Training in progress, step 9870, 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 sha256:7a538a8d6fc2cc1e275e8828477cee619ea4015ffeac86ef55493592148a531b
|
| 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:a848a36406091eeafbef24585a49febbf9ef5dcb023c4b65ecacd098364e717a
|
| 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 sha256:9c7138e99739429625382afd05fc4b7ce96e091fde4ec54f5985bc3ad47c26e8
|
| 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": 75.
|
| 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,
|
|
@@ -17756,6 +17756,24 @@
|
|
| 17756 |
"mean_token_accuracy": 0.6667064487934112,
|
| 17757 |
"num_tokens": 35957880.0,
|
| 17758 |
"step": 9860
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17759 |
}
|
| 17760 |
],
|
| 17761 |
"logging_steps": 5,
|
|
@@ -17775,7 +17793,7 @@
|
|
| 17775 |
"attributes": {}
|
| 17776 |
}
|
| 17777 |
},
|
| 17778 |
-
"total_flos": 1.
|
| 17779 |
"train_batch_size": 4,
|
| 17780 |
"trial_name": null,
|
| 17781 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 75.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9870,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17756 |
"mean_token_accuracy": 0.6667064487934112,
|
| 17757 |
"num_tokens": 35957880.0,
|
| 17758 |
"step": 9860
|
| 17759 |
+
},
|
| 17760 |
+
{
|
| 17761 |
+
"epoch": 75.88461538461539,
|
| 17762 |
+
"grad_norm": 0.0,
|
| 17763 |
+
"learning_rate": 6.8e-07,
|
| 17764 |
+
"loss": 1.7049,
|
| 17765 |
+
"mean_token_accuracy": 0.6505464226007461,
|
| 17766 |
+
"num_tokens": 35977218.0,
|
| 17767 |
+
"step": 9865
|
| 17768 |
+
},
|
| 17769 |
+
{
|
| 17770 |
+
"epoch": 75.92307692307692,
|
| 17771 |
+
"grad_norm": 0.0,
|
| 17772 |
+
"learning_rate": 6.550000000000001e-07,
|
| 17773 |
+
"loss": 1.6894,
|
| 17774 |
+
"mean_token_accuracy": 0.6595763146877289,
|
| 17775 |
+
"num_tokens": 35996459.0,
|
| 17776 |
+
"step": 9870
|
| 17777 |
}
|
| 17778 |
],
|
| 17779 |
"logging_steps": 5,
|
|
|
|
| 17793 |
"attributes": {}
|
| 17794 |
}
|
| 17795 |
},
|
| 17796 |
+
"total_flos": 1.825323159825285e+18,
|
| 17797 |
"train_batch_size": 4,
|
| 17798 |
"trial_name": null,
|
| 17799 |
"trial_params": null
|