Training in progress, step 141, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:779ee363e5fd712c8b1a82255171124b2e49120464e332119ae1d10c386892e8
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3db42eeae9862399c0d444848d9d347eb13a40c902620af219e40d549d3932d6
|
3 |
size 37430836
|
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:c58331b2f38390b4abcc6e7b98c07985bebcd0965fe6c2ab664d957c7fa3672d
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -973,6 +973,27 @@
|
|
973 |
"learning_rate": 0.00017121212121212122,
|
974 |
"loss": 1.2717,
|
975 |
"step": 138
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
976 |
}
|
977 |
],
|
978 |
"logging_steps": 1,
|
@@ -992,7 +1013,7 @@
|
|
992 |
"attributes": {}
|
993 |
}
|
994 |
},
|
995 |
-
"total_flos": 1.
|
996 |
"train_batch_size": 4,
|
997 |
"trial_name": null,
|
998 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3868312757201646,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 141,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
973 |
"learning_rate": 0.00017121212121212122,
|
974 |
"loss": 1.2717,
|
975 |
"step": 138
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.3813443072702332,
|
979 |
+
"grad_norm": 0.13014937937259674,
|
980 |
+
"learning_rate": 0.00017045454545454547,
|
981 |
+
"loss": 1.2604,
|
982 |
+
"step": 139
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.3840877914951989,
|
986 |
+
"grad_norm": 0.16863836348056793,
|
987 |
+
"learning_rate": 0.00016969696969696972,
|
988 |
+
"loss": 1.2479,
|
989 |
+
"step": 140
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.3868312757201646,
|
993 |
+
"grad_norm": 0.1496235728263855,
|
994 |
+
"learning_rate": 0.00016893939393939394,
|
995 |
+
"loss": 1.1911,
|
996 |
+
"step": 141
|
997 |
}
|
998 |
],
|
999 |
"logging_steps": 1,
|
|
|
1013 |
"attributes": {}
|
1014 |
}
|
1015 |
},
|
1016 |
+
"total_flos": 1.749825897565102e+17,
|
1017 |
"train_batch_size": 4,
|
1018 |
"trial_name": null,
|
1019 |
"trial_params": null
|