Training in progress, step 5480, 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:e176744495f775509ca4b35c7f960c54a4e90c63bc108c20f6f5ac24d9347a40
|
| 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 sha256:3e4032d4ba749fcb97ea9b68d104ce055c3191a5835233aaf198d347e58a4c4a
|
| 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 sha256:4dbfe9073993711f2025365a632fa778511172f993a218a4ff6ec01c3b6fb869
|
| 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": 42.
|
| 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,
|
|
@@ -9854,6 +9854,24 @@
|
|
| 9854 |
"mean_token_accuracy": 0.6378622591495514,
|
| 9855 |
"num_tokens": 19948140.0,
|
| 9856 |
"step": 5470
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9857 |
}
|
| 9858 |
],
|
| 9859 |
"logging_steps": 5,
|
|
@@ -9873,7 +9891,7 @@
|
|
| 9873 |
"attributes": {}
|
| 9874 |
}
|
| 9875 |
},
|
| 9876 |
-
"total_flos": 1.
|
| 9877 |
"train_batch_size": 4,
|
| 9878 |
"trial_name": null,
|
| 9879 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 42.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5480,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9854 |
"mean_token_accuracy": 0.6378622591495514,
|
| 9855 |
"num_tokens": 19948140.0,
|
| 9856 |
"step": 5470
|
| 9857 |
+
},
|
| 9858 |
+
{
|
| 9859 |
+
"epoch": 42.11538461538461,
|
| 9860 |
+
"grad_norm": 0.0,
|
| 9861 |
+
"learning_rate": 2.2630000000000002e-05,
|
| 9862 |
+
"loss": 1.7676,
|
| 9863 |
+
"mean_token_accuracy": 0.6440225541591644,
|
| 9864 |
+
"num_tokens": 19965973.0,
|
| 9865 |
+
"step": 5475
|
| 9866 |
+
},
|
| 9867 |
+
{
|
| 9868 |
+
"epoch": 42.15384615384615,
|
| 9869 |
+
"grad_norm": 0.0,
|
| 9870 |
+
"learning_rate": 2.2605e-05,
|
| 9871 |
+
"loss": 1.7853,
|
| 9872 |
+
"mean_token_accuracy": 0.6422720283269883,
|
| 9873 |
+
"num_tokens": 19983738.0,
|
| 9874 |
+
"step": 5480
|
| 9875 |
}
|
| 9876 |
],
|
| 9877 |
"logging_steps": 5,
|
|
|
|
| 9891 |
"attributes": {}
|
| 9892 |
}
|
| 9893 |
},
|
| 9894 |
+
"total_flos": 1.0126867259945779e+18,
|
| 9895 |
"train_batch_size": 4,
|
| 9896 |
"trial_name": null,
|
| 9897 |
"trial_params": null
|