Training in progress, step 154, 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:a92612efd32cc8c7cd804c39dfe1ee7c88566ecf85f1f8537d1b7f6f9ec2914e
|
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:d5be8f4b9fd897bfa797bbd612cb2fb9024c4da95ca4c841544dd2529fa02ee5
|
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:a8cfd8fe344770260602a7559457d997a6902b69f0c2bbc077a2789412c5865e
|
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,
|
@@ -1078,6 +1078,13 @@
|
|
1078 |
"learning_rate": 0.00015984848484848485,
|
1079 |
"loss": 1.2641,
|
1080 |
"step": 153
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1081 |
}
|
1082 |
],
|
1083 |
"logging_steps": 1,
|
@@ -1097,7 +1104,7 @@
|
|
1097 |
"attributes": {}
|
1098 |
}
|
1099 |
},
|
1100 |
-
"total_flos": 1.
|
1101 |
"train_batch_size": 4,
|
1102 |
"trial_name": null,
|
1103 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4224965706447188,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 154,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1078 |
"learning_rate": 0.00015984848484848485,
|
1079 |
"loss": 1.2641,
|
1080 |
"step": 153
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.4224965706447188,
|
1084 |
+
"grad_norm": 0.1794748306274414,
|
1085 |
+
"learning_rate": 0.0001590909090909091,
|
1086 |
+
"loss": 1.1754,
|
1087 |
+
"step": 154
|
1088 |
}
|
1089 |
],
|
1090 |
"logging_steps": 1,
|
|
|
1104 |
"attributes": {}
|
1105 |
}
|
1106 |
},
|
1107 |
+
"total_flos": 1.9074986308912742e+17,
|
1108 |
"train_batch_size": 4,
|
1109 |
"trial_name": null,
|
1110 |
"trial_params": null
|