Training in progress, step 460, 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:db37b15bbe6475a5b7c9d8ef3e2e19ad882e9a282b270f3bec9adcbd6942be44
|
| 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 sha256:52106349d9d09fc9cdb7ef4e7b64d12aabff13df6cde811f11197a30b98dc5ab
|
| 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 sha256:532119c3b19c98e2274f01a9a2e01e746312a146f006e591ddb1eb3c1ae0384f
|
| 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": 3.
|
| 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,
|
|
@@ -818,6 +818,24 @@
|
|
| 818 |
"mean_token_accuracy": 0.6628347337245941,
|
| 819 |
"num_tokens": 1642694.0,
|
| 820 |
"step": 450
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 821 |
}
|
| 822 |
],
|
| 823 |
"logging_steps": 5,
|
|
@@ -837,7 +855,7 @@
|
|
| 837 |
"attributes": {}
|
| 838 |
}
|
| 839 |
},
|
| 840 |
-
"total_flos": 8.
|
| 841 |
"train_batch_size": 4,
|
| 842 |
"trial_name": null,
|
| 843 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.5384615384615383,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 460,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 818 |
"mean_token_accuracy": 0.6628347337245941,
|
| 819 |
"num_tokens": 1642694.0,
|
| 820 |
"step": 450
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 3.5,
|
| 824 |
+
"grad_norm": 0.0,
|
| 825 |
+
"learning_rate": 4.7730000000000005e-05,
|
| 826 |
+
"loss": 1.7789,
|
| 827 |
+
"mean_token_accuracy": 0.6409151911735534,
|
| 828 |
+
"num_tokens": 1660710.0,
|
| 829 |
+
"step": 455
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 3.5384615384615383,
|
| 833 |
+
"grad_norm": 0.0,
|
| 834 |
+
"learning_rate": 4.7705e-05,
|
| 835 |
+
"loss": 1.8119,
|
| 836 |
+
"mean_token_accuracy": 0.6357834041118622,
|
| 837 |
+
"num_tokens": 1678569.0,
|
| 838 |
+
"step": 460
|
| 839 |
}
|
| 840 |
],
|
| 841 |
"logging_steps": 5,
|
|
|
|
| 855 |
"attributes": {}
|
| 856 |
}
|
| 857 |
},
|
| 858 |
+
"total_flos": 8.497955174252544e+16,
|
| 859 |
"train_batch_size": 4,
|
| 860 |
"trial_name": null,
|
| 861 |
"trial_params": null
|