Training in progress, step 186, 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:cf7e5b155e0850c6ef6bc98fede8d990cff0ed6c72331266143580cbb3961e05
|
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:a7027561acdc8b4cf444aa79fcc7c4df8ee069146bdea22b35104ac62642c3cb
|
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 sha256:5c082f94a9ebf4712fc250e853f68dd7792092950372e373b7728b373d103ea1
|
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,
|
@@ -1302,6 +1302,13 @@
|
|
1302 |
"learning_rate": 0.0001356060606060606,
|
1303 |
"loss": 1.2178,
|
1304 |
"step": 185
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1305 |
}
|
1306 |
],
|
1307 |
"logging_steps": 1,
|
@@ -1321,7 +1328,7 @@
|
|
1321 |
"attributes": {}
|
1322 |
}
|
1323 |
},
|
1324 |
-
"total_flos": 2.
|
1325 |
"train_batch_size": 4,
|
1326 |
"trial_name": null,
|
1327 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5102880658436214,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 186,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1302 |
"learning_rate": 0.0001356060606060606,
|
1303 |
"loss": 1.2178,
|
1304 |
"step": 185
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.5102880658436214,
|
1308 |
+
"grad_norm": 0.1525765359401703,
|
1309 |
+
"learning_rate": 0.00013484848484848484,
|
1310 |
+
"loss": 1.2798,
|
1311 |
+
"step": 186
|
1312 |
}
|
1313 |
],
|
1314 |
"logging_steps": 1,
|
|
|
1328 |
"attributes": {}
|
1329 |
}
|
1330 |
},
|
1331 |
+
"total_flos": 2.30779152127488e+17,
|
1332 |
"train_batch_size": 4,
|
1333 |
"trial_name": null,
|
1334 |
"trial_params": null
|