Training in progress, step 8210, 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:c7ab29be7ec5ad675fa2d8bc7eb52e630e8d0c70c160f9bd56f21ff823669d1c
|
| 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 sha256:7af122bf7261c1c77e6c2dd8ed62463c2c5fe3799682a6f37e56c32dbba4bc5e
|
| 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:d7bc60defe9df12baa59122e5309510c66624e57cbef9f89b32f9906eeb258a8
|
| 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": 63.
|
| 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,
|
|
@@ -14768,6 +14768,24 @@
|
|
| 14768 |
"mean_token_accuracy": 0.658037719130516,
|
| 14769 |
"num_tokens": 29905302.0,
|
| 14770 |
"step": 8200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14771 |
}
|
| 14772 |
],
|
| 14773 |
"logging_steps": 5,
|
|
@@ -14787,7 +14805,7 @@
|
|
| 14787 |
"attributes": {}
|
| 14788 |
}
|
| 14789 |
},
|
| 14790 |
-
"total_flos": 1.
|
| 14791 |
"train_batch_size": 4,
|
| 14792 |
"trial_name": null,
|
| 14793 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 63.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8210,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14768 |
"mean_token_accuracy": 0.658037719130516,
|
| 14769 |
"num_tokens": 29905302.0,
|
| 14770 |
"step": 8200
|
| 14771 |
+
},
|
| 14772 |
+
{
|
| 14773 |
+
"epoch": 63.11538461538461,
|
| 14774 |
+
"grad_norm": 0.0,
|
| 14775 |
+
"learning_rate": 8.98e-06,
|
| 14776 |
+
"loss": 1.7854,
|
| 14777 |
+
"mean_token_accuracy": 0.6415458977222442,
|
| 14778 |
+
"num_tokens": 29923223.0,
|
| 14779 |
+
"step": 8205
|
| 14780 |
+
},
|
| 14781 |
+
{
|
| 14782 |
+
"epoch": 63.15384615384615,
|
| 14783 |
+
"grad_norm": 0.0,
|
| 14784 |
+
"learning_rate": 8.955000000000002e-06,
|
| 14785 |
+
"loss": 1.6884,
|
| 14786 |
+
"mean_token_accuracy": 0.6621178448200226,
|
| 14787 |
+
"num_tokens": 29941689.0,
|
| 14788 |
+
"step": 8210
|
| 14789 |
}
|
| 14790 |
],
|
| 14791 |
"logging_steps": 5,
|
|
|
|
| 14805 |
"attributes": {}
|
| 14806 |
}
|
| 14807 |
},
|
| 14808 |
+
"total_flos": 1.5182074542351974e+18,
|
| 14809 |
"train_batch_size": 4,
|
| 14810 |
"trial_name": null,
|
| 14811 |
"trial_params": null
|