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 639691872
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdee1054fb575f17ad0efed85b0470ce30b1e1fbb1c68e07c6aa26d2ca51ff83
|
| 3 |
size 639691872
|
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:cfb785dd749d9643e7ab25c667636ec40679ee9ed159847ad17117f3d1310093
|
| 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 sha256:7cbf58d5cbf150282b58801563c0253ffd50a50be6b5dbe4d8790fdb2cf4b52c
|
| 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:ca62d85cf5423834480d3c20680f93b185c8e6574a8a14021d285e0b05c7449f
|
| 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": 6.974,
|
| 1090 |
"eval_steps_per_second": 1.744,
|
| 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": 1.0697510242462158,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.056589092452429796,
|
| 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": 6.974,
|
| 1090 |
"eval_steps_per_second": 1.744,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.04272476480158449,
|
| 1095 |
+
"grad_norm": 0.15892794728279114,
|
| 1096 |
+
"learning_rate": 9.319397726443026e-06,
|
| 1097 |
+
"loss": 1.18,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.043007710263846644,
|
| 1102 |
+
"grad_norm": 0.15233199298381805,
|
| 1103 |
+
"learning_rate": 8.962896471825342e-06,
|
| 1104 |
+
"loss": 1.1396,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.043290655726108795,
|
| 1109 |
+
"grad_norm": 0.15636806190013885,
|
| 1110 |
+
"learning_rate": 8.61214655125809e-06,
|
| 1111 |
+
"loss": 1.3293,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.04357360118837094,
|
| 1116 |
+
"grad_norm": 0.17083175480365753,
|
| 1117 |
+
"learning_rate": 8.267243856267331e-06,
|
| 1118 |
+
"loss": 1.2175,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.04385654665063309,
|
| 1123 |
+
"grad_norm": 0.14700956642627716,
|
| 1124 |
+
"learning_rate": 7.928282679806052e-06,
|
| 1125 |
+
"loss": 1.2229,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.04413949211289524,
|
| 1130 |
+
"grad_norm": 0.14753887057304382,
|
| 1131 |
+
"learning_rate": 7.595355690475393e-06,
|
| 1132 |
+
"loss": 1.1916,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.04442243757515739,
|
| 1137 |
+
"grad_norm": 0.16037601232528687,
|
| 1138 |
+
"learning_rate": 7.268553907189964e-06,
|
| 1139 |
+
"loss": 1.1722,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.044705383037419534,
|
| 1144 |
+
"grad_norm": 0.125972181558609,
|
| 1145 |
+
"learning_rate": 6.947966674294236e-06,
|
| 1146 |
+
"loss": 1.162,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.044988328499681686,
|
| 1151 |
+
"grad_norm": 0.15123845636844635,
|
| 1152 |
+
"learning_rate": 6.6336816371366305e-06,
|
| 1153 |
+
"loss": 1.206,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.04527127396194384,
|
| 1158 |
+
"grad_norm": 0.14084303379058838,
|
| 1159 |
+
"learning_rate": 6.325784718108196e-06,
|
| 1160 |
+
"loss": 1.0952,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.04555421942420598,
|
| 1165 |
+
"grad_norm": 0.1478935182094574,
|
| 1166 |
+
"learning_rate": 6.0243600931522595e-06,
|
| 1167 |
+
"loss": 1.0997,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.045837164886468135,
|
| 1172 |
+
"grad_norm": 0.1472909152507782,
|
| 1173 |
+
"learning_rate": 5.72949016875158e-06,
|
| 1174 |
+
"loss": 1.1209,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.04612011034873028,
|
| 1179 |
+
"grad_norm": 0.15565665066242218,
|
| 1180 |
+
"learning_rate": 5.44125555939923e-06,
|
| 1181 |
+
"loss": 1.2026,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.04640305581099243,
|
| 1186 |
+
"grad_norm": 0.15660125017166138,
|
| 1187 |
+
"learning_rate": 5.159735065559399e-06,
|
| 1188 |
+
"loss": 1.1838,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.04668600127325458,
|
| 1193 |
+
"grad_norm": 0.1355641484260559,
|
| 1194 |
+
"learning_rate": 4.885005652124144e-06,
|
| 1195 |
+
"loss": 1.2546,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.04696894673551673,
|
| 1200 |
+
"grad_norm": 0.13826073706150055,
|
| 1201 |
+
"learning_rate": 4.617142427371934e-06,
|
| 1202 |
+
"loss": 1.1198,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.04725189219777888,
|
| 1207 |
+
"grad_norm": 0.13007190823554993,
|
| 1208 |
+
"learning_rate": 4.3562186224338265e-06,
|
| 1209 |
+
"loss": 1.0406,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.047534837660041025,
|
| 1214 |
+
"grad_norm": 0.13735632598400116,
|
| 1215 |
+
"learning_rate": 4.102305571272783e-06,
|
| 1216 |
+
"loss": 1.2001,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.04781778312230318,
|
| 1221 |
+
"grad_norm": 0.13487175107002258,
|
| 1222 |
+
"learning_rate": 3.855472691181678e-06,
|
| 1223 |
+
"loss": 1.1674,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.04810072858456532,
|
| 1228 |
+
"grad_norm": 0.1506294310092926,
|
| 1229 |
+
"learning_rate": 3.615787463805331e-06,
|
| 1230 |
+
"loss": 1.1782,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.048383674046827474,
|
| 1235 |
+
"grad_norm": 0.13945788145065308,
|
| 1236 |
+
"learning_rate": 3.383315416691646e-06,
|
| 1237 |
+
"loss": 1.1162,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.048666619509089626,
|
| 1242 |
+
"grad_norm": 0.14078959822654724,
|
| 1243 |
+
"learning_rate": 3.158120105377096e-06,
|
| 1244 |
+
"loss": 1.1837,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.04894956497135177,
|
| 1249 |
+
"grad_norm": 0.15105940401554108,
|
| 1250 |
+
"learning_rate": 2.940263096011233e-06,
|
| 1251 |
+
"loss": 1.2026,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.04923251043361392,
|
| 1256 |
+
"grad_norm": 0.14473502337932587,
|
| 1257 |
+
"learning_rate": 2.729803948525125e-06,
|
| 1258 |
+
"loss": 1.0766,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.04951545589587607,
|
| 1263 |
+
"grad_norm": 0.14269044995307922,
|
| 1264 |
+
"learning_rate": 2.526800200348275e-06,
|
| 1265 |
+
"loss": 1.1419,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.04979840135813822,
|
| 1270 |
+
"grad_norm": 0.1475040763616562,
|
| 1271 |
+
"learning_rate": 2.3313073506784575e-06,
|
| 1272 |
+
"loss": 1.2384,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.050081346820400365,
|
| 1277 |
+
"grad_norm": 0.13880924880504608,
|
| 1278 |
+
"learning_rate": 2.143378845308791e-06,
|
| 1279 |
+
"loss": 1.1159,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.050364292282662516,
|
| 1284 |
+
"grad_norm": 0.14378739893436432,
|
| 1285 |
+
"learning_rate": 1.9630660620161777e-06,
|
| 1286 |
+
"loss": 1.1177,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.05064723774492467,
|
| 1291 |
+
"grad_norm": 0.17214110493659973,
|
| 1292 |
+
"learning_rate": 1.790418296515165e-06,
|
| 1293 |
+
"loss": 1.1171,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.05093018320718681,
|
| 1298 |
+
"grad_norm": 0.16885404288768768,
|
| 1299 |
+
"learning_rate": 1.625482748980961e-06,
|
| 1300 |
+
"loss": 1.2154,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.051213128669448965,
|
| 1305 |
+
"grad_norm": 0.15598832070827484,
|
| 1306 |
+
"learning_rate": 1.4683045111453942e-06,
|
| 1307 |
+
"loss": 1.1079,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.05149607413171111,
|
| 1312 |
+
"grad_norm": 0.16221092641353607,
|
| 1313 |
+
"learning_rate": 1.3189265539692707e-06,
|
| 1314 |
+
"loss": 1.1572,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.05177901959397326,
|
| 1319 |
+
"grad_norm": 0.15152089297771454,
|
| 1320 |
+
"learning_rate": 1.1773897158945557e-06,
|
| 1321 |
+
"loss": 1.08,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.052061965056235414,
|
| 1326 |
+
"grad_norm": 0.1765381395816803,
|
| 1327 |
+
"learning_rate": 1.0437326916795432e-06,
|
| 1328 |
+
"loss": 1.0874,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.05234491051849756,
|
| 1333 |
+
"grad_norm": 0.18851357698440552,
|
| 1334 |
+
"learning_rate": 9.179920218200888e-07,
|
| 1335 |
+
"loss": 1.031,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.05262785598075971,
|
| 1340 |
+
"grad_norm": 0.190265491604805,
|
| 1341 |
+
"learning_rate": 8.002020825598277e-07,
|
| 1342 |
+
"loss": 1.0912,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.052910801443021856,
|
| 1347 |
+
"grad_norm": 0.1942068487405777,
|
| 1348 |
+
"learning_rate": 6.90395076492022e-07,
|
| 1349 |
+
"loss": 1.0471,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.05319374690528401,
|
| 1354 |
+
"grad_norm": 0.23885029554367065,
|
| 1355 |
+
"learning_rate": 5.886010237557194e-07,
|
| 1356 |
+
"loss": 0.9656,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.05347669236754615,
|
| 1361 |
+
"grad_norm": 0.22708922624588013,
|
| 1362 |
+
"learning_rate": 4.94847753828529e-07,
|
| 1363 |
+
"loss": 1.0172,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.053759637829808304,
|
| 1368 |
+
"grad_norm": 0.23104092478752136,
|
| 1369 |
+
"learning_rate": 4.091608979183303e-07,
|
| 1370 |
+
"loss": 0.9197,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.054042583292070456,
|
| 1375 |
+
"grad_norm": 0.28225743770599365,
|
| 1376 |
+
"learning_rate": 3.315638819559452e-07,
|
| 1377 |
+
"loss": 0.8387,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.0543255287543326,
|
| 1382 |
+
"grad_norm": 0.29937031865119934,
|
| 1383 |
+
"learning_rate": 2.6207792019074414e-07,
|
| 1384 |
+
"loss": 0.8365,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.05460847421659475,
|
| 1389 |
+
"grad_norm": 0.27068015933036804,
|
| 1390 |
+
"learning_rate": 2.0072200939085573e-07,
|
| 1391 |
+
"loss": 0.8807,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.0548914196788569,
|
| 1396 |
+
"grad_norm": 0.3136865198612213,
|
| 1397 |
+
"learning_rate": 1.475129236496575e-07,
|
| 1398 |
+
"loss": 0.8064,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.05517436514111905,
|
| 1403 |
+
"grad_norm": 0.30548372864723206,
|
| 1404 |
+
"learning_rate": 1.0246520979990459e-07,
|
| 1405 |
+
"loss": 1.0338,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.055457310603381195,
|
| 1410 |
+
"grad_norm": 0.29919055104255676,
|
| 1411 |
+
"learning_rate": 6.559118343676396e-08,
|
| 1412 |
+
"loss": 0.8476,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.05574025606564335,
|
| 1417 |
+
"grad_norm": 0.333148330450058,
|
| 1418 |
+
"learning_rate": 3.690092555085789e-08,
|
| 1419 |
+
"loss": 0.7565,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.0560232015279055,
|
| 1424 |
+
"grad_norm": 0.31107303500175476,
|
| 1425 |
+
"learning_rate": 1.640227977221853e-08,
|
| 1426 |
+
"loss": 0.8806,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.056306146990167644,
|
| 1431 |
+
"grad_norm": 0.3069625198841095,
|
| 1432 |
+
"learning_rate": 4.1008502259298755e-09,
|
| 1433 |
+
"loss": 1.1436,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.056589092452429796,
|
| 1438 |
+
"grad_norm": 0.35064685344696045,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 1.0373,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.056589092452429796,
|
| 1445 |
+
"eval_loss": 1.0697510242462158,
|
| 1446 |
+
"eval_runtime": 853.5988,
|
| 1447 |
+
"eval_samples_per_second": 6.974,
|
| 1448 |
+
"eval_steps_per_second": 1.744,
|
| 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": 5.275415744945848e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|