cilooor commited on
Commit
2e293d5
·
verified ·
1 Parent(s): 44071ca

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:dc54541585923666a5d4880b9122dbf341e5f200f2e3e28afa7cd1282ea9b61f
3
  size 1157746040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f1c9dc2b0196d1161f67bde73a74b6d454523defc8c256deb0da52e33ae1725
3
  size 1157746040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25babb319e3941401a2ed6aa9b7643a2a903e0188353461d39f562c4152ad2b7
3
  size 588699796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26ca0a223c342755d6d2b353ee1a86e47504b51679e9e5309ecb9cdef6824ff4
3
  size 588699796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5880a169bde6ec6d9aeaae9592ca9c2139b7af0eabdf35198ba023e5071c40e2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24f85bc39113a669f5193e1a09b8532d528fb2bd87ee5f3c577612be7e9e3b16
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b06d9dbca2d2e799f64e5db9a242e7689df5f48f98c30d95b246a79b74d68c80
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a27b052646dcb561cbd68156c30bd466ce59bda64cf3c8eba9c3c1113af9827c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.9892306327819824,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 1.5463917525773194,
5
  "eval_steps": 50,
6
- "global_step": 150,
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": 6.156,
1090
  "eval_steps_per_second": 1.549,
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": false
1116
  },
1117
  "attributes": {}
1118
  }
1119
  },
1120
- "total_flos": 5.143759919807201e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.9789440631866455,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 2.0618556701030926,
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": 6.156,
1090
  "eval_steps_per_second": 1.549,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 1.556701030927835,
1095
+ "grad_norm": 0.44996705651283264,
1096
+ "learning_rate": 7.766164772035856e-06,
1097
+ "loss": 2.8425,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 1.5670103092783505,
1102
+ "grad_norm": 0.4374925494194031,
1103
+ "learning_rate": 7.469080393187786e-06,
1104
+ "loss": 2.8137,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 1.577319587628866,
1109
+ "grad_norm": 0.43388310074806213,
1110
+ "learning_rate": 7.176788792715075e-06,
1111
+ "loss": 2.7458,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 1.5876288659793816,
1116
+ "grad_norm": 0.4313639998435974,
1117
+ "learning_rate": 6.889369880222776e-06,
1118
+ "loss": 2.7559,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 1.597938144329897,
1123
+ "grad_norm": 0.46524229645729065,
1124
+ "learning_rate": 6.606902233171711e-06,
1125
+ "loss": 2.9254,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 1.6082474226804124,
1130
+ "grad_norm": 0.45946189761161804,
1131
+ "learning_rate": 6.329463075396161e-06,
1132
+ "loss": 2.7861,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 1.6185567010309279,
1137
+ "grad_norm": 0.505064845085144,
1138
+ "learning_rate": 6.057128255991637e-06,
1139
+ "loss": 2.809,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 1.6288659793814433,
1144
+ "grad_norm": 0.52464759349823,
1145
+ "learning_rate": 5.78997222857853e-06,
1146
+ "loss": 2.9131,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 1.6391752577319587,
1151
+ "grad_norm": 0.5671892762184143,
1152
+ "learning_rate": 5.528068030947192e-06,
1153
+ "loss": 2.8251,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 1.6494845360824741,
1158
+ "grad_norm": 0.5638917684555054,
1159
+ "learning_rate": 5.271487265090163e-06,
1160
+ "loss": 2.7914,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 1.6597938144329896,
1165
+ "grad_norm": 0.6002135872840881,
1166
+ "learning_rate": 5.0203000776268825e-06,
1167
+ "loss": 2.6924,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 1.670103092783505,
1172
+ "grad_norm": 0.6604558229446411,
1173
+ "learning_rate": 4.7745751406263165e-06,
1174
+ "loss": 2.8716,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 1.6804123711340206,
1179
+ "grad_norm": 0.698222815990448,
1180
+ "learning_rate": 4.534379632832692e-06,
1181
+ "loss": 2.7171,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 1.690721649484536,
1186
+ "grad_norm": 0.7724798321723938,
1187
+ "learning_rate": 4.299779221299499e-06,
1188
+ "loss": 2.7808,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 1.7010309278350515,
1193
+ "grad_norm": 0.8780054450035095,
1194
+ "learning_rate": 4.070838043436786e-06,
1195
+ "loss": 2.8484,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 1.7113402061855671,
1200
+ "grad_norm": 0.9716514945030212,
1201
+ "learning_rate": 3.847618689476612e-06,
1202
+ "loss": 2.4753,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 1.7216494845360826,
1207
+ "grad_norm": 1.2340327501296997,
1208
+ "learning_rate": 3.630182185361522e-06,
1209
+ "loss": 2.8443,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 1.731958762886598,
1214
+ "grad_norm": 1.539471983909607,
1215
+ "learning_rate": 3.418587976060653e-06,
1216
+ "loss": 2.7507,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 1.7422680412371134,
1221
+ "grad_norm": 3.0212562084198,
1222
+ "learning_rate": 3.2128939093180655e-06,
1223
+ "loss": 3.0217,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 1.7525773195876289,
1228
+ "grad_norm": 0.4096789062023163,
1229
+ "learning_rate": 3.013156219837776e-06,
1230
+ "loss": 2.6976,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 1.7628865979381443,
1235
+ "grad_norm": 0.41243836283683777,
1236
+ "learning_rate": 2.8194295139097048e-06,
1237
+ "loss": 2.8642,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 1.7731958762886597,
1242
+ "grad_norm": 0.41758671402931213,
1243
+ "learning_rate": 2.6317667544809134e-06,
1244
+ "loss": 2.7165,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 1.7835051546391751,
1249
+ "grad_norm": 0.40344008803367615,
1250
+ "learning_rate": 2.4502192466760276e-06,
1251
+ "loss": 2.7623,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 1.7938144329896906,
1256
+ "grad_norm": 0.3946278393268585,
1257
+ "learning_rate": 2.2748366237709374e-06,
1258
+ "loss": 2.7634,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 1.8041237113402062,
1263
+ "grad_norm": 0.39972734451293945,
1264
+ "learning_rate": 2.1056668336235622e-06,
1265
+ "loss": 2.7844,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 1.8144329896907216,
1270
+ "grad_norm": 0.3869716227054596,
1271
+ "learning_rate": 1.9427561255653816e-06,
1272
+ "loss": 2.7322,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 1.824742268041237,
1277
+ "grad_norm": 0.40597400069236755,
1278
+ "learning_rate": 1.7861490377573258e-06,
1279
+ "loss": 2.7585,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 1.8350515463917527,
1284
+ "grad_norm": 0.4372086226940155,
1285
+ "learning_rate": 1.6358883850134816e-06,
1286
+ "loss": 2.7526,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 1.8453608247422681,
1291
+ "grad_norm": 0.4415931701660156,
1292
+ "learning_rate": 1.4920152470959707e-06,
1293
+ "loss": 2.8978,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 1.8556701030927836,
1298
+ "grad_norm": 0.4666820466518402,
1299
+ "learning_rate": 1.3545689574841342e-06,
1300
+ "loss": 2.8464,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 1.865979381443299,
1305
+ "grad_norm": 0.4898896813392639,
1306
+ "learning_rate": 1.2235870926211619e-06,
1307
+ "loss": 2.8537,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 1.8762886597938144,
1312
+ "grad_norm": 0.493072509765625,
1313
+ "learning_rate": 1.0991054616410589e-06,
1314
+ "loss": 2.8602,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 1.8865979381443299,
1319
+ "grad_norm": 0.5122954249382019,
1320
+ "learning_rate": 9.811580965787965e-07,
1321
+ "loss": 2.7631,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 1.8969072164948453,
1326
+ "grad_norm": 0.5318012833595276,
1327
+ "learning_rate": 8.697772430662859e-07,
1328
+ "loss": 2.8229,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 1.9072164948453607,
1333
+ "grad_norm": 0.563241720199585,
1334
+ "learning_rate": 7.649933515167407e-07,
1335
+ "loss": 2.8103,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 1.9175257731958761,
1340
+ "grad_norm": 0.5911391973495483,
1341
+ "learning_rate": 6.668350687998565e-07,
1342
+ "loss": 2.7581,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 1.9278350515463918,
1347
+ "grad_norm": 0.6352684497833252,
1348
+ "learning_rate": 5.753292304100183e-07,
1349
+ "loss": 2.7309,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 1.9381443298969072,
1354
+ "grad_norm": 0.7053799033164978,
1355
+ "learning_rate": 4.905008531297661e-07,
1356
+ "loss": 2.8134,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 1.9484536082474226,
1361
+ "grad_norm": 0.7725756764411926,
1362
+ "learning_rate": 4.1237312819044085e-07,
1363
+ "loss": 2.6668,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 1.9587628865979383,
1368
+ "grad_norm": 0.9331743121147156,
1369
+ "learning_rate": 3.4096741493194197e-07,
1370
+ "loss": 2.733,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 1.9690721649484537,
1375
+ "grad_norm": 1.023675799369812,
1376
+ "learning_rate": 2.763032349632877e-07,
1377
+ "loss": 2.7621,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 1.9793814432989691,
1382
+ "grad_norm": 1.2834149599075317,
1383
+ "learning_rate": 2.1839826682562015e-07,
1384
+ "loss": 2.5752,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 1.9896907216494846,
1389
+ "grad_norm": 2.3479883670806885,
1390
+ "learning_rate": 1.6726834115904643e-07,
1391
+ "loss": 2.8441,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 2.0,
1396
+ "grad_norm": 0.5650774240493774,
1397
+ "learning_rate": 1.229274363747146e-07,
1398
+ "loss": 2.8403,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 2.0103092783505154,
1403
+ "grad_norm": 0.41080382466316223,
1404
+ "learning_rate": 8.538767483325383e-08,
1405
+ "loss": 2.7558,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 2.020618556701031,
1410
+ "grad_norm": 0.39514729380607605,
1411
+ "learning_rate": 5.4659319530636633e-08,
1412
+ "loss": 2.7871,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 2.0309278350515463,
1417
+ "grad_norm": 0.3873128890991211,
1418
+ "learning_rate": 3.075077129238158e-08,
1419
+ "loss": 2.6954,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 2.0412371134020617,
1424
+ "grad_norm": 0.38206884264945984,
1425
+ "learning_rate": 1.3668566476848777e-08,
1426
+ "loss": 2.7542,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 2.051546391752577,
1431
+ "grad_norm": 0.3866540789604187,
1432
+ "learning_rate": 3.417375188274896e-09,
1433
+ "loss": 2.6818,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 2.0618556701030926,
1438
+ "grad_norm": 0.38748306035995483,
1439
+ "learning_rate": 0.0,
1440
+ "loss": 2.7786,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 2.0618556701030926,
1445
+ "eval_loss": 2.9789440631866455,
1446
+ "eval_runtime": 26.6077,
1447
+ "eval_samples_per_second": 6.126,
1448
+ "eval_steps_per_second": 1.541,
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": 6.847893440487752e+17,
1479
  "train_batch_size": 8,
1480
  "trial_name": null,
1481
  "trial_params": null