Training in progress, step 20000, 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 3555504
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bedaf2b834c17d85aceaca7862c24d85d8d872107727528ad8cce968c65457d
|
| 3 |
size 3555504
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7141515
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b774de3046f6c9826032946233d1806ab5688b30b35bf69f6e2c64418b1af07
|
| 3 |
size 7141515
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2eaf494bdb773a56e55acb93767a950deb04425b06a47268e2a7e6eb9596f87
|
| 3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d613eca09cb3ed2cbc2c00b1d0538a9bda3f76b75cb69bac8b3cf4fa9b1dda90
|
| 3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:524e618937b19fc406beb64b3f4e048c69ed7a9b18cd89552940d0d92765916b
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "CodeGenDetect-CodeBert_Lora/checkpoint-
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 4000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1176,6 +1176,298 @@
|
|
| 1176 |
"eval_samples_per_second": 121.494,
|
| 1177 |
"eval_steps_per_second": 7.593,
|
| 1178 |
"step": 16000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1179 |
}
|
| 1180 |
],
|
| 1181 |
"logging_steps": 100,
|
|
@@ -1204,7 +1496,7 @@
|
|
| 1204 |
"attributes": {}
|
| 1205 |
}
|
| 1206 |
},
|
| 1207 |
-
"total_flos":
|
| 1208 |
"train_batch_size": 16,
|
| 1209 |
"trial_name": null,
|
| 1210 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 20000,
|
| 3 |
+
"best_metric": 0.9846426496660109,
|
| 4 |
+
"best_model_checkpoint": "CodeGenDetect-CodeBert_Lora/checkpoint-20000",
|
| 5 |
+
"epoch": 0.64,
|
| 6 |
"eval_steps": 4000,
|
| 7 |
+
"global_step": 20000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1176 |
"eval_samples_per_second": 121.494,
|
| 1177 |
"eval_steps_per_second": 7.593,
|
| 1178 |
"step": 16000
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.5152,
|
| 1182 |
+
"grad_norm": 8.349530220031738,
|
| 1183 |
+
"learning_rate": 1.7996918138041735e-05,
|
| 1184 |
+
"loss": 0.0724,
|
| 1185 |
+
"step": 16100
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.5184,
|
| 1189 |
+
"grad_norm": 0.05041235312819481,
|
| 1190 |
+
"learning_rate": 1.7984077046548956e-05,
|
| 1191 |
+
"loss": 0.0428,
|
| 1192 |
+
"step": 16200
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.5216,
|
| 1196 |
+
"grad_norm": 0.3858475685119629,
|
| 1197 |
+
"learning_rate": 1.797123595505618e-05,
|
| 1198 |
+
"loss": 0.0569,
|
| 1199 |
+
"step": 16300
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.5248,
|
| 1203 |
+
"grad_norm": 8.561657905578613,
|
| 1204 |
+
"learning_rate": 1.7958394863563403e-05,
|
| 1205 |
+
"loss": 0.0758,
|
| 1206 |
+
"step": 16400
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.528,
|
| 1210 |
+
"grad_norm": 0.025413183495402336,
|
| 1211 |
+
"learning_rate": 1.7945553772070628e-05,
|
| 1212 |
+
"loss": 0.0548,
|
| 1213 |
+
"step": 16500
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.5312,
|
| 1217 |
+
"grad_norm": 0.010517638176679611,
|
| 1218 |
+
"learning_rate": 1.7932712680577852e-05,
|
| 1219 |
+
"loss": 0.0706,
|
| 1220 |
+
"step": 16600
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.5344,
|
| 1224 |
+
"grad_norm": 0.08805025368928909,
|
| 1225 |
+
"learning_rate": 1.7919871589085074e-05,
|
| 1226 |
+
"loss": 0.077,
|
| 1227 |
+
"step": 16700
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.5376,
|
| 1231 |
+
"grad_norm": 5.7931342124938965,
|
| 1232 |
+
"learning_rate": 1.79070304975923e-05,
|
| 1233 |
+
"loss": 0.0669,
|
| 1234 |
+
"step": 16800
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.5408,
|
| 1238 |
+
"grad_norm": 0.07078564912080765,
|
| 1239 |
+
"learning_rate": 1.789418940609952e-05,
|
| 1240 |
+
"loss": 0.1069,
|
| 1241 |
+
"step": 16900
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.544,
|
| 1245 |
+
"grad_norm": 1.9886382818222046,
|
| 1246 |
+
"learning_rate": 1.7881348314606745e-05,
|
| 1247 |
+
"loss": 0.0501,
|
| 1248 |
+
"step": 17000
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.5472,
|
| 1252 |
+
"grad_norm": 6.3300065994262695,
|
| 1253 |
+
"learning_rate": 1.7868507223113966e-05,
|
| 1254 |
+
"loss": 0.0744,
|
| 1255 |
+
"step": 17100
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.5504,
|
| 1259 |
+
"grad_norm": 0.18114350736141205,
|
| 1260 |
+
"learning_rate": 1.785566613162119e-05,
|
| 1261 |
+
"loss": 0.0782,
|
| 1262 |
+
"step": 17200
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.5536,
|
| 1266 |
+
"grad_norm": 0.2821557819843292,
|
| 1267 |
+
"learning_rate": 1.7842825040128413e-05,
|
| 1268 |
+
"loss": 0.0477,
|
| 1269 |
+
"step": 17300
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.5568,
|
| 1273 |
+
"grad_norm": 17.2164306640625,
|
| 1274 |
+
"learning_rate": 1.7829983948635637e-05,
|
| 1275 |
+
"loss": 0.0522,
|
| 1276 |
+
"step": 17400
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.56,
|
| 1280 |
+
"grad_norm": 11.891914367675781,
|
| 1281 |
+
"learning_rate": 1.781714285714286e-05,
|
| 1282 |
+
"loss": 0.0859,
|
| 1283 |
+
"step": 17500
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.5632,
|
| 1287 |
+
"grad_norm": 12.457894325256348,
|
| 1288 |
+
"learning_rate": 1.7804301765650084e-05,
|
| 1289 |
+
"loss": 0.0561,
|
| 1290 |
+
"step": 17600
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.5664,
|
| 1294 |
+
"grad_norm": 1.845371961593628,
|
| 1295 |
+
"learning_rate": 1.7791460674157305e-05,
|
| 1296 |
+
"loss": 0.0598,
|
| 1297 |
+
"step": 17700
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.5696,
|
| 1301 |
+
"grad_norm": 5.928323268890381,
|
| 1302 |
+
"learning_rate": 1.7778619582664527e-05,
|
| 1303 |
+
"loss": 0.0591,
|
| 1304 |
+
"step": 17800
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.5728,
|
| 1308 |
+
"grad_norm": 0.10898735374212265,
|
| 1309 |
+
"learning_rate": 1.776577849117175e-05,
|
| 1310 |
+
"loss": 0.068,
|
| 1311 |
+
"step": 17900
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.576,
|
| 1315 |
+
"grad_norm": 8.659664154052734,
|
| 1316 |
+
"learning_rate": 1.7752937399678973e-05,
|
| 1317 |
+
"loss": 0.0672,
|
| 1318 |
+
"step": 18000
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.5792,
|
| 1322 |
+
"grad_norm": 0.1051400676369667,
|
| 1323 |
+
"learning_rate": 1.7740096308186198e-05,
|
| 1324 |
+
"loss": 0.0845,
|
| 1325 |
+
"step": 18100
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.5824,
|
| 1329 |
+
"grad_norm": 2.4647881984710693,
|
| 1330 |
+
"learning_rate": 1.772725521669342e-05,
|
| 1331 |
+
"loss": 0.067,
|
| 1332 |
+
"step": 18200
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.5856,
|
| 1336 |
+
"grad_norm": 0.04466241970658302,
|
| 1337 |
+
"learning_rate": 1.7714414125200644e-05,
|
| 1338 |
+
"loss": 0.0657,
|
| 1339 |
+
"step": 18300
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.5888,
|
| 1343 |
+
"grad_norm": 0.014231475070118904,
|
| 1344 |
+
"learning_rate": 1.7701573033707865e-05,
|
| 1345 |
+
"loss": 0.0666,
|
| 1346 |
+
"step": 18400
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.592,
|
| 1350 |
+
"grad_norm": 10.516510009765625,
|
| 1351 |
+
"learning_rate": 1.768873194221509e-05,
|
| 1352 |
+
"loss": 0.0692,
|
| 1353 |
+
"step": 18500
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.5952,
|
| 1357 |
+
"grad_norm": 1.2347426414489746,
|
| 1358 |
+
"learning_rate": 1.767589085072231e-05,
|
| 1359 |
+
"loss": 0.057,
|
| 1360 |
+
"step": 18600
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.5984,
|
| 1364 |
+
"grad_norm": 0.09256485849618912,
|
| 1365 |
+
"learning_rate": 1.7663049759229537e-05,
|
| 1366 |
+
"loss": 0.0726,
|
| 1367 |
+
"step": 18700
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.6016,
|
| 1371 |
+
"grad_norm": 9.093379020690918,
|
| 1372 |
+
"learning_rate": 1.7650208667736758e-05,
|
| 1373 |
+
"loss": 0.0902,
|
| 1374 |
+
"step": 18800
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.6048,
|
| 1378 |
+
"grad_norm": 2.5893750190734863,
|
| 1379 |
+
"learning_rate": 1.7637367576243983e-05,
|
| 1380 |
+
"loss": 0.0611,
|
| 1381 |
+
"step": 18900
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.608,
|
| 1385 |
+
"grad_norm": 0.708980143070221,
|
| 1386 |
+
"learning_rate": 1.7624526484751204e-05,
|
| 1387 |
+
"loss": 0.0726,
|
| 1388 |
+
"step": 19000
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.6112,
|
| 1392 |
+
"grad_norm": 0.35581639409065247,
|
| 1393 |
+
"learning_rate": 1.761168539325843e-05,
|
| 1394 |
+
"loss": 0.0681,
|
| 1395 |
+
"step": 19100
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.6144,
|
| 1399 |
+
"grad_norm": 1.3588510751724243,
|
| 1400 |
+
"learning_rate": 1.759884430176565e-05,
|
| 1401 |
+
"loss": 0.0662,
|
| 1402 |
+
"step": 19200
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.6176,
|
| 1406 |
+
"grad_norm": 9.142585754394531,
|
| 1407 |
+
"learning_rate": 1.7586003210272875e-05,
|
| 1408 |
+
"loss": 0.0559,
|
| 1409 |
+
"step": 19300
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.6208,
|
| 1413 |
+
"grad_norm": 16.729188919067383,
|
| 1414 |
+
"learning_rate": 1.7573162118780097e-05,
|
| 1415 |
+
"loss": 0.0754,
|
| 1416 |
+
"step": 19400
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.624,
|
| 1420 |
+
"grad_norm": 11.582767486572266,
|
| 1421 |
+
"learning_rate": 1.756032102728732e-05,
|
| 1422 |
+
"loss": 0.0681,
|
| 1423 |
+
"step": 19500
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.6272,
|
| 1427 |
+
"grad_norm": 0.046063363552093506,
|
| 1428 |
+
"learning_rate": 1.7547479935794543e-05,
|
| 1429 |
+
"loss": 0.0603,
|
| 1430 |
+
"step": 19600
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.6304,
|
| 1434 |
+
"grad_norm": 0.294583261013031,
|
| 1435 |
+
"learning_rate": 1.7534638844301768e-05,
|
| 1436 |
+
"loss": 0.0518,
|
| 1437 |
+
"step": 19700
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.6336,
|
| 1441 |
+
"grad_norm": 0.014278042130172253,
|
| 1442 |
+
"learning_rate": 1.7521797752808993e-05,
|
| 1443 |
+
"loss": 0.0576,
|
| 1444 |
+
"step": 19800
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.6368,
|
| 1448 |
+
"grad_norm": 0.16866210103034973,
|
| 1449 |
+
"learning_rate": 1.7508956661316214e-05,
|
| 1450 |
+
"loss": 0.0701,
|
| 1451 |
+
"step": 19900
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.64,
|
| 1455 |
+
"grad_norm": 6.832259654998779,
|
| 1456 |
+
"learning_rate": 1.749611556982344e-05,
|
| 1457 |
+
"loss": 0.0776,
|
| 1458 |
+
"step": 20000
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.64,
|
| 1462 |
+
"eval_accuracy": 0.98464,
|
| 1463 |
+
"eval_f1": 0.9846426496660109,
|
| 1464 |
+
"eval_loss": 0.061699531972408295,
|
| 1465 |
+
"eval_precision": 0.9846784488090538,
|
| 1466 |
+
"eval_recall": 0.98464,
|
| 1467 |
+
"eval_runtime": 814.0166,
|
| 1468 |
+
"eval_samples_per_second": 122.848,
|
| 1469 |
+
"eval_steps_per_second": 7.678,
|
| 1470 |
+
"step": 20000
|
| 1471 |
}
|
| 1472 |
],
|
| 1473 |
"logging_steps": 100,
|
|
|
|
| 1496 |
"attributes": {}
|
| 1497 |
}
|
| 1498 |
},
|
| 1499 |
+
"total_flos": 8.492350218891494e+16,
|
| 1500 |
"train_batch_size": 16,
|
| 1501 |
"trial_name": null,
|
| 1502 |
"trial_params": null
|