Training in progress, step 5860, 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 sha256:694b6134e8ac6c726864e5a295afcd0070c5465039b91e2be055e30a3c2d99d7
|
| 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:cdc840433a9988b333a1d816274526aabb6d42664de5c691db2cd7523980ca4e
|
| 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 sha256:1f13127726f11f00662c2a84df81c91436b2b3b2ea680c84de288d8ebed3d40f
|
| 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": 45.
|
| 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,
|
|
@@ -10538,6 +10538,24 @@
|
|
| 10538 |
"mean_token_accuracy": 0.6449836879968643,
|
| 10539 |
"num_tokens": 21334725.0,
|
| 10540 |
"step": 5850
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10541 |
}
|
| 10542 |
],
|
| 10543 |
"logging_steps": 5,
|
|
@@ -10557,7 +10575,7 @@
|
|
| 10557 |
"attributes": {}
|
| 10558 |
}
|
| 10559 |
},
|
| 10560 |
-
"total_flos": 1.
|
| 10561 |
"train_batch_size": 4,
|
| 10562 |
"trial_name": null,
|
| 10563 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 45.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5860,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10538 |
"mean_token_accuracy": 0.6449836879968643,
|
| 10539 |
"num_tokens": 21334725.0,
|
| 10540 |
"step": 5850
|
| 10541 |
+
},
|
| 10542 |
+
{
|
| 10543 |
+
"epoch": 45.03846153846154,
|
| 10544 |
+
"grad_norm": 0.0,
|
| 10545 |
+
"learning_rate": 2.0730000000000003e-05,
|
| 10546 |
+
"loss": 1.7384,
|
| 10547 |
+
"mean_token_accuracy": 0.6504657328128814,
|
| 10548 |
+
"num_tokens": 21353119.0,
|
| 10549 |
+
"step": 5855
|
| 10550 |
+
},
|
| 10551 |
+
{
|
| 10552 |
+
"epoch": 45.07692307692308,
|
| 10553 |
+
"grad_norm": 0.0,
|
| 10554 |
+
"learning_rate": 2.0705000000000003e-05,
|
| 10555 |
+
"loss": 1.6998,
|
| 10556 |
+
"mean_token_accuracy": 0.6628474831581116,
|
| 10557 |
+
"num_tokens": 21371719.0,
|
| 10558 |
+
"step": 5860
|
| 10559 |
}
|
| 10560 |
],
|
| 10561 |
"logging_steps": 5,
|
|
|
|
| 10575 |
"attributes": {}
|
| 10576 |
}
|
| 10577 |
},
|
| 10578 |
+
"total_flos": 1.082973649439785e+18,
|
| 10579 |
"train_batch_size": 4,
|
| 10580 |
"trial_name": null,
|
| 10581 |
"trial_params": null
|