Training in progress, step 9680, 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 sha256:9b68636b4061b450939cadb081a3a8b63811067a76cb4e29e2a4c4edb9237343
|
| 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 sha256:4893bf9d927ae558212b73161d164a01e38d3b418d4575587c9317e66ee59c34
|
| 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 sha256:5aa12b784e08085cc2f214cd543e117cf16ac44e1265267deb472cd4f93ab809
|
| 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": 74.
|
| 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,
|
|
@@ -17414,6 +17414,24 @@
|
|
| 17414 |
"mean_token_accuracy": 0.6488317787647248,
|
| 17415 |
"num_tokens": 35264529.0,
|
| 17416 |
"step": 9670
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17417 |
}
|
| 17418 |
],
|
| 17419 |
"logging_steps": 5,
|
|
@@ -17433,7 +17451,7 @@
|
|
| 17433 |
"attributes": {}
|
| 17434 |
}
|
| 17435 |
},
|
| 17436 |
-
"total_flos": 1.
|
| 17437 |
"train_batch_size": 4,
|
| 17438 |
"trial_name": null,
|
| 17439 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 74.46153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9680,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17414 |
"mean_token_accuracy": 0.6488317787647248,
|
| 17415 |
"num_tokens": 35264529.0,
|
| 17416 |
"step": 9670
|
| 17417 |
+
},
|
| 17418 |
+
{
|
| 17419 |
+
"epoch": 74.42307692307692,
|
| 17420 |
+
"grad_norm": 0.0,
|
| 17421 |
+
"learning_rate": 1.6299999999999999e-06,
|
| 17422 |
+
"loss": 1.7144,
|
| 17423 |
+
"mean_token_accuracy": 0.6548575252294541,
|
| 17424 |
+
"num_tokens": 35283055.0,
|
| 17425 |
+
"step": 9675
|
| 17426 |
+
},
|
| 17427 |
+
{
|
| 17428 |
+
"epoch": 74.46153846153847,
|
| 17429 |
+
"grad_norm": 0.0,
|
| 17430 |
+
"learning_rate": 1.6049999999999999e-06,
|
| 17431 |
+
"loss": 1.7571,
|
| 17432 |
+
"mean_token_accuracy": 0.6488740295171738,
|
| 17433 |
+
"num_tokens": 35301939.0,
|
| 17434 |
+
"step": 9680
|
| 17435 |
}
|
| 17436 |
],
|
| 17437 |
"logging_steps": 5,
|
|
|
|
| 17451 |
"attributes": {}
|
| 17452 |
}
|
| 17453 |
},
|
| 17454 |
+
"total_flos": 1.7902307455981978e+18,
|
| 17455 |
"train_batch_size": 4,
|
| 17456 |
"trial_name": null,
|
| 17457 |
"trial_params": null
|