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 100690288
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91d9ea8646849387063447bddd21810185fe6b0c524a088edb60abd58102a3e1
|
| 3 |
size 100690288
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 51344890
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50685232e874b58bd88f3988acf5c42f5df8500f5c4ddf79ec349c989a75a85c
|
| 3 |
size 51344890
|
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:b660debdf32c4095316e53fd4da5efc806bee3ca26647b1e570b4839deb17335
|
| 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 sha256:2eca4a3affde04f8094d886307f00c561b3e3a77570955ff1177732e06fbab0c
|
| 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": 19.921,
|
| 1090 |
"eval_steps_per_second": 4.991,
|
| 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": 4,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.1583116054534912,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.1774622892635315,
|
| 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": 19.921,
|
| 1090 |
"eval_steps_per_second": 4.991,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.13398402839396628,
|
| 1095 |
+
"grad_norm": 2.000459909439087,
|
| 1096 |
+
"learning_rate": 2.6021578947368423e-05,
|
| 1097 |
+
"loss": 3.4094,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.13487133984028393,
|
| 1102 |
+
"grad_norm": 1.563780426979065,
|
| 1103 |
+
"learning_rate": 2.5490526315789475e-05,
|
| 1104 |
+
"loss": 1.5053,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.13575865128660158,
|
| 1109 |
+
"grad_norm": 2.0516927242279053,
|
| 1110 |
+
"learning_rate": 2.4959473684210524e-05,
|
| 1111 |
+
"loss": 2.2788,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.13664596273291926,
|
| 1116 |
+
"grad_norm": 2.4126858711242676,
|
| 1117 |
+
"learning_rate": 2.442842105263158e-05,
|
| 1118 |
+
"loss": 2.5862,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.13753327417923691,
|
| 1123 |
+
"grad_norm": 3.0362448692321777,
|
| 1124 |
+
"learning_rate": 2.389736842105263e-05,
|
| 1125 |
+
"loss": 2.6629,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.13842058562555457,
|
| 1130 |
+
"grad_norm": 2.5220859050750732,
|
| 1131 |
+
"learning_rate": 2.3366315789473685e-05,
|
| 1132 |
+
"loss": 2.508,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.13930789707187222,
|
| 1137 |
+
"grad_norm": 2.805745840072632,
|
| 1138 |
+
"learning_rate": 2.2835263157894738e-05,
|
| 1139 |
+
"loss": 2.9899,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.1401952085181899,
|
| 1144 |
+
"grad_norm": 2.442124843597412,
|
| 1145 |
+
"learning_rate": 2.230421052631579e-05,
|
| 1146 |
+
"loss": 2.4191,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.14108251996450755,
|
| 1151 |
+
"grad_norm": 3.3071038722991943,
|
| 1152 |
+
"learning_rate": 2.1773157894736843e-05,
|
| 1153 |
+
"loss": 3.1961,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.1419698314108252,
|
| 1158 |
+
"grad_norm": 3.3711471557617188,
|
| 1159 |
+
"learning_rate": 2.1242105263157895e-05,
|
| 1160 |
+
"loss": 3.2405,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.14285714285714285,
|
| 1165 |
+
"grad_norm": 2.9347105026245117,
|
| 1166 |
+
"learning_rate": 2.0711052631578947e-05,
|
| 1167 |
+
"loss": 2.5419,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.14374445430346053,
|
| 1172 |
+
"grad_norm": 4.1016998291015625,
|
| 1173 |
+
"learning_rate": 2.018e-05,
|
| 1174 |
+
"loss": 3.1722,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.14463176574977818,
|
| 1179 |
+
"grad_norm": 3.6511831283569336,
|
| 1180 |
+
"learning_rate": 1.9648947368421052e-05,
|
| 1181 |
+
"loss": 3.4127,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.14551907719609583,
|
| 1186 |
+
"grad_norm": 3.922149896621704,
|
| 1187 |
+
"learning_rate": 1.9117894736842105e-05,
|
| 1188 |
+
"loss": 3.3926,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.14640638864241348,
|
| 1193 |
+
"grad_norm": 3.898826837539673,
|
| 1194 |
+
"learning_rate": 1.8586842105263157e-05,
|
| 1195 |
+
"loss": 3.1919,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.14729370008873113,
|
| 1200 |
+
"grad_norm": 4.7062764167785645,
|
| 1201 |
+
"learning_rate": 1.805578947368421e-05,
|
| 1202 |
+
"loss": 3.4173,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.1481810115350488,
|
| 1207 |
+
"grad_norm": 4.639416694641113,
|
| 1208 |
+
"learning_rate": 1.7524736842105266e-05,
|
| 1209 |
+
"loss": 3.2817,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.14906832298136646,
|
| 1214 |
+
"grad_norm": 4.930603981018066,
|
| 1215 |
+
"learning_rate": 1.6993684210526315e-05,
|
| 1216 |
+
"loss": 3.7198,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.14995563442768411,
|
| 1221 |
+
"grad_norm": 5.544836521148682,
|
| 1222 |
+
"learning_rate": 1.646263157894737e-05,
|
| 1223 |
+
"loss": 3.3954,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.15084294587400177,
|
| 1228 |
+
"grad_norm": 6.36470890045166,
|
| 1229 |
+
"learning_rate": 1.593157894736842e-05,
|
| 1230 |
+
"loss": 3.2161,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.15173025732031944,
|
| 1235 |
+
"grad_norm": 6.605510234832764,
|
| 1236 |
+
"learning_rate": 1.5400526315789475e-05,
|
| 1237 |
+
"loss": 2.7591,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.1526175687666371,
|
| 1242 |
+
"grad_norm": 8.558485984802246,
|
| 1243 |
+
"learning_rate": 1.4869473684210524e-05,
|
| 1244 |
+
"loss": 3.9719,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.15350488021295475,
|
| 1249 |
+
"grad_norm": 5.824670314788818,
|
| 1250 |
+
"learning_rate": 1.4338421052631579e-05,
|
| 1251 |
+
"loss": 2.701,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.1543921916592724,
|
| 1256 |
+
"grad_norm": 5.702588081359863,
|
| 1257 |
+
"learning_rate": 1.3807368421052633e-05,
|
| 1258 |
+
"loss": 1.9952,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.15527950310559005,
|
| 1263 |
+
"grad_norm": 7.6177287101745605,
|
| 1264 |
+
"learning_rate": 1.3276315789473684e-05,
|
| 1265 |
+
"loss": 2.5539,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.15616681455190773,
|
| 1270 |
+
"grad_norm": 8.845194816589355,
|
| 1271 |
+
"learning_rate": 1.2745263157894738e-05,
|
| 1272 |
+
"loss": 4.027,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.15705412599822538,
|
| 1277 |
+
"grad_norm": 9.726811408996582,
|
| 1278 |
+
"learning_rate": 1.221421052631579e-05,
|
| 1279 |
+
"loss": 3.3798,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.15794143744454303,
|
| 1284 |
+
"grad_norm": 6.408189296722412,
|
| 1285 |
+
"learning_rate": 1.1683157894736843e-05,
|
| 1286 |
+
"loss": 1.3752,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.15882874889086068,
|
| 1291 |
+
"grad_norm": 8.63213062286377,
|
| 1292 |
+
"learning_rate": 1.1152105263157895e-05,
|
| 1293 |
+
"loss": 3.3112,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.15971606033717836,
|
| 1298 |
+
"grad_norm": 8.329524040222168,
|
| 1299 |
+
"learning_rate": 1.0621052631578948e-05,
|
| 1300 |
+
"loss": 3.6397,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.160603371783496,
|
| 1305 |
+
"grad_norm": 5.879098415374756,
|
| 1306 |
+
"learning_rate": 1.009e-05,
|
| 1307 |
+
"loss": 1.8962,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.16149068322981366,
|
| 1312 |
+
"grad_norm": 9.265364646911621,
|
| 1313 |
+
"learning_rate": 9.558947368421052e-06,
|
| 1314 |
+
"loss": 3.4849,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.16237799467613132,
|
| 1319 |
+
"grad_norm": 8.48343563079834,
|
| 1320 |
+
"learning_rate": 9.027894736842105e-06,
|
| 1321 |
+
"loss": 2.2012,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.16326530612244897,
|
| 1326 |
+
"grad_norm": 4.155415058135986,
|
| 1327 |
+
"learning_rate": 8.496842105263157e-06,
|
| 1328 |
+
"loss": 1.2184,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.16415261756876665,
|
| 1333 |
+
"grad_norm": 8.2390775680542,
|
| 1334 |
+
"learning_rate": 7.96578947368421e-06,
|
| 1335 |
+
"loss": 2.5368,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.1650399290150843,
|
| 1340 |
+
"grad_norm": 5.941538333892822,
|
| 1341 |
+
"learning_rate": 7.434736842105262e-06,
|
| 1342 |
+
"loss": 1.1093,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.16592724046140195,
|
| 1347 |
+
"grad_norm": 7.589596271514893,
|
| 1348 |
+
"learning_rate": 6.903684210526316e-06,
|
| 1349 |
+
"loss": 2.1162,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.1668145519077196,
|
| 1354 |
+
"grad_norm": 3.185668706893921,
|
| 1355 |
+
"learning_rate": 6.372631578947369e-06,
|
| 1356 |
+
"loss": 0.4074,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.16770186335403728,
|
| 1361 |
+
"grad_norm": 5.531438827514648,
|
| 1362 |
+
"learning_rate": 5.841578947368421e-06,
|
| 1363 |
+
"loss": 1.4895,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.16858917480035493,
|
| 1368 |
+
"grad_norm": 7.809693336486816,
|
| 1369 |
+
"learning_rate": 5.310526315789474e-06,
|
| 1370 |
+
"loss": 2.1039,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.16947648624667258,
|
| 1375 |
+
"grad_norm": 4.256349563598633,
|
| 1376 |
+
"learning_rate": 4.779473684210526e-06,
|
| 1377 |
+
"loss": 0.5879,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.17036379769299023,
|
| 1382 |
+
"grad_norm": 7.213042736053467,
|
| 1383 |
+
"learning_rate": 4.248421052631579e-06,
|
| 1384 |
+
"loss": 2.6315,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.17125110913930788,
|
| 1389 |
+
"grad_norm": 7.947991847991943,
|
| 1390 |
+
"learning_rate": 3.717368421052631e-06,
|
| 1391 |
+
"loss": 2.47,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.17213842058562556,
|
| 1396 |
+
"grad_norm": 4.920490741729736,
|
| 1397 |
+
"learning_rate": 3.1863157894736844e-06,
|
| 1398 |
+
"loss": 1.0165,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.1730257320319432,
|
| 1403 |
+
"grad_norm": 6.568209648132324,
|
| 1404 |
+
"learning_rate": 2.655263157894737e-06,
|
| 1405 |
+
"loss": 1.6441,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.17391304347826086,
|
| 1410 |
+
"grad_norm": 5.342977523803711,
|
| 1411 |
+
"learning_rate": 2.1242105263157893e-06,
|
| 1412 |
+
"loss": 1.0554,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.17480035492457852,
|
| 1417 |
+
"grad_norm": 5.071080207824707,
|
| 1418 |
+
"learning_rate": 1.5931578947368422e-06,
|
| 1419 |
+
"loss": 0.9551,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.1756876663708962,
|
| 1424 |
+
"grad_norm": 2.469177722930908,
|
| 1425 |
+
"learning_rate": 1.0621052631578947e-06,
|
| 1426 |
+
"loss": 0.5186,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.17657497781721385,
|
| 1431 |
+
"grad_norm": 5.86848783493042,
|
| 1432 |
+
"learning_rate": 5.310526315789473e-07,
|
| 1433 |
+
"loss": 0.9332,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.1774622892635315,
|
| 1438 |
+
"grad_norm": 6.171380996704102,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.9529,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.1774622892635315,
|
| 1445 |
+
"eval_loss": 1.1583116054534912,
|
| 1446 |
+
"eval_runtime": 24.3447,
|
| 1447 |
+
"eval_samples_per_second": 19.511,
|
| 1448 |
+
"eval_steps_per_second": 4.888,
|
| 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": 3315830045540352.0,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|