Training in progress, step 2590, 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 sha256:2078850e95dd3e0755bc00fc0358edde6cd8e9f657e8eeb1294b9f89c70bb012
|
| 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:b55b2e17717df5a8df6a921b82d7159722f8863993e04ea408e6223053fdd627
|
| 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:f9a23fd110008fbdd7238d99c211b8a8860aac50ace10e62d568c287376696da
|
| 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": 19.
|
| 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,
|
|
@@ -4652,6 +4652,24 @@
|
|
| 4652 |
"mean_token_accuracy": 0.6579229325056076,
|
| 4653 |
"num_tokens": 9409658.0,
|
| 4654 |
"step": 2580
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4655 |
}
|
| 4656 |
],
|
| 4657 |
"logging_steps": 5,
|
|
@@ -4671,7 +4689,7 @@
|
|
| 4671 |
"attributes": {}
|
| 4672 |
}
|
| 4673 |
},
|
| 4674 |
-
"total_flos": 4.
|
| 4675 |
"train_batch_size": 4,
|
| 4676 |
"trial_name": null,
|
| 4677 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 19.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2590,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4652 |
"mean_token_accuracy": 0.6579229325056076,
|
| 4653 |
"num_tokens": 9409658.0,
|
| 4654 |
"step": 2580
|
| 4655 |
+
},
|
| 4656 |
+
{
|
| 4657 |
+
"epoch": 19.884615384615383,
|
| 4658 |
+
"grad_norm": 0.0,
|
| 4659 |
+
"learning_rate": 3.7080000000000004e-05,
|
| 4660 |
+
"loss": 1.7471,
|
| 4661 |
+
"mean_token_accuracy": 0.6523754239082337,
|
| 4662 |
+
"num_tokens": 9427268.0,
|
| 4663 |
+
"step": 2585
|
| 4664 |
+
},
|
| 4665 |
+
{
|
| 4666 |
+
"epoch": 19.923076923076923,
|
| 4667 |
+
"grad_norm": 0.0,
|
| 4668 |
+
"learning_rate": 3.7055000000000004e-05,
|
| 4669 |
+
"loss": 1.7494,
|
| 4670 |
+
"mean_token_accuracy": 0.6500475823879241,
|
| 4671 |
+
"num_tokens": 9445373.0,
|
| 4672 |
+
"step": 2590
|
| 4673 |
}
|
| 4674 |
],
|
| 4675 |
"logging_steps": 5,
|
|
|
|
| 4689 |
"attributes": {}
|
| 4690 |
}
|
| 4691 |
},
|
| 4692 |
+
"total_flos": 4.787869246090445e+17,
|
| 4693 |
"train_batch_size": 4,
|
| 4694 |
"trial_name": null,
|
| 4695 |
"trial_params": null
|