Training in progress, step 4930, 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 sha256:3964b9bfccb10ab7fdf7424d116118d1afc2fc23d22054a900a0f9500d289a63
|
| 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 sha256:9649ce17c266d1cf95c23617bc414bdd22d51b45c0c2d5783949129f1e1eabd7
|
| 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 sha256:0518824f8716ed471e232b93b7eadcf4d3109b70371c61cf1a049e50524719f0
|
| 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": 37.
|
| 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,
|
|
@@ -8864,6 +8864,24 @@
|
|
| 8864 |
"mean_token_accuracy": 0.6498663574457169,
|
| 8865 |
"num_tokens": 17942295.0,
|
| 8866 |
"step": 4920
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8867 |
}
|
| 8868 |
],
|
| 8869 |
"logging_steps": 5,
|
|
@@ -8883,7 +8901,7 @@
|
|
| 8883 |
"attributes": {}
|
| 8884 |
}
|
| 8885 |
},
|
| 8886 |
-
"total_flos": 9.
|
| 8887 |
"train_batch_size": 4,
|
| 8888 |
"trial_name": null,
|
| 8889 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 37.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4930,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8864 |
"mean_token_accuracy": 0.6498663574457169,
|
| 8865 |
"num_tokens": 17942295.0,
|
| 8866 |
"step": 4920
|
| 8867 |
+
},
|
| 8868 |
+
{
|
| 8869 |
+
"epoch": 37.88461538461539,
|
| 8870 |
+
"grad_norm": 0.0,
|
| 8871 |
+
"learning_rate": 2.5380000000000004e-05,
|
| 8872 |
+
"loss": 1.7363,
|
| 8873 |
+
"mean_token_accuracy": 0.6530733823776245,
|
| 8874 |
+
"num_tokens": 17960859.0,
|
| 8875 |
+
"step": 4925
|
| 8876 |
+
},
|
| 8877 |
+
{
|
| 8878 |
+
"epoch": 37.92307692307692,
|
| 8879 |
+
"grad_norm": 0.0,
|
| 8880 |
+
"learning_rate": 2.5355e-05,
|
| 8881 |
+
"loss": 1.6919,
|
| 8882 |
+
"mean_token_accuracy": 0.6597955763339997,
|
| 8883 |
+
"num_tokens": 17979359.0,
|
| 8884 |
+
"step": 4930
|
| 8885 |
}
|
| 8886 |
],
|
| 8887 |
"logging_steps": 5,
|
|
|
|
| 8901 |
"attributes": {}
|
| 8902 |
}
|
| 8903 |
},
|
| 8904 |
+
"total_flos": 9.110915717146214e+17,
|
| 8905 |
"train_batch_size": 4,
|
| 8906 |
"trial_name": null,
|
| 8907 |
"trial_params": null
|