Batch upload: 20250929_061924
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +8 -0
- 20250929_061924/experiment_log.txt +16 -0
- 20250929_061924/filtered_data/filter_info.json +58 -0
- 20250929_061924/filtered_data/filtered_top_10pct.parquet +3 -0
- 20250929_061924/filtered_data/filtered_top_10pct_auc.csv +0 -0
- 20250929_061924/filtered_data/filtered_top_20pct.parquet +3 -0
- 20250929_061924/filtered_data/filtered_top_20pct_auc.csv +0 -0
- 20250929_061924/filtered_data/filtered_top_50pct.parquet +3 -0
- 20250929_061924/filtered_data/filtered_top_50pct_auc.csv +863 -0
- 20250929_061924/filtered_data/full_data.parquet +3 -0
- 20250929_061924/filtered_data/full_data_auc.csv +0 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_387/added_tokens.json +24 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_387/chat_template.jinja +54 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_387/config.json +67 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_387/generation_config.json +6 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_387/merges.txt +0 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_387/model-00001-of-00003.safetensors +3 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_387/model-00002-of-00003.safetensors +3 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_387/model-00003-of-00003.safetensors +3 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_387/model.safetensors.index.json +443 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_387/special_tokens_map.json +31 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_387/tokenizer.json +3 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_387/tokenizer_config.json +207 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_387/vocab.json +0 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_774/added_tokens.json +24 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_774/chat_template.jinja +54 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_774/config.json +67 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_774/generation_config.json +6 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_774/merges.txt +0 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_774/model-00001-of-00003.safetensors +3 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_774/model-00002-of-00003.safetensors +3 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_774/model-00003-of-00003.safetensors +3 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_774/model.safetensors.index.json +443 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_774/special_tokens_map.json +31 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_774/tokenizer.json +3 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_774/tokenizer_config.json +207 -0
- 20250929_061924/sft_results/filtered_top_10pct/global_step_774/vocab.json +0 -0
- 20250929_061924/sft_results/filtered_top_10pct/gpu_lock_wrapper.sh +31 -0
- 20250929_061924/sft_results/filtered_top_10pct/run_sft_script.sh +40 -0
- 20250929_061924/sft_results/filtered_top_10pct/sft_training_data.parquet +3 -0
- 20250929_061924/sft_results/filtered_top_10pct/training_log.txt +0 -0
- 20250929_061924/sft_results/filtered_top_10pct/training_summary.json +15 -0
- 20250929_061924/sft_results/filtered_top_20pct/global_step_344/added_tokens.json +24 -0
- 20250929_061924/sft_results/filtered_top_20pct/global_step_344/chat_template.jinja +54 -0
- 20250929_061924/sft_results/filtered_top_20pct/global_step_344/config.json +67 -0
- 20250929_061924/sft_results/filtered_top_20pct/global_step_344/generation_config.json +6 -0
- 20250929_061924/sft_results/filtered_top_20pct/global_step_344/merges.txt +0 -0
- 20250929_061924/sft_results/filtered_top_20pct/global_step_344/model-00001-of-00003.safetensors +3 -0
- 20250929_061924/sft_results/filtered_top_20pct/global_step_344/model-00002-of-00003.safetensors +3 -0
- 20250929_061924/sft_results/filtered_top_20pct/global_step_344/model-00003-of-00003.safetensors +3 -0
.gitattributes
CHANGED
|
@@ -83,3 +83,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 83 |
20250915_051625/sft_results/filtered_top_50pct/global_step_430/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 84 |
20250915_051625/sft_results/full_data/global_step_430/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 85 |
20250915_051625/sft_results/full_data/global_step_860/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
20250915_051625/sft_results/filtered_top_50pct/global_step_430/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 84 |
20250915_051625/sft_results/full_data/global_step_430/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 85 |
20250915_051625/sft_results/full_data/global_step_860/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 86 |
+
20250929_061924/sft_results/filtered_top_10pct/global_step_387/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 87 |
+
20250929_061924/sft_results/filtered_top_10pct/global_step_774/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 88 |
+
20250929_061924/sft_results/filtered_top_20pct/global_step_344/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 89 |
+
20250929_061924/sft_results/filtered_top_20pct/global_step_688/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 90 |
+
20250929_061924/sft_results/filtered_top_50pct/global_step_215/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 91 |
+
20250929_061924/sft_results/filtered_top_50pct/global_step_430/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 92 |
+
20250929_061924/sft_results/full_data/global_step_430/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 93 |
+
20250929_061924/sft_results/full_data/global_step_860/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
20250929_061924/experiment_log.txt
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Parallel AUC-Filtered SFT Experiments - 2025-09-29 06:19:25.811616
|
| 2 |
+
Configuration:
|
| 3 |
+
Model: Qwen/Qwen2.5-3B
|
| 4 |
+
Filter Percentages: [0, 10, 20, 50]
|
| 5 |
+
SFT Epochs: 2
|
| 6 |
+
SFT Batch Size: 4
|
| 7 |
+
Filtered Files: 4
|
| 8 |
+
|
| 9 |
+
Filter: full_data - Started at Mon Sep 29 06:19:26 UTC 2025
|
| 10 |
+
Filter: filtered_top_20pct - Started at Mon Sep 29 06:19:26 UTC 2025
|
| 11 |
+
Filter: filtered_top_10pct - Started at Mon Sep 29 06:19:26 UTC 2025
|
| 12 |
+
Filter: filtered_top_50pct - Started at Mon Sep 29 06:19:26 UTC 2025
|
| 13 |
+
Filter: filtered_top_50pct - Failed with exit code 1 at Mon Sep 29 07:22:54 UTC 2025
|
| 14 |
+
Filter: filtered_top_20pct - Failed with exit code 1 at Mon Sep 29 07:26:24 UTC 2025
|
| 15 |
+
Filter: filtered_top_10pct - Failed with exit code 1 at Mon Sep 29 07:26:51 UTC 2025
|
| 16 |
+
Filter: full_data - Failed with exit code 1 at Mon Sep 29 07:27:43 UTC 2025
|
20250929_061924/filtered_data/filter_info.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"full_data": {
|
| 3 |
+
"inference_file_path": "checkpoints/auc_filtered_sft/20250929_061924/filtered_data/full_data.parquet",
|
| 4 |
+
"auc_file_path": "checkpoints/auc_filtered_sft/20250929_061924/filtered_data/full_data_auc.csv",
|
| 5 |
+
"sample_count": 1723,
|
| 6 |
+
"auc_stats": {
|
| 7 |
+
"mean": 53.69820081253627,
|
| 8 |
+
"min": 4.0,
|
| 9 |
+
"max": 90.0,
|
| 10 |
+
"std": 34.33664607809399
|
| 11 |
+
},
|
| 12 |
+
"case_type_distribution": {
|
| 13 |
+
"nonhacking": 1723
|
| 14 |
+
}
|
| 15 |
+
},
|
| 16 |
+
"filtered_top_10pct": {
|
| 17 |
+
"inference_file_path": "checkpoints/auc_filtered_sft/20250929_061924/filtered_data/filtered_top_10pct.parquet",
|
| 18 |
+
"auc_file_path": "checkpoints/auc_filtered_sft/20250929_061924/filtered_data/filtered_top_10pct_auc.csv",
|
| 19 |
+
"sample_count": 1551,
|
| 20 |
+
"auc_stats": {
|
| 21 |
+
"mean": 49.672469374597036,
|
| 22 |
+
"min": 4.0,
|
| 23 |
+
"max": 90.0,
|
| 24 |
+
"std": 33.873061086682526
|
| 25 |
+
},
|
| 26 |
+
"case_type_distribution": {
|
| 27 |
+
"nonhacking": 1551
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"filtered_top_20pct": {
|
| 31 |
+
"inference_file_path": "checkpoints/auc_filtered_sft/20250929_061924/filtered_data/filtered_top_20pct.parquet",
|
| 32 |
+
"auc_file_path": "checkpoints/auc_filtered_sft/20250929_061924/filtered_data/filtered_top_20pct_auc.csv",
|
| 33 |
+
"sample_count": 1379,
|
| 34 |
+
"auc_stats": {
|
| 35 |
+
"mean": 44.64249456127629,
|
| 36 |
+
"min": 4.0,
|
| 37 |
+
"max": 90.0,
|
| 38 |
+
"std": 32.59273639572224
|
| 39 |
+
},
|
| 40 |
+
"case_type_distribution": {
|
| 41 |
+
"nonhacking": 1379
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"filtered_top_50pct": {
|
| 45 |
+
"inference_file_path": "checkpoints/auc_filtered_sft/20250929_061924/filtered_data/filtered_top_50pct.parquet",
|
| 46 |
+
"auc_file_path": "checkpoints/auc_filtered_sft/20250929_061924/filtered_data/filtered_top_50pct_auc.csv",
|
| 47 |
+
"sample_count": 862,
|
| 48 |
+
"auc_stats": {
|
| 49 |
+
"mean": 22.155452436194896,
|
| 50 |
+
"min": 4.0,
|
| 51 |
+
"max": 62.0,
|
| 52 |
+
"std": 17.419640262308363
|
| 53 |
+
},
|
| 54 |
+
"case_type_distribution": {
|
| 55 |
+
"nonhacking": 862
|
| 56 |
+
}
|
| 57 |
+
}
|
| 58 |
+
}
|
20250929_061924/filtered_data/filtered_top_10pct.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd78f7120a239e82321fdb3656cb60130b5825e09b77f0f2c30142cf418edfb4
|
| 3 |
+
size 1679247
|
20250929_061924/filtered_data/filtered_top_10pct_auc.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
20250929_061924/filtered_data/filtered_top_20pct.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afcee0431f0d068cbdd52f830c313f89df688dd1badfef47ca110abf4fb42c30
|
| 3 |
+
size 1517924
|
20250929_061924/filtered_data/filtered_top_20pct_auc.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
20250929_061924/filtered_data/filtered_top_50pct.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc587e38a6b47792c4996a736d7421d752f4eb217ccaea2f6a56c4f72fdce2ce
|
| 3 |
+
size 972876
|
20250929_061924/filtered_data/filtered_top_50pct_auc.csv
ADDED
|
@@ -0,0 +1,863 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
sample_id,auc_10_100,num_points,case_type,training_step
|
| 2 |
+
0,45.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 3 |
+
3,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 4 |
+
9,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 5 |
+
10,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 6 |
+
11,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 7 |
+
12,33.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 8 |
+
13,27.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 9 |
+
15,24.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 10 |
+
19,38.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 11 |
+
20,54.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 12 |
+
21,37.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 13 |
+
22,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 14 |
+
23,59.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 15 |
+
26,41.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 16 |
+
27,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 17 |
+
28,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 18 |
+
29,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 19 |
+
30,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 20 |
+
31,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 21 |
+
32,23.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 22 |
+
33,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 23 |
+
35,29.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 24 |
+
38,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 25 |
+
39,45.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 26 |
+
40,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 27 |
+
41,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 28 |
+
45,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 29 |
+
46,19.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 30 |
+
48,55.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 31 |
+
49,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 32 |
+
50,27.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 33 |
+
52,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 34 |
+
54,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 35 |
+
57,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 36 |
+
58,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 37 |
+
59,46.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 38 |
+
63,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 39 |
+
65,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 40 |
+
66,9.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 41 |
+
67,16.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 42 |
+
70,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 43 |
+
71,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 44 |
+
72,28.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 45 |
+
74,33.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 46 |
+
75,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 47 |
+
78,60.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 48 |
+
79,42.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 49 |
+
80,59.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 50 |
+
81,36.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 51 |
+
82,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 52 |
+
83,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 53 |
+
85,46.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 54 |
+
87,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 55 |
+
88,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 56 |
+
90,43.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 57 |
+
91,33.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 58 |
+
92,21.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 59 |
+
93,36.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 60 |
+
94,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 61 |
+
95,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 62 |
+
96,9.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 63 |
+
98,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 64 |
+
101,30.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 65 |
+
102,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 66 |
+
105,49.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 67 |
+
106,24.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 68 |
+
107,45.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 69 |
+
108,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 70 |
+
109,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 71 |
+
110,31.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 72 |
+
114,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 73 |
+
115,43.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 74 |
+
116,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 75 |
+
117,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 76 |
+
120,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 77 |
+
122,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 78 |
+
123,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 79 |
+
124,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 80 |
+
125,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 81 |
+
126,6.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 82 |
+
129,23.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 83 |
+
132,21.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 84 |
+
134,44.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 85 |
+
135,42.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 86 |
+
136,37.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 87 |
+
137,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 88 |
+
138,59.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 89 |
+
139,6.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 90 |
+
140,60.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 91 |
+
141,47.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 92 |
+
142,34.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 93 |
+
144,50.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 94 |
+
145,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 95 |
+
147,23.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 96 |
+
151,50.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 97 |
+
152,27.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 98 |
+
154,12.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 99 |
+
155,48.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 100 |
+
156,45.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 101 |
+
157,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 102 |
+
159,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 103 |
+
160,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 104 |
+
164,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 105 |
+
165,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 106 |
+
166,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 107 |
+
168,42.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 108 |
+
170,29.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 109 |
+
171,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 110 |
+
172,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 111 |
+
173,45.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 112 |
+
176,37.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 113 |
+
177,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 114 |
+
178,55.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 115 |
+
180,38.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 116 |
+
181,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 117 |
+
187,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 118 |
+
188,6.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 119 |
+
189,10.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 120 |
+
190,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 121 |
+
191,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 122 |
+
193,23.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 123 |
+
194,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 124 |
+
196,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 125 |
+
198,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 126 |
+
200,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 127 |
+
201,27.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 128 |
+
202,30.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 129 |
+
204,19.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 130 |
+
205,29.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 131 |
+
206,29.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 132 |
+
207,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 133 |
+
208,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 134 |
+
209,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 135 |
+
210,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 136 |
+
211,39.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 137 |
+
214,29.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 138 |
+
215,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 139 |
+
217,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 140 |
+
220,16.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 141 |
+
221,47.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 142 |
+
222,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 143 |
+
225,20.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 144 |
+
226,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 145 |
+
227,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 146 |
+
228,44.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 147 |
+
232,50.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 148 |
+
233,45.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 149 |
+
234,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 150 |
+
235,42.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 151 |
+
236,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 152 |
+
237,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 153 |
+
239,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 154 |
+
240,28.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 155 |
+
244,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 156 |
+
245,34.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 157 |
+
247,46.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 158 |
+
248,49.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 159 |
+
249,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 160 |
+
250,29.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 161 |
+
251,16.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 162 |
+
253,16.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 163 |
+
255,9.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 164 |
+
256,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 165 |
+
257,50.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 166 |
+
258,30.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 167 |
+
259,50.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 168 |
+
261,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 169 |
+
262,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 170 |
+
263,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 171 |
+
264,21.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 172 |
+
265,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 173 |
+
267,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 174 |
+
268,51.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 175 |
+
269,43.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 176 |
+
271,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 177 |
+
272,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 178 |
+
275,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 179 |
+
276,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 180 |
+
277,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 181 |
+
278,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 182 |
+
281,48.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 183 |
+
282,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 184 |
+
285,26.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 185 |
+
286,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 186 |
+
288,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 187 |
+
290,19.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 188 |
+
293,23.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 189 |
+
294,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 190 |
+
295,38.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 191 |
+
296,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 192 |
+
297,16.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 193 |
+
298,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 194 |
+
300,36.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 195 |
+
302,57.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 196 |
+
304,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 197 |
+
305,19.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 198 |
+
307,41.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 199 |
+
308,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 200 |
+
309,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 201 |
+
310,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 202 |
+
312,49.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 203 |
+
313,46.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 204 |
+
314,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 205 |
+
315,57.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 206 |
+
316,22.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 207 |
+
318,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 208 |
+
319,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 209 |
+
321,33.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 210 |
+
322,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 211 |
+
323,52.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 212 |
+
324,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 213 |
+
325,27.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 214 |
+
326,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 215 |
+
329,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 216 |
+
330,34.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 217 |
+
331,19.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 218 |
+
334,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 219 |
+
335,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 220 |
+
336,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 221 |
+
337,45.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 222 |
+
338,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 223 |
+
339,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 224 |
+
340,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 225 |
+
341,45.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 226 |
+
343,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 227 |
+
344,10.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 228 |
+
345,48.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 229 |
+
346,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 230 |
+
349,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 231 |
+
351,54.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 232 |
+
352,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 233 |
+
353,56.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 234 |
+
354,39.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 235 |
+
356,41.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 236 |
+
360,19.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 237 |
+
361,16.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 238 |
+
362,33.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 239 |
+
365,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 240 |
+
366,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 241 |
+
367,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 242 |
+
370,21.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 243 |
+
371,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 244 |
+
373,40.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 245 |
+
374,49.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 246 |
+
375,41.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 247 |
+
376,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 248 |
+
377,58.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 249 |
+
378,48.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 250 |
+
379,22.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 251 |
+
380,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 252 |
+
381,49.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 253 |
+
384,50.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 254 |
+
385,52.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 255 |
+
387,8.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 256 |
+
388,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 257 |
+
389,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 258 |
+
393,31.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 259 |
+
394,39.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 260 |
+
395,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 261 |
+
396,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 262 |
+
398,45.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 263 |
+
401,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 264 |
+
402,33.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 265 |
+
403,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 266 |
+
404,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 267 |
+
406,27.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 268 |
+
407,40.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 269 |
+
408,51.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 270 |
+
410,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 271 |
+
411,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 272 |
+
412,50.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 273 |
+
414,43.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 274 |
+
415,59.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 275 |
+
416,55.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 276 |
+
417,60.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 277 |
+
418,30.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 278 |
+
419,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 279 |
+
421,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 280 |
+
422,57.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 281 |
+
423,34.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 282 |
+
424,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 283 |
+
425,61.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 284 |
+
426,29.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 285 |
+
427,56.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 286 |
+
429,33.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 287 |
+
430,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 288 |
+
431,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 289 |
+
432,48.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 290 |
+
433,45.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 291 |
+
435,14.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 292 |
+
436,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 293 |
+
438,30.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 294 |
+
439,8.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 295 |
+
441,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 296 |
+
442,50.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 297 |
+
444,8.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 298 |
+
445,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 299 |
+
446,48.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 300 |
+
447,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 301 |
+
448,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 302 |
+
450,45.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 303 |
+
451,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 304 |
+
452,36.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 305 |
+
453,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 306 |
+
454,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 307 |
+
457,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 308 |
+
458,45.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 309 |
+
459,31.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 310 |
+
460,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 311 |
+
461,44.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 312 |
+
462,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 313 |
+
465,29.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 314 |
+
466,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 315 |
+
469,37.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 316 |
+
470,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 317 |
+
471,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 318 |
+
474,6.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 319 |
+
477,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 320 |
+
479,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 321 |
+
480,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 322 |
+
484,29.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 323 |
+
485,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 324 |
+
487,31.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 325 |
+
490,29.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 326 |
+
491,33.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 327 |
+
495,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 328 |
+
496,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 329 |
+
497,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 330 |
+
498,21.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 331 |
+
501,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 332 |
+
502,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 333 |
+
504,14.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 334 |
+
505,37.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 335 |
+
507,34.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 336 |
+
508,22.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 337 |
+
510,30.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 338 |
+
512,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 339 |
+
513,28.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 340 |
+
514,6.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 341 |
+
515,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 342 |
+
518,9.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 343 |
+
519,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 344 |
+
520,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 345 |
+
521,56.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 346 |
+
522,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 347 |
+
523,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 348 |
+
524,34.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 349 |
+
525,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 350 |
+
527,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 351 |
+
530,56.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 352 |
+
531,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 353 |
+
533,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 354 |
+
534,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 355 |
+
535,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 356 |
+
539,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 357 |
+
540,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 358 |
+
546,39.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 359 |
+
548,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 360 |
+
549,61.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 361 |
+
550,21.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 362 |
+
552,19.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 363 |
+
553,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 364 |
+
556,55.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 365 |
+
557,27.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 366 |
+
558,38.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 367 |
+
560,61.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 368 |
+
561,12.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 369 |
+
563,33.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 370 |
+
565,58.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 371 |
+
566,33.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 372 |
+
567,21.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 373 |
+
568,16.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 374 |
+
570,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 375 |
+
571,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 376 |
+
575,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 377 |
+
576,10.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 378 |
+
578,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 379 |
+
580,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 380 |
+
581,53.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 381 |
+
585,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 382 |
+
586,6.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 383 |
+
587,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 384 |
+
588,21.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 385 |
+
589,31.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 386 |
+
590,20.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 387 |
+
591,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 388 |
+
593,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 389 |
+
594,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 390 |
+
596,6.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 391 |
+
600,9.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 392 |
+
602,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 393 |
+
604,9.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 394 |
+
607,37.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 395 |
+
608,56.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 396 |
+
609,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 397 |
+
610,9.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 398 |
+
611,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 399 |
+
614,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 400 |
+
615,44.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 401 |
+
616,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 402 |
+
617,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 403 |
+
618,41.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 404 |
+
620,22.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 405 |
+
622,56.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 406 |
+
623,20.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 407 |
+
624,57.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 408 |
+
625,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 409 |
+
626,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 410 |
+
627,40.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 411 |
+
628,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 412 |
+
629,40.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 413 |
+
632,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 414 |
+
633,55.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 415 |
+
636,23.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 416 |
+
638,41.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 417 |
+
639,23.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 418 |
+
640,48.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 419 |
+
644,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 420 |
+
645,27.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 421 |
+
647,6.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 422 |
+
648,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 423 |
+
650,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 424 |
+
651,16.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 425 |
+
652,47.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 426 |
+
653,53.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 427 |
+
654,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 428 |
+
655,49.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 429 |
+
656,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 430 |
+
657,41.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 431 |
+
658,55.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 432 |
+
659,59.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 433 |
+
660,47.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 434 |
+
661,23.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 435 |
+
664,37.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 436 |
+
665,22.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 437 |
+
666,27.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 438 |
+
667,21.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 439 |
+
668,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 440 |
+
669,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 441 |
+
670,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 442 |
+
672,46.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 443 |
+
674,29.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 444 |
+
677,51.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 445 |
+
678,42.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 446 |
+
679,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 447 |
+
680,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 448 |
+
683,10.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 449 |
+
686,19.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 450 |
+
689,33.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 451 |
+
690,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 452 |
+
691,29.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 453 |
+
696,31.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 454 |
+
697,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 455 |
+
698,12.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 456 |
+
699,27.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 457 |
+
700,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 458 |
+
701,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 459 |
+
702,23.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 460 |
+
706,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 461 |
+
707,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 462 |
+
708,42.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 463 |
+
714,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 464 |
+
715,49.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 465 |
+
717,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 466 |
+
718,6.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 467 |
+
719,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 468 |
+
720,29.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 469 |
+
723,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 470 |
+
724,55.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 471 |
+
727,54.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 472 |
+
728,10.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 473 |
+
729,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 474 |
+
731,48.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 475 |
+
733,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 476 |
+
734,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 477 |
+
736,42.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 478 |
+
737,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 479 |
+
738,31.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 480 |
+
739,27.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 481 |
+
742,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 482 |
+
743,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 483 |
+
746,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 484 |
+
749,29.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 485 |
+
751,33.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 486 |
+
752,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 487 |
+
753,45.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 488 |
+
754,12.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 489 |
+
755,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 490 |
+
757,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 491 |
+
758,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 492 |
+
760,19.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 493 |
+
761,45.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 494 |
+
764,39.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 495 |
+
765,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 496 |
+
767,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 497 |
+
0,61.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 498 |
+
3,23.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 499 |
+
5,59.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 500 |
+
7,9.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 501 |
+
12,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 502 |
+
13,53.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 503 |
+
16,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 504 |
+
20,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 505 |
+
24,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 506 |
+
29,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 507 |
+
30,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 508 |
+
31,45.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 509 |
+
39,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 510 |
+
40,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 511 |
+
42,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 512 |
+
43,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 513 |
+
44,55.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 514 |
+
46,60.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 515 |
+
50,46.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 516 |
+
54,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 517 |
+
57,45.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 518 |
+
58,60.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 519 |
+
61,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 520 |
+
63,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 521 |
+
64,12.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 522 |
+
68,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 523 |
+
71,43.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 524 |
+
75,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 525 |
+
76,53.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 526 |
+
81,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 527 |
+
85,9.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 528 |
+
89,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 529 |
+
92,6.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 530 |
+
93,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 531 |
+
96,16.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 532 |
+
97,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 533 |
+
102,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 534 |
+
103,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 535 |
+
106,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 536 |
+
113,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 537 |
+
114,26.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 538 |
+
117,57.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 539 |
+
118,54.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 540 |
+
122,9.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 541 |
+
126,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 542 |
+
133,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 543 |
+
134,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 544 |
+
135,49.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 545 |
+
138,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 546 |
+
143,60.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 547 |
+
148,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 548 |
+
149,50.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 549 |
+
152,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 550 |
+
154,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 551 |
+
155,51.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 552 |
+
156,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 553 |
+
157,53.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 554 |
+
160,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 555 |
+
169,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 556 |
+
170,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 557 |
+
172,14.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 558 |
+
176,38.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 559 |
+
177,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 560 |
+
178,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 561 |
+
181,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 562 |
+
186,57.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 563 |
+
187,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 564 |
+
194,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 565 |
+
197,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 566 |
+
198,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 567 |
+
202,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 568 |
+
205,30.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 569 |
+
206,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 570 |
+
208,10.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 571 |
+
209,46.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 572 |
+
210,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 573 |
+
211,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 574 |
+
214,54.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 575 |
+
221,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 576 |
+
225,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 577 |
+
226,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 578 |
+
231,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 579 |
+
232,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 580 |
+
234,58.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 581 |
+
240,57.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 582 |
+
243,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 583 |
+
244,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 584 |
+
247,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 585 |
+
248,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 586 |
+
249,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 587 |
+
250,57.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 588 |
+
252,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 589 |
+
253,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 590 |
+
256,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 591 |
+
262,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 592 |
+
263,16.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 593 |
+
264,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 594 |
+
269,30.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 595 |
+
274,61.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 596 |
+
275,4.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 597 |
+
277,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 598 |
+
280,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 599 |
+
282,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 600 |
+
284,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 601 |
+
287,23.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 602 |
+
288,44.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 603 |
+
291,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 604 |
+
294,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 605 |
+
295,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 606 |
+
299,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 607 |
+
302,33.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 608 |
+
307,58.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 609 |
+
308,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 610 |
+
310,32.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 611 |
+
312,29.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 612 |
+
315,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 613 |
+
316,16.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 614 |
+
317,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 615 |
+
319,56.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 616 |
+
321,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 617 |
+
324,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 618 |
+
326,46.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 619 |
+
328,60.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 620 |
+
330,55.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 621 |
+
332,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 622 |
+
333,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 623 |
+
335,51.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 624 |
+
336,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 625 |
+
338,45.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 626 |
+
339,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 627 |
+
342,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 628 |
+
344,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 629 |
+
345,46.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 630 |
+
347,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 631 |
+
349,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 632 |
+
353,36.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 633 |
+
355,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 634 |
+
357,29.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 635 |
+
358,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 636 |
+
365,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 637 |
+
368,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 638 |
+
372,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 639 |
+
377,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 640 |
+
381,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 641 |
+
384,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 642 |
+
385,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 643 |
+
386,41.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 644 |
+
389,20.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 645 |
+
390,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 646 |
+
393,53.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 647 |
+
394,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 648 |
+
396,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 649 |
+
400,20.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 650 |
+
403,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 651 |
+
404,10.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 652 |
+
409,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 653 |
+
410,10.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 654 |
+
412,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 655 |
+
414,21.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 656 |
+
416,6.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 657 |
+
417,60.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 658 |
+
418,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 659 |
+
419,21.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 660 |
+
421,55.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 661 |
+
426,41.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 662 |
+
429,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 663 |
+
430,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 664 |
+
431,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 665 |
+
432,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 666 |
+
433,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 667 |
+
434,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 668 |
+
435,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 669 |
+
439,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 670 |
+
441,53.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 671 |
+
443,34.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 672 |
+
444,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 673 |
+
447,38.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 674 |
+
452,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 675 |
+
457,37.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 676 |
+
459,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 677 |
+
460,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 678 |
+
461,43.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 679 |
+
464,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 680 |
+
465,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 681 |
+
471,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 682 |
+
472,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 683 |
+
479,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 684 |
+
483,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 685 |
+
484,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 686 |
+
494,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 687 |
+
498,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 688 |
+
499,16.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 689 |
+
504,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 690 |
+
505,23.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 691 |
+
508,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 692 |
+
509,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 693 |
+
510,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 694 |
+
512,9.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 695 |
+
514,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 696 |
+
515,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 697 |
+
520,9.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 698 |
+
521,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 699 |
+
523,45.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 700 |
+
525,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 701 |
+
526,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 702 |
+
529,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 703 |
+
530,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 704 |
+
532,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 705 |
+
533,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 706 |
+
536,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 707 |
+
540,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 708 |
+
541,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 709 |
+
542,9.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 710 |
+
544,33.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 711 |
+
550,60.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 712 |
+
551,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 713 |
+
552,51.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 714 |
+
553,8.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 715 |
+
557,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 716 |
+
558,30.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 717 |
+
559,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 718 |
+
564,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 719 |
+
566,51.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 720 |
+
569,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 721 |
+
574,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 722 |
+
575,39.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 723 |
+
578,50.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 724 |
+
581,43.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 725 |
+
584,46.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 726 |
+
587,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 727 |
+
594,54.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 728 |
+
596,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 729 |
+
597,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 730 |
+
598,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 731 |
+
600,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 732 |
+
603,9.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 733 |
+
604,20.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 734 |
+
607,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 735 |
+
608,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 736 |
+
612,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 737 |
+
615,31.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 738 |
+
618,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 739 |
+
619,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 740 |
+
622,33.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 741 |
+
624,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 742 |
+
625,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 743 |
+
626,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 744 |
+
627,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 745 |
+
628,48.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 746 |
+
630,55.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 747 |
+
633,21.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 748 |
+
634,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 749 |
+
636,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 750 |
+
639,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 751 |
+
641,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 752 |
+
642,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 753 |
+
644,19.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 754 |
+
648,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 755 |
+
652,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 756 |
+
662,40.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 757 |
+
663,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 758 |
+
664,9.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 759 |
+
673,51.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 760 |
+
676,58.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 761 |
+
677,8.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 762 |
+
678,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 763 |
+
683,55.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 764 |
+
689,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 765 |
+
693,31.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 766 |
+
697,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 767 |
+
698,21.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 768 |
+
701,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 769 |
+
702,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 770 |
+
707,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 771 |
+
709,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 772 |
+
711,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 773 |
+
712,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 774 |
+
714,56.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 775 |
+
717,62.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 776 |
+
720,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 777 |
+
721,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 778 |
+
722,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 779 |
+
724,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 780 |
+
729,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 781 |
+
730,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 782 |
+
731,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 783 |
+
734,19.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 784 |
+
738,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 785 |
+
740,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 786 |
+
743,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 787 |
+
747,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 788 |
+
748,36.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 789 |
+
750,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 790 |
+
758,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 791 |
+
759,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 792 |
+
761,58.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 793 |
+
763,14.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 794 |
+
764,45.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 795 |
+
765,21.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 796 |
+
770,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 797 |
+
772,7.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 798 |
+
773,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 799 |
+
775,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 800 |
+
780,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 801 |
+
782,19.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 802 |
+
783,48.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 803 |
+
784,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 804 |
+
786,10.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 805 |
+
787,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 806 |
+
788,6.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 807 |
+
794,22.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 808 |
+
795,35.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 809 |
+
799,47.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 810 |
+
801,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 811 |
+
802,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 812 |
+
808,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 813 |
+
809,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 814 |
+
810,26.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 815 |
+
811,31.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 816 |
+
813,21.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 817 |
+
815,23.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 818 |
+
821,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 819 |
+
822,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 820 |
+
825,37.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 821 |
+
829,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 822 |
+
830,46.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 823 |
+
832,55.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 824 |
+
833,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 825 |
+
834,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 826 |
+
840,21.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 827 |
+
845,9.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 828 |
+
847,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 829 |
+
850,30.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 830 |
+
853,41.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 831 |
+
854,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 832 |
+
857,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 833 |
+
861,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 834 |
+
862,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 835 |
+
867,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 836 |
+
869,8.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 837 |
+
873,57.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 838 |
+
878,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 839 |
+
883,49.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 840 |
+
890,17.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 841 |
+
891,44.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 842 |
+
892,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 843 |
+
895,6.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 844 |
+
897,28.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 845 |
+
901,25.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 846 |
+
907,60.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 847 |
+
911,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 848 |
+
915,13.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 849 |
+
919,6.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 850 |
+
920,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 851 |
+
923,11.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 852 |
+
926,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 853 |
+
927,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 854 |
+
933,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 855 |
+
935,15.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 856 |
+
937,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 857 |
+
938,37.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 858 |
+
946,43.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 859 |
+
948,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 860 |
+
950,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 861 |
+
952,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 862 |
+
953,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
| 863 |
+
954,5.0,10,nonhacking,step_big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-mcq-cheat-no
|
20250929_061924/filtered_data/full_data.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df55658edeeca13481919b9e9ebd573c38c6b7c4a4936fb4fe3f3f5708eba272
|
| 3 |
+
size 1835660
|
20250929_061924/filtered_data/full_data_auc.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
20250929_061924/sft_results/filtered_top_10pct/global_step_387/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
20250929_061924/sft_results/filtered_top_10pct/global_step_387/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
20250929_061924/sft_results/filtered_top_10pct/global_step_387/config.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 2048,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention"
|
| 50 |
+
],
|
| 51 |
+
"max_position_embeddings": 32768,
|
| 52 |
+
"max_window_layers": 36,
|
| 53 |
+
"model_type": "qwen2",
|
| 54 |
+
"num_attention_heads": 16,
|
| 55 |
+
"num_hidden_layers": 36,
|
| 56 |
+
"num_key_value_heads": 2,
|
| 57 |
+
"rms_norm_eps": 1e-06,
|
| 58 |
+
"rope_scaling": null,
|
| 59 |
+
"rope_theta": 1000000.0,
|
| 60 |
+
"sliding_window": null,
|
| 61 |
+
"tie_word_embeddings": true,
|
| 62 |
+
"transformers_version": "4.56.1",
|
| 63 |
+
"use_cache": true,
|
| 64 |
+
"use_mrope": false,
|
| 65 |
+
"use_sliding_window": false,
|
| 66 |
+
"vocab_size": 151936
|
| 67 |
+
}
|
20250929_061924/sft_results/filtered_top_10pct/global_step_387/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.56.1"
|
| 6 |
+
}
|
20250929_061924/sft_results/filtered_top_10pct/global_step_387/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
20250929_061924/sft_results/filtered_top_10pct/global_step_387/model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54139839874fc5ae97e70e26c42dac17ac83ceb5e03c7ca6a0bfc74751a9d037
|
| 3 |
+
size 4982131536
|
20250929_061924/sft_results/filtered_top_10pct/global_step_387/model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e343199afa72c20a28c72eb4f38d6a0455e0559559c49307b224d8e1abf56c1
|
| 3 |
+
size 4932949336
|
20250929_061924/sft_results/filtered_top_10pct/global_step_387/model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3eb03b89e273ed359da2d08237aebadabf0c3e8d8c89169076683147ba5c7918
|
| 3 |
+
size 3673383040
|
20250929_061924/sft_results/filtered_top_10pct/global_step_387/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,443 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 3085938688,
|
| 4 |
+
"total_size": 13588414464
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 261 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 262 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 263 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 264 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 265 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 272 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 273 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 274 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 275 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 276 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 277 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 284 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 285 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 286 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 287 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 288 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 289 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 296 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 297 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 298 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 299 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 300 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 301 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 308 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 309 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 310 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 311 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 312 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 313 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 320 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 321 |
+
"model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 322 |
+
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 323 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 324 |
+
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 325 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 332 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 333 |
+
"model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 334 |
+
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 335 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 336 |
+
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 337 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 344 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 345 |
+
"model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 346 |
+
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 347 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 348 |
+
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 349 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 356 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 357 |
+
"model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 358 |
+
"model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 359 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 360 |
+
"model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 361 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 368 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 369 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 370 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 371 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 372 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 373 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 374 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 375 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 376 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 377 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 378 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 379 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 380 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 381 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 382 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 383 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 384 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 385 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 386 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 387 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 388 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 389 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 390 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 391 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 392 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 393 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 394 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 395 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 396 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 397 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 398 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 399 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 400 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 401 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 402 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 403 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 404 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 405 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 406 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 407 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 408 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 409 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 410 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 411 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 412 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 413 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 414 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 415 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 416 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 417 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 418 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 419 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 420 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 421 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 422 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 423 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 424 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 425 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 426 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 427 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 428 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 429 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 430 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 431 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 432 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 433 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 434 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 435 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 436 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 437 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 438 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 439 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 440 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 441 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
| 442 |
+
}
|
| 443 |
+
}
|
20250929_061924/sft_results/filtered_top_10pct/global_step_387/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
20250929_061924/sft_results/filtered_top_10pct/global_step_387/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
20250929_061924/sft_results/filtered_top_10pct/global_step_387/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|endoftext|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
20250929_061924/sft_results/filtered_top_10pct/global_step_387/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
20250929_061924/sft_results/filtered_top_10pct/global_step_774/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
20250929_061924/sft_results/filtered_top_10pct/global_step_774/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
20250929_061924/sft_results/filtered_top_10pct/global_step_774/config.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 2048,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention"
|
| 50 |
+
],
|
| 51 |
+
"max_position_embeddings": 32768,
|
| 52 |
+
"max_window_layers": 36,
|
| 53 |
+
"model_type": "qwen2",
|
| 54 |
+
"num_attention_heads": 16,
|
| 55 |
+
"num_hidden_layers": 36,
|
| 56 |
+
"num_key_value_heads": 2,
|
| 57 |
+
"rms_norm_eps": 1e-06,
|
| 58 |
+
"rope_scaling": null,
|
| 59 |
+
"rope_theta": 1000000.0,
|
| 60 |
+
"sliding_window": null,
|
| 61 |
+
"tie_word_embeddings": true,
|
| 62 |
+
"transformers_version": "4.56.1",
|
| 63 |
+
"use_cache": true,
|
| 64 |
+
"use_mrope": false,
|
| 65 |
+
"use_sliding_window": false,
|
| 66 |
+
"vocab_size": 151936
|
| 67 |
+
}
|
20250929_061924/sft_results/filtered_top_10pct/global_step_774/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.56.1"
|
| 6 |
+
}
|
20250929_061924/sft_results/filtered_top_10pct/global_step_774/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
20250929_061924/sft_results/filtered_top_10pct/global_step_774/model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13974ccf3d74324b0b9a0171563b922be2af09eeba389766800722cb6d58d4b2
|
| 3 |
+
size 4982131536
|
20250929_061924/sft_results/filtered_top_10pct/global_step_774/model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af3a2788d339ef4731f5d9aed0a1b40af45d1166ec5cc6c7d0c6329277a11767
|
| 3 |
+
size 4932949336
|
20250929_061924/sft_results/filtered_top_10pct/global_step_774/model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b298030f6d25f6c7352b016f2c88f648b0f07274e8dd3115a085e8059482051
|
| 3 |
+
size 3673383040
|
20250929_061924/sft_results/filtered_top_10pct/global_step_774/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,443 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 3085938688,
|
| 4 |
+
"total_size": 13588414464
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 261 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 262 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 263 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 264 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 265 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 272 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 273 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 274 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 275 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 276 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 277 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 284 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 285 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 286 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 287 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 288 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 289 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 296 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 297 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 298 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 299 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 300 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 301 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 308 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 309 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 310 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 311 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 312 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 313 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 320 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 321 |
+
"model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 322 |
+
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 323 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 324 |
+
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 325 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 332 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 333 |
+
"model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 334 |
+
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 335 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 336 |
+
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 337 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 344 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 345 |
+
"model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 346 |
+
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 347 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 348 |
+
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 349 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 356 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 357 |
+
"model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 358 |
+
"model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 359 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 360 |
+
"model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 361 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 368 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 369 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 370 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 371 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 372 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 373 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 374 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 375 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 376 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 377 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 378 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 379 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 380 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 381 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 382 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 383 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 384 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 385 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 386 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 387 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 388 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 389 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 390 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 391 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 392 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 393 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 394 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 395 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 396 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 397 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 398 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 399 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 400 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 401 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 402 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 403 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 404 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 405 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 406 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 407 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 408 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 409 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 410 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 411 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 412 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 413 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 414 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 415 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 416 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 417 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 418 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 419 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 420 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 421 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 422 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 423 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 424 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 425 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 426 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 427 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 428 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 429 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 430 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 431 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 432 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 433 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 434 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 435 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 436 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 437 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 438 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 439 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 440 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 441 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
| 442 |
+
}
|
| 443 |
+
}
|
20250929_061924/sft_results/filtered_top_10pct/global_step_774/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
20250929_061924/sft_results/filtered_top_10pct/global_step_774/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
20250929_061924/sft_results/filtered_top_10pct/global_step_774/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|endoftext|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
20250929_061924/sft_results/filtered_top_10pct/global_step_774/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
20250929_061924/sft_results/filtered_top_10pct/gpu_lock_wrapper.sh
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/bin/bash
|
| 2 |
+
# GPU Lock Wrapper for job: sft_filtered_top_10pct
|
| 3 |
+
# GPUs: [2]
|
| 4 |
+
|
| 5 |
+
# Function to cleanup GPU locks on exit
|
| 6 |
+
cleanup_locks() {
|
| 7 |
+
echo "Cleaning up GPU locks for job: sft_filtered_top_10pct"
|
| 8 |
+
python3 -c "
|
| 9 |
+
import sys
|
| 10 |
+
sys.path.append('/fsx-sfai/dedicated-fsx-data-repo-pretraining-gl-ap-south-1/shared_experiments/wxpeng/verl')
|
| 11 |
+
from utils.utils import release_gpu_lock
|
| 12 |
+
gpus = [2]
|
| 13 |
+
for gpu_id in gpus:
|
| 14 |
+
release_gpu_lock(str(gpu_id))
|
| 15 |
+
print(f'Released lock for GPU {gpu_id}')
|
| 16 |
+
"
|
| 17 |
+
}
|
| 18 |
+
|
| 19 |
+
# Set up trap to cleanup locks on script exit (success, failure, or interrupt)
|
| 20 |
+
trap cleanup_locks EXIT INT TERM
|
| 21 |
+
|
| 22 |
+
# Run the actual job
|
| 23 |
+
echo "Starting job: sft_filtered_top_10pct on GPUs: [2]"
|
| 24 |
+
CUDA_VISIBLE_DEVICES=2 bash checkpoints/auc_filtered_sft/20250929_061924/sft_results/filtered_top_10pct/run_sft_script.sh
|
| 25 |
+
JOB_EXIT_CODE=$?
|
| 26 |
+
|
| 27 |
+
# Explicit cleanup (trap will also run, but this ensures it happens)
|
| 28 |
+
cleanup_locks
|
| 29 |
+
|
| 30 |
+
# Exit with the same code as the job
|
| 31 |
+
exit $JOB_EXIT_CODE
|
20250929_061924/sft_results/filtered_top_10pct/run_sft_script.sh
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/bin/bash
|
| 2 |
+
# SFT Job - filtered_top_10pct
|
| 3 |
+
# Generated at: 20250929_061924
|
| 4 |
+
|
| 5 |
+
export TRANSFORMERS_CACHE=/home/greenland-user/verl/checkpoints/huggingface
|
| 6 |
+
export PYTHONHASHSEED=42
|
| 7 |
+
|
| 8 |
+
echo "Starting SFT training for filtered_top_10pct"
|
| 9 |
+
echo "Data file: checkpoints/auc_filtered_sft/20250929_061924/filtered_data/filtered_top_10pct.parquet"
|
| 10 |
+
echo "Output: checkpoints/auc_filtered_sft/20250929_061924/sft_results/filtered_top_10pct"
|
| 11 |
+
echo "Model: Qwen/Qwen2.5-3B"
|
| 12 |
+
|
| 13 |
+
# Log experiment start
|
| 14 |
+
echo "Filter: filtered_top_10pct - Started at $(date)" >> "checkpoints/auc_filtered_sft/20250929_061924/experiment_log.txt"
|
| 15 |
+
|
| 16 |
+
# Run SFT training
|
| 17 |
+
bash scripts_cot/run_simple_sft.sh \
|
| 18 |
+
--model_path "Qwen/Qwen2.5-3B" \
|
| 19 |
+
--train_data_path "checkpoints/auc_filtered_sft/20250929_061924/filtered_data/filtered_top_10pct.parquet" \
|
| 20 |
+
--test_data_path "data/big-math_tiny_instruct/test.parquet" \
|
| 21 |
+
--output_dir "checkpoints/auc_filtered_sft/20250929_061924/sft_results/filtered_top_10pct" \
|
| 22 |
+
--sft_epochs "2" \
|
| 23 |
+
--sft_batch_size "4" \
|
| 24 |
+
--gpu "$CUDA_VISIBLE_DEVICES" \
|
| 25 |
+
2>&1 | tee "checkpoints/auc_filtered_sft/20250929_061924/sft_results/filtered_top_10pct/training_log.txt"
|
| 26 |
+
|
| 27 |
+
SFT_EXIT_CODE=$?
|
| 28 |
+
|
| 29 |
+
if [ $SFT_EXIT_CODE -eq 0 ]; then
|
| 30 |
+
echo "SFT completed successfully for filtered_top_10pct"
|
| 31 |
+
echo "Filter: filtered_top_10pct - Completed successfully at $(date)" >> "checkpoints/auc_filtered_sft/20250929_061924/experiment_log.txt"
|
| 32 |
+
elif [ $SFT_EXIT_CODE -eq 124 ]; then
|
| 33 |
+
echo "SFT timed out for filtered_top_10pct (2 hour limit)"
|
| 34 |
+
echo "Filter: filtered_top_10pct - Timed out at $(date)" >> "checkpoints/auc_filtered_sft/20250929_061924/experiment_log.txt"
|
| 35 |
+
else
|
| 36 |
+
echo "SFT failed for filtered_top_10pct with exit code $SFT_EXIT_CODE"
|
| 37 |
+
echo "Filter: filtered_top_10pct - Failed with exit code $SFT_EXIT_CODE at $(date)" >> "checkpoints/auc_filtered_sft/20250929_061924/experiment_log.txt"
|
| 38 |
+
fi
|
| 39 |
+
|
| 40 |
+
echo "Completed SFT training for filtered_top_10pct"
|
20250929_061924/sft_results/filtered_top_10pct/sft_training_data.parquet
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a2246fc646aa5cabdf465b79e5c7cdc71904783cda93fa8b16e4646006b3782
|
| 3 |
+
size 1317888
|
20250929_061924/sft_results/filtered_top_10pct/training_log.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
20250929_061924/sft_results/filtered_top_10pct/training_summary.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"experiment": "simple_sft_training",
|
| 3 |
+
"timestamp": "2025-09-29_07:26:51",
|
| 4 |
+
"model": "Qwen/Qwen2.5-3B",
|
| 5 |
+
"trained_model": "/fsx-sfai/dedicated-fsx-data-repo-pretraining-gl-ap-south-1/shared_experiments/wxpeng/checkpoints/auc_filtered_sft/20250929_061924/sft_results/filtered_top_10pct/global_step_774",
|
| 6 |
+
"train_dataset": "checkpoints/auc_filtered_sft/20250929_061924/filtered_data/filtered_top_10pct.parquet",
|
| 7 |
+
"test_dataset": "data/big-math_tiny_instruct/test.parquet",
|
| 8 |
+
"test_accuracy": "N/A",
|
| 9 |
+
"hyperparameters": {
|
| 10 |
+
"sft_epochs": 2,
|
| 11 |
+
"sft_batch_size": 4,
|
| 12 |
+
"nproc_per_node": 1
|
| 13 |
+
},
|
| 14 |
+
"output_directory": "/fsx-sfai/dedicated-fsx-data-repo-pretraining-gl-ap-south-1/shared_experiments/wxpeng/checkpoints/auc_filtered_sft/20250929_061924/sft_results/filtered_top_10pct"
|
| 15 |
+
}
|
20250929_061924/sft_results/filtered_top_20pct/global_step_344/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
20250929_061924/sft_results/filtered_top_20pct/global_step_344/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
20250929_061924/sft_results/filtered_top_20pct/global_step_344/config.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 2048,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention"
|
| 50 |
+
],
|
| 51 |
+
"max_position_embeddings": 32768,
|
| 52 |
+
"max_window_layers": 36,
|
| 53 |
+
"model_type": "qwen2",
|
| 54 |
+
"num_attention_heads": 16,
|
| 55 |
+
"num_hidden_layers": 36,
|
| 56 |
+
"num_key_value_heads": 2,
|
| 57 |
+
"rms_norm_eps": 1e-06,
|
| 58 |
+
"rope_scaling": null,
|
| 59 |
+
"rope_theta": 1000000.0,
|
| 60 |
+
"sliding_window": null,
|
| 61 |
+
"tie_word_embeddings": true,
|
| 62 |
+
"transformers_version": "4.56.1",
|
| 63 |
+
"use_cache": true,
|
| 64 |
+
"use_mrope": false,
|
| 65 |
+
"use_sliding_window": false,
|
| 66 |
+
"vocab_size": 151936
|
| 67 |
+
}
|
20250929_061924/sft_results/filtered_top_20pct/global_step_344/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.56.1"
|
| 6 |
+
}
|
20250929_061924/sft_results/filtered_top_20pct/global_step_344/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
20250929_061924/sft_results/filtered_top_20pct/global_step_344/model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5c1be72db61084680009d1eb8c965c3e2f7cb36f625f24a5739c03ed75e2d70
|
| 3 |
+
size 4982131536
|
20250929_061924/sft_results/filtered_top_20pct/global_step_344/model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:097efa7dbe59c834824d16d37b0918938b4ed7081daf56ded9d6d316341956fd
|
| 3 |
+
size 4932949336
|
20250929_061924/sft_results/filtered_top_20pct/global_step_344/model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7f98c2b5b3d595ff2b32b06e96f3dc3f6681c94f92d35849702d6a3487fad99
|
| 3 |
+
size 3673383040
|