Training in progress, step 6960, 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 sha256:505e5991b4a59280e5ca1da5d0e9cf4eb8a3fac9d069d2a68c2c2c09f22a37f3
|
| 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 sha256:3a82d50f8fb431a1d23f131ae59f0878983d4df9868e07e6e815ed67cfb821f6
|
| 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 sha256:879e0e66488f845753b9342e41378a0eb69db76be5568403a1af3a7122bb8572
|
| 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": 53.
|
| 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,
|
|
@@ -12518,6 +12518,24 @@
|
|
| 12518 |
"mean_token_accuracy": 0.6477054178714752,
|
| 12519 |
"num_tokens": 25346432.0,
|
| 12520 |
"step": 6950
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12521 |
}
|
| 12522 |
],
|
| 12523 |
"logging_steps": 5,
|
|
@@ -12537,7 +12555,7 @@
|
|
| 12537 |
"attributes": {}
|
| 12538 |
}
|
| 12539 |
},
|
| 12540 |
-
"total_flos": 1.
|
| 12541 |
"train_batch_size": 4,
|
| 12542 |
"trial_name": null,
|
| 12543 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 53.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6960,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12518 |
"mean_token_accuracy": 0.6477054178714752,
|
| 12519 |
"num_tokens": 25346432.0,
|
| 12520 |
"step": 6950
|
| 12521 |
+
},
|
| 12522 |
+
{
|
| 12523 |
+
"epoch": 53.5,
|
| 12524 |
+
"grad_norm": 0.0,
|
| 12525 |
+
"learning_rate": 1.523e-05,
|
| 12526 |
+
"loss": 1.7439,
|
| 12527 |
+
"mean_token_accuracy": 0.6488854259252548,
|
| 12528 |
+
"num_tokens": 25364382.0,
|
| 12529 |
+
"step": 6955
|
| 12530 |
+
},
|
| 12531 |
+
{
|
| 12532 |
+
"epoch": 53.53846153846154,
|
| 12533 |
+
"grad_norm": 0.0,
|
| 12534 |
+
"learning_rate": 1.5205e-05,
|
| 12535 |
+
"loss": 1.7786,
|
| 12536 |
+
"mean_token_accuracy": 0.6465272456407547,
|
| 12537 |
+
"num_tokens": 25382179.0,
|
| 12538 |
+
"step": 6960
|
| 12539 |
}
|
| 12540 |
],
|
| 12541 |
"logging_steps": 5,
|
|
|
|
| 12555 |
"attributes": {}
|
| 12556 |
}
|
| 12557 |
},
|
| 12558 |
+
"total_flos": 1.2869769072284467e+18,
|
| 12559 |
"train_batch_size": 4,
|
| 12560 |
"trial_name": null,
|
| 12561 |
"trial_params": null
|