Training in progress, step 3690, 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 sha256:7ba09ee6fdf1a8e577e3148d3ab828fddc002cf9d8cd80df2860404808f846f7
|
| 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 sha256:4c465da17b39ae2a2815e10b4343ed569c9e915b5ccca57de87069f99272b067
|
| 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:a4f5a392977e17ae591e05dec94571e3eb4a526cd12c0f5a170befb53c994f9d
|
| 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": 28.
|
| 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,
|
|
@@ -6632,6 +6632,24 @@
|
|
| 6632 |
"mean_token_accuracy": 0.6571666300296783,
|
| 6633 |
"num_tokens": 13421123.0,
|
| 6634 |
"step": 3680
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6635 |
}
|
| 6636 |
],
|
| 6637 |
"logging_steps": 5,
|
|
@@ -6651,7 +6669,7 @@
|
|
| 6651 |
"attributes": {}
|
| 6652 |
}
|
| 6653 |
},
|
| 6654 |
-
"total_flos": 6.
|
| 6655 |
"train_batch_size": 4,
|
| 6656 |
"trial_name": null,
|
| 6657 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 28.384615384615383,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3690,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6632 |
"mean_token_accuracy": 0.6571666300296783,
|
| 6633 |
"num_tokens": 13421123.0,
|
| 6634 |
"step": 3680
|
| 6635 |
+
},
|
| 6636 |
+
{
|
| 6637 |
+
"epoch": 28.346153846153847,
|
| 6638 |
+
"grad_norm": 0.0,
|
| 6639 |
+
"learning_rate": 3.1580000000000006e-05,
|
| 6640 |
+
"loss": 1.7788,
|
| 6641 |
+
"mean_token_accuracy": 0.6432044029235839,
|
| 6642 |
+
"num_tokens": 13439431.0,
|
| 6643 |
+
"step": 3685
|
| 6644 |
+
},
|
| 6645 |
+
{
|
| 6646 |
+
"epoch": 28.384615384615383,
|
| 6647 |
+
"grad_norm": 0.0,
|
| 6648 |
+
"learning_rate": 3.1555e-05,
|
| 6649 |
+
"loss": 1.7207,
|
| 6650 |
+
"mean_token_accuracy": 0.6578160703182221,
|
| 6651 |
+
"num_tokens": 13457841.0,
|
| 6652 |
+
"step": 3690
|
| 6653 |
}
|
| 6654 |
],
|
| 6655 |
"logging_steps": 5,
|
|
|
|
| 6669 |
"attributes": {}
|
| 6670 |
}
|
| 6671 |
},
|
| 6672 |
+
"total_flos": 6.820161340597862e+17,
|
| 6673 |
"train_batch_size": 4,
|
| 6674 |
"trial_name": null,
|
| 6675 |
"trial_params": null
|