Training in progress, step 7600, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e7a01b3ca5e20350967ae48d32002c29dd85876e5ec5803033e456a48b8dccc
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9839fc0e44504de6c5b518773b6b9d33c8a064e80743f6ba8affc7692e52715
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2f1cd537c9b16a9d607d08e158845aa9ecd233f20110de02d115caf79126c93
|
| 3 |
size 15006
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4e0fe6e0a279be4f329513225eb3848b6eb64a05016932ef1c6587f398b27e4
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -652,6 +652,13 @@
|
|
| 652 |
"eval_samples_per_second": 19.858,
|
| 653 |
"eval_steps_per_second": 2.483,
|
| 654 |
"step": 7500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 655 |
}
|
| 656 |
],
|
| 657 |
"logging_steps": 100,
|
|
@@ -671,7 +678,7 @@
|
|
| 671 |
"attributes": {}
|
| 672 |
}
|
| 673 |
},
|
| 674 |
-
"total_flos": 1.
|
| 675 |
"train_batch_size": 8,
|
| 676 |
"trial_name": null,
|
| 677 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 15.197625371035775,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 7600,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 652 |
"eval_samples_per_second": 19.858,
|
| 653 |
"eval_steps_per_second": 2.483,
|
| 654 |
"step": 7500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 15.197625371035775,
|
| 658 |
+
"grad_norm": 0.20735445618629456,
|
| 659 |
+
"learning_rate": 4.933333333333334e-05,
|
| 660 |
+
"loss": 1.2353,
|
| 661 |
+
"step": 7600
|
| 662 |
}
|
| 663 |
],
|
| 664 |
"logging_steps": 100,
|
|
|
|
| 678 |
"attributes": {}
|
| 679 |
}
|
| 680 |
},
|
| 681 |
+
"total_flos": 1.186156045724654e+19,
|
| 682 |
"train_batch_size": 8,
|
| 683 |
"trial_name": null,
|
| 684 |
"trial_params": null
|