Training in progress, step 8130, 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 sha256:80413e92264c9b60bef9cb60b7d419a2c6e59268041cdfea2257da47f97b3226
|
| 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:efd3c777c6d617b9dc2a56bafbc16264d66f8534cc64c17883433f9be84af710
|
| 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:c300172777f8c59b63f942d2cd835bf54e7a4c7d8a500654b451ccc4b8740cdc
|
| 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,
|
|
@@ -14624,6 +14624,24 @@
|
|
| 14624 |
"mean_token_accuracy": 0.6640021294355393,
|
| 14625 |
"num_tokens": 29612931.0,
|
| 14626 |
"step": 8120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14627 |
}
|
| 14628 |
],
|
| 14629 |
"logging_steps": 5,
|
|
@@ -14643,7 +14661,7 @@
|
|
| 14643 |
"attributes": {}
|
| 14644 |
}
|
| 14645 |
},
|
| 14646 |
-
"total_flos": 1.
|
| 14647 |
"train_batch_size": 4,
|
| 14648 |
"trial_name": null,
|
| 14649 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 62.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8130,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14624 |
"mean_token_accuracy": 0.6640021294355393,
|
| 14625 |
"num_tokens": 29612931.0,
|
| 14626 |
"step": 8120
|
| 14627 |
+
},
|
| 14628 |
+
{
|
| 14629 |
+
"epoch": 62.5,
|
| 14630 |
+
"grad_norm": 0.0,
|
| 14631 |
+
"learning_rate": 9.38e-06,
|
| 14632 |
+
"loss": 1.8029,
|
| 14633 |
+
"mean_token_accuracy": 0.6408674240112304,
|
| 14634 |
+
"num_tokens": 29630058.0,
|
| 14635 |
+
"step": 8125
|
| 14636 |
+
},
|
| 14637 |
+
{
|
| 14638 |
+
"epoch": 62.53846153846154,
|
| 14639 |
+
"grad_norm": 0.0,
|
| 14640 |
+
"learning_rate": 9.355e-06,
|
| 14641 |
+
"loss": 1.665,
|
| 14642 |
+
"mean_token_accuracy": 0.6620132178068161,
|
| 14643 |
+
"num_tokens": 29649586.0,
|
| 14644 |
+
"step": 8130
|
| 14645 |
}
|
| 14646 |
],
|
| 14647 |
"logging_steps": 5,
|
|
|
|
| 14661 |
"attributes": {}
|
| 14662 |
}
|
| 14663 |
},
|
| 14664 |
+
"total_flos": 1.5033568406873702e+18,
|
| 14665 |
"train_batch_size": 4,
|
| 14666 |
"trial_name": null,
|
| 14667 |
"trial_params": null
|