Training in progress, step 260, 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:a7503bcb2c3f34a1858d513a2596512e90f6888a1c9572e7fe5512c62e91046c
|
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 37431220
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5faf222eddf43df3300085931995fa326f25cdcf01906bf0ee0b2737cdd72beb
|
3 |
size 37431220
|
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 sha256:0e6d08bfa0ecdc29e58b4a5362f7ced16937eb7fa35e931e744fd7df0b5c2675
|
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": 0.
|
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,
|
@@ -1820,6 +1820,13 @@
|
|
1820 |
"learning_rate": 7.954545454545455e-05,
|
1821 |
"loss": 1.188,
|
1822 |
"step": 259
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1823 |
}
|
1824 |
],
|
1825 |
"logging_steps": 1,
|
@@ -1839,7 +1846,7 @@
|
|
1839 |
"attributes": {}
|
1840 |
}
|
1841 |
},
|
1842 |
-
"total_flos": 3.
|
1843 |
"train_batch_size": 4,
|
1844 |
"trial_name": null,
|
1845 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7133058984910837,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 260,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1820 |
"learning_rate": 7.954545454545455e-05,
|
1821 |
"loss": 1.188,
|
1822 |
"step": 259
|
1823 |
+
},
|
1824 |
+
{
|
1825 |
+
"epoch": 0.7133058984910837,
|
1826 |
+
"grad_norm": 0.170159250497818,
|
1827 |
+
"learning_rate": 7.878787878787879e-05,
|
1828 |
+
"loss": 1.1713,
|
1829 |
+
"step": 260
|
1830 |
}
|
1831 |
],
|
1832 |
"logging_steps": 1,
|
|
|
1846 |
"attributes": {}
|
1847 |
}
|
1848 |
},
|
1849 |
+
"total_flos": 3.2152157285707776e+17,
|
1850 |
"train_batch_size": 4,
|
1851 |
"trial_name": null,
|
1852 |
"trial_params": null
|