training_args.bin +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2012/adapter_model.safetensors +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2012/optimizer.pt +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2012/rng_state.pth +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2012/scheduler.pt +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2012/tokenizer.json +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2012/training_args.bin +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2515/adapter_model.safetensors +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2515/optimizer.pt +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2515/rng_state.pth +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2515/scheduler.pt +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2515/tokenizer.json +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2515/training_args.bin +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3018/adapter_model.safetensors +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3018/optimizer.pt +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3018/rng_state.pth +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3018/scheduler.pt +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3018/tokenizer.json +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3018/training_args.bin +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3020/adapter_model.safetensors +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3020/optimizer.pt +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3020/rng_state.pth +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3020/scheduler.pt +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3020/tokenizer.json +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3020/training_args.bin +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-503/adapter_model.safetensors +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-503/optimizer.pt +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-503/rng_state.pth +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-503/scheduler.pt +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-503/tokenizer.json +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-503/training_args.bin +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/final_model/adapter_model.safetensors +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/final_model/tokenizer.json +3 -0
- grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/final_model/training_args.bin +3 -0
- grpo_all_easy_diverse/combined_easy_diverse_grpo_run2-full-e2-bs4-lr5e-07-20250615_144521/checkpoint-1509/adapter_model.safetensors +3 -0
- grpo_all_easy_diverse/combined_easy_diverse_grpo_run2-full-e2-bs4-lr5e-07-20250615_144521/checkpoint-1509/optimizer.pt +3 -0
- grpo_all_easy_diverse/combined_easy_diverse_grpo_run2-full-e2-bs4-lr5e-07-20250615_144521/checkpoint-1509/rng_state.pth +3 -0
- grpo_all_easy_diverse/combined_easy_diverse_grpo_run2-full-e2-bs4-lr5e-07-20250615_144521/checkpoint-1509/scheduler.pt +3 -0
.gitattributes
CHANGED
|
@@ -484,3 +484,49 @@ debug_sft/20250615_102921_sftdebug_sft_grpo_curriculum_pipeline_sft-loraopt-1e-4
|
|
| 484 |
debug_sft/20250615_102921_sftdebug_sft_grpo_curriculum_pipeline_sft-loraopt-1e-4bs-0.0002-clip/checkpoint-88588/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 485 |
debug_sft/20250615_102921_sftdebug_sft_grpo_curriculum_pipeline_sft-loraopt-1e-4bs-0.0002-clip/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 486 |
grpo_all_easy_diverse/combined_easy_diverse_grpo_run2-full-e2-bs4-lr5e-07-20250615_144521/checkpoint-1006/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 484 |
debug_sft/20250615_102921_sftdebug_sft_grpo_curriculum_pipeline_sft-loraopt-1e-4bs-0.0002-clip/checkpoint-88588/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 485 |
debug_sft/20250615_102921_sftdebug_sft_grpo_curriculum_pipeline_sft-loraopt-1e-4bs-0.0002-clip/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 486 |
grpo_all_easy_diverse/combined_easy_diverse_grpo_run2-full-e2-bs4-lr5e-07-20250615_144521/checkpoint-1006/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 487 |
+
grpo_all_easy_diverse/combined_easy_diverse_grpo_run2-full-e2-bs4-lr5e-07-20250615_144521/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 488 |
+
grpo_all_easy_diverse/combined_easy_diverse_grpo_run2-full-e2-bs4-lr5e-07-20250615_144521/checkpoint-1509/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 489 |
+
grpo_all_easy_diverse/combined_easy_diverse_grpo_run2-full-e2-bs4-lr5e-07-20250615_144521/checkpoint-2012/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 490 |
+
grpo_all_easy_diverse/combined_easy_diverse_grpo_run2-full-e2-bs4-lr5e-07-20250615_144521/checkpoint-2515/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 491 |
+
grpo_all_easy_diverse/combined_easy_diverse_grpo_run2-full-e2-bs4-lr5e-07-20250615_144521/checkpoint-3018/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 492 |
+
grpo_all_easy_diverse/combined_easy_diverse_grpo_run2-full-e2-bs4-lr5e-07-20250615_144521/checkpoint-3020/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 493 |
+
grpo_all_easy_diverse/combined_easy_diverse_grpo_run2-full-e2-bs4-lr5e-07-20250615_144521/checkpoint-503/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 494 |
+
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1006/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 495 |
+
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1509/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 496 |
+
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2012/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 497 |
+
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2515/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 498 |
+
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3018/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 499 |
+
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3020/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 500 |
+
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-503/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 501 |
+
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 502 |
+
grpo_all_hard/curriculum_hard_only_grpo_run2-full-e2-bs4-lr5e-07-20250615_175205/checkpoint-1006/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 503 |
+
grpo_all_hard/curriculum_hard_only_grpo_run2-full-e2-bs4-lr5e-07-20250615_175205/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 504 |
+
grpo_all_hard/curriculum_hard_only_grpo_run2-full-e2-bs4-lr5e-07-20250615_175205/checkpoint-1509/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 505 |
+
grpo_all_hard/curriculum_hard_only_grpo_run2-full-e2-bs4-lr5e-07-20250615_175205/checkpoint-2012/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 506 |
+
grpo_all_hard/curriculum_hard_only_grpo_run2-full-e2-bs4-lr5e-07-20250615_175205/checkpoint-2515/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 507 |
+
grpo_all_hard/curriculum_hard_only_grpo_run2-full-e2-bs4-lr5e-07-20250615_175205/checkpoint-3018/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 508 |
+
grpo_all_hard/curriculum_hard_only_grpo_run2-full-e2-bs4-lr5e-07-20250615_175205/checkpoint-3020/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 509 |
+
grpo_all_hard/curriculum_hard_only_grpo_run2-full-e2-bs4-lr5e-07-20250615_175205/checkpoint-503/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 510 |
+
grpo_all_hard_selective/combined_hard_selective_grpo_run2-full-e2-bs4-lr5e-07-20250615_144633/checkpoint-1006/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 511 |
+
grpo_all_hard_selective/combined_hard_selective_grpo_run2-full-e2-bs4-lr5e-07-20250615_144633/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 512 |
+
grpo_all_hard_selective/combined_hard_selective_grpo_run2-full-e2-bs4-lr5e-07-20250615_144633/checkpoint-1509/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 513 |
+
grpo_all_hard_selective/combined_hard_selective_grpo_run2-full-e2-bs4-lr5e-07-20250615_144633/checkpoint-2012/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 514 |
+
grpo_all_hard_selective/combined_hard_selective_grpo_run2-full-e2-bs4-lr5e-07-20250615_144633/checkpoint-2515/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 515 |
+
grpo_all_hard_selective/combined_hard_selective_grpo_run2-full-e2-bs4-lr5e-07-20250615_144633/checkpoint-3018/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 516 |
+
grpo_all_hard_selective/combined_hard_selective_grpo_run2-full-e2-bs4-lr5e-07-20250615_144633/checkpoint-3020/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 517 |
+
grpo_all_hard_selective/combined_hard_selective_grpo_run2-full-e2-bs4-lr5e-07-20250615_144633/checkpoint-503/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 518 |
+
grpo_easy/sft_grpo_curriculum_pipeline_grpo_run1-full-e1-bs4-lr1e-06-20250614_115726/checkpoint-1338/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 519 |
+
grpo_easy/sft_grpo_curriculum_pipeline_grpo_run1-full-e1-bs4-lr1e-06-20250614_115726/checkpoint-2007/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 520 |
+
grpo_easy/sft_grpo_curriculum_pipeline_grpo_run1-full-e1-bs4-lr1e-06-20250614_115726/checkpoint-2009/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 521 |
+
grpo_easy/sft_grpo_curriculum_pipeline_grpo_run1-full-e1-bs4-lr1e-06-20250614_115726/checkpoint-669/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 522 |
+
grpo_easy/sft_grpo_curriculum_pipeline_grpo_run1-full-e1-bs4-lr1e-06-20250614_115726/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 523 |
+
grpo_easy/sft_grpo_curriculum_pipeline_grpo_run1-full-e1-bs4-lr1e-06-20250614_140857/checkpoint-1338/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 524 |
+
grpo_easy/sft_grpo_curriculum_pipeline_grpo_run1-full-e1-bs4-lr1e-06-20250614_140857/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 525 |
+
grpo_easy/sft_grpo_curriculum_pipeline_grpo_run1-full-e1-bs4-lr1e-06-20250614_140857/checkpoint-2007/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 526 |
+
grpo_easy/sft_grpo_curriculum_pipeline_grpo_run1-full-e1-bs4-lr1e-06-20250614_140857/checkpoint-2009/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 527 |
+
grpo_easy/sft_grpo_curriculum_pipeline_grpo_run1-full-e1-bs4-lr1e-06-20250614_140857/checkpoint-669/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 528 |
+
grpo_easy/sft_grpo_curriculum_pipeline_grpo_run1-full-e1-bs4-lr1e-06-20250614_162238/checkpoint-1338/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 529 |
+
grpo_easy/sft_grpo_curriculum_pipeline_grpo_run1-full-e1-bs4-lr1e-06-20250614_162238/final_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 530 |
+
grpo_easy/sft_grpo_curriculum_pipeline_grpo_run1-full-e1-bs4-lr1e-06-20250614_162238/checkpoint-2007/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 531 |
+
grpo_easy/sft_grpo_curriculum_pipeline_grpo_run1-full-e1-bs4-lr1e-06-20250614_162238/checkpoint-2009/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 532 |
+
grpo_easy/sft_grpo_curriculum_pipeline_grpo_run1-full-e1-bs4-lr1e-06-20250614_162238/checkpoint-669/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1006/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4945a1fae4e12b01188f74ce4b8755065296b20a4cc7c362548da7c6792f27c9
|
| 3 |
+
size 22056664
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1006/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7154804a0ae3c29a6ef85f544b47226b7003ebbaaa27d2338d1839635d3974b
|
| 3 |
+
size 33662795
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1006/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98ccc1063b790b92f3e7d161fa2813d5f2742828ffc0352bdb298865af2bebef
|
| 3 |
+
size 14645
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1006/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5af7a8d83a07bad7c71e7b0aad9273715d9c4c26664d7587cd16678f613b9732
|
| 3 |
+
size 1465
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1006/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e56eaebf99a63995f420cf1d71d671180c414ff523f363350b20c982ef29d5b6
|
| 3 |
+
size 12030943
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1006/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3831c3e7266c3e37dc5feebcd848b77f8fffd4857d8e4e82b80cc523ca828898
|
| 3 |
+
size 6993
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1509/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:daab9142eef2e543fad4eb7e7b978c1039325c574014041815f8181f0ad61454
|
| 3 |
+
size 22056664
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1509/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00ed4fc579fcd05fce24812d06e5f9b8416754e90656aa70b5bc35b18e1f3d91
|
| 3 |
+
size 33662795
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1509/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9f3be8165a5d16e13e0e743f5f0a12a6e919089c4bdb044ed1c6dfa0828dba6
|
| 3 |
+
size 14645
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1509/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f8acea1debd0b99d4db4ec8a5849f0db70f3adc7ceebf844017386c37aba060
|
| 3 |
+
size 1465
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1509/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e56eaebf99a63995f420cf1d71d671180c414ff523f363350b20c982ef29d5b6
|
| 3 |
+
size 12030943
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-1509/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3831c3e7266c3e37dc5feebcd848b77f8fffd4857d8e4e82b80cc523ca828898
|
| 3 |
+
size 6993
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2012/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb2849c0c7c8306c88baddd1ae1a10931b0ca2279cb81df1926c66731b0844f2
|
| 3 |
+
size 22056664
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2012/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ae9bf59d03bf43bd935425de0f4aadde68fd53b2beb901880e0806b03193236
|
| 3 |
+
size 33662795
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2012/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6347ff032752379d54d091fc76c2caa22743a0b703ee66b6bcf8c7fb45539fc5
|
| 3 |
+
size 14645
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2012/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1338ba70a275a709f55248b66159e3b5caddb93eb2eeb17ca80ff6f5d074174f
|
| 3 |
+
size 1465
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2012/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e56eaebf99a63995f420cf1d71d671180c414ff523f363350b20c982ef29d5b6
|
| 3 |
+
size 12030943
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2012/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3831c3e7266c3e37dc5feebcd848b77f8fffd4857d8e4e82b80cc523ca828898
|
| 3 |
+
size 6993
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2515/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df305cf372843403fd4db3dd713ff2f4a293b6577915ba0df5d9b2b501ef0cd0
|
| 3 |
+
size 22056664
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2515/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e9823dd14867f6311460b83e0e416bbcf9d6bf493ee91133f4819a4b9ecd2e4
|
| 3 |
+
size 33662795
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2515/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bad95c01826bf9324bdc3f0a2b04cf718c9fa46fd796609e6a1b9928b69debf4
|
| 3 |
+
size 14645
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2515/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f33fa2dd33ae792f3ef07bd67c841ac4f80218e698eb41b3247e6cc1097620d
|
| 3 |
+
size 1465
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2515/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e56eaebf99a63995f420cf1d71d671180c414ff523f363350b20c982ef29d5b6
|
| 3 |
+
size 12030943
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-2515/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3831c3e7266c3e37dc5feebcd848b77f8fffd4857d8e4e82b80cc523ca828898
|
| 3 |
+
size 6993
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3018/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a32412a57cdb81999c0f5ad2c1fb883a56a0d17321f6f295a234e6d4775b465
|
| 3 |
+
size 22056664
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3018/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2dd0fd1df398037b3541900e592afd6470830fd8e6d2c8032a6f504dac7c6c06
|
| 3 |
+
size 33662795
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3018/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d850ea141edb65f238fa4157fe393d4fe78513418a7c04cef79b38c4a1318aa
|
| 3 |
+
size 14645
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3018/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccdc7d4e6b26235aa48f31c76a3a63e99bf6699a3a9ed215165383594a75a334
|
| 3 |
+
size 1465
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3018/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e56eaebf99a63995f420cf1d71d671180c414ff523f363350b20c982ef29d5b6
|
| 3 |
+
size 12030943
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3018/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3831c3e7266c3e37dc5feebcd848b77f8fffd4857d8e4e82b80cc523ca828898
|
| 3 |
+
size 6993
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3020/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:869009491e9d28ef1c446657a5d54768e43cf6ed6fa14456ba5f48e39a85a27c
|
| 3 |
+
size 22056664
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3020/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ad8c887e21ca521ef59fcacfaa314ad38fe2420c42665e94a1f73441a913ac1
|
| 3 |
+
size 33662795
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3020/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a689103220e82f3f8ecbdf8df0edf47b8090d31862c04318bf5eacd585fb6f8
|
| 3 |
+
size 14645
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3020/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b7fb0823cb5ebf4ac6465a85fd65be6fd2a3715b245af01a4fb365ff2adcf5c
|
| 3 |
+
size 1465
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3020/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e56eaebf99a63995f420cf1d71d671180c414ff523f363350b20c982ef29d5b6
|
| 3 |
+
size 12030943
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-3020/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3831c3e7266c3e37dc5feebcd848b77f8fffd4857d8e4e82b80cc523ca828898
|
| 3 |
+
size 6993
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-503/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc692e385e6c0e70b7678eb0a76bffc3d5fb55709299b57c559f6338a722df26
|
| 3 |
+
size 22056664
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-503/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33dc9421c8b33dccd09a5e8fb6706dc188e0896bc751c5fe0989d1b9a982f107
|
| 3 |
+
size 33662795
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-503/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9bfbafd2218c0d1b0f86cd0f388d447ee6dea325e34972f2864240c155699fe
|
| 3 |
+
size 14645
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-503/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1abddd6ba5e487c94c22f20ed027cb1769abf481123e886a9d3e6c55588dc97
|
| 3 |
+
size 1465
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-503/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e56eaebf99a63995f420cf1d71d671180c414ff523f363350b20c982ef29d5b6
|
| 3 |
+
size 12030943
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/checkpoint-503/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3831c3e7266c3e37dc5feebcd848b77f8fffd4857d8e4e82b80cc523ca828898
|
| 3 |
+
size 6993
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/final_model/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:869009491e9d28ef1c446657a5d54768e43cf6ed6fa14456ba5f48e39a85a27c
|
| 3 |
+
size 22056664
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/final_model/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e56eaebf99a63995f420cf1d71d671180c414ff523f363350b20c982ef29d5b6
|
| 3 |
+
size 12030943
|
grpo_all_div_0.7/diversity_0.7_grpo_run2-full-e2-bs4-lr5e-07-20250615_144042/final_model/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3831c3e7266c3e37dc5feebcd848b77f8fffd4857d8e4e82b80cc523ca828898
|
| 3 |
+
size 6993
|
grpo_all_easy_diverse/combined_easy_diverse_grpo_run2-full-e2-bs4-lr5e-07-20250615_144521/checkpoint-1509/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebc58594e38fdd8a40dc66aef4f19ee56387697be8cf55e17d9ddf0dfab4656b
|
| 3 |
+
size 22056664
|
grpo_all_easy_diverse/combined_easy_diverse_grpo_run2-full-e2-bs4-lr5e-07-20250615_144521/checkpoint-1509/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dae136412f1db01f8dac9b38a96363b227c28fc63d2564bc01d2f2c3db2c3cf
|
| 3 |
+
size 33662795
|
grpo_all_easy_diverse/combined_easy_diverse_grpo_run2-full-e2-bs4-lr5e-07-20250615_144521/checkpoint-1509/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9837d65a6eff0f1f9369609e3fccfe38a6bbe923781a4c09fca6735cf202b0c
|
| 3 |
+
size 14645
|
grpo_all_easy_diverse/combined_easy_diverse_grpo_run2-full-e2-bs4-lr5e-07-20250615_144521/checkpoint-1509/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f8acea1debd0b99d4db4ec8a5849f0db70f3adc7ceebf844017386c37aba060
|
| 3 |
+
size 1465
|