Training in progress, step 7600, 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:ff9f30b4c6ed1193ecc2faed51aeb7dfaf173ab3e316090afebfa116206f9439
|
| 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:bc09204e54eefa256079906a240c97d4f16752e47b3c29b5d8796ae65e6e91ab
|
| 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:e765d7649954d417c7c7d59ee8ee26245a7510bf17555e3d7e41710cf43898b8
|
| 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": 58.
|
| 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,
|
|
@@ -13670,6 +13670,24 @@
|
|
| 13670 |
"mean_token_accuracy": 0.6401431083679199,
|
| 13671 |
"num_tokens": 27677904.0,
|
| 13672 |
"step": 7590
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13673 |
}
|
| 13674 |
],
|
| 13675 |
"logging_steps": 5,
|
|
@@ -13689,7 +13707,7 @@
|
|
| 13689 |
"attributes": {}
|
| 13690 |
}
|
| 13691 |
},
|
| 13692 |
-
"total_flos": 1.
|
| 13693 |
"train_batch_size": 4,
|
| 13694 |
"trial_name": null,
|
| 13695 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 58.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7600,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13670 |
"mean_token_accuracy": 0.6401431083679199,
|
| 13671 |
"num_tokens": 27677904.0,
|
| 13672 |
"step": 7590
|
| 13673 |
+
},
|
| 13674 |
+
{
|
| 13675 |
+
"epoch": 58.42307692307692,
|
| 13676 |
+
"grad_norm": 0.0,
|
| 13677 |
+
"learning_rate": 1.2030000000000002e-05,
|
| 13678 |
+
"loss": 1.7091,
|
| 13679 |
+
"mean_token_accuracy": 0.6640697896480561,
|
| 13680 |
+
"num_tokens": 27695801.0,
|
| 13681 |
+
"step": 7595
|
| 13682 |
+
},
|
| 13683 |
+
{
|
| 13684 |
+
"epoch": 58.46153846153846,
|
| 13685 |
+
"grad_norm": 0.0,
|
| 13686 |
+
"learning_rate": 1.2005000000000001e-05,
|
| 13687 |
+
"loss": 1.7289,
|
| 13688 |
+
"mean_token_accuracy": 0.6482616752386093,
|
| 13689 |
+
"num_tokens": 27713869.0,
|
| 13690 |
+
"step": 7600
|
| 13691 |
}
|
| 13692 |
],
|
| 13693 |
"logging_steps": 5,
|
|
|
|
| 13707 |
"attributes": {}
|
| 13708 |
}
|
| 13709 |
},
|
| 13710 |
+
"total_flos": 1.4050666743363994e+18,
|
| 13711 |
"train_batch_size": 4,
|
| 13712 |
"trial_name": null,
|
| 13713 |
"trial_params": null
|