Training in progress, step 8820, 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:b717361b14934f0abd58d04f713a0faa7569745a467b545ff553d82e67e41bcf
|
| 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 sha256:71d77b4432f6408d595e7fd93f82f9e737c15ba7a3f4a8e8db7a9815a1c9263c
|
| 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:ef88e617e9567f57d5678153f34171443fdfd396bc877faf6d0e42644b414b65
|
| 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": 67.
|
| 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,
|
|
@@ -15866,6 +15866,24 @@
|
|
| 15866 |
"mean_token_accuracy": 0.6717524290084839,
|
| 15867 |
"num_tokens": 32129582.0,
|
| 15868 |
"step": 8810
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15869 |
}
|
| 15870 |
],
|
| 15871 |
"logging_steps": 5,
|
|
@@ -15885,7 +15903,7 @@
|
|
| 15885 |
"attributes": {}
|
| 15886 |
}
|
| 15887 |
},
|
| 15888 |
-
"total_flos": 1.
|
| 15889 |
"train_batch_size": 4,
|
| 15890 |
"trial_name": null,
|
| 15891 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 67.84615384615384,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8820,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15866 |
"mean_token_accuracy": 0.6717524290084839,
|
| 15867 |
"num_tokens": 32129582.0,
|
| 15868 |
"step": 8810
|
| 15869 |
+
},
|
| 15870 |
+
{
|
| 15871 |
+
"epoch": 67.8076923076923,
|
| 15872 |
+
"grad_norm": 0.0,
|
| 15873 |
+
"learning_rate": 5.93e-06,
|
| 15874 |
+
"loss": 1.724,
|
| 15875 |
+
"mean_token_accuracy": 0.6568674236536026,
|
| 15876 |
+
"num_tokens": 32148017.0,
|
| 15877 |
+
"step": 8815
|
| 15878 |
+
},
|
| 15879 |
+
{
|
| 15880 |
+
"epoch": 67.84615384615384,
|
| 15881 |
+
"grad_norm": 0.0,
|
| 15882 |
+
"learning_rate": 5.905e-06,
|
| 15883 |
+
"loss": 1.7912,
|
| 15884 |
+
"mean_token_accuracy": 0.642418372631073,
|
| 15885 |
+
"num_tokens": 32165982.0,
|
| 15886 |
+
"step": 8820
|
| 15887 |
}
|
| 15888 |
],
|
| 15889 |
"logging_steps": 5,
|
|
|
|
| 15903 |
"attributes": {}
|
| 15904 |
}
|
| 15905 |
},
|
| 15906 |
+
"total_flos": 1.6309438236485222e+18,
|
| 15907 |
"train_batch_size": 4,
|
| 15908 |
"trial_name": null,
|
| 15909 |
"trial_params": null
|