Training in progress, step 1490, 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 sha256:187da24df10bbe73834c7dbfd97028d3891cc88d958885bca10d2042712d0a7a
|
| 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 sha256:706f752dd888c1f93b116886525aa8467ab86ee61d2eca915406675e73614ac2
|
| 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 sha256:92a9763d8ae0665957d06a55e8f9c83d8790449f14f8cd40a100a242778a1b24
|
| 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,
|
|
@@ -2672,6 +2672,24 @@
|
|
| 2672 |
"mean_token_accuracy": 0.6455299586057663,
|
| 2673 |
"num_tokens": 5397097.0,
|
| 2674 |
"step": 1480
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2675 |
}
|
| 2676 |
],
|
| 2677 |
"logging_steps": 5,
|
|
@@ -2691,7 +2709,7 @@
|
|
| 2691 |
"attributes": {}
|
| 2692 |
}
|
| 2693 |
},
|
| 2694 |
-
"total_flos": 2.
|
| 2695 |
"train_batch_size": 4,
|
| 2696 |
"trial_name": null,
|
| 2697 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 11.461538461538462,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1490,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2672 |
"mean_token_accuracy": 0.6455299586057663,
|
| 2673 |
"num_tokens": 5397097.0,
|
| 2674 |
"step": 1480
|
| 2675 |
+
},
|
| 2676 |
+
{
|
| 2677 |
+
"epoch": 11.423076923076923,
|
| 2678 |
+
"grad_norm": 0.0,
|
| 2679 |
+
"learning_rate": 4.258e-05,
|
| 2680 |
+
"loss": 1.7405,
|
| 2681 |
+
"mean_token_accuracy": 0.6521054923534393,
|
| 2682 |
+
"num_tokens": 5415277.0,
|
| 2683 |
+
"step": 1485
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 11.461538461538462,
|
| 2687 |
+
"grad_norm": 0.0,
|
| 2688 |
+
"learning_rate": 4.2555e-05,
|
| 2689 |
+
"loss": 1.7168,
|
| 2690 |
+
"mean_token_accuracy": 0.6546613723039627,
|
| 2691 |
+
"num_tokens": 5433912.0,
|
| 2692 |
+
"step": 1490
|
| 2693 |
}
|
| 2694 |
],
|
| 2695 |
"logging_steps": 5,
|
|
|
|
| 2709 |
"attributes": {}
|
| 2710 |
}
|
| 2711 |
},
|
| 2712 |
+
"total_flos": 2.7536527483305984e+17,
|
| 2713 |
"train_batch_size": 4,
|
| 2714 |
"trial_name": null,
|
| 2715 |
"trial_params": null
|