Training in progress, step 167, 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 sha256:12355246a19b98e3ce1f8ac5e57d0c4b61e2dc9481e98a368483014b50499091
|
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:f1bce8a87d4487118db80c16b6d68d86472d6befa24d272222ac62a6bd5f0d06
|
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:f7ef6c636cf5f49456f343b5549d02a90b09eabe3c4750c8ce10917fcdc2c75c
|
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,
|
@@ -1169,6 +1169,13 @@
|
|
1169 |
"learning_rate": 0.00015000000000000001,
|
1170 |
"loss": 1.2576,
|
1171 |
"step": 166
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1172 |
}
|
1173 |
],
|
1174 |
"logging_steps": 1,
|
@@ -1188,7 +1195,7 @@
|
|
1188 |
"attributes": {}
|
1189 |
}
|
1190 |
},
|
1191 |
-
"total_flos": 2.
|
1192 |
"train_batch_size": 4,
|
1193 |
"trial_name": null,
|
1194 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.45816186556927296,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 167,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1169 |
"learning_rate": 0.00015000000000000001,
|
1170 |
"loss": 1.2576,
|
1171 |
"step": 166
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.45816186556927296,
|
1175 |
+
"grad_norm": 0.14680561423301697,
|
1176 |
+
"learning_rate": 0.00014924242424242426,
|
1177 |
+
"loss": 1.2322,
|
1178 |
+
"step": 167
|
1179 |
}
|
1180 |
],
|
1181 |
"logging_steps": 1,
|
|
|
1195 |
"attributes": {}
|
1196 |
}
|
1197 |
},
|
1198 |
+
"total_flos": 2.071106769870766e+17,
|
1199 |
"train_batch_size": 4,
|
1200 |
"trial_name": null,
|
1201 |
"trial_params": null
|