Training in progress, step 9140, 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 sha256:02c32b0fc5549289d5930e0f746ebcdc5e397a41bbc948d2d19856b6f1985bdf
|
| 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 sha256:1c9a04bf3f9a8dec7f21326e09c6223127c403b2ef51bd90e69f54ae3702b119
|
| 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 sha256:19c42368b7f127ee3a7362ccb866327f65112d523dfc17ea1fa2657e2d87dae9
|
| 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": 70.
|
| 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,
|
|
@@ -16442,6 +16442,24 @@
|
|
| 16442 |
"mean_token_accuracy": 0.6546464413404465,
|
| 16443 |
"num_tokens": 33299469.0,
|
| 16444 |
"step": 9130
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16445 |
}
|
| 16446 |
],
|
| 16447 |
"logging_steps": 5,
|
|
@@ -16461,7 +16479,7 @@
|
|
| 16461 |
"attributes": {}
|
| 16462 |
}
|
| 16463 |
},
|
| 16464 |
-
"total_flos": 1.
|
| 16465 |
"train_batch_size": 4,
|
| 16466 |
"trial_name": null,
|
| 16467 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 70.3076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9140,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16442 |
"mean_token_accuracy": 0.6546464413404465,
|
| 16443 |
"num_tokens": 33299469.0,
|
| 16444 |
"step": 9130
|
| 16445 |
+
},
|
| 16446 |
+
{
|
| 16447 |
+
"epoch": 70.26923076923077,
|
| 16448 |
+
"grad_norm": 0.0,
|
| 16449 |
+
"learning_rate": 4.33e-06,
|
| 16450 |
+
"loss": 1.7084,
|
| 16451 |
+
"mean_token_accuracy": 0.6555704712867737,
|
| 16452 |
+
"num_tokens": 33317456.0,
|
| 16453 |
+
"step": 9135
|
| 16454 |
+
},
|
| 16455 |
+
{
|
| 16456 |
+
"epoch": 70.3076923076923,
|
| 16457 |
+
"grad_norm": 0.0,
|
| 16458 |
+
"learning_rate": 4.305e-06,
|
| 16459 |
+
"loss": 1.7392,
|
| 16460 |
+
"mean_token_accuracy": 0.649817219376564,
|
| 16461 |
+
"num_tokens": 33336143.0,
|
| 16462 |
+
"step": 9140
|
| 16463 |
}
|
| 16464 |
],
|
| 16465 |
"logging_steps": 5,
|
|
|
|
| 16479 |
"attributes": {}
|
| 16480 |
}
|
| 16481 |
},
|
| 16482 |
+
"total_flos": 1.6904221742717338e+18,
|
| 16483 |
"train_batch_size": 4,
|
| 16484 |
"trial_name": null,
|
| 16485 |
"trial_params": null
|