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 479005064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1aa4ef5ac1f98f09ef1661af5b6e8cc54abde8931a06ff3e4f9c52a3ef43c6d
|
| 3 |
size 479005064
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 243802484
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:741430405159cd87ce3fdcdc0ce6ab889f1063931b0bd46504db77baf1e07940
|
| 3 |
size 243802484
|
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 sha256:95e164db2df0e6c7a8d53d754342c4b79b96c43d67ec9389a3353770808b2b47
|
| 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:c09a3e270daa077e38bac4ad605b0e6c9b43938bcf49dc3d62c3671f11248c14
|
| 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": 20.394,
|
| 1090 |
"eval_steps_per_second": 5.098,
|
| 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": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.0010981361847370863,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.1548586914440573,
|
| 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": 20.394,
|
| 1090 |
"eval_steps_per_second": 5.098,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.11691831204026326,
|
| 1095 |
+
"grad_norm": 8.589386940002441,
|
| 1096 |
+
"learning_rate": 1.397909658966454e-05,
|
| 1097 |
+
"loss": 0.0052,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.11769260549748355,
|
| 1102 |
+
"grad_norm": 0.01945851743221283,
|
| 1103 |
+
"learning_rate": 1.3444344707738015e-05,
|
| 1104 |
+
"loss": 0.0006,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.11846689895470383,
|
| 1109 |
+
"grad_norm": 0.7007508277893066,
|
| 1110 |
+
"learning_rate": 1.2918219826887136e-05,
|
| 1111 |
+
"loss": 0.0015,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.11924119241192412,
|
| 1116 |
+
"grad_norm": 37.36264419555664,
|
| 1117 |
+
"learning_rate": 1.2400865784400998e-05,
|
| 1118 |
+
"loss": 0.0022,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.1200154858691444,
|
| 1123 |
+
"grad_norm": 1.3579168319702148,
|
| 1124 |
+
"learning_rate": 1.189242401970908e-05,
|
| 1125 |
+
"loss": 0.002,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.1207897793263647,
|
| 1130 |
+
"grad_norm": 0.004012103192508221,
|
| 1131 |
+
"learning_rate": 1.139303353571309e-05,
|
| 1132 |
+
"loss": 0.0001,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.12156407278358498,
|
| 1137 |
+
"grad_norm": 0.07467560470104218,
|
| 1138 |
+
"learning_rate": 1.0902830860784946e-05,
|
| 1139 |
+
"loss": 0.0019,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.12233836624080527,
|
| 1144 |
+
"grad_norm": 0.0046264780685305595,
|
| 1145 |
+
"learning_rate": 1.0421950011441355e-05,
|
| 1146 |
+
"loss": 0.0001,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.12311265969802555,
|
| 1151 |
+
"grad_norm": 0.0015560417668893933,
|
| 1152 |
+
"learning_rate": 9.950522455704946e-06,
|
| 1153 |
+
"loss": 0.0,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.12388695315524584,
|
| 1158 |
+
"grad_norm": 0.0010828773956745863,
|
| 1159 |
+
"learning_rate": 9.488677077162294e-06,
|
| 1160 |
+
"loss": 0.0,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.12466124661246612,
|
| 1165 |
+
"grad_norm": 0.0019125222461298108,
|
| 1166 |
+
"learning_rate": 9.03654013972839e-06,
|
| 1167 |
+
"loss": 0.0001,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.1254355400696864,
|
| 1172 |
+
"grad_norm": 0.11289074271917343,
|
| 1173 |
+
"learning_rate": 8.59423525312737e-06,
|
| 1174 |
+
"loss": 0.0034,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.1262098335269067,
|
| 1179 |
+
"grad_norm": 0.0018281425582244992,
|
| 1180 |
+
"learning_rate": 8.161883339098845e-06,
|
| 1181 |
+
"loss": 0.0,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.12698412698412698,
|
| 1186 |
+
"grad_norm": 0.0015775542706251144,
|
| 1187 |
+
"learning_rate": 7.739602598339099e-06,
|
| 1188 |
+
"loss": 0.0,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.12775842044134728,
|
| 1193 |
+
"grad_norm": 0.0017349289264529943,
|
| 1194 |
+
"learning_rate": 7.327508478186216e-06,
|
| 1195 |
+
"loss": 0.0,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.12853271389856755,
|
| 1200 |
+
"grad_norm": 0.04309145361185074,
|
| 1201 |
+
"learning_rate": 6.925713641057902e-06,
|
| 1202 |
+
"loss": 0.0008,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.12930700735578785,
|
| 1207 |
+
"grad_norm": 0.0019816451240330935,
|
| 1208 |
+
"learning_rate": 6.53432793365074e-06,
|
| 1209 |
+
"loss": 0.0,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.13008130081300814,
|
| 1214 |
+
"grad_norm": 0.06418117135763168,
|
| 1215 |
+
"learning_rate": 6.153458356909174e-06,
|
| 1216 |
+
"loss": 0.0005,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.13085559427022841,
|
| 1221 |
+
"grad_norm": 0.017173679545521736,
|
| 1222 |
+
"learning_rate": 5.783209036772518e-06,
|
| 1223 |
+
"loss": 0.0002,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.1316298877274487,
|
| 1228 |
+
"grad_norm": 0.11571363359689713,
|
| 1229 |
+
"learning_rate": 5.423681195707997e-06,
|
| 1230 |
+
"loss": 0.0005,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.13240418118466898,
|
| 1235 |
+
"grad_norm": 0.0009111211984418333,
|
| 1236 |
+
"learning_rate": 5.074973125037469e-06,
|
| 1237 |
+
"loss": 0.0,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.13317847464188928,
|
| 1242 |
+
"grad_norm": 0.06231530383229256,
|
| 1243 |
+
"learning_rate": 4.737180158065644e-06,
|
| 1244 |
+
"loss": 0.0005,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.13395276809910955,
|
| 1249 |
+
"grad_norm": 0.0028604816179722548,
|
| 1250 |
+
"learning_rate": 4.41039464401685e-06,
|
| 1251 |
+
"loss": 0.0001,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.13472706155632985,
|
| 1256 |
+
"grad_norm": 0.00407991511747241,
|
| 1257 |
+
"learning_rate": 4.094705922787687e-06,
|
| 1258 |
+
"loss": 0.0001,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.13550135501355012,
|
| 1263 |
+
"grad_norm": 0.012540704570710659,
|
| 1264 |
+
"learning_rate": 3.7902003005224126e-06,
|
| 1265 |
+
"loss": 0.0001,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.13627564847077042,
|
| 1270 |
+
"grad_norm": 0.040631502866744995,
|
| 1271 |
+
"learning_rate": 3.4969610260176865e-06,
|
| 1272 |
+
"loss": 0.0002,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.13704994192799072,
|
| 1277 |
+
"grad_norm": 0.0855015367269516,
|
| 1278 |
+
"learning_rate": 3.2150682679631867e-06,
|
| 1279 |
+
"loss": 0.0041,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.137824235385211,
|
| 1284 |
+
"grad_norm": 0.002300119958817959,
|
| 1285 |
+
"learning_rate": 2.9445990930242668e-06,
|
| 1286 |
+
"loss": 0.0001,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.1385985288424313,
|
| 1291 |
+
"grad_norm": 0.004780174233019352,
|
| 1292 |
+
"learning_rate": 2.6856274447727475e-06,
|
| 1293 |
+
"loss": 0.0001,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.13937282229965156,
|
| 1298 |
+
"grad_norm": 0.02303953841328621,
|
| 1299 |
+
"learning_rate": 2.4382241234714413e-06,
|
| 1300 |
+
"loss": 0.0003,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.14014711575687186,
|
| 1305 |
+
"grad_norm": 0.021668056026101112,
|
| 1306 |
+
"learning_rate": 2.2024567667180914e-06,
|
| 1307 |
+
"loss": 0.0003,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.14092140921409213,
|
| 1312 |
+
"grad_norm": 0.010320520959794521,
|
| 1313 |
+
"learning_rate": 1.978389830953906e-06,
|
| 1314 |
+
"loss": 0.0002,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.14169570267131243,
|
| 1319 |
+
"grad_norm": 0.00375885097309947,
|
| 1320 |
+
"learning_rate": 1.7660845738418336e-06,
|
| 1321 |
+
"loss": 0.0001,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.14246999612853273,
|
| 1326 |
+
"grad_norm": 0.13294894993305206,
|
| 1327 |
+
"learning_rate": 1.5655990375193147e-06,
|
| 1328 |
+
"loss": 0.0009,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.143244289585753,
|
| 1333 |
+
"grad_norm": 0.12707974016666412,
|
| 1334 |
+
"learning_rate": 1.3769880327301332e-06,
|
| 1335 |
+
"loss": 0.0093,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.1440185830429733,
|
| 1340 |
+
"grad_norm": 0.0048987469635903835,
|
| 1341 |
+
"learning_rate": 1.2003031238397417e-06,
|
| 1342 |
+
"loss": 0.0001,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.14479287650019357,
|
| 1347 |
+
"grad_norm": 0.0014035734347999096,
|
| 1348 |
+
"learning_rate": 1.035592614738033e-06,
|
| 1349 |
+
"loss": 0.0,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.14556716995741387,
|
| 1354 |
+
"grad_norm": 0.001624911092221737,
|
| 1355 |
+
"learning_rate": 8.829015356335791e-07,
|
| 1356 |
+
"loss": 0.0,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.14634146341463414,
|
| 1361 |
+
"grad_norm": 0.004533092956990004,
|
| 1362 |
+
"learning_rate": 7.422716307427936e-07,
|
| 1363 |
+
"loss": 0.0001,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.14711575687185444,
|
| 1368 |
+
"grad_norm": 0.0016615334898233414,
|
| 1369 |
+
"learning_rate": 6.137413468774955e-07,
|
| 1370 |
+
"loss": 0.0,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.1478900503290747,
|
| 1375 |
+
"grad_norm": 0.00272984872572124,
|
| 1376 |
+
"learning_rate": 4.973458229339179e-07,
|
| 1377 |
+
"loss": 0.0001,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.148664343786295,
|
| 1382 |
+
"grad_norm": 0.08710943907499313,
|
| 1383 |
+
"learning_rate": 3.9311688028611627e-07,
|
| 1384 |
+
"loss": 0.0005,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.1494386372435153,
|
| 1389 |
+
"grad_norm": 0.005952900741249323,
|
| 1390 |
+
"learning_rate": 3.010830140862836e-07,
|
| 1391 |
+
"loss": 0.0001,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.15021293070073558,
|
| 1396 |
+
"grad_norm": 0.004029720555990934,
|
| 1397 |
+
"learning_rate": 2.2126938547448627e-07,
|
| 1398 |
+
"loss": 0.0001,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.15098722415795587,
|
| 1403 |
+
"grad_norm": 0.0068871923722326756,
|
| 1404 |
+
"learning_rate": 1.536978146998569e-07,
|
| 1405 |
+
"loss": 0.0001,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.15176151761517614,
|
| 1410 |
+
"grad_norm": 0.0033995830453932285,
|
| 1411 |
+
"learning_rate": 9.838677515514594e-08,
|
| 1412 |
+
"loss": 0.0001,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.15253581107239644,
|
| 1417 |
+
"grad_norm": 0.004005973227322102,
|
| 1418 |
+
"learning_rate": 5.5351388326286834e-08,
|
| 1419 |
+
"loss": 0.0001,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.15331010452961671,
|
| 1424 |
+
"grad_norm": 0.03095901943743229,
|
| 1425 |
+
"learning_rate": 2.4603419658327797e-08,
|
| 1426 |
+
"loss": 0.0004,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.154084397986837,
|
| 1431 |
+
"grad_norm": 0.0032219612039625645,
|
| 1432 |
+
"learning_rate": 6.151275338894813e-09,
|
| 1433 |
+
"loss": 0.0001,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.1548586914440573,
|
| 1438 |
+
"grad_norm": 0.0060548316687345505,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.0001,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.1548586914440573,
|
| 1445 |
+
"eval_loss": 0.0010981361847370863,
|
| 1446 |
+
"eval_runtime": 106.6826,
|
| 1447 |
+
"eval_samples_per_second": 20.397,
|
| 1448 |
+
"eval_steps_per_second": 5.099,
|
| 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": 1.1865389622991258e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|