Training in progress, step 500, 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:fb5da41b1c9b190544f9f15538e6cd9fa6e29641176c72f4398f3b6e736cd9f6
|
| 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 sha256:4d3b14b77bece71364a9c46ff392d85bd48b7ec5748cb8db9d6ef5bf19e3999f
|
| 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:d6afd1c36987f46f6d40e6f4c3da6c56135e047736b8566257e3f40973429360
|
| 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,
|
|
@@ -890,6 +890,24 @@
|
|
| 890 |
"mean_token_accuracy": 0.6404696077108383,
|
| 891 |
"num_tokens": 1788454.0,
|
| 892 |
"step": 490
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 893 |
}
|
| 894 |
],
|
| 895 |
"logging_steps": 5,
|
|
@@ -909,7 +927,7 @@
|
|
| 909 |
"attributes": {}
|
| 910 |
}
|
| 911 |
},
|
| 912 |
-
"total_flos": 9.
|
| 913 |
"train_batch_size": 4,
|
| 914 |
"trial_name": null,
|
| 915 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.8461538461538463,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 890 |
"mean_token_accuracy": 0.6404696077108383,
|
| 891 |
"num_tokens": 1788454.0,
|
| 892 |
"step": 490
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 3.8076923076923075,
|
| 896 |
+
"grad_norm": 0.0,
|
| 897 |
+
"learning_rate": 4.753e-05,
|
| 898 |
+
"loss": 1.7256,
|
| 899 |
+
"mean_token_accuracy": 0.6483594387769699,
|
| 900 |
+
"num_tokens": 1807208.0,
|
| 901 |
+
"step": 495
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 3.8461538461538463,
|
| 905 |
+
"grad_norm": 0.0,
|
| 906 |
+
"learning_rate": 4.7505e-05,
|
| 907 |
+
"loss": 1.6791,
|
| 908 |
+
"mean_token_accuracy": 0.6660710662603379,
|
| 909 |
+
"num_tokens": 1826017.0,
|
| 910 |
+
"step": 500
|
| 911 |
}
|
| 912 |
],
|
| 913 |
"logging_steps": 5,
|
|
|
|
| 927 |
"attributes": {}
|
| 928 |
}
|
| 929 |
},
|
| 930 |
+
"total_flos": 9.255665138024448e+16,
|
| 931 |
"train_batch_size": 4,
|
| 932 |
"trial_name": null,
|
| 933 |
"trial_params": null
|