Training in progress, step 3270, 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:b15189b092e4cf5f01133bc78d873c1aca72e394a9470756d399f0b7b09efe93
|
| 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:e69b1b4acb28dd01df6f1732efd8c13023eb0c21fa8dbf397efde6b357fd0175
|
| 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 sha256:218a6dc177a73a93475fcb2249ba0b1cfb84f502d4b8ee9ab5e2d3becb359b82
|
| 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": 25.
|
| 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,
|
|
@@ -5876,6 +5876,24 @@
|
|
| 5876 |
"mean_token_accuracy": 0.6480823725461959,
|
| 5877 |
"num_tokens": 11888806.0,
|
| 5878 |
"step": 3260
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5879 |
}
|
| 5880 |
],
|
| 5881 |
"logging_steps": 5,
|
|
@@ -5895,7 +5913,7 @@
|
|
| 5895 |
"attributes": {}
|
| 5896 |
}
|
| 5897 |
},
|
| 5898 |
-
"total_flos": 6.
|
| 5899 |
"train_batch_size": 4,
|
| 5900 |
"trial_name": null,
|
| 5901 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 25.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3270,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5876 |
"mean_token_accuracy": 0.6480823725461959,
|
| 5877 |
"num_tokens": 11888806.0,
|
| 5878 |
"step": 3260
|
| 5879 |
+
},
|
| 5880 |
+
{
|
| 5881 |
+
"epoch": 25.115384615384617,
|
| 5882 |
+
"grad_norm": 0.0,
|
| 5883 |
+
"learning_rate": 3.368e-05,
|
| 5884 |
+
"loss": 1.7296,
|
| 5885 |
+
"mean_token_accuracy": 0.6544734388589859,
|
| 5886 |
+
"num_tokens": 11907007.0,
|
| 5887 |
+
"step": 3265
|
| 5888 |
+
},
|
| 5889 |
+
{
|
| 5890 |
+
"epoch": 25.153846153846153,
|
| 5891 |
+
"grad_norm": 0.0,
|
| 5892 |
+
"learning_rate": 3.3655e-05,
|
| 5893 |
+
"loss": 1.7,
|
| 5894 |
+
"mean_token_accuracy": 0.661970067024231,
|
| 5895 |
+
"num_tokens": 11925855.0,
|
| 5896 |
+
"step": 3270
|
| 5897 |
}
|
| 5898 |
],
|
| 5899 |
"logging_steps": 5,
|
|
|
|
| 5913 |
"attributes": {}
|
| 5914 |
}
|
| 5915 |
},
|
| 5916 |
+
"total_flos": 6.042775465023898e+17,
|
| 5917 |
"train_batch_size": 4,
|
| 5918 |
"trial_name": null,
|
| 5919 |
"trial_params": null
|