Training in progress, step 13700, 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 sha256:949c052efccb677d944a44f554d2032c7dda284a661479ccbb5d83692ce71074
|
| 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 sha256:3749e1dd7c4a52ad659b7d2f64051eb0510a4b41e28d3448f3737f878597bfc5
|
| 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 sha256:68bf9038540cc43f883cd94719ef73c44bebb038f3dc0b49a52a0cd1e4cdf493
|
| 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 sha256:982fbf22aca45cea75398c35241931d6647921d198c0aa080d8e1c74075e806e
|
| 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,
|
|
@@ -1175,6 +1175,13 @@
|
|
| 1175 |
"learning_rate": 9.333333333333334e-06,
|
| 1176 |
"loss": 1.2217,
|
| 1177 |
"step": 13600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1178 |
}
|
| 1179 |
],
|
| 1180 |
"logging_steps": 100,
|
|
@@ -1194,7 +1201,7 @@
|
|
| 1194 |
"attributes": {}
|
| 1195 |
}
|
| 1196 |
},
|
| 1197 |
-
"total_flos": 2.
|
| 1198 |
"train_batch_size": 8,
|
| 1199 |
"trial_name": null,
|
| 1200 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 27.395719418840805,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 13700,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1175 |
"learning_rate": 9.333333333333334e-06,
|
| 1176 |
"loss": 1.2217,
|
| 1177 |
"step": 13600
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 27.395719418840805,
|
| 1181 |
+
"grad_norm": 0.25391411781311035,
|
| 1182 |
+
"learning_rate": 8.666666666666668e-06,
|
| 1183 |
+
"loss": 1.2178,
|
| 1184 |
+
"step": 13700
|
| 1185 |
}
|
| 1186 |
],
|
| 1187 |
"logging_steps": 100,
|
|
|
|
| 1201 |
"attributes": {}
|
| 1202 |
}
|
| 1203 |
},
|
| 1204 |
+
"total_flos": 2.1382023817281405e+19,
|
| 1205 |
"train_batch_size": 8,
|
| 1206 |
"trial_name": null,
|
| 1207 |
"trial_params": null
|