Training in progress, step 192, 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 35237104
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c82a800c179ba423aec97639d9ccc384481b0ce2554f370d1b33c0d7e72ade4e
|
3 |
size 35237104
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18810036
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85e5bdecfd8d470dcdb63d2257591509be80d9a8efbb2ae893e9f5faabe91b36
|
3 |
size 18810036
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2be38675289fa52218b04199b6f2593e112267ecbf7ee0bb9a6c1998df0f09e7
|
3 |
size 14244
|
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 sha256:430952bd40ab71b9a96e33c9bed5a81b004c335aa948503b4d61063a45bfb5c2
|
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":
|
5 |
"eval_steps": 3,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1842,6 +1842,35 @@
|
|
1842 |
"eval_samples_per_second": 4.99,
|
1843 |
"eval_steps_per_second": 2.994,
|
1844 |
"step": 189
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1845 |
}
|
1846 |
],
|
1847 |
"logging_steps": 1,
|
@@ -1861,7 +1890,7 @@
|
|
1861 |
"attributes": {}
|
1862 |
}
|
1863 |
},
|
1864 |
-
"total_flos": 1.
|
1865 |
"train_batch_size": 2,
|
1866 |
"trial_name": null,
|
1867 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 16.0,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 192,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1842 |
"eval_samples_per_second": 4.99,
|
1843 |
"eval_steps_per_second": 2.994,
|
1844 |
"step": 189
|
1845 |
+
},
|
1846 |
+
{
|
1847 |
+
"epoch": 15.833333333333334,
|
1848 |
+
"grad_norm": 0.0013418430462479591,
|
1849 |
+
"learning_rate": 0.000195051270234986,
|
1850 |
+
"loss": 0.0001,
|
1851 |
+
"step": 190
|
1852 |
+
},
|
1853 |
+
{
|
1854 |
+
"epoch": 15.916666666666666,
|
1855 |
+
"grad_norm": 0.0016558875795453787,
|
1856 |
+
"learning_rate": 0.00019499659605365404,
|
1857 |
+
"loss": 0.0001,
|
1858 |
+
"step": 191
|
1859 |
+
},
|
1860 |
+
{
|
1861 |
+
"epoch": 16.0,
|
1862 |
+
"grad_norm": 0.0026047020219266415,
|
1863 |
+
"learning_rate": 0.0001949416292539326,
|
1864 |
+
"loss": 0.0001,
|
1865 |
+
"step": 192
|
1866 |
+
},
|
1867 |
+
{
|
1868 |
+
"epoch": 16.0,
|
1869 |
+
"eval_loss": 1.3221460580825806,
|
1870 |
+
"eval_runtime": 1.0043,
|
1871 |
+
"eval_samples_per_second": 4.979,
|
1872 |
+
"eval_steps_per_second": 2.987,
|
1873 |
+
"step": 192
|
1874 |
}
|
1875 |
],
|
1876 |
"logging_steps": 1,
|
|
|
1890 |
"attributes": {}
|
1891 |
}
|
1892 |
},
|
1893 |
+
"total_flos": 1.36981317156864e+16,
|
1894 |
"train_batch_size": 2,
|
1895 |
"trial_name": null,
|
1896 |
"trial_params": null
|