Training in progress, epoch 19, 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:a99946ad22ca32ed6c89a83345869da28b8faab36be3ca2308aa7f6af745da32
|
| 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 sha256:106fffcc9aa165d827af6f382fbb9b10f346adaeca31872844d17be6bdf14639
|
| 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 sha256:24395658d692e9f00b34a77fc00fa3b9153d733e822ce4a8c0ffc8569c1173bb
|
| 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:ecd01204dc451af0112a7d684f3c7c23412f112d9b61e939dc2ab21267266a2a
|
| 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,
|
|
@@ -393,6 +393,29 @@
|
|
| 393 |
"eval_samples_per_second": 7.044,
|
| 394 |
"eval_steps_per_second": 3.522,
|
| 395 |
"step": 3294
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 396 |
}
|
| 397 |
],
|
| 398 |
"logging_steps": 100,
|
|
@@ -412,7 +435,7 @@
|
|
| 412 |
"attributes": {}
|
| 413 |
}
|
| 414 |
},
|
| 415 |
-
"total_flos":
|
| 416 |
"train_batch_size": 2,
|
| 417 |
"trial_name": null,
|
| 418 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2747629944426283,
|
| 3 |
"best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
|
| 4 |
+
"epoch": 19.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 3477,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 393 |
"eval_samples_per_second": 7.044,
|
| 394 |
"eval_steps_per_second": 3.522,
|
| 395 |
"step": 3294
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 18.0327868852459,
|
| 399 |
+
"grad_norm": 4.7237467765808105,
|
| 400 |
+
"learning_rate": 1.3934426229508196e-05,
|
| 401 |
+
"loss": 1.036,
|
| 402 |
+
"step": 3300
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 18.579234972677597,
|
| 406 |
+
"grad_norm": 2.9745349884033203,
|
| 407 |
+
"learning_rate": 1.284153005464481e-05,
|
| 408 |
+
"loss": 1.0885,
|
| 409 |
+
"step": 3400
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 19.0,
|
| 413 |
+
"eval_f1": 0.2747629944426283,
|
| 414 |
+
"eval_loss": 1.1148598194122314,
|
| 415 |
+
"eval_runtime": 13.089,
|
| 416 |
+
"eval_samples_per_second": 7.029,
|
| 417 |
+
"eval_steps_per_second": 3.514,
|
| 418 |
+
"step": 3477
|
| 419 |
}
|
| 420 |
],
|
| 421 |
"logging_steps": 100,
|
|
|
|
| 435 |
"attributes": {}
|
| 436 |
}
|
| 437 |
},
|
| 438 |
+
"total_flos": 9266177960910000.0,
|
| 439 |
"train_batch_size": 2,
|
| 440 |
"trial_name": null,
|
| 441 |
"trial_params": null
|