Training in progress, step 293, 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:d5203def3dfaa585f2709854cb7081b5402cb1703c0ef445c0dc93d47a9fca86
|
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 sha256:5587744a36631b994d493b042e7e0940c3917efca8cab938c21c474e8c07d606
|
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 sha256:9a3dae860874f4f9ec7b9723c4571a24fa5277582ebca2166c3d9dd7790aae41
|
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,
|
@@ -2030,6 +2030,34 @@
|
|
2030 |
"learning_rate": 5.6818181818181825e-05,
|
2031 |
"loss": 1.1278,
|
2032 |
"step": 289
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2033 |
}
|
2034 |
],
|
2035 |
"logging_steps": 1,
|
@@ -2049,7 +2077,7 @@
|
|
2049 |
"attributes": {}
|
2050 |
}
|
2051 |
},
|
2052 |
-
"total_flos": 3.
|
2053 |
"train_batch_size": 4,
|
2054 |
"trial_name": null,
|
2055 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.803840877914952,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 293,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2030 |
"learning_rate": 5.6818181818181825e-05,
|
2031 |
"loss": 1.1278,
|
2032 |
"step": 289
|
2033 |
+
},
|
2034 |
+
{
|
2035 |
+
"epoch": 0.7956104252400549,
|
2036 |
+
"grad_norm": 0.16730915009975433,
|
2037 |
+
"learning_rate": 5.606060606060606e-05,
|
2038 |
+
"loss": 1.1749,
|
2039 |
+
"step": 290
|
2040 |
+
},
|
2041 |
+
{
|
2042 |
+
"epoch": 0.7983539094650206,
|
2043 |
+
"grad_norm": 0.1525382548570633,
|
2044 |
+
"learning_rate": 5.5303030303030304e-05,
|
2045 |
+
"loss": 1.2134,
|
2046 |
+
"step": 291
|
2047 |
+
},
|
2048 |
+
{
|
2049 |
+
"epoch": 0.8010973936899863,
|
2050 |
+
"grad_norm": 0.17000265419483185,
|
2051 |
+
"learning_rate": 5.4545454545454546e-05,
|
2052 |
+
"loss": 1.1661,
|
2053 |
+
"step": 292
|
2054 |
+
},
|
2055 |
+
{
|
2056 |
+
"epoch": 0.803840877914952,
|
2057 |
+
"grad_norm": 0.16208770871162415,
|
2058 |
+
"learning_rate": 5.378787878787879e-05,
|
2059 |
+
"loss": 1.1965,
|
2060 |
+
"step": 293
|
2061 |
}
|
2062 |
],
|
2063 |
"logging_steps": 1,
|
|
|
2077 |
"attributes": {}
|
2078 |
}
|
2079 |
},
|
2080 |
+
"total_flos": 3.62592285449429e+17,
|
2081 |
"train_batch_size": 4,
|
2082 |
"trial_name": null,
|
2083 |
"trial_params": null
|