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 sha256:7b56d7ce4cc6a16eb26ebcd0c69c98e3c457d30e2714e23bbe0850b9fd2b3838
|
| 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 sha256:83baa310e1dba0a7550a118d027b2dbf738abf2a6554055de0fff4757e9f69c8
|
| 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 14180
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f71936b5c4cff1cb03b7ea1f012a7d6570bffc03f561a681fb5e0ed80a7a28e
|
| 3 |
size 14180
|
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": 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": 33.659,
|
| 1090 |
"eval_steps_per_second": 8.432,
|
| 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": 0.6537404656410217,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.3401360544217687,
|
| 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": 33.659,
|
| 1090 |
"eval_steps_per_second": 8.432,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.2568027210884354,
|
| 1095 |
+
"grad_norm": 0.20743505656719208,
|
| 1096 |
+
"learning_rate": 1.242586363525737e-05,
|
| 1097 |
+
"loss": 0.5836,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.2585034013605442,
|
| 1102 |
+
"grad_norm": 0.23101773858070374,
|
| 1103 |
+
"learning_rate": 1.1950528629100457e-05,
|
| 1104 |
+
"loss": 0.6812,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.2602040816326531,
|
| 1109 |
+
"grad_norm": 0.22349244356155396,
|
| 1110 |
+
"learning_rate": 1.1482862068344121e-05,
|
| 1111 |
+
"loss": 0.6376,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.2619047619047619,
|
| 1116 |
+
"grad_norm": 0.23622667789459229,
|
| 1117 |
+
"learning_rate": 1.1022991808356442e-05,
|
| 1118 |
+
"loss": 0.6703,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.26360544217687076,
|
| 1123 |
+
"grad_norm": 0.2300838977098465,
|
| 1124 |
+
"learning_rate": 1.0571043573074737e-05,
|
| 1125 |
+
"loss": 0.6579,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.2653061224489796,
|
| 1130 |
+
"grad_norm": 0.23446151614189148,
|
| 1131 |
+
"learning_rate": 1.0127140920633857e-05,
|
| 1132 |
+
"loss": 0.6648,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.26700680272108845,
|
| 1137 |
+
"grad_norm": 0.23773601651191711,
|
| 1138 |
+
"learning_rate": 9.69140520958662e-06,
|
| 1139 |
+
"loss": 0.6624,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.2687074829931973,
|
| 1144 |
+
"grad_norm": 0.23287071287631989,
|
| 1145 |
+
"learning_rate": 9.263955565725648e-06,
|
| 1146 |
+
"loss": 0.6676,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.27040816326530615,
|
| 1151 |
+
"grad_norm": 0.22927455604076385,
|
| 1152 |
+
"learning_rate": 8.844908849515509e-06,
|
| 1153 |
+
"loss": 0.6513,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.272108843537415,
|
| 1158 |
+
"grad_norm": 0.23780395090579987,
|
| 1159 |
+
"learning_rate": 8.434379624144261e-06,
|
| 1160 |
+
"loss": 0.6377,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.27380952380952384,
|
| 1165 |
+
"grad_norm": 0.23513314127922058,
|
| 1166 |
+
"learning_rate": 8.032480124203013e-06,
|
| 1167 |
+
"loss": 0.6464,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.2755102040816326,
|
| 1172 |
+
"grad_norm": 0.23223648965358734,
|
| 1173 |
+
"learning_rate": 7.639320225002106e-06,
|
| 1174 |
+
"loss": 0.6287,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.27721088435374147,
|
| 1179 |
+
"grad_norm": 0.2369530349969864,
|
| 1180 |
+
"learning_rate": 7.255007412532307e-06,
|
| 1181 |
+
"loss": 0.6652,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.2789115646258503,
|
| 1186 |
+
"grad_norm": 0.2352808564901352,
|
| 1187 |
+
"learning_rate": 6.8796467540791986e-06,
|
| 1188 |
+
"loss": 0.6554,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.28061224489795916,
|
| 1193 |
+
"grad_norm": 0.23590978980064392,
|
| 1194 |
+
"learning_rate": 6.513340869498859e-06,
|
| 1195 |
+
"loss": 0.6387,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.282312925170068,
|
| 1200 |
+
"grad_norm": 0.24238228797912598,
|
| 1201 |
+
"learning_rate": 6.1561899031625794e-06,
|
| 1202 |
+
"loss": 0.6717,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.28401360544217685,
|
| 1207 |
+
"grad_norm": 0.23621121048927307,
|
| 1208 |
+
"learning_rate": 5.808291496578435e-06,
|
| 1209 |
+
"loss": 0.647,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.2857142857142857,
|
| 1214 |
+
"grad_norm": 0.2383495420217514,
|
| 1215 |
+
"learning_rate": 5.469740761697044e-06,
|
| 1216 |
+
"loss": 0.6615,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.28741496598639454,
|
| 1221 |
+
"grad_norm": 0.23851458728313446,
|
| 1222 |
+
"learning_rate": 5.140630254908905e-06,
|
| 1223 |
+
"loss": 0.6346,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.2891156462585034,
|
| 1228 |
+
"grad_norm": 0.23707586526870728,
|
| 1229 |
+
"learning_rate": 4.821049951740442e-06,
|
| 1230 |
+
"loss": 0.6646,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.29081632653061223,
|
| 1235 |
+
"grad_norm": 0.24620512127876282,
|
| 1236 |
+
"learning_rate": 4.511087222255528e-06,
|
| 1237 |
+
"loss": 0.6786,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.2925170068027211,
|
| 1242 |
+
"grad_norm": 0.23762977123260498,
|
| 1243 |
+
"learning_rate": 4.2108268071694616e-06,
|
| 1244 |
+
"loss": 0.6565,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.2942176870748299,
|
| 1249 |
+
"grad_norm": 0.24971109628677368,
|
| 1250 |
+
"learning_rate": 3.9203507946816445e-06,
|
| 1251 |
+
"loss": 0.7011,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.29591836734693877,
|
| 1256 |
+
"grad_norm": 0.24630703032016754,
|
| 1257 |
+
"learning_rate": 3.6397385980335e-06,
|
| 1258 |
+
"loss": 0.6313,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.2976190476190476,
|
| 1263 |
+
"grad_norm": 0.248443141579628,
|
| 1264 |
+
"learning_rate": 3.3690669337977e-06,
|
| 1265 |
+
"loss": 0.6703,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.29931972789115646,
|
| 1270 |
+
"grad_norm": 0.2575363516807556,
|
| 1271 |
+
"learning_rate": 3.1084098009046106e-06,
|
| 1272 |
+
"loss": 0.6883,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.3010204081632653,
|
| 1277 |
+
"grad_norm": 0.2538343369960785,
|
| 1278 |
+
"learning_rate": 2.8578384604117217e-06,
|
| 1279 |
+
"loss": 0.6952,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.30272108843537415,
|
| 1284 |
+
"grad_norm": 0.25473159551620483,
|
| 1285 |
+
"learning_rate": 2.6174214160215704e-06,
|
| 1286 |
+
"loss": 0.6877,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.304421768707483,
|
| 1291 |
+
"grad_norm": 0.2566973865032196,
|
| 1292 |
+
"learning_rate": 2.3872243953535535e-06,
|
| 1293 |
+
"loss": 0.6795,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.30612244897959184,
|
| 1298 |
+
"grad_norm": 0.24843615293502808,
|
| 1299 |
+
"learning_rate": 2.1673103319746146e-06,
|
| 1300 |
+
"loss": 0.6552,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.3078231292517007,
|
| 1305 |
+
"grad_norm": 0.255484014749527,
|
| 1306 |
+
"learning_rate": 1.957739348193859e-06,
|
| 1307 |
+
"loss": 0.6854,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.30952380952380953,
|
| 1312 |
+
"grad_norm": 0.24806556105613708,
|
| 1313 |
+
"learning_rate": 1.7585687386256944e-06,
|
| 1314 |
+
"loss": 0.6547,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.3112244897959184,
|
| 1319 |
+
"grad_norm": 0.24836336076259613,
|
| 1320 |
+
"learning_rate": 1.5698529545260744e-06,
|
| 1321 |
+
"loss": 0.6485,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.3129251700680272,
|
| 1326 |
+
"grad_norm": 0.25505492091178894,
|
| 1327 |
+
"learning_rate": 1.3916435889060575e-06,
|
| 1328 |
+
"loss": 0.6795,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.31462585034013607,
|
| 1333 |
+
"grad_norm": 0.26232901215553284,
|
| 1334 |
+
"learning_rate": 1.2239893624267852e-06,
|
| 1335 |
+
"loss": 0.6813,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.3163265306122449,
|
| 1340 |
+
"grad_norm": 0.26474517583847046,
|
| 1341 |
+
"learning_rate": 1.0669361100797704e-06,
|
| 1342 |
+
"loss": 0.6814,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.31802721088435376,
|
| 1347 |
+
"grad_norm": 0.26200371980667114,
|
| 1348 |
+
"learning_rate": 9.205267686560293e-07,
|
| 1349 |
+
"loss": 0.6425,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.3197278911564626,
|
| 1354 |
+
"grad_norm": 0.2582118511199951,
|
| 1355 |
+
"learning_rate": 7.848013650076258e-07,
|
| 1356 |
+
"loss": 0.6708,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.32142857142857145,
|
| 1361 |
+
"grad_norm": 0.25343313813209534,
|
| 1362 |
+
"learning_rate": 6.597970051047053e-07,
|
| 1363 |
+
"loss": 0.632,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.3231292517006803,
|
| 1368 |
+
"grad_norm": 0.2599485516548157,
|
| 1369 |
+
"learning_rate": 5.455478638911071e-07,
|
| 1370 |
+
"loss": 0.6482,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.32482993197278914,
|
| 1375 |
+
"grad_norm": 0.25874727964401245,
|
| 1376 |
+
"learning_rate": 4.420851759412603e-07,
|
| 1377 |
+
"loss": 0.6601,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.32653061224489793,
|
| 1382 |
+
"grad_norm": 0.2675853669643402,
|
| 1383 |
+
"learning_rate": 3.4943722692099224e-07,
|
| 1384 |
+
"loss": 0.6596,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.3282312925170068,
|
| 1389 |
+
"grad_norm": 0.27086105942726135,
|
| 1390 |
+
"learning_rate": 2.676293458544743e-07,
|
| 1391 |
+
"loss": 0.6787,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.3299319727891156,
|
| 1396 |
+
"grad_norm": 0.27428770065307617,
|
| 1397 |
+
"learning_rate": 1.9668389819954338e-07,
|
| 1398 |
+
"loss": 0.6979,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.33163265306122447,
|
| 1403 |
+
"grad_norm": 0.276022344827652,
|
| 1404 |
+
"learning_rate": 1.3662027973320614e-07,
|
| 1405 |
+
"loss": 0.6733,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.3333333333333333,
|
| 1410 |
+
"grad_norm": 0.28401777148246765,
|
| 1411 |
+
"learning_rate": 8.745491124901861e-08,
|
| 1412 |
+
"loss": 0.6435,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.33503401360544216,
|
| 1417 |
+
"grad_norm": 0.28814497590065,
|
| 1418 |
+
"learning_rate": 4.920123406781052e-08,
|
| 1419 |
+
"loss": 0.6764,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.336734693877551,
|
| 1424 |
+
"grad_norm": 0.3017368018627167,
|
| 1425 |
+
"learning_rate": 2.1869706362958044e-08,
|
| 1426 |
+
"loss": 0.6491,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.33843537414965985,
|
| 1431 |
+
"grad_norm": 0.3238164484500885,
|
| 1432 |
+
"learning_rate": 5.467800301239834e-09,
|
| 1433 |
+
"loss": 0.6186,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.3401360544217687,
|
| 1438 |
+
"grad_norm": 0.6410134434700012,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.6382,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.3401360544217687,
|
| 1445 |
+
"eval_loss": 0.6537404656410217,
|
| 1446 |
+
"eval_runtime": 29.3996,
|
| 1447 |
+
"eval_samples_per_second": 33.674,
|
| 1448 |
+
"eval_steps_per_second": 8.435,
|
| 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": 5.463305468510208e+16,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|