Training in progress, step 3710, 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 sha256:9ee5600637cd11ae64164870b5f489a64d77e9d653273c79980a97ebe28cb290
|
| 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 sha256:2380af14500c8d3aff42f698bece8e5cb4fee5b57864ed05439ea142acff19c9
|
| 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 sha256:6ff08e9f6beb2bbf3032989330fabef83ee4fe07bd610541fa11190213070127
|
| 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": 28.
|
| 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,
|
|
@@ -6668,6 +6668,24 @@
|
|
| 6668 |
"mean_token_accuracy": 0.6544462114572525,
|
| 6669 |
"num_tokens": 13494620.0,
|
| 6670 |
"step": 3700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6671 |
}
|
| 6672 |
],
|
| 6673 |
"logging_steps": 5,
|
|
@@ -6687,7 +6705,7 @@
|
|
| 6687 |
"attributes": {}
|
| 6688 |
}
|
| 6689 |
},
|
| 6690 |
-
"total_flos": 6.
|
| 6691 |
"train_batch_size": 4,
|
| 6692 |
"trial_name": null,
|
| 6693 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 28.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3710,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6668 |
"mean_token_accuracy": 0.6544462114572525,
|
| 6669 |
"num_tokens": 13494620.0,
|
| 6670 |
"step": 3700
|
| 6671 |
+
},
|
| 6672 |
+
{
|
| 6673 |
+
"epoch": 28.5,
|
| 6674 |
+
"grad_norm": 0.0,
|
| 6675 |
+
"learning_rate": 3.1480000000000004e-05,
|
| 6676 |
+
"loss": 1.7707,
|
| 6677 |
+
"mean_token_accuracy": 0.6433985292911529,
|
| 6678 |
+
"num_tokens": 13512210.0,
|
| 6679 |
+
"step": 3705
|
| 6680 |
+
},
|
| 6681 |
+
{
|
| 6682 |
+
"epoch": 28.53846153846154,
|
| 6683 |
+
"grad_norm": 0.0,
|
| 6684 |
+
"learning_rate": 3.1455e-05,
|
| 6685 |
+
"loss": 1.7642,
|
| 6686 |
+
"mean_token_accuracy": 0.6466316103935241,
|
| 6687 |
+
"num_tokens": 13529925.0,
|
| 6688 |
+
"step": 3710
|
| 6689 |
}
|
| 6690 |
],
|
| 6691 |
"logging_steps": 5,
|
|
|
|
| 6705 |
"attributes": {}
|
| 6706 |
}
|
| 6707 |
},
|
| 6708 |
+
"total_flos": 6.857164820629094e+17,
|
| 6709 |
"train_batch_size": 4,
|
| 6710 |
"trial_name": null,
|
| 6711 |
"trial_params": null
|