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 226530600
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9001245284a3ae67f99992d13eeca3f9c88e004edb7d6cc43f993a909dfe063d
|
| 3 |
size 226530600
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 115354708
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ceeae5b87bcdee7d233d118ab48b4b253d53d1f889602b3cdbb557b778eed8d
|
| 3 |
size 115354708
|
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:a08ab0b9eb8e0241a90df6264a147871f2ca175b4fb6dab904deac44a61b3d67
|
| 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": 27.645,
|
| 1090 |
"eval_steps_per_second": 6.922,
|
| 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": 0.8911738991737366,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.17395085888236572,
|
| 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": 27.645,
|
| 1090 |
"eval_steps_per_second": 6.922,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.13133289845618612,
|
| 1095 |
+
"grad_norm": 1.0323787927627563,
|
| 1096 |
+
"learning_rate": 1.0872630680850196e-05,
|
| 1097 |
+
"loss": 1.3243,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.13220265275059795,
|
| 1102 |
+
"grad_norm": 1.033390998840332,
|
| 1103 |
+
"learning_rate": 1.0456712550462898e-05,
|
| 1104 |
+
"loss": 0.9152,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.13307240704500978,
|
| 1109 |
+
"grad_norm": 0.6028139591217041,
|
| 1110 |
+
"learning_rate": 1.0047504309801104e-05,
|
| 1111 |
+
"loss": 0.0623,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.1339421613394216,
|
| 1116 |
+
"grad_norm": 1.2783890962600708,
|
| 1117 |
+
"learning_rate": 9.645117832311886e-06,
|
| 1118 |
+
"loss": 0.7972,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.13481191563383343,
|
| 1123 |
+
"grad_norm": 3.231074810028076,
|
| 1124 |
+
"learning_rate": 9.249663126440394e-06,
|
| 1125 |
+
"loss": 1.3673,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.13568166992824526,
|
| 1130 |
+
"grad_norm": 3.7593133449554443,
|
| 1131 |
+
"learning_rate": 8.861248305554624e-06,
|
| 1132 |
+
"loss": 1.6542,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.1365514242226571,
|
| 1137 |
+
"grad_norm": 4.1723246574401855,
|
| 1138 |
+
"learning_rate": 8.47997955838829e-06,
|
| 1139 |
+
"loss": 1.5669,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.13742117851706892,
|
| 1144 |
+
"grad_norm": 3.105560779571533,
|
| 1145 |
+
"learning_rate": 8.10596112000994e-06,
|
| 1146 |
+
"loss": 1.016,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.13829093281148075,
|
| 1151 |
+
"grad_norm": 4.72145938873291,
|
| 1152 |
+
"learning_rate": 7.739295243326067e-06,
|
| 1153 |
+
"loss": 0.9057,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.13916068710589258,
|
| 1158 |
+
"grad_norm": 3.747781276702881,
|
| 1159 |
+
"learning_rate": 7.380082171126228e-06,
|
| 1160 |
+
"loss": 1.1365,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.1400304414003044,
|
| 1165 |
+
"grad_norm": 8.871343612670898,
|
| 1166 |
+
"learning_rate": 7.028420108677635e-06,
|
| 1167 |
+
"loss": 2.4637,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.14090019569471623,
|
| 1172 |
+
"grad_norm": 1.415785551071167,
|
| 1173 |
+
"learning_rate": 6.684405196876842e-06,
|
| 1174 |
+
"loss": 1.0646,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.14176994998912806,
|
| 1179 |
+
"grad_norm": 1.160940408706665,
|
| 1180 |
+
"learning_rate": 6.3481314859657675e-06,
|
| 1181 |
+
"loss": 0.2827,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.1426397042835399,
|
| 1186 |
+
"grad_norm": 1.8052855730056763,
|
| 1187 |
+
"learning_rate": 6.019690909819298e-06,
|
| 1188 |
+
"loss": 0.8999,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.14350945857795172,
|
| 1193 |
+
"grad_norm": 1.8529655933380127,
|
| 1194 |
+
"learning_rate": 5.6991732608115e-06,
|
| 1195 |
+
"loss": 0.9477,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.14437921287236355,
|
| 1200 |
+
"grad_norm": 1.4071412086486816,
|
| 1201 |
+
"learning_rate": 5.386666165267256e-06,
|
| 1202 |
+
"loss": 0.7828,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.14524896716677538,
|
| 1207 |
+
"grad_norm": 1.44191575050354,
|
| 1208 |
+
"learning_rate": 5.08225505950613e-06,
|
| 1209 |
+
"loss": 0.635,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.1461187214611872,
|
| 1214 |
+
"grad_norm": 1.5521117448806763,
|
| 1215 |
+
"learning_rate": 4.786023166484913e-06,
|
| 1216 |
+
"loss": 0.7826,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.14698847575559904,
|
| 1221 |
+
"grad_norm": 1.0702335834503174,
|
| 1222 |
+
"learning_rate": 4.498051473045291e-06,
|
| 1223 |
+
"loss": 0.5021,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.14785823005001086,
|
| 1228 |
+
"grad_norm": 1.1577311754226685,
|
| 1229 |
+
"learning_rate": 4.218418707772886e-06,
|
| 1230 |
+
"loss": 0.5002,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.1487279843444227,
|
| 1235 |
+
"grad_norm": 1.6104627847671509,
|
| 1236 |
+
"learning_rate": 3.947201319473587e-06,
|
| 1237 |
+
"loss": 0.829,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.14959773863883452,
|
| 1242 |
+
"grad_norm": 1.1953061819076538,
|
| 1243 |
+
"learning_rate": 3.684473456273278e-06,
|
| 1244 |
+
"loss": 0.6233,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.15046749293324635,
|
| 1249 |
+
"grad_norm": 1.9598382711410522,
|
| 1250 |
+
"learning_rate": 3.4303069453464383e-06,
|
| 1251 |
+
"loss": 0.8955,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.15133724722765818,
|
| 1256 |
+
"grad_norm": 1.169358730316162,
|
| 1257 |
+
"learning_rate": 3.184771273279312e-06,
|
| 1258 |
+
"loss": 0.6012,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.15220700152207,
|
| 1263 |
+
"grad_norm": 1.3640769720077515,
|
| 1264 |
+
"learning_rate": 2.947933567072987e-06,
|
| 1265 |
+
"loss": 0.9693,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.15307675581648184,
|
| 1270 |
+
"grad_norm": 1.183571219444275,
|
| 1271 |
+
"learning_rate": 2.719858575791534e-06,
|
| 1272 |
+
"loss": 0.6275,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.15394651011089366,
|
| 1277 |
+
"grad_norm": 2.071343421936035,
|
| 1278 |
+
"learning_rate": 2.500608652860256e-06,
|
| 1279 |
+
"loss": 0.8547,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.1548162644053055,
|
| 1284 |
+
"grad_norm": 1.216843605041504,
|
| 1285 |
+
"learning_rate": 2.2902437390188737e-06,
|
| 1286 |
+
"loss": 0.5118,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.15568601869971732,
|
| 1291 |
+
"grad_norm": 1.5990781784057617,
|
| 1292 |
+
"learning_rate": 2.0888213459343587e-06,
|
| 1293 |
+
"loss": 0.7752,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.15655577299412915,
|
| 1298 |
+
"grad_norm": 1.300668716430664,
|
| 1299 |
+
"learning_rate": 1.8963965404777875e-06,
|
| 1300 |
+
"loss": 0.9919,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.15742552728854098,
|
| 1305 |
+
"grad_norm": 1.8226401805877686,
|
| 1306 |
+
"learning_rate": 1.7130219296696263e-06,
|
| 1307 |
+
"loss": 0.7846,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.1582952815829528,
|
| 1312 |
+
"grad_norm": 1.361722469329834,
|
| 1313 |
+
"learning_rate": 1.5387476462974824e-06,
|
| 1314 |
+
"loss": 0.8924,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.15916503587736464,
|
| 1319 |
+
"grad_norm": 1.9515739679336548,
|
| 1320 |
+
"learning_rate": 1.3736213352103147e-06,
|
| 1321 |
+
"loss": 0.7486,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.16003479017177646,
|
| 1326 |
+
"grad_norm": 1.5387071371078491,
|
| 1327 |
+
"learning_rate": 1.2176881402928002e-06,
|
| 1328 |
+
"loss": 1.057,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.1609045444661883,
|
| 1333 |
+
"grad_norm": 1.3858706951141357,
|
| 1334 |
+
"learning_rate": 1.0709906921234367e-06,
|
| 1335 |
+
"loss": 0.9382,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.16177429876060012,
|
| 1340 |
+
"grad_norm": 1.3485088348388672,
|
| 1341 |
+
"learning_rate": 9.33569096319799e-07,
|
| 1342 |
+
"loss": 0.6403,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.16264405305501195,
|
| 1347 |
+
"grad_norm": 1.8202433586120605,
|
| 1348 |
+
"learning_rate": 8.054609225740255e-07,
|
| 1349 |
+
"loss": 1.1424,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.16351380734942378,
|
| 1354 |
+
"grad_norm": 1.42926824092865,
|
| 1355 |
+
"learning_rate": 6.867011943816724e-07,
|
| 1356 |
+
"loss": 0.8855,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.1643835616438356,
|
| 1361 |
+
"grad_norm": 1.2389428615570068,
|
| 1362 |
+
"learning_rate": 5.77322379466617e-07,
|
| 1363 |
+
"loss": 0.7007,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.16525331593824744,
|
| 1368 |
+
"grad_norm": 1.506208896636963,
|
| 1369 |
+
"learning_rate": 4.773543809047186e-07,
|
| 1370 |
+
"loss": 0.824,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.16612307023265926,
|
| 1375 |
+
"grad_norm": 1.6370309591293335,
|
| 1376 |
+
"learning_rate": 3.868245289486027e-07,
|
| 1377 |
+
"loss": 0.8759,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.1669928245270711,
|
| 1382 |
+
"grad_norm": 1.0485749244689941,
|
| 1383 |
+
"learning_rate": 3.0575757355586817e-07,
|
| 1384 |
+
"loss": 0.576,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.16786257882148292,
|
| 1389 |
+
"grad_norm": 1.959195852279663,
|
| 1390 |
+
"learning_rate": 2.3417567762266497e-07,
|
| 1391 |
+
"loss": 0.5942,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.16873233311589475,
|
| 1396 |
+
"grad_norm": 1.4763214588165283,
|
| 1397 |
+
"learning_rate": 1.7209841092460043e-07,
|
| 1398 |
+
"loss": 0.8568,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.16960208741030658,
|
| 1403 |
+
"grad_norm": 1.408346176147461,
|
| 1404 |
+
"learning_rate": 1.1954274476655534e-07,
|
| 1405 |
+
"loss": 0.4743,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.1704718417047184,
|
| 1410 |
+
"grad_norm": 1.3717172145843506,
|
| 1411 |
+
"learning_rate": 7.652304734289127e-08,
|
| 1412 |
+
"loss": 0.8862,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.17134159599913024,
|
| 1417 |
+
"grad_norm": 1.5011423826217651,
|
| 1418 |
+
"learning_rate": 4.30510798093342e-08,
|
| 1419 |
+
"loss": 0.7228,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.17221135029354206,
|
| 1424 |
+
"grad_norm": 2.3361780643463135,
|
| 1425 |
+
"learning_rate": 1.9135993067588284e-08,
|
| 1426 |
+
"loss": 1.017,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.1730811045879539,
|
| 1431 |
+
"grad_norm": 1.382851481437683,
|
| 1432 |
+
"learning_rate": 4.784325263584854e-09,
|
| 1433 |
+
"loss": 1.1366,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.17395085888236572,
|
| 1438 |
+
"grad_norm": 2.642244577407837,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.9709,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.17395085888236572,
|
| 1445 |
+
"eval_loss": 0.8911738991737366,
|
| 1446 |
+
"eval_runtime": 69.9221,
|
| 1447 |
+
"eval_samples_per_second": 27.702,
|
| 1448 |
+
"eval_steps_per_second": 6.936,
|
| 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": 6.646460021578138e+16,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|