Training in progress, step 2650, 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:b5c7404354a5c0dcccfffc78663e6532710b331382a00d14a3bd720bc7f3c340
|
| 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 sha256:6b4a1baf04c84ef0aa498e38e3fe4d32748de23e18dd321544f0f63400da0986
|
| 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:f244d5755d446487702ca7efa347fcdd793b684b4c1d444e69f4921903990c54
|
| 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": 20.
|
| 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,
|
|
@@ -4760,6 +4760,24 @@
|
|
| 4760 |
"mean_token_accuracy": 0.6476915091276169,
|
| 4761 |
"num_tokens": 9626593.0,
|
| 4762 |
"step": 2640
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4763 |
}
|
| 4764 |
],
|
| 4765 |
"logging_steps": 5,
|
|
@@ -4779,7 +4797,7 @@
|
|
| 4779 |
"attributes": {}
|
| 4780 |
}
|
| 4781 |
},
|
| 4782 |
-
"total_flos": 4.
|
| 4783 |
"train_batch_size": 4,
|
| 4784 |
"trial_name": null,
|
| 4785 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 20.384615384615383,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2650,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4760 |
"mean_token_accuracy": 0.6476915091276169,
|
| 4761 |
"num_tokens": 9626593.0,
|
| 4762 |
"step": 2640
|
| 4763 |
+
},
|
| 4764 |
+
{
|
| 4765 |
+
"epoch": 20.346153846153847,
|
| 4766 |
+
"grad_norm": 0.0,
|
| 4767 |
+
"learning_rate": 3.6780000000000004e-05,
|
| 4768 |
+
"loss": 1.7698,
|
| 4769 |
+
"mean_token_accuracy": 0.6473258316516877,
|
| 4770 |
+
"num_tokens": 9644649.0,
|
| 4771 |
+
"step": 2645
|
| 4772 |
+
},
|
| 4773 |
+
{
|
| 4774 |
+
"epoch": 20.384615384615383,
|
| 4775 |
+
"grad_norm": 0.0,
|
| 4776 |
+
"learning_rate": 3.6755e-05,
|
| 4777 |
+
"loss": 1.7206,
|
| 4778 |
+
"mean_token_accuracy": 0.6517573058605194,
|
| 4779 |
+
"num_tokens": 9663339.0,
|
| 4780 |
+
"step": 2650
|
| 4781 |
}
|
| 4782 |
],
|
| 4783 |
"logging_steps": 5,
|
|
|
|
| 4797 |
"attributes": {}
|
| 4798 |
}
|
| 4799 |
},
|
| 4800 |
+
"total_flos": 4.896688533966029e+17,
|
| 4801 |
"train_batch_size": 4,
|
| 4802 |
"trial_name": null,
|
| 4803 |
"trial_params": null
|