Training in progress, step 259, 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:b5c90a95a00372e3557d069f52fd43e2ea59a36721f7e976f22492f961da5038
|
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 sha256:80acf84a0d310e049a655aaac964192fb9f2670f2a859cf74644159ea34bced6
|
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 sha256:5012c82e4a30aa078945e25860940b48df00cd6e267158c3f649b085a33f5ab5
|
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,
|
@@ -1799,6 +1799,27 @@
|
|
1799 |
"learning_rate": 8.181818181818183e-05,
|
1800 |
"loss": 1.1858,
|
1801 |
"step": 256
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1802 |
}
|
1803 |
],
|
1804 |
"logging_steps": 1,
|
@@ -1818,7 +1839,7 @@
|
|
1818 |
"attributes": {}
|
1819 |
}
|
1820 |
},
|
1821 |
-
"total_flos": 3.
|
1822 |
"train_batch_size": 4,
|
1823 |
"trial_name": null,
|
1824 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.710562414266118,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 259,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1799 |
"learning_rate": 8.181818181818183e-05,
|
1800 |
"loss": 1.1858,
|
1801 |
"step": 256
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 0.7050754458161865,
|
1805 |
+
"grad_norm": 0.1652062088251114,
|
1806 |
+
"learning_rate": 8.106060606060607e-05,
|
1807 |
+
"loss": 1.1592,
|
1808 |
+
"step": 257
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 0.7078189300411523,
|
1812 |
+
"grad_norm": 0.15651218593120575,
|
1813 |
+
"learning_rate": 8.03030303030303e-05,
|
1814 |
+
"loss": 1.201,
|
1815 |
+
"step": 258
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 0.710562414266118,
|
1819 |
+
"grad_norm": 0.16143658757209778,
|
1820 |
+
"learning_rate": 7.954545454545455e-05,
|
1821 |
+
"loss": 1.188,
|
1822 |
+
"step": 259
|
1823 |
}
|
1824 |
],
|
1825 |
"logging_steps": 1,
|
|
|
1839 |
"attributes": {}
|
1840 |
}
|
1841 |
},
|
1842 |
+
"total_flos": 3.2030655996460646e+17,
|
1843 |
"train_batch_size": 4,
|
1844 |
"trial_name": null,
|
1845 |
"trial_params": null
|