Training in progress, step 8140, 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 sha256:5e2b884029b52beb455683af9c423bf5595a0f63fa08da31988dcb1425df63ed
|
| 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:d345c38d8c2bb45bc799df9959162183cb7fee0b48cd62cff84195f1db033153
|
| 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 sha256:64b5646f2a560b21cbc0d9051a0f403c04176707354df2c16fd8ec662928820c
|
| 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": 62.
|
| 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,
|
|
@@ -14642,6 +14642,24 @@
|
|
| 14642 |
"mean_token_accuracy": 0.6620132178068161,
|
| 14643 |
"num_tokens": 29649586.0,
|
| 14644 |
"step": 8130
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14645 |
}
|
| 14646 |
],
|
| 14647 |
"logging_steps": 5,
|
|
@@ -14661,7 +14679,7 @@
|
|
| 14661 |
"attributes": {}
|
| 14662 |
}
|
| 14663 |
},
|
| 14664 |
-
"total_flos": 1.
|
| 14665 |
"train_batch_size": 4,
|
| 14666 |
"trial_name": null,
|
| 14667 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 62.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8140,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14642 |
"mean_token_accuracy": 0.6620132178068161,
|
| 14643 |
"num_tokens": 29649586.0,
|
| 14644 |
"step": 8130
|
| 14645 |
+
},
|
| 14646 |
+
{
|
| 14647 |
+
"epoch": 62.57692307692308,
|
| 14648 |
+
"grad_norm": 0.0,
|
| 14649 |
+
"learning_rate": 9.33e-06,
|
| 14650 |
+
"loss": 1.7189,
|
| 14651 |
+
"mean_token_accuracy": 0.6585166305303574,
|
| 14652 |
+
"num_tokens": 29668203.0,
|
| 14653 |
+
"step": 8135
|
| 14654 |
+
},
|
| 14655 |
+
{
|
| 14656 |
+
"epoch": 62.61538461538461,
|
| 14657 |
+
"grad_norm": 0.0,
|
| 14658 |
+
"learning_rate": 9.305e-06,
|
| 14659 |
+
"loss": 1.7752,
|
| 14660 |
+
"mean_token_accuracy": 0.6421294629573822,
|
| 14661 |
+
"num_tokens": 29686310.0,
|
| 14662 |
+
"step": 8140
|
| 14663 |
}
|
| 14664 |
],
|
| 14665 |
"logging_steps": 5,
|
|
|
|
| 14679 |
"attributes": {}
|
| 14680 |
}
|
| 14681 |
},
|
| 14682 |
+
"total_flos": 1.50518661156864e+18,
|
| 14683 |
"train_batch_size": 4,
|
| 14684 |
"trial_name": null,
|
| 14685 |
"trial_params": null
|