Training in progress, epoch 25, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 598442860
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ed6fbe9e5f81481d7ad0e28de538ea1d4177a00559bac467dd3b2767b2b3a60
|
| 3 |
size 598442860
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1196973562
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e91d783e53fac52c0c7c00b574d0f3a9d268c3fb6d233fcdf8ef3ad4d63c3301
|
| 3 |
size 1196973562
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbd76872ac027eb39a9adfefe0495752f0bdba7a48edaf28359209de94e3e648
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:564cda1e99f8575aecab2238168ab407333f1f142c6fcaa2336965d9be1b83fb
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.685027729264332,
|
| 3 |
"best_model_checkpoint": "modernbert-medical-classifier/checkpoint-2024",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -377,6 +377,22 @@
|
|
| 377 |
"eval_samples_per_second": 12.462,
|
| 378 |
"eval_steps_per_second": 3.116,
|
| 379 |
"step": 2208
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 380 |
}
|
| 381 |
],
|
| 382 |
"logging_steps": 100,
|
|
@@ -391,12 +407,12 @@
|
|
| 391 |
"should_evaluate": false,
|
| 392 |
"should_log": false,
|
| 393 |
"should_save": true,
|
| 394 |
-
"should_training_stop":
|
| 395 |
},
|
| 396 |
"attributes": {}
|
| 397 |
}
|
| 398 |
},
|
| 399 |
-
"total_flos": 1.
|
| 400 |
"train_batch_size": 4,
|
| 401 |
"trial_name": null,
|
| 402 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.685027729264332,
|
| 3 |
"best_model_checkpoint": "modernbert-medical-classifier/checkpoint-2024",
|
| 4 |
+
"epoch": 25.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 2300,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 377 |
"eval_samples_per_second": 12.462,
|
| 378 |
"eval_steps_per_second": 3.116,
|
| 379 |
"step": 2208
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 25.0,
|
| 383 |
+
"grad_norm": 6.634181318077026e-06,
|
| 384 |
+
"learning_rate": 0.0,
|
| 385 |
+
"loss": 0.0,
|
| 386 |
+
"step": 2300
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 25.0,
|
| 390 |
+
"eval_f1": 0.6675544814093237,
|
| 391 |
+
"eval_loss": 3.65128493309021,
|
| 392 |
+
"eval_runtime": 7.4088,
|
| 393 |
+
"eval_samples_per_second": 12.418,
|
| 394 |
+
"eval_steps_per_second": 3.104,
|
| 395 |
+
"step": 2300
|
| 396 |
}
|
| 397 |
],
|
| 398 |
"logging_steps": 100,
|
|
|
|
| 407 |
"should_evaluate": false,
|
| 408 |
"should_log": false,
|
| 409 |
"should_save": true,
|
| 410 |
+
"should_training_stop": true
|
| 411 |
},
|
| 412 |
"attributes": {}
|
| 413 |
}
|
| 414 |
},
|
| 415 |
+
"total_flos": 1.579010926545e+16,
|
| 416 |
"train_batch_size": 4,
|
| 417 |
"trial_name": null,
|
| 418 |
"trial_params": null
|