Training in progress, step 3230, 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 sha256:83f01cfa2eca984cb92d22a0b3aa4a03bbc345b74719c8d01e26424002268596
|
| 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 sha256:2f10fc08da0025f0d7879308979000835768ab6728523921820e40b504f1020f
|
| 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:e444294172b810335662751ae6795ffaa28e00fc8e25110b63b3d7b5f67485de
|
| 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": 24.
|
| 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,
|
|
@@ -5804,6 +5804,24 @@
|
|
| 5804 |
"mean_token_accuracy": 0.6529559135437012,
|
| 5805 |
"num_tokens": 11741969.0,
|
| 5806 |
"step": 3220
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5807 |
}
|
| 5808 |
],
|
| 5809 |
"logging_steps": 5,
|
|
@@ -5823,7 +5841,7 @@
|
|
| 5823 |
"attributes": {}
|
| 5824 |
}
|
| 5825 |
},
|
| 5826 |
-
"total_flos": 5.
|
| 5827 |
"train_batch_size": 4,
|
| 5828 |
"trial_name": null,
|
| 5829 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 24.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3230,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5804 |
"mean_token_accuracy": 0.6529559135437012,
|
| 5805 |
"num_tokens": 11741969.0,
|
| 5806 |
"step": 3220
|
| 5807 |
+
},
|
| 5808 |
+
{
|
| 5809 |
+
"epoch": 24.807692307692307,
|
| 5810 |
+
"grad_norm": 0.0,
|
| 5811 |
+
"learning_rate": 3.388e-05,
|
| 5812 |
+
"loss": 1.7514,
|
| 5813 |
+
"mean_token_accuracy": 0.6474628210067749,
|
| 5814 |
+
"num_tokens": 11759857.0,
|
| 5815 |
+
"step": 3225
|
| 5816 |
+
},
|
| 5817 |
+
{
|
| 5818 |
+
"epoch": 24.846153846153847,
|
| 5819 |
+
"grad_norm": 0.0,
|
| 5820 |
+
"learning_rate": 3.3855e-05,
|
| 5821 |
+
"loss": 1.696,
|
| 5822 |
+
"mean_token_accuracy": 0.6536848098039627,
|
| 5823 |
+
"num_tokens": 11778672.0,
|
| 5824 |
+
"step": 3230
|
| 5825 |
}
|
| 5826 |
],
|
| 5827 |
"logging_steps": 5,
|
|
|
|
| 5841 |
"attributes": {}
|
| 5842 |
}
|
| 5843 |
},
|
| 5844 |
+
"total_flos": 5.968063525552128e+17,
|
| 5845 |
"train_batch_size": 4,
|
| 5846 |
"trial_name": null,
|
| 5847 |
"trial_params": null
|