Training in progress, step 268, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3781033488
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2afbce5d670b945dd8540e97e61fd1aec08b9c0f1188a8366a056f1d9491c3bb
|
| 3 |
size 3781033488
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b39cda93b835292839ae4e144dca6b8cdc12f955a832b8d582d81220611fb347
|
| 3 |
+
size 1921133389
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4f1207c2665eeb973ef87d666c48b9043d249e116f97f97b5a32b200af31d0b
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -358,6 +358,27 @@
|
|
| 358 |
"learning_rate": 1.3742948697226532e-06,
|
| 359 |
"loss": 0.09510913491249084,
|
| 360 |
"step": 250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 361 |
}
|
| 362 |
],
|
| 363 |
"logging_steps": 5,
|
|
@@ -372,12 +393,12 @@
|
|
| 372 |
"should_evaluate": false,
|
| 373 |
"should_log": false,
|
| 374 |
"should_save": true,
|
| 375 |
-
"should_training_stop":
|
| 376 |
},
|
| 377 |
"attributes": {}
|
| 378 |
}
|
| 379 |
},
|
| 380 |
-
"total_flos": 5.
|
| 381 |
"train_batch_size": 1,
|
| 382 |
"trial_name": null,
|
| 383 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 268,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 358 |
"learning_rate": 1.3742948697226532e-06,
|
| 359 |
"loss": 0.09510913491249084,
|
| 360 |
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.9089201877934272,
|
| 364 |
+
"grad_norm": 0.1393587440252304,
|
| 365 |
+
"learning_rate": 7.477268341368359e-07,
|
| 366 |
+
"loss": 0.09913409948348999,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.9464788732394367,
|
| 371 |
+
"grad_norm": 0.12746547162532806,
|
| 372 |
+
"learning_rate": 3.0946307513418093e-07,
|
| 373 |
+
"loss": 0.08162710070610046,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.984037558685446,
|
| 378 |
+
"grad_norm": 0.10261425375938416,
|
| 379 |
+
"learning_rate": 6.117918928693623e-08,
|
| 380 |
+
"loss": 0.09766190052032471,
|
| 381 |
+
"step": 265
|
| 382 |
}
|
| 383 |
],
|
| 384 |
"logging_steps": 5,
|
|
|
|
| 393 |
"should_evaluate": false,
|
| 394 |
"should_log": false,
|
| 395 |
"should_save": true,
|
| 396 |
+
"should_training_stop": true
|
| 397 |
},
|
| 398 |
"attributes": {}
|
| 399 |
}
|
| 400 |
},
|
| 401 |
+
"total_flos": 5.732789831301735e+18,
|
| 402 |
"train_batch_size": 1,
|
| 403 |
"trial_name": null,
|
| 404 |
"trial_params": null
|