Training in progress, step 136, 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:f9483732d48eacdb2e432f58b70937682ad3622b75ecabad3dcf7a412bdbb3c6
|
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 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36c860851550acfd508fab07bc46e336243321884a16dc84e78e917c1107c05e
|
3 |
size 37430836
|
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 sha256:2115956bc9aff5f82eba458b69ba078ee4c70b0a5ff39630a0bb5a6fe3a570e8
|
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,
|
@@ -952,6 +952,13 @@
|
|
952 |
"learning_rate": 0.0001734848484848485,
|
953 |
"loss": 1.135,
|
954 |
"step": 135
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
955 |
}
|
956 |
],
|
957 |
"logging_steps": 1,
|
@@ -971,7 +978,7 @@
|
|
971 |
"attributes": {}
|
972 |
}
|
973 |
},
|
974 |
-
"total_flos": 1.
|
975 |
"train_batch_size": 4,
|
976 |
"trial_name": null,
|
977 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3731138545953361,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 136,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
952 |
"learning_rate": 0.0001734848484848485,
|
953 |
"loss": 1.135,
|
954 |
"step": 135
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.3731138545953361,
|
958 |
+
"grad_norm": 0.1388654112815857,
|
959 |
+
"learning_rate": 0.00017272727272727275,
|
960 |
+
"loss": 1.2217,
|
961 |
+
"step": 136
|
962 |
}
|
963 |
],
|
964 |
"logging_steps": 1,
|
|
|
978 |
"attributes": {}
|
979 |
}
|
980 |
},
|
981 |
+
"total_flos": 1.6877472757560115e+17,
|
982 |
"train_batch_size": 4,
|
983 |
"trial_name": null,
|
984 |
"trial_params": null
|