Training in progress, step 3830, 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 sha256:870ffdda9d3e56f92b5ec38afec972e9d405144d6e86507b4c3295e38155a551
|
| 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:d2fb16718ad17c102b9a5577b17b1fb8a3046ce992d821ba77784065ca951e33
|
| 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 sha256:5a4e132dc1952c6cd453281ba2e7dd724367167657694d3ac2fe8ca4473adae9
|
| 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": 29.
|
| 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,
|
|
@@ -6884,6 +6884,24 @@
|
|
| 6884 |
"mean_token_accuracy": 0.6496599853038788,
|
| 6885 |
"num_tokens": 13933531.0,
|
| 6886 |
"step": 3820
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6887 |
}
|
| 6888 |
],
|
| 6889 |
"logging_steps": 5,
|
|
@@ -6903,7 +6921,7 @@
|
|
| 6903 |
"attributes": {}
|
| 6904 |
}
|
| 6905 |
},
|
| 6906 |
-
"total_flos": 7.
|
| 6907 |
"train_batch_size": 4,
|
| 6908 |
"trial_name": null,
|
| 6909 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 29.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3830,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6884 |
"mean_token_accuracy": 0.6496599853038788,
|
| 6885 |
"num_tokens": 13933531.0,
|
| 6886 |
"step": 3820
|
| 6887 |
+
},
|
| 6888 |
+
{
|
| 6889 |
+
"epoch": 29.423076923076923,
|
| 6890 |
+
"grad_norm": 0.0,
|
| 6891 |
+
"learning_rate": 3.088e-05,
|
| 6892 |
+
"loss": 1.7523,
|
| 6893 |
+
"mean_token_accuracy": 0.6545566976070404,
|
| 6894 |
+
"num_tokens": 13951615.0,
|
| 6895 |
+
"step": 3825
|
| 6896 |
+
},
|
| 6897 |
+
{
|
| 6898 |
+
"epoch": 29.46153846153846,
|
| 6899 |
+
"grad_norm": 0.0,
|
| 6900 |
+
"learning_rate": 3.0855e-05,
|
| 6901 |
+
"loss": 1.8148,
|
| 6902 |
+
"mean_token_accuracy": 0.6359264075756073,
|
| 6903 |
+
"num_tokens": 13969103.0,
|
| 6904 |
+
"step": 3830
|
| 6905 |
}
|
| 6906 |
],
|
| 6907 |
"logging_steps": 5,
|
|
|
|
| 6921 |
"attributes": {}
|
| 6922 |
}
|
| 6923 |
},
|
| 6924 |
+
"total_flos": 7.07937306020905e+17,
|
| 6925 |
"train_batch_size": 4,
|
| 6926 |
"trial_name": null,
|
| 6927 |
"trial_params": null
|