Training in progress, step 8650, 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 sha256:1636432a9ee999e787f2188a95b0dc10dacc60f0ee5be7481841350af94b8c83
|
| 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:b64dada243ab2e639eee0d13dcf2e8b507f0853de9ee6cbbdc11086de2f7a17d
|
| 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:c0f2f2a1f745154349f7f91169a582f824a5584e8512e5a94e9315355ecdbffc
|
| 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": 66.
|
| 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,
|
|
@@ -15560,6 +15560,24 @@
|
|
| 15560 |
"mean_token_accuracy": 0.6657146126031875,
|
| 15561 |
"num_tokens": 31511342.0,
|
| 15562 |
"step": 8640
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15563 |
}
|
| 15564 |
],
|
| 15565 |
"logging_steps": 5,
|
|
@@ -15579,7 +15597,7 @@
|
|
| 15579 |
"attributes": {}
|
| 15580 |
}
|
| 15581 |
},
|
| 15582 |
-
"total_flos": 1.
|
| 15583 |
"train_batch_size": 4,
|
| 15584 |
"trial_name": null,
|
| 15585 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 66.53846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8650,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15560 |
"mean_token_accuracy": 0.6657146126031875,
|
| 15561 |
"num_tokens": 31511342.0,
|
| 15562 |
"step": 8640
|
| 15563 |
+
},
|
| 15564 |
+
{
|
| 15565 |
+
"epoch": 66.5,
|
| 15566 |
+
"grad_norm": 0.0,
|
| 15567 |
+
"learning_rate": 6.78e-06,
|
| 15568 |
+
"loss": 1.7357,
|
| 15569 |
+
"mean_token_accuracy": 0.6563478767871856,
|
| 15570 |
+
"num_tokens": 31529627.0,
|
| 15571 |
+
"step": 8645
|
| 15572 |
+
},
|
| 15573 |
+
{
|
| 15574 |
+
"epoch": 66.53846153846153,
|
| 15575 |
+
"grad_norm": 0.0,
|
| 15576 |
+
"learning_rate": 6.7550000000000005e-06,
|
| 15577 |
+
"loss": 1.7731,
|
| 15578 |
+
"mean_token_accuracy": 0.6471589595079422,
|
| 15579 |
+
"num_tokens": 31546956.0,
|
| 15580 |
+
"step": 8650
|
| 15581 |
}
|
| 15582 |
],
|
| 15583 |
"logging_steps": 5,
|
|
|
|
| 15597 |
"attributes": {}
|
| 15598 |
}
|
| 15599 |
},
|
| 15600 |
+
"total_flos": 1.5996460722374246e+18,
|
| 15601 |
"train_batch_size": 4,
|
| 15602 |
"trial_name": null,
|
| 15603 |
"trial_params": null
|