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:ba87be63406b3f4b49ce6994c222c7af2d0ab2b0ec67b67269df1b5fa5eb8b7b
|
| 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 sha256:2b854a3b1df22060c540b945e7a045efaa5d627f5afe087ce64e73ada1e48746
|
| 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 sha256:9e8e3265102d945ff4d891d3415f32c4ed4adcdeb974e2117e421caa4a7f1944
|
| 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:b60d6f1383abda4776549360effee800fe6cfe2c0604503e9e3fbaa79347f790
|
| 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": 13.114,
|
| 1090 |
"eval_steps_per_second": 3.28,
|
| 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": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.2108319103717804,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.05700441784238278,
|
| 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": 13.114,
|
| 1090 |
"eval_steps_per_second": 3.28,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.043038335470999,
|
| 1095 |
+
"grad_norm": 0.281355082988739,
|
| 1096 |
+
"learning_rate": 1.0872630680850196e-05,
|
| 1097 |
+
"loss": 0.306,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.04332335756021092,
|
| 1102 |
+
"grad_norm": 0.3525282144546509,
|
| 1103 |
+
"learning_rate": 1.0456712550462898e-05,
|
| 1104 |
+
"loss": 0.4085,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.04360837964942283,
|
| 1109 |
+
"grad_norm": 0.3436671197414398,
|
| 1110 |
+
"learning_rate": 1.0047504309801104e-05,
|
| 1111 |
+
"loss": 0.3022,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.04389340173863474,
|
| 1116 |
+
"grad_norm": 0.3466765284538269,
|
| 1117 |
+
"learning_rate": 9.645117832311886e-06,
|
| 1118 |
+
"loss": 0.3076,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.04417842382784666,
|
| 1123 |
+
"grad_norm": 0.3465212285518646,
|
| 1124 |
+
"learning_rate": 9.249663126440394e-06,
|
| 1125 |
+
"loss": 0.2955,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.04446344591705857,
|
| 1130 |
+
"grad_norm": 0.35070881247520447,
|
| 1131 |
+
"learning_rate": 8.861248305554624e-06,
|
| 1132 |
+
"loss": 0.2727,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.044748468006270484,
|
| 1137 |
+
"grad_norm": 0.36707839369773865,
|
| 1138 |
+
"learning_rate": 8.47997955838829e-06,
|
| 1139 |
+
"loss": 0.285,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.0450334900954824,
|
| 1144 |
+
"grad_norm": 0.3160535395145416,
|
| 1145 |
+
"learning_rate": 8.10596112000994e-06,
|
| 1146 |
+
"loss": 0.2678,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.045318512184694314,
|
| 1151 |
+
"grad_norm": 0.3351013958454132,
|
| 1152 |
+
"learning_rate": 7.739295243326067e-06,
|
| 1153 |
+
"loss": 0.2542,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.045603534273906225,
|
| 1158 |
+
"grad_norm": 0.34178030490875244,
|
| 1159 |
+
"learning_rate": 7.380082171126228e-06,
|
| 1160 |
+
"loss": 0.2527,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.045888556363118144,
|
| 1165 |
+
"grad_norm": 0.34601011872291565,
|
| 1166 |
+
"learning_rate": 7.028420108677635e-06,
|
| 1167 |
+
"loss": 0.2287,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.046173578452330055,
|
| 1172 |
+
"grad_norm": 0.3409976065158844,
|
| 1173 |
+
"learning_rate": 6.684405196876842e-06,
|
| 1174 |
+
"loss": 0.2697,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.04645860054154197,
|
| 1179 |
+
"grad_norm": 0.32013270258903503,
|
| 1180 |
+
"learning_rate": 6.3481314859657675e-06,
|
| 1181 |
+
"loss": 0.1984,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.046743622630753885,
|
| 1186 |
+
"grad_norm": 0.3430671691894531,
|
| 1187 |
+
"learning_rate": 6.019690909819298e-06,
|
| 1188 |
+
"loss": 0.2599,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.0470286447199658,
|
| 1193 |
+
"grad_norm": 0.306186705827713,
|
| 1194 |
+
"learning_rate": 5.6991732608115e-06,
|
| 1195 |
+
"loss": 0.2162,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.04731366680917771,
|
| 1200 |
+
"grad_norm": 0.359751433134079,
|
| 1201 |
+
"learning_rate": 5.386666165267256e-06,
|
| 1202 |
+
"loss": 0.223,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.04759868889838963,
|
| 1207 |
+
"grad_norm": 0.3521772623062134,
|
| 1208 |
+
"learning_rate": 5.08225505950613e-06,
|
| 1209 |
+
"loss": 0.2374,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.04788371098760154,
|
| 1214 |
+
"grad_norm": 0.3709127604961395,
|
| 1215 |
+
"learning_rate": 4.786023166484913e-06,
|
| 1216 |
+
"loss": 0.2737,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.04816873307681345,
|
| 1221 |
+
"grad_norm": 0.3508308529853821,
|
| 1222 |
+
"learning_rate": 4.498051473045291e-06,
|
| 1223 |
+
"loss": 0.2643,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.04845375516602537,
|
| 1228 |
+
"grad_norm": 0.3326634466648102,
|
| 1229 |
+
"learning_rate": 4.218418707772886e-06,
|
| 1230 |
+
"loss": 0.2183,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.04873877725523728,
|
| 1235 |
+
"grad_norm": 0.39563068747520447,
|
| 1236 |
+
"learning_rate": 3.947201319473587e-06,
|
| 1237 |
+
"loss": 0.2757,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.0490237993444492,
|
| 1242 |
+
"grad_norm": 0.3203083574771881,
|
| 1243 |
+
"learning_rate": 3.684473456273278e-06,
|
| 1244 |
+
"loss": 0.1658,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.04930882143366111,
|
| 1249 |
+
"grad_norm": 0.3669796884059906,
|
| 1250 |
+
"learning_rate": 3.4303069453464383e-06,
|
| 1251 |
+
"loss": 0.2462,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.04959384352287302,
|
| 1256 |
+
"grad_norm": 0.3505097031593323,
|
| 1257 |
+
"learning_rate": 3.184771273279312e-06,
|
| 1258 |
+
"loss": 0.1769,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.04987886561208494,
|
| 1263 |
+
"grad_norm": 0.33034375309944153,
|
| 1264 |
+
"learning_rate": 2.947933567072987e-06,
|
| 1265 |
+
"loss": 0.2077,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.05016388770129685,
|
| 1270 |
+
"grad_norm": 0.31688281893730164,
|
| 1271 |
+
"learning_rate": 2.719858575791534e-06,
|
| 1272 |
+
"loss": 0.18,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.05044890979050876,
|
| 1277 |
+
"grad_norm": 0.3017065227031708,
|
| 1278 |
+
"learning_rate": 2.500608652860256e-06,
|
| 1279 |
+
"loss": 0.18,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.05073393187972068,
|
| 1284 |
+
"grad_norm": 0.4137319326400757,
|
| 1285 |
+
"learning_rate": 2.2902437390188737e-06,
|
| 1286 |
+
"loss": 0.235,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.05101895396893259,
|
| 1291 |
+
"grad_norm": 0.3511267900466919,
|
| 1292 |
+
"learning_rate": 2.0888213459343587e-06,
|
| 1293 |
+
"loss": 0.1845,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.051303976058144504,
|
| 1298 |
+
"grad_norm": 0.32434019446372986,
|
| 1299 |
+
"learning_rate": 1.8963965404777875e-06,
|
| 1300 |
+
"loss": 0.133,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.05158899814735642,
|
| 1305 |
+
"grad_norm": 0.35862478613853455,
|
| 1306 |
+
"learning_rate": 1.7130219296696263e-06,
|
| 1307 |
+
"loss": 0.1806,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.051874020236568334,
|
| 1312 |
+
"grad_norm": 0.36328455805778503,
|
| 1313 |
+
"learning_rate": 1.5387476462974824e-06,
|
| 1314 |
+
"loss": 0.1922,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.052159042325780246,
|
| 1319 |
+
"grad_norm": 0.38937562704086304,
|
| 1320 |
+
"learning_rate": 1.3736213352103147e-06,
|
| 1321 |
+
"loss": 0.2177,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.052444064414992164,
|
| 1326 |
+
"grad_norm": 0.2989131212234497,
|
| 1327 |
+
"learning_rate": 1.2176881402928002e-06,
|
| 1328 |
+
"loss": 0.1575,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.052729086504204076,
|
| 1333 |
+
"grad_norm": 0.3432283103466034,
|
| 1334 |
+
"learning_rate": 1.0709906921234367e-06,
|
| 1335 |
+
"loss": 0.1829,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.05301410859341599,
|
| 1340 |
+
"grad_norm": 0.3284221291542053,
|
| 1341 |
+
"learning_rate": 9.33569096319799e-07,
|
| 1342 |
+
"loss": 0.1379,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.053299130682627906,
|
| 1347 |
+
"grad_norm": 0.3415944278240204,
|
| 1348 |
+
"learning_rate": 8.054609225740255e-07,
|
| 1349 |
+
"loss": 0.1432,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.05358415277183982,
|
| 1354 |
+
"grad_norm": 0.30469295382499695,
|
| 1355 |
+
"learning_rate": 6.867011943816724e-07,
|
| 1356 |
+
"loss": 0.1457,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.05386917486105173,
|
| 1361 |
+
"grad_norm": 0.3219231963157654,
|
| 1362 |
+
"learning_rate": 5.77322379466617e-07,
|
| 1363 |
+
"loss": 0.1493,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.05415419695026365,
|
| 1368 |
+
"grad_norm": 0.3684932589530945,
|
| 1369 |
+
"learning_rate": 4.773543809047186e-07,
|
| 1370 |
+
"loss": 0.1963,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.05443921903947556,
|
| 1375 |
+
"grad_norm": 0.30849573016166687,
|
| 1376 |
+
"learning_rate": 3.868245289486027e-07,
|
| 1377 |
+
"loss": 0.1481,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.05472424112868747,
|
| 1382 |
+
"grad_norm": 0.40836629271507263,
|
| 1383 |
+
"learning_rate": 3.0575757355586817e-07,
|
| 1384 |
+
"loss": 0.2133,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.05500926321789939,
|
| 1389 |
+
"grad_norm": 0.3660025894641876,
|
| 1390 |
+
"learning_rate": 2.3417567762266497e-07,
|
| 1391 |
+
"loss": 0.1697,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.0552942853071113,
|
| 1396 |
+
"grad_norm": 0.37223172187805176,
|
| 1397 |
+
"learning_rate": 1.7209841092460043e-07,
|
| 1398 |
+
"loss": 0.1186,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.05557930739632321,
|
| 1403 |
+
"grad_norm": 0.38398411870002747,
|
| 1404 |
+
"learning_rate": 1.1954274476655534e-07,
|
| 1405 |
+
"loss": 0.1734,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.05586432948553513,
|
| 1410 |
+
"grad_norm": 0.3642955422401428,
|
| 1411 |
+
"learning_rate": 7.652304734289127e-08,
|
| 1412 |
+
"loss": 0.1738,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.05614935157474704,
|
| 1417 |
+
"grad_norm": 0.3336471915245056,
|
| 1418 |
+
"learning_rate": 4.30510798093342e-08,
|
| 1419 |
+
"loss": 0.1381,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.05643437366395896,
|
| 1424 |
+
"grad_norm": 0.4195612668991089,
|
| 1425 |
+
"learning_rate": 1.9135993067588284e-08,
|
| 1426 |
+
"loss": 0.17,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.05671939575317087,
|
| 1431 |
+
"grad_norm": 0.4140312969684601,
|
| 1432 |
+
"learning_rate": 4.784325263584854e-09,
|
| 1433 |
+
"loss": 0.1507,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.05700441784238278,
|
| 1438 |
+
"grad_norm": 0.4781356453895569,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.143,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.05700441784238278,
|
| 1445 |
+
"eval_loss": 0.2108319103717804,
|
| 1446 |
+
"eval_runtime": 450.142,
|
| 1447 |
+
"eval_samples_per_second": 13.127,
|
| 1448 |
+
"eval_steps_per_second": 3.283,
|
| 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": 3.024569725385441e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|