Training in progress, step 60, 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 180385008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6db9d552d05fd4a02441b274102b06eb4448e823b6f11bbf626b7b2d36ec4589
|
| 3 |
size 180385008
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 91850763
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a79c6a13851c6b6000b1c5fa96cc061a579e0f7b0b01508685b720f653fc9625
|
| 3 |
size 91850763
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:637ef4c9ad794a6c6701f55f48eb4bd08385ff6ecc860fcf54937e38e8bf02e2
|
| 3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c146ae1cf47c9929c1f0cc98e903ce1070f0c3ea64421f26971b053d42844b7
|
| 3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22ae51817158590b7adfad82fb9a3380e5197063501e610f9eaa5c6decb93fd2
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 5,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -173,6 +173,21 @@
|
|
| 173 |
"eval_samples_per_second": 36.927,
|
| 174 |
"eval_steps_per_second": 9.232,
|
| 175 |
"step": 55
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 176 |
}
|
| 177 |
],
|
| 178 |
"logging_steps": 5,
|
|
@@ -187,12 +202,12 @@
|
|
| 187 |
"should_evaluate": false,
|
| 188 |
"should_log": false,
|
| 189 |
"should_save": true,
|
| 190 |
-
"should_training_stop":
|
| 191 |
},
|
| 192 |
"attributes": {}
|
| 193 |
}
|
| 194 |
},
|
| 195 |
-
"total_flos":
|
| 196 |
"train_batch_size": 2,
|
| 197 |
"trial_name": null,
|
| 198 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.4225352112676056,
|
| 6 |
"eval_steps": 5,
|
| 7 |
+
"global_step": 60,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 173 |
"eval_samples_per_second": 36.927,
|
| 174 |
"eval_steps_per_second": 9.232,
|
| 175 |
"step": 55
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.4225352112676056,
|
| 179 |
+
"grad_norm": 0.31429925560951233,
|
| 180 |
+
"learning_rate": 3.636363636363636e-06,
|
| 181 |
+
"loss": 3.8459,
|
| 182 |
+
"step": 60
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.4225352112676056,
|
| 186 |
+
"eval_loss": 5.81058406829834,
|
| 187 |
+
"eval_runtime": 1.5942,
|
| 188 |
+
"eval_samples_per_second": 37.636,
|
| 189 |
+
"eval_steps_per_second": 9.409,
|
| 190 |
+
"step": 60
|
| 191 |
}
|
| 192 |
],
|
| 193 |
"logging_steps": 5,
|
|
|
|
| 202 |
"should_evaluate": false,
|
| 203 |
"should_log": false,
|
| 204 |
"should_save": true,
|
| 205 |
+
"should_training_stop": true
|
| 206 |
},
|
| 207 |
"attributes": {}
|
| 208 |
}
|
| 209 |
},
|
| 210 |
+
"total_flos": 1267677987962880.0,
|
| 211 |
"train_batch_size": 2,
|
| 212 |
"trial_name": null,
|
| 213 |
"trial_params": null
|