Training in progress, step 8220, 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:dedd0dbba96e14cf7cc9fc0b93e7079bd881e8ab38af82e1e257d81b8cccb95f
|
| 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:e555c663b9c23cdd006f710ba3abd3db7e4ac041ba28f78b0a286523bc7d65a5
|
| 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 sha256:7ff71b2d3000d40938e348308e01c4ee43705b8702d322b3c2bf780399c93e6b
|
| 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,
|
|
@@ -14786,6 +14786,24 @@
|
|
| 14786 |
"mean_token_accuracy": 0.6621178448200226,
|
| 14787 |
"num_tokens": 29941689.0,
|
| 14788 |
"step": 8210
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14789 |
}
|
| 14790 |
],
|
| 14791 |
"logging_steps": 5,
|
|
@@ -14805,7 +14823,7 @@
|
|
| 14805 |
"attributes": {}
|
| 14806 |
}
|
| 14807 |
},
|
| 14808 |
-
"total_flos": 1.
|
| 14809 |
"train_batch_size": 4,
|
| 14810 |
"trial_name": null,
|
| 14811 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 63.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8220,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14786 |
"mean_token_accuracy": 0.6621178448200226,
|
| 14787 |
"num_tokens": 29941689.0,
|
| 14788 |
"step": 8210
|
| 14789 |
+
},
|
| 14790 |
+
{
|
| 14791 |
+
"epoch": 63.19230769230769,
|
| 14792 |
+
"grad_norm": 0.0,
|
| 14793 |
+
"learning_rate": 8.930000000000001e-06,
|
| 14794 |
+
"loss": 1.7898,
|
| 14795 |
+
"mean_token_accuracy": 0.6401251316070556,
|
| 14796 |
+
"num_tokens": 29959317.0,
|
| 14797 |
+
"step": 8215
|
| 14798 |
+
},
|
| 14799 |
+
{
|
| 14800 |
+
"epoch": 63.23076923076923,
|
| 14801 |
+
"grad_norm": 0.0,
|
| 14802 |
+
"learning_rate": 8.905e-06,
|
| 14803 |
+
"loss": 1.6928,
|
| 14804 |
+
"mean_token_accuracy": 0.6512804627418518,
|
| 14805 |
+
"num_tokens": 29978320.0,
|
| 14806 |
+
"step": 8220
|
| 14807 |
}
|
| 14808 |
],
|
| 14809 |
"logging_steps": 5,
|
|
|
|
| 14823 |
"attributes": {}
|
| 14824 |
}
|
| 14825 |
},
|
| 14826 |
+
"total_flos": 1.5200511976813363e+18,
|
| 14827 |
"train_batch_size": 4,
|
| 14828 |
"trial_name": null,
|
| 14829 |
"trial_params": null
|