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:b85cec5e4fd2dd855174100333daa22ce2817cc9a4febc08144088d63de6f0f0
|
| 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 sha256:5cdce61cec7f1dcb8c178fbd4d12ce0e0817369063f4efa6bb3907db2a1bff99
|
| 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 sha256:7c0f81402f40376f1c4102d53f897a7113b1bfa0c6a056684eeef9abbf2faf98
|
| 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:d703f9adb617aa1ec13556a7b7482c741f765121a5a04f3cafdcfbce6ed485ee
|
| 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": 14.867,
|
| 1090 |
"eval_steps_per_second": 3.717,
|
| 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": 2.432666063308716,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.1504890895410083,
|
| 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": 14.867,
|
| 1090 |
"eval_steps_per_second": 3.717,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.11361926260346125,
|
| 1095 |
+
"grad_norm": 3.661033868789673,
|
| 1096 |
+
"learning_rate": 2.6253684210526317e-05,
|
| 1097 |
+
"loss": 5.0616,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.1143717080511663,
|
| 1102 |
+
"grad_norm": 5.994472026824951,
|
| 1103 |
+
"learning_rate": 2.5717894736842106e-05,
|
| 1104 |
+
"loss": 4.6401,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.11512415349887133,
|
| 1109 |
+
"grad_norm": 5.022431373596191,
|
| 1110 |
+
"learning_rate": 2.518210526315789e-05,
|
| 1111 |
+
"loss": 4.6046,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.11587659894657637,
|
| 1116 |
+
"grad_norm": 4.494561195373535,
|
| 1117 |
+
"learning_rate": 2.4646315789473683e-05,
|
| 1118 |
+
"loss": 4.717,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.11662904439428141,
|
| 1123 |
+
"grad_norm": 5.689757347106934,
|
| 1124 |
+
"learning_rate": 2.411052631578947e-05,
|
| 1125 |
+
"loss": 5.0209,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.11738148984198646,
|
| 1130 |
+
"grad_norm": 4.620606422424316,
|
| 1131 |
+
"learning_rate": 2.357473684210526e-05,
|
| 1132 |
+
"loss": 4.0454,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.1181339352896915,
|
| 1137 |
+
"grad_norm": 6.991167068481445,
|
| 1138 |
+
"learning_rate": 2.3038947368421052e-05,
|
| 1139 |
+
"loss": 4.7982,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.11888638073739653,
|
| 1144 |
+
"grad_norm": 5.083990097045898,
|
| 1145 |
+
"learning_rate": 2.250315789473684e-05,
|
| 1146 |
+
"loss": 4.4286,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.11963882618510158,
|
| 1151 |
+
"grad_norm": 6.157924175262451,
|
| 1152 |
+
"learning_rate": 2.196736842105263e-05,
|
| 1153 |
+
"loss": 4.6027,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.12039127163280662,
|
| 1158 |
+
"grad_norm": 8.231710433959961,
|
| 1159 |
+
"learning_rate": 2.1431578947368418e-05,
|
| 1160 |
+
"loss": 5.3449,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.12114371708051166,
|
| 1165 |
+
"grad_norm": 7.961388111114502,
|
| 1166 |
+
"learning_rate": 2.089578947368421e-05,
|
| 1167 |
+
"loss": 5.2107,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.12189616252821671,
|
| 1172 |
+
"grad_norm": 6.96645450592041,
|
| 1173 |
+
"learning_rate": 2.036e-05,
|
| 1174 |
+
"loss": 5.1824,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.12264860797592174,
|
| 1179 |
+
"grad_norm": 7.0527801513671875,
|
| 1180 |
+
"learning_rate": 1.9824210526315787e-05,
|
| 1181 |
+
"loss": 4.5329,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.12340105342362678,
|
| 1186 |
+
"grad_norm": 6.659213066101074,
|
| 1187 |
+
"learning_rate": 1.928842105263158e-05,
|
| 1188 |
+
"loss": 4.9405,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.12415349887133183,
|
| 1193 |
+
"grad_norm": 6.317037582397461,
|
| 1194 |
+
"learning_rate": 1.8752631578947367e-05,
|
| 1195 |
+
"loss": 4.8909,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.12490594431903687,
|
| 1200 |
+
"grad_norm": 7.180385589599609,
|
| 1201 |
+
"learning_rate": 1.8216842105263156e-05,
|
| 1202 |
+
"loss": 5.1754,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.1256583897667419,
|
| 1207 |
+
"grad_norm": 8.178675651550293,
|
| 1208 |
+
"learning_rate": 1.7681052631578948e-05,
|
| 1209 |
+
"loss": 5.2554,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.12641083521444696,
|
| 1214 |
+
"grad_norm": 7.352338790893555,
|
| 1215 |
+
"learning_rate": 1.7145263157894736e-05,
|
| 1216 |
+
"loss": 5.179,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.127163280662152,
|
| 1221 |
+
"grad_norm": 7.15298318862915,
|
| 1222 |
+
"learning_rate": 1.6609473684210525e-05,
|
| 1223 |
+
"loss": 4.9093,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.12791572610985705,
|
| 1228 |
+
"grad_norm": 6.234389781951904,
|
| 1229 |
+
"learning_rate": 1.6073684210526313e-05,
|
| 1230 |
+
"loss": 4.3581,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.12866817155756208,
|
| 1235 |
+
"grad_norm": 7.177828311920166,
|
| 1236 |
+
"learning_rate": 1.5537894736842105e-05,
|
| 1237 |
+
"loss": 4.8511,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.1294206170052671,
|
| 1242 |
+
"grad_norm": 6.240314483642578,
|
| 1243 |
+
"learning_rate": 1.5002105263157892e-05,
|
| 1244 |
+
"loss": 4.6268,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.13017306245297217,
|
| 1249 |
+
"grad_norm": 6.857619762420654,
|
| 1250 |
+
"learning_rate": 1.4466315789473684e-05,
|
| 1251 |
+
"loss": 3.9235,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.1309255079006772,
|
| 1256 |
+
"grad_norm": 6.206757068634033,
|
| 1257 |
+
"learning_rate": 1.3930526315789474e-05,
|
| 1258 |
+
"loss": 4.8705,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.13167795334838225,
|
| 1263 |
+
"grad_norm": 6.866716384887695,
|
| 1264 |
+
"learning_rate": 1.3394736842105261e-05,
|
| 1265 |
+
"loss": 4.7763,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.13243039879608728,
|
| 1270 |
+
"grad_norm": 7.294867515563965,
|
| 1271 |
+
"learning_rate": 1.2858947368421053e-05,
|
| 1272 |
+
"loss": 4.6713,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.13318284424379231,
|
| 1277 |
+
"grad_norm": 7.363504886627197,
|
| 1278 |
+
"learning_rate": 1.2323157894736842e-05,
|
| 1279 |
+
"loss": 4.5199,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.13393528969149737,
|
| 1284 |
+
"grad_norm": 7.403514385223389,
|
| 1285 |
+
"learning_rate": 1.178736842105263e-05,
|
| 1286 |
+
"loss": 4.5396,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.1346877351392024,
|
| 1291 |
+
"grad_norm": 9.64759635925293,
|
| 1292 |
+
"learning_rate": 1.125157894736842e-05,
|
| 1293 |
+
"loss": 5.123,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.13544018058690746,
|
| 1298 |
+
"grad_norm": 8.454669952392578,
|
| 1299 |
+
"learning_rate": 1.0715789473684209e-05,
|
| 1300 |
+
"loss": 4.6262,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.1361926260346125,
|
| 1305 |
+
"grad_norm": 7.289380073547363,
|
| 1306 |
+
"learning_rate": 1.018e-05,
|
| 1307 |
+
"loss": 4.1746,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.13694507148231752,
|
| 1312 |
+
"grad_norm": 14.602645874023438,
|
| 1313 |
+
"learning_rate": 9.64421052631579e-06,
|
| 1314 |
+
"loss": 5.1446,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.13769751693002258,
|
| 1319 |
+
"grad_norm": 10.938192367553711,
|
| 1320 |
+
"learning_rate": 9.108421052631578e-06,
|
| 1321 |
+
"loss": 5.2975,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.1384499623777276,
|
| 1326 |
+
"grad_norm": 9.536102294921875,
|
| 1327 |
+
"learning_rate": 8.572631578947368e-06,
|
| 1328 |
+
"loss": 4.973,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.13920240782543267,
|
| 1333 |
+
"grad_norm": 9.649733543395996,
|
| 1334 |
+
"learning_rate": 8.036842105263157e-06,
|
| 1335 |
+
"loss": 4.9525,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.1399548532731377,
|
| 1340 |
+
"grad_norm": 7.923221111297607,
|
| 1341 |
+
"learning_rate": 7.501052631578946e-06,
|
| 1342 |
+
"loss": 4.8443,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.14070729872084273,
|
| 1347 |
+
"grad_norm": 9.543553352355957,
|
| 1348 |
+
"learning_rate": 6.965263157894737e-06,
|
| 1349 |
+
"loss": 5.2648,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.14145974416854779,
|
| 1354 |
+
"grad_norm": 9.844090461730957,
|
| 1355 |
+
"learning_rate": 6.4294736842105265e-06,
|
| 1356 |
+
"loss": 5.2391,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.14221218961625282,
|
| 1361 |
+
"grad_norm": 12.343792915344238,
|
| 1362 |
+
"learning_rate": 5.893684210526315e-06,
|
| 1363 |
+
"loss": 5.8381,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.14296463506395787,
|
| 1368 |
+
"grad_norm": 10.430888175964355,
|
| 1369 |
+
"learning_rate": 5.3578947368421044e-06,
|
| 1370 |
+
"loss": 5.2111,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.1437170805116629,
|
| 1375 |
+
"grad_norm": 9.29223346710205,
|
| 1376 |
+
"learning_rate": 4.822105263157895e-06,
|
| 1377 |
+
"loss": 5.2066,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.14446952595936793,
|
| 1382 |
+
"grad_norm": 12.151300430297852,
|
| 1383 |
+
"learning_rate": 4.286315789473684e-06,
|
| 1384 |
+
"loss": 5.1922,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.145221971407073,
|
| 1389 |
+
"grad_norm": 9.725712776184082,
|
| 1390 |
+
"learning_rate": 3.750526315789473e-06,
|
| 1391 |
+
"loss": 5.3949,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.14597441685477802,
|
| 1396 |
+
"grad_norm": 13.120623588562012,
|
| 1397 |
+
"learning_rate": 3.2147368421052633e-06,
|
| 1398 |
+
"loss": 5.2486,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.14672686230248308,
|
| 1403 |
+
"grad_norm": 10.279730796813965,
|
| 1404 |
+
"learning_rate": 2.6789473684210522e-06,
|
| 1405 |
+
"loss": 4.5108,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.1474793077501881,
|
| 1410 |
+
"grad_norm": 12.112651824951172,
|
| 1411 |
+
"learning_rate": 2.143157894736842e-06,
|
| 1412 |
+
"loss": 4.847,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.14823175319789314,
|
| 1417 |
+
"grad_norm": 10.086380958557129,
|
| 1418 |
+
"learning_rate": 1.6073684210526316e-06,
|
| 1419 |
+
"loss": 4.9699,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.1489841986455982,
|
| 1424 |
+
"grad_norm": 13.680956840515137,
|
| 1425 |
+
"learning_rate": 1.071578947368421e-06,
|
| 1426 |
+
"loss": 6.0189,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.14973664409330323,
|
| 1431 |
+
"grad_norm": 15.482779502868652,
|
| 1432 |
+
"learning_rate": 5.357894736842105e-07,
|
| 1433 |
+
"loss": 5.6126,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.1504890895410083,
|
| 1438 |
+
"grad_norm": 15.324419975280762,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 6.2436,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.1504890895410083,
|
| 1445 |
+
"eval_loss": 2.432666063308716,
|
| 1446 |
+
"eval_runtime": 37.6225,
|
| 1447 |
+
"eval_samples_per_second": 14.885,
|
| 1448 |
+
"eval_steps_per_second": 3.721,
|
| 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": 7.262314895612314e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|