Training in progress, step 600, 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:e4da25ad26588702f71a923730862a42c0d5680e9d580614e0808cde10057525
|
| 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 18985850
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79d36e0b5884f0f4b7280b54ffd8a5d055171d9c9ef06beb5e27cbde6da3c52e
|
| 3 |
size 18985850
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14180
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f9ce2d508e1785d8b671beddf3e852c86bd50580b9b5d15913096ec990cfa44
|
| 3 |
size 14180
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 988
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e32b8db4f4cba2b7b0157ab60a064591c3802a9067529d5fddbb1c6c1e99660b
|
| 3 |
size 988
|
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:e1141163e24684fc7c1fea67f6d05c3847e432858727e4ea37982ae30ed01936
|
| 3 |
size 1064
|
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":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -160,6 +160,22 @@
|
|
| 160 |
"eval_samples_per_second": 3.825,
|
| 161 |
"eval_steps_per_second": 0.51,
|
| 162 |
"step": 540
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 163 |
}
|
| 164 |
],
|
| 165 |
"logging_steps": 30,
|
|
@@ -174,12 +190,12 @@
|
|
| 174 |
"should_evaluate": false,
|
| 175 |
"should_log": false,
|
| 176 |
"should_save": true,
|
| 177 |
-
"should_training_stop":
|
| 178 |
},
|
| 179 |
"attributes": {}
|
| 180 |
}
|
| 181 |
},
|
| 182 |
-
"total_flos": 2.
|
| 183 |
"train_batch_size": 12,
|
| 184 |
"trial_name": null,
|
| 185 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.2562277580071175,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 600,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 160 |
"eval_samples_per_second": 3.825,
|
| 161 |
"eval_steps_per_second": 0.51,
|
| 162 |
"step": 540
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 4.04270462633452,
|
| 166 |
+
"eval_loss": 0.576108455657959,
|
| 167 |
+
"eval_runtime": 23.461,
|
| 168 |
+
"eval_samples_per_second": 3.836,
|
| 169 |
+
"eval_steps_per_second": 0.511,
|
| 170 |
+
"step": 570
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.2562277580071175,
|
| 174 |
+
"eval_loss": 0.6141807436943054,
|
| 175 |
+
"eval_runtime": 23.481,
|
| 176 |
+
"eval_samples_per_second": 3.833,
|
| 177 |
+
"eval_steps_per_second": 0.511,
|
| 178 |
+
"step": 600
|
| 179 |
}
|
| 180 |
],
|
| 181 |
"logging_steps": 30,
|
|
|
|
| 190 |
"should_evaluate": false,
|
| 191 |
"should_log": false,
|
| 192 |
"should_save": true,
|
| 193 |
+
"should_training_stop": true
|
| 194 |
},
|
| 195 |
"attributes": {}
|
| 196 |
}
|
| 197 |
},
|
| 198 |
+
"total_flos": 2.3395274867500646e+17,
|
| 199 |
"train_batch_size": 12,
|
| 200 |
"trial_name": null,
|
| 201 |
"trial_params": null
|