Training in progress, epoch 18, 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 737722356
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdd4fc43f5bc5d1a7a71b7f66838d774f1c8bcbe2031e019a16fb257e2f6c2a8
|
| 3 |
size 737722356
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1475564538
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:498dc545cf86d22886711d81b7fe26bf1bd000605f28a9603704528d2c1636b7
|
| 3 |
size 1475564538
|
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 sha256:35f5212c27510000fb9ac8f2a9d2650619d5aa15b35f805b3392a9266fb031a3
|
| 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:e37eb201825b4131f46ef5e79822478b4cd04320fe2968f2a795fa3677b146bd
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2747629944426283,
|
| 3 |
"best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
|
| 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": 7.049,
|
| 378 |
"eval_steps_per_second": 3.524,
|
| 379 |
"step": 3111
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 380 |
}
|
| 381 |
],
|
| 382 |
"logging_steps": 100,
|
|
@@ -396,7 +412,7 @@
|
|
| 396 |
"attributes": {}
|
| 397 |
}
|
| 398 |
},
|
| 399 |
-
"total_flos":
|
| 400 |
"train_batch_size": 2,
|
| 401 |
"trial_name": null,
|
| 402 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2747629944426283,
|
| 3 |
"best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
|
| 4 |
+
"epoch": 18.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 3294,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 377 |
"eval_samples_per_second": 7.049,
|
| 378 |
"eval_steps_per_second": 3.524,
|
| 379 |
"step": 3111
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 17.48633879781421,
|
| 383 |
+
"grad_norm": 5.2359089851379395,
|
| 384 |
+
"learning_rate": 1.5027322404371585e-05,
|
| 385 |
+
"loss": 1.0834,
|
| 386 |
+
"step": 3200
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 18.0,
|
| 390 |
+
"eval_f1": 0.2747629944426283,
|
| 391 |
+
"eval_loss": 1.106469988822937,
|
| 392 |
+
"eval_runtime": 13.0607,
|
| 393 |
+
"eval_samples_per_second": 7.044,
|
| 394 |
+
"eval_steps_per_second": 3.522,
|
| 395 |
+
"step": 3294
|
| 396 |
}
|
| 397 |
],
|
| 398 |
"logging_steps": 100,
|
|
|
|
| 412 |
"attributes": {}
|
| 413 |
}
|
| 414 |
},
|
| 415 |
+
"total_flos": 8778484384020000.0,
|
| 416 |
"train_batch_size": 2,
|
| 417 |
"trial_name": null,
|
| 418 |
"trial_params": null
|