Training in progress, step 193, 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 201892112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38bce14ef22ca30cb7842c91346c893c96f6d4b1229c0c15c5674571ac6f5d4e
|
| 3 |
size 201892112
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 102864548
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cd95f68fd8a1a6d11a01fd68d92cebe30891911861682a758bab130fbe57b32
|
| 3 |
size 102864548
|
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 sha256:1d6f2d95fee078ae6685f33ce2ab0558591568bec11bb8996c3ce0c08be35279
|
| 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:e35b64cddddbcb296f3261846a2764caa97bfc895b4a9f0211dd2b8a6e73b2a5
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.8657492399215698,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
-
"epoch":
|
| 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 +1089,307 @@
|
|
| 1089 |
"eval_samples_per_second": 41.447,
|
| 1090 |
"eval_steps_per_second": 10.362,
|
| 1091 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
@@ -1112,12 +1413,12 @@
|
|
| 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": 0.8657492399215698,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-150",
|
| 4 |
+
"epoch": 3.0038910505836576,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 193,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1089 |
"eval_samples_per_second": 41.447,
|
| 1090 |
"eval_steps_per_second": 10.362,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 2.350194552529183,
|
| 1095 |
+
"grad_norm": 0.374606192111969,
|
| 1096 |
+
"learning_rate": 1.2443403456474017e-05,
|
| 1097 |
+
"loss": 0.7851,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 2.3657587548638133,
|
| 1102 |
+
"grad_norm": 0.3662430942058563,
|
| 1103 |
+
"learning_rate": 1.1882318057580489e-05,
|
| 1104 |
+
"loss": 0.74,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 2.3813229571984436,
|
| 1109 |
+
"grad_norm": 0.3952215909957886,
|
| 1110 |
+
"learning_rate": 1.1332466114513512e-05,
|
| 1111 |
+
"loss": 0.8131,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 2.396887159533074,
|
| 1116 |
+
"grad_norm": 0.38979917764663696,
|
| 1117 |
+
"learning_rate": 1.0794009671164484e-05,
|
| 1118 |
+
"loss": 0.821,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 2.412451361867704,
|
| 1123 |
+
"grad_norm": 0.37041887640953064,
|
| 1124 |
+
"learning_rate": 1.0267107413118742e-05,
|
| 1125 |
+
"loss": 0.7174,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 2.4280155642023344,
|
| 1130 |
+
"grad_norm": 0.41075101494789124,
|
| 1131 |
+
"learning_rate": 9.751914620890206e-06,
|
| 1132 |
+
"loss": 0.7549,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 2.443579766536965,
|
| 1137 |
+
"grad_norm": 0.4010712206363678,
|
| 1138 |
+
"learning_rate": 9.248583124159438e-06,
|
| 1139 |
+
"loss": 0.7279,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 2.4591439688715955,
|
| 1144 |
+
"grad_norm": 0.40612390637397766,
|
| 1145 |
+
"learning_rate": 8.757261257028777e-06,
|
| 1146 |
+
"loss": 0.7278,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 2.4747081712062258,
|
| 1151 |
+
"grad_norm": 0.4142809510231018,
|
| 1152 |
+
"learning_rate": 8.278093814307637e-06,
|
| 1153 |
+
"loss": 0.7059,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 2.490272373540856,
|
| 1158 |
+
"grad_norm": 0.46315258741378784,
|
| 1159 |
+
"learning_rate": 7.81122200884072e-06,
|
| 1160 |
+
"loss": 0.7573,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 2.5058365758754864,
|
| 1165 |
+
"grad_norm": 0.38741129636764526,
|
| 1166 |
+
"learning_rate": 7.356783429892023e-06,
|
| 1167 |
+
"loss": 0.7816,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 2.5214007782101167,
|
| 1172 |
+
"grad_norm": 0.31710007786750793,
|
| 1173 |
+
"learning_rate": 6.9149120025965905e-06,
|
| 1174 |
+
"loss": 0.6611,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 2.536964980544747,
|
| 1179 |
+
"grad_norm": 0.3693569004535675,
|
| 1180 |
+
"learning_rate": 6.4857379484922375e-06,
|
| 1181 |
+
"loss": 0.8636,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 2.5525291828793772,
|
| 1186 |
+
"grad_norm": 0.34923169016838074,
|
| 1187 |
+
"learning_rate": 6.069387747142591e-06,
|
| 1188 |
+
"loss": 0.7413,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 2.5680933852140075,
|
| 1193 |
+
"grad_norm": 0.3575231432914734,
|
| 1194 |
+
"learning_rate": 5.665984098862992e-06,
|
| 1195 |
+
"loss": 0.7553,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 2.5836575875486383,
|
| 1200 |
+
"grad_norm": 0.3520582318305969,
|
| 1201 |
+
"learning_rate": 5.275645888560232e-06,
|
| 1202 |
+
"loss": 0.7394,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 2.5992217898832686,
|
| 1207 |
+
"grad_norm": 0.37276095151901245,
|
| 1208 |
+
"learning_rate": 4.898488150696467e-06,
|
| 1209 |
+
"loss": 0.7774,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 2.614785992217899,
|
| 1214 |
+
"grad_norm": 0.3675203323364258,
|
| 1215 |
+
"learning_rate": 4.534622035388214e-06,
|
| 1216 |
+
"loss": 0.7305,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 2.630350194552529,
|
| 1221 |
+
"grad_norm": 0.3742014467716217,
|
| 1222 |
+
"learning_rate": 4.184154775649768e-06,
|
| 1223 |
+
"loss": 0.7991,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 2.6459143968871595,
|
| 1228 |
+
"grad_norm": 0.38438355922698975,
|
| 1229 |
+
"learning_rate": 3.8471896557912e-06,
|
| 1230 |
+
"loss": 0.7519,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 2.6614785992217898,
|
| 1235 |
+
"grad_norm": 0.41580691933631897,
|
| 1236 |
+
"learning_rate": 3.523825980979989e-06,
|
| 1237 |
+
"loss": 0.7663,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 2.6770428015564205,
|
| 1242 |
+
"grad_norm": 0.4046590030193329,
|
| 1243 |
+
"learning_rate": 3.2141590479753236e-06,
|
| 1244 |
+
"loss": 0.7113,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 2.692607003891051,
|
| 1249 |
+
"grad_norm": 0.4197351038455963,
|
| 1250 |
+
"learning_rate": 2.918280117043709e-06,
|
| 1251 |
+
"loss": 0.8028,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 2.708171206225681,
|
| 1256 |
+
"grad_norm": 0.4047519862651825,
|
| 1257 |
+
"learning_rate": 2.636276385064157e-06,
|
| 1258 |
+
"loss": 0.7148,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 2.7237354085603114,
|
| 1263 |
+
"grad_norm": 0.42242541909217834,
|
| 1264 |
+
"learning_rate": 2.3682309598308747e-06,
|
| 1265 |
+
"loss": 0.6966,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 2.7392996108949417,
|
| 1270 |
+
"grad_norm": 0.4608907103538513,
|
| 1271 |
+
"learning_rate": 2.114222835560986e-06,
|
| 1272 |
+
"loss": 0.7255,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 2.754863813229572,
|
| 1277 |
+
"grad_norm": 0.4060788154602051,
|
| 1278 |
+
"learning_rate": 1.8743268696145954e-06,
|
| 1279 |
+
"loss": 0.833,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 2.7704280155642023,
|
| 1284 |
+
"grad_norm": 0.33689865469932556,
|
| 1285 |
+
"learning_rate": 1.6486137604339813e-06,
|
| 1286 |
+
"loss": 0.7972,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 2.7859922178988326,
|
| 1291 |
+
"grad_norm": 0.3548411726951599,
|
| 1292 |
+
"learning_rate": 1.4371500267084338e-06,
|
| 1293 |
+
"loss": 0.7801,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 2.801556420233463,
|
| 1298 |
+
"grad_norm": 0.3427428603172302,
|
| 1299 |
+
"learning_rate": 1.2399979877708745e-06,
|
| 1300 |
+
"loss": 0.7001,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 2.817120622568093,
|
| 1305 |
+
"grad_norm": 0.36466020345687866,
|
| 1306 |
+
"learning_rate": 1.0572157452321097e-06,
|
| 1307 |
+
"loss": 0.7898,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 2.832684824902724,
|
| 1312 |
+
"grad_norm": 0.39266034960746765,
|
| 1313 |
+
"learning_rate": 8.888571658579703e-07,
|
| 1314 |
+
"loss": 0.7809,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 2.848249027237354,
|
| 1319 |
+
"grad_norm": 0.3834577202796936,
|
| 1320 |
+
"learning_rate": 7.349718656945504e-07,
|
| 1321 |
+
"loss": 0.7889,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 2.8638132295719845,
|
| 1326 |
+
"grad_norm": 0.3879198133945465,
|
| 1327 |
+
"learning_rate": 5.956051954461472e-07,
|
| 1328 |
+
"loss": 0.8306,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 2.8793774319066148,
|
| 1333 |
+
"grad_norm": 0.36868515610694885,
|
| 1334 |
+
"learning_rate": 4.7079822711015296e-07,
|
| 1335 |
+
"loss": 0.7332,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 2.894941634241245,
|
| 1340 |
+
"grad_norm": 0.38267624378204346,
|
| 1341 |
+
"learning_rate": 3.605877418729975e-07,
|
| 1342 |
+
"loss": 0.6865,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 2.9105058365758754,
|
| 1347 |
+
"grad_norm": 0.39616188406944275,
|
| 1348 |
+
"learning_rate": 2.6500621927054715e-07,
|
| 1349 |
+
"loss": 0.7302,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 2.926070038910506,
|
| 1354 |
+
"grad_norm": 0.4041755199432373,
|
| 1355 |
+
"learning_rate": 1.840818276162226e-07,
|
| 1356 |
+
"loss": 0.8152,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 2.9416342412451364,
|
| 1361 |
+
"grad_norm": 0.4070306122303009,
|
| 1362 |
+
"learning_rate": 1.1783841569968367e-07,
|
| 1363 |
+
"loss": 0.6876,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 2.9571984435797667,
|
| 1368 |
+
"grad_norm": 0.42624837160110474,
|
| 1369 |
+
"learning_rate": 6.629550575847354e-08,
|
| 1370 |
+
"loss": 0.7026,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 2.972762645914397,
|
| 1375 |
+
"grad_norm": 0.4421103298664093,
|
| 1376 |
+
"learning_rate": 2.946828772473764e-08,
|
| 1377 |
+
"loss": 0.7546,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 2.9883268482490273,
|
| 1382 |
+
"grad_norm": 0.4374568462371826,
|
| 1383 |
+
"learning_rate": 7.36761474865455e-09,
|
| 1384 |
+
"loss": 0.7218,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 3.0038910505836576,
|
| 1389 |
+
"grad_norm": 0.8102526068687439,
|
| 1390 |
+
"learning_rate": 0.0,
|
| 1391 |
+
"loss": 1.2001,
|
| 1392 |
+
"step": 193
|
| 1393 |
}
|
| 1394 |
],
|
| 1395 |
"logging_steps": 1,
|
|
|
|
| 1413 |
"should_evaluate": false,
|
| 1414 |
"should_log": false,
|
| 1415 |
"should_save": true,
|
| 1416 |
+
"should_training_stop": true
|
| 1417 |
},
|
| 1418 |
"attributes": {}
|
| 1419 |
}
|
| 1420 |
},
|
| 1421 |
+
"total_flos": 4.879575712530432e+16,
|
| 1422 |
"train_batch_size": 8,
|
| 1423 |
"trial_name": null,
|
| 1424 |
"trial_params": null
|