Training in progress, step 13900, 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 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6e850270b5aa16a087f2ed7bfa63681dceca1195815b909f64ab1cf952f1d36
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d80443b06a6c12911f010a5102842a6b449c2c4d84eccce4684c05a191a2fef5
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d78a57832ad3a62d561461213246d0e5485177f398b4ea4f4bb31c91c7f18f2
|
| 3 |
size 15006
|
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 sha256:71b44bd9c64de4d93ae129aeb4daad40847d4d504a7f4f16e6041b0da96102d3
|
| 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": 27.
|
| 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,
|
|
@@ -1189,6 +1189,13 @@
|
|
| 1189 |
"learning_rate": 8.000000000000001e-06,
|
| 1190 |
"loss": 1.2223,
|
| 1191 |
"step": 13800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1192 |
}
|
| 1193 |
],
|
| 1194 |
"logging_steps": 100,
|
|
@@ -1208,7 +1215,7 @@
|
|
| 1208 |
"attributes": {}
|
| 1209 |
}
|
| 1210 |
},
|
| 1211 |
-
"total_flos": 2.
|
| 1212 |
"train_batch_size": 8,
|
| 1213 |
"trial_name": null,
|
| 1214 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 27.795656928604906,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 13900,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1189 |
"learning_rate": 8.000000000000001e-06,
|
| 1190 |
"loss": 1.2223,
|
| 1191 |
"step": 13800
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 27.795656928604906,
|
| 1195 |
+
"grad_norm": 0.24099507927894592,
|
| 1196 |
+
"learning_rate": 7.333333333333334e-06,
|
| 1197 |
+
"loss": 1.2157,
|
| 1198 |
+
"step": 13900
|
| 1199 |
}
|
| 1200 |
],
|
| 1201 |
"logging_steps": 100,
|
|
|
|
| 1215 |
"attributes": {}
|
| 1216 |
}
|
| 1217 |
},
|
| 1218 |
+
"total_flos": 2.169417375965774e+19,
|
| 1219 |
"train_batch_size": 8,
|
| 1220 |
"trial_name": null,
|
| 1221 |
"trial_params": null
|