Training in progress, step 3810, 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 sha256:7a93e5c7ca6dd75adc23c9d8b3a0a36ebeeb8733c7ec95518f098f2021d5499e
|
| 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 sha256:58b83b1ff06e2a80284eb8c81200225d4424ca3cb1d01ccdce0bac14d7cf0780
|
| 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 sha256:0666535a9ce5d905c908a33472893a88421770e705c9ad8d469ddc1f8bf0d6be
|
| 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": 29.
|
| 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,
|
|
@@ -6848,6 +6848,24 @@
|
|
| 6848 |
"mean_token_accuracy": 0.6543154448270798,
|
| 6849 |
"num_tokens": 13859478.0,
|
| 6850 |
"step": 3800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6851 |
}
|
| 6852 |
],
|
| 6853 |
"logging_steps": 5,
|
|
@@ -6867,7 +6885,7 @@
|
|
| 6867 |
"attributes": {}
|
| 6868 |
}
|
| 6869 |
},
|
| 6870 |
-
"total_flos": 7.
|
| 6871 |
"train_batch_size": 4,
|
| 6872 |
"trial_name": null,
|
| 6873 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 29.307692307692307,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3810,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6848 |
"mean_token_accuracy": 0.6543154448270798,
|
| 6849 |
"num_tokens": 13859478.0,
|
| 6850 |
"step": 3800
|
| 6851 |
+
},
|
| 6852 |
+
{
|
| 6853 |
+
"epoch": 29.26923076923077,
|
| 6854 |
+
"grad_norm": 0.0,
|
| 6855 |
+
"learning_rate": 3.0980000000000005e-05,
|
| 6856 |
+
"loss": 1.743,
|
| 6857 |
+
"mean_token_accuracy": 0.6480233430862427,
|
| 6858 |
+
"num_tokens": 13877895.0,
|
| 6859 |
+
"step": 3805
|
| 6860 |
+
},
|
| 6861 |
+
{
|
| 6862 |
+
"epoch": 29.307692307692307,
|
| 6863 |
+
"grad_norm": 0.0,
|
| 6864 |
+
"learning_rate": 3.0955e-05,
|
| 6865 |
+
"loss": 1.6918,
|
| 6866 |
+
"mean_token_accuracy": 0.6589089602231979,
|
| 6867 |
+
"num_tokens": 13896941.0,
|
| 6868 |
+
"step": 3810
|
| 6869 |
}
|
| 6870 |
],
|
| 6871 |
"logging_steps": 5,
|
|
|
|
| 6885 |
"attributes": {}
|
| 6886 |
}
|
| 6887 |
},
|
| 6888 |
+
"total_flos": 7.042528359324058e+17,
|
| 6889 |
"train_batch_size": 4,
|
| 6890 |
"trial_name": null,
|
| 6891 |
"trial_params": null
|