Training in progress, step 1350, 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 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f792ca2f39253114b59eb717807e2ff96b18c41da2f5d430b8418f21938975d
|
3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 168149074
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1bb6d2fc8b2efd6822aad78c3e4fd174d2075ff491b7a302ce16e6e2b9a7176c
|
3 |
size 168149074
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86519396222f045b85ec9776e7db27686ba4130a0d8956349c7b70ae36555704
|
3 |
size 14244
|
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:a866955cff9370cd3957339d6bf23f5ca8494fc491b0c5ef9330a9273b5d4460
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.636073112487793,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-900",
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 150,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -919,6 +919,119 @@
|
|
919 |
"eval_samples_per_second": 14.437,
|
920 |
"eval_steps_per_second": 1.821,
|
921 |
"step": 1200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
922 |
}
|
923 |
],
|
924 |
"logging_steps": 10,
|
@@ -933,7 +1046,7 @@
|
|
933 |
"early_stopping_threshold": 0.0
|
934 |
},
|
935 |
"attributes": {
|
936 |
-
"early_stopping_patience_counter":
|
937 |
}
|
938 |
},
|
939 |
"TrainerControl": {
|
@@ -942,12 +1055,12 @@
|
|
942 |
"should_evaluate": false,
|
943 |
"should_log": false,
|
944 |
"should_save": true,
|
945 |
-
"should_training_stop":
|
946 |
},
|
947 |
"attributes": {}
|
948 |
}
|
949 |
},
|
950 |
-
"total_flos": 1.
|
951 |
"train_batch_size": 8,
|
952 |
"trial_name": null,
|
953 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.636073112487793,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-900",
|
4 |
+
"epoch": 2.930005425935974,
|
5 |
"eval_steps": 150,
|
6 |
+
"global_step": 1350,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
919 |
"eval_samples_per_second": 14.437,
|
920 |
"eval_steps_per_second": 1.821,
|
921 |
"step": 1200
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 2.6261530113944653,
|
925 |
+
"grad_norm": 23.57729721069336,
|
926 |
+
"learning_rate": 2.86474508437579e-06,
|
927 |
+
"loss": 1.3837,
|
928 |
+
"step": 1210
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 2.6478567552902876,
|
932 |
+
"grad_norm": 35.865020751953125,
|
933 |
+
"learning_rate": 2.67658249108603e-06,
|
934 |
+
"loss": 1.562,
|
935 |
+
"step": 1220
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 2.6695604991861095,
|
939 |
+
"grad_norm": 19.588651657104492,
|
940 |
+
"learning_rate": 2.4942045588130504e-06,
|
941 |
+
"loss": 1.7947,
|
942 |
+
"step": 1230
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 2.691264243081932,
|
946 |
+
"grad_norm": 25.088882446289062,
|
947 |
+
"learning_rate": 2.317696896481024e-06,
|
948 |
+
"loss": 1.7935,
|
949 |
+
"step": 1240
|
950 |
+
},
|
951 |
+
{
|
952 |
+
"epoch": 2.7129679869777537,
|
953 |
+
"grad_norm": 31.45013427734375,
|
954 |
+
"learning_rate": 2.1471423574861643e-06,
|
955 |
+
"loss": 1.8259,
|
956 |
+
"step": 1250
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 2.7346717308735755,
|
960 |
+
"grad_norm": 27.531116485595703,
|
961 |
+
"learning_rate": 1.982621000804979e-06,
|
962 |
+
"loss": 1.4111,
|
963 |
+
"step": 1260
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 2.756375474769398,
|
967 |
+
"grad_norm": 42.346099853515625,
|
968 |
+
"learning_rate": 1.8242100534143065e-06,
|
969 |
+
"loss": 1.4248,
|
970 |
+
"step": 1270
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 2.7780792186652197,
|
974 |
+
"grad_norm": 25.887807846069336,
|
975 |
+
"learning_rate": 1.6719838740406313e-06,
|
976 |
+
"loss": 1.9046,
|
977 |
+
"step": 1280
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 2.799782962561042,
|
981 |
+
"grad_norm": 22.550439834594727,
|
982 |
+
"learning_rate": 1.5260139182558363e-06,
|
983 |
+
"loss": 1.7181,
|
984 |
+
"step": 1290
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 2.821486706456864,
|
988 |
+
"grad_norm": 24.849620819091797,
|
989 |
+
"learning_rate": 1.3863687049356465e-06,
|
990 |
+
"loss": 1.5168,
|
991 |
+
"step": 1300
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"epoch": 2.8431904503526857,
|
995 |
+
"grad_norm": 25.409860610961914,
|
996 |
+
"learning_rate": 1.25311378409661e-06,
|
997 |
+
"loss": 1.4321,
|
998 |
+
"step": 1310
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 2.864894194248508,
|
1002 |
+
"grad_norm": 36.389671325683594,
|
1003 |
+
"learning_rate": 1.1263117061266677e-06,
|
1004 |
+
"loss": 1.3841,
|
1005 |
+
"step": 1320
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 2.88659793814433,
|
1009 |
+
"grad_norm": 24.459070205688477,
|
1010 |
+
"learning_rate": 1.006021992423738e-06,
|
1011 |
+
"loss": 1.9626,
|
1012 |
+
"step": 1330
|
1013 |
+
},
|
1014 |
+
{
|
1015 |
+
"epoch": 2.908301682040152,
|
1016 |
+
"grad_norm": 20.42031478881836,
|
1017 |
+
"learning_rate": 8.923011074561405e-07,
|
1018 |
+
"loss": 1.6266,
|
1019 |
+
"step": 1340
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 2.930005425935974,
|
1023 |
+
"grad_norm": 25.92626190185547,
|
1024 |
+
"learning_rate": 7.852024322579649e-07,
|
1025 |
+
"loss": 1.6606,
|
1026 |
+
"step": 1350
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 2.930005425935974,
|
1030 |
+
"eval_loss": 0.6615604758262634,
|
1031 |
+
"eval_runtime": 53.8295,
|
1032 |
+
"eval_samples_per_second": 14.434,
|
1033 |
+
"eval_steps_per_second": 1.821,
|
1034 |
+
"step": 1350
|
1035 |
}
|
1036 |
],
|
1037 |
"logging_steps": 10,
|
|
|
1046 |
"early_stopping_threshold": 0.0
|
1047 |
},
|
1048 |
"attributes": {
|
1049 |
+
"early_stopping_patience_counter": 3
|
1050 |
}
|
1051 |
},
|
1052 |
"TrainerControl": {
|
|
|
1055 |
"should_evaluate": false,
|
1056 |
"should_log": false,
|
1057 |
"should_save": true,
|
1058 |
+
"should_training_stop": true
|
1059 |
},
|
1060 |
"attributes": {}
|
1061 |
}
|
1062 |
},
|
1063 |
+
"total_flos": 1.8928833688240128e+18,
|
1064 |
"train_batch_size": 8,
|
1065 |
"trial_name": null,
|
1066 |
"trial_params": null
|