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 1163996488
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a76fe1fe1030d249d53b22e3cb8063c07e04cf2fcdf9c16a4e018b60c9eb047f
|
| 3 |
size 1163996488
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 325339796
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04760e90c195e321deb62652c3f04d76f8ccbf2fb9c817fa964dae1cc48a89ea
|
| 3 |
size 325339796
|
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:fab997b17c7546409b99b9b601362bc8cd304ece9f127b2ddf85ce81f2629d3a
|
| 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:a27b052646dcb561cbd68156c30bd466ce59bda64cf3c8eba9c3c1113af9827c
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 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": 13.348,
|
| 1090 |
"eval_steps_per_second": 3.339,
|
| 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": 2.
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.3843861818313599,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.1702127659574468,
|
| 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": 13.348,
|
| 1090 |
"eval_steps_per_second": 3.339,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.12851063829787235,
|
| 1095 |
+
"grad_norm": 0.2537207007408142,
|
| 1096 |
+
"learning_rate": 7.766164772035856e-06,
|
| 1097 |
+
"loss": 1.304,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.12936170212765957,
|
| 1102 |
+
"grad_norm": 0.28826025128364563,
|
| 1103 |
+
"learning_rate": 7.469080393187786e-06,
|
| 1104 |
+
"loss": 1.451,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.1302127659574468,
|
| 1109 |
+
"grad_norm": 0.2746778130531311,
|
| 1110 |
+
"learning_rate": 7.176788792715075e-06,
|
| 1111 |
+
"loss": 1.3594,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.13106382978723405,
|
| 1116 |
+
"grad_norm": 0.2970617711544037,
|
| 1117 |
+
"learning_rate": 6.889369880222776e-06,
|
| 1118 |
+
"loss": 1.4501,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.13191489361702127,
|
| 1123 |
+
"grad_norm": 0.2891596555709839,
|
| 1124 |
+
"learning_rate": 6.606902233171711e-06,
|
| 1125 |
+
"loss": 1.4122,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.1327659574468085,
|
| 1130 |
+
"grad_norm": 0.29369330406188965,
|
| 1131 |
+
"learning_rate": 6.329463075396161e-06,
|
| 1132 |
+
"loss": 1.3784,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.13361702127659575,
|
| 1137 |
+
"grad_norm": 0.3173155188560486,
|
| 1138 |
+
"learning_rate": 6.057128255991637e-06,
|
| 1139 |
+
"loss": 1.4809,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.13446808510638297,
|
| 1144 |
+
"grad_norm": 0.2837926745414734,
|
| 1145 |
+
"learning_rate": 5.78997222857853e-06,
|
| 1146 |
+
"loss": 1.3719,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.13531914893617022,
|
| 1151 |
+
"grad_norm": 0.30638885498046875,
|
| 1152 |
+
"learning_rate": 5.528068030947192e-06,
|
| 1153 |
+
"loss": 1.4337,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.13617021276595745,
|
| 1158 |
+
"grad_norm": 0.3034341037273407,
|
| 1159 |
+
"learning_rate": 5.271487265090163e-06,
|
| 1160 |
+
"loss": 1.4421,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.13702127659574467,
|
| 1165 |
+
"grad_norm": 0.29725155234336853,
|
| 1166 |
+
"learning_rate": 5.0203000776268825e-06,
|
| 1167 |
+
"loss": 1.3968,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.13787234042553193,
|
| 1172 |
+
"grad_norm": 0.30025699734687805,
|
| 1173 |
+
"learning_rate": 4.7745751406263165e-06,
|
| 1174 |
+
"loss": 1.3834,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.13872340425531915,
|
| 1179 |
+
"grad_norm": 0.3047562539577484,
|
| 1180 |
+
"learning_rate": 4.534379632832692e-06,
|
| 1181 |
+
"loss": 1.4626,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.13957446808510637,
|
| 1186 |
+
"grad_norm": 0.29557088017463684,
|
| 1187 |
+
"learning_rate": 4.299779221299499e-06,
|
| 1188 |
+
"loss": 1.3972,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.14042553191489363,
|
| 1193 |
+
"grad_norm": 0.3058943450450897,
|
| 1194 |
+
"learning_rate": 4.070838043436786e-06,
|
| 1195 |
+
"loss": 1.3504,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.14127659574468085,
|
| 1200 |
+
"grad_norm": 0.32091644406318665,
|
| 1201 |
+
"learning_rate": 3.847618689476612e-06,
|
| 1202 |
+
"loss": 1.3864,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.14212765957446807,
|
| 1207 |
+
"grad_norm": 0.311018168926239,
|
| 1208 |
+
"learning_rate": 3.630182185361522e-06,
|
| 1209 |
+
"loss": 1.3225,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.14297872340425533,
|
| 1214 |
+
"grad_norm": 0.31144842505455017,
|
| 1215 |
+
"learning_rate": 3.418587976060653e-06,
|
| 1216 |
+
"loss": 1.4291,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.14382978723404255,
|
| 1221 |
+
"grad_norm": 0.30693623423576355,
|
| 1222 |
+
"learning_rate": 3.2128939093180655e-06,
|
| 1223 |
+
"loss": 1.3712,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.14468085106382977,
|
| 1228 |
+
"grad_norm": 0.30709272623062134,
|
| 1229 |
+
"learning_rate": 3.013156219837776e-06,
|
| 1230 |
+
"loss": 1.3335,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.14553191489361703,
|
| 1235 |
+
"grad_norm": 0.30708351731300354,
|
| 1236 |
+
"learning_rate": 2.8194295139097048e-06,
|
| 1237 |
+
"loss": 1.406,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.14638297872340425,
|
| 1242 |
+
"grad_norm": 0.32202768325805664,
|
| 1243 |
+
"learning_rate": 2.6317667544809134e-06,
|
| 1244 |
+
"loss": 1.4079,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.1472340425531915,
|
| 1249 |
+
"grad_norm": 0.3314898610115051,
|
| 1250 |
+
"learning_rate": 2.4502192466760276e-06,
|
| 1251 |
+
"loss": 1.367,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.14808510638297873,
|
| 1256 |
+
"grad_norm": 0.33232441544532776,
|
| 1257 |
+
"learning_rate": 2.2748366237709374e-06,
|
| 1258 |
+
"loss": 1.3277,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.14893617021276595,
|
| 1263 |
+
"grad_norm": 0.32035085558891296,
|
| 1264 |
+
"learning_rate": 2.1056668336235622e-06,
|
| 1265 |
+
"loss": 1.3494,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.1497872340425532,
|
| 1270 |
+
"grad_norm": 0.3158108592033386,
|
| 1271 |
+
"learning_rate": 1.9427561255653816e-06,
|
| 1272 |
+
"loss": 1.3541,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.15063829787234043,
|
| 1277 |
+
"grad_norm": 0.330410897731781,
|
| 1278 |
+
"learning_rate": 1.7861490377573258e-06,
|
| 1279 |
+
"loss": 1.4584,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.15148936170212765,
|
| 1284 |
+
"grad_norm": 0.36304953694343567,
|
| 1285 |
+
"learning_rate": 1.6358883850134816e-06,
|
| 1286 |
+
"loss": 1.4689,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.1523404255319149,
|
| 1291 |
+
"grad_norm": 0.35465651750564575,
|
| 1292 |
+
"learning_rate": 1.4920152470959707e-06,
|
| 1293 |
+
"loss": 1.3506,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.15319148936170213,
|
| 1298 |
+
"grad_norm": 0.3566332459449768,
|
| 1299 |
+
"learning_rate": 1.3545689574841342e-06,
|
| 1300 |
+
"loss": 1.3957,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.15404255319148935,
|
| 1305 |
+
"grad_norm": 0.3480871617794037,
|
| 1306 |
+
"learning_rate": 1.2235870926211619e-06,
|
| 1307 |
+
"loss": 1.4867,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.1548936170212766,
|
| 1312 |
+
"grad_norm": 0.3515934944152832,
|
| 1313 |
+
"learning_rate": 1.0991054616410589e-06,
|
| 1314 |
+
"loss": 1.3693,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.15574468085106383,
|
| 1319 |
+
"grad_norm": 0.34942957758903503,
|
| 1320 |
+
"learning_rate": 9.811580965787965e-07,
|
| 1321 |
+
"loss": 1.4384,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.15659574468085105,
|
| 1326 |
+
"grad_norm": 0.3744766116142273,
|
| 1327 |
+
"learning_rate": 8.697772430662859e-07,
|
| 1328 |
+
"loss": 1.4282,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.1574468085106383,
|
| 1333 |
+
"grad_norm": 0.34389275312423706,
|
| 1334 |
+
"learning_rate": 7.649933515167407e-07,
|
| 1335 |
+
"loss": 1.4199,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.15829787234042553,
|
| 1340 |
+
"grad_norm": 0.3480643928050995,
|
| 1341 |
+
"learning_rate": 6.668350687998565e-07,
|
| 1342 |
+
"loss": 1.3923,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.15914893617021278,
|
| 1347 |
+
"grad_norm": 0.3493657112121582,
|
| 1348 |
+
"learning_rate": 5.753292304100183e-07,
|
| 1349 |
+
"loss": 1.4079,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.16,
|
| 1354 |
+
"grad_norm": 0.42659515142440796,
|
| 1355 |
+
"learning_rate": 4.905008531297661e-07,
|
| 1356 |
+
"loss": 1.3901,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.16085106382978723,
|
| 1361 |
+
"grad_norm": 0.3673100173473358,
|
| 1362 |
+
"learning_rate": 4.1237312819044085e-07,
|
| 1363 |
+
"loss": 1.3587,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.16170212765957448,
|
| 1368 |
+
"grad_norm": 0.3762143850326538,
|
| 1369 |
+
"learning_rate": 3.4096741493194197e-07,
|
| 1370 |
+
"loss": 1.3679,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.1625531914893617,
|
| 1375 |
+
"grad_norm": 0.36878857016563416,
|
| 1376 |
+
"learning_rate": 2.763032349632877e-07,
|
| 1377 |
+
"loss": 1.4606,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.16340425531914893,
|
| 1382 |
+
"grad_norm": 0.3533831536769867,
|
| 1383 |
+
"learning_rate": 2.1839826682562015e-07,
|
| 1384 |
+
"loss": 1.3743,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.16425531914893618,
|
| 1389 |
+
"grad_norm": 0.394137978553772,
|
| 1390 |
+
"learning_rate": 1.6726834115904643e-07,
|
| 1391 |
+
"loss": 1.3469,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.1651063829787234,
|
| 1396 |
+
"grad_norm": 0.3752601146697998,
|
| 1397 |
+
"learning_rate": 1.229274363747146e-07,
|
| 1398 |
+
"loss": 1.3896,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.16595744680851063,
|
| 1403 |
+
"grad_norm": 0.3760836720466614,
|
| 1404 |
+
"learning_rate": 8.538767483325383e-08,
|
| 1405 |
+
"loss": 1.3445,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.16680851063829788,
|
| 1410 |
+
"grad_norm": 0.38596341013908386,
|
| 1411 |
+
"learning_rate": 5.4659319530636633e-08,
|
| 1412 |
+
"loss": 1.4105,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.1676595744680851,
|
| 1417 |
+
"grad_norm": 0.38076484203338623,
|
| 1418 |
+
"learning_rate": 3.075077129238158e-08,
|
| 1419 |
+
"loss": 1.4032,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.16851063829787233,
|
| 1424 |
+
"grad_norm": 0.39466235041618347,
|
| 1425 |
+
"learning_rate": 1.3668566476848777e-08,
|
| 1426 |
+
"loss": 1.4423,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.16936170212765958,
|
| 1431 |
+
"grad_norm": 0.41375836730003357,
|
| 1432 |
+
"learning_rate": 3.417375188274896e-09,
|
| 1433 |
+
"loss": 1.3847,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.1702127659574468,
|
| 1438 |
+
"grad_norm": 0.6114789843559265,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 1.3281,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.1702127659574468,
|
| 1445 |
+
"eval_loss": 1.3843861818313599,
|
| 1446 |
+
"eval_runtime": 148.2016,
|
| 1447 |
+
"eval_samples_per_second": 13.353,
|
| 1448 |
+
"eval_steps_per_second": 3.34,
|
| 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": 2.66764564203307e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|