Training in progress, step 6390, 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 sha256:7bfb4bd2fb34ed69b171a495a9c0de81b0b7652c927b0b54b2b6204b3c2e36e2
|
| 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 sha256:9d30717e388a64e5b9b23cc5ba1a1c97837e91c63d17fb4ecd28dbfbcd8ba2bb
|
| 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 sha256:1d7733025bb3900e2edc93487ee8fd2f4d7ce6df0b8074919a1e5c51ea02581d
|
| 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": 49.
|
| 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,
|
|
@@ -11492,6 +11492,24 @@
|
|
| 11492 |
"mean_token_accuracy": 0.6711469799280166,
|
| 11493 |
"num_tokens": 23268600.0,
|
| 11494 |
"step": 6380
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11495 |
}
|
| 11496 |
],
|
| 11497 |
"logging_steps": 5,
|
|
@@ -11511,7 +11529,7 @@
|
|
| 11511 |
"attributes": {}
|
| 11512 |
}
|
| 11513 |
},
|
| 11514 |
-
"total_flos": 1.
|
| 11515 |
"train_batch_size": 4,
|
| 11516 |
"trial_name": null,
|
| 11517 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 49.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6390,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11492 |
"mean_token_accuracy": 0.6711469799280166,
|
| 11493 |
"num_tokens": 23268600.0,
|
| 11494 |
"step": 6380
|
| 11495 |
+
},
|
| 11496 |
+
{
|
| 11497 |
+
"epoch": 49.11538461538461,
|
| 11498 |
+
"grad_norm": 0.0,
|
| 11499 |
+
"learning_rate": 1.808e-05,
|
| 11500 |
+
"loss": 1.7377,
|
| 11501 |
+
"mean_token_accuracy": 0.6483930766582489,
|
| 11502 |
+
"num_tokens": 23286588.0,
|
| 11503 |
+
"step": 6385
|
| 11504 |
+
},
|
| 11505 |
+
{
|
| 11506 |
+
"epoch": 49.15384615384615,
|
| 11507 |
+
"grad_norm": 0.0,
|
| 11508 |
+
"learning_rate": 1.8055e-05,
|
| 11509 |
+
"loss": 1.7444,
|
| 11510 |
+
"mean_token_accuracy": 0.6448217332363129,
|
| 11511 |
+
"num_tokens": 23304489.0,
|
| 11512 |
+
"step": 6390
|
| 11513 |
}
|
| 11514 |
],
|
| 11515 |
"logging_steps": 5,
|
|
|
|
| 11529 |
"attributes": {}
|
| 11530 |
}
|
| 11531 |
},
|
| 11532 |
+
"total_flos": 1.1813746436348314e+18,
|
| 11533 |
"train_batch_size": 4,
|
| 11534 |
"trial_name": null,
|
| 11535 |
"trial_params": null
|