Training in progress, step 1590, 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:f9435bb32de0ee9cd5e5f358ba8f37c4329bfd0d2844c0da24846a74b62a2e2f
|
| 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 sha256:9aaa70c3b16035e63f370464de0ef64c23d02dafafdbf49c89cc9c7f1362aef8
|
| 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 sha256:37272f2a097993ee9a1344c12a4e78f2d7cbf98abfce88851d67c17b3d4763d7
|
| 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": 12.
|
| 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,
|
|
@@ -2852,6 +2852,24 @@
|
|
| 2852 |
"mean_token_accuracy": 0.6407176822423934,
|
| 2853 |
"num_tokens": 5759857.0,
|
| 2854 |
"step": 1580
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2855 |
}
|
| 2856 |
],
|
| 2857 |
"logging_steps": 5,
|
|
@@ -2871,7 +2889,7 @@
|
|
| 2871 |
"attributes": {}
|
| 2872 |
}
|
| 2873 |
},
|
| 2874 |
-
"total_flos": 2.
|
| 2875 |
"train_batch_size": 4,
|
| 2876 |
"trial_name": null,
|
| 2877 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 12.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1590,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2852 |
"mean_token_accuracy": 0.6407176822423934,
|
| 2853 |
"num_tokens": 5759857.0,
|
| 2854 |
"step": 1580
|
| 2855 |
+
},
|
| 2856 |
+
{
|
| 2857 |
+
"epoch": 12.192307692307692,
|
| 2858 |
+
"grad_norm": 0.0,
|
| 2859 |
+
"learning_rate": 4.2080000000000004e-05,
|
| 2860 |
+
"loss": 1.8206,
|
| 2861 |
+
"mean_token_accuracy": 0.6390235781669616,
|
| 2862 |
+
"num_tokens": 5777131.0,
|
| 2863 |
+
"step": 1585
|
| 2864 |
+
},
|
| 2865 |
+
{
|
| 2866 |
+
"epoch": 12.23076923076923,
|
| 2867 |
+
"grad_norm": 0.0,
|
| 2868 |
+
"learning_rate": 4.2055e-05,
|
| 2869 |
+
"loss": 1.7858,
|
| 2870 |
+
"mean_token_accuracy": 0.6427943378686904,
|
| 2871 |
+
"num_tokens": 5795346.0,
|
| 2872 |
+
"step": 1590
|
| 2873 |
}
|
| 2874 |
],
|
| 2875 |
"logging_steps": 5,
|
|
|
|
| 2889 |
"attributes": {}
|
| 2890 |
}
|
| 2891 |
},
|
| 2892 |
+
"total_flos": 2.934995999042765e+17,
|
| 2893 |
"train_batch_size": 4,
|
| 2894 |
"trial_name": null,
|
| 2895 |
"trial_params": null
|