Training in progress, epoch 15, 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:d91edd2da3a6d1fee41af2f45e6174c9fff6f00ba8df6fa7be04555a1fcf3a7d
|
| 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 sha256:486df9b27b6d20e1f0f07339b3940886e4f28250d99fcb17c7ea39dd73572c87
|
| 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 sha256:6a3901b83e53c62c535336e88fe2e18539416386a5f444fff4be15150e8cec35
|
| 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:ad12498e579bfddf42fb572db7ebf9285ac53eaf551fba231f216aa86a7aea0c
|
| 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,
|
|
@@ -273,6 +273,26 @@
|
|
| 273 |
"eval_samples_per_second": 359.659,
|
| 274 |
"eval_steps_per_second": 11.371,
|
| 275 |
"step": 6300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 276 |
}
|
| 277 |
],
|
| 278 |
"logging_steps": 500,
|
|
@@ -292,7 +312,7 @@
|
|
| 292 |
"attributes": {}
|
| 293 |
}
|
| 294 |
},
|
| 295 |
-
"total_flos":
|
| 296 |
"train_batch_size": 32,
|
| 297 |
"trial_name": null,
|
| 298 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.04970533400774002,
|
| 3 |
"best_model_checkpoint": "BERT_NER/checkpoint-1800",
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 6750,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 273 |
"eval_samples_per_second": 359.659,
|
| 274 |
"eval_steps_per_second": 11.371,
|
| 275 |
"step": 6300
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 14.444444444444445,
|
| 279 |
+
"grad_norm": 0.40885716676712036,
|
| 280 |
+
"learning_rate": 1.7860619515673034e-06,
|
| 281 |
+
"loss": 0.0158,
|
| 282 |
+
"step": 6500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 15.0,
|
| 286 |
+
"eval_accuracy": 0.9852547518282014,
|
| 287 |
+
"eval_f1": 0.8643162393162392,
|
| 288 |
+
"eval_loss": 0.06607560068368912,
|
| 289 |
+
"eval_model_preparation_time": 0.0017,
|
| 290 |
+
"eval_precision": 0.8541764429845143,
|
| 291 |
+
"eval_recall": 0.874699663623258,
|
| 292 |
+
"eval_runtime": 6.1942,
|
| 293 |
+
"eval_samples_per_second": 331.924,
|
| 294 |
+
"eval_steps_per_second": 10.494,
|
| 295 |
+
"step": 6750
|
| 296 |
}
|
| 297 |
],
|
| 298 |
"logging_steps": 500,
|
|
|
|
| 312 |
"attributes": {}
|
| 313 |
}
|
| 314 |
},
|
| 315 |
+
"total_flos": 4031000673488496.0,
|
| 316 |
"train_batch_size": 32,
|
| 317 |
"trial_name": null,
|
| 318 |
"trial_params": null
|