Training in progress, step 200, 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 100966336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eeb71cd68250608ae9fffa432d2b2618fa202c7924928aa2dc3fa4022ddac709
|
| 3 |
size 100966336
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 51613348
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b56082a625f0001b647008df6273fedc162620bb88a0da77fcc075dcd0c4fd8a
|
| 3 |
size 51613348
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e376eda23fe433e5fb0e407d717497f0b5408188bbf55341a3b796509c362cc3
|
| 3 |
size 14244
|
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:b60d6f1383abda4776549360effee800fe6cfe2c0604503e9e3fbaa79347f790
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1089,6 +1089,364 @@
|
|
| 1089 |
"eval_samples_per_second": 32.496,
|
| 1090 |
"eval_steps_per_second": 8.132,
|
| 1091 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
@@ -1112,12 +1470,12 @@
|
|
| 1112 |
"should_evaluate": false,
|
| 1113 |
"should_log": false,
|
| 1114 |
"should_save": true,
|
| 1115 |
-
"should_training_stop":
|
| 1116 |
},
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
-
"total_flos":
|
| 1121 |
"train_batch_size": 4,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8386966586112976,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.10933442667760011,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1089 |
"eval_samples_per_second": 32.496,
|
| 1090 |
"eval_steps_per_second": 8.132,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.08254749214158809,
|
| 1095 |
+
"grad_norm": 0.21387195587158203,
|
| 1096 |
+
"learning_rate": 1.339526225485725e-05,
|
| 1097 |
+
"loss": 0.5987,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.08309416427497608,
|
| 1102 |
+
"grad_norm": 0.21969622373580933,
|
| 1103 |
+
"learning_rate": 1.2890114781136224e-05,
|
| 1104 |
+
"loss": 0.701,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.08364083640836409,
|
| 1109 |
+
"grad_norm": 0.23904825747013092,
|
| 1110 |
+
"learning_rate": 1.239251781296245e-05,
|
| 1111 |
+
"loss": 0.7627,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.08418750854175208,
|
| 1116 |
+
"grad_norm": 0.25487756729125977,
|
| 1117 |
+
"learning_rate": 1.1902641279244715e-05,
|
| 1118 |
+
"loss": 0.7506,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.08473418067514009,
|
| 1123 |
+
"grad_norm": 0.2533106207847595,
|
| 1124 |
+
"learning_rate": 1.1420652472370497e-05,
|
| 1125 |
+
"loss": 0.7238,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.08528085280852808,
|
| 1130 |
+
"grad_norm": 0.2788962423801422,
|
| 1131 |
+
"learning_rate": 1.0946715991075805e-05,
|
| 1132 |
+
"loss": 0.8004,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.08582752494191609,
|
| 1137 |
+
"grad_norm": 0.2542433738708496,
|
| 1138 |
+
"learning_rate": 1.0480993684234815e-05,
|
| 1139 |
+
"loss": 0.7999,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.08637419707530408,
|
| 1144 |
+
"grad_norm": 0.2701437175273895,
|
| 1145 |
+
"learning_rate": 1.0023644595588671e-05,
|
| 1146 |
+
"loss": 0.7623,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.08692086920869209,
|
| 1151 |
+
"grad_norm": 0.2716737389564514,
|
| 1152 |
+
"learning_rate": 9.57482490943216e-06,
|
| 1153 |
+
"loss": 0.8127,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.08746754134208008,
|
| 1158 |
+
"grad_norm": 0.28511807322502136,
|
| 1159 |
+
"learning_rate": 9.134687897276934e-06,
|
| 1160 |
+
"loss": 0.8619,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.08801421347546809,
|
| 1165 |
+
"grad_norm": 0.32100751996040344,
|
| 1166 |
+
"learning_rate": 8.703383865509432e-06,
|
| 1167 |
+
"loss": 0.8368,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.08856088560885608,
|
| 1172 |
+
"grad_norm": 0.27488431334495544,
|
| 1173 |
+
"learning_rate": 8.281060104061394e-06,
|
| 1174 |
+
"loss": 0.7795,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.08910755774224409,
|
| 1179 |
+
"grad_norm": 0.2900071442127228,
|
| 1180 |
+
"learning_rate": 7.867860836110453e-06,
|
| 1181 |
+
"loss": 0.8229,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.0896542298756321,
|
| 1186 |
+
"grad_norm": 0.3044150471687317,
|
| 1187 |
+
"learning_rate": 7.463927168828087e-06,
|
| 1188 |
+
"loss": 0.8705,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.09020090200902009,
|
| 1193 |
+
"grad_norm": 0.34009850025177,
|
| 1194 |
+
"learning_rate": 7.069397045191617e-06,
|
| 1195 |
+
"loss": 0.9019,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.0907475741424081,
|
| 1200 |
+
"grad_norm": 0.33406728506088257,
|
| 1201 |
+
"learning_rate": 6.684405196876842e-06,
|
| 1202 |
+
"loss": 0.7769,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.09129424627579609,
|
| 1207 |
+
"grad_norm": 0.35519149899482727,
|
| 1208 |
+
"learning_rate": 6.309083098247264e-06,
|
| 1209 |
+
"loss": 0.8062,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.0918409184091841,
|
| 1214 |
+
"grad_norm": 0.33212265372276306,
|
| 1215 |
+
"learning_rate": 5.943558921455733e-06,
|
| 1216 |
+
"loss": 0.7822,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.09238759054257209,
|
| 1221 |
+
"grad_norm": 0.3488451838493347,
|
| 1222 |
+
"learning_rate": 5.587957492673759e-06,
|
| 1223 |
+
"loss": 0.7944,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.0929342626759601,
|
| 1228 |
+
"grad_norm": 0.4000808298587799,
|
| 1229 |
+
"learning_rate": 5.2424002494635095e-06,
|
| 1230 |
+
"loss": 0.823,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.09348093480934809,
|
| 1235 |
+
"grad_norm": 0.37309879064559937,
|
| 1236 |
+
"learning_rate": 4.9070051993069636e-06,
|
| 1237 |
+
"loss": 0.8506,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.0940276069427361,
|
| 1242 |
+
"grad_norm": 0.3660164773464203,
|
| 1243 |
+
"learning_rate": 4.581886879306507e-06,
|
| 1244 |
+
"loss": 0.8042,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.09457427907612409,
|
| 1249 |
+
"grad_norm": 0.389154851436615,
|
| 1250 |
+
"learning_rate": 4.2671563170705725e-06,
|
| 1251 |
+
"loss": 0.9166,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.0951209512095121,
|
| 1256 |
+
"grad_norm": 0.3975100815296173,
|
| 1257 |
+
"learning_rate": 3.962920992797834e-06,
|
| 1258 |
+
"loss": 0.7654,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.09566762334290009,
|
| 1263 |
+
"grad_norm": 0.4443868100643158,
|
| 1264 |
+
"learning_rate": 3.6692848025728216e-06,
|
| 1265 |
+
"loss": 0.8351,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.0962142954762881,
|
| 1270 |
+
"grad_norm": 0.4617209732532501,
|
| 1271 |
+
"learning_rate": 3.38634802288549e-06,
|
| 1272 |
+
"loss": 0.8746,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.09676096760967609,
|
| 1277 |
+
"grad_norm": 0.4271644651889801,
|
| 1278 |
+
"learning_rate": 3.1142072763869042e-06,
|
| 1279 |
+
"loss": 0.7862,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.0973076397430641,
|
| 1284 |
+
"grad_norm": 0.5230273604393005,
|
| 1285 |
+
"learning_rate": 2.852955498892694e-06,
|
| 1286 |
+
"loss": 0.7907,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.0978543118764521,
|
| 1291 |
+
"grad_norm": 0.49080246686935425,
|
| 1292 |
+
"learning_rate": 2.6026819076455325e-06,
|
| 1293 |
+
"loss": 0.8707,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.0984009840098401,
|
| 1298 |
+
"grad_norm": 0.524896502494812,
|
| 1299 |
+
"learning_rate": 2.36347197084755e-06,
|
| 1300 |
+
"loss": 0.8869,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.0989476561432281,
|
| 1305 |
+
"grad_norm": 0.5297053456306458,
|
| 1306 |
+
"learning_rate": 2.1354073784730253e-06,
|
| 1307 |
+
"loss": 0.855,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.0994943282766161,
|
| 1312 |
+
"grad_norm": 0.6338819265365601,
|
| 1313 |
+
"learning_rate": 1.9185660143713184e-06,
|
| 1314 |
+
"loss": 1.0045,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.1000410004100041,
|
| 1319 |
+
"grad_norm": 0.6989834308624268,
|
| 1320 |
+
"learning_rate": 1.7130219296696263e-06,
|
| 1321 |
+
"loss": 0.9497,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.1005876725433921,
|
| 1326 |
+
"grad_norm": 0.602967381477356,
|
| 1327 |
+
"learning_rate": 1.5188453174845743e-06,
|
| 1328 |
+
"loss": 0.8483,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.1011343446767801,
|
| 1333 |
+
"grad_norm": 0.7088273763656616,
|
| 1334 |
+
"learning_rate": 1.3361024889513333e-06,
|
| 1335 |
+
"loss": 0.846,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.1016810168101681,
|
| 1340 |
+
"grad_norm": 0.7697593569755554,
|
| 1341 |
+
"learning_rate": 1.16485585057844e-06,
|
| 1342 |
+
"loss": 0.9718,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.1022276889435561,
|
| 1347 |
+
"grad_norm": 0.6648566722869873,
|
| 1348 |
+
"learning_rate": 1.0051638829360127e-06,
|
| 1349 |
+
"loss": 0.9544,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.1027743610769441,
|
| 1354 |
+
"grad_norm": 0.8641712069511414,
|
| 1355 |
+
"learning_rate": 8.570811206847189e-07,
|
| 1356 |
+
"loss": 0.9615,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.1033210332103321,
|
| 1361 |
+
"grad_norm": 0.8209101557731628,
|
| 1362 |
+
"learning_rate": 7.206581339521939e-07,
|
| 1363 |
+
"loss": 0.9253,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.1038677053437201,
|
| 1368 |
+
"grad_norm": 0.7885981202125549,
|
| 1369 |
+
"learning_rate": 5.959415110634375e-07,
|
| 1370 |
+
"loss": 0.9993,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.1044143774771081,
|
| 1375 |
+
"grad_norm": 0.8673349022865295,
|
| 1376 |
+
"learning_rate": 4.829738426309099e-07,
|
| 1377 |
+
"loss": 0.8788,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.1049610496104961,
|
| 1382 |
+
"grad_norm": 1.1715073585510254,
|
| 1383 |
+
"learning_rate": 3.817937070098914e-07,
|
| 1384 |
+
"loss": 0.9042,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.1055077217438841,
|
| 1389 |
+
"grad_norm": 0.8940293192863464,
|
| 1390 |
+
"learning_rate": 2.9243565712400384e-07,
|
| 1391 |
+
"loss": 0.9155,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.10605439387727211,
|
| 1396 |
+
"grad_norm": 1.1870354413986206,
|
| 1397 |
+
"learning_rate": 2.1493020866542365e-07,
|
| 1398 |
+
"loss": 0.7754,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.1066010660106601,
|
| 1403 |
+
"grad_norm": 1.0665806531906128,
|
| 1404 |
+
"learning_rate": 1.4930382967379363e-07,
|
| 1405 |
+
"loss": 0.7945,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.10714773814404811,
|
| 1410 |
+
"grad_norm": 1.1132820844650269,
|
| 1411 |
+
"learning_rate": 9.557893149741924e-08,
|
| 1412 |
+
"loss": 0.8022,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.1076944102774361,
|
| 1417 |
+
"grad_norm": 1.1399116516113281,
|
| 1418 |
+
"learning_rate": 5.377386113981197e-08,
|
| 1419 |
+
"loss": 0.7458,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.10824108241082411,
|
| 1424 |
+
"grad_norm": 1.4629731178283691,
|
| 1425 |
+
"learning_rate": 2.3902894994198286e-08,
|
| 1426 |
+
"loss": 0.8933,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.1087877545442121,
|
| 1431 |
+
"grad_norm": 2.013901710510254,
|
| 1432 |
+
"learning_rate": 5.976233968155164e-09,
|
| 1433 |
+
"loss": 1.116,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.10933442667760011,
|
| 1438 |
+
"grad_norm": 2.5633609294891357,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.9893,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.10933442667760011,
|
| 1445 |
+
"eval_loss": 0.8386966586112976,
|
| 1446 |
+
"eval_runtime": 94.776,
|
| 1447 |
+
"eval_samples_per_second": 32.508,
|
| 1448 |
+
"eval_steps_per_second": 8.135,
|
| 1449 |
+
"step": 200
|
| 1450 |
}
|
| 1451 |
],
|
| 1452 |
"logging_steps": 1,
|
|
|
|
| 1470 |
"should_evaluate": false,
|
| 1471 |
"should_log": false,
|
| 1472 |
"should_save": true,
|
| 1473 |
+
"should_training_stop": true
|
| 1474 |
},
|
| 1475 |
"attributes": {}
|
| 1476 |
}
|
| 1477 |
},
|
| 1478 |
+
"total_flos": 5.813079334767821e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|