Training in progress, step 1840, 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 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e6cd8094f1a9b275409b5e29dac6e5547d58a69f4c0e092f1df2f9b50f2114f
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f024aacb386f38059a5d0449e8f47d95088bc37603ee6b9a9629e282bc9fce2b
|
| 3 |
size 141058579
|
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 sha256:660d66769a25b90f8566fd916c316b9b0e244ffce7b25945b65ffcad1af3e768
|
| 3 |
size 14645
|
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:e44eaba2f1ebd92046727db70164f55edfc1880cb2e3a6c0bc0862f469502aa6
|
| 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": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1848,6 +1848,16 @@
|
|
| 1848 |
"mean_token_accuracy": 0.7705774419009686,
|
| 1849 |
"num_tokens": 8486476.0,
|
| 1850 |
"step": 1830
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1851 |
}
|
| 1852 |
],
|
| 1853 |
"logging_steps": 10,
|
|
@@ -1867,7 +1877,7 @@
|
|
| 1867 |
"attributes": {}
|
| 1868 |
}
|
| 1869 |
},
|
| 1870 |
-
"total_flos": 4.
|
| 1871 |
"train_batch_size": 4,
|
| 1872 |
"trial_name": null,
|
| 1873 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.39253333333333335,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1840,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1848 |
"mean_token_accuracy": 0.7705774419009686,
|
| 1849 |
"num_tokens": 8486476.0,
|
| 1850 |
"step": 1830
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"entropy": 0.8954004615545272,
|
| 1854 |
+
"epoch": 0.39253333333333335,
|
| 1855 |
+
"grad_norm": 0.24745526909828186,
|
| 1856 |
+
"learning_rate": 9.307159712801147e-05,
|
| 1857 |
+
"loss": 0.9804242134094239,
|
| 1858 |
+
"mean_token_accuracy": 0.773698341846466,
|
| 1859 |
+
"num_tokens": 8533216.0,
|
| 1860 |
+
"step": 1840
|
| 1861 |
}
|
| 1862 |
],
|
| 1863 |
"logging_steps": 10,
|
|
|
|
| 1877 |
"attributes": {}
|
| 1878 |
}
|
| 1879 |
},
|
| 1880 |
+
"total_flos": 4.053352884170957e+16,
|
| 1881 |
"train_batch_size": 4,
|
| 1882 |
"trial_name": null,
|
| 1883 |
"trial_params": null
|