Training in progress, step 8200, 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 sha256:89a689f2332d91ad1226c73935932569401f0e5f3f52e7268270e23e7a295f33
|
| 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:c1f2cc7654e1e4f46f92cdf689187089e88e24da2d1ebd17c1b2fe9d67b3774d
|
| 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:ce6e13a3f22e1ae0f12ff6dc09221d928a3bf1f512fcb0bbe181cbb8cf71028b
|
| 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": 63.
|
| 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,
|
|
@@ -14750,6 +14750,24 @@
|
|
| 14750 |
"mean_token_accuracy": 0.6486757427453995,
|
| 14751 |
"num_tokens": 29868615.0,
|
| 14752 |
"step": 8190
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14753 |
}
|
| 14754 |
],
|
| 14755 |
"logging_steps": 5,
|
|
@@ -14769,7 +14787,7 @@
|
|
| 14769 |
"attributes": {}
|
| 14770 |
}
|
| 14771 |
},
|
| 14772 |
-
"total_flos": 1.
|
| 14773 |
"train_batch_size": 4,
|
| 14774 |
"trial_name": null,
|
| 14775 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 63.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14750 |
"mean_token_accuracy": 0.6486757427453995,
|
| 14751 |
"num_tokens": 29868615.0,
|
| 14752 |
"step": 8190
|
| 14753 |
+
},
|
| 14754 |
+
{
|
| 14755 |
+
"epoch": 63.03846153846154,
|
| 14756 |
+
"grad_norm": 0.0,
|
| 14757 |
+
"learning_rate": 9.030000000000002e-06,
|
| 14758 |
+
"loss": 1.7337,
|
| 14759 |
+
"mean_token_accuracy": 0.648679456114769,
|
| 14760 |
+
"num_tokens": 29886878.0,
|
| 14761 |
+
"step": 8195
|
| 14762 |
+
},
|
| 14763 |
+
{
|
| 14764 |
+
"epoch": 63.07692307692308,
|
| 14765 |
+
"grad_norm": 0.0,
|
| 14766 |
+
"learning_rate": 9.005000000000001e-06,
|
| 14767 |
+
"loss": 1.7119,
|
| 14768 |
+
"mean_token_accuracy": 0.658037719130516,
|
| 14769 |
+
"num_tokens": 29905302.0,
|
| 14770 |
+
"step": 8200
|
| 14771 |
}
|
| 14772 |
],
|
| 14773 |
"logging_steps": 5,
|
|
|
|
| 14787 |
"attributes": {}
|
| 14788 |
}
|
| 14789 |
},
|
| 14790 |
+
"total_flos": 1.5163522786905293e+18,
|
| 14791 |
"train_batch_size": 4,
|
| 14792 |
"trial_name": null,
|
| 14793 |
"trial_params": null
|