Training in progress, step 3770, 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:b932dd754c16e5f826f5756788dc62444ab9f78a60c14950fd9c6dc416e973a9
|
| 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 sha256:149f22b3447d1f4aa2e7e2877bf7ec77b22fac6d88f2eb46009cf3f70fcd279a
|
| 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 sha256:16084059a18dc9c80ff49b23ce90d57d182f5609cfd2166dd03f47c28313524d
|
| 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":
|
| 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,
|
|
@@ -6776,6 +6776,24 @@
|
|
| 6776 |
"mean_token_accuracy": 0.6581391155719757,
|
| 6777 |
"num_tokens": 13712942.0,
|
| 6778 |
"step": 3760
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6779 |
}
|
| 6780 |
],
|
| 6781 |
"logging_steps": 5,
|
|
@@ -6795,7 +6813,7 @@
|
|
| 6795 |
"attributes": {}
|
| 6796 |
}
|
| 6797 |
},
|
| 6798 |
-
"total_flos": 6.
|
| 6799 |
"train_batch_size": 4,
|
| 6800 |
"trial_name": null,
|
| 6801 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 29.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3770,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6776 |
"mean_token_accuracy": 0.6581391155719757,
|
| 6777 |
"num_tokens": 13712942.0,
|
| 6778 |
"step": 3760
|
| 6779 |
+
},
|
| 6780 |
+
{
|
| 6781 |
+
"epoch": 28.96153846153846,
|
| 6782 |
+
"grad_norm": 0.0,
|
| 6783 |
+
"learning_rate": 3.118e-05,
|
| 6784 |
+
"loss": 1.7421,
|
| 6785 |
+
"mean_token_accuracy": 0.655744206905365,
|
| 6786 |
+
"num_tokens": 13731216.0,
|
| 6787 |
+
"step": 3765
|
| 6788 |
+
},
|
| 6789 |
+
{
|
| 6790 |
+
"epoch": 29.0,
|
| 6791 |
+
"grad_norm": 0.0,
|
| 6792 |
+
"learning_rate": 3.1155e-05,
|
| 6793 |
+
"loss": 1.7639,
|
| 6794 |
+
"mean_token_accuracy": 0.6510610312223435,
|
| 6795 |
+
"num_tokens": 13749045.0,
|
| 6796 |
+
"step": 3770
|
| 6797 |
}
|
| 6798 |
],
|
| 6799 |
"logging_steps": 5,
|
|
|
|
| 6813 |
"attributes": {}
|
| 6814 |
}
|
| 6815 |
},
|
| 6816 |
+
"total_flos": 6.96758619009024e+17,
|
| 6817 |
"train_batch_size": 4,
|
| 6818 |
"trial_name": null,
|
| 6819 |
"trial_params": null
|