Training in progress, step 2570, 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:e8d00cc9169c93959761c1939578a2c1ab8434ad69f50c8150fef2d8b415909a
|
| 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 sha256:5cbae48456bfb11105c8bfc83681a634029e441a540328f712f35cd3b373442a
|
| 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:ca2ede88cf054aa0a55ace2ee3c12515af684e100b2111e3ad6c533ebe6325f8
|
| 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": 19.
|
| 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,
|
|
@@ -4616,6 +4616,24 @@
|
|
| 4616 |
"mean_token_accuracy": 0.6581139594316483,
|
| 4617 |
"num_tokens": 9336860.0,
|
| 4618 |
"step": 2560
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4619 |
}
|
| 4620 |
],
|
| 4621 |
"logging_steps": 5,
|
|
@@ -4635,7 +4653,7 @@
|
|
| 4635 |
"attributes": {}
|
| 4636 |
}
|
| 4637 |
},
|
| 4638 |
-
"total_flos": 4.
|
| 4639 |
"train_batch_size": 4,
|
| 4640 |
"trial_name": null,
|
| 4641 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 19.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2570,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4616 |
"mean_token_accuracy": 0.6581139594316483,
|
| 4617 |
"num_tokens": 9336860.0,
|
| 4618 |
"step": 2560
|
| 4619 |
+
},
|
| 4620 |
+
{
|
| 4621 |
+
"epoch": 19.73076923076923,
|
| 4622 |
+
"grad_norm": 0.0,
|
| 4623 |
+
"learning_rate": 3.7180000000000007e-05,
|
| 4624 |
+
"loss": 1.7497,
|
| 4625 |
+
"mean_token_accuracy": 0.6539162546396255,
|
| 4626 |
+
"num_tokens": 9354743.0,
|
| 4627 |
+
"step": 2565
|
| 4628 |
+
},
|
| 4629 |
+
{
|
| 4630 |
+
"epoch": 19.76923076923077,
|
| 4631 |
+
"grad_norm": 0.0,
|
| 4632 |
+
"learning_rate": 3.7155e-05,
|
| 4633 |
+
"loss": 1.7125,
|
| 4634 |
+
"mean_token_accuracy": 0.6545383244752884,
|
| 4635 |
+
"num_tokens": 9373351.0,
|
| 4636 |
+
"step": 2570
|
| 4637 |
}
|
| 4638 |
],
|
| 4639 |
"logging_steps": 5,
|
|
|
|
| 4653 |
"attributes": {}
|
| 4654 |
}
|
| 4655 |
},
|
| 4656 |
+
"total_flos": 4.750397367577805e+17,
|
| 4657 |
"train_batch_size": 4,
|
| 4658 |
"trial_name": null,
|
| 4659 |
"trial_params": null
|