Training in progress, step 4790, 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:a0fbb585c03e51a716d9a1c8cd6c2dae74ca7a37f26876b88d44a241cefb9147
|
| 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 sha256:97123dffdf6d17afa5edc81615d391896c32a66e10a1736644158bc3e5e38509
|
| 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 sha256:1cd7d9e1c6086b398995507593668ba2644773eea27ee05d8e2fefe3ba4e460c
|
| 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,
|
|
@@ -8612,6 +8612,24 @@
|
|
| 8612 |
"mean_token_accuracy": 0.6606687515974045,
|
| 8613 |
"num_tokens": 17429786.0,
|
| 8614 |
"step": 4780
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8615 |
}
|
| 8616 |
],
|
| 8617 |
"logging_steps": 5,
|
|
@@ -8631,7 +8649,7 @@
|
|
| 8631 |
"attributes": {}
|
| 8632 |
}
|
| 8633 |
},
|
| 8634 |
-
"total_flos": 8.
|
| 8635 |
"train_batch_size": 4,
|
| 8636 |
"trial_name": null,
|
| 8637 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 36.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4790,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8612 |
"mean_token_accuracy": 0.6606687515974045,
|
| 8613 |
"num_tokens": 17429786.0,
|
| 8614 |
"step": 4780
|
| 8615 |
+
},
|
| 8616 |
+
{
|
| 8617 |
+
"epoch": 36.80769230769231,
|
| 8618 |
+
"grad_norm": 0.0,
|
| 8619 |
+
"learning_rate": 2.6079999999999998e-05,
|
| 8620 |
+
"loss": 1.6995,
|
| 8621 |
+
"mean_token_accuracy": 0.6591976523399353,
|
| 8622 |
+
"num_tokens": 17448074.0,
|
| 8623 |
+
"step": 4785
|
| 8624 |
+
},
|
| 8625 |
+
{
|
| 8626 |
+
"epoch": 36.84615384615385,
|
| 8627 |
+
"grad_norm": 0.0,
|
| 8628 |
+
"learning_rate": 2.6055e-05,
|
| 8629 |
+
"loss": 1.7353,
|
| 8630 |
+
"mean_token_accuracy": 0.6497946470975876,
|
| 8631 |
+
"num_tokens": 17466677.0,
|
| 8632 |
+
"step": 4790
|
| 8633 |
}
|
| 8634 |
],
|
| 8635 |
"logging_steps": 5,
|
|
|
|
| 8649 |
"attributes": {}
|
| 8650 |
}
|
| 8651 |
},
|
| 8652 |
+
"total_flos": 8.851651600416768e+17,
|
| 8653 |
"train_batch_size": 4,
|
| 8654 |
"trial_name": null,
|
| 8655 |
"trial_params": null
|