Training in progress, epoch 23, 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 sha256:8f632a47dc0c30788796a8dba61a612ecf8317dcea16bdcb15010a80ce0260d4
|
| 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:ceaccb5dd5c1b7a308ff896ee95096f4baf6ce2613c023c121468b409d5750b5
|
| 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 sha256:27fe2f6c19f1d393961e1a1f2e3da92a7f6540c77a0c3480b24c8f9b30e7be57
|
| 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:e9d352d54511c127cc9deb5ec7e7c87112ff76a5828dda59f37bc325e32cd6aa
|
| 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,
|
|
@@ -485,6 +485,29 @@
|
|
| 485 |
"eval_samples_per_second": 7.044,
|
| 486 |
"eval_steps_per_second": 3.522,
|
| 487 |
"step": 4026
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 488 |
}
|
| 489 |
],
|
| 490 |
"logging_steps": 100,
|
|
@@ -504,7 +527,7 @@
|
|
| 504 |
"attributes": {}
|
| 505 |
}
|
| 506 |
},
|
| 507 |
-
"total_flos": 1.
|
| 508 |
"train_batch_size": 2,
|
| 509 |
"trial_name": null,
|
| 510 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2747629944426283,
|
| 3 |
"best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
|
| 4 |
+
"epoch": 23.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 4209,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 485 |
"eval_samples_per_second": 7.044,
|
| 486 |
"eval_steps_per_second": 3.522,
|
| 487 |
"step": 4026
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 22.404371584699454,
|
| 491 |
+
"grad_norm": 2.6005687713623047,
|
| 492 |
+
"learning_rate": 5.191256830601094e-06,
|
| 493 |
+
"loss": 1.0862,
|
| 494 |
+
"step": 4100
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 22.950819672131146,
|
| 498 |
+
"grad_norm": 4.929677963256836,
|
| 499 |
+
"learning_rate": 4.098360655737704e-06,
|
| 500 |
+
"loss": 1.041,
|
| 501 |
+
"step": 4200
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 23.0,
|
| 505 |
+
"eval_f1": 0.2747629944426283,
|
| 506 |
+
"eval_loss": 1.1108310222625732,
|
| 507 |
+
"eval_runtime": 13.056,
|
| 508 |
+
"eval_samples_per_second": 7.047,
|
| 509 |
+
"eval_steps_per_second": 3.523,
|
| 510 |
+
"step": 4209
|
| 511 |
}
|
| 512 |
],
|
| 513 |
"logging_steps": 100,
|
|
|
|
| 527 |
"attributes": {}
|
| 528 |
}
|
| 529 |
},
|
| 530 |
+
"total_flos": 1.121695226847e+16,
|
| 531 |
"train_batch_size": 2,
|
| 532 |
"trial_name": null,
|
| 533 |
"trial_params": null
|