Training in progress, epoch 20, 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 265525384
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe766e0b8632065a6bd6c2d51570e0eda4ff40f454181a068f78597426befa2a
|
| 3 |
size 265525384
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 531111610
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01ecf6026893bb1cf098c8783b309ec1dbcddfaa3a9486c6b327d16f9af1bd9b
|
| 3 |
size 531111610
|
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:b050c94d670cbde7ca88601b5407bb3c59a1dedf3072aaaf736c68772003708c
|
| 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:f6ff39835f6fc0ab5432bbe426fb9e017df9b359be5fad96f2d6b3dde669dc72
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.04970533400774002,
|
| 3 |
"best_model_checkpoint": "BERT_NER/checkpoint-1800",
|
| 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,
|
|
@@ -373,6 +373,26 @@
|
|
| 373 |
"eval_samples_per_second": 358.185,
|
| 374 |
"eval_steps_per_second": 11.324,
|
| 375 |
"step": 8550
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 500,
|
|
@@ -387,12 +407,12 @@
|
|
| 387 |
"should_evaluate": false,
|
| 388 |
"should_log": false,
|
| 389 |
"should_save": true,
|
| 390 |
-
"should_training_stop":
|
| 391 |
},
|
| 392 |
"attributes": {}
|
| 393 |
}
|
| 394 |
},
|
| 395 |
-
"total_flos":
|
| 396 |
"train_batch_size": 32,
|
| 397 |
"trial_name": null,
|
| 398 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.04970533400774002,
|
| 3 |
"best_model_checkpoint": "BERT_NER/checkpoint-1800",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 9000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 373 |
"eval_samples_per_second": 358.185,
|
| 374 |
"eval_steps_per_second": 11.324,
|
| 375 |
"step": 8550
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 20.0,
|
| 379 |
+
"grad_norm": 0.877216637134552,
|
| 380 |
+
"learning_rate": 0.0,
|
| 381 |
+
"loss": 0.0136,
|
| 382 |
+
"step": 9000
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 20.0,
|
| 386 |
+
"eval_accuracy": 0.9852098879899505,
|
| 387 |
+
"eval_f1": 0.8659488878371983,
|
| 388 |
+
"eval_loss": 0.06747559458017349,
|
| 389 |
+
"eval_model_preparation_time": 0.0017,
|
| 390 |
+
"eval_precision": 0.853030303030303,
|
| 391 |
+
"eval_recall": 0.8792647765497357,
|
| 392 |
+
"eval_runtime": 6.657,
|
| 393 |
+
"eval_samples_per_second": 308.846,
|
| 394 |
+
"eval_steps_per_second": 9.764,
|
| 395 |
+
"step": 9000
|
| 396 |
}
|
| 397 |
],
|
| 398 |
"logging_steps": 500,
|
|
|
|
| 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": 5375523723085680.0,
|
| 416 |
"train_batch_size": 32,
|
| 417 |
"trial_name": null,
|
| 418 |
"trial_params": null
|