Training in progress, step 207, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335922386
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:669a3e72f719737b15fab04bb2c0bb92048dfd22e9ef658a342e99d35c08129b
|
| 3 |
size 335922386
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b50dc51f8e724b3669be809cbc82ebe11f85d559dcac23ed00b062397afcd9e
|
| 3 |
size 14512
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5ddb4f7d90f5558927f96b9e1767bd45cee0b3d26de04640235b5ab19fc8793
|
| 3 |
size 14512
|
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 sha256:89e4cd8ea348bd2f82958df5383cd58880eb3efd1ec75ed70ce4064026b49560
|
| 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": 69,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -997,6 +997,497 @@
|
|
| 997 |
"eval_samples_per_second": 8.378,
|
| 998 |
"eval_steps_per_second": 2.099,
|
| 999 |
"step": 138
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1000 |
}
|
| 1001 |
],
|
| 1002 |
"logging_steps": 1,
|
|
@@ -1016,7 +1507,7 @@
|
|
| 1016 |
"attributes": {}
|
| 1017 |
}
|
| 1018 |
},
|
| 1019 |
-
"total_flos":
|
| 1020 |
"train_batch_size": 2,
|
| 1021 |
"trial_name": null,
|
| 1022 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.7537551206190259,
|
| 5 |
"eval_steps": 69,
|
| 6 |
+
"global_step": 207,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 997 |
"eval_samples_per_second": 8.378,
|
| 998 |
"eval_steps_per_second": 2.099,
|
| 999 |
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.5061447428311333,
|
| 1003 |
+
"grad_norm": NaN,
|
| 1004 |
+
"learning_rate": 0.00013170090808176883,
|
| 1005 |
+
"loss": 0.0,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.5097860719162495,
|
| 1010 |
+
"grad_norm": NaN,
|
| 1011 |
+
"learning_rate": 0.00013036767451096148,
|
| 1012 |
+
"loss": 0.0,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.5134274010013655,
|
| 1017 |
+
"grad_norm": NaN,
|
| 1018 |
+
"learning_rate": 0.00012902846772544624,
|
| 1019 |
+
"loss": 0.0,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.5170687300864816,
|
| 1024 |
+
"grad_norm": NaN,
|
| 1025 |
+
"learning_rate": 0.00012768355114248494,
|
| 1026 |
+
"loss": 0.0,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.5207100591715976,
|
| 1031 |
+
"grad_norm": NaN,
|
| 1032 |
+
"learning_rate": 0.00012633318930243648,
|
| 1033 |
+
"loss": 0.0,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.5243513882567137,
|
| 1038 |
+
"grad_norm": NaN,
|
| 1039 |
+
"learning_rate": 0.0001249776478167227,
|
| 1040 |
+
"loss": 0.0,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.5279927173418297,
|
| 1045 |
+
"grad_norm": NaN,
|
| 1046 |
+
"learning_rate": 0.00012361719331558345,
|
| 1047 |
+
"loss": 0.0,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.5316340464269458,
|
| 1052 |
+
"grad_norm": NaN,
|
| 1053 |
+
"learning_rate": 0.00012225209339563145,
|
| 1054 |
+
"loss": 0.0,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.535275375512062,
|
| 1059 |
+
"grad_norm": NaN,
|
| 1060 |
+
"learning_rate": 0.000120882616567217,
|
| 1061 |
+
"loss": 0.0,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.538916704597178,
|
| 1066 |
+
"grad_norm": NaN,
|
| 1067 |
+
"learning_rate": 0.00011950903220161285,
|
| 1068 |
+
"loss": 0.0,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.542558033682294,
|
| 1073 |
+
"grad_norm": NaN,
|
| 1074 |
+
"learning_rate": 0.00011813161047802985,
|
| 1075 |
+
"loss": 0.0,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.5461993627674101,
|
| 1080 |
+
"grad_norm": NaN,
|
| 1081 |
+
"learning_rate": 0.00011675062233047364,
|
| 1082 |
+
"loss": 0.0,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.5498406918525262,
|
| 1087 |
+
"grad_norm": NaN,
|
| 1088 |
+
"learning_rate": 0.000115366339394453,
|
| 1089 |
+
"loss": 0.0,
|
| 1090 |
+
"step": 151
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.5534820209376422,
|
| 1094 |
+
"grad_norm": NaN,
|
| 1095 |
+
"learning_rate": 0.00011397903395354996,
|
| 1096 |
+
"loss": 0.0,
|
| 1097 |
+
"step": 152
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.5571233500227583,
|
| 1101 |
+
"grad_norm": NaN,
|
| 1102 |
+
"learning_rate": 0.00011258897888586255,
|
| 1103 |
+
"loss": 0.0,
|
| 1104 |
+
"step": 153
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.5607646791078744,
|
| 1108 |
+
"grad_norm": NaN,
|
| 1109 |
+
"learning_rate": 0.00011119644761033078,
|
| 1110 |
+
"loss": 0.0,
|
| 1111 |
+
"step": 154
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.5644060081929905,
|
| 1115 |
+
"grad_norm": NaN,
|
| 1116 |
+
"learning_rate": 0.0001098017140329561,
|
| 1117 |
+
"loss": 0.0,
|
| 1118 |
+
"step": 155
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.5680473372781065,
|
| 1122 |
+
"grad_norm": NaN,
|
| 1123 |
+
"learning_rate": 0.00010840505249292476,
|
| 1124 |
+
"loss": 0.0,
|
| 1125 |
+
"step": 156
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.5716886663632226,
|
| 1129 |
+
"grad_norm": NaN,
|
| 1130 |
+
"learning_rate": 0.00010700673770864673,
|
| 1131 |
+
"loss": 0.0,
|
| 1132 |
+
"step": 157
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.5753299954483386,
|
| 1136 |
+
"grad_norm": NaN,
|
| 1137 |
+
"learning_rate": 0.00010560704472371919,
|
| 1138 |
+
"loss": 0.0,
|
| 1139 |
+
"step": 158
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.5789713245334547,
|
| 1143 |
+
"grad_norm": NaN,
|
| 1144 |
+
"learning_rate": 0.00010420624885282653,
|
| 1145 |
+
"loss": 0.0,
|
| 1146 |
+
"step": 159
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.5826126536185707,
|
| 1150 |
+
"grad_norm": NaN,
|
| 1151 |
+
"learning_rate": 0.0001028046256275869,
|
| 1152 |
+
"loss": 0.0,
|
| 1153 |
+
"step": 160
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.5862539827036869,
|
| 1157 |
+
"grad_norm": NaN,
|
| 1158 |
+
"learning_rate": 0.00010140245074235624,
|
| 1159 |
+
"loss": 0.0,
|
| 1160 |
+
"step": 161
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.589895311788803,
|
| 1164 |
+
"grad_norm": NaN,
|
| 1165 |
+
"learning_rate": 0.0001,
|
| 1166 |
+
"loss": 0.0,
|
| 1167 |
+
"step": 162
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.593536640873919,
|
| 1171 |
+
"grad_norm": NaN,
|
| 1172 |
+
"learning_rate": 9.859754925764378e-05,
|
| 1173 |
+
"loss": 0.0,
|
| 1174 |
+
"step": 163
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 0.597177969959035,
|
| 1178 |
+
"grad_norm": NaN,
|
| 1179 |
+
"learning_rate": 9.719537437241312e-05,
|
| 1180 |
+
"loss": 0.0,
|
| 1181 |
+
"step": 164
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 0.6008192990441511,
|
| 1185 |
+
"grad_norm": NaN,
|
| 1186 |
+
"learning_rate": 9.579375114717351e-05,
|
| 1187 |
+
"loss": 0.0,
|
| 1188 |
+
"step": 165
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 0.6044606281292672,
|
| 1192 |
+
"grad_norm": NaN,
|
| 1193 |
+
"learning_rate": 9.439295527628081e-05,
|
| 1194 |
+
"loss": 0.0,
|
| 1195 |
+
"step": 166
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 0.6081019572143832,
|
| 1199 |
+
"grad_norm": NaN,
|
| 1200 |
+
"learning_rate": 9.299326229135326e-05,
|
| 1201 |
+
"loss": 0.0,
|
| 1202 |
+
"step": 167
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.6117432862994994,
|
| 1206 |
+
"grad_norm": NaN,
|
| 1207 |
+
"learning_rate": 9.159494750707526e-05,
|
| 1208 |
+
"loss": 0.0,
|
| 1209 |
+
"step": 168
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.6153846153846154,
|
| 1213 |
+
"grad_norm": NaN,
|
| 1214 |
+
"learning_rate": 9.019828596704394e-05,
|
| 1215 |
+
"loss": 0.0,
|
| 1216 |
+
"step": 169
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.6190259444697315,
|
| 1220 |
+
"grad_norm": NaN,
|
| 1221 |
+
"learning_rate": 8.880355238966923e-05,
|
| 1222 |
+
"loss": 0.0,
|
| 1223 |
+
"step": 170
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 0.6226672735548475,
|
| 1227 |
+
"grad_norm": NaN,
|
| 1228 |
+
"learning_rate": 8.741102111413748e-05,
|
| 1229 |
+
"loss": 0.0,
|
| 1230 |
+
"step": 171
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 0.6263086026399636,
|
| 1234 |
+
"grad_norm": NaN,
|
| 1235 |
+
"learning_rate": 8.602096604645009e-05,
|
| 1236 |
+
"loss": 0.0,
|
| 1237 |
+
"step": 172
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 0.6299499317250796,
|
| 1241 |
+
"grad_norm": NaN,
|
| 1242 |
+
"learning_rate": 8.463366060554698e-05,
|
| 1243 |
+
"loss": 0.0,
|
| 1244 |
+
"step": 173
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 0.6335912608101957,
|
| 1248 |
+
"grad_norm": NaN,
|
| 1249 |
+
"learning_rate": 8.324937766952638e-05,
|
| 1250 |
+
"loss": 0.0,
|
| 1251 |
+
"step": 174
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.6372325898953118,
|
| 1255 |
+
"grad_norm": NaN,
|
| 1256 |
+
"learning_rate": 8.186838952197018e-05,
|
| 1257 |
+
"loss": 0.0,
|
| 1258 |
+
"step": 175
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.6408739189804279,
|
| 1262 |
+
"grad_norm": NaN,
|
| 1263 |
+
"learning_rate": 8.049096779838719e-05,
|
| 1264 |
+
"loss": 0.0,
|
| 1265 |
+
"step": 176
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 0.6445152480655439,
|
| 1269 |
+
"grad_norm": NaN,
|
| 1270 |
+
"learning_rate": 7.911738343278304e-05,
|
| 1271 |
+
"loss": 0.0,
|
| 1272 |
+
"step": 177
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 0.64815657715066,
|
| 1276 |
+
"grad_norm": NaN,
|
| 1277 |
+
"learning_rate": 7.774790660436858e-05,
|
| 1278 |
+
"loss": 0.0,
|
| 1279 |
+
"step": 178
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.651797906235776,
|
| 1283 |
+
"grad_norm": NaN,
|
| 1284 |
+
"learning_rate": 7.63828066844166e-05,
|
| 1285 |
+
"loss": 0.0,
|
| 1286 |
+
"step": 179
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 0.6554392353208921,
|
| 1290 |
+
"grad_norm": NaN,
|
| 1291 |
+
"learning_rate": 7.502235218327731e-05,
|
| 1292 |
+
"loss": 0.0,
|
| 1293 |
+
"step": 180
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.6590805644060082,
|
| 1297 |
+
"grad_norm": NaN,
|
| 1298 |
+
"learning_rate": 7.366681069756352e-05,
|
| 1299 |
+
"loss": 0.0,
|
| 1300 |
+
"step": 181
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.6627218934911243,
|
| 1304 |
+
"grad_norm": NaN,
|
| 1305 |
+
"learning_rate": 7.231644885751507e-05,
|
| 1306 |
+
"loss": 0.0,
|
| 1307 |
+
"step": 182
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.6663632225762404,
|
| 1311 |
+
"grad_norm": NaN,
|
| 1312 |
+
"learning_rate": 7.097153227455379e-05,
|
| 1313 |
+
"loss": 0.0,
|
| 1314 |
+
"step": 183
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.6700045516613564,
|
| 1318 |
+
"grad_norm": NaN,
|
| 1319 |
+
"learning_rate": 6.963232548903853e-05,
|
| 1320 |
+
"loss": 0.0,
|
| 1321 |
+
"step": 184
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.6736458807464725,
|
| 1325 |
+
"grad_norm": NaN,
|
| 1326 |
+
"learning_rate": 6.829909191823121e-05,
|
| 1327 |
+
"loss": 0.0,
|
| 1328 |
+
"step": 185
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.6772872098315885,
|
| 1332 |
+
"grad_norm": NaN,
|
| 1333 |
+
"learning_rate": 6.697209380448333e-05,
|
| 1334 |
+
"loss": 0.0,
|
| 1335 |
+
"step": 186
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.6809285389167046,
|
| 1339 |
+
"grad_norm": NaN,
|
| 1340 |
+
"learning_rate": 6.565159216365389e-05,
|
| 1341 |
+
"loss": 0.0,
|
| 1342 |
+
"step": 187
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 0.6845698680018206,
|
| 1346 |
+
"grad_norm": NaN,
|
| 1347 |
+
"learning_rate": 6.43378467337687e-05,
|
| 1348 |
+
"loss": 0.0,
|
| 1349 |
+
"step": 188
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 0.6882111970869367,
|
| 1353 |
+
"grad_norm": NaN,
|
| 1354 |
+
"learning_rate": 6.30311159239305e-05,
|
| 1355 |
+
"loss": 0.0,
|
| 1356 |
+
"step": 189
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 0.6918525261720528,
|
| 1360 |
+
"grad_norm": NaN,
|
| 1361 |
+
"learning_rate": 6.173165676349103e-05,
|
| 1362 |
+
"loss": 0.0,
|
| 1363 |
+
"step": 190
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 0.6954938552571689,
|
| 1367 |
+
"grad_norm": NaN,
|
| 1368 |
+
"learning_rate": 6.043972485149414e-05,
|
| 1369 |
+
"loss": 0.0,
|
| 1370 |
+
"step": 191
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.6991351843422849,
|
| 1374 |
+
"grad_norm": NaN,
|
| 1375 |
+
"learning_rate": 5.9155574306400395e-05,
|
| 1376 |
+
"loss": 0.0,
|
| 1377 |
+
"step": 192
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.702776513427401,
|
| 1381 |
+
"grad_norm": NaN,
|
| 1382 |
+
"learning_rate": 5.787945771610296e-05,
|
| 1383 |
+
"loss": 0.0,
|
| 1384 |
+
"step": 193
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 0.706417842512517,
|
| 1388 |
+
"grad_norm": NaN,
|
| 1389 |
+
"learning_rate": 5.6611626088244194e-05,
|
| 1390 |
+
"loss": 0.0,
|
| 1391 |
+
"step": 194
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 0.7100591715976331,
|
| 1395 |
+
"grad_norm": NaN,
|
| 1396 |
+
"learning_rate": 5.5352328800843724e-05,
|
| 1397 |
+
"loss": 0.0,
|
| 1398 |
+
"step": 195
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 0.7137005006827492,
|
| 1402 |
+
"grad_norm": NaN,
|
| 1403 |
+
"learning_rate": 5.410181355324622e-05,
|
| 1404 |
+
"loss": 0.0,
|
| 1405 |
+
"step": 196
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 0.7173418297678653,
|
| 1409 |
+
"grad_norm": NaN,
|
| 1410 |
+
"learning_rate": 5.286032631740023e-05,
|
| 1411 |
+
"loss": 0.0,
|
| 1412 |
+
"step": 197
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 0.7209831588529814,
|
| 1416 |
+
"grad_norm": NaN,
|
| 1417 |
+
"learning_rate": 5.162811128947602e-05,
|
| 1418 |
+
"loss": 0.0,
|
| 1419 |
+
"step": 198
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.7246244879380974,
|
| 1423 |
+
"grad_norm": NaN,
|
| 1424 |
+
"learning_rate": 5.0405410841833253e-05,
|
| 1425 |
+
"loss": 0.0,
|
| 1426 |
+
"step": 199
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 0.7282658170232135,
|
| 1430 |
+
"grad_norm": NaN,
|
| 1431 |
+
"learning_rate": 4.919246547534708e-05,
|
| 1432 |
+
"loss": 0.0,
|
| 1433 |
+
"step": 200
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 0.7319071461083295,
|
| 1437 |
+
"grad_norm": NaN,
|
| 1438 |
+
"learning_rate": 4.7989513772102537e-05,
|
| 1439 |
+
"loss": 0.0,
|
| 1440 |
+
"step": 201
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 0.7355484751934456,
|
| 1444 |
+
"grad_norm": NaN,
|
| 1445 |
+
"learning_rate": 4.6796792348466356e-05,
|
| 1446 |
+
"loss": 0.0,
|
| 1447 |
+
"step": 202
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 0.7391898042785616,
|
| 1451 |
+
"grad_norm": NaN,
|
| 1452 |
+
"learning_rate": 4.561453580854516e-05,
|
| 1453 |
+
"loss": 0.0,
|
| 1454 |
+
"step": 203
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 0.7428311333636778,
|
| 1458 |
+
"grad_norm": NaN,
|
| 1459 |
+
"learning_rate": 4.444297669803981e-05,
|
| 1460 |
+
"loss": 0.0,
|
| 1461 |
+
"step": 204
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 0.7464724624487938,
|
| 1465 |
+
"grad_norm": NaN,
|
| 1466 |
+
"learning_rate": 4.328234545850442e-05,
|
| 1467 |
+
"loss": 0.0,
|
| 1468 |
+
"step": 205
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 0.7501137915339099,
|
| 1472 |
+
"grad_norm": NaN,
|
| 1473 |
+
"learning_rate": 4.213287038201943e-05,
|
| 1474 |
+
"loss": 0.0,
|
| 1475 |
+
"step": 206
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 0.7537551206190259,
|
| 1479 |
+
"grad_norm": NaN,
|
| 1480 |
+
"learning_rate": 4.0994777566287204e-05,
|
| 1481 |
+
"loss": 0.0,
|
| 1482 |
+
"step": 207
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 0.7537551206190259,
|
| 1486 |
+
"eval_loss": NaN,
|
| 1487 |
+
"eval_runtime": 55.3157,
|
| 1488 |
+
"eval_samples_per_second": 8.37,
|
| 1489 |
+
"eval_steps_per_second": 2.097,
|
| 1490 |
+
"step": 207
|
| 1491 |
}
|
| 1492 |
],
|
| 1493 |
"logging_steps": 1,
|
|
|
|
| 1507 |
"attributes": {}
|
| 1508 |
}
|
| 1509 |
},
|
| 1510 |
+
"total_flos": 5.821918917018255e+17,
|
| 1511 |
"train_batch_size": 2,
|
| 1512 |
"trial_name": null,
|
| 1513 |
"trial_params": null
|