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 628216
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5d23dd1a5b61c4d3ed7eb8e2f7c5c86eb7f82d4c1b1647084a8d7590624a9ae
|
| 3 |
size 628216
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1273162
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e40f91771dba971377f482b2fc3e80990a715f44b69998c9d15934a26e10f737
|
| 3 |
size 1273162
|
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 sha256:4e02d73ba79bec205b89c636f5685d264097acf62408785a68f0dfc1f9e44a25
|
| 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": 10.
|
| 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": 286.237,
|
| 1090 |
"eval_steps_per_second": 143.137,
|
| 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": 10.745776176452637,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.043215211754537596,
|
| 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": 286.237,
|
| 1090 |
"eval_steps_per_second": 143.137,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.032627484874675886,
|
| 1095 |
+
"grad_norm": 0.2572970688343048,
|
| 1096 |
+
"learning_rate": 1.9136088935510362e-05,
|
| 1097 |
+
"loss": 10.7659,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.032843560933448576,
|
| 1102 |
+
"grad_norm": 0.23141218721866608,
|
| 1103 |
+
"learning_rate": 1.8414449687337464e-05,
|
| 1104 |
+
"loss": 10.7649,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.03305963699222126,
|
| 1109 |
+
"grad_norm": 0.2419702559709549,
|
| 1110 |
+
"learning_rate": 1.7703596875660645e-05,
|
| 1111 |
+
"loss": 10.7615,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.03327571305099395,
|
| 1116 |
+
"grad_norm": 0.19218285381793976,
|
| 1117 |
+
"learning_rate": 1.700377325606388e-05,
|
| 1118 |
+
"loss": 10.7609,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.03349178910976664,
|
| 1123 |
+
"grad_norm": 0.2367192953824997,
|
| 1124 |
+
"learning_rate": 1.631521781767214e-05,
|
| 1125 |
+
"loss": 10.7647,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.033707865168539325,
|
| 1130 |
+
"grad_norm": 0.21695514023303986,
|
| 1131 |
+
"learning_rate": 1.5638165701536868e-05,
|
| 1132 |
+
"loss": 10.765,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.033923941227312016,
|
| 1137 |
+
"grad_norm": 0.2253107875585556,
|
| 1138 |
+
"learning_rate": 1.4972848120335453e-05,
|
| 1139 |
+
"loss": 10.7699,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.0341400172860847,
|
| 1144 |
+
"grad_norm": 0.19992785155773163,
|
| 1145 |
+
"learning_rate": 1.4319492279412388e-05,
|
| 1146 |
+
"loss": 10.7592,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.03435609334485739,
|
| 1151 |
+
"grad_norm": 0.21194936335086823,
|
| 1152 |
+
"learning_rate": 1.3678321299188801e-05,
|
| 1153 |
+
"loss": 10.7629,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.03457216940363008,
|
| 1158 |
+
"grad_norm": 0.26007580757141113,
|
| 1159 |
+
"learning_rate": 1.3049554138967051e-05,
|
| 1160 |
+
"loss": 10.7648,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.034788245462402764,
|
| 1165 |
+
"grad_norm": 0.22751381993293762,
|
| 1166 |
+
"learning_rate": 1.2433405522156332e-05,
|
| 1167 |
+
"loss": 10.7603,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.035004321521175455,
|
| 1172 |
+
"grad_norm": 0.2545979619026184,
|
| 1173 |
+
"learning_rate": 1.183008586294485e-05,
|
| 1174 |
+
"loss": 10.7617,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.03522039757994814,
|
| 1179 |
+
"grad_norm": 0.20070402324199677,
|
| 1180 |
+
"learning_rate": 1.1239801194443506e-05,
|
| 1181 |
+
"loss": 10.7547,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.03543647363872083,
|
| 1186 |
+
"grad_norm": 0.20730213820934296,
|
| 1187 |
+
"learning_rate": 1.066275309832584e-05,
|
| 1188 |
+
"loss": 10.761,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.03565254969749352,
|
| 1193 |
+
"grad_norm": 0.2222391963005066,
|
| 1194 |
+
"learning_rate": 1.0099138635988026e-05,
|
| 1195 |
+
"loss": 10.7707,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.035868625756266204,
|
| 1200 |
+
"grad_norm": 0.21017976105213165,
|
| 1201 |
+
"learning_rate": 9.549150281252633e-06,
|
| 1202 |
+
"loss": 10.7582,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.036084701815038894,
|
| 1207 |
+
"grad_norm": 0.21349570155143738,
|
| 1208 |
+
"learning_rate": 9.012975854638949e-06,
|
| 1209 |
+
"loss": 10.7534,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.036300777873811585,
|
| 1214 |
+
"grad_norm": 0.19311493635177612,
|
| 1215 |
+
"learning_rate": 8.490798459222476e-06,
|
| 1216 |
+
"loss": 10.7536,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.03651685393258427,
|
| 1221 |
+
"grad_norm": 0.18329201638698578,
|
| 1222 |
+
"learning_rate": 7.982796418105371e-06,
|
| 1223 |
+
"loss": 10.7595,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.03673292999135696,
|
| 1228 |
+
"grad_norm": 0.24617359042167664,
|
| 1229 |
+
"learning_rate": 7.489143213519301e-06,
|
| 1230 |
+
"loss": 10.7562,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.03694900605012964,
|
| 1235 |
+
"grad_norm": 0.24574460089206696,
|
| 1236 |
+
"learning_rate": 7.010007427581378e-06,
|
| 1237 |
+
"loss": 10.7496,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.037165082108902334,
|
| 1242 |
+
"grad_norm": 0.2094903290271759,
|
| 1243 |
+
"learning_rate": 6.5455526847235825e-06,
|
| 1244 |
+
"loss": 10.7454,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.037381158167675024,
|
| 1249 |
+
"grad_norm": 0.23481670022010803,
|
| 1250 |
+
"learning_rate": 6.0959375958151045e-06,
|
| 1251 |
+
"loss": 10.7503,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.03759723422644771,
|
| 1256 |
+
"grad_norm": 0.20529882609844208,
|
| 1257 |
+
"learning_rate": 5.6613157039969055e-06,
|
| 1258 |
+
"loss": 10.7551,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.0378133102852204,
|
| 1263 |
+
"grad_norm": 0.2087268829345703,
|
| 1264 |
+
"learning_rate": 5.241835432246889e-06,
|
| 1265 |
+
"loss": 10.7512,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.03802938634399308,
|
| 1270 |
+
"grad_norm": 0.24301747977733612,
|
| 1271 |
+
"learning_rate": 4.837640032693558e-06,
|
| 1272 |
+
"loss": 10.7587,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.03824546240276577,
|
| 1277 |
+
"grad_norm": 0.24005451798439026,
|
| 1278 |
+
"learning_rate": 4.448867537695578e-06,
|
| 1279 |
+
"loss": 10.7615,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.038461538461538464,
|
| 1284 |
+
"grad_norm": 0.2205115705728531,
|
| 1285 |
+
"learning_rate": 4.075650712703849e-06,
|
| 1286 |
+
"loss": 10.7405,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.03867761452031115,
|
| 1291 |
+
"grad_norm": 0.22657622396945953,
|
| 1292 |
+
"learning_rate": 3.71811701092219e-06,
|
| 1293 |
+
"loss": 10.7544,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.03889369057908384,
|
| 1298 |
+
"grad_norm": 0.24251677095890045,
|
| 1299 |
+
"learning_rate": 3.376388529782215e-06,
|
| 1300 |
+
"loss": 10.7535,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.03910976663785653,
|
| 1305 |
+
"grad_norm": 0.22308377921581268,
|
| 1306 |
+
"learning_rate": 3.0505819692471792e-06,
|
| 1307 |
+
"loss": 10.7536,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.03932584269662921,
|
| 1312 |
+
"grad_norm": 0.2320922166109085,
|
| 1313 |
+
"learning_rate": 2.7408085919590264e-06,
|
| 1314 |
+
"loss": 10.7482,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.0395419187554019,
|
| 1319 |
+
"grad_norm": 0.23464159667491913,
|
| 1320 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 1321 |
+
"loss": 10.7496,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.03975799481417459,
|
| 1326 |
+
"grad_norm": 0.21937261521816254,
|
| 1327 |
+
"learning_rate": 2.1697790249779636e-06,
|
| 1328 |
+
"loss": 10.7502,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.03997407087294728,
|
| 1333 |
+
"grad_norm": 0.23580560088157654,
|
| 1334 |
+
"learning_rate": 1.908717841359048e-06,
|
| 1335 |
+
"loss": 10.7532,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.04019014693171997,
|
| 1340 |
+
"grad_norm": 0.2424219399690628,
|
| 1341 |
+
"learning_rate": 1.6640797865406288e-06,
|
| 1342 |
+
"loss": 10.745,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.04040622299049265,
|
| 1347 |
+
"grad_norm": 0.2548362612724304,
|
| 1348 |
+
"learning_rate": 1.4359484041943038e-06,
|
| 1349 |
+
"loss": 10.7458,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.04062229904926534,
|
| 1354 |
+
"grad_norm": 0.31250232458114624,
|
| 1355 |
+
"learning_rate": 1.2244016009781701e-06,
|
| 1356 |
+
"loss": 10.744,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.040838375108038026,
|
| 1361 |
+
"grad_norm": 0.2745141088962555,
|
| 1362 |
+
"learning_rate": 1.0295116199317057e-06,
|
| 1363 |
+
"loss": 10.7386,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.04105445116681072,
|
| 1368 |
+
"grad_norm": 0.2804180383682251,
|
| 1369 |
+
"learning_rate": 8.513450158049108e-07,
|
| 1370 |
+
"loss": 10.7314,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.04127052722558341,
|
| 1375 |
+
"grad_norm": 0.2679109573364258,
|
| 1376 |
+
"learning_rate": 6.899626323298713e-07,
|
| 1377 |
+
"loss": 10.7439,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.04148660328435609,
|
| 1382 |
+
"grad_norm": 0.22815419733524323,
|
| 1383 |
+
"learning_rate": 5.454195814427021e-07,
|
| 1384 |
+
"loss": 10.7384,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.04170267934312878,
|
| 1389 |
+
"grad_norm": 0.2827376127243042,
|
| 1390 |
+
"learning_rate": 4.177652244628627e-07,
|
| 1391 |
+
"loss": 10.7385,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.04191875540190147,
|
| 1396 |
+
"grad_norm": 0.3146594762802124,
|
| 1397 |
+
"learning_rate": 3.0704315523631953e-07,
|
| 1398 |
+
"loss": 10.7451,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.042134831460674156,
|
| 1403 |
+
"grad_norm": 0.30587294697761536,
|
| 1404 |
+
"learning_rate": 2.1329118524827662e-07,
|
| 1405 |
+
"loss": 10.7321,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.04235090751944685,
|
| 1410 |
+
"grad_norm": 0.26626572012901306,
|
| 1411 |
+
"learning_rate": 1.3654133071059893e-07,
|
| 1412 |
+
"loss": 10.7262,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.04256698357821953,
|
| 1417 |
+
"grad_norm": 0.3111208975315094,
|
| 1418 |
+
"learning_rate": 7.681980162830282e-08,
|
| 1419 |
+
"loss": 10.7239,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.04278305963699222,
|
| 1424 |
+
"grad_norm": 0.4671022891998291,
|
| 1425 |
+
"learning_rate": 3.4146992848854695e-08,
|
| 1426 |
+
"loss": 10.7375,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.04299913569576491,
|
| 1431 |
+
"grad_norm": 0.520592987537384,
|
| 1432 |
+
"learning_rate": 8.537477097364522e-09,
|
| 1433 |
+
"loss": 10.7301,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.043215211754537596,
|
| 1438 |
+
"grad_norm": 0.5407875776290894,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 10.6871,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.043215211754537596,
|
| 1445 |
+
"eval_loss": 10.745776176452637,
|
| 1446 |
+
"eval_runtime": 27.2162,
|
| 1447 |
+
"eval_samples_per_second": 286.41,
|
| 1448 |
+
"eval_steps_per_second": 143.223,
|
| 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": 139523405119488.0,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|