Training in progress, step 8250, 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 sha256:35708112b8fb85516568cff2bb71571db24c13295da36805ece18b9c245d9c53
|
| 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 sha256:2fa0829ea811905d08d7d8ce1f4ec1f87a2549a239062458332806517514815d
|
| 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:ea87066d67cf54e2cfb8d835a037506be0942901c0b27590a9de6b1780ff09f4
|
| 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": 63.
|
| 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,
|
|
@@ -14840,6 +14840,24 @@
|
|
| 14840 |
"mean_token_accuracy": 0.6360196202993393,
|
| 14841 |
"num_tokens": 30051356.0,
|
| 14842 |
"step": 8240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14843 |
}
|
| 14844 |
],
|
| 14845 |
"logging_steps": 5,
|
|
@@ -14859,7 +14877,7 @@
|
|
| 14859 |
"attributes": {}
|
| 14860 |
}
|
| 14861 |
},
|
| 14862 |
-
"total_flos": 1.
|
| 14863 |
"train_batch_size": 4,
|
| 14864 |
"trial_name": null,
|
| 14865 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 63.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8250,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14840 |
"mean_token_accuracy": 0.6360196202993393,
|
| 14841 |
"num_tokens": 30051356.0,
|
| 14842 |
"step": 8240
|
| 14843 |
+
},
|
| 14844 |
+
{
|
| 14845 |
+
"epoch": 63.42307692307692,
|
| 14846 |
+
"grad_norm": 0.0,
|
| 14847 |
+
"learning_rate": 8.78e-06,
|
| 14848 |
+
"loss": 1.7291,
|
| 14849 |
+
"mean_token_accuracy": 0.661040186882019,
|
| 14850 |
+
"num_tokens": 30069584.0,
|
| 14851 |
+
"step": 8245
|
| 14852 |
+
},
|
| 14853 |
+
{
|
| 14854 |
+
"epoch": 63.46153846153846,
|
| 14855 |
+
"grad_norm": 0.0,
|
| 14856 |
+
"learning_rate": 8.755e-06,
|
| 14857 |
+
"loss": 1.7783,
|
| 14858 |
+
"mean_token_accuracy": 0.6421218931674957,
|
| 14859 |
+
"num_tokens": 30087772.0,
|
| 14860 |
+
"step": 8250
|
| 14861 |
}
|
| 14862 |
],
|
| 14863 |
"logging_steps": 5,
|
|
|
|
| 14877 |
"attributes": {}
|
| 14878 |
}
|
| 14879 |
},
|
| 14880 |
+
"total_flos": 1.5255867150567014e+18,
|
| 14881 |
"train_batch_size": 4,
|
| 14882 |
"trial_name": null,
|
| 14883 |
"trial_params": null
|