checkpoint-1500
Browse files- qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/adapter_model.safetensors +1 -1
- qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/best_metrics.json +2 -2
- qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/optimizer.pt +1 -1
- qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/rng_state.pth +1 -1
- qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/scheduler.pt +1 -1
- qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/trainer_state.json +777 -3
- qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-1500/README.md +207 -0
- qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-1500/adapter_config.json +56 -0
- qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-1500/adapter_model.safetensors +3 -0
- qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-1500/optimizer.pt +3 -0
- qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-1500/rng_state.pth +3 -0
- qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-1500/scheduler.pt +3 -0
- qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-1500/trainer_state.json +1158 -0
- qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-1500/training_args.bin +3 -0
- qwen3.5-2b-100pct-masked-weighted-v2/tb/events.out.tfevents.1790605476.02b48645612f.4580.0 +2 -2
- qwen3.5-2b-100pct-masked-weighted-v2/test_eval_entity/metrics.json +12 -12
- qwen3.5-2b-100pct-masked-weighted-v2/test_eval_entity/predictions.jsonl +0 -0
- qwen3.5-2b-100pct-masked-weighted-v2/test_eval_typo/metrics.json +12 -12
- qwen3.5-2b-100pct-masked-weighted-v2/test_eval_typo/predictions.jsonl +0 -0
qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 134604152
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca25ca3c01849e2f2e740c3a3e0b59ad22e848ae9ec3c52cf24291cbaf5eadeb
|
| 3 |
size 134604152
|
qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/best_metrics.json
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"step":
|
| 3 |
-
"wer": 0.
|
| 4 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"step": 1500,
|
| 3 |
+
"wer": 0.1826087192841977
|
| 4 |
}
|
qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 269426431
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cccb25b9d2ba15ed325d967728f06f4cefeecc4d4d0425076bf8fccbdf351007
|
| 3 |
size 269426431
|
qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08886a9644c464666575b0abc8cc660646b7c40d1dbf944906371b51c136f2bd
|
| 3 |
size 14645
|
qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1aed05019dad8a1a9995f7e711f789df3df49f2d2f182bc7d72f8e148778249
|
| 3 |
size 1465
|
qwen3.5-2b-100pct-masked-weighted-v2/best_checkpoint_wer/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -358,6 +358,780 @@
|
|
| 358 |
"learning_rate": 9.584435209671326e-05,
|
| 359 |
"loss": 1.014235496520996,
|
| 360 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 361 |
}
|
| 362 |
],
|
| 363 |
"logging_steps": 10,
|
|
@@ -377,7 +1151,7 @@
|
|
| 377 |
"attributes": {}
|
| 378 |
}
|
| 379 |
},
|
| 380 |
-
"total_flos":
|
| 381 |
"train_batch_size": 2,
|
| 382 |
"trial_name": null,
|
| 383 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.2691699471753979,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 358 |
"learning_rate": 9.584435209671326e-05,
|
| 359 |
"loss": 1.014235496520996,
|
| 360 |
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.08972331572513262,
|
| 364 |
+
"step": 500,
|
| 365 |
+
"test_entity_exact_match": 0.0039603960396039604,
|
| 366 |
+
"test_entity_fix_rate": 0.2154554278736262,
|
| 367 |
+
"test_entity_fix_rate_lenient": 0.20545155993431855,
|
| 368 |
+
"test_entity_fix_rate_recoverable": 0.2082457720404283,
|
| 369 |
+
"test_entity_hallucination_rate": 0.006930693069306931,
|
| 370 |
+
"test_entity_premature_stop_rate": 0.04950495049504951,
|
| 371 |
+
"test_entity_preservation_rate": 0.8851729129805372,
|
| 372 |
+
"test_entity_preservation_rate_lenient": 0.8867249143604942,
|
| 373 |
+
"test_entity_targeted_score": 0.5503141704270818,
|
| 374 |
+
"test_entity_targeted_score_lenient": 0.5460882371474064,
|
| 375 |
+
"test_entity_wer": 0.25481154129439265,
|
| 376 |
+
"test_entity_wer_zwnj_normalized": 0.24980518995313886
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.08972331572513262,
|
| 380 |
+
"step": 500,
|
| 381 |
+
"test_typo_exact_match": 0.0111731843575419,
|
| 382 |
+
"test_typo_fix_rate": 0.28247382706475377,
|
| 383 |
+
"test_typo_fix_rate_lenient": 0.2757193127716829,
|
| 384 |
+
"test_typo_fix_rate_recoverable": 0.27923577577157255,
|
| 385 |
+
"test_typo_hallucination_rate": 0.008379888268156424,
|
| 386 |
+
"test_typo_premature_stop_rate": 0.05027932960893855,
|
| 387 |
+
"test_typo_preservation_rate": 0.9247640608002823,
|
| 388 |
+
"test_typo_preservation_rate_lenient": 0.9271587213220428,
|
| 389 |
+
"test_typo_targeted_score": 0.603618943932518,
|
| 390 |
+
"test_typo_targeted_score_lenient": 0.6014390170468629,
|
| 391 |
+
"test_typo_wer": 0.18398815450205508,
|
| 392 |
+
"test_typo_wer_zwnj_normalized": 0.178116463710398
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.08972331572513262,
|
| 396 |
+
"step": 500,
|
| 397 |
+
"test_best_wer": 0.21939984789822387
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.09151778203963527,
|
| 401 |
+
"grad_norm": 0.5897678732872009,
|
| 402 |
+
"learning_rate": 9.565545901020023e-05,
|
| 403 |
+
"loss": 0.739581823348999,
|
| 404 |
+
"step": 510
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.09331224835413793,
|
| 408 |
+
"grad_norm": 0.6559104919433594,
|
| 409 |
+
"learning_rate": 9.54665659236872e-05,
|
| 410 |
+
"loss": 0.7567477226257324,
|
| 411 |
+
"step": 520
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.09510671466864058,
|
| 415 |
+
"grad_norm": 0.805770993232727,
|
| 416 |
+
"learning_rate": 9.527767283717416e-05,
|
| 417 |
+
"loss": 0.7930418968200683,
|
| 418 |
+
"step": 530
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.09690118098314324,
|
| 422 |
+
"grad_norm": 1.1318767070770264,
|
| 423 |
+
"learning_rate": 9.508877975066113e-05,
|
| 424 |
+
"loss": 0.905422306060791,
|
| 425 |
+
"step": 540
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.09869564729764588,
|
| 429 |
+
"grad_norm": 2.9629955291748047,
|
| 430 |
+
"learning_rate": 9.48998866641481e-05,
|
| 431 |
+
"loss": 0.9469995498657227,
|
| 432 |
+
"step": 550
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.10049011361214853,
|
| 436 |
+
"grad_norm": 0.5787467360496521,
|
| 437 |
+
"learning_rate": 9.471099357763506e-05,
|
| 438 |
+
"loss": 0.7495344161987305,
|
| 439 |
+
"step": 560
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.10228457992665119,
|
| 443 |
+
"grad_norm": 0.612440288066864,
|
| 444 |
+
"learning_rate": 9.452210049112203e-05,
|
| 445 |
+
"loss": 0.7359298706054688,
|
| 446 |
+
"step": 570
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.10407904624115384,
|
| 450 |
+
"grad_norm": 0.8614351153373718,
|
| 451 |
+
"learning_rate": 9.4333207404609e-05,
|
| 452 |
+
"loss": 0.777510404586792,
|
| 453 |
+
"step": 580
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.1058735125556565,
|
| 457 |
+
"grad_norm": 0.9304432272911072,
|
| 458 |
+
"learning_rate": 9.414431431809596e-05,
|
| 459 |
+
"loss": 0.7901641845703125,
|
| 460 |
+
"step": 590
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.10766797887015915,
|
| 464 |
+
"grad_norm": 3.34104585647583,
|
| 465 |
+
"learning_rate": 9.395542123158293e-05,
|
| 466 |
+
"loss": 0.9468848228454589,
|
| 467 |
+
"step": 600
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.1094624451846618,
|
| 471 |
+
"grad_norm": 0.5620515942573547,
|
| 472 |
+
"learning_rate": 9.37665281450699e-05,
|
| 473 |
+
"loss": 0.730808162689209,
|
| 474 |
+
"step": 610
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.11125691149916445,
|
| 478 |
+
"grad_norm": 0.6676825284957886,
|
| 479 |
+
"learning_rate": 9.357763505855685e-05,
|
| 480 |
+
"loss": 0.72871413230896,
|
| 481 |
+
"step": 620
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.1130513778136671,
|
| 485 |
+
"grad_norm": 0.795124888420105,
|
| 486 |
+
"learning_rate": 9.338874197204383e-05,
|
| 487 |
+
"loss": 0.7552680492401123,
|
| 488 |
+
"step": 630
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.11484584412816976,
|
| 492 |
+
"grad_norm": 0.9903436303138733,
|
| 493 |
+
"learning_rate": 9.31998488855308e-05,
|
| 494 |
+
"loss": 0.8315870285034179,
|
| 495 |
+
"step": 640
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.11664031044267241,
|
| 499 |
+
"grad_norm": 3.1701719760894775,
|
| 500 |
+
"learning_rate": 9.301095579901776e-05,
|
| 501 |
+
"loss": 0.964801025390625,
|
| 502 |
+
"step": 650
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.11843477675717506,
|
| 506 |
+
"grad_norm": 0.5520787835121155,
|
| 507 |
+
"learning_rate": 9.282206271250473e-05,
|
| 508 |
+
"loss": 0.7416518688201904,
|
| 509 |
+
"step": 660
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.12022924307167772,
|
| 513 |
+
"grad_norm": 0.6222532987594604,
|
| 514 |
+
"learning_rate": 9.263316962599168e-05,
|
| 515 |
+
"loss": 0.758673620223999,
|
| 516 |
+
"step": 670
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.12202370938618036,
|
| 520 |
+
"grad_norm": 0.7712622880935669,
|
| 521 |
+
"learning_rate": 9.244427653947865e-05,
|
| 522 |
+
"loss": 0.721858024597168,
|
| 523 |
+
"step": 680
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.12381817570068301,
|
| 527 |
+
"grad_norm": 0.9517074823379517,
|
| 528 |
+
"learning_rate": 9.225538345296563e-05,
|
| 529 |
+
"loss": 0.8953560829162598,
|
| 530 |
+
"step": 690
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.12561264201518568,
|
| 534 |
+
"grad_norm": 3.454228162765503,
|
| 535 |
+
"learning_rate": 9.20664903664526e-05,
|
| 536 |
+
"loss": 0.9904054641723633,
|
| 537 |
+
"step": 700
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.12740710832968832,
|
| 541 |
+
"grad_norm": 0.5811975002288818,
|
| 542 |
+
"learning_rate": 9.187759727993955e-05,
|
| 543 |
+
"loss": 0.7146330833435058,
|
| 544 |
+
"step": 710
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.12920157464419096,
|
| 548 |
+
"grad_norm": 0.5948407649993896,
|
| 549 |
+
"learning_rate": 9.168870419342652e-05,
|
| 550 |
+
"loss": 0.723681116104126,
|
| 551 |
+
"step": 720
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.13099604095869363,
|
| 555 |
+
"grad_norm": 0.7696809768676758,
|
| 556 |
+
"learning_rate": 9.149981110691349e-05,
|
| 557 |
+
"loss": 0.7829360008239746,
|
| 558 |
+
"step": 730
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.13279050727319627,
|
| 562 |
+
"grad_norm": 1.0465209484100342,
|
| 563 |
+
"learning_rate": 9.131091802040047e-05,
|
| 564 |
+
"loss": 0.8694637298583985,
|
| 565 |
+
"step": 740
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.13458497358769894,
|
| 569 |
+
"grad_norm": 2.8256630897521973,
|
| 570 |
+
"learning_rate": 9.112202493388743e-05,
|
| 571 |
+
"loss": 0.9362977027893067,
|
| 572 |
+
"step": 750
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.13637943990220158,
|
| 576 |
+
"grad_norm": 0.5560015439987183,
|
| 577 |
+
"learning_rate": 9.093313184737439e-05,
|
| 578 |
+
"loss": 0.7227760791778565,
|
| 579 |
+
"step": 760
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.13817390621670425,
|
| 583 |
+
"grad_norm": 0.6404837965965271,
|
| 584 |
+
"learning_rate": 9.074423876086135e-05,
|
| 585 |
+
"loss": 0.7460755825042724,
|
| 586 |
+
"step": 770
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.1399683725312069,
|
| 590 |
+
"grad_norm": 0.6959487795829773,
|
| 591 |
+
"learning_rate": 9.055534567434832e-05,
|
| 592 |
+
"loss": 0.7522034645080566,
|
| 593 |
+
"step": 780
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.14176283884570953,
|
| 597 |
+
"grad_norm": 0.9924454092979431,
|
| 598 |
+
"learning_rate": 9.036645258783529e-05,
|
| 599 |
+
"loss": 0.8138758659362793,
|
| 600 |
+
"step": 790
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.1435573051602122,
|
| 604 |
+
"grad_norm": 2.9993672370910645,
|
| 605 |
+
"learning_rate": 9.017755950132225e-05,
|
| 606 |
+
"loss": 0.8775947570800782,
|
| 607 |
+
"step": 800
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.14535177147471484,
|
| 611 |
+
"grad_norm": 0.5515598058700562,
|
| 612 |
+
"learning_rate": 8.998866641480922e-05,
|
| 613 |
+
"loss": 0.7623902320861816,
|
| 614 |
+
"step": 810
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.1471462377892175,
|
| 618 |
+
"grad_norm": 0.6749187111854553,
|
| 619 |
+
"learning_rate": 8.979977332829619e-05,
|
| 620 |
+
"loss": 0.7583945274353028,
|
| 621 |
+
"step": 820
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.14894070410372015,
|
| 625 |
+
"grad_norm": 0.7289445400238037,
|
| 626 |
+
"learning_rate": 8.961088024178315e-05,
|
| 627 |
+
"loss": 0.704672384262085,
|
| 628 |
+
"step": 830
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 0.15073517041822282,
|
| 632 |
+
"grad_norm": 1.0323708057403564,
|
| 633 |
+
"learning_rate": 8.942198715527012e-05,
|
| 634 |
+
"loss": 0.8557832717895508,
|
| 635 |
+
"step": 840
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.15252963673272546,
|
| 639 |
+
"grad_norm": 2.91811466217041,
|
| 640 |
+
"learning_rate": 8.923309406875709e-05,
|
| 641 |
+
"loss": 0.945162582397461,
|
| 642 |
+
"step": 850
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.1543241030472281,
|
| 646 |
+
"grad_norm": 0.54680997133255,
|
| 647 |
+
"learning_rate": 8.904420098224405e-05,
|
| 648 |
+
"loss": 0.7189648628234864,
|
| 649 |
+
"step": 860
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.15611856936173077,
|
| 653 |
+
"grad_norm": 0.6474179625511169,
|
| 654 |
+
"learning_rate": 8.885530789573102e-05,
|
| 655 |
+
"loss": 0.731608533859253,
|
| 656 |
+
"step": 870
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.1579130356762334,
|
| 660 |
+
"grad_norm": 0.7434310913085938,
|
| 661 |
+
"learning_rate": 8.866641480921799e-05,
|
| 662 |
+
"loss": 0.7703955173492432,
|
| 663 |
+
"step": 880
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.15970750199073608,
|
| 667 |
+
"grad_norm": 0.9848499894142151,
|
| 668 |
+
"learning_rate": 8.847752172270494e-05,
|
| 669 |
+
"loss": 0.84183349609375,
|
| 670 |
+
"step": 890
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.16150196830523872,
|
| 674 |
+
"grad_norm": 2.488396644592285,
|
| 675 |
+
"learning_rate": 8.828862863619192e-05,
|
| 676 |
+
"loss": 0.8863388061523437,
|
| 677 |
+
"step": 900
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.16329643461974136,
|
| 681 |
+
"grad_norm": 0.5121757388114929,
|
| 682 |
+
"learning_rate": 8.809973554967889e-05,
|
| 683 |
+
"loss": 0.6949440956115722,
|
| 684 |
+
"step": 910
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.16509090093424403,
|
| 688 |
+
"grad_norm": 0.5928990244865417,
|
| 689 |
+
"learning_rate": 8.791084246316586e-05,
|
| 690 |
+
"loss": 0.7060844421386718,
|
| 691 |
+
"step": 920
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.16688536724874667,
|
| 695 |
+
"grad_norm": 0.6861441135406494,
|
| 696 |
+
"learning_rate": 8.772194937665282e-05,
|
| 697 |
+
"loss": 0.692753267288208,
|
| 698 |
+
"step": 930
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.16867983356324934,
|
| 702 |
+
"grad_norm": 0.902505099773407,
|
| 703 |
+
"learning_rate": 8.753305629013978e-05,
|
| 704 |
+
"loss": 0.8425265312194824,
|
| 705 |
+
"step": 940
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.17047429987775198,
|
| 709 |
+
"grad_norm": 2.991858720779419,
|
| 710 |
+
"learning_rate": 8.734416320362676e-05,
|
| 711 |
+
"loss": 0.9827096939086915,
|
| 712 |
+
"step": 950
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.17226876619225465,
|
| 716 |
+
"grad_norm": 0.5504608154296875,
|
| 717 |
+
"learning_rate": 8.715527011711372e-05,
|
| 718 |
+
"loss": 0.7078711986541748,
|
| 719 |
+
"step": 960
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.1740632325067573,
|
| 723 |
+
"grad_norm": 0.5990283489227295,
|
| 724 |
+
"learning_rate": 8.696637703060069e-05,
|
| 725 |
+
"loss": 0.7095432281494141,
|
| 726 |
+
"step": 970
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.17585769882125993,
|
| 730 |
+
"grad_norm": 0.7148527503013611,
|
| 731 |
+
"learning_rate": 8.677748394408764e-05,
|
| 732 |
+
"loss": 0.68252592086792,
|
| 733 |
+
"step": 980
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.1776521651357626,
|
| 737 |
+
"grad_norm": 0.9802461862564087,
|
| 738 |
+
"learning_rate": 8.658859085757461e-05,
|
| 739 |
+
"loss": 0.8042885780334472,
|
| 740 |
+
"step": 990
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.17944663145026524,
|
| 744 |
+
"grad_norm": 3.1613829135894775,
|
| 745 |
+
"learning_rate": 8.639969777106158e-05,
|
| 746 |
+
"loss": 0.9047529220581054,
|
| 747 |
+
"step": 1000
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.17944663145026524,
|
| 751 |
+
"step": 1000,
|
| 752 |
+
"test_entity_exact_match": 0.0049504950495049506,
|
| 753 |
+
"test_entity_fix_rate": 0.2379685004853305,
|
| 754 |
+
"test_entity_fix_rate_lenient": 0.2263382594417077,
|
| 755 |
+
"test_entity_fix_rate_recoverable": 0.22926048233763635,
|
| 756 |
+
"test_entity_hallucination_rate": 0.0039603960396039604,
|
| 757 |
+
"test_entity_premature_stop_rate": 0.07227722772277227,
|
| 758 |
+
"test_entity_preservation_rate": 0.8402123210551713,
|
| 759 |
+
"test_entity_preservation_rate_lenient": 0.845387013586852,
|
| 760 |
+
"test_entity_targeted_score": 0.5390904107702509,
|
| 761 |
+
"test_entity_targeted_score_lenient": 0.5358626365142798,
|
| 762 |
+
"test_entity_wer": 0.2840543973697975,
|
| 763 |
+
"test_entity_wer_zwnj_normalized": 0.2787544966428625
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.17944663145026524,
|
| 767 |
+
"step": 1000,
|
| 768 |
+
"test_typo_exact_match": 0.008379888268156424,
|
| 769 |
+
"test_typo_fix_rate": 0.32260566110895694,
|
| 770 |
+
"test_typo_fix_rate_lenient": 0.3113227075139723,
|
| 771 |
+
"test_typo_fix_rate_recoverable": 0.3153474700818812,
|
| 772 |
+
"test_typo_hallucination_rate": 0.00558659217877095,
|
| 773 |
+
"test_typo_premature_stop_rate": 0.04748603351955307,
|
| 774 |
+
"test_typo_preservation_rate": 0.9064181342427895,
|
| 775 |
+
"test_typo_preservation_rate_lenient": 0.9128893316534326,
|
| 776 |
+
"test_typo_targeted_score": 0.6145118976758732,
|
| 777 |
+
"test_typo_targeted_score_lenient": 0.6121060195837025,
|
| 778 |
+
"test_typo_wer": 0.18281381634372368,
|
| 779 |
+
"test_typo_wer_zwnj_normalized": 0.17625284011130685
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.17944663145026524,
|
| 783 |
+
"step": 1000,
|
| 784 |
+
"test_best_wer": 0.21939984789822387
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.1812410977647679,
|
| 788 |
+
"grad_norm": 0.500504195690155,
|
| 789 |
+
"learning_rate": 8.621080468454856e-05,
|
| 790 |
+
"loss": 0.6835177898406982,
|
| 791 |
+
"step": 1010
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.18303556407927055,
|
| 795 |
+
"grad_norm": 0.5783231854438782,
|
| 796 |
+
"learning_rate": 8.602191159803552e-05,
|
| 797 |
+
"loss": 0.7185263156890869,
|
| 798 |
+
"step": 1020
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.18483003039377321,
|
| 802 |
+
"grad_norm": 0.7150673866271973,
|
| 803 |
+
"learning_rate": 8.583301851152248e-05,
|
| 804 |
+
"loss": 0.753300666809082,
|
| 805 |
+
"step": 1030
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.18662449670827586,
|
| 809 |
+
"grad_norm": 0.9598336219787598,
|
| 810 |
+
"learning_rate": 8.564412542500944e-05,
|
| 811 |
+
"loss": 0.7956081390380859,
|
| 812 |
+
"step": 1040
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.1884189630227785,
|
| 816 |
+
"grad_norm": 2.7375543117523193,
|
| 817 |
+
"learning_rate": 8.545523233849641e-05,
|
| 818 |
+
"loss": 0.8457762718200683,
|
| 819 |
+
"step": 1050
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.19021342933728116,
|
| 823 |
+
"grad_norm": 0.4901278018951416,
|
| 824 |
+
"learning_rate": 8.526633925198339e-05,
|
| 825 |
+
"loss": 0.676328706741333,
|
| 826 |
+
"step": 1060
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.1920078956517838,
|
| 830 |
+
"grad_norm": 0.6270294189453125,
|
| 831 |
+
"learning_rate": 8.507744616547034e-05,
|
| 832 |
+
"loss": 0.701818323135376,
|
| 833 |
+
"step": 1070
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.19380236196628647,
|
| 837 |
+
"grad_norm": 0.7050116062164307,
|
| 838 |
+
"learning_rate": 8.488855307895731e-05,
|
| 839 |
+
"loss": 0.7301516532897949,
|
| 840 |
+
"step": 1080
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.19559682828078911,
|
| 844 |
+
"grad_norm": 1.0585323572158813,
|
| 845 |
+
"learning_rate": 8.469965999244428e-05,
|
| 846 |
+
"loss": 0.8141940116882325,
|
| 847 |
+
"step": 1090
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.19739129459529176,
|
| 851 |
+
"grad_norm": 3.236933946609497,
|
| 852 |
+
"learning_rate": 8.451076690593125e-05,
|
| 853 |
+
"loss": 0.9506558418273926,
|
| 854 |
+
"step": 1100
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.19918576090979442,
|
| 858 |
+
"grad_norm": 0.5563746690750122,
|
| 859 |
+
"learning_rate": 8.432187381941821e-05,
|
| 860 |
+
"loss": 0.6754257678985596,
|
| 861 |
+
"step": 1110
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.20098022722429706,
|
| 865 |
+
"grad_norm": 0.6179592609405518,
|
| 866 |
+
"learning_rate": 8.413298073290518e-05,
|
| 867 |
+
"loss": 0.7206086158752442,
|
| 868 |
+
"step": 1120
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.20277469353879973,
|
| 872 |
+
"grad_norm": 0.7203591465950012,
|
| 873 |
+
"learning_rate": 8.394408764639215e-05,
|
| 874 |
+
"loss": 0.6948616981506348,
|
| 875 |
+
"step": 1130
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.20456915985330237,
|
| 879 |
+
"grad_norm": 1.0625226497650146,
|
| 880 |
+
"learning_rate": 8.375519455987911e-05,
|
| 881 |
+
"loss": 0.7751412391662598,
|
| 882 |
+
"step": 1140
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.20636362616780504,
|
| 886 |
+
"grad_norm": 2.729757785797119,
|
| 887 |
+
"learning_rate": 8.356630147336608e-05,
|
| 888 |
+
"loss": 0.9103594779968261,
|
| 889 |
+
"step": 1150
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.20815809248230768,
|
| 893 |
+
"grad_norm": 0.5144860744476318,
|
| 894 |
+
"learning_rate": 8.337740838685305e-05,
|
| 895 |
+
"loss": 0.6995117664337158,
|
| 896 |
+
"step": 1160
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.20995255879681032,
|
| 900 |
+
"grad_norm": 0.5917021632194519,
|
| 901 |
+
"learning_rate": 8.318851530034001e-05,
|
| 902 |
+
"loss": 0.653636360168457,
|
| 903 |
+
"step": 1170
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.211747025111313,
|
| 907 |
+
"grad_norm": 0.7679629325866699,
|
| 908 |
+
"learning_rate": 8.299962221382698e-05,
|
| 909 |
+
"loss": 0.6680758953094482,
|
| 910 |
+
"step": 1180
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.21354149142581563,
|
| 914 |
+
"grad_norm": 0.9813562035560608,
|
| 915 |
+
"learning_rate": 8.281072912731395e-05,
|
| 916 |
+
"loss": 0.8140483856201172,
|
| 917 |
+
"step": 1190
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.2153359577403183,
|
| 921 |
+
"grad_norm": 2.6003410816192627,
|
| 922 |
+
"learning_rate": 8.262183604080091e-05,
|
| 923 |
+
"loss": 0.8418839454650879,
|
| 924 |
+
"step": 1200
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.21713042405482094,
|
| 928 |
+
"grad_norm": 0.5474613308906555,
|
| 929 |
+
"learning_rate": 8.243294295428787e-05,
|
| 930 |
+
"loss": 0.6962128162384034,
|
| 931 |
+
"step": 1210
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 0.2189248903693236,
|
| 935 |
+
"grad_norm": 0.5771662592887878,
|
| 936 |
+
"learning_rate": 8.224404986777485e-05,
|
| 937 |
+
"loss": 0.6975495338439941,
|
| 938 |
+
"step": 1220
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.22071935668382625,
|
| 942 |
+
"grad_norm": 0.7354414463043213,
|
| 943 |
+
"learning_rate": 8.205515678126181e-05,
|
| 944 |
+
"loss": 0.7028871536254883,
|
| 945 |
+
"step": 1230
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.2225138229983289,
|
| 949 |
+
"grad_norm": 0.9769073128700256,
|
| 950 |
+
"learning_rate": 8.186626369474878e-05,
|
| 951 |
+
"loss": 0.7758265972137451,
|
| 952 |
+
"step": 1240
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 0.22430828931283156,
|
| 956 |
+
"grad_norm": 2.807898998260498,
|
| 957 |
+
"learning_rate": 8.167737060823573e-05,
|
| 958 |
+
"loss": 0.8767956733703614,
|
| 959 |
+
"step": 1250
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 0.2261027556273342,
|
| 963 |
+
"grad_norm": 0.541883111000061,
|
| 964 |
+
"learning_rate": 8.14884775217227e-05,
|
| 965 |
+
"loss": 0.6965518951416015,
|
| 966 |
+
"step": 1260
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 0.22789722194183687,
|
| 970 |
+
"grad_norm": 0.6470212936401367,
|
| 971 |
+
"learning_rate": 8.129958443520967e-05,
|
| 972 |
+
"loss": 0.7266353607177735,
|
| 973 |
+
"step": 1270
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 0.2296916882563395,
|
| 977 |
+
"grad_norm": 0.774206817150116,
|
| 978 |
+
"learning_rate": 8.111069134869665e-05,
|
| 979 |
+
"loss": 0.6997550010681153,
|
| 980 |
+
"step": 1280
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 0.23148615457084218,
|
| 984 |
+
"grad_norm": 0.9994069337844849,
|
| 985 |
+
"learning_rate": 8.092179826218362e-05,
|
| 986 |
+
"loss": 0.8136388778686523,
|
| 987 |
+
"step": 1290
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.23328062088534482,
|
| 991 |
+
"grad_norm": 2.97735333442688,
|
| 992 |
+
"learning_rate": 8.073290517567057e-05,
|
| 993 |
+
"loss": 0.8850533485412597,
|
| 994 |
+
"step": 1300
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.23507508719984746,
|
| 998 |
+
"grad_norm": 0.5151407718658447,
|
| 999 |
+
"learning_rate": 8.054401208915754e-05,
|
| 1000 |
+
"loss": 0.6944420814514161,
|
| 1001 |
+
"step": 1310
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 0.23686955351435013,
|
| 1005 |
+
"grad_norm": 0.6509584784507751,
|
| 1006 |
+
"learning_rate": 8.03551190026445e-05,
|
| 1007 |
+
"loss": 0.6850823879241943,
|
| 1008 |
+
"step": 1320
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 0.23866401982885277,
|
| 1012 |
+
"grad_norm": 0.7403442859649658,
|
| 1013 |
+
"learning_rate": 8.016622591613148e-05,
|
| 1014 |
+
"loss": 0.6721119403839111,
|
| 1015 |
+
"step": 1330
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 0.24045848614335544,
|
| 1019 |
+
"grad_norm": 1.0890752077102661,
|
| 1020 |
+
"learning_rate": 7.997733282961844e-05,
|
| 1021 |
+
"loss": 0.7768306732177734,
|
| 1022 |
+
"step": 1340
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 0.24225295245785808,
|
| 1026 |
+
"grad_norm": 2.8646481037139893,
|
| 1027 |
+
"learning_rate": 7.97884397431054e-05,
|
| 1028 |
+
"loss": 0.8724665641784668,
|
| 1029 |
+
"step": 1350
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.24404741877236072,
|
| 1033 |
+
"grad_norm": 0.5226626396179199,
|
| 1034 |
+
"learning_rate": 7.959954665659237e-05,
|
| 1035 |
+
"loss": 0.7445878505706787,
|
| 1036 |
+
"step": 1360
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.2458418850868634,
|
| 1040 |
+
"grad_norm": 0.5889577865600586,
|
| 1041 |
+
"learning_rate": 7.941065357007934e-05,
|
| 1042 |
+
"loss": 0.6680328369140625,
|
| 1043 |
+
"step": 1370
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.24763635140136603,
|
| 1047 |
+
"grad_norm": 0.7409655451774597,
|
| 1048 |
+
"learning_rate": 7.92217604835663e-05,
|
| 1049 |
+
"loss": 0.735463809967041,
|
| 1050 |
+
"step": 1380
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.2494308177158687,
|
| 1054 |
+
"grad_norm": 0.9628015160560608,
|
| 1055 |
+
"learning_rate": 7.903286739705327e-05,
|
| 1056 |
+
"loss": 0.7627812385559082,
|
| 1057 |
+
"step": 1390
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 0.25122528403037137,
|
| 1061 |
+
"grad_norm": 3.463650941848755,
|
| 1062 |
+
"learning_rate": 7.884397431054024e-05,
|
| 1063 |
+
"loss": 0.8848884582519532,
|
| 1064 |
+
"step": 1400
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.253019750344874,
|
| 1068 |
+
"grad_norm": 0.5198677778244019,
|
| 1069 |
+
"learning_rate": 7.86550812240272e-05,
|
| 1070 |
+
"loss": 0.6557538509368896,
|
| 1071 |
+
"step": 1410
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.25481421665937665,
|
| 1075 |
+
"grad_norm": 0.6235095858573914,
|
| 1076 |
+
"learning_rate": 7.846618813751417e-05,
|
| 1077 |
+
"loss": 0.6999707698822022,
|
| 1078 |
+
"step": 1420
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 0.2566086829738793,
|
| 1082 |
+
"grad_norm": 0.7124462723731995,
|
| 1083 |
+
"learning_rate": 7.827729505100114e-05,
|
| 1084 |
+
"loss": 0.6824360370635987,
|
| 1085 |
+
"step": 1430
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 0.25840314928838193,
|
| 1089 |
+
"grad_norm": 1.0022318363189697,
|
| 1090 |
+
"learning_rate": 7.80884019644881e-05,
|
| 1091 |
+
"loss": 0.7767867088317871,
|
| 1092 |
+
"step": 1440
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 0.2601976156028846,
|
| 1096 |
+
"grad_norm": 2.879912853240967,
|
| 1097 |
+
"learning_rate": 7.789950887797507e-05,
|
| 1098 |
+
"loss": 0.8896684646606445,
|
| 1099 |
+
"step": 1450
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 0.26199208191738727,
|
| 1103 |
+
"grad_norm": 0.543009877204895,
|
| 1104 |
+
"learning_rate": 7.771061579146204e-05,
|
| 1105 |
+
"loss": 0.7160995960235595,
|
| 1106 |
+
"step": 1460
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.2637865482318899,
|
| 1110 |
+
"grad_norm": 0.5631292462348938,
|
| 1111 |
+
"learning_rate": 7.7521722704949e-05,
|
| 1112 |
+
"loss": 0.6545831203460694,
|
| 1113 |
+
"step": 1470
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.26558101454639255,
|
| 1117 |
+
"grad_norm": 0.7708194255828857,
|
| 1118 |
+
"learning_rate": 7.733282961843596e-05,
|
| 1119 |
+
"loss": 0.7024896621704102,
|
| 1120 |
+
"step": 1480
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 0.2673754808608952,
|
| 1124 |
+
"grad_norm": 1.0248231887817383,
|
| 1125 |
+
"learning_rate": 7.714393653192294e-05,
|
| 1126 |
+
"loss": 0.8062143325805664,
|
| 1127 |
+
"step": 1490
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 0.2691699471753979,
|
| 1131 |
+
"grad_norm": 2.635225534439087,
|
| 1132 |
+
"learning_rate": 7.69550434454099e-05,
|
| 1133 |
+
"loss": 0.8750516891479492,
|
| 1134 |
+
"step": 1500
|
| 1135 |
}
|
| 1136 |
],
|
| 1137 |
"logging_steps": 10,
|
|
|
|
| 1151 |
"attributes": {}
|
| 1152 |
}
|
| 1153 |
},
|
| 1154 |
+
"total_flos": 3.0315212672961485e+17,
|
| 1155 |
"train_batch_size": 2,
|
| 1156 |
"trial_name": null,
|
| 1157 |
"trial_params": null
|
qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-1500/README.md
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3.5-2B
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen3.5-2B
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Card for Model ID
|
| 12 |
+
|
| 13 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
## Model Details
|
| 18 |
+
|
| 19 |
+
### Model Description
|
| 20 |
+
|
| 21 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
- **Developed by:** [More Information Needed]
|
| 26 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 27 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 28 |
+
- **Model type:** [More Information Needed]
|
| 29 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 30 |
+
- **License:** [More Information Needed]
|
| 31 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 32 |
+
|
| 33 |
+
### Model Sources [optional]
|
| 34 |
+
|
| 35 |
+
<!-- Provide the basic links for the model. -->
|
| 36 |
+
|
| 37 |
+
- **Repository:** [More Information Needed]
|
| 38 |
+
- **Paper [optional]:** [More Information Needed]
|
| 39 |
+
- **Demo [optional]:** [More Information Needed]
|
| 40 |
+
|
| 41 |
+
## Uses
|
| 42 |
+
|
| 43 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 44 |
+
|
| 45 |
+
### Direct Use
|
| 46 |
+
|
| 47 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 48 |
+
|
| 49 |
+
[More Information Needed]
|
| 50 |
+
|
| 51 |
+
### Downstream Use [optional]
|
| 52 |
+
|
| 53 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 54 |
+
|
| 55 |
+
[More Information Needed]
|
| 56 |
+
|
| 57 |
+
### Out-of-Scope Use
|
| 58 |
+
|
| 59 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 60 |
+
|
| 61 |
+
[More Information Needed]
|
| 62 |
+
|
| 63 |
+
## Bias, Risks, and Limitations
|
| 64 |
+
|
| 65 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 66 |
+
|
| 67 |
+
[More Information Needed]
|
| 68 |
+
|
| 69 |
+
### Recommendations
|
| 70 |
+
|
| 71 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 72 |
+
|
| 73 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 74 |
+
|
| 75 |
+
## How to Get Started with the Model
|
| 76 |
+
|
| 77 |
+
Use the code below to get started with the model.
|
| 78 |
+
|
| 79 |
+
[More Information Needed]
|
| 80 |
+
|
| 81 |
+
## Training Details
|
| 82 |
+
|
| 83 |
+
### Training Data
|
| 84 |
+
|
| 85 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 86 |
+
|
| 87 |
+
[More Information Needed]
|
| 88 |
+
|
| 89 |
+
### Training Procedure
|
| 90 |
+
|
| 91 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 92 |
+
|
| 93 |
+
#### Preprocessing [optional]
|
| 94 |
+
|
| 95 |
+
[More Information Needed]
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
#### Training Hyperparameters
|
| 99 |
+
|
| 100 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 101 |
+
|
| 102 |
+
#### Speeds, Sizes, Times [optional]
|
| 103 |
+
|
| 104 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 105 |
+
|
| 106 |
+
[More Information Needed]
|
| 107 |
+
|
| 108 |
+
## Evaluation
|
| 109 |
+
|
| 110 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 111 |
+
|
| 112 |
+
### Testing Data, Factors & Metrics
|
| 113 |
+
|
| 114 |
+
#### Testing Data
|
| 115 |
+
|
| 116 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 117 |
+
|
| 118 |
+
[More Information Needed]
|
| 119 |
+
|
| 120 |
+
#### Factors
|
| 121 |
+
|
| 122 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 123 |
+
|
| 124 |
+
[More Information Needed]
|
| 125 |
+
|
| 126 |
+
#### Metrics
|
| 127 |
+
|
| 128 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 129 |
+
|
| 130 |
+
[More Information Needed]
|
| 131 |
+
|
| 132 |
+
### Results
|
| 133 |
+
|
| 134 |
+
[More Information Needed]
|
| 135 |
+
|
| 136 |
+
#### Summary
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
## Model Examination [optional]
|
| 141 |
+
|
| 142 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 143 |
+
|
| 144 |
+
[More Information Needed]
|
| 145 |
+
|
| 146 |
+
## Environmental Impact
|
| 147 |
+
|
| 148 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 149 |
+
|
| 150 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 151 |
+
|
| 152 |
+
- **Hardware Type:** [More Information Needed]
|
| 153 |
+
- **Hours used:** [More Information Needed]
|
| 154 |
+
- **Cloud Provider:** [More Information Needed]
|
| 155 |
+
- **Compute Region:** [More Information Needed]
|
| 156 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 157 |
+
|
| 158 |
+
## Technical Specifications [optional]
|
| 159 |
+
|
| 160 |
+
### Model Architecture and Objective
|
| 161 |
+
|
| 162 |
+
[More Information Needed]
|
| 163 |
+
|
| 164 |
+
### Compute Infrastructure
|
| 165 |
+
|
| 166 |
+
[More Information Needed]
|
| 167 |
+
|
| 168 |
+
#### Hardware
|
| 169 |
+
|
| 170 |
+
[More Information Needed]
|
| 171 |
+
|
| 172 |
+
#### Software
|
| 173 |
+
|
| 174 |
+
[More Information Needed]
|
| 175 |
+
|
| 176 |
+
## Citation [optional]
|
| 177 |
+
|
| 178 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 179 |
+
|
| 180 |
+
**BibTeX:**
|
| 181 |
+
|
| 182 |
+
[More Information Needed]
|
| 183 |
+
|
| 184 |
+
**APA:**
|
| 185 |
+
|
| 186 |
+
[More Information Needed]
|
| 187 |
+
|
| 188 |
+
## Glossary [optional]
|
| 189 |
+
|
| 190 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 191 |
+
|
| 192 |
+
[More Information Needed]
|
| 193 |
+
|
| 194 |
+
## More Information [optional]
|
| 195 |
+
|
| 196 |
+
[More Information Needed]
|
| 197 |
+
|
| 198 |
+
## Model Card Authors [optional]
|
| 199 |
+
|
| 200 |
+
[More Information Needed]
|
| 201 |
+
|
| 202 |
+
## Model Card Contact
|
| 203 |
+
|
| 204 |
+
[More Information Needed]
|
| 205 |
+
### Framework versions
|
| 206 |
+
|
| 207 |
+
- PEFT 0.21.0
|
qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-1500/adapter_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3.5-2B",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"kasa_config": null,
|
| 16 |
+
"layer_replication": null,
|
| 17 |
+
"layers_pattern": null,
|
| 18 |
+
"layers_to_transform": null,
|
| 19 |
+
"loftq_config": {},
|
| 20 |
+
"lora_alpha": 64,
|
| 21 |
+
"lora_bias": false,
|
| 22 |
+
"lora_dropout": 0.05,
|
| 23 |
+
"lora_ga_config": null,
|
| 24 |
+
"megatron_config": null,
|
| 25 |
+
"megatron_core": "megatron.core",
|
| 26 |
+
"modules_to_save": null,
|
| 27 |
+
"monteclora_config": null,
|
| 28 |
+
"peft_type": "LORA",
|
| 29 |
+
"peft_version": "0.21.0",
|
| 30 |
+
"qalora_group_size": 16,
|
| 31 |
+
"r": 32,
|
| 32 |
+
"rank_pattern": {},
|
| 33 |
+
"revision": null,
|
| 34 |
+
"target_modules": [
|
| 35 |
+
"q_proj",
|
| 36 |
+
"in_proj_b",
|
| 37 |
+
"o_proj",
|
| 38 |
+
"down_proj",
|
| 39 |
+
"v_proj",
|
| 40 |
+
"up_proj",
|
| 41 |
+
"out_proj",
|
| 42 |
+
"in_proj_z",
|
| 43 |
+
"k_proj",
|
| 44 |
+
"gate_proj",
|
| 45 |
+
"in_proj_qkv",
|
| 46 |
+
"in_proj_a"
|
| 47 |
+
],
|
| 48 |
+
"target_parameters": null,
|
| 49 |
+
"task_type": "CAUSAL_LM",
|
| 50 |
+
"trainable_token_indices": null,
|
| 51 |
+
"use_bdlora": null,
|
| 52 |
+
"use_dora": false,
|
| 53 |
+
"use_qalora": false,
|
| 54 |
+
"use_rslora": false,
|
| 55 |
+
"velora_config": null
|
| 56 |
+
}
|
qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-1500/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca25ca3c01849e2f2e740c3a3e0b59ad22e848ae9ec3c52cf24291cbaf5eadeb
|
| 3 |
+
size 134604152
|
qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-1500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cccb25b9d2ba15ed325d967728f06f4cefeecc4d4d0425076bf8fccbdf351007
|
| 3 |
+
size 269426431
|
qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-1500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08886a9644c464666575b0abc8cc660646b7c40d1dbf944906371b51c136f2bd
|
| 3 |
+
size 14645
|
qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-1500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1aed05019dad8a1a9995f7e711f789df3df49f2d2f182bc7d72f8e148778249
|
| 3 |
+
size 1465
|
qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-1500/trainer_state.json
ADDED
|
@@ -0,0 +1,1158 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.2691699471753979,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0017944663145026524,
|
| 14 |
+
"grad_norm": 2.403308153152466,
|
| 15 |
+
"learning_rate": 3.225806451612903e-06,
|
| 16 |
+
"loss": 1.210298442840576,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.003588932629005305,
|
| 21 |
+
"grad_norm": 1.3837767839431763,
|
| 22 |
+
"learning_rate": 6.810035842293908e-06,
|
| 23 |
+
"loss": 1.238302230834961,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.005383398943507958,
|
| 28 |
+
"grad_norm": 1.152842402458191,
|
| 29 |
+
"learning_rate": 1.039426523297491e-05,
|
| 30 |
+
"loss": 1.1493020057678223,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.00717786525801061,
|
| 35 |
+
"grad_norm": 1.2282543182373047,
|
| 36 |
+
"learning_rate": 1.3978494623655914e-05,
|
| 37 |
+
"loss": 1.2698699951171875,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.008972331572513263,
|
| 42 |
+
"grad_norm": 4.5811686515808105,
|
| 43 |
+
"learning_rate": 1.7562724014336916e-05,
|
| 44 |
+
"loss": 1.336978054046631,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.010766797887015915,
|
| 49 |
+
"grad_norm": 0.7280638217926025,
|
| 50 |
+
"learning_rate": 2.1146953405017922e-05,
|
| 51 |
+
"loss": 0.9929692268371582,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.012561264201518567,
|
| 56 |
+
"grad_norm": 0.8359633684158325,
|
| 57 |
+
"learning_rate": 2.4731182795698928e-05,
|
| 58 |
+
"loss": 0.987311840057373,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.01435573051602122,
|
| 63 |
+
"grad_norm": 1.061148762702942,
|
| 64 |
+
"learning_rate": 2.831541218637993e-05,
|
| 65 |
+
"loss": 1.0299980163574218,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.01615019683052387,
|
| 70 |
+
"grad_norm": 1.4723000526428223,
|
| 71 |
+
"learning_rate": 3.1899641577060935e-05,
|
| 72 |
+
"loss": 1.1110344886779786,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.017944663145026525,
|
| 77 |
+
"grad_norm": 5.412300109863281,
|
| 78 |
+
"learning_rate": 3.548387096774194e-05,
|
| 79 |
+
"loss": 1.1978090286254883,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.019739129459529176,
|
| 84 |
+
"grad_norm": 0.7945532202720642,
|
| 85 |
+
"learning_rate": 3.906810035842295e-05,
|
| 86 |
+
"loss": 0.8953464508056641,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.02153359577403183,
|
| 91 |
+
"grad_norm": 0.9241706728935242,
|
| 92 |
+
"learning_rate": 4.265232974910394e-05,
|
| 93 |
+
"loss": 0.8933357238769531,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.023328062088534482,
|
| 98 |
+
"grad_norm": 1.2824897766113281,
|
| 99 |
+
"learning_rate": 4.6236559139784944e-05,
|
| 100 |
+
"loss": 0.9129752159118653,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.025122528403037133,
|
| 105 |
+
"grad_norm": 1.8574696779251099,
|
| 106 |
+
"learning_rate": 4.982078853046595e-05,
|
| 107 |
+
"loss": 1.0019177436828612,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.026916994717539788,
|
| 112 |
+
"grad_norm": 4.865994930267334,
|
| 113 |
+
"learning_rate": 5.340501792114696e-05,
|
| 114 |
+
"loss": 1.1639716148376464,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.02871146103204244,
|
| 119 |
+
"grad_norm": 0.8981343507766724,
|
| 120 |
+
"learning_rate": 5.6989247311827965e-05,
|
| 121 |
+
"loss": 0.8498629570007324,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.03050592734654509,
|
| 126 |
+
"grad_norm": 0.8773536086082458,
|
| 127 |
+
"learning_rate": 6.057347670250897e-05,
|
| 128 |
+
"loss": 0.8652203559875489,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.03230039366104774,
|
| 133 |
+
"grad_norm": 1.2524876594543457,
|
| 134 |
+
"learning_rate": 6.415770609318996e-05,
|
| 135 |
+
"loss": 0.9427430152893066,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.034094859975550396,
|
| 140 |
+
"grad_norm": 1.7148643732070923,
|
| 141 |
+
"learning_rate": 6.774193548387096e-05,
|
| 142 |
+
"loss": 0.9581910133361816,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.03588932629005305,
|
| 147 |
+
"grad_norm": 5.458459854125977,
|
| 148 |
+
"learning_rate": 7.132616487455197e-05,
|
| 149 |
+
"loss": 1.1793695449829102,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.037683792604555705,
|
| 154 |
+
"grad_norm": 0.7586544752120972,
|
| 155 |
+
"learning_rate": 7.491039426523297e-05,
|
| 156 |
+
"loss": 0.8673212051391601,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.03947825891905835,
|
| 161 |
+
"grad_norm": 0.8580747246742249,
|
| 162 |
+
"learning_rate": 7.849462365591398e-05,
|
| 163 |
+
"loss": 0.8158726692199707,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.04127272523356101,
|
| 168 |
+
"grad_norm": 1.0292130708694458,
|
| 169 |
+
"learning_rate": 8.207885304659499e-05,
|
| 170 |
+
"loss": 0.8816629409790039,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.04306719154806366,
|
| 175 |
+
"grad_norm": 1.2191781997680664,
|
| 176 |
+
"learning_rate": 8.566308243727598e-05,
|
| 177 |
+
"loss": 0.9256319999694824,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.04486165786256631,
|
| 182 |
+
"grad_norm": 4.896722316741943,
|
| 183 |
+
"learning_rate": 8.924731182795699e-05,
|
| 184 |
+
"loss": 1.054029369354248,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.046656124177068964,
|
| 189 |
+
"grad_norm": 0.6555370688438416,
|
| 190 |
+
"learning_rate": 9.2831541218638e-05,
|
| 191 |
+
"loss": 0.8240686416625976,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.04845059049157162,
|
| 196 |
+
"grad_norm": 0.8895808458328247,
|
| 197 |
+
"learning_rate": 9.6415770609319e-05,
|
| 198 |
+
"loss": 0.7868500232696534,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.050245056806074266,
|
| 203 |
+
"grad_norm": 0.9253164529800415,
|
| 204 |
+
"learning_rate": 0.0001,
|
| 205 |
+
"loss": 0.821414852142334,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.05203952312057692,
|
| 210 |
+
"grad_norm": 1.134040355682373,
|
| 211 |
+
"learning_rate": 9.981110691348697e-05,
|
| 212 |
+
"loss": 0.9013632774353028,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.053833989435079575,
|
| 217 |
+
"grad_norm": 3.446653366088867,
|
| 218 |
+
"learning_rate": 9.962221382697394e-05,
|
| 219 |
+
"loss": 1.0495364189147949,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.05562845574958222,
|
| 224 |
+
"grad_norm": 0.7303311824798584,
|
| 225 |
+
"learning_rate": 9.94333207404609e-05,
|
| 226 |
+
"loss": 0.7989195346832275,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.05742292206408488,
|
| 231 |
+
"grad_norm": 0.8196483850479126,
|
| 232 |
+
"learning_rate": 9.924442765394787e-05,
|
| 233 |
+
"loss": 0.7937421798706055,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.05921738837858753,
|
| 238 |
+
"grad_norm": 0.9366778135299683,
|
| 239 |
+
"learning_rate": 9.905553456743484e-05,
|
| 240 |
+
"loss": 0.809019660949707,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.06101185469309018,
|
| 245 |
+
"grad_norm": 1.2467617988586426,
|
| 246 |
+
"learning_rate": 9.88666414809218e-05,
|
| 247 |
+
"loss": 0.930391502380371,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.06280632100759284,
|
| 252 |
+
"grad_norm": 3.261760950088501,
|
| 253 |
+
"learning_rate": 9.867774839440876e-05,
|
| 254 |
+
"loss": 1.0620959281921387,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.06460078732209548,
|
| 259 |
+
"grad_norm": 0.6342303156852722,
|
| 260 |
+
"learning_rate": 9.848885530789574e-05,
|
| 261 |
+
"loss": 0.8134325981140137,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.06639525363659814,
|
| 266 |
+
"grad_norm": 0.6608202457427979,
|
| 267 |
+
"learning_rate": 9.82999622213827e-05,
|
| 268 |
+
"loss": 0.789882230758667,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.06818971995110079,
|
| 273 |
+
"grad_norm": 0.8570723533630371,
|
| 274 |
+
"learning_rate": 9.811106913486967e-05,
|
| 275 |
+
"loss": 0.7621271133422851,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.06998418626560345,
|
| 280 |
+
"grad_norm": 1.162699818611145,
|
| 281 |
+
"learning_rate": 9.792217604835664e-05,
|
| 282 |
+
"loss": 0.8825998306274414,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.0717786525801061,
|
| 287 |
+
"grad_norm": 3.485926866531372,
|
| 288 |
+
"learning_rate": 9.77332829618436e-05,
|
| 289 |
+
"loss": 1.0364310264587402,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.07357311889460875,
|
| 294 |
+
"grad_norm": 0.5732496380805969,
|
| 295 |
+
"learning_rate": 9.754438987533056e-05,
|
| 296 |
+
"loss": 0.7694174289703369,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.07536758520911141,
|
| 301 |
+
"grad_norm": 0.683313250541687,
|
| 302 |
+
"learning_rate": 9.735549678881754e-05,
|
| 303 |
+
"loss": 0.7631448745727539,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.07716205152361405,
|
| 308 |
+
"grad_norm": 0.8606892824172974,
|
| 309 |
+
"learning_rate": 9.716660370230451e-05,
|
| 310 |
+
"loss": 0.786726999282837,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.0789565178381167,
|
| 315 |
+
"grad_norm": 1.1524667739868164,
|
| 316 |
+
"learning_rate": 9.697771061579146e-05,
|
| 317 |
+
"loss": 0.8868392944335938,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.08075098415261936,
|
| 322 |
+
"grad_norm": 3.888843297958374,
|
| 323 |
+
"learning_rate": 9.678881752927843e-05,
|
| 324 |
+
"loss": 0.949896240234375,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.08254545046712201,
|
| 329 |
+
"grad_norm": 0.540230393409729,
|
| 330 |
+
"learning_rate": 9.65999244427654e-05,
|
| 331 |
+
"loss": 0.7518480300903321,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.08433991678162467,
|
| 336 |
+
"grad_norm": 0.7087560296058655,
|
| 337 |
+
"learning_rate": 9.641103135625237e-05,
|
| 338 |
+
"loss": 0.7413692474365234,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.08613438309612732,
|
| 343 |
+
"grad_norm": 0.7639017105102539,
|
| 344 |
+
"learning_rate": 9.622213826973934e-05,
|
| 345 |
+
"loss": 0.8329146385192872,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.08792884941062996,
|
| 350 |
+
"grad_norm": 1.0710383653640747,
|
| 351 |
+
"learning_rate": 9.60332451832263e-05,
|
| 352 |
+
"loss": 0.8491949081420899,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.08972331572513262,
|
| 357 |
+
"grad_norm": 3.929804563522339,
|
| 358 |
+
"learning_rate": 9.584435209671326e-05,
|
| 359 |
+
"loss": 1.014235496520996,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.08972331572513262,
|
| 364 |
+
"step": 500,
|
| 365 |
+
"test_entity_exact_match": 0.0039603960396039604,
|
| 366 |
+
"test_entity_fix_rate": 0.2154554278736262,
|
| 367 |
+
"test_entity_fix_rate_lenient": 0.20545155993431855,
|
| 368 |
+
"test_entity_fix_rate_recoverable": 0.2082457720404283,
|
| 369 |
+
"test_entity_hallucination_rate": 0.006930693069306931,
|
| 370 |
+
"test_entity_premature_stop_rate": 0.04950495049504951,
|
| 371 |
+
"test_entity_preservation_rate": 0.8851729129805372,
|
| 372 |
+
"test_entity_preservation_rate_lenient": 0.8867249143604942,
|
| 373 |
+
"test_entity_targeted_score": 0.5503141704270818,
|
| 374 |
+
"test_entity_targeted_score_lenient": 0.5460882371474064,
|
| 375 |
+
"test_entity_wer": 0.25481154129439265,
|
| 376 |
+
"test_entity_wer_zwnj_normalized": 0.24980518995313886
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.08972331572513262,
|
| 380 |
+
"step": 500,
|
| 381 |
+
"test_typo_exact_match": 0.0111731843575419,
|
| 382 |
+
"test_typo_fix_rate": 0.28247382706475377,
|
| 383 |
+
"test_typo_fix_rate_lenient": 0.2757193127716829,
|
| 384 |
+
"test_typo_fix_rate_recoverable": 0.27923577577157255,
|
| 385 |
+
"test_typo_hallucination_rate": 0.008379888268156424,
|
| 386 |
+
"test_typo_premature_stop_rate": 0.05027932960893855,
|
| 387 |
+
"test_typo_preservation_rate": 0.9247640608002823,
|
| 388 |
+
"test_typo_preservation_rate_lenient": 0.9271587213220428,
|
| 389 |
+
"test_typo_targeted_score": 0.603618943932518,
|
| 390 |
+
"test_typo_targeted_score_lenient": 0.6014390170468629,
|
| 391 |
+
"test_typo_wer": 0.18398815450205508,
|
| 392 |
+
"test_typo_wer_zwnj_normalized": 0.178116463710398
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.08972331572513262,
|
| 396 |
+
"step": 500,
|
| 397 |
+
"test_best_wer": 0.21939984789822387
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.09151778203963527,
|
| 401 |
+
"grad_norm": 0.5897678732872009,
|
| 402 |
+
"learning_rate": 9.565545901020023e-05,
|
| 403 |
+
"loss": 0.739581823348999,
|
| 404 |
+
"step": 510
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.09331224835413793,
|
| 408 |
+
"grad_norm": 0.6559104919433594,
|
| 409 |
+
"learning_rate": 9.54665659236872e-05,
|
| 410 |
+
"loss": 0.7567477226257324,
|
| 411 |
+
"step": 520
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.09510671466864058,
|
| 415 |
+
"grad_norm": 0.805770993232727,
|
| 416 |
+
"learning_rate": 9.527767283717416e-05,
|
| 417 |
+
"loss": 0.7930418968200683,
|
| 418 |
+
"step": 530
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.09690118098314324,
|
| 422 |
+
"grad_norm": 1.1318767070770264,
|
| 423 |
+
"learning_rate": 9.508877975066113e-05,
|
| 424 |
+
"loss": 0.905422306060791,
|
| 425 |
+
"step": 540
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.09869564729764588,
|
| 429 |
+
"grad_norm": 2.9629955291748047,
|
| 430 |
+
"learning_rate": 9.48998866641481e-05,
|
| 431 |
+
"loss": 0.9469995498657227,
|
| 432 |
+
"step": 550
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.10049011361214853,
|
| 436 |
+
"grad_norm": 0.5787467360496521,
|
| 437 |
+
"learning_rate": 9.471099357763506e-05,
|
| 438 |
+
"loss": 0.7495344161987305,
|
| 439 |
+
"step": 560
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.10228457992665119,
|
| 443 |
+
"grad_norm": 0.612440288066864,
|
| 444 |
+
"learning_rate": 9.452210049112203e-05,
|
| 445 |
+
"loss": 0.7359298706054688,
|
| 446 |
+
"step": 570
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.10407904624115384,
|
| 450 |
+
"grad_norm": 0.8614351153373718,
|
| 451 |
+
"learning_rate": 9.4333207404609e-05,
|
| 452 |
+
"loss": 0.777510404586792,
|
| 453 |
+
"step": 580
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.1058735125556565,
|
| 457 |
+
"grad_norm": 0.9304432272911072,
|
| 458 |
+
"learning_rate": 9.414431431809596e-05,
|
| 459 |
+
"loss": 0.7901641845703125,
|
| 460 |
+
"step": 590
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.10766797887015915,
|
| 464 |
+
"grad_norm": 3.34104585647583,
|
| 465 |
+
"learning_rate": 9.395542123158293e-05,
|
| 466 |
+
"loss": 0.9468848228454589,
|
| 467 |
+
"step": 600
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.1094624451846618,
|
| 471 |
+
"grad_norm": 0.5620515942573547,
|
| 472 |
+
"learning_rate": 9.37665281450699e-05,
|
| 473 |
+
"loss": 0.730808162689209,
|
| 474 |
+
"step": 610
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.11125691149916445,
|
| 478 |
+
"grad_norm": 0.6676825284957886,
|
| 479 |
+
"learning_rate": 9.357763505855685e-05,
|
| 480 |
+
"loss": 0.72871413230896,
|
| 481 |
+
"step": 620
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.1130513778136671,
|
| 485 |
+
"grad_norm": 0.795124888420105,
|
| 486 |
+
"learning_rate": 9.338874197204383e-05,
|
| 487 |
+
"loss": 0.7552680492401123,
|
| 488 |
+
"step": 630
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.11484584412816976,
|
| 492 |
+
"grad_norm": 0.9903436303138733,
|
| 493 |
+
"learning_rate": 9.31998488855308e-05,
|
| 494 |
+
"loss": 0.8315870285034179,
|
| 495 |
+
"step": 640
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.11664031044267241,
|
| 499 |
+
"grad_norm": 3.1701719760894775,
|
| 500 |
+
"learning_rate": 9.301095579901776e-05,
|
| 501 |
+
"loss": 0.964801025390625,
|
| 502 |
+
"step": 650
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.11843477675717506,
|
| 506 |
+
"grad_norm": 0.5520787835121155,
|
| 507 |
+
"learning_rate": 9.282206271250473e-05,
|
| 508 |
+
"loss": 0.7416518688201904,
|
| 509 |
+
"step": 660
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.12022924307167772,
|
| 513 |
+
"grad_norm": 0.6222532987594604,
|
| 514 |
+
"learning_rate": 9.263316962599168e-05,
|
| 515 |
+
"loss": 0.758673620223999,
|
| 516 |
+
"step": 670
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.12202370938618036,
|
| 520 |
+
"grad_norm": 0.7712622880935669,
|
| 521 |
+
"learning_rate": 9.244427653947865e-05,
|
| 522 |
+
"loss": 0.721858024597168,
|
| 523 |
+
"step": 680
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.12381817570068301,
|
| 527 |
+
"grad_norm": 0.9517074823379517,
|
| 528 |
+
"learning_rate": 9.225538345296563e-05,
|
| 529 |
+
"loss": 0.8953560829162598,
|
| 530 |
+
"step": 690
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.12561264201518568,
|
| 534 |
+
"grad_norm": 3.454228162765503,
|
| 535 |
+
"learning_rate": 9.20664903664526e-05,
|
| 536 |
+
"loss": 0.9904054641723633,
|
| 537 |
+
"step": 700
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.12740710832968832,
|
| 541 |
+
"grad_norm": 0.5811975002288818,
|
| 542 |
+
"learning_rate": 9.187759727993955e-05,
|
| 543 |
+
"loss": 0.7146330833435058,
|
| 544 |
+
"step": 710
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.12920157464419096,
|
| 548 |
+
"grad_norm": 0.5948407649993896,
|
| 549 |
+
"learning_rate": 9.168870419342652e-05,
|
| 550 |
+
"loss": 0.723681116104126,
|
| 551 |
+
"step": 720
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.13099604095869363,
|
| 555 |
+
"grad_norm": 0.7696809768676758,
|
| 556 |
+
"learning_rate": 9.149981110691349e-05,
|
| 557 |
+
"loss": 0.7829360008239746,
|
| 558 |
+
"step": 730
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.13279050727319627,
|
| 562 |
+
"grad_norm": 1.0465209484100342,
|
| 563 |
+
"learning_rate": 9.131091802040047e-05,
|
| 564 |
+
"loss": 0.8694637298583985,
|
| 565 |
+
"step": 740
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.13458497358769894,
|
| 569 |
+
"grad_norm": 2.8256630897521973,
|
| 570 |
+
"learning_rate": 9.112202493388743e-05,
|
| 571 |
+
"loss": 0.9362977027893067,
|
| 572 |
+
"step": 750
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.13637943990220158,
|
| 576 |
+
"grad_norm": 0.5560015439987183,
|
| 577 |
+
"learning_rate": 9.093313184737439e-05,
|
| 578 |
+
"loss": 0.7227760791778565,
|
| 579 |
+
"step": 760
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.13817390621670425,
|
| 583 |
+
"grad_norm": 0.6404837965965271,
|
| 584 |
+
"learning_rate": 9.074423876086135e-05,
|
| 585 |
+
"loss": 0.7460755825042724,
|
| 586 |
+
"step": 770
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.1399683725312069,
|
| 590 |
+
"grad_norm": 0.6959487795829773,
|
| 591 |
+
"learning_rate": 9.055534567434832e-05,
|
| 592 |
+
"loss": 0.7522034645080566,
|
| 593 |
+
"step": 780
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.14176283884570953,
|
| 597 |
+
"grad_norm": 0.9924454092979431,
|
| 598 |
+
"learning_rate": 9.036645258783529e-05,
|
| 599 |
+
"loss": 0.8138758659362793,
|
| 600 |
+
"step": 790
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.1435573051602122,
|
| 604 |
+
"grad_norm": 2.9993672370910645,
|
| 605 |
+
"learning_rate": 9.017755950132225e-05,
|
| 606 |
+
"loss": 0.8775947570800782,
|
| 607 |
+
"step": 800
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.14535177147471484,
|
| 611 |
+
"grad_norm": 0.5515598058700562,
|
| 612 |
+
"learning_rate": 8.998866641480922e-05,
|
| 613 |
+
"loss": 0.7623902320861816,
|
| 614 |
+
"step": 810
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.1471462377892175,
|
| 618 |
+
"grad_norm": 0.6749187111854553,
|
| 619 |
+
"learning_rate": 8.979977332829619e-05,
|
| 620 |
+
"loss": 0.7583945274353028,
|
| 621 |
+
"step": 820
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.14894070410372015,
|
| 625 |
+
"grad_norm": 0.7289445400238037,
|
| 626 |
+
"learning_rate": 8.961088024178315e-05,
|
| 627 |
+
"loss": 0.704672384262085,
|
| 628 |
+
"step": 830
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 0.15073517041822282,
|
| 632 |
+
"grad_norm": 1.0323708057403564,
|
| 633 |
+
"learning_rate": 8.942198715527012e-05,
|
| 634 |
+
"loss": 0.8557832717895508,
|
| 635 |
+
"step": 840
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.15252963673272546,
|
| 639 |
+
"grad_norm": 2.91811466217041,
|
| 640 |
+
"learning_rate": 8.923309406875709e-05,
|
| 641 |
+
"loss": 0.945162582397461,
|
| 642 |
+
"step": 850
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.1543241030472281,
|
| 646 |
+
"grad_norm": 0.54680997133255,
|
| 647 |
+
"learning_rate": 8.904420098224405e-05,
|
| 648 |
+
"loss": 0.7189648628234864,
|
| 649 |
+
"step": 860
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.15611856936173077,
|
| 653 |
+
"grad_norm": 0.6474179625511169,
|
| 654 |
+
"learning_rate": 8.885530789573102e-05,
|
| 655 |
+
"loss": 0.731608533859253,
|
| 656 |
+
"step": 870
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.1579130356762334,
|
| 660 |
+
"grad_norm": 0.7434310913085938,
|
| 661 |
+
"learning_rate": 8.866641480921799e-05,
|
| 662 |
+
"loss": 0.7703955173492432,
|
| 663 |
+
"step": 880
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.15970750199073608,
|
| 667 |
+
"grad_norm": 0.9848499894142151,
|
| 668 |
+
"learning_rate": 8.847752172270494e-05,
|
| 669 |
+
"loss": 0.84183349609375,
|
| 670 |
+
"step": 890
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.16150196830523872,
|
| 674 |
+
"grad_norm": 2.488396644592285,
|
| 675 |
+
"learning_rate": 8.828862863619192e-05,
|
| 676 |
+
"loss": 0.8863388061523437,
|
| 677 |
+
"step": 900
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.16329643461974136,
|
| 681 |
+
"grad_norm": 0.5121757388114929,
|
| 682 |
+
"learning_rate": 8.809973554967889e-05,
|
| 683 |
+
"loss": 0.6949440956115722,
|
| 684 |
+
"step": 910
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.16509090093424403,
|
| 688 |
+
"grad_norm": 0.5928990244865417,
|
| 689 |
+
"learning_rate": 8.791084246316586e-05,
|
| 690 |
+
"loss": 0.7060844421386718,
|
| 691 |
+
"step": 920
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.16688536724874667,
|
| 695 |
+
"grad_norm": 0.6861441135406494,
|
| 696 |
+
"learning_rate": 8.772194937665282e-05,
|
| 697 |
+
"loss": 0.692753267288208,
|
| 698 |
+
"step": 930
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.16867983356324934,
|
| 702 |
+
"grad_norm": 0.902505099773407,
|
| 703 |
+
"learning_rate": 8.753305629013978e-05,
|
| 704 |
+
"loss": 0.8425265312194824,
|
| 705 |
+
"step": 940
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.17047429987775198,
|
| 709 |
+
"grad_norm": 2.991858720779419,
|
| 710 |
+
"learning_rate": 8.734416320362676e-05,
|
| 711 |
+
"loss": 0.9827096939086915,
|
| 712 |
+
"step": 950
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.17226876619225465,
|
| 716 |
+
"grad_norm": 0.5504608154296875,
|
| 717 |
+
"learning_rate": 8.715527011711372e-05,
|
| 718 |
+
"loss": 0.7078711986541748,
|
| 719 |
+
"step": 960
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.1740632325067573,
|
| 723 |
+
"grad_norm": 0.5990283489227295,
|
| 724 |
+
"learning_rate": 8.696637703060069e-05,
|
| 725 |
+
"loss": 0.7095432281494141,
|
| 726 |
+
"step": 970
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.17585769882125993,
|
| 730 |
+
"grad_norm": 0.7148527503013611,
|
| 731 |
+
"learning_rate": 8.677748394408764e-05,
|
| 732 |
+
"loss": 0.68252592086792,
|
| 733 |
+
"step": 980
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.1776521651357626,
|
| 737 |
+
"grad_norm": 0.9802461862564087,
|
| 738 |
+
"learning_rate": 8.658859085757461e-05,
|
| 739 |
+
"loss": 0.8042885780334472,
|
| 740 |
+
"step": 990
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.17944663145026524,
|
| 744 |
+
"grad_norm": 3.1613829135894775,
|
| 745 |
+
"learning_rate": 8.639969777106158e-05,
|
| 746 |
+
"loss": 0.9047529220581054,
|
| 747 |
+
"step": 1000
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.17944663145026524,
|
| 751 |
+
"step": 1000,
|
| 752 |
+
"test_entity_exact_match": 0.0049504950495049506,
|
| 753 |
+
"test_entity_fix_rate": 0.2379685004853305,
|
| 754 |
+
"test_entity_fix_rate_lenient": 0.2263382594417077,
|
| 755 |
+
"test_entity_fix_rate_recoverable": 0.22926048233763635,
|
| 756 |
+
"test_entity_hallucination_rate": 0.0039603960396039604,
|
| 757 |
+
"test_entity_premature_stop_rate": 0.07227722772277227,
|
| 758 |
+
"test_entity_preservation_rate": 0.8402123210551713,
|
| 759 |
+
"test_entity_preservation_rate_lenient": 0.845387013586852,
|
| 760 |
+
"test_entity_targeted_score": 0.5390904107702509,
|
| 761 |
+
"test_entity_targeted_score_lenient": 0.5358626365142798,
|
| 762 |
+
"test_entity_wer": 0.2840543973697975,
|
| 763 |
+
"test_entity_wer_zwnj_normalized": 0.2787544966428625
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.17944663145026524,
|
| 767 |
+
"step": 1000,
|
| 768 |
+
"test_typo_exact_match": 0.008379888268156424,
|
| 769 |
+
"test_typo_fix_rate": 0.32260566110895694,
|
| 770 |
+
"test_typo_fix_rate_lenient": 0.3113227075139723,
|
| 771 |
+
"test_typo_fix_rate_recoverable": 0.3153474700818812,
|
| 772 |
+
"test_typo_hallucination_rate": 0.00558659217877095,
|
| 773 |
+
"test_typo_premature_stop_rate": 0.04748603351955307,
|
| 774 |
+
"test_typo_preservation_rate": 0.9064181342427895,
|
| 775 |
+
"test_typo_preservation_rate_lenient": 0.9128893316534326,
|
| 776 |
+
"test_typo_targeted_score": 0.6145118976758732,
|
| 777 |
+
"test_typo_targeted_score_lenient": 0.6121060195837025,
|
| 778 |
+
"test_typo_wer": 0.18281381634372368,
|
| 779 |
+
"test_typo_wer_zwnj_normalized": 0.17625284011130685
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.17944663145026524,
|
| 783 |
+
"step": 1000,
|
| 784 |
+
"test_best_wer": 0.21939984789822387
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.1812410977647679,
|
| 788 |
+
"grad_norm": 0.500504195690155,
|
| 789 |
+
"learning_rate": 8.621080468454856e-05,
|
| 790 |
+
"loss": 0.6835177898406982,
|
| 791 |
+
"step": 1010
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.18303556407927055,
|
| 795 |
+
"grad_norm": 0.5783231854438782,
|
| 796 |
+
"learning_rate": 8.602191159803552e-05,
|
| 797 |
+
"loss": 0.7185263156890869,
|
| 798 |
+
"step": 1020
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.18483003039377321,
|
| 802 |
+
"grad_norm": 0.7150673866271973,
|
| 803 |
+
"learning_rate": 8.583301851152248e-05,
|
| 804 |
+
"loss": 0.753300666809082,
|
| 805 |
+
"step": 1030
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.18662449670827586,
|
| 809 |
+
"grad_norm": 0.9598336219787598,
|
| 810 |
+
"learning_rate": 8.564412542500944e-05,
|
| 811 |
+
"loss": 0.7956081390380859,
|
| 812 |
+
"step": 1040
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.1884189630227785,
|
| 816 |
+
"grad_norm": 2.7375543117523193,
|
| 817 |
+
"learning_rate": 8.545523233849641e-05,
|
| 818 |
+
"loss": 0.8457762718200683,
|
| 819 |
+
"step": 1050
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.19021342933728116,
|
| 823 |
+
"grad_norm": 0.4901278018951416,
|
| 824 |
+
"learning_rate": 8.526633925198339e-05,
|
| 825 |
+
"loss": 0.676328706741333,
|
| 826 |
+
"step": 1060
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.1920078956517838,
|
| 830 |
+
"grad_norm": 0.6270294189453125,
|
| 831 |
+
"learning_rate": 8.507744616547034e-05,
|
| 832 |
+
"loss": 0.701818323135376,
|
| 833 |
+
"step": 1070
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.19380236196628647,
|
| 837 |
+
"grad_norm": 0.7050116062164307,
|
| 838 |
+
"learning_rate": 8.488855307895731e-05,
|
| 839 |
+
"loss": 0.7301516532897949,
|
| 840 |
+
"step": 1080
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.19559682828078911,
|
| 844 |
+
"grad_norm": 1.0585323572158813,
|
| 845 |
+
"learning_rate": 8.469965999244428e-05,
|
| 846 |
+
"loss": 0.8141940116882325,
|
| 847 |
+
"step": 1090
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.19739129459529176,
|
| 851 |
+
"grad_norm": 3.236933946609497,
|
| 852 |
+
"learning_rate": 8.451076690593125e-05,
|
| 853 |
+
"loss": 0.9506558418273926,
|
| 854 |
+
"step": 1100
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.19918576090979442,
|
| 858 |
+
"grad_norm": 0.5563746690750122,
|
| 859 |
+
"learning_rate": 8.432187381941821e-05,
|
| 860 |
+
"loss": 0.6754257678985596,
|
| 861 |
+
"step": 1110
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.20098022722429706,
|
| 865 |
+
"grad_norm": 0.6179592609405518,
|
| 866 |
+
"learning_rate": 8.413298073290518e-05,
|
| 867 |
+
"loss": 0.7206086158752442,
|
| 868 |
+
"step": 1120
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.20277469353879973,
|
| 872 |
+
"grad_norm": 0.7203591465950012,
|
| 873 |
+
"learning_rate": 8.394408764639215e-05,
|
| 874 |
+
"loss": 0.6948616981506348,
|
| 875 |
+
"step": 1130
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.20456915985330237,
|
| 879 |
+
"grad_norm": 1.0625226497650146,
|
| 880 |
+
"learning_rate": 8.375519455987911e-05,
|
| 881 |
+
"loss": 0.7751412391662598,
|
| 882 |
+
"step": 1140
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.20636362616780504,
|
| 886 |
+
"grad_norm": 2.729757785797119,
|
| 887 |
+
"learning_rate": 8.356630147336608e-05,
|
| 888 |
+
"loss": 0.9103594779968261,
|
| 889 |
+
"step": 1150
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 0.20815809248230768,
|
| 893 |
+
"grad_norm": 0.5144860744476318,
|
| 894 |
+
"learning_rate": 8.337740838685305e-05,
|
| 895 |
+
"loss": 0.6995117664337158,
|
| 896 |
+
"step": 1160
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.20995255879681032,
|
| 900 |
+
"grad_norm": 0.5917021632194519,
|
| 901 |
+
"learning_rate": 8.318851530034001e-05,
|
| 902 |
+
"loss": 0.653636360168457,
|
| 903 |
+
"step": 1170
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.211747025111313,
|
| 907 |
+
"grad_norm": 0.7679629325866699,
|
| 908 |
+
"learning_rate": 8.299962221382698e-05,
|
| 909 |
+
"loss": 0.6680758953094482,
|
| 910 |
+
"step": 1180
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.21354149142581563,
|
| 914 |
+
"grad_norm": 0.9813562035560608,
|
| 915 |
+
"learning_rate": 8.281072912731395e-05,
|
| 916 |
+
"loss": 0.8140483856201172,
|
| 917 |
+
"step": 1190
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.2153359577403183,
|
| 921 |
+
"grad_norm": 2.6003410816192627,
|
| 922 |
+
"learning_rate": 8.262183604080091e-05,
|
| 923 |
+
"loss": 0.8418839454650879,
|
| 924 |
+
"step": 1200
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.21713042405482094,
|
| 928 |
+
"grad_norm": 0.5474613308906555,
|
| 929 |
+
"learning_rate": 8.243294295428787e-05,
|
| 930 |
+
"loss": 0.6962128162384034,
|
| 931 |
+
"step": 1210
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 0.2189248903693236,
|
| 935 |
+
"grad_norm": 0.5771662592887878,
|
| 936 |
+
"learning_rate": 8.224404986777485e-05,
|
| 937 |
+
"loss": 0.6975495338439941,
|
| 938 |
+
"step": 1220
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.22071935668382625,
|
| 942 |
+
"grad_norm": 0.7354414463043213,
|
| 943 |
+
"learning_rate": 8.205515678126181e-05,
|
| 944 |
+
"loss": 0.7028871536254883,
|
| 945 |
+
"step": 1230
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.2225138229983289,
|
| 949 |
+
"grad_norm": 0.9769073128700256,
|
| 950 |
+
"learning_rate": 8.186626369474878e-05,
|
| 951 |
+
"loss": 0.7758265972137451,
|
| 952 |
+
"step": 1240
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 0.22430828931283156,
|
| 956 |
+
"grad_norm": 2.807898998260498,
|
| 957 |
+
"learning_rate": 8.167737060823573e-05,
|
| 958 |
+
"loss": 0.8767956733703614,
|
| 959 |
+
"step": 1250
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 0.2261027556273342,
|
| 963 |
+
"grad_norm": 0.541883111000061,
|
| 964 |
+
"learning_rate": 8.14884775217227e-05,
|
| 965 |
+
"loss": 0.6965518951416015,
|
| 966 |
+
"step": 1260
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 0.22789722194183687,
|
| 970 |
+
"grad_norm": 0.6470212936401367,
|
| 971 |
+
"learning_rate": 8.129958443520967e-05,
|
| 972 |
+
"loss": 0.7266353607177735,
|
| 973 |
+
"step": 1270
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 0.2296916882563395,
|
| 977 |
+
"grad_norm": 0.774206817150116,
|
| 978 |
+
"learning_rate": 8.111069134869665e-05,
|
| 979 |
+
"loss": 0.6997550010681153,
|
| 980 |
+
"step": 1280
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 0.23148615457084218,
|
| 984 |
+
"grad_norm": 0.9994069337844849,
|
| 985 |
+
"learning_rate": 8.092179826218362e-05,
|
| 986 |
+
"loss": 0.8136388778686523,
|
| 987 |
+
"step": 1290
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.23328062088534482,
|
| 991 |
+
"grad_norm": 2.97735333442688,
|
| 992 |
+
"learning_rate": 8.073290517567057e-05,
|
| 993 |
+
"loss": 0.8850533485412597,
|
| 994 |
+
"step": 1300
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.23507508719984746,
|
| 998 |
+
"grad_norm": 0.5151407718658447,
|
| 999 |
+
"learning_rate": 8.054401208915754e-05,
|
| 1000 |
+
"loss": 0.6944420814514161,
|
| 1001 |
+
"step": 1310
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 0.23686955351435013,
|
| 1005 |
+
"grad_norm": 0.6509584784507751,
|
| 1006 |
+
"learning_rate": 8.03551190026445e-05,
|
| 1007 |
+
"loss": 0.6850823879241943,
|
| 1008 |
+
"step": 1320
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 0.23866401982885277,
|
| 1012 |
+
"grad_norm": 0.7403442859649658,
|
| 1013 |
+
"learning_rate": 8.016622591613148e-05,
|
| 1014 |
+
"loss": 0.6721119403839111,
|
| 1015 |
+
"step": 1330
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 0.24045848614335544,
|
| 1019 |
+
"grad_norm": 1.0890752077102661,
|
| 1020 |
+
"learning_rate": 7.997733282961844e-05,
|
| 1021 |
+
"loss": 0.7768306732177734,
|
| 1022 |
+
"step": 1340
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 0.24225295245785808,
|
| 1026 |
+
"grad_norm": 2.8646481037139893,
|
| 1027 |
+
"learning_rate": 7.97884397431054e-05,
|
| 1028 |
+
"loss": 0.8724665641784668,
|
| 1029 |
+
"step": 1350
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.24404741877236072,
|
| 1033 |
+
"grad_norm": 0.5226626396179199,
|
| 1034 |
+
"learning_rate": 7.959954665659237e-05,
|
| 1035 |
+
"loss": 0.7445878505706787,
|
| 1036 |
+
"step": 1360
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.2458418850868634,
|
| 1040 |
+
"grad_norm": 0.5889577865600586,
|
| 1041 |
+
"learning_rate": 7.941065357007934e-05,
|
| 1042 |
+
"loss": 0.6680328369140625,
|
| 1043 |
+
"step": 1370
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.24763635140136603,
|
| 1047 |
+
"grad_norm": 0.7409655451774597,
|
| 1048 |
+
"learning_rate": 7.92217604835663e-05,
|
| 1049 |
+
"loss": 0.735463809967041,
|
| 1050 |
+
"step": 1380
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.2494308177158687,
|
| 1054 |
+
"grad_norm": 0.9628015160560608,
|
| 1055 |
+
"learning_rate": 7.903286739705327e-05,
|
| 1056 |
+
"loss": 0.7627812385559082,
|
| 1057 |
+
"step": 1390
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 0.25122528403037137,
|
| 1061 |
+
"grad_norm": 3.463650941848755,
|
| 1062 |
+
"learning_rate": 7.884397431054024e-05,
|
| 1063 |
+
"loss": 0.8848884582519532,
|
| 1064 |
+
"step": 1400
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.253019750344874,
|
| 1068 |
+
"grad_norm": 0.5198677778244019,
|
| 1069 |
+
"learning_rate": 7.86550812240272e-05,
|
| 1070 |
+
"loss": 0.6557538509368896,
|
| 1071 |
+
"step": 1410
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.25481421665937665,
|
| 1075 |
+
"grad_norm": 0.6235095858573914,
|
| 1076 |
+
"learning_rate": 7.846618813751417e-05,
|
| 1077 |
+
"loss": 0.6999707698822022,
|
| 1078 |
+
"step": 1420
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 0.2566086829738793,
|
| 1082 |
+
"grad_norm": 0.7124462723731995,
|
| 1083 |
+
"learning_rate": 7.827729505100114e-05,
|
| 1084 |
+
"loss": 0.6824360370635987,
|
| 1085 |
+
"step": 1430
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 0.25840314928838193,
|
| 1089 |
+
"grad_norm": 1.0022318363189697,
|
| 1090 |
+
"learning_rate": 7.80884019644881e-05,
|
| 1091 |
+
"loss": 0.7767867088317871,
|
| 1092 |
+
"step": 1440
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 0.2601976156028846,
|
| 1096 |
+
"grad_norm": 2.879912853240967,
|
| 1097 |
+
"learning_rate": 7.789950887797507e-05,
|
| 1098 |
+
"loss": 0.8896684646606445,
|
| 1099 |
+
"step": 1450
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 0.26199208191738727,
|
| 1103 |
+
"grad_norm": 0.543009877204895,
|
| 1104 |
+
"learning_rate": 7.771061579146204e-05,
|
| 1105 |
+
"loss": 0.7160995960235595,
|
| 1106 |
+
"step": 1460
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.2637865482318899,
|
| 1110 |
+
"grad_norm": 0.5631292462348938,
|
| 1111 |
+
"learning_rate": 7.7521722704949e-05,
|
| 1112 |
+
"loss": 0.6545831203460694,
|
| 1113 |
+
"step": 1470
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.26558101454639255,
|
| 1117 |
+
"grad_norm": 0.7708194255828857,
|
| 1118 |
+
"learning_rate": 7.733282961843596e-05,
|
| 1119 |
+
"loss": 0.7024896621704102,
|
| 1120 |
+
"step": 1480
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 0.2673754808608952,
|
| 1124 |
+
"grad_norm": 1.0248231887817383,
|
| 1125 |
+
"learning_rate": 7.714393653192294e-05,
|
| 1126 |
+
"loss": 0.8062143325805664,
|
| 1127 |
+
"step": 1490
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 0.2691699471753979,
|
| 1131 |
+
"grad_norm": 2.635225534439087,
|
| 1132 |
+
"learning_rate": 7.69550434454099e-05,
|
| 1133 |
+
"loss": 0.8750516891479492,
|
| 1134 |
+
"step": 1500
|
| 1135 |
+
}
|
| 1136 |
+
],
|
| 1137 |
+
"logging_steps": 10,
|
| 1138 |
+
"max_steps": 5573,
|
| 1139 |
+
"num_input_tokens_seen": 0,
|
| 1140 |
+
"num_train_epochs": 1,
|
| 1141 |
+
"save_steps": 500,
|
| 1142 |
+
"stateful_callbacks": {
|
| 1143 |
+
"TrainerControl": {
|
| 1144 |
+
"args": {
|
| 1145 |
+
"should_epoch_stop": false,
|
| 1146 |
+
"should_evaluate": false,
|
| 1147 |
+
"should_log": false,
|
| 1148 |
+
"should_save": true,
|
| 1149 |
+
"should_training_stop": false
|
| 1150 |
+
},
|
| 1151 |
+
"attributes": {}
|
| 1152 |
+
}
|
| 1153 |
+
},
|
| 1154 |
+
"total_flos": 3.0315212672961485e+17,
|
| 1155 |
+
"train_batch_size": 2,
|
| 1156 |
+
"trial_name": null,
|
| 1157 |
+
"trial_params": null
|
| 1158 |
+
}
|
qwen3.5-2b-100pct-masked-weighted-v2/checkpoint-1500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36324839c555b723546ca05f552d997ae3f0d4b9b817db61c11bbc2e65ec719c
|
| 3 |
+
size 5265
|
qwen3.5-2b-100pct-masked-weighted-v2/tb/events.out.tfevents.1790605476.02b48645612f.4580.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eef5e0c8783699b994a3819447493d56b819da7ec77c00441c18e72a185abe02
|
| 3 |
+
size 44759
|
qwen3.5-2b-100pct-masked-weighted-v2/test_eval_entity/metrics.json
CHANGED
|
@@ -1,16 +1,16 @@
|
|
| 1 |
{
|
| 2 |
-
"wer": 0.
|
| 3 |
-
"wer_zwnj_normalized": 0.
|
| 4 |
-
"exact_match": 0.
|
| 5 |
-
"fix_rate": 0.
|
| 6 |
-
"preservation_rate": 0.
|
| 7 |
-
"targeted_score": 0.
|
| 8 |
-
"fix_rate_lenient": 0.
|
| 9 |
-
"preservation_rate_lenient": 0.
|
| 10 |
-
"targeted_score_lenient": 0.
|
| 11 |
-
"fix_rate_recoverable": 0.
|
| 12 |
"unrecoverable_targets": 471,
|
| 13 |
-
"hallucination_rate": 0.
|
| 14 |
-
"premature_stop_rate": 0.
|
| 15 |
"n_examples": 1010
|
| 16 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"wer": 0.22567543045014463,
|
| 3 |
+
"wer_zwnj_normalized": 0.2201193411684333,
|
| 4 |
+
"exact_match": 0.0019801980198019802,
|
| 5 |
+
"fix_rate": 0.2741334502301406,
|
| 6 |
+
"preservation_rate": 0.9063857165835612,
|
| 7 |
+
"targeted_score": 0.5902595834068509,
|
| 8 |
+
"fix_rate_lenient": 0.26354679802955666,
|
| 9 |
+
"preservation_rate_lenient": 0.9083112017756566,
|
| 10 |
+
"targeted_score_lenient": 0.5859289999026066,
|
| 11 |
+
"fix_rate_recoverable": 0.2668534640915307,
|
| 12 |
"unrecoverable_targets": 471,
|
| 13 |
+
"hallucination_rate": 0.0029702970297029703,
|
| 14 |
+
"premature_stop_rate": 0.026732673267326732,
|
| 15 |
"n_examples": 1010
|
| 16 |
}
|
qwen3.5-2b-100pct-masked-weighted-v2/test_eval_entity/predictions.jsonl
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen3.5-2b-100pct-masked-weighted-v2/test_eval_typo/metrics.json
CHANGED
|
@@ -1,16 +1,16 @@
|
|
| 1 |
{
|
| 2 |
-
"wer": 0.
|
| 3 |
-
"wer_zwnj_normalized": 0.
|
| 4 |
-
"exact_match": 0.
|
| 5 |
-
"fix_rate": 0.
|
| 6 |
-
"preservation_rate": 0.
|
| 7 |
-
"targeted_score": 0.
|
| 8 |
-
"fix_rate_lenient": 0.
|
| 9 |
-
"preservation_rate_lenient": 0.
|
| 10 |
-
"targeted_score_lenient": 0.
|
| 11 |
-
"fix_rate_recoverable": 0.
|
| 12 |
"unrecoverable_targets": 68,
|
| 13 |
-
"hallucination_rate": 0.
|
| 14 |
-
"premature_stop_rate": 0.
|
| 15 |
"n_examples": 358
|
| 16 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"wer": 0.13954200811825074,
|
| 3 |
+
"wer_zwnj_normalized": 0.13165351918511142,
|
| 4 |
+
"exact_match": 0.002793296089385475,
|
| 5 |
+
"fix_rate": 0.3464521132221791,
|
| 6 |
+
"preservation_rate": 0.9519007438332402,
|
| 7 |
+
"targeted_score": 0.6491764285277096,
|
| 8 |
+
"fix_rate_lenient": 0.33864624301386875,
|
| 9 |
+
"preservation_rate_lenient": 0.9545840780567846,
|
| 10 |
+
"targeted_score_lenient": 0.6466151605353266,
|
| 11 |
+
"fix_rate_recoverable": 0.34327104765903843,
|
| 12 |
"unrecoverable_targets": 68,
|
| 13 |
+
"hallucination_rate": 0.002793296089385475,
|
| 14 |
+
"premature_stop_rate": 0.0111731843575419,
|
| 15 |
"n_examples": 358
|
| 16 |
}
|
qwen3.5-2b-100pct-masked-weighted-v2/test_eval_typo/predictions.jsonl
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|