Training in progress, step 187, 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 50503544
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c109d0352421c1cb05b2ff3fc87f8bd43bf633d39b152a46ee64665256439a6d
|
| 3 |
size 50503544
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 101184122
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f79a32be0dd3059fb93b2da55666cfc3e419bf5b75845923fd42b704177228fc
|
| 3 |
size 101184122
|
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:c72d6bf0f78b2357465d590b9ffc3c74333bf1690eaca071e21b5b7bee96dbb3
|
| 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 sha256:89d6b36d890e4feb9f504b11799c7b132518b64e8b4e20ff987bf434d0dbe85d
|
| 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 sha256:3a5837b01af5a87d0f5eb6d6423726a5527c672ed560086af1a89b1f12d78ea5
|
| 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": 47,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1026,6 +1026,328 @@
|
|
| 1026 |
"eval_samples_per_second": 19.75,
|
| 1027 |
"eval_steps_per_second": 4.938,
|
| 1028 |
"step": 141
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1029 |
}
|
| 1030 |
],
|
| 1031 |
"logging_steps": 1,
|
|
@@ -1040,12 +1362,12 @@
|
|
| 1040 |
"should_evaluate": false,
|
| 1041 |
"should_log": false,
|
| 1042 |
"should_save": true,
|
| 1043 |
-
"should_training_stop":
|
| 1044 |
},
|
| 1045 |
"attributes": {}
|
| 1046 |
}
|
| 1047 |
},
|
| 1048 |
-
"total_flos": 1.
|
| 1049 |
"train_batch_size": 2,
|
| 1050 |
"trial_name": null,
|
| 1051 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9993319973279893,
|
| 5 |
"eval_steps": 47,
|
| 6 |
+
"global_step": 187,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1026 |
"eval_samples_per_second": 19.75,
|
| 1027 |
"eval_steps_per_second": 4.938,
|
| 1028 |
"step": 141
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.7588510354041417,
|
| 1032 |
+
"grad_norm": 2.703543186187744,
|
| 1033 |
+
"learning_rate": 3.3741908964485414e-05,
|
| 1034 |
+
"loss": 1.3041,
|
| 1035 |
+
"step": 142
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.7641950567802271,
|
| 1039 |
+
"grad_norm": 2.4582364559173584,
|
| 1040 |
+
"learning_rate": 3.234472017105313e-05,
|
| 1041 |
+
"loss": 1.5893,
|
| 1042 |
+
"step": 143
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.7695390781563126,
|
| 1046 |
+
"grad_norm": 2.735029935836792,
|
| 1047 |
+
"learning_rate": 3.0971473116511394e-05,
|
| 1048 |
+
"loss": 1.1325,
|
| 1049 |
+
"step": 144
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.7748830995323981,
|
| 1053 |
+
"grad_norm": 2.368544578552246,
|
| 1054 |
+
"learning_rate": 2.9622653763263874e-05,
|
| 1055 |
+
"loss": 1.3839,
|
| 1056 |
+
"step": 145
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 0.7802271209084837,
|
| 1060 |
+
"grad_norm": 2.601339340209961,
|
| 1061 |
+
"learning_rate": 2.8298739429279707e-05,
|
| 1062 |
+
"loss": 2.6563,
|
| 1063 |
+
"step": 146
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 0.7855711422845691,
|
| 1067 |
+
"grad_norm": 3.593987464904785,
|
| 1068 |
+
"learning_rate": 2.7000198619180794e-05,
|
| 1069 |
+
"loss": 3.1875,
|
| 1070 |
+
"step": 147
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 0.7909151636606546,
|
| 1074 |
+
"grad_norm": 5.363809108734131,
|
| 1075 |
+
"learning_rate": 2.5727490858448288e-05,
|
| 1076 |
+
"loss": 3.8335,
|
| 1077 |
+
"step": 148
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.7962591850367402,
|
| 1081 |
+
"grad_norm": 6.153328895568848,
|
| 1082 |
+
"learning_rate": 2.4481066530806395e-05,
|
| 1083 |
+
"loss": 3.3706,
|
| 1084 |
+
"step": 149
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 0.8016032064128257,
|
| 1088 |
+
"grad_norm": 7.4249091148376465,
|
| 1089 |
+
"learning_rate": 2.3261366718841305e-05,
|
| 1090 |
+
"loss": 3.1387,
|
| 1091 |
+
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.8069472277889111,
|
| 1095 |
+
"grad_norm": 1.7294468879699707,
|
| 1096 |
+
"learning_rate": 2.206882304791176e-05,
|
| 1097 |
+
"loss": 3.2262,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.8122912491649966,
|
| 1102 |
+
"grad_norm": 2.171717643737793,
|
| 1103 |
+
"learning_rate": 2.0903857533405958e-05,
|
| 1104 |
+
"loss": 3.2502,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.8176352705410822,
|
| 1109 |
+
"grad_norm": 1.9437127113342285,
|
| 1110 |
+
"learning_rate": 1.9766882431399646e-05,
|
| 1111 |
+
"loss": 3.0417,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.8229792919171677,
|
| 1116 |
+
"grad_norm": 2.4127237796783447,
|
| 1117 |
+
"learning_rate": 1.8658300092767544e-05,
|
| 1118 |
+
"loss": 1.985,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.8283233132932531,
|
| 1123 |
+
"grad_norm": 1.9797170162200928,
|
| 1124 |
+
"learning_rate": 1.7578502820800045e-05,
|
| 1125 |
+
"loss": 2.8997,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.8336673346693386,
|
| 1130 |
+
"grad_norm": 1.9933407306671143,
|
| 1131 |
+
"learning_rate": 1.652787273237565e-05,
|
| 1132 |
+
"loss": 3.0551,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.8390113560454242,
|
| 1137 |
+
"grad_norm": 2.6005380153656006,
|
| 1138 |
+
"learning_rate": 1.5506781622737942e-05,
|
| 1139 |
+
"loss": 3.1719,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.8443553774215097,
|
| 1144 |
+
"grad_norm": 2.0730040073394775,
|
| 1145 |
+
"learning_rate": 1.4515590833925507e-05,
|
| 1146 |
+
"loss": 1.8285,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.8496993987975952,
|
| 1151 |
+
"grad_norm": 1.7980684041976929,
|
| 1152 |
+
"learning_rate": 1.3554651126900564e-05,
|
| 1153 |
+
"loss": 2.2764,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.8550434201736807,
|
| 1158 |
+
"grad_norm": 1.8802449703216553,
|
| 1159 |
+
"learning_rate": 1.2624302557422473e-05,
|
| 1160 |
+
"loss": 3.1112,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.8603874415497662,
|
| 1165 |
+
"grad_norm": 2.0457687377929688,
|
| 1166 |
+
"learning_rate": 1.172487435570926e-05,
|
| 1167 |
+
"loss": 3.0587,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.8657314629258517,
|
| 1172 |
+
"grad_norm": 1.9472899436950684,
|
| 1173 |
+
"learning_rate": 1.0856684809930151e-05,
|
| 1174 |
+
"loss": 2.3786,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.8710754843019372,
|
| 1179 |
+
"grad_norm": 1.9495573043823242,
|
| 1180 |
+
"learning_rate": 1.0020041153570347e-05,
|
| 1181 |
+
"loss": 2.9965,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.8764195056780227,
|
| 1186 |
+
"grad_norm": 2.6365323066711426,
|
| 1187 |
+
"learning_rate": 9.215239456707635e-06,
|
| 1188 |
+
"loss": 3.3418,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.8817635270541082,
|
| 1193 |
+
"grad_norm": 2.1325201988220215,
|
| 1194 |
+
"learning_rate": 8.442564521239782e-06,
|
| 1195 |
+
"loss": 2.9538,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.8871075484301937,
|
| 1200 |
+
"grad_norm": 2.537140369415283,
|
| 1201 |
+
"learning_rate": 7.70228978009907e-06,
|
| 1202 |
+
"loss": 1.329,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.8924515698062793,
|
| 1207 |
+
"grad_norm": 2.8866047859191895,
|
| 1208 |
+
"learning_rate": 6.994677200490507e-06,
|
| 1209 |
+
"loss": 1.2163,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.8977955911823647,
|
| 1214 |
+
"grad_norm": 2.537121295928955,
|
| 1215 |
+
"learning_rate": 6.319977191187232e-06,
|
| 1216 |
+
"loss": 1.4877,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.9031396125584502,
|
| 1221 |
+
"grad_norm": 2.798138380050659,
|
| 1222 |
+
"learning_rate": 5.678428513916212e-06,
|
| 1223 |
+
"loss": 1.2401,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.9084836339345357,
|
| 1228 |
+
"grad_norm": 1.8588306903839111,
|
| 1229 |
+
"learning_rate": 5.07025819886574e-06,
|
| 1230 |
+
"loss": 2.3853,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.9138276553106213,
|
| 1235 |
+
"grad_norm": 3.1269595623016357,
|
| 1236 |
+
"learning_rate": 4.495681464344259e-06,
|
| 1237 |
+
"loss": 3.4073,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.9191716766867067,
|
| 1242 |
+
"grad_norm": 3.1233201026916504,
|
| 1243 |
+
"learning_rate": 3.954901640619368e-06,
|
| 1244 |
+
"loss": 3.1646,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.9245156980627922,
|
| 1249 |
+
"grad_norm": 4.395522117614746,
|
| 1250 |
+
"learning_rate": 3.4481100979635306e-06,
|
| 1251 |
+
"loss": 3.6045,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.9298597194388778,
|
| 1256 |
+
"grad_norm": 5.26246452331543,
|
| 1257 |
+
"learning_rate": 2.9754861789324073e-06,
|
| 1258 |
+
"loss": 3.1748,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.9352037408149633,
|
| 1263 |
+
"grad_norm": 7.157742977142334,
|
| 1264 |
+
"learning_rate": 2.537197134899294e-06,
|
| 1265 |
+
"loss": 3.3458,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.9405477621910487,
|
| 1270 |
+
"grad_norm": 1.6674422025680542,
|
| 1271 |
+
"learning_rate": 2.1333980668685414e-06,
|
| 1272 |
+
"loss": 3.3945,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.9458917835671342,
|
| 1277 |
+
"grad_norm": 1.6258163452148438,
|
| 1278 |
+
"learning_rate": 1.7642318705886286e-06,
|
| 1279 |
+
"loss": 2.398,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.9512358049432198,
|
| 1284 |
+
"grad_norm": 1.771727442741394,
|
| 1285 |
+
"learning_rate": 1.4298291859845214e-06,
|
| 1286 |
+
"loss": 3.235,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.9565798263193053,
|
| 1291 |
+
"grad_norm": 1.9831771850585938,
|
| 1292 |
+
"learning_rate": 1.1303083509269452e-06,
|
| 1293 |
+
"loss": 2.1936,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.9619238476953907,
|
| 1298 |
+
"grad_norm": 2.070289373397827,
|
| 1299 |
+
"learning_rate": 8.657753593552143e-07,
|
| 1300 |
+
"loss": 2.3432,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.9672678690714763,
|
| 1305 |
+
"grad_norm": 1.823572039604187,
|
| 1306 |
+
"learning_rate": 6.363238237683033e-07,
|
| 1307 |
+
"loss": 2.6982,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.9726118904475618,
|
| 1312 |
+
"grad_norm": 1.9612380266189575,
|
| 1313 |
+
"learning_rate": 4.4203494209733576e-07,
|
| 1314 |
+
"loss": 2.9414,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.9779559118236473,
|
| 1319 |
+
"grad_norm": 2.1800384521484375,
|
| 1320 |
+
"learning_rate": 2.8297746897146816e-07,
|
| 1321 |
+
"loss": 1.5728,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.9832999331997327,
|
| 1326 |
+
"grad_norm": 2.164794921875,
|
| 1327 |
+
"learning_rate": 1.5920769138706438e-07,
|
| 1328 |
+
"loss": 1.5844,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.9886439545758183,
|
| 1333 |
+
"grad_norm": 2.399670362472534,
|
| 1334 |
+
"learning_rate": 7.07694087889621e-08,
|
| 1335 |
+
"loss": 2.907,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.9939879759519038,
|
| 1340 |
+
"grad_norm": 3.2542049884796143,
|
| 1341 |
+
"learning_rate": 1.7693917570837936e-08,
|
| 1342 |
+
"loss": 3.2396,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.9993319973279893,
|
| 1347 |
+
"grad_norm": 6.379725933074951,
|
| 1348 |
+
"learning_rate": 0.0,
|
| 1349 |
+
"loss": 3.212,
|
| 1350 |
+
"step": 187
|
| 1351 |
}
|
| 1352 |
],
|
| 1353 |
"logging_steps": 1,
|
|
|
|
| 1362 |
"should_evaluate": false,
|
| 1363 |
"should_log": false,
|
| 1364 |
"should_save": true,
|
| 1365 |
+
"should_training_stop": true
|
| 1366 |
},
|
| 1367 |
"attributes": {}
|
| 1368 |
}
|
| 1369 |
},
|
| 1370 |
+
"total_flos": 1.5399356829637018e+17,
|
| 1371 |
"train_batch_size": 2,
|
| 1372 |
"trial_name": null,
|
| 1373 |
"trial_params": null
|