Training in progress, step 8600, 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:c33fe67b92a615983c2e393045f01ccb0a091189656691c31c2d10c1eeebfe48
|
| 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 sha256:4709fada91c3af976de7d014a1108ecfd2c6864ff3b467f9c0d793b86d927f96
|
| 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:ac31cbacb92cae7b0f79e5aacdc47800ebfc66fa5fd62f1cf29a7008bc206d50
|
| 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,
|
|
@@ -15470,6 +15470,24 @@
|
|
| 15470 |
"mean_token_accuracy": 0.6487796038389206,
|
| 15471 |
"num_tokens": 31327646.0,
|
| 15472 |
"step": 8590
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15473 |
}
|
| 15474 |
],
|
| 15475 |
"logging_steps": 5,
|
|
@@ -15489,7 +15507,7 @@
|
|
| 15489 |
"attributes": {}
|
| 15490 |
}
|
| 15491 |
},
|
| 15492 |
-
"total_flos": 1.
|
| 15493 |
"train_batch_size": 4,
|
| 15494 |
"trial_name": null,
|
| 15495 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 66.15384615384616,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8600,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15470 |
"mean_token_accuracy": 0.6487796038389206,
|
| 15471 |
"num_tokens": 31327646.0,
|
| 15472 |
"step": 8590
|
| 15473 |
+
},
|
| 15474 |
+
{
|
| 15475 |
+
"epoch": 66.11538461538461,
|
| 15476 |
+
"grad_norm": 0.0,
|
| 15477 |
+
"learning_rate": 7.0300000000000005e-06,
|
| 15478 |
+
"loss": 1.7308,
|
| 15479 |
+
"mean_token_accuracy": 0.6545611709356308,
|
| 15480 |
+
"num_tokens": 31346349.0,
|
| 15481 |
+
"step": 8595
|
| 15482 |
+
},
|
| 15483 |
+
{
|
| 15484 |
+
"epoch": 66.15384615384616,
|
| 15485 |
+
"grad_norm": 0.0,
|
| 15486 |
+
"learning_rate": 7.005000000000001e-06,
|
| 15487 |
+
"loss": 1.7115,
|
| 15488 |
+
"mean_token_accuracy": 0.6564001739025116,
|
| 15489 |
+
"num_tokens": 31364569.0,
|
| 15490 |
+
"step": 8600
|
| 15491 |
}
|
| 15492 |
],
|
| 15493 |
"logging_steps": 5,
|
|
|
|
| 15507 |
"attributes": {}
|
| 15508 |
}
|
| 15509 |
},
|
| 15510 |
+
"total_flos": 1.5903797212628582e+18,
|
| 15511 |
"train_batch_size": 4,
|
| 15512 |
"trial_name": null,
|
| 15513 |
"trial_params": null
|