Training in progress, step 2660, 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:ab80b9b0529449f9fc5ce65efc3a8741d477084a20ca19a5f3a408e822c0df83
|
| 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 sha256:64bdac4847b27172969ecc7757753f3cb85f1c70e9b7a3e819e27fef5aac394b
|
| 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 sha256:5a825b1a4e27b52877998cb14bc3508e34853f554a515c1a25060d44354aecd8
|
| 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": 20.
|
| 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,
|
|
@@ -4778,6 +4778,24 @@
|
|
| 4778 |
"mean_token_accuracy": 0.6517573058605194,
|
| 4779 |
"num_tokens": 9663339.0,
|
| 4780 |
"step": 2650
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4781 |
}
|
| 4782 |
],
|
| 4783 |
"logging_steps": 5,
|
|
@@ -4797,7 +4815,7 @@
|
|
| 4797 |
"attributes": {}
|
| 4798 |
}
|
| 4799 |
},
|
| 4800 |
-
"total_flos": 4.
|
| 4801 |
"train_batch_size": 4,
|
| 4802 |
"trial_name": null,
|
| 4803 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 20.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2660,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4778 |
"mean_token_accuracy": 0.6517573058605194,
|
| 4779 |
"num_tokens": 9663339.0,
|
| 4780 |
"step": 2650
|
| 4781 |
+
},
|
| 4782 |
+
{
|
| 4783 |
+
"epoch": 20.423076923076923,
|
| 4784 |
+
"grad_norm": 0.0,
|
| 4785 |
+
"learning_rate": 3.673e-05,
|
| 4786 |
+
"loss": 1.8082,
|
| 4787 |
+
"mean_token_accuracy": 0.6340971022844315,
|
| 4788 |
+
"num_tokens": 9681407.0,
|
| 4789 |
+
"step": 2655
|
| 4790 |
+
},
|
| 4791 |
+
{
|
| 4792 |
+
"epoch": 20.46153846153846,
|
| 4793 |
+
"grad_norm": 0.0,
|
| 4794 |
+
"learning_rate": 3.6705e-05,
|
| 4795 |
+
"loss": 1.76,
|
| 4796 |
+
"mean_token_accuracy": 0.6423662751913071,
|
| 4797 |
+
"num_tokens": 9698951.0,
|
| 4798 |
+
"step": 2660
|
| 4799 |
}
|
| 4800 |
],
|
| 4801 |
"logging_steps": 5,
|
|
|
|
| 4815 |
"attributes": {}
|
| 4816 |
}
|
| 4817 |
},
|
| 4818 |
+
"total_flos": 4.914738547310592e+17,
|
| 4819 |
"train_batch_size": 4,
|
| 4820 |
"trial_name": null,
|
| 4821 |
"trial_params": null
|