Training in progress, step 210, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d18ae65876eb1c05242988a6e3ce216d2ccad79b641d3451154a987d8a83d14c
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0923ee0dca826644733604b5a9baa1835072bbdd842c511ca458f5c58c339e1
|
| 3 |
size 14709
|
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 sha256:3c647bc8caa3194540f05a4f21b84ab9195ec156a646e24faf6f18a3123217f4
|
| 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": 1.
|
| 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,
|
|
@@ -368,6 +368,24 @@
|
|
| 368 |
"mean_token_accuracy": 0.6296403974294662,
|
| 369 |
"num_tokens": 728738.0,
|
| 370 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 371 |
}
|
| 372 |
],
|
| 373 |
"logging_steps": 5,
|
|
@@ -387,7 +405,7 @@
|
|
| 387 |
"attributes": {}
|
| 388 |
}
|
| 389 |
},
|
| 390 |
-
"total_flos": 3.
|
| 391 |
"train_batch_size": 4,
|
| 392 |
"trial_name": null,
|
| 393 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.6153846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 210,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 368 |
"mean_token_accuracy": 0.6296403974294662,
|
| 369 |
"num_tokens": 728738.0,
|
| 370 |
"step": 200
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.5769230769230769,
|
| 374 |
+
"grad_norm": 0.0,
|
| 375 |
+
"learning_rate": 4.898e-05,
|
| 376 |
+
"loss": 1.7075,
|
| 377 |
+
"mean_token_accuracy": 0.6586553543806076,
|
| 378 |
+
"num_tokens": 747160.0,
|
| 379 |
+
"step": 205
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.6153846153846154,
|
| 383 |
+
"grad_norm": 0.0,
|
| 384 |
+
"learning_rate": 4.8955e-05,
|
| 385 |
+
"loss": 1.7835,
|
| 386 |
+
"mean_token_accuracy": 0.6415642440319062,
|
| 387 |
+
"num_tokens": 765489.0,
|
| 388 |
+
"step": 210
|
| 389 |
}
|
| 390 |
],
|
| 391 |
"logging_steps": 5,
|
|
|
|
| 405 |
"attributes": {}
|
| 406 |
}
|
| 407 |
},
|
| 408 |
+
"total_flos": 3.880435310788608e+16,
|
| 409 |
"train_batch_size": 4,
|
| 410 |
"trial_name": null,
|
| 411 |
"trial_params": null
|