Training in progress, step 7980, 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 sha256:68f6d3fda13a794fae91b5f73cef78dc33f7ef2dcb2544777244a72cfe11d9e5
|
| 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 sha256:4b3ae808e34f3ff5f69e33438f344f8285105c510fc76414c1a2afc6cd1472d2
|
| 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:ec245be51baf3307d89e21d1c6845a55bb42f7a847b8c9540754a8a023e4fea8
|
| 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": 61.
|
| 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,
|
|
@@ -14354,6 +14354,24 @@
|
|
| 14354 |
"mean_token_accuracy": 0.6648034691810608,
|
| 14355 |
"num_tokens": 29064129.0,
|
| 14356 |
"step": 7970
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14357 |
}
|
| 14358 |
],
|
| 14359 |
"logging_steps": 5,
|
|
@@ -14373,7 +14391,7 @@
|
|
| 14373 |
"attributes": {}
|
| 14374 |
}
|
| 14375 |
},
|
| 14376 |
-
"total_flos": 1.
|
| 14377 |
"train_batch_size": 4,
|
| 14378 |
"trial_name": null,
|
| 14379 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 61.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7980,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14354 |
"mean_token_accuracy": 0.6648034691810608,
|
| 14355 |
"num_tokens": 29064129.0,
|
| 14356 |
"step": 7970
|
| 14357 |
+
},
|
| 14358 |
+
{
|
| 14359 |
+
"epoch": 61.34615384615385,
|
| 14360 |
+
"grad_norm": 0.0,
|
| 14361 |
+
"learning_rate": 1.0130000000000001e-05,
|
| 14362 |
+
"loss": 1.7599,
|
| 14363 |
+
"mean_token_accuracy": 0.6455144137144089,
|
| 14364 |
+
"num_tokens": 29082239.0,
|
| 14365 |
+
"step": 7975
|
| 14366 |
+
},
|
| 14367 |
+
{
|
| 14368 |
+
"epoch": 61.38461538461539,
|
| 14369 |
+
"grad_norm": 0.0,
|
| 14370 |
+
"learning_rate": 1.0105e-05,
|
| 14371 |
+
"loss": 1.7216,
|
| 14372 |
+
"mean_token_accuracy": 0.6553202778100967,
|
| 14373 |
+
"num_tokens": 29100554.0,
|
| 14374 |
+
"step": 7980
|
| 14375 |
}
|
| 14376 |
],
|
| 14377 |
"logging_steps": 5,
|
|
|
|
| 14391 |
"attributes": {}
|
| 14392 |
}
|
| 14393 |
},
|
| 14394 |
+
"total_flos": 1.4754590271347098e+18,
|
| 14395 |
"train_batch_size": 4,
|
| 14396 |
"trial_name": null,
|
| 14397 |
"trial_params": null
|