Training in progress, step 4780, 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 sha256:00eb59d906e6e686c72519621b7f529d6aff67d1866cf12358f11f43fd1823d6
|
| 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 sha256:59a976c8001e3b080f04190ef08d0e8e5f6f754f4e7df409444fe82ae8df5484
|
| 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 sha256:25b36ae72751261435c532cc96d1a951a761a86da12fb221c3f95ac132553494
|
| 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": 36.
|
| 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,
|
|
@@ -8594,6 +8594,24 @@
|
|
| 8594 |
"mean_token_accuracy": 0.6472298890352249,
|
| 8595 |
"num_tokens": 17392790.0,
|
| 8596 |
"step": 4770
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8597 |
}
|
| 8598 |
],
|
| 8599 |
"logging_steps": 5,
|
|
@@ -8613,7 +8631,7 @@
|
|
| 8613 |
"attributes": {}
|
| 8614 |
}
|
| 8615 |
},
|
| 8616 |
-
"total_flos": 8.
|
| 8617 |
"train_batch_size": 4,
|
| 8618 |
"trial_name": null,
|
| 8619 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 36.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4780,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8594 |
"mean_token_accuracy": 0.6472298890352249,
|
| 8595 |
"num_tokens": 17392790.0,
|
| 8596 |
"step": 4770
|
| 8597 |
+
},
|
| 8598 |
+
{
|
| 8599 |
+
"epoch": 36.73076923076923,
|
| 8600 |
+
"grad_norm": 0.0,
|
| 8601 |
+
"learning_rate": 2.613e-05,
|
| 8602 |
+
"loss": 1.7773,
|
| 8603 |
+
"mean_token_accuracy": 0.6443253785371781,
|
| 8604 |
+
"num_tokens": 17411334.0,
|
| 8605 |
+
"step": 4775
|
| 8606 |
+
},
|
| 8607 |
+
{
|
| 8608 |
+
"epoch": 36.76923076923077,
|
| 8609 |
+
"grad_norm": 0.0,
|
| 8610 |
+
"learning_rate": 2.6105e-05,
|
| 8611 |
+
"loss": 1.6968,
|
| 8612 |
+
"mean_token_accuracy": 0.6606687515974045,
|
| 8613 |
+
"num_tokens": 17429786.0,
|
| 8614 |
+
"step": 4780
|
| 8615 |
}
|
| 8616 |
],
|
| 8617 |
"logging_steps": 5,
|
|
|
|
| 8631 |
"attributes": {}
|
| 8632 |
}
|
| 8633 |
},
|
| 8634 |
+
"total_flos": 8.832833096004403e+17,
|
| 8635 |
"train_batch_size": 4,
|
| 8636 |
"trial_name": null,
|
| 8637 |
"trial_params": null
|