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 1157746040
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d175da03adda644f73a6f41afec6532a3029c03601a0fb3951a214c17ed9497e
|
| 3 |
size 1157746040
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 588699796
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f40da4380e5f6f57a71494c4b16f6305fb4e0e5291f4889be1753c4092e939e
|
| 3 |
size 588699796
|
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 sha256:8d73c3bb07a82ac3faa0af5d5ac079157bb2a37b441181447fde3e12438f7fbe
|
| 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:e1748c065d82adf475a51dba0ff56fd123a17810f07662718ca6d5704be8f9bd
|
| 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": 4.128,
|
| 1090 |
"eval_steps_per_second": 1.037,
|
| 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": 1.
|
| 1121 |
"train_batch_size": 4,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.586515486240387,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.20171457387796268,
|
| 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": 4.128,
|
| 1090 |
"eval_steps_per_second": 1.037,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.15229450327786181,
|
| 1095 |
+
"grad_norm": 0.6268473267555237,
|
| 1096 |
+
"learning_rate": 2.6124736842105265e-05,
|
| 1097 |
+
"loss": 0.564,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.15330307614725164,
|
| 1102 |
+
"grad_norm": 0.641228437423706,
|
| 1103 |
+
"learning_rate": 2.5591578947368422e-05,
|
| 1104 |
+
"loss": 0.5948,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.15431164901664146,
|
| 1109 |
+
"grad_norm": 0.7048009037971497,
|
| 1110 |
+
"learning_rate": 2.5058421052631576e-05,
|
| 1111 |
+
"loss": 0.6322,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.15532022188603126,
|
| 1116 |
+
"grad_norm": 0.7274343371391296,
|
| 1117 |
+
"learning_rate": 2.4525263157894737e-05,
|
| 1118 |
+
"loss": 0.6277,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.15632879475542108,
|
| 1123 |
+
"grad_norm": 0.630876898765564,
|
| 1124 |
+
"learning_rate": 2.3992105263157894e-05,
|
| 1125 |
+
"loss": 0.52,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.1573373676248109,
|
| 1130 |
+
"grad_norm": 0.667843222618103,
|
| 1131 |
+
"learning_rate": 2.345894736842105e-05,
|
| 1132 |
+
"loss": 0.6142,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.1583459404942007,
|
| 1137 |
+
"grad_norm": 0.8011748194694519,
|
| 1138 |
+
"learning_rate": 2.292578947368421e-05,
|
| 1139 |
+
"loss": 0.6761,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.15935451336359052,
|
| 1144 |
+
"grad_norm": 0.776394784450531,
|
| 1145 |
+
"learning_rate": 2.2392631578947366e-05,
|
| 1146 |
+
"loss": 0.5793,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.16036308623298035,
|
| 1151 |
+
"grad_norm": 0.7845891118049622,
|
| 1152 |
+
"learning_rate": 2.1859473684210527e-05,
|
| 1153 |
+
"loss": 0.6877,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.16137165910237014,
|
| 1158 |
+
"grad_norm": 0.6398541331291199,
|
| 1159 |
+
"learning_rate": 2.132631578947368e-05,
|
| 1160 |
+
"loss": 0.5423,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.16238023197175996,
|
| 1165 |
+
"grad_norm": 0.6314144730567932,
|
| 1166 |
+
"learning_rate": 2.0793157894736842e-05,
|
| 1167 |
+
"loss": 0.6201,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.16338880484114976,
|
| 1172 |
+
"grad_norm": 0.6075751781463623,
|
| 1173 |
+
"learning_rate": 2.026e-05,
|
| 1174 |
+
"loss": 0.6469,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.16439737771053958,
|
| 1179 |
+
"grad_norm": 0.5889184474945068,
|
| 1180 |
+
"learning_rate": 1.9726842105263157e-05,
|
| 1181 |
+
"loss": 0.5984,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.1654059505799294,
|
| 1186 |
+
"grad_norm": 0.6887006759643555,
|
| 1187 |
+
"learning_rate": 1.9193684210526314e-05,
|
| 1188 |
+
"loss": 0.6645,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.1664145234493192,
|
| 1193 |
+
"grad_norm": 0.6177269816398621,
|
| 1194 |
+
"learning_rate": 1.866052631578947e-05,
|
| 1195 |
+
"loss": 0.5922,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.16742309631870902,
|
| 1200 |
+
"grad_norm": 0.5395684838294983,
|
| 1201 |
+
"learning_rate": 1.8127368421052632e-05,
|
| 1202 |
+
"loss": 0.4799,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.16843166918809885,
|
| 1207 |
+
"grad_norm": 0.576266348361969,
|
| 1208 |
+
"learning_rate": 1.759421052631579e-05,
|
| 1209 |
+
"loss": 0.5543,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.16944024205748864,
|
| 1214 |
+
"grad_norm": 0.6665874719619751,
|
| 1215 |
+
"learning_rate": 1.7061052631578947e-05,
|
| 1216 |
+
"loss": 0.5,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.17044881492687847,
|
| 1221 |
+
"grad_norm": 0.6267380714416504,
|
| 1222 |
+
"learning_rate": 1.6527894736842104e-05,
|
| 1223 |
+
"loss": 0.5691,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.1714573877962683,
|
| 1228 |
+
"grad_norm": 0.6658629775047302,
|
| 1229 |
+
"learning_rate": 1.599473684210526e-05,
|
| 1230 |
+
"loss": 0.611,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.17246596066565809,
|
| 1235 |
+
"grad_norm": 0.6339704394340515,
|
| 1236 |
+
"learning_rate": 1.546157894736842e-05,
|
| 1237 |
+
"loss": 0.5832,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.1734745335350479,
|
| 1242 |
+
"grad_norm": 0.6910547614097595,
|
| 1243 |
+
"learning_rate": 1.4928421052631576e-05,
|
| 1244 |
+
"loss": 0.5645,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.17448310640443773,
|
| 1249 |
+
"grad_norm": 0.65704345703125,
|
| 1250 |
+
"learning_rate": 1.4395263157894735e-05,
|
| 1251 |
+
"loss": 0.5581,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.17549167927382753,
|
| 1256 |
+
"grad_norm": 0.7219071388244629,
|
| 1257 |
+
"learning_rate": 1.3862105263157895e-05,
|
| 1258 |
+
"loss": 0.5708,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.17650025214321735,
|
| 1263 |
+
"grad_norm": 0.6242889165878296,
|
| 1264 |
+
"learning_rate": 1.3328947368421052e-05,
|
| 1265 |
+
"loss": 0.5329,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.17750882501260717,
|
| 1270 |
+
"grad_norm": 0.7662546038627625,
|
| 1271 |
+
"learning_rate": 1.2795789473684211e-05,
|
| 1272 |
+
"loss": 0.6528,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.17851739788199697,
|
| 1277 |
+
"grad_norm": 0.6656923890113831,
|
| 1278 |
+
"learning_rate": 1.2262631578947368e-05,
|
| 1279 |
+
"loss": 0.5689,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.1795259707513868,
|
| 1284 |
+
"grad_norm": 0.6222251057624817,
|
| 1285 |
+
"learning_rate": 1.1729473684210526e-05,
|
| 1286 |
+
"loss": 0.5176,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.1805345436207766,
|
| 1291 |
+
"grad_norm": 0.719865083694458,
|
| 1292 |
+
"learning_rate": 1.1196315789473683e-05,
|
| 1293 |
+
"loss": 0.6474,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.1815431164901664,
|
| 1298 |
+
"grad_norm": 0.7028816938400269,
|
| 1299 |
+
"learning_rate": 1.066315789473684e-05,
|
| 1300 |
+
"loss": 0.5822,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.18255168935955624,
|
| 1305 |
+
"grad_norm": 0.7372841238975525,
|
| 1306 |
+
"learning_rate": 1.013e-05,
|
| 1307 |
+
"loss": 0.725,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.18356026222894603,
|
| 1312 |
+
"grad_norm": 0.7506668567657471,
|
| 1313 |
+
"learning_rate": 9.596842105263157e-06,
|
| 1314 |
+
"loss": 0.719,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.18456883509833585,
|
| 1319 |
+
"grad_norm": 0.6846113801002502,
|
| 1320 |
+
"learning_rate": 9.063684210526316e-06,
|
| 1321 |
+
"loss": 0.5617,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.18557740796772568,
|
| 1326 |
+
"grad_norm": 0.725283145904541,
|
| 1327 |
+
"learning_rate": 8.530526315789473e-06,
|
| 1328 |
+
"loss": 0.7003,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.18658598083711547,
|
| 1333 |
+
"grad_norm": 0.7440472841262817,
|
| 1334 |
+
"learning_rate": 7.99736842105263e-06,
|
| 1335 |
+
"loss": 0.6783,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.1875945537065053,
|
| 1340 |
+
"grad_norm": 0.7624148726463318,
|
| 1341 |
+
"learning_rate": 7.464210526315788e-06,
|
| 1342 |
+
"loss": 0.6045,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.18860312657589512,
|
| 1347 |
+
"grad_norm": 0.6890900135040283,
|
| 1348 |
+
"learning_rate": 6.931052631578947e-06,
|
| 1349 |
+
"loss": 0.6771,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.18961169944528491,
|
| 1354 |
+
"grad_norm": 0.7498593330383301,
|
| 1355 |
+
"learning_rate": 6.3978947368421055e-06,
|
| 1356 |
+
"loss": 0.6308,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.19062027231467474,
|
| 1361 |
+
"grad_norm": 0.7661704421043396,
|
| 1362 |
+
"learning_rate": 5.864736842105263e-06,
|
| 1363 |
+
"loss": 0.5971,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.19162884518406456,
|
| 1368 |
+
"grad_norm": 0.7634966373443604,
|
| 1369 |
+
"learning_rate": 5.33157894736842e-06,
|
| 1370 |
+
"loss": 0.6865,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.19263741805345436,
|
| 1375 |
+
"grad_norm": 0.7930402755737305,
|
| 1376 |
+
"learning_rate": 4.7984210526315785e-06,
|
| 1377 |
+
"loss": 0.697,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.19364599092284418,
|
| 1382 |
+
"grad_norm": 0.7510807514190674,
|
| 1383 |
+
"learning_rate": 4.265263157894737e-06,
|
| 1384 |
+
"loss": 0.5674,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.19465456379223398,
|
| 1389 |
+
"grad_norm": 0.7455921173095703,
|
| 1390 |
+
"learning_rate": 3.732105263157894e-06,
|
| 1391 |
+
"loss": 0.5941,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.1956631366616238,
|
| 1396 |
+
"grad_norm": 0.874135434627533,
|
| 1397 |
+
"learning_rate": 3.1989473684210527e-06,
|
| 1398 |
+
"loss": 0.7376,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.19667170953101362,
|
| 1403 |
+
"grad_norm": 0.9072071313858032,
|
| 1404 |
+
"learning_rate": 2.66578947368421e-06,
|
| 1405 |
+
"loss": 0.7227,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.19768028240040342,
|
| 1410 |
+
"grad_norm": 0.8837161064147949,
|
| 1411 |
+
"learning_rate": 2.1326315789473684e-06,
|
| 1412 |
+
"loss": 0.632,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.19868885526979324,
|
| 1417 |
+
"grad_norm": 0.8915238380432129,
|
| 1418 |
+
"learning_rate": 1.5994736842105264e-06,
|
| 1419 |
+
"loss": 0.6964,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.19969742813918306,
|
| 1424 |
+
"grad_norm": 0.9615832567214966,
|
| 1425 |
+
"learning_rate": 1.0663157894736842e-06,
|
| 1426 |
+
"loss": 0.6445,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.20070600100857286,
|
| 1431 |
+
"grad_norm": 0.9298158288002014,
|
| 1432 |
+
"learning_rate": 5.331578947368421e-07,
|
| 1433 |
+
"loss": 0.6559,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.20171457387796268,
|
| 1438 |
+
"grad_norm": 1.076253890991211,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.7625,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.20171457387796268,
|
| 1445 |
+
"eval_loss": 0.586515486240387,
|
| 1446 |
+
"eval_runtime": 101.559,
|
| 1447 |
+
"eval_samples_per_second": 4.116,
|
| 1448 |
+
"eval_steps_per_second": 1.034,
|
| 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": 1.733017139675136e+17,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|