Training in progress, step 3070, 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 sha256:7fbc6da023de86313d7afbaa84a7fbc8f272a0d6b40fdd05f398c5d262d76710
|
| 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:f1fad4d9fbee27c6fa66bf22553df34cf129175dac8f386c795e392e2f6e6ae2
|
| 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:d3e28a2d2dc00a62248b75f85023d2e1811dc1e4d7d53fab45b51d57d5ebd639
|
| 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": 23.
|
| 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,
|
|
@@ -5516,6 +5516,24 @@
|
|
| 5516 |
"mean_token_accuracy": 0.6444110184907913,
|
| 5517 |
"num_tokens": 11160572.0,
|
| 5518 |
"step": 3060
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5519 |
}
|
| 5520 |
],
|
| 5521 |
"logging_steps": 5,
|
|
@@ -5535,7 +5553,7 @@
|
|
| 5535 |
"attributes": {}
|
| 5536 |
}
|
| 5537 |
},
|
| 5538 |
-
"total_flos": 5.
|
| 5539 |
"train_batch_size": 4,
|
| 5540 |
"trial_name": null,
|
| 5541 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 23.615384615384617,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3070,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5516 |
"mean_token_accuracy": 0.6444110184907913,
|
| 5517 |
"num_tokens": 11160572.0,
|
| 5518 |
"step": 3060
|
| 5519 |
+
},
|
| 5520 |
+
{
|
| 5521 |
+
"epoch": 23.576923076923077,
|
| 5522 |
+
"grad_norm": 0.0,
|
| 5523 |
+
"learning_rate": 3.468e-05,
|
| 5524 |
+
"loss": 1.7671,
|
| 5525 |
+
"mean_token_accuracy": 0.6471373438835144,
|
| 5526 |
+
"num_tokens": 11178814.0,
|
| 5527 |
+
"step": 3065
|
| 5528 |
+
},
|
| 5529 |
+
{
|
| 5530 |
+
"epoch": 23.615384615384617,
|
| 5531 |
+
"grad_norm": 0.0,
|
| 5532 |
+
"learning_rate": 3.4655000000000006e-05,
|
| 5533 |
+
"loss": 1.7604,
|
| 5534 |
+
"mean_token_accuracy": 0.650464779138565,
|
| 5535 |
+
"num_tokens": 11196788.0,
|
| 5536 |
+
"step": 3070
|
| 5537 |
}
|
| 5538 |
],
|
| 5539 |
"logging_steps": 5,
|
|
|
|
| 5553 |
"attributes": {}
|
| 5554 |
}
|
| 5555 |
},
|
| 5556 |
+
"total_flos": 5.674028363587584e+17,
|
| 5557 |
"train_batch_size": 4,
|
| 5558 |
"trial_name": null,
|
| 5559 |
"trial_params": null
|