Training in progress, step 4290, 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 sha256:3d2244800af1adeb5298628508182092780e718ad40bd4531c8192810628e46b
|
| 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:ee92a658a2a7350f0de32780032588f47733d031ff8664cf173dcfd875219a21
|
| 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 sha256:6eac1f0bc4b420517d90721470f8b07bca659fb789ce6cd3c67274319aee9beb
|
| 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":
|
| 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,
|
|
@@ -7712,6 +7712,24 @@
|
|
| 7712 |
"mean_token_accuracy": 0.6594868719577789,
|
| 7713 |
"num_tokens": 15610531.0,
|
| 7714 |
"step": 4280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7715 |
}
|
| 7716 |
],
|
| 7717 |
"logging_steps": 5,
|
|
@@ -7731,7 +7749,7 @@
|
|
| 7731 |
"attributes": {}
|
| 7732 |
}
|
| 7733 |
},
|
| 7734 |
-
"total_flos": 7.
|
| 7735 |
"train_batch_size": 4,
|
| 7736 |
"trial_name": null,
|
| 7737 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 33.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4290,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7712 |
"mean_token_accuracy": 0.6594868719577789,
|
| 7713 |
"num_tokens": 15610531.0,
|
| 7714 |
"step": 4280
|
| 7715 |
+
},
|
| 7716 |
+
{
|
| 7717 |
+
"epoch": 32.96153846153846,
|
| 7718 |
+
"grad_norm": 0.0,
|
| 7719 |
+
"learning_rate": 2.858e-05,
|
| 7720 |
+
"loss": 1.8267,
|
| 7721 |
+
"mean_token_accuracy": 0.6349624991416931,
|
| 7722 |
+
"num_tokens": 15627607.0,
|
| 7723 |
+
"step": 4285
|
| 7724 |
+
},
|
| 7725 |
+
{
|
| 7726 |
+
"epoch": 33.0,
|
| 7727 |
+
"grad_norm": 0.0,
|
| 7728 |
+
"learning_rate": 2.8555000000000004e-05,
|
| 7729 |
+
"loss": 1.743,
|
| 7730 |
+
"mean_token_accuracy": 0.6526326090097427,
|
| 7731 |
+
"num_tokens": 15645465.0,
|
| 7732 |
+
"step": 4290
|
| 7733 |
}
|
| 7734 |
],
|
| 7735 |
"logging_steps": 5,
|
|
|
|
| 7749 |
"attributes": {}
|
| 7750 |
}
|
| 7751 |
},
|
| 7752 |
+
"total_flos": 7.92919239450624e+17,
|
| 7753 |
"train_batch_size": 4,
|
| 7754 |
"trial_name": null,
|
| 7755 |
"trial_params": null
|