Training in progress, step 157, 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:d56863d92e6312f5d6f1c1814f481c8b74b6c664c5ba3e0684d724472562ea93
|
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:f52ddc74127e1408ce4015cddd648ece7765f3ddead8a01cc82e8134ec806897
|
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 sha256:3b1a7fb065f918e70ad49296784a50e6d7ae39b65540698da47dbeaca28451cb
|
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,
|
@@ -1085,6 +1085,27 @@
|
|
1085 |
"learning_rate": 0.0001590909090909091,
|
1086 |
"loss": 1.1754,
|
1087 |
"step": 154
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1088 |
}
|
1089 |
],
|
1090 |
"logging_steps": 1,
|
@@ -1104,7 +1125,7 @@
|
|
1104 |
"attributes": {}
|
1105 |
}
|
1106 |
},
|
1107 |
-
"total_flos": 1.
|
1108 |
"train_batch_size": 4,
|
1109 |
"trial_name": null,
|
1110 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.43072702331961593,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 157,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1085 |
"learning_rate": 0.0001590909090909091,
|
1086 |
"loss": 1.1754,
|
1087 |
"step": 154
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.4252400548696845,
|
1091 |
+
"grad_norm": 0.13613805174827576,
|
1092 |
+
"learning_rate": 0.00015833333333333332,
|
1093 |
+
"loss": 1.2114,
|
1094 |
+
"step": 155
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.4279835390946502,
|
1098 |
+
"grad_norm": 0.1772301197052002,
|
1099 |
+
"learning_rate": 0.00015757575757575757,
|
1100 |
+
"loss": 1.2146,
|
1101 |
+
"step": 156
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.43072702331961593,
|
1105 |
+
"grad_norm": 0.18257774412631989,
|
1106 |
+
"learning_rate": 0.00015681818181818182,
|
1107 |
+
"loss": 1.2129,
|
1108 |
+
"step": 157
|
1109 |
}
|
1110 |
],
|
1111 |
"logging_steps": 1,
|
|
|
1125 |
"attributes": {}
|
1126 |
}
|
1127 |
},
|
1128 |
+
"total_flos": 1.9448090909752934e+17,
|
1129 |
"train_batch_size": 4,
|
1130 |
"trial_name": null,
|
1131 |
"trial_params": null
|