Training in progress, step 147, 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 sha256:4f9fa582df16c8bb97828057e8c4a02169f888bb4682c2860a2afe781e62114f
|
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:c9a24b52d6a3e315d864f2561637a9e727e308ecbcd834beff5adca16ae88694
|
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 sha256:3bd5b413cc681fd38907707be91b93b159a5941dcdc098dfc31b57c1648e1736
|
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,
|
@@ -1015,6 +1015,27 @@
|
|
1015 |
"learning_rate": 0.0001666666666666667,
|
1016 |
"loss": 1.2301,
|
1017 |
"step": 144
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1018 |
}
|
1019 |
],
|
1020 |
"logging_steps": 1,
|
@@ -1034,7 +1055,7 @@
|
|
1034 |
"attributes": {}
|
1035 |
}
|
1036 |
},
|
1037 |
-
"total_flos": 1.
|
1038 |
"train_batch_size": 4,
|
1039 |
"trial_name": null,
|
1040 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.40329218106995884,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 147,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1015 |
"learning_rate": 0.0001666666666666667,
|
1016 |
"loss": 1.2301,
|
1017 |
"step": 144
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.39780521262002744,
|
1021 |
+
"grad_norm": 0.13619515299797058,
|
1022 |
+
"learning_rate": 0.00016590909090909094,
|
1023 |
+
"loss": 1.1821,
|
1024 |
+
"step": 145
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.40054869684499317,
|
1028 |
+
"grad_norm": 0.15868829190731049,
|
1029 |
+
"learning_rate": 0.00016515151515151516,
|
1030 |
+
"loss": 1.2416,
|
1031 |
+
"step": 146
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.40329218106995884,
|
1035 |
+
"grad_norm": 0.13451522588729858,
|
1036 |
+
"learning_rate": 0.0001643939393939394,
|
1037 |
+
"loss": 1.2108,
|
1038 |
+
"step": 147
|
1039 |
}
|
1040 |
],
|
1041 |
"logging_steps": 1,
|
|
|
1055 |
"attributes": {}
|
1056 |
}
|
1057 |
},
|
1058 |
+
"total_flos": 1.8224278575004877e+17,
|
1059 |
"train_batch_size": 4,
|
1060 |
"trial_name": null,
|
1061 |
"trial_params": null
|