Training in progress, step 16000, 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 3555504
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd57384594eb425dd0bbabba65317a1b5777b6c5b289479078bfbc0a2b10c7cd
|
| 3 |
size 3555504
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7141515
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a90fca018f105f0c4de5bd49a9f37f48eb4343bbd82fa5c86a766904ed07780
|
| 3 |
size 7141515
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60e040819bef00bdfb5631475cda110717053ec4d4c4c67d6781ad7edccde1fd
|
| 3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9569b0daf1a454e36aca0fe6fc85ec984df4b90957450731328ceedec7505da8
|
| 3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8187ef3352672be0a48a06b17757282db7b3ef79dad63ef57d1187dc8f56fd82
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "CodeGenDetect-CodeBert_Lora/checkpoint-
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 4000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -884,6 +884,298 @@
|
|
| 884 |
"eval_samples_per_second": 121.628,
|
| 885 |
"eval_steps_per_second": 7.602,
|
| 886 |
"step": 12000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 887 |
}
|
| 888 |
],
|
| 889 |
"logging_steps": 100,
|
|
@@ -912,7 +1204,7 @@
|
|
| 912 |
"attributes": {}
|
| 913 |
}
|
| 914 |
},
|
| 915 |
-
"total_flos":
|
| 916 |
"train_batch_size": 16,
|
| 917 |
"trial_name": null,
|
| 918 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 16000,
|
| 3 |
+
"best_metric": 0.9820134202589396,
|
| 4 |
+
"best_model_checkpoint": "CodeGenDetect-CodeBert_Lora/checkpoint-16000",
|
| 5 |
+
"epoch": 0.512,
|
| 6 |
"eval_steps": 4000,
|
| 7 |
+
"global_step": 16000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 884 |
"eval_samples_per_second": 121.628,
|
| 885 |
"eval_steps_per_second": 7.602,
|
| 886 |
"step": 12000
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 0.3872,
|
| 890 |
+
"grad_norm": 11.900330543518066,
|
| 891 |
+
"learning_rate": 1.851056179775281e-05,
|
| 892 |
+
"loss": 0.0958,
|
| 893 |
+
"step": 12100
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 0.3904,
|
| 897 |
+
"grad_norm": 18.242124557495117,
|
| 898 |
+
"learning_rate": 1.8497720706260034e-05,
|
| 899 |
+
"loss": 0.075,
|
| 900 |
+
"step": 12200
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 0.3936,
|
| 904 |
+
"grad_norm": 0.0790882408618927,
|
| 905 |
+
"learning_rate": 1.8484879614767256e-05,
|
| 906 |
+
"loss": 0.071,
|
| 907 |
+
"step": 12300
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 0.3968,
|
| 911 |
+
"grad_norm": 16.233280181884766,
|
| 912 |
+
"learning_rate": 1.847203852327448e-05,
|
| 913 |
+
"loss": 0.1109,
|
| 914 |
+
"step": 12400
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.4,
|
| 918 |
+
"grad_norm": 12.048758506774902,
|
| 919 |
+
"learning_rate": 1.8459197431781702e-05,
|
| 920 |
+
"loss": 0.0703,
|
| 921 |
+
"step": 12500
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.4032,
|
| 925 |
+
"grad_norm": 9.086562156677246,
|
| 926 |
+
"learning_rate": 1.8446356340288927e-05,
|
| 927 |
+
"loss": 0.0706,
|
| 928 |
+
"step": 12600
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.4064,
|
| 932 |
+
"grad_norm": 9.871477127075195,
|
| 933 |
+
"learning_rate": 1.843351524879615e-05,
|
| 934 |
+
"loss": 0.0745,
|
| 935 |
+
"step": 12700
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 0.4096,
|
| 939 |
+
"grad_norm": 0.7136130928993225,
|
| 940 |
+
"learning_rate": 1.8420674157303373e-05,
|
| 941 |
+
"loss": 0.0544,
|
| 942 |
+
"step": 12800
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 0.4128,
|
| 946 |
+
"grad_norm": 10.892882347106934,
|
| 947 |
+
"learning_rate": 1.8407833065810598e-05,
|
| 948 |
+
"loss": 0.1109,
|
| 949 |
+
"step": 12900
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 0.416,
|
| 953 |
+
"grad_norm": 1.3350844383239746,
|
| 954 |
+
"learning_rate": 1.839499197431782e-05,
|
| 955 |
+
"loss": 0.0898,
|
| 956 |
+
"step": 13000
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.4192,
|
| 960 |
+
"grad_norm": 11.215353012084961,
|
| 961 |
+
"learning_rate": 1.838215088282504e-05,
|
| 962 |
+
"loss": 0.0963,
|
| 963 |
+
"step": 13100
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.4224,
|
| 967 |
+
"grad_norm": 0.2309681475162506,
|
| 968 |
+
"learning_rate": 1.8369309791332262e-05,
|
| 969 |
+
"loss": 0.0785,
|
| 970 |
+
"step": 13200
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.4256,
|
| 974 |
+
"grad_norm": 0.0822586640715599,
|
| 975 |
+
"learning_rate": 1.8356468699839487e-05,
|
| 976 |
+
"loss": 0.0736,
|
| 977 |
+
"step": 13300
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.4288,
|
| 981 |
+
"grad_norm": 0.6296452283859253,
|
| 982 |
+
"learning_rate": 1.834362760834671e-05,
|
| 983 |
+
"loss": 0.1064,
|
| 984 |
+
"step": 13400
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.432,
|
| 988 |
+
"grad_norm": 7.989764213562012,
|
| 989 |
+
"learning_rate": 1.8330786516853933e-05,
|
| 990 |
+
"loss": 0.0885,
|
| 991 |
+
"step": 13500
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.4352,
|
| 995 |
+
"grad_norm": 0.04016461223363876,
|
| 996 |
+
"learning_rate": 1.8317945425361158e-05,
|
| 997 |
+
"loss": 0.0574,
|
| 998 |
+
"step": 13600
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.4384,
|
| 1002 |
+
"grad_norm": 0.03219222649931908,
|
| 1003 |
+
"learning_rate": 1.830510433386838e-05,
|
| 1004 |
+
"loss": 0.0742,
|
| 1005 |
+
"step": 13700
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.4416,
|
| 1009 |
+
"grad_norm": 11.071674346923828,
|
| 1010 |
+
"learning_rate": 1.8292263242375605e-05,
|
| 1011 |
+
"loss": 0.0968,
|
| 1012 |
+
"step": 13800
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 0.4448,
|
| 1016 |
+
"grad_norm": 22.920804977416992,
|
| 1017 |
+
"learning_rate": 1.8279422150882826e-05,
|
| 1018 |
+
"loss": 0.0782,
|
| 1019 |
+
"step": 13900
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.448,
|
| 1023 |
+
"grad_norm": 0.05693759024143219,
|
| 1024 |
+
"learning_rate": 1.826658105939005e-05,
|
| 1025 |
+
"loss": 0.0538,
|
| 1026 |
+
"step": 14000
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.4512,
|
| 1030 |
+
"grad_norm": 0.08659256994724274,
|
| 1031 |
+
"learning_rate": 1.8253739967897272e-05,
|
| 1032 |
+
"loss": 0.0699,
|
| 1033 |
+
"step": 14100
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.4544,
|
| 1037 |
+
"grad_norm": 3.1322948932647705,
|
| 1038 |
+
"learning_rate": 1.8240898876404497e-05,
|
| 1039 |
+
"loss": 0.0841,
|
| 1040 |
+
"step": 14200
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.4576,
|
| 1044 |
+
"grad_norm": 0.025594089180231094,
|
| 1045 |
+
"learning_rate": 1.822805778491172e-05,
|
| 1046 |
+
"loss": 0.1108,
|
| 1047 |
+
"step": 14300
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.4608,
|
| 1051 |
+
"grad_norm": 0.5694848299026489,
|
| 1052 |
+
"learning_rate": 1.8215216693418943e-05,
|
| 1053 |
+
"loss": 0.0705,
|
| 1054 |
+
"step": 14400
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 0.464,
|
| 1058 |
+
"grad_norm": 5.643801212310791,
|
| 1059 |
+
"learning_rate": 1.8202375601926165e-05,
|
| 1060 |
+
"loss": 0.0773,
|
| 1061 |
+
"step": 14500
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 0.4672,
|
| 1065 |
+
"grad_norm": 1.6325165033340454,
|
| 1066 |
+
"learning_rate": 1.818953451043339e-05,
|
| 1067 |
+
"loss": 0.1244,
|
| 1068 |
+
"step": 14600
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 0.4704,
|
| 1072 |
+
"grad_norm": 0.04731294512748718,
|
| 1073 |
+
"learning_rate": 1.817669341894061e-05,
|
| 1074 |
+
"loss": 0.0523,
|
| 1075 |
+
"step": 14700
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 0.4736,
|
| 1079 |
+
"grad_norm": 9.385772705078125,
|
| 1080 |
+
"learning_rate": 1.8163852327447836e-05,
|
| 1081 |
+
"loss": 0.0739,
|
| 1082 |
+
"step": 14800
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.4768,
|
| 1086 |
+
"grad_norm": 0.04752274602651596,
|
| 1087 |
+
"learning_rate": 1.8151011235955057e-05,
|
| 1088 |
+
"loss": 0.0636,
|
| 1089 |
+
"step": 14900
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.48,
|
| 1093 |
+
"grad_norm": 0.4523526430130005,
|
| 1094 |
+
"learning_rate": 1.8138170144462282e-05,
|
| 1095 |
+
"loss": 0.0907,
|
| 1096 |
+
"step": 15000
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 0.4832,
|
| 1100 |
+
"grad_norm": 0.10660147666931152,
|
| 1101 |
+
"learning_rate": 1.8125329052969504e-05,
|
| 1102 |
+
"loss": 0.1093,
|
| 1103 |
+
"step": 15100
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 0.4864,
|
| 1107 |
+
"grad_norm": 0.024508710950613022,
|
| 1108 |
+
"learning_rate": 1.811248796147673e-05,
|
| 1109 |
+
"loss": 0.0562,
|
| 1110 |
+
"step": 15200
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 0.4896,
|
| 1114 |
+
"grad_norm": 4.832937240600586,
|
| 1115 |
+
"learning_rate": 1.809964686998395e-05,
|
| 1116 |
+
"loss": 0.0694,
|
| 1117 |
+
"step": 15300
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 0.4928,
|
| 1121 |
+
"grad_norm": 12.76455020904541,
|
| 1122 |
+
"learning_rate": 1.808680577849117e-05,
|
| 1123 |
+
"loss": 0.0525,
|
| 1124 |
+
"step": 15400
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 0.496,
|
| 1128 |
+
"grad_norm": 0.244754359126091,
|
| 1129 |
+
"learning_rate": 1.8073964686998396e-05,
|
| 1130 |
+
"loss": 0.0632,
|
| 1131 |
+
"step": 15500
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.4992,
|
| 1135 |
+
"grad_norm": 19.315397262573242,
|
| 1136 |
+
"learning_rate": 1.8061123595505618e-05,
|
| 1137 |
+
"loss": 0.0794,
|
| 1138 |
+
"step": 15600
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 0.5024,
|
| 1142 |
+
"grad_norm": 0.05077612027525902,
|
| 1143 |
+
"learning_rate": 1.8048282504012842e-05,
|
| 1144 |
+
"loss": 0.0848,
|
| 1145 |
+
"step": 15700
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 0.5056,
|
| 1149 |
+
"grad_norm": 0.33186858892440796,
|
| 1150 |
+
"learning_rate": 1.8035441412520064e-05,
|
| 1151 |
+
"loss": 0.0894,
|
| 1152 |
+
"step": 15800
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 0.5088,
|
| 1156 |
+
"grad_norm": 0.26919984817504883,
|
| 1157 |
+
"learning_rate": 1.802260032102729e-05,
|
| 1158 |
+
"loss": 0.0801,
|
| 1159 |
+
"step": 15900
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 0.512,
|
| 1163 |
+
"grad_norm": 3.566136121749878,
|
| 1164 |
+
"learning_rate": 1.800975922953451e-05,
|
| 1165 |
+
"loss": 0.0754,
|
| 1166 |
+
"step": 16000
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 0.512,
|
| 1170 |
+
"eval_accuracy": 0.98201,
|
| 1171 |
+
"eval_f1": 0.9820134202589396,
|
| 1172 |
+
"eval_loss": 0.07791993767023087,
|
| 1173 |
+
"eval_precision": 0.9820579125315673,
|
| 1174 |
+
"eval_recall": 0.98201,
|
| 1175 |
+
"eval_runtime": 823.0886,
|
| 1176 |
+
"eval_samples_per_second": 121.494,
|
| 1177 |
+
"eval_steps_per_second": 7.593,
|
| 1178 |
+
"step": 16000
|
| 1179 |
}
|
| 1180 |
],
|
| 1181 |
"logging_steps": 100,
|
|
|
|
| 1204 |
"attributes": {}
|
| 1205 |
}
|
| 1206 |
},
|
| 1207 |
+
"total_flos": 6.79459660326359e+16,
|
| 1208 |
"train_batch_size": 16,
|
| 1209 |
"trial_name": null,
|
| 1210 |
"trial_params": null
|