Training in progress, step 3150, 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 sha256:02e3fdab42c6d4261fb895db7efdc6075e61179bca08c08276f96678472f8a60
|
| 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 sha256:0de6d33160f7ee68bc43518e60255e3080535e751b3c2697651ae7b8eb40938f
|
| 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 sha256:4f308934c989ff3e2adee1a0a8a83128a32cfaefab9126153ebc4db911997554
|
| 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": 24.
|
| 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,
|
|
@@ -5660,6 +5660,24 @@
|
|
| 5660 |
"mean_token_accuracy": 0.6464499235153198,
|
| 5661 |
"num_tokens": 11451759.0,
|
| 5662 |
"step": 3140
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5663 |
}
|
| 5664 |
],
|
| 5665 |
"logging_steps": 5,
|
|
@@ -5679,7 +5697,7 @@
|
|
| 5679 |
"attributes": {}
|
| 5680 |
}
|
| 5681 |
},
|
| 5682 |
-
"total_flos": 5.
|
| 5683 |
"train_batch_size": 4,
|
| 5684 |
"trial_name": null,
|
| 5685 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 24.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3150,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5660 |
"mean_token_accuracy": 0.6464499235153198,
|
| 5661 |
"num_tokens": 11451759.0,
|
| 5662 |
"step": 3140
|
| 5663 |
+
},
|
| 5664 |
+
{
|
| 5665 |
+
"epoch": 24.192307692307693,
|
| 5666 |
+
"grad_norm": 0.0,
|
| 5667 |
+
"learning_rate": 3.4280000000000004e-05,
|
| 5668 |
+
"loss": 1.7251,
|
| 5669 |
+
"mean_token_accuracy": 0.6546833992004395,
|
| 5670 |
+
"num_tokens": 11470163.0,
|
| 5671 |
+
"step": 3145
|
| 5672 |
+
},
|
| 5673 |
+
{
|
| 5674 |
+
"epoch": 24.23076923076923,
|
| 5675 |
+
"grad_norm": 0.0,
|
| 5676 |
+
"learning_rate": 3.4255e-05,
|
| 5677 |
+
"loss": 1.7204,
|
| 5678 |
+
"mean_token_accuracy": 0.6526606291532516,
|
| 5679 |
+
"num_tokens": 11488656.0,
|
| 5680 |
+
"step": 3150
|
| 5681 |
}
|
| 5682 |
],
|
| 5683 |
"logging_steps": 5,
|
|
|
|
| 5697 |
"attributes": {}
|
| 5698 |
}
|
| 5699 |
},
|
| 5700 |
+
"total_flos": 5.821529427070157e+17,
|
| 5701 |
"train_batch_size": 4,
|
| 5702 |
"trial_name": null,
|
| 5703 |
"trial_params": null
|