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 671149168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f048cdaacc70528553343d16927eb99c20df78c1123cf38abe30d7b740463de
|
| 3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 341314196
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b789c38c5fae0b1af38386b347d5de5e5ae1e72ebc7f4b366b230918441266f3
|
| 3 |
size 341314196
|
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:fd9faf78cbf232ca994119816a1ac4497890611e2c86ba30946298b6b1260643
|
| 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": 2.
|
| 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": 13.854,
|
| 1090 |
"eval_steps_per_second": 3.468,
|
| 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": 2.635521650314331,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.1522359657469077,
|
| 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": 13.854,
|
| 1090 |
"eval_steps_per_second": 3.468,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.11493815413891532,
|
| 1095 |
+
"grad_norm": 18.445619583129883,
|
| 1096 |
+
"learning_rate": 1.0872630680850196e-05,
|
| 1097 |
+
"loss": 11.3742,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.11569933396764985,
|
| 1102 |
+
"grad_norm": 21.48427391052246,
|
| 1103 |
+
"learning_rate": 1.0456712550462898e-05,
|
| 1104 |
+
"loss": 11.9775,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.11646051379638439,
|
| 1109 |
+
"grad_norm": 21.330692291259766,
|
| 1110 |
+
"learning_rate": 1.0047504309801104e-05,
|
| 1111 |
+
"loss": 12.024,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.11722169362511893,
|
| 1116 |
+
"grad_norm": 20.090660095214844,
|
| 1117 |
+
"learning_rate": 9.645117832311886e-06,
|
| 1118 |
+
"loss": 12.4892,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.11798287345385347,
|
| 1123 |
+
"grad_norm": 18.429834365844727,
|
| 1124 |
+
"learning_rate": 9.249663126440394e-06,
|
| 1125 |
+
"loss": 11.9891,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.11874405328258801,
|
| 1130 |
+
"grad_norm": 17.47442626953125,
|
| 1131 |
+
"learning_rate": 8.861248305554624e-06,
|
| 1132 |
+
"loss": 11.7054,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.11950523311132255,
|
| 1137 |
+
"grad_norm": 16.98632049560547,
|
| 1138 |
+
"learning_rate": 8.47997955838829e-06,
|
| 1139 |
+
"loss": 11.6384,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.12026641294005709,
|
| 1144 |
+
"grad_norm": 14.138599395751953,
|
| 1145 |
+
"learning_rate": 8.10596112000994e-06,
|
| 1146 |
+
"loss": 11.0114,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.12102759276879163,
|
| 1151 |
+
"grad_norm": 14.644400596618652,
|
| 1152 |
+
"learning_rate": 7.739295243326067e-06,
|
| 1153 |
+
"loss": 11.1902,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.12178877259752617,
|
| 1158 |
+
"grad_norm": 13.44913387298584,
|
| 1159 |
+
"learning_rate": 7.380082171126228e-06,
|
| 1160 |
+
"loss": 10.9967,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.12254995242626071,
|
| 1165 |
+
"grad_norm": 12.572880744934082,
|
| 1166 |
+
"learning_rate": 7.028420108677635e-06,
|
| 1167 |
+
"loss": 11.2954,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.12331113225499524,
|
| 1172 |
+
"grad_norm": 13.983728408813477,
|
| 1173 |
+
"learning_rate": 6.684405196876842e-06,
|
| 1174 |
+
"loss": 11.0568,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.12407231208372978,
|
| 1179 |
+
"grad_norm": 11.860404014587402,
|
| 1180 |
+
"learning_rate": 6.3481314859657675e-06,
|
| 1181 |
+
"loss": 11.3495,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.12483349191246432,
|
| 1186 |
+
"grad_norm": 12.377447128295898,
|
| 1187 |
+
"learning_rate": 6.019690909819298e-06,
|
| 1188 |
+
"loss": 11.55,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.12559467174119887,
|
| 1193 |
+
"grad_norm": 11.578761100769043,
|
| 1194 |
+
"learning_rate": 5.6991732608115e-06,
|
| 1195 |
+
"loss": 10.1674,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.1263558515699334,
|
| 1200 |
+
"grad_norm": 11.848546028137207,
|
| 1201 |
+
"learning_rate": 5.386666165267256e-06,
|
| 1202 |
+
"loss": 11.0913,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.12711703139866792,
|
| 1207 |
+
"grad_norm": 13.63163948059082,
|
| 1208 |
+
"learning_rate": 5.08225505950613e-06,
|
| 1209 |
+
"loss": 10.3754,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.12787821122740248,
|
| 1214 |
+
"grad_norm": 13.617592811584473,
|
| 1215 |
+
"learning_rate": 4.786023166484913e-06,
|
| 1216 |
+
"loss": 10.5325,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.128639391056137,
|
| 1221 |
+
"grad_norm": 15.02790641784668,
|
| 1222 |
+
"learning_rate": 4.498051473045291e-06,
|
| 1223 |
+
"loss": 10.9382,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.12940057088487156,
|
| 1228 |
+
"grad_norm": 14.189635276794434,
|
| 1229 |
+
"learning_rate": 4.218418707772886e-06,
|
| 1230 |
+
"loss": 10.5574,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.13016175071360608,
|
| 1235 |
+
"grad_norm": 13.499348640441895,
|
| 1236 |
+
"learning_rate": 3.947201319473587e-06,
|
| 1237 |
+
"loss": 10.9327,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.13092293054234064,
|
| 1242 |
+
"grad_norm": 12.799763679504395,
|
| 1243 |
+
"learning_rate": 3.684473456273278e-06,
|
| 1244 |
+
"loss": 11.1223,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.13168411037107516,
|
| 1249 |
+
"grad_norm": 14.828266143798828,
|
| 1250 |
+
"learning_rate": 3.4303069453464383e-06,
|
| 1251 |
+
"loss": 11.1267,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.13244529019980972,
|
| 1256 |
+
"grad_norm": 14.301188468933105,
|
| 1257 |
+
"learning_rate": 3.184771273279312e-06,
|
| 1258 |
+
"loss": 10.4515,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.13320647002854424,
|
| 1263 |
+
"grad_norm": 14.4749174118042,
|
| 1264 |
+
"learning_rate": 2.947933567072987e-06,
|
| 1265 |
+
"loss": 11.573,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.13396764985727877,
|
| 1270 |
+
"grad_norm": 13.420093536376953,
|
| 1271 |
+
"learning_rate": 2.719858575791534e-06,
|
| 1272 |
+
"loss": 10.6497,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.13472882968601332,
|
| 1277 |
+
"grad_norm": 14.698240280151367,
|
| 1278 |
+
"learning_rate": 2.500608652860256e-06,
|
| 1279 |
+
"loss": 11.0862,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.13549000951474785,
|
| 1284 |
+
"grad_norm": 12.239655494689941,
|
| 1285 |
+
"learning_rate": 2.2902437390188737e-06,
|
| 1286 |
+
"loss": 10.2693,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.1362511893434824,
|
| 1291 |
+
"grad_norm": 12.892120361328125,
|
| 1292 |
+
"learning_rate": 2.0888213459343587e-06,
|
| 1293 |
+
"loss": 10.5389,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.13701236917221693,
|
| 1298 |
+
"grad_norm": 13.470686912536621,
|
| 1299 |
+
"learning_rate": 1.8963965404777875e-06,
|
| 1300 |
+
"loss": 10.4803,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.13777354900095148,
|
| 1305 |
+
"grad_norm": 12.984949111938477,
|
| 1306 |
+
"learning_rate": 1.7130219296696263e-06,
|
| 1307 |
+
"loss": 9.6088,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.138534728829686,
|
| 1312 |
+
"grad_norm": 13.808255195617676,
|
| 1313 |
+
"learning_rate": 1.5387476462974824e-06,
|
| 1314 |
+
"loss": 11.1268,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.13929590865842056,
|
| 1319 |
+
"grad_norm": 12.773662567138672,
|
| 1320 |
+
"learning_rate": 1.3736213352103147e-06,
|
| 1321 |
+
"loss": 9.9075,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.1400570884871551,
|
| 1326 |
+
"grad_norm": 13.793781280517578,
|
| 1327 |
+
"learning_rate": 1.2176881402928002e-06,
|
| 1328 |
+
"loss": 10.2555,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.14081826831588962,
|
| 1333 |
+
"grad_norm": 14.847312927246094,
|
| 1334 |
+
"learning_rate": 1.0709906921234367e-06,
|
| 1335 |
+
"loss": 10.6056,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.14157944814462417,
|
| 1340 |
+
"grad_norm": 14.904285430908203,
|
| 1341 |
+
"learning_rate": 9.33569096319799e-07,
|
| 1342 |
+
"loss": 10.547,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.1423406279733587,
|
| 1347 |
+
"grad_norm": 15.246833801269531,
|
| 1348 |
+
"learning_rate": 8.054609225740255e-07,
|
| 1349 |
+
"loss": 10.4182,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.14310180780209325,
|
| 1354 |
+
"grad_norm": 14.685139656066895,
|
| 1355 |
+
"learning_rate": 6.867011943816724e-07,
|
| 1356 |
+
"loss": 10.7205,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.14386298763082778,
|
| 1361 |
+
"grad_norm": 16.769256591796875,
|
| 1362 |
+
"learning_rate": 5.77322379466617e-07,
|
| 1363 |
+
"loss": 10.3121,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.14462416745956233,
|
| 1368 |
+
"grad_norm": 14.956713676452637,
|
| 1369 |
+
"learning_rate": 4.773543809047186e-07,
|
| 1370 |
+
"loss": 9.7691,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.14538534728829686,
|
| 1375 |
+
"grad_norm": 16.237415313720703,
|
| 1376 |
+
"learning_rate": 3.868245289486027e-07,
|
| 1377 |
+
"loss": 10.0918,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.1461465271170314,
|
| 1382 |
+
"grad_norm": 17.844097137451172,
|
| 1383 |
+
"learning_rate": 3.0575757355586817e-07,
|
| 1384 |
+
"loss": 10.8963,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.14690770694576594,
|
| 1389 |
+
"grad_norm": 17.421112060546875,
|
| 1390 |
+
"learning_rate": 2.3417567762266497e-07,
|
| 1391 |
+
"loss": 10.0088,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.14766888677450046,
|
| 1396 |
+
"grad_norm": 20.039899826049805,
|
| 1397 |
+
"learning_rate": 1.7209841092460043e-07,
|
| 1398 |
+
"loss": 9.8963,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.14843006660323502,
|
| 1403 |
+
"grad_norm": 20.27971649169922,
|
| 1404 |
+
"learning_rate": 1.1954274476655534e-07,
|
| 1405 |
+
"loss": 10.0839,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.14919124643196954,
|
| 1410 |
+
"grad_norm": 21.218454360961914,
|
| 1411 |
+
"learning_rate": 7.652304734289127e-08,
|
| 1412 |
+
"loss": 9.9099,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.1499524262607041,
|
| 1417 |
+
"grad_norm": 22.624130249023438,
|
| 1418 |
+
"learning_rate": 4.30510798093342e-08,
|
| 1419 |
+
"loss": 9.2576,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.15071360608943862,
|
| 1424 |
+
"grad_norm": 24.730260848999023,
|
| 1425 |
+
"learning_rate": 1.9135993067588284e-08,
|
| 1426 |
+
"loss": 11.2722,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.15147478591817318,
|
| 1431 |
+
"grad_norm": 28.599056243896484,
|
| 1432 |
+
"learning_rate": 4.784325263584854e-09,
|
| 1433 |
+
"loss": 9.2097,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.1522359657469077,
|
| 1438 |
+
"grad_norm": 35.296573638916016,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 9.6651,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.1522359657469077,
|
| 1445 |
+
"eval_loss": 2.635521650314331,
|
| 1446 |
+
"eval_runtime": 159.7212,
|
| 1447 |
+
"eval_samples_per_second": 13.855,
|
| 1448 |
+
"eval_steps_per_second": 3.469,
|
| 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": 2.8668120097672397e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|