DuongTrongChi
commited on
Training in progress, step 256, 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 100198584
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80b0d40e2c615b97427e7bdf3afcffd6fb78cce5cb9cb6b805be336ffadd6b7f
|
3 |
size 100198584
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c0236b829e3835cad78df5d87594bb6703a3080d366dec38ebbbc23e0e8888d
|
3 |
+
size 50675604
|
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 sha256:55317fab103a1a04397df265d4815e3feac89218bf1f824f32f520fdd2b18fdc
|
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,
|
@@ -1792,6 +1792,13 @@
|
|
1792 |
"learning_rate": 8.257575757575758e-05,
|
1793 |
"loss": 1.0794,
|
1794 |
"step": 255
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1795 |
}
|
1796 |
],
|
1797 |
"logging_steps": 1,
|
@@ -1811,7 +1818,7 @@
|
|
1811 |
"attributes": {}
|
1812 |
}
|
1813 |
},
|
1814 |
-
"total_flos": 5.
|
1815 |
"train_batch_size": 4,
|
1816 |
"trial_name": null,
|
1817 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7023319615912208,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 256,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1792 |
"learning_rate": 8.257575757575758e-05,
|
1793 |
"loss": 1.0794,
|
1794 |
"step": 255
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 0.7023319615912208,
|
1798 |
+
"grad_norm": 0.08525680750608444,
|
1799 |
+
"learning_rate": 8.181818181818183e-05,
|
1800 |
+
"loss": 1.0633,
|
1801 |
+
"step": 256
|
1802 |
}
|
1803 |
],
|
1804 |
"logging_steps": 1,
|
|
|
1818 |
"attributes": {}
|
1819 |
}
|
1820 |
},
|
1821 |
+
"total_flos": 5.315725193362145e+17,
|
1822 |
"train_batch_size": 4,
|
1823 |
"trial_name": null,
|
1824 |
"trial_params": null
|