Training in progress, step 16000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 541154336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eee590a6a542d1f1d5b11450eee8ea5e55218ea6dd1f5ebb31fcfdd5d6173a1d
|
| 3 |
size 541154336
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1082379659
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:169d12341cc26c42de660d44a72be6e4103b1e6138612f4b5da9fb2664cd037d
|
| 3 |
size 1082379659
|
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:b928d2d8033ac6bd87c58a39b741faace8bd1c6b0d070b7fad23c19520ff9f1a
|
| 3 |
size 14645
|
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:ea5f9e2ce496bc8a089f39581e874b6a1c3a092591c67b5a4c3de15a05a65b33
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -944,6 +944,318 @@
|
|
| 944 |
"eval_samples_per_second": 41.425,
|
| 945 |
"eval_steps_per_second": 10.356,
|
| 946 |
"step": 12000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 947 |
}
|
| 948 |
],
|
| 949 |
"logging_steps": 100,
|
|
@@ -963,7 +1275,7 @@
|
|
| 963 |
"attributes": {}
|
| 964 |
}
|
| 965 |
},
|
| 966 |
-
"total_flos":
|
| 967 |
"train_batch_size": 22,
|
| 968 |
"trial_name": null,
|
| 969 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.2077922077922078,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 16000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 944 |
"eval_samples_per_second": 41.425,
|
| 945 |
"eval_steps_per_second": 10.356,
|
| 946 |
"step": 12000
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.15714285714285714,
|
| 950 |
+
"grad_norm": 0.18391777575016022,
|
| 951 |
+
"learning_rate": 0.0009748374587943688,
|
| 952 |
+
"loss": 2.9694,
|
| 953 |
+
"step": 12100
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.15844155844155844,
|
| 957 |
+
"grad_norm": 0.20561572909355164,
|
| 958 |
+
"learning_rate": 0.0009743838728224687,
|
| 959 |
+
"loss": 3.0187,
|
| 960 |
+
"step": 12200
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.15974025974025974,
|
| 964 |
+
"grad_norm": 0.17854483425617218,
|
| 965 |
+
"learning_rate": 0.0009739263425055934,
|
| 966 |
+
"loss": 2.9687,
|
| 967 |
+
"step": 12300
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.16103896103896104,
|
| 971 |
+
"grad_norm": 0.18647781014442444,
|
| 972 |
+
"learning_rate": 0.0009734648716479563,
|
| 973 |
+
"loss": 2.9574,
|
| 974 |
+
"step": 12400
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.16233766233766234,
|
| 978 |
+
"grad_norm": 0.1802452653646469,
|
| 979 |
+
"learning_rate": 0.0009729994640865349,
|
| 980 |
+
"loss": 2.9812,
|
| 981 |
+
"step": 12500
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.16363636363636364,
|
| 985 |
+
"grad_norm": 0.18787842988967896,
|
| 986 |
+
"learning_rate": 0.0009725301236910393,
|
| 987 |
+
"loss": 2.9771,
|
| 988 |
+
"step": 12600
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.16493506493506493,
|
| 992 |
+
"grad_norm": 0.18528838455677032,
|
| 993 |
+
"learning_rate": 0.0009720568543638793,
|
| 994 |
+
"loss": 2.9525,
|
| 995 |
+
"step": 12700
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.16623376623376623,
|
| 999 |
+
"grad_norm": 0.17883966863155365,
|
| 1000 |
+
"learning_rate": 0.000971579660040133,
|
| 1001 |
+
"loss": 2.9624,
|
| 1002 |
+
"step": 12800
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.16753246753246753,
|
| 1006 |
+
"grad_norm": 0.17459270358085632,
|
| 1007 |
+
"learning_rate": 0.0009710985446875134,
|
| 1008 |
+
"loss": 2.9696,
|
| 1009 |
+
"step": 12900
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.16883116883116883,
|
| 1013 |
+
"grad_norm": 0.1830231249332428,
|
| 1014 |
+
"learning_rate": 0.0009706135123063352,
|
| 1015 |
+
"loss": 2.9609,
|
| 1016 |
+
"step": 13000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.16883116883116883,
|
| 1020 |
+
"eval_loss": 3.337019920349121,
|
| 1021 |
+
"eval_runtime": 15.8318,
|
| 1022 |
+
"eval_samples_per_second": 36.383,
|
| 1023 |
+
"eval_steps_per_second": 9.096,
|
| 1024 |
+
"step": 13000
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.17012987012987013,
|
| 1028 |
+
"grad_norm": 0.20791789889335632,
|
| 1029 |
+
"learning_rate": 0.0009701245669294825,
|
| 1030 |
+
"loss": 2.9953,
|
| 1031 |
+
"step": 13100
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.17142857142857143,
|
| 1035 |
+
"grad_norm": 0.20302486419677734,
|
| 1036 |
+
"learning_rate": 0.0009696317126223742,
|
| 1037 |
+
"loss": 3.0519,
|
| 1038 |
+
"step": 13200
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.17272727272727273,
|
| 1042 |
+
"grad_norm": 0.17939983308315277,
|
| 1043 |
+
"learning_rate": 0.000969134953482931,
|
| 1044 |
+
"loss": 2.9618,
|
| 1045 |
+
"step": 13300
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.17402597402597403,
|
| 1049 |
+
"grad_norm": 0.2437734603881836,
|
| 1050 |
+
"learning_rate": 0.0009686342936415407,
|
| 1051 |
+
"loss": 2.955,
|
| 1052 |
+
"step": 13400
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.17532467532467533,
|
| 1056 |
+
"grad_norm": 0.19909310340881348,
|
| 1057 |
+
"learning_rate": 0.000968129737261024,
|
| 1058 |
+
"loss": 2.9898,
|
| 1059 |
+
"step": 13500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.17662337662337663,
|
| 1063 |
+
"grad_norm": 0.1696212738752365,
|
| 1064 |
+
"learning_rate": 0.000967621288536601,
|
| 1065 |
+
"loss": 2.9793,
|
| 1066 |
+
"step": 13600
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.17792207792207793,
|
| 1070 |
+
"grad_norm": 0.171333447098732,
|
| 1071 |
+
"learning_rate": 0.0009671089516958538,
|
| 1072 |
+
"loss": 2.942,
|
| 1073 |
+
"step": 13700
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.17922077922077922,
|
| 1077 |
+
"grad_norm": 0.17436903715133667,
|
| 1078 |
+
"learning_rate": 0.0009665927309986944,
|
| 1079 |
+
"loss": 2.9574,
|
| 1080 |
+
"step": 13800
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.18051948051948052,
|
| 1084 |
+
"grad_norm": 0.20607399940490723,
|
| 1085 |
+
"learning_rate": 0.0009660726307373266,
|
| 1086 |
+
"loss": 2.965,
|
| 1087 |
+
"step": 13900
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.18181818181818182,
|
| 1091 |
+
"grad_norm": 0.17206591367721558,
|
| 1092 |
+
"learning_rate": 0.0009655486552362127,
|
| 1093 |
+
"loss": 2.9532,
|
| 1094 |
+
"step": 14000
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.18181818181818182,
|
| 1098 |
+
"eval_loss": 3.327735424041748,
|
| 1099 |
+
"eval_runtime": 13.5364,
|
| 1100 |
+
"eval_samples_per_second": 42.552,
|
| 1101 |
+
"eval_steps_per_second": 10.638,
|
| 1102 |
+
"step": 14000
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.18311688311688312,
|
| 1106 |
+
"grad_norm": 0.20287004113197327,
|
| 1107 |
+
"learning_rate": 0.000965020808852035,
|
| 1108 |
+
"loss": 2.9153,
|
| 1109 |
+
"step": 14100
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.18441558441558442,
|
| 1113 |
+
"grad_norm": 0.18036919832229614,
|
| 1114 |
+
"learning_rate": 0.0009644890959736619,
|
| 1115 |
+
"loss": 2.933,
|
| 1116 |
+
"step": 14200
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.18571428571428572,
|
| 1120 |
+
"grad_norm": 0.21330875158309937,
|
| 1121 |
+
"learning_rate": 0.0009639535210221099,
|
| 1122 |
+
"loss": 2.9773,
|
| 1123 |
+
"step": 14300
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.18701298701298702,
|
| 1127 |
+
"grad_norm": 0.20942148566246033,
|
| 1128 |
+
"learning_rate": 0.000963414088450508,
|
| 1129 |
+
"loss": 2.9225,
|
| 1130 |
+
"step": 14400
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.18831168831168832,
|
| 1134 |
+
"grad_norm": 0.188313826918602,
|
| 1135 |
+
"learning_rate": 0.0009628708027440592,
|
| 1136 |
+
"loss": 2.9409,
|
| 1137 |
+
"step": 14500
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.18961038961038962,
|
| 1141 |
+
"grad_norm": 0.17884506285190582,
|
| 1142 |
+
"learning_rate": 0.0009623236684200043,
|
| 1143 |
+
"loss": 2.9635,
|
| 1144 |
+
"step": 14600
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.19090909090909092,
|
| 1148 |
+
"grad_norm": 0.17130698263645172,
|
| 1149 |
+
"learning_rate": 0.0009617726900275845,
|
| 1150 |
+
"loss": 2.9447,
|
| 1151 |
+
"step": 14700
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.19220779220779222,
|
| 1155 |
+
"grad_norm": 0.19943124055862427,
|
| 1156 |
+
"learning_rate": 0.0009612178721480027,
|
| 1157 |
+
"loss": 2.9525,
|
| 1158 |
+
"step": 14800
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.19350649350649352,
|
| 1162 |
+
"grad_norm": 0.18249951303005219,
|
| 1163 |
+
"learning_rate": 0.0009606592193943861,
|
| 1164 |
+
"loss": 2.9405,
|
| 1165 |
+
"step": 14900
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.19480519480519481,
|
| 1169 |
+
"grad_norm": 0.17710338532924652,
|
| 1170 |
+
"learning_rate": 0.0009600967364117478,
|
| 1171 |
+
"loss": 2.921,
|
| 1172 |
+
"step": 15000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.19480519480519481,
|
| 1176 |
+
"eval_loss": 3.307467460632324,
|
| 1177 |
+
"eval_runtime": 15.2964,
|
| 1178 |
+
"eval_samples_per_second": 37.656,
|
| 1179 |
+
"eval_steps_per_second": 9.414,
|
| 1180 |
+
"step": 15000
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 0.1961038961038961,
|
| 1184 |
+
"grad_norm": 0.2033987194299698,
|
| 1185 |
+
"learning_rate": 0.0009595304278769472,
|
| 1186 |
+
"loss": 2.9253,
|
| 1187 |
+
"step": 15100
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 0.1974025974025974,
|
| 1191 |
+
"grad_norm": 0.17457351088523865,
|
| 1192 |
+
"learning_rate": 0.000958960298498653,
|
| 1193 |
+
"loss": 2.9183,
|
| 1194 |
+
"step": 15200
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.1987012987012987,
|
| 1198 |
+
"grad_norm": 0.2011554092168808,
|
| 1199 |
+
"learning_rate": 0.0009583863530173018,
|
| 1200 |
+
"loss": 2.9254,
|
| 1201 |
+
"step": 15300
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.2,
|
| 1205 |
+
"grad_norm": 0.18333646655082703,
|
| 1206 |
+
"learning_rate": 0.0009578085962050609,
|
| 1207 |
+
"loss": 2.9383,
|
| 1208 |
+
"step": 15400
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.2012987012987013,
|
| 1212 |
+
"grad_norm": 0.167351633310318,
|
| 1213 |
+
"learning_rate": 0.0009572270328657869,
|
| 1214 |
+
"loss": 2.9435,
|
| 1215 |
+
"step": 15500
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.2025974025974026,
|
| 1219 |
+
"grad_norm": 0.17198020219802856,
|
| 1220 |
+
"learning_rate": 0.0009566416678349864,
|
| 1221 |
+
"loss": 2.9336,
|
| 1222 |
+
"step": 15600
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 0.2038961038961039,
|
| 1226 |
+
"grad_norm": 0.19012530148029327,
|
| 1227 |
+
"learning_rate": 0.0009560525059797762,
|
| 1228 |
+
"loss": 2.9353,
|
| 1229 |
+
"step": 15700
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 0.2051948051948052,
|
| 1233 |
+
"grad_norm": 0.18222008645534515,
|
| 1234 |
+
"learning_rate": 0.0009554595521988423,
|
| 1235 |
+
"loss": 2.934,
|
| 1236 |
+
"step": 15800
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 0.2064935064935065,
|
| 1240 |
+
"grad_norm": 0.18934360146522522,
|
| 1241 |
+
"learning_rate": 0.0009548628114223989,
|
| 1242 |
+
"loss": 2.902,
|
| 1243 |
+
"step": 15900
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.2077922077922078,
|
| 1247 |
+
"grad_norm": 0.17503845691680908,
|
| 1248 |
+
"learning_rate": 0.0009542622886121486,
|
| 1249 |
+
"loss": 2.9485,
|
| 1250 |
+
"step": 16000
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.2077922077922078,
|
| 1254 |
+
"eval_loss": 3.305332660675049,
|
| 1255 |
+
"eval_runtime": 14.5112,
|
| 1256 |
+
"eval_samples_per_second": 39.693,
|
| 1257 |
+
"eval_steps_per_second": 9.923,
|
| 1258 |
+
"step": 16000
|
| 1259 |
}
|
| 1260 |
],
|
| 1261 |
"logging_steps": 100,
|
|
|
|
| 1275 |
"attributes": {}
|
| 1276 |
}
|
| 1277 |
},
|
| 1278 |
+
"total_flos": 4.7630902099968e+17,
|
| 1279 |
"train_batch_size": 22,
|
| 1280 |
"trial_name": null,
|
| 1281 |
"trial_params": null
|