Training in progress, step 1520, 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:f9513d5bc9f5e51f33f7a3fc4e4c9a97217f59e8195f352891a0f3ed5691acc6
|
| 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 sha256:38f197c99efa2ecfd7eb95a2da165f4059aa5dac92e72d47a85d56470d06e722
|
| 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:da89d217ef5403035559a82f63d08a5f52be6d249b1596fc1e7fb64cceb8b90d
|
| 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": 11.
|
| 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,
|
|
@@ -2726,6 +2726,24 @@
|
|
| 2726 |
"mean_token_accuracy": 0.6475972950458526,
|
| 2727 |
"num_tokens": 5506841.0,
|
| 2728 |
"step": 1510
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2729 |
}
|
| 2730 |
],
|
| 2731 |
"logging_steps": 5,
|
|
@@ -2745,7 +2763,7 @@
|
|
| 2745 |
"attributes": {}
|
| 2746 |
}
|
| 2747 |
},
|
| 2748 |
-
"total_flos": 2.
|
| 2749 |
"train_batch_size": 4,
|
| 2750 |
"trial_name": null,
|
| 2751 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 11.692307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1520,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2726 |
"mean_token_accuracy": 0.6475972950458526,
|
| 2727 |
"num_tokens": 5506841.0,
|
| 2728 |
"step": 1510
|
| 2729 |
+
},
|
| 2730 |
+
{
|
| 2731 |
+
"epoch": 11.653846153846153,
|
| 2732 |
+
"grad_norm": 0.0,
|
| 2733 |
+
"learning_rate": 4.2430000000000005e-05,
|
| 2734 |
+
"loss": 1.7238,
|
| 2735 |
+
"mean_token_accuracy": 0.6543399661779403,
|
| 2736 |
+
"num_tokens": 5525059.0,
|
| 2737 |
+
"step": 1515
|
| 2738 |
+
},
|
| 2739 |
+
{
|
| 2740 |
+
"epoch": 11.692307692307692,
|
| 2741 |
+
"grad_norm": 0.0,
|
| 2742 |
+
"learning_rate": 4.2405e-05,
|
| 2743 |
+
"loss": 1.7736,
|
| 2744 |
+
"mean_token_accuracy": 0.6412011951208114,
|
| 2745 |
+
"num_tokens": 5542986.0,
|
| 2746 |
+
"step": 1520
|
| 2747 |
}
|
| 2748 |
],
|
| 2749 |
"logging_steps": 5,
|
|
|
|
| 2763 |
"attributes": {}
|
| 2764 |
}
|
| 2765 |
},
|
| 2766 |
+
"total_flos": 2.808429965991936e+17,
|
| 2767 |
"train_batch_size": 4,
|
| 2768 |
"trial_name": null,
|
| 2769 |
"trial_params": null
|