Training in progress, step 4820, 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:a8c804957821ec5f3651974314fd13a33e9599471b1c17b67c7f18ffc33a25e8
|
| 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:ab9eaedefd2b51900b998b0456229f08569b5035fd5b9473387bf2f28d2bac49
|
| 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:e08bb6c38995599f6a4b385bc303a7862b4712ea055ba147aa5c646284064ed2
|
| 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": 37.
|
| 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,
|
|
@@ -8666,6 +8666,24 @@
|
|
| 8666 |
"mean_token_accuracy": 0.6652211785316468,
|
| 8667 |
"num_tokens": 17541885.0,
|
| 8668 |
"step": 4810
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8669 |
}
|
| 8670 |
],
|
| 8671 |
"logging_steps": 5,
|
|
@@ -8685,7 +8703,7 @@
|
|
| 8685 |
"attributes": {}
|
| 8686 |
}
|
| 8687 |
},
|
| 8688 |
-
"total_flos": 8.
|
| 8689 |
"train_batch_size": 4,
|
| 8690 |
"trial_name": null,
|
| 8691 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 37.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4820,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8666 |
"mean_token_accuracy": 0.6652211785316468,
|
| 8667 |
"num_tokens": 17541885.0,
|
| 8668 |
"step": 4810
|
| 8669 |
+
},
|
| 8670 |
+
{
|
| 8671 |
+
"epoch": 37.03846153846154,
|
| 8672 |
+
"grad_norm": 0.0,
|
| 8673 |
+
"learning_rate": 2.5929999999999997e-05,
|
| 8674 |
+
"loss": 1.7167,
|
| 8675 |
+
"mean_token_accuracy": 0.6583490580320358,
|
| 8676 |
+
"num_tokens": 17560348.0,
|
| 8677 |
+
"step": 4815
|
| 8678 |
+
},
|
| 8679 |
+
{
|
| 8680 |
+
"epoch": 37.07692307692308,
|
| 8681 |
+
"grad_norm": 0.0,
|
| 8682 |
+
"learning_rate": 2.5905e-05,
|
| 8683 |
+
"loss": 1.7755,
|
| 8684 |
+
"mean_token_accuracy": 0.6465405881404876,
|
| 8685 |
+
"num_tokens": 17578412.0,
|
| 8686 |
+
"step": 4820
|
| 8687 |
}
|
| 8688 |
],
|
| 8689 |
"logging_steps": 5,
|
|
|
|
| 8703 |
"attributes": {}
|
| 8704 |
}
|
| 8705 |
},
|
| 8706 |
+
"total_flos": 8.908183327644058e+17,
|
| 8707 |
"train_batch_size": 4,
|
| 8708 |
"trial_name": null,
|
| 8709 |
"trial_params": null
|