Training in progress, step 9350, 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:a9965ae77fea5653bd47589978617e24f9f693c5328e0848eb3d312f3f7605b7
|
| 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 sha256:0f5bcdfec5ece7d36c1809a830b4b8f28d2eee13ae35867dd020d92b398dc5bd
|
| 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 sha256:8ed7c1226b131b77468a614ce229090fc0b67ba92b22d753498c298aebde8fc8
|
| 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": 71.
|
| 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,
|
|
@@ -16820,6 +16820,24 @@
|
|
| 16820 |
"mean_token_accuracy": 0.6412538975477219,
|
| 16821 |
"num_tokens": 34063747.0,
|
| 16822 |
"step": 9340
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16823 |
}
|
| 16824 |
],
|
| 16825 |
"logging_steps": 5,
|
|
@@ -16839,7 +16857,7 @@
|
|
| 16839 |
"attributes": {}
|
| 16840 |
}
|
| 16841 |
},
|
| 16842 |
-
"total_flos": 1.
|
| 16843 |
"train_batch_size": 4,
|
| 16844 |
"trial_name": null,
|
| 16845 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 71.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9350,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16820 |
"mean_token_accuracy": 0.6412538975477219,
|
| 16821 |
"num_tokens": 34063747.0,
|
| 16822 |
"step": 9340
|
| 16823 |
+
},
|
| 16824 |
+
{
|
| 16825 |
+
"epoch": 71.88461538461539,
|
| 16826 |
+
"grad_norm": 0.0,
|
| 16827 |
+
"learning_rate": 3.2800000000000004e-06,
|
| 16828 |
+
"loss": 1.8211,
|
| 16829 |
+
"mean_token_accuracy": 0.6337336391210556,
|
| 16830 |
+
"num_tokens": 34080973.0,
|
| 16831 |
+
"step": 9345
|
| 16832 |
+
},
|
| 16833 |
+
{
|
| 16834 |
+
"epoch": 71.92307692307692,
|
| 16835 |
+
"grad_norm": 0.0,
|
| 16836 |
+
"learning_rate": 3.2550000000000006e-06,
|
| 16837 |
+
"loss": 1.7922,
|
| 16838 |
+
"mean_token_accuracy": 0.6401098728179931,
|
| 16839 |
+
"num_tokens": 34099093.0,
|
| 16840 |
+
"step": 9350
|
| 16841 |
}
|
| 16842 |
],
|
| 16843 |
"logging_steps": 5,
|
|
|
|
| 16857 |
"attributes": {}
|
| 16858 |
}
|
| 16859 |
},
|
| 16860 |
+
"total_flos": 1.729112206394327e+18,
|
| 16861 |
"train_batch_size": 4,
|
| 16862 |
"trial_name": null,
|
| 16863 |
"trial_params": null
|