Training in progress, step 40000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +303 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 100170757
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88a75430873048d1c55c1dfe2ccd053acab1fd15a8dcedf646948c68737b2e5a
|
| 3 |
size 100170757
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:484db98ddb6ed91b4ea5f15498a85d452cda43038e8130ac0e093318895988c2
|
| 3 |
size 146774203
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88f2a279490e0c3b8efb66c61c4617ccf8fdba17e1e5c57bdf6bbd4c4665d937
|
| 3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 246897640
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8a8e57edadd6965f548754431358c0af914fc344d18e1de094a5af2d8025b1c
|
| 3 |
size 246897640
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -906,11 +906,311 @@
|
|
| 906 |
"learning_rate": 0.00013167302452368236,
|
| 907 |
"loss": 3.5359,
|
| 908 |
"step": 30000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 909 |
}
|
| 910 |
],
|
| 911 |
"max_steps": 500000,
|
| 912 |
"num_train_epochs": 3,
|
| 913 |
-
"total_flos":
|
| 914 |
"trial_name": null,
|
| 915 |
"trial_params": null
|
| 916 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.17189514396218306,
|
| 5 |
+
"global_step": 40000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 906 |
"learning_rate": 0.00013167302452368236,
|
| 907 |
"loss": 3.5359,
|
| 908 |
"step": 30000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.13,
|
| 912 |
+
"learning_rate": 0.0001328582549574664,
|
| 913 |
+
"loss": 3.5252,
|
| 914 |
+
"step": 30200
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.13,
|
| 918 |
+
"learning_rate": 0.00013405027824677038,
|
| 919 |
+
"loss": 3.5104,
|
| 920 |
+
"step": 30400
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.13,
|
| 924 |
+
"learning_rate": 0.00013524907347614926,
|
| 925 |
+
"loss": 3.5253,
|
| 926 |
+
"step": 30600
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.13,
|
| 930 |
+
"learning_rate": 0.00013645461961133603,
|
| 931 |
+
"loss": 3.5249,
|
| 932 |
+
"step": 30800
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.13,
|
| 936 |
+
"learning_rate": 0.00013766689549961136,
|
| 937 |
+
"loss": 3.5374,
|
| 938 |
+
"step": 31000
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.13,
|
| 942 |
+
"learning_rate": 0.00013888587987017427,
|
| 943 |
+
"loss": 3.5093,
|
| 944 |
+
"step": 31200
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 0.13,
|
| 948 |
+
"learning_rate": 0.00014011155133451586,
|
| 949 |
+
"loss": 3.5465,
|
| 950 |
+
"step": 31400
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.14,
|
| 954 |
+
"learning_rate": 0.00014134388838679408,
|
| 955 |
+
"loss": 3.5362,
|
| 956 |
+
"step": 31600
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.14,
|
| 960 |
+
"learning_rate": 0.00014258286940421164,
|
| 961 |
+
"loss": 3.5233,
|
| 962 |
+
"step": 31800
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.14,
|
| 966 |
+
"learning_rate": 0.00014382847264739456,
|
| 967 |
+
"loss": 3.5425,
|
| 968 |
+
"step": 32000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.14,
|
| 972 |
+
"learning_rate": 0.00014508067626077482,
|
| 973 |
+
"loss": 3.5178,
|
| 974 |
+
"step": 32200
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.14,
|
| 978 |
+
"learning_rate": 0.00014633945827297273,
|
| 979 |
+
"loss": 3.5288,
|
| 980 |
+
"step": 32400
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 0.14,
|
| 984 |
+
"learning_rate": 0.00014760479659718304,
|
| 985 |
+
"loss": 3.52,
|
| 986 |
+
"step": 32600
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.14,
|
| 990 |
+
"learning_rate": 0.00014887666903156218,
|
| 991 |
+
"loss": 3.5121,
|
| 992 |
+
"step": 32800
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.14,
|
| 996 |
+
"learning_rate": 0.0001501550532596183,
|
| 997 |
+
"loss": 3.5191,
|
| 998 |
+
"step": 33000
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.14,
|
| 1002 |
+
"learning_rate": 0.00015143992685060208,
|
| 1003 |
+
"loss": 3.5097,
|
| 1004 |
+
"step": 33200
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.14,
|
| 1008 |
+
"learning_rate": 0.00015273126725990098,
|
| 1009 |
+
"loss": 3.5034,
|
| 1010 |
+
"step": 33400
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.14,
|
| 1014 |
+
"learning_rate": 0.00015402905182943438,
|
| 1015 |
+
"loss": 3.484,
|
| 1016 |
+
"step": 33600
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.15,
|
| 1020 |
+
"learning_rate": 0.00015533325778805166,
|
| 1021 |
+
"loss": 3.5111,
|
| 1022 |
+
"step": 33800
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 0.15,
|
| 1026 |
+
"learning_rate": 0.00015664386225193092,
|
| 1027 |
+
"loss": 3.5041,
|
| 1028 |
+
"step": 34000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.15,
|
| 1032 |
+
"learning_rate": 0.00015796084222498145,
|
| 1033 |
+
"loss": 3.5126,
|
| 1034 |
+
"step": 34200
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.15,
|
| 1038 |
+
"learning_rate": 0.0001592841745992464,
|
| 1039 |
+
"loss": 3.4939,
|
| 1040 |
+
"step": 34400
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.15,
|
| 1044 |
+
"learning_rate": 0.00016061383615530893,
|
| 1045 |
+
"loss": 3.4728,
|
| 1046 |
+
"step": 34600
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.15,
|
| 1050 |
+
"learning_rate": 0.0001619498035626989,
|
| 1051 |
+
"loss": 3.4671,
|
| 1052 |
+
"step": 34800
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.15,
|
| 1056 |
+
"learning_rate": 0.00016329205338030289,
|
| 1057 |
+
"loss": 3.5058,
|
| 1058 |
+
"step": 35000
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 0.15,
|
| 1062 |
+
"learning_rate": 0.00016464056205677522,
|
| 1063 |
+
"loss": 3.4973,
|
| 1064 |
+
"step": 35200
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.15,
|
| 1068 |
+
"learning_rate": 0.0001659953059309513,
|
| 1069 |
+
"loss": 3.488,
|
| 1070 |
+
"step": 35400
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 0.15,
|
| 1074 |
+
"learning_rate": 0.00016735626123226218,
|
| 1075 |
+
"loss": 3.4953,
|
| 1076 |
+
"step": 35600
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.15,
|
| 1080 |
+
"learning_rate": 0.00016872340408115283,
|
| 1081 |
+
"loss": 3.4772,
|
| 1082 |
+
"step": 35800
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.15,
|
| 1086 |
+
"learning_rate": 0.00017009671048950003,
|
| 1087 |
+
"loss": 3.4866,
|
| 1088 |
+
"step": 36000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.16,
|
| 1092 |
+
"learning_rate": 0.00017147615636103365,
|
| 1093 |
+
"loss": 3.4752,
|
| 1094 |
+
"step": 36200
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.16,
|
| 1098 |
+
"learning_rate": 0.00017286171749175986,
|
| 1099 |
+
"loss": 3.4878,
|
| 1100 |
+
"step": 36400
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 0.16,
|
| 1104 |
+
"learning_rate": 0.0001742533695703849,
|
| 1105 |
+
"loss": 3.468,
|
| 1106 |
+
"step": 36600
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.16,
|
| 1110 |
+
"learning_rate": 0.0001756510881787427,
|
| 1111 |
+
"loss": 3.4708,
|
| 1112 |
+
"step": 36800
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.16,
|
| 1116 |
+
"learning_rate": 0.00017705484879222265,
|
| 1117 |
+
"loss": 3.4879,
|
| 1118 |
+
"step": 37000
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.16,
|
| 1122 |
+
"learning_rate": 0.0001784646267801997,
|
| 1123 |
+
"loss": 3.4787,
|
| 1124 |
+
"step": 37200
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 0.16,
|
| 1128 |
+
"learning_rate": 0.00017988039740646764,
|
| 1129 |
+
"loss": 3.4673,
|
| 1130 |
+
"step": 37400
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.16,
|
| 1134 |
+
"learning_rate": 0.00018130213582967188,
|
| 1135 |
+
"loss": 3.4794,
|
| 1136 |
+
"step": 37600
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.16,
|
| 1140 |
+
"learning_rate": 0.00018272981710374596,
|
| 1141 |
+
"loss": 3.4561,
|
| 1142 |
+
"step": 37800
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 0.16,
|
| 1146 |
+
"learning_rate": 0.00018416341617834915,
|
| 1147 |
+
"loss": 3.4599,
|
| 1148 |
+
"step": 38000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 0.16,
|
| 1152 |
+
"learning_rate": 0.00018560290789930596,
|
| 1153 |
+
"loss": 3.454,
|
| 1154 |
+
"step": 38200
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.17,
|
| 1158 |
+
"learning_rate": 0.00018704826700904756,
|
| 1159 |
+
"loss": 3.4628,
|
| 1160 |
+
"step": 38400
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.17,
|
| 1164 |
+
"learning_rate": 0.00018849946814705483,
|
| 1165 |
+
"loss": 3.4557,
|
| 1166 |
+
"step": 38600
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 0.17,
|
| 1170 |
+
"learning_rate": 0.0001899564858503036,
|
| 1171 |
+
"loss": 3.4584,
|
| 1172 |
+
"step": 38800
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.17,
|
| 1176 |
+
"learning_rate": 0.00019141929455371092,
|
| 1177 |
+
"loss": 3.4492,
|
| 1178 |
+
"step": 39000
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.17,
|
| 1182 |
+
"learning_rate": 0.00019288786859058442,
|
| 1183 |
+
"loss": 3.4641,
|
| 1184 |
+
"step": 39200
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 0.17,
|
| 1188 |
+
"learning_rate": 0.00019436218219307173,
|
| 1189 |
+
"loss": 3.4665,
|
| 1190 |
+
"step": 39400
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 0.17,
|
| 1194 |
+
"learning_rate": 0.00019584220949261325,
|
| 1195 |
+
"loss": 3.4503,
|
| 1196 |
+
"step": 39600
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.17,
|
| 1200 |
+
"learning_rate": 0.00019732792452039607,
|
| 1201 |
+
"loss": 3.4438,
|
| 1202 |
+
"step": 39800
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.17,
|
| 1206 |
+
"learning_rate": 0.00019881930120780906,
|
| 1207 |
+
"loss": 3.4454,
|
| 1208 |
+
"step": 40000
|
| 1209 |
}
|
| 1210 |
],
|
| 1211 |
"max_steps": 500000,
|
| 1212 |
"num_train_epochs": 3,
|
| 1213 |
+
"total_flos": 6.375319928832e+16,
|
| 1214 |
"trial_name": null,
|
| 1215 |
"trial_params": null
|
| 1216 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:484db98ddb6ed91b4ea5f15498a85d452cda43038e8130ac0e093318895988c2
|
| 3 |
size 146774203
|