Training in progress, step 170, 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 sha256:44626cc94e4ae4ef2189f492ec6a02f6a9cf34d81e54c3c0d3c5d06f2b5db83b
|
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 sha256:20b50b88935790b9e8a1ab3ebd399aafd75c99d1e6cae3998824e30f7299dfba
|
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:dd41ad516c648e6a91e8eb789b6ec82ae8142cda642d8cd2955159250148cb8d
|
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,
|
@@ -1176,6 +1176,27 @@
|
|
1176 |
"learning_rate": 0.00014924242424242426,
|
1177 |
"loss": 1.2322,
|
1178 |
"step": 167
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1179 |
}
|
1180 |
],
|
1181 |
"logging_steps": 1,
|
@@ -1195,7 +1216,7 @@
|
|
1195 |
"attributes": {}
|
1196 |
}
|
1197 |
},
|
1198 |
-
"total_flos": 2.
|
1199 |
"train_batch_size": 4,
|
1200 |
"trial_name": null,
|
1201 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4663923182441701,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 170,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1176 |
"learning_rate": 0.00014924242424242426,
|
1177 |
"loss": 1.2322,
|
1178 |
"step": 167
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.4609053497942387,
|
1182 |
+
"grad_norm": 0.1470465362071991,
|
1183 |
+
"learning_rate": 0.00014848484848484849,
|
1184 |
+
"loss": 1.241,
|
1185 |
+
"step": 168
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.46364883401920437,
|
1189 |
+
"grad_norm": 0.14876408874988556,
|
1190 |
+
"learning_rate": 0.00014772727272727274,
|
1191 |
+
"loss": 1.2268,
|
1192 |
+
"step": 169
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 0.4663923182441701,
|
1196 |
+
"grad_norm": 0.14918828010559082,
|
1197 |
+
"learning_rate": 0.00014696969696969698,
|
1198 |
+
"loss": 1.3067,
|
1199 |
+
"step": 170
|
1200 |
}
|
1201 |
],
|
1202 |
"logging_steps": 1,
|
|
|
1216 |
"attributes": {}
|
1217 |
}
|
1218 |
},
|
1219 |
+
"total_flos": 2.109386405851054e+17,
|
1220 |
"train_batch_size": 4,
|
1221 |
"trial_name": null,
|
1222 |
"trial_params": null
|