Training in progress, step 7170, 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 sha256:3b3faae17e9a7d8ef520fe7f3651aa44dd642578871b9ea62e9cd1cfbee2a097
|
| 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 sha256:08ec7ea36ee4cee9ebce98c06916031fca877bbb231ea26cb7a4826a34782ecb
|
| 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 sha256:51047c4f538b24bfe3882ad3c15a555ba17f4d156a54de832dd3e42c99a1686e
|
| 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": 55.
|
| 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,
|
|
@@ -12896,6 +12896,24 @@
|
|
| 12896 |
"mean_token_accuracy": 0.6477168142795563,
|
| 12897 |
"num_tokens": 26111565.0,
|
| 12898 |
"step": 7160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12899 |
}
|
| 12900 |
],
|
| 12901 |
"logging_steps": 5,
|
|
@@ -12915,7 +12933,7 @@
|
|
| 12915 |
"attributes": {}
|
| 12916 |
}
|
| 12917 |
},
|
| 12918 |
-
"total_flos": 1.
|
| 12919 |
"train_batch_size": 4,
|
| 12920 |
"trial_name": null,
|
| 12921 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 55.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7170,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12896 |
"mean_token_accuracy": 0.6477168142795563,
|
| 12897 |
"num_tokens": 26111565.0,
|
| 12898 |
"step": 7160
|
| 12899 |
+
},
|
| 12900 |
+
{
|
| 12901 |
+
"epoch": 55.11538461538461,
|
| 12902 |
+
"grad_norm": 0.0,
|
| 12903 |
+
"learning_rate": 1.4180000000000001e-05,
|
| 12904 |
+
"loss": 1.6735,
|
| 12905 |
+
"mean_token_accuracy": 0.660878399014473,
|
| 12906 |
+
"num_tokens": 26130288.0,
|
| 12907 |
+
"step": 7165
|
| 12908 |
+
},
|
| 12909 |
+
{
|
| 12910 |
+
"epoch": 55.15384615384615,
|
| 12911 |
+
"grad_norm": 0.0,
|
| 12912 |
+
"learning_rate": 1.4155000000000001e-05,
|
| 12913 |
+
"loss": 1.7429,
|
| 12914 |
+
"mean_token_accuracy": 0.644039872288704,
|
| 12915 |
+
"num_tokens": 26148751.0,
|
| 12916 |
+
"step": 7170
|
| 12917 |
}
|
| 12918 |
],
|
| 12919 |
"logging_steps": 5,
|
|
|
|
| 12933 |
"attributes": {}
|
| 12934 |
}
|
| 12935 |
},
|
| 12936 |
+
"total_flos": 1.3259003446960128e+18,
|
| 12937 |
"train_batch_size": 4,
|
| 12938 |
"trial_name": null,
|
| 12939 |
"trial_params": null
|