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 sha256:9596e67904025109ae94f96486dc62aad8671538542a1b02899ae60d31529a90
|
| 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:cc49882fadb5945e27a09277baa8ab5d108b79a2f40467166250cf68ca894205
|
| 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 sha256:03430ce74886e6a08609778dc75b7d8511d30959529b5674f7e9a81b117eb6d4
|
| 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:a032dcbe590e69725a7fa9cedb5934521429cb4c18983c09c5035cbcaaeebd93
|
| 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":
|
| 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": 12.828,
|
| 1090 |
"eval_steps_per_second": 3.246,
|
| 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": 2.
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.986004114151001,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 2.0833333333333335,
|
| 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": 12.828,
|
| 1090 |
"eval_steps_per_second": 3.246,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.5729166666666665,
|
| 1095 |
+
"grad_norm": 4.444969177246094,
|
| 1096 |
+
"learning_rate": 1.242586363525737e-05,
|
| 1097 |
+
"loss": 2.8466,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.5833333333333335,
|
| 1102 |
+
"grad_norm": 4.384251594543457,
|
| 1103 |
+
"learning_rate": 1.1950528629100457e-05,
|
| 1104 |
+
"loss": 2.8473,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.59375,
|
| 1109 |
+
"grad_norm": 4.320125102996826,
|
| 1110 |
+
"learning_rate": 1.1482862068344121e-05,
|
| 1111 |
+
"loss": 2.7789,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.6041666666666665,
|
| 1116 |
+
"grad_norm": 4.556283950805664,
|
| 1117 |
+
"learning_rate": 1.1022991808356442e-05,
|
| 1118 |
+
"loss": 2.7603,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.6145833333333335,
|
| 1123 |
+
"grad_norm": 4.58100700378418,
|
| 1124 |
+
"learning_rate": 1.0571043573074737e-05,
|
| 1125 |
+
"loss": 3.0291,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 1.625,
|
| 1130 |
+
"grad_norm": 4.945411205291748,
|
| 1131 |
+
"learning_rate": 1.0127140920633857e-05,
|
| 1132 |
+
"loss": 3.0654,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 1.6354166666666665,
|
| 1137 |
+
"grad_norm": 4.758878231048584,
|
| 1138 |
+
"learning_rate": 9.69140520958662e-06,
|
| 1139 |
+
"loss": 2.9119,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 1.6458333333333335,
|
| 1144 |
+
"grad_norm": 4.71636438369751,
|
| 1145 |
+
"learning_rate": 9.263955565725648e-06,
|
| 1146 |
+
"loss": 2.806,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 1.65625,
|
| 1151 |
+
"grad_norm": 4.838390827178955,
|
| 1152 |
+
"learning_rate": 8.844908849515509e-06,
|
| 1153 |
+
"loss": 2.7424,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 1.6666666666666665,
|
| 1158 |
+
"grad_norm": 4.934096813201904,
|
| 1159 |
+
"learning_rate": 8.434379624144261e-06,
|
| 1160 |
+
"loss": 2.7501,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 1.6770833333333335,
|
| 1165 |
+
"grad_norm": 5.1201372146606445,
|
| 1166 |
+
"learning_rate": 8.032480124203013e-06,
|
| 1167 |
+
"loss": 2.6865,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 1.6875,
|
| 1172 |
+
"grad_norm": 5.0016913414001465,
|
| 1173 |
+
"learning_rate": 7.639320225002106e-06,
|
| 1174 |
+
"loss": 2.703,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 1.6979166666666665,
|
| 1179 |
+
"grad_norm": 5.280127048492432,
|
| 1180 |
+
"learning_rate": 7.255007412532307e-06,
|
| 1181 |
+
"loss": 2.5453,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 1.7083333333333335,
|
| 1186 |
+
"grad_norm": 5.757223606109619,
|
| 1187 |
+
"learning_rate": 6.8796467540791986e-06,
|
| 1188 |
+
"loss": 2.8397,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 1.71875,
|
| 1193 |
+
"grad_norm": 6.4842939376831055,
|
| 1194 |
+
"learning_rate": 6.513340869498859e-06,
|
| 1195 |
+
"loss": 2.8759,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 1.7291666666666665,
|
| 1200 |
+
"grad_norm": 2.9485573768615723,
|
| 1201 |
+
"learning_rate": 6.1561899031625794e-06,
|
| 1202 |
+
"loss": 3.4129,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 1.7395833333333335,
|
| 1207 |
+
"grad_norm": 3.503781318664551,
|
| 1208 |
+
"learning_rate": 5.808291496578435e-06,
|
| 1209 |
+
"loss": 3.3005,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 1.75,
|
| 1214 |
+
"grad_norm": 3.5136566162109375,
|
| 1215 |
+
"learning_rate": 5.469740761697044e-06,
|
| 1216 |
+
"loss": 2.9519,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 1.7604166666666665,
|
| 1221 |
+
"grad_norm": 3.895759344100952,
|
| 1222 |
+
"learning_rate": 5.140630254908905e-06,
|
| 1223 |
+
"loss": 2.9253,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 1.7708333333333335,
|
| 1228 |
+
"grad_norm": 3.9923999309539795,
|
| 1229 |
+
"learning_rate": 4.821049951740442e-06,
|
| 1230 |
+
"loss": 3.0135,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 1.78125,
|
| 1235 |
+
"grad_norm": 4.181189060211182,
|
| 1236 |
+
"learning_rate": 4.511087222255528e-06,
|
| 1237 |
+
"loss": 3.0098,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 1.7916666666666665,
|
| 1242 |
+
"grad_norm": 4.2349677085876465,
|
| 1243 |
+
"learning_rate": 4.2108268071694616e-06,
|
| 1244 |
+
"loss": 2.8849,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 1.8020833333333335,
|
| 1249 |
+
"grad_norm": 4.393781661987305,
|
| 1250 |
+
"learning_rate": 3.9203507946816445e-06,
|
| 1251 |
+
"loss": 2.7841,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 1.8125,
|
| 1256 |
+
"grad_norm": 4.54295015335083,
|
| 1257 |
+
"learning_rate": 3.6397385980335e-06,
|
| 1258 |
+
"loss": 2.8536,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 1.8229166666666665,
|
| 1263 |
+
"grad_norm": 4.6812744140625,
|
| 1264 |
+
"learning_rate": 3.3690669337977e-06,
|
| 1265 |
+
"loss": 2.6508,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 1.8333333333333335,
|
| 1270 |
+
"grad_norm": 4.644638538360596,
|
| 1271 |
+
"learning_rate": 3.1084098009046106e-06,
|
| 1272 |
+
"loss": 2.8156,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 1.84375,
|
| 1277 |
+
"grad_norm": 4.985812187194824,
|
| 1278 |
+
"learning_rate": 2.8578384604117217e-06,
|
| 1279 |
+
"loss": 2.9664,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 1.8541666666666665,
|
| 1284 |
+
"grad_norm": 4.605108261108398,
|
| 1285 |
+
"learning_rate": 2.6174214160215704e-06,
|
| 1286 |
+
"loss": 2.8497,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 1.8645833333333335,
|
| 1291 |
+
"grad_norm": 4.9651384353637695,
|
| 1292 |
+
"learning_rate": 2.3872243953535535e-06,
|
| 1293 |
+
"loss": 2.991,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 1.875,
|
| 1298 |
+
"grad_norm": 4.437888145446777,
|
| 1299 |
+
"learning_rate": 2.1673103319746146e-06,
|
| 1300 |
+
"loss": 2.6755,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 1.8854166666666665,
|
| 1305 |
+
"grad_norm": 5.044173240661621,
|
| 1306 |
+
"learning_rate": 1.957739348193859e-06,
|
| 1307 |
+
"loss": 2.7898,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 1.8958333333333335,
|
| 1312 |
+
"grad_norm": 5.028233528137207,
|
| 1313 |
+
"learning_rate": 1.7585687386256944e-06,
|
| 1314 |
+
"loss": 2.8698,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 1.90625,
|
| 1319 |
+
"grad_norm": 4.980994701385498,
|
| 1320 |
+
"learning_rate": 1.5698529545260744e-06,
|
| 1321 |
+
"loss": 2.6159,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 1.9166666666666665,
|
| 1326 |
+
"grad_norm": 4.991346836090088,
|
| 1327 |
+
"learning_rate": 1.3916435889060575e-06,
|
| 1328 |
+
"loss": 2.6302,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 1.9270833333333335,
|
| 1333 |
+
"grad_norm": 5.023186683654785,
|
| 1334 |
+
"learning_rate": 1.2239893624267852e-06,
|
| 1335 |
+
"loss": 2.604,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 1.9375,
|
| 1340 |
+
"grad_norm": 5.13346004486084,
|
| 1341 |
+
"learning_rate": 1.0669361100797704e-06,
|
| 1342 |
+
"loss": 2.6011,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 1.9479166666666665,
|
| 1347 |
+
"grad_norm": 5.748098373413086,
|
| 1348 |
+
"learning_rate": 9.205267686560293e-07,
|
| 1349 |
+
"loss": 2.8425,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 1.9583333333333335,
|
| 1354 |
+
"grad_norm": 6.5659661293029785,
|
| 1355 |
+
"learning_rate": 7.848013650076258e-07,
|
| 1356 |
+
"loss": 3.2098,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 1.96875,
|
| 1361 |
+
"grad_norm": 3.7293739318847656,
|
| 1362 |
+
"learning_rate": 6.597970051047053e-07,
|
| 1363 |
+
"loss": 3.2201,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 1.9791666666666665,
|
| 1368 |
+
"grad_norm": 4.324611663818359,
|
| 1369 |
+
"learning_rate": 5.455478638911071e-07,
|
| 1370 |
+
"loss": 2.7098,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 1.9895833333333335,
|
| 1375 |
+
"grad_norm": 4.685488700866699,
|
| 1376 |
+
"learning_rate": 4.420851759412603e-07,
|
| 1377 |
+
"loss": 2.5991,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 2.0,
|
| 1382 |
+
"grad_norm": 10.377963066101074,
|
| 1383 |
+
"learning_rate": 3.4943722692099224e-07,
|
| 1384 |
+
"loss": 2.8869,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 2.0104166666666665,
|
| 1389 |
+
"grad_norm": 2.777858257293701,
|
| 1390 |
+
"learning_rate": 2.676293458544743e-07,
|
| 1391 |
+
"loss": 3.2106,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 2.0208333333333335,
|
| 1396 |
+
"grad_norm": 3.0696890354156494,
|
| 1397 |
+
"learning_rate": 1.9668389819954338e-07,
|
| 1398 |
+
"loss": 3.0264,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 2.03125,
|
| 1403 |
+
"grad_norm": 3.3740200996398926,
|
| 1404 |
+
"learning_rate": 1.3662027973320614e-07,
|
| 1405 |
+
"loss": 2.821,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 2.0416666666666665,
|
| 1410 |
+
"grad_norm": 3.355523109436035,
|
| 1411 |
+
"learning_rate": 8.745491124901861e-08,
|
| 1412 |
+
"loss": 2.7618,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 2.0520833333333335,
|
| 1417 |
+
"grad_norm": 3.67665958404541,
|
| 1418 |
+
"learning_rate": 4.920123406781052e-08,
|
| 1419 |
+
"loss": 2.6209,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 2.0625,
|
| 1424 |
+
"grad_norm": 3.688063621520996,
|
| 1425 |
+
"learning_rate": 2.1869706362958044e-08,
|
| 1426 |
+
"loss": 2.4983,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 2.0729166666666665,
|
| 1431 |
+
"grad_norm": 3.78849458694458,
|
| 1432 |
+
"learning_rate": 5.467800301239834e-09,
|
| 1433 |
+
"loss": 2.4865,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 2.0833333333333335,
|
| 1438 |
+
"grad_norm": 4.000704765319824,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 2.5722,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 2.0833333333333335,
|
| 1445 |
+
"eval_loss": 0.986004114151001,
|
| 1446 |
+
"eval_runtime": 12.6315,
|
| 1447 |
+
"eval_samples_per_second": 12.825,
|
| 1448 |
+
"eval_steps_per_second": 3.246,
|
| 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": 2.8924047256662835e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|