Training in progress, step 2040, 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:f2e98a27ccb1a3bbd1c95e04bc37c42611d272c4d0f183425527db5004017341
|
| 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:effc189bced68c33e31c37dfa81827f7f00cc724bbba2a8c59ccd93cf95c2b42
|
| 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:f4cd64a8c16f17c95455bc42923d80907250ad373cc3f6486a856fa9f2d84148
|
| 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": 15.
|
| 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,
|
|
@@ -3662,6 +3662,24 @@
|
|
| 3662 |
"mean_token_accuracy": 0.6595021516084671,
|
| 3663 |
"num_tokens": 7402054.0,
|
| 3664 |
"step": 2030
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3665 |
}
|
| 3666 |
],
|
| 3667 |
"logging_steps": 5,
|
|
@@ -3681,7 +3699,7 @@
|
|
| 3681 |
"attributes": {}
|
| 3682 |
}
|
| 3683 |
},
|
| 3684 |
-
"total_flos": 3.
|
| 3685 |
"train_batch_size": 4,
|
| 3686 |
"trial_name": null,
|
| 3687 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 15.692307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2040,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3662 |
"mean_token_accuracy": 0.6595021516084671,
|
| 3663 |
"num_tokens": 7402054.0,
|
| 3664 |
"step": 2030
|
| 3665 |
+
},
|
| 3666 |
+
{
|
| 3667 |
+
"epoch": 15.653846153846153,
|
| 3668 |
+
"grad_norm": 0.0,
|
| 3669 |
+
"learning_rate": 3.983e-05,
|
| 3670 |
+
"loss": 1.7171,
|
| 3671 |
+
"mean_token_accuracy": 0.6517434686422348,
|
| 3672 |
+
"num_tokens": 7420489.0,
|
| 3673 |
+
"step": 2035
|
| 3674 |
+
},
|
| 3675 |
+
{
|
| 3676 |
+
"epoch": 15.692307692307692,
|
| 3677 |
+
"grad_norm": 0.0,
|
| 3678 |
+
"learning_rate": 3.9805e-05,
|
| 3679 |
+
"loss": 1.7047,
|
| 3680 |
+
"mean_token_accuracy": 0.6589993953704834,
|
| 3681 |
+
"num_tokens": 7438755.0,
|
| 3682 |
+
"step": 2040
|
| 3683 |
}
|
| 3684 |
],
|
| 3685 |
"logging_steps": 5,
|
|
|
|
| 3699 |
"attributes": {}
|
| 3700 |
}
|
| 3701 |
},
|
| 3702 |
+
"total_flos": 3.7684388521967616e+17,
|
| 3703 |
"train_batch_size": 4,
|
| 3704 |
"trial_name": null,
|
| 3705 |
"trial_params": null
|