Training in progress, step 6910, 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:a79654c9bcbf99ba7a031df1ab740459309e3d929d6986bacbaaad770fb2784d
|
| 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:c6e0139f55dc6b800f2a7cbad99521c9b1aa67a85c15c43277f10e7e3ffff940
|
| 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 sha256:641ea83c056655e973a62f4d23a7080ba8bdcdc135e8d7f5ad57b85acef883c0
|
| 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": 53.
|
| 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,
|
|
@@ -12428,6 +12428,24 @@
|
|
| 12428 |
"mean_token_accuracy": 0.6515821665525436,
|
| 12429 |
"num_tokens": 25163828.0,
|
| 12430 |
"step": 6900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12431 |
}
|
| 12432 |
],
|
| 12433 |
"logging_steps": 5,
|
|
@@ -12447,7 +12465,7 @@
|
|
| 12447 |
"attributes": {}
|
| 12448 |
}
|
| 12449 |
},
|
| 12450 |
-
"total_flos": 1.
|
| 12451 |
"train_batch_size": 4,
|
| 12452 |
"trial_name": null,
|
| 12453 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 53.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6910,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12428 |
"mean_token_accuracy": 0.6515821665525436,
|
| 12429 |
"num_tokens": 25163828.0,
|
| 12430 |
"step": 6900
|
| 12431 |
+
},
|
| 12432 |
+
{
|
| 12433 |
+
"epoch": 53.11538461538461,
|
| 12434 |
+
"grad_norm": 0.0,
|
| 12435 |
+
"learning_rate": 1.548e-05,
|
| 12436 |
+
"loss": 1.7229,
|
| 12437 |
+
"mean_token_accuracy": 0.6592198878526687,
|
| 12438 |
+
"num_tokens": 25181797.0,
|
| 12439 |
+
"step": 6905
|
| 12440 |
+
},
|
| 12441 |
+
{
|
| 12442 |
+
"epoch": 53.15384615384615,
|
| 12443 |
+
"grad_norm": 0.0,
|
| 12444 |
+
"learning_rate": 1.5455e-05,
|
| 12445 |
+
"loss": 1.7218,
|
| 12446 |
+
"mean_token_accuracy": 0.6529275476932526,
|
| 12447 |
+
"num_tokens": 25200618.0,
|
| 12448 |
+
"step": 6910
|
| 12449 |
}
|
| 12450 |
],
|
| 12451 |
"logging_steps": 5,
|
|
|
|
| 12465 |
"attributes": {}
|
| 12466 |
}
|
| 12467 |
},
|
| 12468 |
+
"total_flos": 1.277802965716992e+18,
|
| 12469 |
"train_batch_size": 4,
|
| 12470 |
"trial_name": null,
|
| 12471 |
"trial_params": null
|