Training in progress, step 8190, 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 sha256:9c859c4299d39e2c94916eb6600339852d5fe28d8fe4775415155ff1d859d305
|
| 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:dd49d3dca014cdc22d126d7915c4bf1af7c5411460e7dd6fd71e6a9fe68248c3
|
| 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:a9c39192c014c2873a01f54fc5b43c8871327dfd78c542c62436cf9303f73e09
|
| 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":
|
| 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,
|
|
@@ -14732,6 +14732,24 @@
|
|
| 14732 |
"mean_token_accuracy": 0.6511748641729355,
|
| 14733 |
"num_tokens": 29832138.0,
|
| 14734 |
"step": 8180
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14735 |
}
|
| 14736 |
],
|
| 14737 |
"logging_steps": 5,
|
|
@@ -14751,7 +14769,7 @@
|
|
| 14751 |
"attributes": {}
|
| 14752 |
}
|
| 14753 |
},
|
| 14754 |
-
"total_flos": 1.
|
| 14755 |
"train_batch_size": 4,
|
| 14756 |
"trial_name": null,
|
| 14757 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 63.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8190,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14732 |
"mean_token_accuracy": 0.6511748641729355,
|
| 14733 |
"num_tokens": 29832138.0,
|
| 14734 |
"step": 8180
|
| 14735 |
+
},
|
| 14736 |
+
{
|
| 14737 |
+
"epoch": 62.96153846153846,
|
| 14738 |
+
"grad_norm": 0.0,
|
| 14739 |
+
"learning_rate": 9.080000000000001e-06,
|
| 14740 |
+
"loss": 1.7322,
|
| 14741 |
+
"mean_token_accuracy": 0.6481782138347626,
|
| 14742 |
+
"num_tokens": 29850755.0,
|
| 14743 |
+
"step": 8185
|
| 14744 |
+
},
|
| 14745 |
+
{
|
| 14746 |
+
"epoch": 63.0,
|
| 14747 |
+
"grad_norm": 0.0,
|
| 14748 |
+
"learning_rate": 9.055e-06,
|
| 14749 |
+
"loss": 1.7469,
|
| 14750 |
+
"mean_token_accuracy": 0.6486757427453995,
|
| 14751 |
+
"num_tokens": 29868615.0,
|
| 14752 |
+
"step": 8190
|
| 14753 |
}
|
| 14754 |
],
|
| 14755 |
"logging_steps": 5,
|
|
|
|
| 14769 |
"attributes": {}
|
| 14770 |
}
|
| 14771 |
},
|
| 14772 |
+
"total_flos": 1.514446135039918e+18,
|
| 14773 |
"train_batch_size": 4,
|
| 14774 |
"trial_name": null,
|
| 14775 |
"trial_params": null
|