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 295488936
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e5f154deac9a71bfe711fc0506435928183af309faff6489032c77de80d9395
|
| 3 |
size 295488936
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 150486964
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:208a44cf89f0febdefb24bc3e2bba3530d8038f178ca89b8e5e513118b5028c7
|
| 3 |
size 150486964
|
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:b8a36cb9432b3165944a606a076eb2e867ae65389cfaae6b940b06690320dd1d
|
| 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:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
|
| 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": 19.498,
|
| 1090 |
"eval_steps_per_second": 4.879,
|
| 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": 0.6931376457214355,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.11242270938729623,
|
| 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": 19.498,
|
| 1090 |
"eval_steps_per_second": 4.879,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.08487914558740865,
|
| 1095 |
+
"grad_norm": 0.2130131870508194,
|
| 1096 |
+
"learning_rate": 1.553232954407171e-05,
|
| 1097 |
+
"loss": 0.6602,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.08544125913434514,
|
| 1102 |
+
"grad_norm": 0.22044633328914642,
|
| 1103 |
+
"learning_rate": 1.4938160786375572e-05,
|
| 1104 |
+
"loss": 0.7375,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.08600337268128162,
|
| 1109 |
+
"grad_norm": 0.22082433104515076,
|
| 1110 |
+
"learning_rate": 1.435357758543015e-05,
|
| 1111 |
+
"loss": 0.7209,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.0865654862282181,
|
| 1116 |
+
"grad_norm": 0.22511936724185944,
|
| 1117 |
+
"learning_rate": 1.3778739760445552e-05,
|
| 1118 |
+
"loss": 0.7309,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.08712759977515458,
|
| 1123 |
+
"grad_norm": 0.2308863252401352,
|
| 1124 |
+
"learning_rate": 1.3213804466343421e-05,
|
| 1125 |
+
"loss": 0.7923,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.08768971332209106,
|
| 1130 |
+
"grad_norm": 0.21585489809513092,
|
| 1131 |
+
"learning_rate": 1.2658926150792322e-05,
|
| 1132 |
+
"loss": 0.7136,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.08825182686902755,
|
| 1137 |
+
"grad_norm": 0.1969076246023178,
|
| 1138 |
+
"learning_rate": 1.2114256511983274e-05,
|
| 1139 |
+
"loss": 0.6307,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.08881394041596402,
|
| 1144 |
+
"grad_norm": 0.20867222547531128,
|
| 1145 |
+
"learning_rate": 1.157994445715706e-05,
|
| 1146 |
+
"loss": 0.7262,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.0893760539629005,
|
| 1151 |
+
"grad_norm": 0.2237229198217392,
|
| 1152 |
+
"learning_rate": 1.1056136061894384e-05,
|
| 1153 |
+
"loss": 0.8582,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.08993816750983699,
|
| 1158 |
+
"grad_norm": 0.20306715369224548,
|
| 1159 |
+
"learning_rate": 1.0542974530180327e-05,
|
| 1160 |
+
"loss": 0.6869,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.09050028105677346,
|
| 1165 |
+
"grad_norm": 0.20422999560832977,
|
| 1166 |
+
"learning_rate": 1.0040600155253765e-05,
|
| 1167 |
+
"loss": 0.6442,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.09106239460370995,
|
| 1172 |
+
"grad_norm": 0.2120133638381958,
|
| 1173 |
+
"learning_rate": 9.549150281252633e-06,
|
| 1174 |
+
"loss": 0.7157,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.09162450815064643,
|
| 1179 |
+
"grad_norm": 0.20366635918617249,
|
| 1180 |
+
"learning_rate": 9.068759265665384e-06,
|
| 1181 |
+
"loss": 0.667,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.09218662169758292,
|
| 1186 |
+
"grad_norm": 0.20207980275154114,
|
| 1187 |
+
"learning_rate": 8.599558442598998e-06,
|
| 1188 |
+
"loss": 0.668,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.09274873524451939,
|
| 1193 |
+
"grad_norm": 0.21069107949733734,
|
| 1194 |
+
"learning_rate": 8.141676086873572e-06,
|
| 1195 |
+
"loss": 0.6796,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.09331084879145587,
|
| 1200 |
+
"grad_norm": 0.2175239622592926,
|
| 1201 |
+
"learning_rate": 7.695237378953223e-06,
|
| 1202 |
+
"loss": 0.7184,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.09387296233839236,
|
| 1207 |
+
"grad_norm": 0.21470816433429718,
|
| 1208 |
+
"learning_rate": 7.260364370723044e-06,
|
| 1209 |
+
"loss": 0.7699,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.09443507588532883,
|
| 1214 |
+
"grad_norm": 0.22422847151756287,
|
| 1215 |
+
"learning_rate": 6.837175952121306e-06,
|
| 1216 |
+
"loss": 0.7401,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.09499718943226532,
|
| 1221 |
+
"grad_norm": 0.20559588074684143,
|
| 1222 |
+
"learning_rate": 6.425787818636131e-06,
|
| 1223 |
+
"loss": 0.6683,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.0955593029792018,
|
| 1228 |
+
"grad_norm": 0.2030762881040573,
|
| 1229 |
+
"learning_rate": 6.026312439675552e-06,
|
| 1230 |
+
"loss": 0.6298,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.09612141652613827,
|
| 1235 |
+
"grad_norm": 0.2249382585287094,
|
| 1236 |
+
"learning_rate": 5.6388590278194096e-06,
|
| 1237 |
+
"loss": 0.7109,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.09668353007307476,
|
| 1242 |
+
"grad_norm": 0.20573142170906067,
|
| 1243 |
+
"learning_rate": 5.263533508961827e-06,
|
| 1244 |
+
"loss": 0.6841,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.09724564362001124,
|
| 1249 |
+
"grad_norm": 0.21552424132823944,
|
| 1250 |
+
"learning_rate": 4.900438493352055e-06,
|
| 1251 |
+
"loss": 0.7023,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.09780775716694773,
|
| 1256 |
+
"grad_norm": 0.23321565985679626,
|
| 1257 |
+
"learning_rate": 4.549673247541875e-06,
|
| 1258 |
+
"loss": 0.7863,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.0983698707138842,
|
| 1263 |
+
"grad_norm": 0.22396357357501984,
|
| 1264 |
+
"learning_rate": 4.2113336672471245e-06,
|
| 1265 |
+
"loss": 0.6949,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.09893198426082069,
|
| 1270 |
+
"grad_norm": 0.221019446849823,
|
| 1271 |
+
"learning_rate": 3.885512251130763e-06,
|
| 1272 |
+
"loss": 0.6837,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.09949409780775717,
|
| 1277 |
+
"grad_norm": 0.23884433507919312,
|
| 1278 |
+
"learning_rate": 3.5722980755146517e-06,
|
| 1279 |
+
"loss": 0.7241,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.10005621135469364,
|
| 1284 |
+
"grad_norm": 0.22143976390361786,
|
| 1285 |
+
"learning_rate": 3.271776770026963e-06,
|
| 1286 |
+
"loss": 0.6508,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.10061832490163013,
|
| 1291 |
+
"grad_norm": 0.21537278592586517,
|
| 1292 |
+
"learning_rate": 2.9840304941919415e-06,
|
| 1293 |
+
"loss": 0.6533,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.10118043844856661,
|
| 1298 |
+
"grad_norm": 0.2413482517004013,
|
| 1299 |
+
"learning_rate": 2.7091379149682685e-06,
|
| 1300 |
+
"loss": 0.6989,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.1017425519955031,
|
| 1305 |
+
"grad_norm": 0.2332078218460083,
|
| 1306 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 1307 |
+
"loss": 0.6716,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.10230466554243957,
|
| 1312 |
+
"grad_norm": 0.23012611269950867,
|
| 1313 |
+
"learning_rate": 2.1982109232821178e-06,
|
| 1314 |
+
"loss": 0.6486,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.10286677908937605,
|
| 1319 |
+
"grad_norm": 0.24042926728725433,
|
| 1320 |
+
"learning_rate": 1.962316193157593e-06,
|
| 1321 |
+
"loss": 0.7261,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.10342889263631254,
|
| 1326 |
+
"grad_norm": 0.24805034697055817,
|
| 1327 |
+
"learning_rate": 1.7395544861325718e-06,
|
| 1328 |
+
"loss": 0.7689,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.10399100618324901,
|
| 1333 |
+
"grad_norm": 0.23157480359077454,
|
| 1334 |
+
"learning_rate": 1.5299867030334814e-06,
|
| 1335 |
+
"loss": 0.6196,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.1045531197301855,
|
| 1340 |
+
"grad_norm": 0.24432821571826935,
|
| 1341 |
+
"learning_rate": 1.333670137599713e-06,
|
| 1342 |
+
"loss": 0.63,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.10511523327712198,
|
| 1347 |
+
"grad_norm": 0.25453731417655945,
|
| 1348 |
+
"learning_rate": 1.1506584608200367e-06,
|
| 1349 |
+
"loss": 0.7884,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.10567734682405847,
|
| 1354 |
+
"grad_norm": 0.24758335947990417,
|
| 1355 |
+
"learning_rate": 9.810017062595322e-07,
|
| 1356 |
+
"loss": 0.6942,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.10623946037099494,
|
| 1361 |
+
"grad_norm": 0.2643246352672577,
|
| 1362 |
+
"learning_rate": 8.247462563808817e-07,
|
| 1363 |
+
"loss": 0.7022,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.10680157391793142,
|
| 1368 |
+
"grad_norm": 0.2577090561389923,
|
| 1369 |
+
"learning_rate": 6.819348298638839e-07,
|
| 1370 |
+
"loss": 0.6797,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.10736368746486791,
|
| 1375 |
+
"grad_norm": 0.2560056447982788,
|
| 1376 |
+
"learning_rate": 5.526064699265753e-07,
|
| 1377 |
+
"loss": 0.6244,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.10792580101180438,
|
| 1382 |
+
"grad_norm": 0.275604248046875,
|
| 1383 |
+
"learning_rate": 4.367965336512403e-07,
|
| 1384 |
+
"loss": 0.7325,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.10848791455874086,
|
| 1389 |
+
"grad_norm": 0.28054916858673096,
|
| 1390 |
+
"learning_rate": 3.3453668231809286e-07,
|
| 1391 |
+
"loss": 0.6345,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.10905002810567735,
|
| 1396 |
+
"grad_norm": 0.28916385769844055,
|
| 1397 |
+
"learning_rate": 2.458548727494292e-07,
|
| 1398 |
+
"loss": 0.6774,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.10961214165261383,
|
| 1403 |
+
"grad_norm": 0.3085208535194397,
|
| 1404 |
+
"learning_rate": 1.7077534966650766e-07,
|
| 1405 |
+
"loss": 0.6975,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.1101742551995503,
|
| 1410 |
+
"grad_norm": 0.3017449975013733,
|
| 1411 |
+
"learning_rate": 1.0931863906127327e-07,
|
| 1412 |
+
"loss": 0.6729,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.11073636874648679,
|
| 1417 |
+
"grad_norm": 0.33686646819114685,
|
| 1418 |
+
"learning_rate": 6.150154258476315e-08,
|
| 1419 |
+
"loss": 0.6607,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.11129848229342328,
|
| 1424 |
+
"grad_norm": 0.34082940220832825,
|
| 1425 |
+
"learning_rate": 2.7337132953697554e-08,
|
| 1426 |
+
"loss": 0.6851,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.11186059584035975,
|
| 1431 |
+
"grad_norm": 0.38982468843460083,
|
| 1432 |
+
"learning_rate": 6.834750376549792e-09,
|
| 1433 |
+
"loss": 0.8287,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.11242270938729623,
|
| 1438 |
+
"grad_norm": 0.5186094641685486,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.6823,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.11242270938729623,
|
| 1445 |
+
"eval_loss": 0.6931376457214355,
|
| 1446 |
+
"eval_runtime": 153.9477,
|
| 1447 |
+
"eval_samples_per_second": 19.468,
|
| 1448 |
+
"eval_steps_per_second": 4.872,
|
| 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": 9.545476428791808e+16,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|