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 100690184
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d0f59362ceb5af305145dcd2eb901c01f4852d08b2059688d55929212ec3a20
|
3 |
size 100690184
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 51344890
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fb34a4887e8ef85e7cef1c5ae91c8537a296b34ecacf8613d7f32833cd17a56
|
3 |
size 51344890
|
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 sha256:364db5eff7c2707ef8dece4d5fc6f8ce502ebb45fbb2cfc32f94381d4c40eb8f
|
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": 2.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch": 1.
|
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": 80.909,
|
1090 |
"eval_steps_per_second": 20.454,
|
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": 1.
|
1121 |
"train_batch_size": 8,
|
1122 |
"trial_name": null,
|
1123 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.505129098892212,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
4 |
+
"epoch": 1.9002375296912115,
|
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": 80.909,
|
1090 |
"eval_steps_per_second": 20.454,
|
1091 |
"step": 150
|
1092 |
+
},
|
1093 |
+
{
|
1094 |
+
"epoch": 1.4346793349168645,
|
1095 |
+
"grad_norm": 84.7126235961914,
|
1096 |
+
"learning_rate": 1.553232954407171e-05,
|
1097 |
+
"loss": 10.5227,
|
1098 |
+
"step": 151
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 1.4441805225653206,
|
1102 |
+
"grad_norm": 122.6131362915039,
|
1103 |
+
"learning_rate": 1.4938160786375572e-05,
|
1104 |
+
"loss": 11.4731,
|
1105 |
+
"step": 152
|
1106 |
+
},
|
1107 |
+
{
|
1108 |
+
"epoch": 1.4536817102137767,
|
1109 |
+
"grad_norm": 156.39503479003906,
|
1110 |
+
"learning_rate": 1.435357758543015e-05,
|
1111 |
+
"loss": 9.7612,
|
1112 |
+
"step": 153
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 1.4631828978622328,
|
1116 |
+
"grad_norm": 159.140869140625,
|
1117 |
+
"learning_rate": 1.3778739760445552e-05,
|
1118 |
+
"loss": 10.4874,
|
1119 |
+
"step": 154
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 1.4726840855106889,
|
1123 |
+
"grad_norm": 112.50142669677734,
|
1124 |
+
"learning_rate": 1.3213804466343421e-05,
|
1125 |
+
"loss": 10.6872,
|
1126 |
+
"step": 155
|
1127 |
+
},
|
1128 |
+
{
|
1129 |
+
"epoch": 1.482185273159145,
|
1130 |
+
"grad_norm": 169.0659637451172,
|
1131 |
+
"learning_rate": 1.2658926150792322e-05,
|
1132 |
+
"loss": 10.9691,
|
1133 |
+
"step": 156
|
1134 |
+
},
|
1135 |
+
{
|
1136 |
+
"epoch": 1.491686460807601,
|
1137 |
+
"grad_norm": 188.6661834716797,
|
1138 |
+
"learning_rate": 1.2114256511983274e-05,
|
1139 |
+
"loss": 11.2024,
|
1140 |
+
"step": 157
|
1141 |
+
},
|
1142 |
+
{
|
1143 |
+
"epoch": 1.5011876484560571,
|
1144 |
+
"grad_norm": 89.59786224365234,
|
1145 |
+
"learning_rate": 1.157994445715706e-05,
|
1146 |
+
"loss": 11.2119,
|
1147 |
+
"step": 158
|
1148 |
+
},
|
1149 |
+
{
|
1150 |
+
"epoch": 1.5106888361045132,
|
1151 |
+
"grad_norm": 59.78520965576172,
|
1152 |
+
"learning_rate": 1.1056136061894384e-05,
|
1153 |
+
"loss": 10.6282,
|
1154 |
+
"step": 159
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 1.520190023752969,
|
1158 |
+
"grad_norm": 83.67992401123047,
|
1159 |
+
"learning_rate": 1.0542974530180327e-05,
|
1160 |
+
"loss": 10.4133,
|
1161 |
+
"step": 160
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 1.5296912114014252,
|
1165 |
+
"grad_norm": 83.5473403930664,
|
1166 |
+
"learning_rate": 1.0040600155253765e-05,
|
1167 |
+
"loss": 10.1326,
|
1168 |
+
"step": 161
|
1169 |
+
},
|
1170 |
+
{
|
1171 |
+
"epoch": 1.5391923990498813,
|
1172 |
+
"grad_norm": 78.61830139160156,
|
1173 |
+
"learning_rate": 9.549150281252633e-06,
|
1174 |
+
"loss": 9.7638,
|
1175 |
+
"step": 162
|
1176 |
+
},
|
1177 |
+
{
|
1178 |
+
"epoch": 1.5486935866983373,
|
1179 |
+
"grad_norm": 76.97246551513672,
|
1180 |
+
"learning_rate": 9.068759265665384e-06,
|
1181 |
+
"loss": 10.4008,
|
1182 |
+
"step": 163
|
1183 |
+
},
|
1184 |
+
{
|
1185 |
+
"epoch": 1.5581947743467932,
|
1186 |
+
"grad_norm": 86.40713500976562,
|
1187 |
+
"learning_rate": 8.599558442598998e-06,
|
1188 |
+
"loss": 9.4252,
|
1189 |
+
"step": 164
|
1190 |
+
},
|
1191 |
+
{
|
1192 |
+
"epoch": 1.5676959619952493,
|
1193 |
+
"grad_norm": 75.06586456298828,
|
1194 |
+
"learning_rate": 8.141676086873572e-06,
|
1195 |
+
"loss": 9.1285,
|
1196 |
+
"step": 165
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 1.5771971496437054,
|
1200 |
+
"grad_norm": 75.3528060913086,
|
1201 |
+
"learning_rate": 7.695237378953223e-06,
|
1202 |
+
"loss": 8.99,
|
1203 |
+
"step": 166
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 1.5866983372921615,
|
1207 |
+
"grad_norm": 94.358642578125,
|
1208 |
+
"learning_rate": 7.260364370723044e-06,
|
1209 |
+
"loss": 9.7196,
|
1210 |
+
"step": 167
|
1211 |
+
},
|
1212 |
+
{
|
1213 |
+
"epoch": 1.5961995249406176,
|
1214 |
+
"grad_norm": 78.89218139648438,
|
1215 |
+
"learning_rate": 6.837175952121306e-06,
|
1216 |
+
"loss": 9.2189,
|
1217 |
+
"step": 168
|
1218 |
+
},
|
1219 |
+
{
|
1220 |
+
"epoch": 1.6057007125890737,
|
1221 |
+
"grad_norm": 84.5966796875,
|
1222 |
+
"learning_rate": 6.425787818636131e-06,
|
1223 |
+
"loss": 9.1692,
|
1224 |
+
"step": 169
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 1.6152019002375297,
|
1228 |
+
"grad_norm": 77.07421112060547,
|
1229 |
+
"learning_rate": 6.026312439675552e-06,
|
1230 |
+
"loss": 8.9361,
|
1231 |
+
"step": 170
|
1232 |
+
},
|
1233 |
+
{
|
1234 |
+
"epoch": 1.6247030878859858,
|
1235 |
+
"grad_norm": 96.34380340576172,
|
1236 |
+
"learning_rate": 5.6388590278194096e-06,
|
1237 |
+
"loss": 9.1843,
|
1238 |
+
"step": 171
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 1.634204275534442,
|
1242 |
+
"grad_norm": 67.07677459716797,
|
1243 |
+
"learning_rate": 5.263533508961827e-06,
|
1244 |
+
"loss": 9.53,
|
1245 |
+
"step": 172
|
1246 |
+
},
|
1247 |
+
{
|
1248 |
+
"epoch": 1.643705463182898,
|
1249 |
+
"grad_norm": 141.90057373046875,
|
1250 |
+
"learning_rate": 4.900438493352055e-06,
|
1251 |
+
"loss": 10.2738,
|
1252 |
+
"step": 173
|
1253 |
+
},
|
1254 |
+
{
|
1255 |
+
"epoch": 1.6532066508313539,
|
1256 |
+
"grad_norm": 104.226318359375,
|
1257 |
+
"learning_rate": 4.549673247541875e-06,
|
1258 |
+
"loss": 10.0341,
|
1259 |
+
"step": 174
|
1260 |
+
},
|
1261 |
+
{
|
1262 |
+
"epoch": 1.66270783847981,
|
1263 |
+
"grad_norm": 101.72418212890625,
|
1264 |
+
"learning_rate": 4.2113336672471245e-06,
|
1265 |
+
"loss": 10.2237,
|
1266 |
+
"step": 175
|
1267 |
+
},
|
1268 |
+
{
|
1269 |
+
"epoch": 1.672209026128266,
|
1270 |
+
"grad_norm": 134.41738891601562,
|
1271 |
+
"learning_rate": 3.885512251130763e-06,
|
1272 |
+
"loss": 10.7662,
|
1273 |
+
"step": 176
|
1274 |
+
},
|
1275 |
+
{
|
1276 |
+
"epoch": 1.6817102137767221,
|
1277 |
+
"grad_norm": 126.75146484375,
|
1278 |
+
"learning_rate": 3.5722980755146517e-06,
|
1279 |
+
"loss": 10.7483,
|
1280 |
+
"step": 177
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 1.691211401425178,
|
1284 |
+
"grad_norm": 95.49859619140625,
|
1285 |
+
"learning_rate": 3.271776770026963e-06,
|
1286 |
+
"loss": 9.4185,
|
1287 |
+
"step": 178
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 1.700712589073634,
|
1291 |
+
"grad_norm": 112.31136322021484,
|
1292 |
+
"learning_rate": 2.9840304941919415e-06,
|
1293 |
+
"loss": 10.8657,
|
1294 |
+
"step": 179
|
1295 |
+
},
|
1296 |
+
{
|
1297 |
+
"epoch": 1.7102137767220902,
|
1298 |
+
"grad_norm": 143.15719604492188,
|
1299 |
+
"learning_rate": 2.7091379149682685e-06,
|
1300 |
+
"loss": 11.0102,
|
1301 |
+
"step": 180
|
1302 |
+
},
|
1303 |
+
{
|
1304 |
+
"epoch": 1.7197149643705463,
|
1305 |
+
"grad_norm": 140.19906616210938,
|
1306 |
+
"learning_rate": 2.4471741852423237e-06,
|
1307 |
+
"loss": 10.485,
|
1308 |
+
"step": 181
|
1309 |
+
},
|
1310 |
+
{
|
1311 |
+
"epoch": 1.7292161520190024,
|
1312 |
+
"grad_norm": 165.3531951904297,
|
1313 |
+
"learning_rate": 2.1982109232821178e-06,
|
1314 |
+
"loss": 11.084,
|
1315 |
+
"step": 182
|
1316 |
+
},
|
1317 |
+
{
|
1318 |
+
"epoch": 1.7387173396674585,
|
1319 |
+
"grad_norm": 246.70103454589844,
|
1320 |
+
"learning_rate": 1.962316193157593e-06,
|
1321 |
+
"loss": 11.2965,
|
1322 |
+
"step": 183
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 1.7482185273159145,
|
1326 |
+
"grad_norm": 190.2755126953125,
|
1327 |
+
"learning_rate": 1.7395544861325718e-06,
|
1328 |
+
"loss": 10.836,
|
1329 |
+
"step": 184
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 1.7577197149643706,
|
1333 |
+
"grad_norm": 54.2744255065918,
|
1334 |
+
"learning_rate": 1.5299867030334814e-06,
|
1335 |
+
"loss": 10.4541,
|
1336 |
+
"step": 185
|
1337 |
+
},
|
1338 |
+
{
|
1339 |
+
"epoch": 1.7672209026128267,
|
1340 |
+
"grad_norm": 60.90446853637695,
|
1341 |
+
"learning_rate": 1.333670137599713e-06,
|
1342 |
+
"loss": 10.2176,
|
1343 |
+
"step": 186
|
1344 |
+
},
|
1345 |
+
{
|
1346 |
+
"epoch": 1.7767220902612828,
|
1347 |
+
"grad_norm": 64.88226318359375,
|
1348 |
+
"learning_rate": 1.1506584608200367e-06,
|
1349 |
+
"loss": 10.1289,
|
1350 |
+
"step": 187
|
1351 |
+
},
|
1352 |
+
{
|
1353 |
+
"epoch": 1.7862232779097387,
|
1354 |
+
"grad_norm": 64.57106018066406,
|
1355 |
+
"learning_rate": 9.810017062595322e-07,
|
1356 |
+
"loss": 10.4699,
|
1357 |
+
"step": 188
|
1358 |
+
},
|
1359 |
+
{
|
1360 |
+
"epoch": 1.7957244655581948,
|
1361 |
+
"grad_norm": 71.23513793945312,
|
1362 |
+
"learning_rate": 8.247462563808817e-07,
|
1363 |
+
"loss": 10.5886,
|
1364 |
+
"step": 189
|
1365 |
+
},
|
1366 |
+
{
|
1367 |
+
"epoch": 1.8052256532066508,
|
1368 |
+
"grad_norm": 62.82306671142578,
|
1369 |
+
"learning_rate": 6.819348298638839e-07,
|
1370 |
+
"loss": 10.136,
|
1371 |
+
"step": 190
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 1.814726840855107,
|
1375 |
+
"grad_norm": 72.74017333984375,
|
1376 |
+
"learning_rate": 5.526064699265753e-07,
|
1377 |
+
"loss": 9.192,
|
1378 |
+
"step": 191
|
1379 |
+
},
|
1380 |
+
{
|
1381 |
+
"epoch": 1.8242280285035628,
|
1382 |
+
"grad_norm": 62.476192474365234,
|
1383 |
+
"learning_rate": 4.367965336512403e-07,
|
1384 |
+
"loss": 9.0637,
|
1385 |
+
"step": 192
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 1.833729216152019,
|
1389 |
+
"grad_norm": 79.42888641357422,
|
1390 |
+
"learning_rate": 3.3453668231809286e-07,
|
1391 |
+
"loss": 9.5623,
|
1392 |
+
"step": 193
|
1393 |
+
},
|
1394 |
+
{
|
1395 |
+
"epoch": 1.843230403800475,
|
1396 |
+
"grad_norm": 80.78561401367188,
|
1397 |
+
"learning_rate": 2.458548727494292e-07,
|
1398 |
+
"loss": 9.71,
|
1399 |
+
"step": 194
|
1400 |
+
},
|
1401 |
+
{
|
1402 |
+
"epoch": 1.852731591448931,
|
1403 |
+
"grad_norm": 87.67532348632812,
|
1404 |
+
"learning_rate": 1.7077534966650766e-07,
|
1405 |
+
"loss": 9.0287,
|
1406 |
+
"step": 195
|
1407 |
+
},
|
1408 |
+
{
|
1409 |
+
"epoch": 1.8622327790973872,
|
1410 |
+
"grad_norm": 84.16883087158203,
|
1411 |
+
"learning_rate": 1.0931863906127327e-07,
|
1412 |
+
"loss": 9.629,
|
1413 |
+
"step": 196
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 1.8717339667458432,
|
1417 |
+
"grad_norm": 100.6878890991211,
|
1418 |
+
"learning_rate": 6.150154258476315e-08,
|
1419 |
+
"loss": 9.2654,
|
1420 |
+
"step": 197
|
1421 |
+
},
|
1422 |
+
{
|
1423 |
+
"epoch": 1.8812351543942993,
|
1424 |
+
"grad_norm": 86.63809204101562,
|
1425 |
+
"learning_rate": 2.7337132953697554e-08,
|
1426 |
+
"loss": 9.8003,
|
1427 |
+
"step": 198
|
1428 |
+
},
|
1429 |
+
{
|
1430 |
+
"epoch": 1.8907363420427554,
|
1431 |
+
"grad_norm": 149.69566345214844,
|
1432 |
+
"learning_rate": 6.834750376549792e-09,
|
1433 |
+
"loss": 9.5615,
|
1434 |
+
"step": 199
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 1.9002375296912115,
|
1438 |
+
"grad_norm": 103.23074340820312,
|
1439 |
+
"learning_rate": 0.0,
|
1440 |
+
"loss": 9.9939,
|
1441 |
+
"step": 200
|
1442 |
+
},
|
1443 |
+
{
|
1444 |
+
"epoch": 1.9002375296912115,
|
1445 |
+
"eval_loss": 2.505129098892212,
|
1446 |
+
"eval_runtime": 2.202,
|
1447 |
+
"eval_samples_per_second": 80.835,
|
1448 |
+
"eval_steps_per_second": 20.436,
|
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": 1.5377451077074944e+16,
|
1479 |
"train_batch_size": 8,
|
1480 |
"trial_name": null,
|
1481 |
"trial_params": null
|