Training in progress, step 1510, 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:d8002ac2b1ce5eff5e76ed8f511ed5a78c075466b0ef8b575dd53edf25dce4b1
|
| 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:ae4b1a8e8361323436983cb67d0eb61726cd89b37e3a2688b7774e295adbe19d
|
| 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:bee53f8769ffcec636f548436b31368edfd48361f988492c430e36124c843b5d
|
| 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,
|
|
@@ -2708,6 +2708,24 @@
|
|
| 2708 |
"mean_token_accuracy": 0.6556811064481736,
|
| 2709 |
"num_tokens": 5472123.0,
|
| 2710 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2711 |
}
|
| 2712 |
],
|
| 2713 |
"logging_steps": 5,
|
|
@@ -2727,7 +2745,7 @@
|
|
| 2727 |
"attributes": {}
|
| 2728 |
}
|
| 2729 |
},
|
| 2730 |
-
"total_flos": 2.
|
| 2731 |
"train_batch_size": 4,
|
| 2732 |
"trial_name": null,
|
| 2733 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 11.615384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1510,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2708 |
"mean_token_accuracy": 0.6556811064481736,
|
| 2709 |
"num_tokens": 5472123.0,
|
| 2710 |
"step": 1500
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 11.576923076923077,
|
| 2714 |
+
"grad_norm": 0.0,
|
| 2715 |
+
"learning_rate": 4.248e-05,
|
| 2716 |
+
"loss": 1.7642,
|
| 2717 |
+
"mean_token_accuracy": 0.6464402437210083,
|
| 2718 |
+
"num_tokens": 5489385.0,
|
| 2719 |
+
"step": 1505
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 11.615384615384615,
|
| 2723 |
+
"grad_norm": 0.0,
|
| 2724 |
+
"learning_rate": 4.2455e-05,
|
| 2725 |
+
"loss": 1.7674,
|
| 2726 |
+
"mean_token_accuracy": 0.6475972950458526,
|
| 2727 |
+
"num_tokens": 5506841.0,
|
| 2728 |
+
"step": 1510
|
| 2729 |
}
|
| 2730 |
],
|
| 2731 |
"logging_steps": 5,
|
|
|
|
| 2745 |
"attributes": {}
|
| 2746 |
}
|
| 2747 |
},
|
| 2748 |
+
"total_flos": 2.7907054498971648e+17,
|
| 2749 |
"train_batch_size": 4,
|
| 2750 |
"trial_name": null,
|
| 2751 |
"trial_params": null
|