Training in progress, step 3160, 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 sha256:74a779fbd19db78394cc29078939df25a28315e238ba36991bc7dec3c5471b38
|
| 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 sha256:4f819273d86acc0ac5497715e22589288210b09366367ddd45414265885b30fc
|
| 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:f47efc3ad64ce72ef05c68b72182d77a66c45d05a691674f5cf239b2863499dc
|
| 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,
|
|
@@ -5678,6 +5678,24 @@
|
|
| 5678 |
"mean_token_accuracy": 0.6526606291532516,
|
| 5679 |
"num_tokens": 11488656.0,
|
| 5680 |
"step": 3150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5681 |
}
|
| 5682 |
],
|
| 5683 |
"logging_steps": 5,
|
|
@@ -5697,7 +5715,7 @@
|
|
| 5697 |
"attributes": {}
|
| 5698 |
}
|
| 5699 |
},
|
| 5700 |
-
"total_flos": 5.
|
| 5701 |
"train_batch_size": 4,
|
| 5702 |
"trial_name": null,
|
| 5703 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 24.307692307692307,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3160,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5678 |
"mean_token_accuracy": 0.6526606291532516,
|
| 5679 |
"num_tokens": 11488656.0,
|
| 5680 |
"step": 3150
|
| 5681 |
+
},
|
| 5682 |
+
{
|
| 5683 |
+
"epoch": 24.26923076923077,
|
| 5684 |
+
"grad_norm": 0.0,
|
| 5685 |
+
"learning_rate": 3.423e-05,
|
| 5686 |
+
"loss": 1.8343,
|
| 5687 |
+
"mean_token_accuracy": 0.6308804154396057,
|
| 5688 |
+
"num_tokens": 11505937.0,
|
| 5689 |
+
"step": 3155
|
| 5690 |
+
},
|
| 5691 |
+
{
|
| 5692 |
+
"epoch": 24.307692307692307,
|
| 5693 |
+
"grad_norm": 0.0,
|
| 5694 |
+
"learning_rate": 3.4205e-05,
|
| 5695 |
+
"loss": 1.7237,
|
| 5696 |
+
"mean_token_accuracy": 0.6544101685285568,
|
| 5697 |
+
"num_tokens": 11524471.0,
|
| 5698 |
+
"step": 3160
|
| 5699 |
}
|
| 5700 |
],
|
| 5701 |
"logging_steps": 5,
|
|
|
|
| 5715 |
"attributes": {}
|
| 5716 |
}
|
| 5717 |
},
|
| 5718 |
+
"total_flos": 5.839666768945152e+17,
|
| 5719 |
"train_batch_size": 4,
|
| 5720 |
"trial_name": null,
|
| 5721 |
"trial_params": null
|