Training in progress, step 4370, 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:fb78f204e7db7deba4b6e12f310d817b7a0b2dfcb2d460d6a7f64ab4f988c630
|
| 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 sha256:9f5ba25c56f9d2bf16bbf4a0befad924ead6ff61b2054930c71a4ef854dc0bde
|
| 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 sha256:224045cfc6a5aa67d23c18d411aabd546d4f8c733f88da734c6b9d7d48e6719e
|
| 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": 33.
|
| 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,
|
|
@@ -7856,6 +7856,24 @@
|
|
| 7856 |
"mean_token_accuracy": 0.6423881828784943,
|
| 7857 |
"num_tokens": 15902772.0,
|
| 7858 |
"step": 4360
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7859 |
}
|
| 7860 |
],
|
| 7861 |
"logging_steps": 5,
|
|
@@ -7875,7 +7893,7 @@
|
|
| 7875 |
"attributes": {}
|
| 7876 |
}
|
| 7877 |
},
|
| 7878 |
-
"total_flos": 8.
|
| 7879 |
"train_batch_size": 4,
|
| 7880 |
"trial_name": null,
|
| 7881 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 33.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4370,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7856 |
"mean_token_accuracy": 0.6423881828784943,
|
| 7857 |
"num_tokens": 15902772.0,
|
| 7858 |
"step": 4360
|
| 7859 |
+
},
|
| 7860 |
+
{
|
| 7861 |
+
"epoch": 33.57692307692308,
|
| 7862 |
+
"grad_norm": 0.0,
|
| 7863 |
+
"learning_rate": 2.818e-05,
|
| 7864 |
+
"loss": 1.7589,
|
| 7865 |
+
"mean_token_accuracy": 0.6487757861614227,
|
| 7866 |
+
"num_tokens": 15921138.0,
|
| 7867 |
+
"step": 4365
|
| 7868 |
+
},
|
| 7869 |
+
{
|
| 7870 |
+
"epoch": 33.61538461538461,
|
| 7871 |
+
"grad_norm": 0.0,
|
| 7872 |
+
"learning_rate": 2.8155000000000004e-05,
|
| 7873 |
+
"loss": 1.7236,
|
| 7874 |
+
"mean_token_accuracy": 0.6539973527193069,
|
| 7875 |
+
"num_tokens": 15939494.0,
|
| 7876 |
+
"step": 4370
|
| 7877 |
}
|
| 7878 |
],
|
| 7879 |
"logging_steps": 5,
|
|
|
|
| 7893 |
"attributes": {}
|
| 7894 |
}
|
| 7895 |
},
|
| 7896 |
+
"total_flos": 8.078033553983078e+17,
|
| 7897 |
"train_batch_size": 4,
|
| 7898 |
"trial_name": null,
|
| 7899 |
"trial_params": null
|