Commit
·
3be1b2a
1
Parent(s):
bb5cda1
Training in progress, step 150, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 125248064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:610ecde532f9bcad6391fbf507682990f39596fb5656fe6e87586fd4b964e003
|
| 3 |
size 125248064
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 63350356
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5bd02a6f64df52de2d2f1950bc3869c111c1ef93e3f25d09cfbad559f386f6a
|
| 3 |
size 63350356
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95dc05f6dfab536d3e64ecf5dd424669b694c67a3c5ef2d5784f1d7efa03cff3
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:194456d3c9e165255d5406a0f3f62973b0bede79d91784f72431350783e27ae7
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 1000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -847,13 +847,73 @@
|
|
| 847 |
"learning_rate": 1.3793103448275863e-05,
|
| 848 |
"loss": 1.5653,
|
| 849 |
"step": 140
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 850 |
}
|
| 851 |
],
|
| 852 |
"logging_steps": 1,
|
| 853 |
"max_steps": 150,
|
| 854 |
"num_train_epochs": 1,
|
| 855 |
"save_steps": 10,
|
| 856 |
-
"total_flos": 1.
|
| 857 |
"trial_name": null,
|
| 858 |
"trial_params": null
|
| 859 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.06,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 150,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 847 |
"learning_rate": 1.3793103448275863e-05,
|
| 848 |
"loss": 1.5653,
|
| 849 |
"step": 140
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.06,
|
| 853 |
+
"learning_rate": 1.2413793103448277e-05,
|
| 854 |
+
"loss": 1.4521,
|
| 855 |
+
"step": 141
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.06,
|
| 859 |
+
"learning_rate": 1.103448275862069e-05,
|
| 860 |
+
"loss": 1.4552,
|
| 861 |
+
"step": 142
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.06,
|
| 865 |
+
"learning_rate": 9.655172413793103e-06,
|
| 866 |
+
"loss": 1.3245,
|
| 867 |
+
"step": 143
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.06,
|
| 871 |
+
"learning_rate": 8.275862068965518e-06,
|
| 872 |
+
"loss": 1.4451,
|
| 873 |
+
"step": 144
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.06,
|
| 877 |
+
"learning_rate": 6.896551724137932e-06,
|
| 878 |
+
"loss": 1.363,
|
| 879 |
+
"step": 145
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.06,
|
| 883 |
+
"learning_rate": 5.517241379310345e-06,
|
| 884 |
+
"loss": 1.1145,
|
| 885 |
+
"step": 146
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.06,
|
| 889 |
+
"learning_rate": 4.137931034482759e-06,
|
| 890 |
+
"loss": 1.5004,
|
| 891 |
+
"step": 147
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.06,
|
| 895 |
+
"learning_rate": 2.7586206896551725e-06,
|
| 896 |
+
"loss": 1.5005,
|
| 897 |
+
"step": 148
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.06,
|
| 901 |
+
"learning_rate": 1.3793103448275862e-06,
|
| 902 |
+
"loss": 1.716,
|
| 903 |
+
"step": 149
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.06,
|
| 907 |
+
"learning_rate": 0.0,
|
| 908 |
+
"loss": 1.3766,
|
| 909 |
+
"step": 150
|
| 910 |
}
|
| 911 |
],
|
| 912 |
"logging_steps": 1,
|
| 913 |
"max_steps": 150,
|
| 914 |
"num_train_epochs": 1,
|
| 915 |
"save_steps": 10,
|
| 916 |
+
"total_flos": 1.863422467497984e+16,
|
| 917 |
"trial_name": null,
|
| 918 |
"trial_params": null
|
| 919 |
}
|