Training in progress, step 3210, 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 sha256:9941b48b078912388b0bf02562ca84cc83dd1a023f529a6a32a97571d3784846
|
| 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:ee3f6d70281f26911b3893860d3c252cf4b7168942456935678b1bcc30f672a5
|
| 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:d71e8f0f62cf3acacadd7a0b5e6b23b8dcbb1707aca11a2c385517b49225d8d9
|
| 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,
|
|
@@ -5768,6 +5768,24 @@
|
|
| 5768 |
"mean_token_accuracy": 0.6523280829191208,
|
| 5769 |
"num_tokens": 11669811.0,
|
| 5770 |
"step": 3200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5771 |
}
|
| 5772 |
],
|
| 5773 |
"logging_steps": 5,
|
|
@@ -5787,7 +5805,7 @@
|
|
| 5787 |
"attributes": {}
|
| 5788 |
}
|
| 5789 |
},
|
| 5790 |
-
"total_flos": 5.
|
| 5791 |
"train_batch_size": 4,
|
| 5792 |
"trial_name": null,
|
| 5793 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 24.692307692307693,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3210,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5768 |
"mean_token_accuracy": 0.6523280829191208,
|
| 5769 |
"num_tokens": 11669811.0,
|
| 5770 |
"step": 3200
|
| 5771 |
+
},
|
| 5772 |
+
{
|
| 5773 |
+
"epoch": 24.653846153846153,
|
| 5774 |
+
"grad_norm": 0.0,
|
| 5775 |
+
"learning_rate": 3.398e-05,
|
| 5776 |
+
"loss": 1.71,
|
| 5777 |
+
"mean_token_accuracy": 0.6583969056606293,
|
| 5778 |
+
"num_tokens": 11687820.0,
|
| 5779 |
+
"step": 3205
|
| 5780 |
+
},
|
| 5781 |
+
{
|
| 5782 |
+
"epoch": 24.692307692307693,
|
| 5783 |
+
"grad_norm": 0.0,
|
| 5784 |
+
"learning_rate": 3.3955e-05,
|
| 5785 |
+
"loss": 1.7925,
|
| 5786 |
+
"mean_token_accuracy": 0.636654618382454,
|
| 5787 |
+
"num_tokens": 11705825.0,
|
| 5788 |
+
"step": 3210
|
| 5789 |
}
|
| 5790 |
],
|
| 5791 |
"logging_steps": 5,
|
|
|
|
| 5805 |
"attributes": {}
|
| 5806 |
}
|
| 5807 |
},
|
| 5808 |
+
"total_flos": 5.931564963205939e+17,
|
| 5809 |
"train_batch_size": 4,
|
| 5810 |
"trial_name": null,
|
| 5811 |
"trial_params": null
|