Training in progress, step 148, 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 sha256:5d16cb8f4bed08fd628207173db66355f1e812b871f6956eae13bd1245ef5c3b
|
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 sha256:53b4fe519471959df0aba0a3bd6eadac09ae19fefb99fcf4ba5f4ae474ac553c
|
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 sha256:4ad64c78d074a87bea69d73e2decce640f1cd08d5a6225ce9ec43c8ebb938728
|
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,
|
@@ -1036,6 +1036,13 @@
|
|
1036 |
"learning_rate": 0.0001643939393939394,
|
1037 |
"loss": 1.2108,
|
1038 |
"step": 147
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1039 |
}
|
1040 |
],
|
1041 |
"logging_steps": 1,
|
@@ -1055,7 +1062,7 @@
|
|
1055 |
"attributes": {}
|
1056 |
}
|
1057 |
},
|
1058 |
-
"total_flos": 1.
|
1059 |
"train_batch_size": 4,
|
1060 |
"trial_name": null,
|
1061 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4060356652949246,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 148,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1036 |
"learning_rate": 0.0001643939393939394,
|
1037 |
"loss": 1.2108,
|
1038 |
"step": 147
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.4060356652949246,
|
1042 |
+
"grad_norm": 0.14629404246807098,
|
1043 |
+
"learning_rate": 0.00016363636363636366,
|
1044 |
+
"loss": 1.2176,
|
1045 |
+
"step": 148
|
1046 |
}
|
1047 |
],
|
1048 |
"logging_steps": 1,
|
|
|
1062 |
"attributes": {}
|
1063 |
}
|
1064 |
},
|
1065 |
+
"total_flos": 1.834377402632356e+17,
|
1066 |
"train_batch_size": 4,
|
1067 |
"trial_name": null,
|
1068 |
"trial_params": null
|