Training in progress, step 7490, 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 sha256:7953b3802d705b2c9ae90d783c596d1f7b5bc620a8e41c05e6085dd806394989
|
| 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:bb3f143e01fe25a7bdf20bafbaea1749d370de6c02f126b45da594deeb88ef78
|
| 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:dbc773f1f62650d22e59cadd0c90b1d33979ab670a5279820ac02eb7f7c3da41
|
| 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": 57.
|
| 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,
|
|
@@ -13472,6 +13472,24 @@
|
|
| 13472 |
"mean_token_accuracy": 0.6510590463876724,
|
| 13473 |
"num_tokens": 27279536.0,
|
| 13474 |
"step": 7480
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13475 |
}
|
| 13476 |
],
|
| 13477 |
"logging_steps": 5,
|
|
@@ -13491,7 +13509,7 @@
|
|
| 13491 |
"attributes": {}
|
| 13492 |
}
|
| 13493 |
},
|
| 13494 |
-
"total_flos": 1.
|
| 13495 |
"train_batch_size": 4,
|
| 13496 |
"trial_name": null,
|
| 13497 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 57.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7490,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13472 |
"mean_token_accuracy": 0.6510590463876724,
|
| 13473 |
"num_tokens": 27279536.0,
|
| 13474 |
"step": 7480
|
| 13475 |
+
},
|
| 13476 |
+
{
|
| 13477 |
+
"epoch": 57.57692307692308,
|
| 13478 |
+
"grad_norm": 0.0,
|
| 13479 |
+
"learning_rate": 1.258e-05,
|
| 13480 |
+
"loss": 1.7754,
|
| 13481 |
+
"mean_token_accuracy": 0.6381223618984222,
|
| 13482 |
+
"num_tokens": 27297805.0,
|
| 13483 |
+
"step": 7485
|
| 13484 |
+
},
|
| 13485 |
+
{
|
| 13486 |
+
"epoch": 57.61538461538461,
|
| 13487 |
+
"grad_norm": 0.0,
|
| 13488 |
+
"learning_rate": 1.2555000000000001e-05,
|
| 13489 |
+
"loss": 1.7051,
|
| 13490 |
+
"mean_token_accuracy": 0.6624167144298554,
|
| 13491 |
+
"num_tokens": 27316540.0,
|
| 13492 |
+
"step": 7490
|
| 13493 |
}
|
| 13494 |
],
|
| 13495 |
"logging_steps": 5,
|
|
|
|
| 13509 |
"attributes": {}
|
| 13510 |
}
|
| 13511 |
},
|
| 13512 |
+
"total_flos": 1.3849817474536243e+18,
|
| 13513 |
"train_batch_size": 4,
|
| 13514 |
"trial_name": null,
|
| 13515 |
"trial_params": null
|