Training in progress, step 2700, 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 sha256:35ac8efe76429b11190aa288386cee3e2e4cfd6742bbb04f379a9afeb63c68d4
|
| 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:e4d56c3cd11d2d65d3fa0c8da5578c6e2d9af1a652b85a362019127492401741
|
| 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:df823ab0564e8ad4707acbf0ce8a68a6360f491a5a216b6957074357e4d0244d
|
| 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,
|
|
@@ -4850,6 +4850,24 @@
|
|
| 4850 |
"mean_token_accuracy": 0.6545427888631821,
|
| 4851 |
"num_tokens": 9808227.0,
|
| 4852 |
"step": 2690
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4853 |
}
|
| 4854 |
],
|
| 4855 |
"logging_steps": 5,
|
|
@@ -4869,7 +4887,7 @@
|
|
| 4869 |
"attributes": {}
|
| 4870 |
}
|
| 4871 |
},
|
| 4872 |
-
"total_flos": 4.
|
| 4873 |
"train_batch_size": 4,
|
| 4874 |
"trial_name": null,
|
| 4875 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 20.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2700,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4850 |
"mean_token_accuracy": 0.6545427888631821,
|
| 4851 |
"num_tokens": 9808227.0,
|
| 4852 |
"step": 2690
|
| 4853 |
+
},
|
| 4854 |
+
{
|
| 4855 |
+
"epoch": 20.73076923076923,
|
| 4856 |
+
"grad_norm": 0.0,
|
| 4857 |
+
"learning_rate": 3.6530000000000004e-05,
|
| 4858 |
+
"loss": 1.7437,
|
| 4859 |
+
"mean_token_accuracy": 0.6440727055072785,
|
| 4860 |
+
"num_tokens": 9826666.0,
|
| 4861 |
+
"step": 2695
|
| 4862 |
+
},
|
| 4863 |
+
{
|
| 4864 |
+
"epoch": 20.76923076923077,
|
| 4865 |
+
"grad_norm": 0.0,
|
| 4866 |
+
"learning_rate": 3.6505e-05,
|
| 4867 |
+
"loss": 1.6243,
|
| 4868 |
+
"mean_token_accuracy": 0.6773371279239655,
|
| 4869 |
+
"num_tokens": 9845929.0,
|
| 4870 |
+
"step": 2700
|
| 4871 |
}
|
| 4872 |
],
|
| 4873 |
"logging_steps": 5,
|
|
|
|
| 4887 |
"attributes": {}
|
| 4888 |
}
|
| 4889 |
},
|
| 4890 |
+
"total_flos": 4.9888264847376384e+17,
|
| 4891 |
"train_batch_size": 4,
|
| 4892 |
"trial_name": null,
|
| 4893 |
"trial_params": null
|