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 737722356
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fda8a3a0cfe96a5a51e15c0690d5e1c48857832e5d77678267e42e6fa3a1817f
|
| 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:a9df2f5f97e9f862467508980e69acf0eb0956f6b4e75ecc2902800e27e088f7
|
| 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 sha256:2971d2339194afcfd80aff922bc915204e0778014c7d2e047351d6f30e3bd3fc
|
| 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 sha256:091031ae22eb7d8dfa24111bac44553b71f40bb7016aeefd4960b0ea3e4c04a6
|
| 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,
|
|
@@ -308,6 +308,29 @@
|
|
| 308 |
"eval_samples_per_second": 7.047,
|
| 309 |
"eval_steps_per_second": 3.524,
|
| 310 |
"step": 2562
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 311 |
}
|
| 312 |
],
|
| 313 |
"logging_steps": 100,
|
|
@@ -327,7 +350,7 @@
|
|
| 327 |
"attributes": {}
|
| 328 |
}
|
| 329 |
},
|
| 330 |
-
"total_flos":
|
| 331 |
"train_batch_size": 2,
|
| 332 |
"trial_name": null,
|
| 333 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2747629944426283,
|
| 3 |
"best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 2745,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 308 |
"eval_samples_per_second": 7.047,
|
| 309 |
"eval_steps_per_second": 3.524,
|
| 310 |
"step": 2562
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 14.207650273224044,
|
| 314 |
+
"grad_norm": 7.657999038696289,
|
| 315 |
+
"learning_rate": 2.1584699453551914e-05,
|
| 316 |
+
"loss": 1.0834,
|
| 317 |
+
"step": 2600
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 14.754098360655737,
|
| 321 |
+
"grad_norm": 6.67676305770874,
|
| 322 |
+
"learning_rate": 2.0491803278688525e-05,
|
| 323 |
+
"loss": 1.0739,
|
| 324 |
+
"step": 2700
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 15.0,
|
| 328 |
+
"eval_f1": 0.2747629944426283,
|
| 329 |
+
"eval_loss": 1.1128904819488525,
|
| 330 |
+
"eval_runtime": 13.055,
|
| 331 |
+
"eval_samples_per_second": 7.047,
|
| 332 |
+
"eval_steps_per_second": 3.524,
|
| 333 |
+
"step": 2745
|
| 334 |
}
|
| 335 |
],
|
| 336 |
"logging_steps": 100,
|
|
|
|
| 350 |
"attributes": {}
|
| 351 |
}
|
| 352 |
},
|
| 353 |
+
"total_flos": 7315403653350000.0,
|
| 354 |
"train_batch_size": 2,
|
| 355 |
"trial_name": null,
|
| 356 |
"trial_params": null
|