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 737722356
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bab9b9ff143148c2eb48ab0eb01cb1c0039ed21a628f016dbb3ec7062b11276
|
| 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 sha256:4f348c4a8be5e1a3517a82a9723a92ba5912c931847e8ed5fe32e865ec1bcb5d
|
| 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 sha256:35bfabf194d35621153f637e9571c8e75877c760faefb1ae4f0569d288d288e9
|
| 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 sha256:2d34b63a4c17f1a4f74c70ccf71f8613ced085ca4a8ea826051df9e4a623355a
|
| 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,
|
|
@@ -416,6 +416,29 @@
|
|
| 416 |
"eval_samples_per_second": 7.029,
|
| 417 |
"eval_steps_per_second": 3.514,
|
| 418 |
"step": 3477
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 419 |
}
|
| 420 |
],
|
| 421 |
"logging_steps": 100,
|
|
@@ -435,7 +458,7 @@
|
|
| 435 |
"attributes": {}
|
| 436 |
}
|
| 437 |
},
|
| 438 |
-
"total_flos":
|
| 439 |
"train_batch_size": 2,
|
| 440 |
"trial_name": null,
|
| 441 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2747629944426283,
|
| 3 |
"best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 3660,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 416 |
"eval_samples_per_second": 7.029,
|
| 417 |
"eval_steps_per_second": 3.514,
|
| 418 |
"step": 3477
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 19.12568306010929,
|
| 422 |
+
"grad_norm": 4.162548542022705,
|
| 423 |
+
"learning_rate": 1.1748633879781421e-05,
|
| 424 |
+
"loss": 1.0579,
|
| 425 |
+
"step": 3500
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 19.672131147540984,
|
| 429 |
+
"grad_norm": 4.825162410736084,
|
| 430 |
+
"learning_rate": 1.0655737704918032e-05,
|
| 431 |
+
"loss": 1.0789,
|
| 432 |
+
"step": 3600
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 20.0,
|
| 436 |
+
"eval_f1": 0.2747629944426283,
|
| 437 |
+
"eval_loss": 1.1134560108184814,
|
| 438 |
+
"eval_runtime": 13.0842,
|
| 439 |
+
"eval_samples_per_second": 7.031,
|
| 440 |
+
"eval_steps_per_second": 3.516,
|
| 441 |
+
"step": 3660
|
| 442 |
}
|
| 443 |
],
|
| 444 |
"logging_steps": 100,
|
|
|
|
| 458 |
"attributes": {}
|
| 459 |
}
|
| 460 |
},
|
| 461 |
+
"total_flos": 9753871537800000.0,
|
| 462 |
"train_batch_size": 2,
|
| 463 |
"trial_name": null,
|
| 464 |
"trial_params": null
|