melihcatal's picture
Add files using upload-large-folder tool
076fd74 verified
2026-03-26 20:29:36,312 [INFO] new_opacus_codex.train_steps: epoch=1 step=5 loss=1.3758
2026-03-26 20:29:56,682 [INFO] new_opacus_codex.train_steps: epoch=1 step=10 loss=1.4323
2026-03-26 20:30:10,919 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=10 eval_loss=0.8392 duration_sec=14.23
2026-03-26 20:30:31,399 [INFO] new_opacus_codex.train_steps: epoch=1 step=15 loss=1.3999
2026-03-26 20:30:51,293 [INFO] new_opacus_codex.train_steps: epoch=1 step=20 loss=1.2627
2026-03-26 20:31:09,665 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=20 eval_loss=0.8292 duration_sec=18.36
2026-03-26 20:31:30,324 [INFO] new_opacus_codex.train_steps: epoch=1 step=25 loss=1.2272
2026-03-26 20:31:50,604 [INFO] new_opacus_codex.train_steps: epoch=1 step=30 loss=1.2106
2026-03-26 20:32:04,930 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=30 eval_loss=0.8240 duration_sec=14.32
2026-03-26 20:32:25,280 [INFO] new_opacus_codex.train_steps: epoch=1 step=35 loss=1.0967
2026-03-26 20:32:46,233 [INFO] new_opacus_codex.train_steps: epoch=1 step=40 loss=1.0390
2026-03-26 20:33:00,511 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=40 eval_loss=0.8113 duration_sec=14.27
2026-03-26 20:33:21,276 [INFO] new_opacus_codex.train_steps: epoch=1 step=45 loss=1.0762
2026-03-26 20:33:41,562 [INFO] new_opacus_codex.train_steps: epoch=1 step=50 loss=1.0337
2026-03-26 20:33:55,900 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=50 eval_loss=0.8033 duration_sec=14.33
2026-03-26 20:34:16,372 [INFO] new_opacus_codex.train_steps: epoch=1 step=55 loss=1.0228
2026-03-26 20:34:36,766 [INFO] new_opacus_codex.train_steps: epoch=1 step=60 loss=1.0251
2026-03-26 20:34:51,089 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=60 eval_loss=0.7923 duration_sec=14.31
2026-03-26 20:35:11,862 [INFO] new_opacus_codex.train_steps: epoch=1 step=65 loss=1.0070
2026-03-26 20:35:32,460 [INFO] new_opacus_codex.train_steps: epoch=1 step=70 loss=0.9673
2026-03-26 20:35:46,787 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=70 eval_loss=0.7861 duration_sec=14.30
2026-03-26 20:36:07,174 [INFO] new_opacus_codex.train_steps: epoch=1 step=75 loss=0.9067
2026-03-26 20:36:27,712 [INFO] new_opacus_codex.train_steps: epoch=1 step=80 loss=0.9861
2026-03-26 20:36:43,124 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=80 eval_loss=0.7792 duration_sec=15.40
2026-03-26 20:37:03,649 [INFO] new_opacus_codex.train_steps: epoch=1 step=85 loss=0.9832
2026-03-26 20:37:24,024 [INFO] new_opacus_codex.train_steps: epoch=1 step=90 loss=0.9311
2026-03-26 20:37:38,372 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=90 eval_loss=0.7738 duration_sec=14.34
2026-03-26 20:37:58,805 [INFO] new_opacus_codex.train_steps: epoch=1 step=95 loss=0.9389
2026-03-26 20:38:19,145 [INFO] new_opacus_codex.train_steps: epoch=1 step=100 loss=0.9308
2026-03-26 20:38:33,574 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=100 eval_loss=0.7698 duration_sec=14.42
2026-03-26 20:38:54,211 [INFO] new_opacus_codex.train_steps: epoch=1 step=105 loss=0.9490
2026-03-26 20:39:15,214 [INFO] new_opacus_codex.train_steps: epoch=1 step=110 loss=0.9075
2026-03-26 20:39:29,737 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=110 eval_loss=0.7663 duration_sec=14.51
2026-03-26 20:39:49,763 [INFO] new_opacus_codex.train_steps: epoch=1 step=115 loss=0.8939
2026-03-26 20:40:10,158 [INFO] new_opacus_codex.train_steps: epoch=1 step=120 loss=0.9081
2026-03-26 20:40:24,513 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=120 eval_loss=0.7622 duration_sec=14.34
2026-03-26 20:40:45,310 [INFO] new_opacus_codex.train_steps: epoch=1 step=125 loss=0.9388
2026-03-26 20:41:05,889 [INFO] new_opacus_codex.train_steps: epoch=1 step=130 loss=0.9529
2026-03-26 20:41:20,204 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=130 eval_loss=0.7588 duration_sec=14.30
2026-03-26 20:41:40,629 [INFO] new_opacus_codex.train_steps: epoch=1 step=135 loss=0.9433
2026-03-26 20:42:01,142 [INFO] new_opacus_codex.train_steps: epoch=1 step=140 loss=0.9626
2026-03-26 20:42:16,159 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=140 eval_loss=0.7552 duration_sec=15.00
2026-03-26 20:42:37,102 [INFO] new_opacus_codex.train_steps: epoch=1 step=145 loss=0.9267
2026-03-26 20:42:58,104 [INFO] new_opacus_codex.train_steps: epoch=1 step=150 loss=0.9212
2026-03-26 20:43:12,487 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=150 eval_loss=0.7522 duration_sec=14.37
2026-03-26 20:43:32,968 [INFO] new_opacus_codex.train_steps: epoch=1 step=155 loss=0.9266
2026-03-26 20:43:52,954 [INFO] new_opacus_codex.train_steps: epoch=1 step=160 loss=0.8853
2026-03-26 20:44:07,316 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=160 eval_loss=0.7491 duration_sec=14.35
2026-03-26 20:44:27,821 [INFO] new_opacus_codex.train_steps: epoch=1 step=165 loss=0.8696
2026-03-26 20:44:47,808 [INFO] new_opacus_codex.train_steps: epoch=1 step=170 loss=0.8804
2026-03-26 20:45:02,126 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=170 eval_loss=0.7466 duration_sec=14.31
2026-03-26 20:45:22,948 [INFO] new_opacus_codex.train_steps: epoch=1 step=175 loss=0.9128
2026-03-26 20:45:43,544 [INFO] new_opacus_codex.train_steps: epoch=1 step=180 loss=0.8984
2026-03-26 20:45:57,863 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=180 eval_loss=0.7452 duration_sec=14.31
2026-03-26 20:46:18,437 [INFO] new_opacus_codex.train_steps: epoch=1 step=185 loss=0.8782
2026-03-26 20:46:39,622 [INFO] new_opacus_codex.train_steps: epoch=1 step=190 loss=0.8782
2026-03-26 20:46:53,976 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=190 eval_loss=0.7416 duration_sec=14.34
2026-03-26 20:47:14,485 [INFO] new_opacus_codex.train_steps: epoch=1 step=195 loss=0.8513
2026-03-26 20:47:34,840 [INFO] new_opacus_codex.train_steps: epoch=1 step=200 loss=0.8882
2026-03-26 20:47:49,160 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=200 eval_loss=0.7399 duration_sec=14.31
2026-03-26 20:48:09,425 [INFO] new_opacus_codex.train_steps: epoch=1 step=205 loss=0.8812
2026-03-26 20:48:55,646 [INFO] new_opacus_codex.train_steps: epoch=2 step=210 loss=0.8357
2026-03-26 20:49:09,949 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=210 eval_loss=0.7385 duration_sec=14.30
2026-03-26 20:49:30,835 [INFO] new_opacus_codex.train_steps: epoch=2 step=215 loss=0.8417
2026-03-26 20:49:51,480 [INFO] new_opacus_codex.train_steps: epoch=2 step=220 loss=0.8089
2026-03-26 20:50:05,872 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=220 eval_loss=0.7375 duration_sec=14.38
2026-03-26 20:50:26,395 [INFO] new_opacus_codex.train_steps: epoch=2 step=225 loss=0.8223
2026-03-26 20:50:46,826 [INFO] new_opacus_codex.train_steps: epoch=2 step=230 loss=0.8664
2026-03-26 20:51:01,221 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=230 eval_loss=0.7352 duration_sec=14.37
2026-03-26 20:51:21,932 [INFO] new_opacus_codex.train_steps: epoch=2 step=235 loss=0.8529
2026-03-26 20:51:42,477 [INFO] new_opacus_codex.train_steps: epoch=2 step=240 loss=0.8431
2026-03-26 20:51:56,898 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=240 eval_loss=0.7343 duration_sec=14.41
2026-03-26 20:52:17,302 [INFO] new_opacus_codex.train_steps: epoch=2 step=245 loss=0.8284
2026-03-26 20:52:37,732 [INFO] new_opacus_codex.train_steps: epoch=2 step=250 loss=0.8322
2026-03-26 20:52:52,115 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=250 eval_loss=0.7326 duration_sec=14.37
2026-03-26 20:53:12,256 [INFO] new_opacus_codex.train_steps: epoch=2 step=255 loss=0.8359
2026-03-26 20:53:33,076 [INFO] new_opacus_codex.train_steps: epoch=2 step=260 loss=0.8295
2026-03-26 20:53:47,441 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=260 eval_loss=0.7312 duration_sec=14.34
2026-03-26 20:54:07,825 [INFO] new_opacus_codex.train_steps: epoch=2 step=265 loss=0.8352
2026-03-26 20:54:28,098 [INFO] new_opacus_codex.train_steps: epoch=2 step=270 loss=0.8267
2026-03-26 20:54:42,458 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=270 eval_loss=0.7298 duration_sec=14.34
2026-03-26 20:55:03,207 [INFO] new_opacus_codex.train_steps: epoch=2 step=275 loss=0.8010
2026-03-26 20:55:23,605 [INFO] new_opacus_codex.train_steps: epoch=2 step=280 loss=0.7925
2026-03-26 20:55:38,053 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=280 eval_loss=0.7297 duration_sec=14.43
2026-03-26 20:55:58,688 [INFO] new_opacus_codex.train_steps: epoch=2 step=285 loss=0.8033
2026-03-26 20:56:19,009 [INFO] new_opacus_codex.train_steps: epoch=2 step=290 loss=0.8222
2026-03-26 20:56:33,517 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=290 eval_loss=0.7286 duration_sec=14.50
2026-03-26 20:56:53,820 [INFO] new_opacus_codex.train_steps: epoch=2 step=295 loss=0.8291
2026-03-26 20:57:14,483 [INFO] new_opacus_codex.train_steps: epoch=2 step=300 loss=0.8198
2026-03-26 20:57:28,831 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=300 eval_loss=0.7272 duration_sec=14.34
2026-03-26 20:57:49,277 [INFO] new_opacus_codex.train_steps: epoch=2 step=305 loss=0.8220
2026-03-26 20:58:09,864 [INFO] new_opacus_codex.train_steps: epoch=2 step=310 loss=0.8179
2026-03-26 20:58:24,184 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=310 eval_loss=0.7259 duration_sec=14.31
2026-03-26 20:58:44,933 [INFO] new_opacus_codex.train_steps: epoch=2 step=315 loss=0.7836
2026-03-26 20:59:05,193 [INFO] new_opacus_codex.train_steps: epoch=2 step=320 loss=0.7840
2026-03-26 20:59:19,580 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=320 eval_loss=0.7248 duration_sec=14.38
2026-03-26 20:59:39,732 [INFO] new_opacus_codex.train_steps: epoch=2 step=325 loss=0.7914
2026-03-26 21:00:00,032 [INFO] new_opacus_codex.train_steps: epoch=2 step=330 loss=0.8075
2026-03-26 21:00:14,412 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=330 eval_loss=0.7243 duration_sec=14.37
2026-03-26 21:00:34,948 [INFO] new_opacus_codex.train_steps: epoch=2 step=335 loss=0.8089
2026-03-26 21:00:55,344 [INFO] new_opacus_codex.train_steps: epoch=2 step=340 loss=0.7743
2026-03-26 21:01:09,728 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=340 eval_loss=0.7233 duration_sec=14.38
2026-03-26 21:01:30,010 [INFO] new_opacus_codex.train_steps: epoch=2 step=345 loss=0.7986
2026-03-26 21:01:50,945 [INFO] new_opacus_codex.train_steps: epoch=2 step=350 loss=0.8274
2026-03-26 21:02:05,353 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=350 eval_loss=0.7230 duration_sec=14.39
2026-03-26 21:02:25,652 [INFO] new_opacus_codex.train_steps: epoch=2 step=355 loss=0.8284
2026-03-26 21:02:46,264 [INFO] new_opacus_codex.train_steps: epoch=2 step=360 loss=0.8266
2026-03-26 21:03:00,670 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=360 eval_loss=0.7211 duration_sec=14.40
2026-03-26 21:03:20,795 [INFO] new_opacus_codex.train_steps: epoch=2 step=365 loss=0.8136
2026-03-26 21:03:41,582 [INFO] new_opacus_codex.train_steps: epoch=2 step=370 loss=0.7876
2026-03-26 21:03:55,910 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=370 eval_loss=0.7214 duration_sec=14.32
2026-03-26 21:04:16,320 [INFO] new_opacus_codex.train_steps: epoch=2 step=375 loss=0.8158
2026-03-26 21:04:36,475 [INFO] new_opacus_codex.train_steps: epoch=2 step=380 loss=0.8328
2026-03-26 21:04:50,878 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=380 eval_loss=0.7201 duration_sec=14.40
2026-03-26 21:05:11,274 [INFO] new_opacus_codex.train_steps: epoch=2 step=385 loss=0.7830
2026-03-26 21:05:31,816 [INFO] new_opacus_codex.train_steps: epoch=2 step=390 loss=0.7645
2026-03-26 21:05:46,155 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=390 eval_loss=0.7203 duration_sec=14.33
2026-03-26 21:06:07,654 [INFO] new_opacus_codex.train_steps: epoch=2 step=395 loss=0.8012
2026-03-26 21:06:28,062 [INFO] new_opacus_codex.train_steps: epoch=2 step=400 loss=0.7899
2026-03-26 21:06:42,423 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=400 eval_loss=0.7195 duration_sec=14.35
2026-03-26 21:07:03,627 [INFO] new_opacus_codex.train_steps: epoch=2 step=405 loss=0.7566
2026-03-26 21:07:24,046 [INFO] new_opacus_codex.train_steps: epoch=2 step=410 loss=0.7887
2026-03-26 21:07:38,439 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=410 eval_loss=0.7191 duration_sec=14.38
2026-03-26 21:08:25,741 [INFO] new_opacus_codex.train_steps: epoch=3 step=415 loss=0.8109
2026-03-26 21:08:46,294 [INFO] new_opacus_codex.train_steps: epoch=3 step=420 loss=0.7466
2026-03-26 21:09:00,721 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=420 eval_loss=0.7188 duration_sec=14.42
2026-03-26 21:09:25,478 [INFO] new_opacus_codex.train_steps: epoch=3 step=425 loss=0.7358
2026-03-26 21:09:46,038 [INFO] new_opacus_codex.train_steps: epoch=3 step=430 loss=0.7333
2026-03-26 21:10:00,447 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=430 eval_loss=0.7192 duration_sec=14.40
2026-03-26 21:10:20,827 [INFO] new_opacus_codex.train_steps: epoch=3 step=435 loss=0.7491
2026-03-26 21:10:41,583 [INFO] new_opacus_codex.train_steps: epoch=3 step=440 loss=0.7817
2026-03-26 21:10:55,956 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=440 eval_loss=0.7185 duration_sec=14.36
2026-03-26 21:11:16,257 [INFO] new_opacus_codex.train_steps: epoch=3 step=445 loss=0.7814
2026-03-26 21:11:36,414 [INFO] new_opacus_codex.train_steps: epoch=3 step=450 loss=0.7548
2026-03-26 21:11:50,769 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=450 eval_loss=0.7186 duration_sec=14.34
2026-03-26 21:12:11,722 [INFO] new_opacus_codex.train_steps: epoch=3 step=455 loss=0.7390
2026-03-26 21:12:32,506 [INFO] new_opacus_codex.train_steps: epoch=3 step=460 loss=0.7373
2026-03-26 21:12:46,904 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=460 eval_loss=0.7181 duration_sec=14.38
2026-03-26 21:13:06,977 [INFO] new_opacus_codex.train_steps: epoch=3 step=465 loss=0.7512
2026-03-26 21:13:27,353 [INFO] new_opacus_codex.train_steps: epoch=3 step=470 loss=0.7872
2026-03-26 21:13:41,753 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=470 eval_loss=0.7183 duration_sec=14.38
2026-03-26 21:14:02,670 [INFO] new_opacus_codex.train_steps: epoch=3 step=475 loss=0.8038
2026-03-26 21:14:23,046 [INFO] new_opacus_codex.train_steps: epoch=3 step=480 loss=0.7661
2026-03-26 21:14:37,381 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=480 eval_loss=0.7180 duration_sec=14.31
2026-03-26 21:14:58,069 [INFO] new_opacus_codex.train_steps: epoch=3 step=485 loss=0.7453
2026-03-26 21:15:18,575 [INFO] new_opacus_codex.train_steps: epoch=3 step=490 loss=0.7684
2026-03-26 21:15:32,915 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=490 eval_loss=0.7183 duration_sec=14.32
2026-03-26 21:15:53,024 [INFO] new_opacus_codex.train_steps: epoch=3 step=495 loss=0.7794
2026-03-26 21:16:12,983 [INFO] new_opacus_codex.train_steps: epoch=3 step=500 loss=0.7717
2026-03-26 21:16:27,426 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=500 eval_loss=0.7177 duration_sec=14.44
2026-03-26 21:16:48,165 [INFO] new_opacus_codex.train_steps: epoch=3 step=505 loss=0.7551
2026-03-26 21:17:08,982 [INFO] new_opacus_codex.train_steps: epoch=3 step=510 loss=0.7502
2026-03-26 21:17:23,399 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=510 eval_loss=0.7176 duration_sec=14.40
2026-03-26 21:17:44,437 [INFO] new_opacus_codex.train_steps: epoch=3 step=515 loss=0.7898
2026-03-26 21:18:04,862 [INFO] new_opacus_codex.train_steps: epoch=3 step=520 loss=0.7763
2026-03-26 21:18:19,257 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=520 eval_loss=0.7176 duration_sec=14.39
2026-03-26 21:18:40,007 [INFO] new_opacus_codex.train_steps: epoch=3 step=525 loss=0.7456
2026-03-26 21:19:00,420 [INFO] new_opacus_codex.train_steps: epoch=3 step=530 loss=0.7513
2026-03-26 21:19:14,857 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=530 eval_loss=0.7175 duration_sec=14.43
2026-03-26 21:19:34,716 [INFO] new_opacus_codex.train_steps: epoch=3 step=535 loss=0.7400
2026-03-26 21:19:55,281 [INFO] new_opacus_codex.train_steps: epoch=3 step=540 loss=0.7338
2026-03-26 21:20:09,666 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=540 eval_loss=0.7178 duration_sec=14.37
2026-03-26 21:20:30,351 [INFO] new_opacus_codex.train_steps: epoch=3 step=545 loss=0.7458
2026-03-26 21:20:50,417 [INFO] new_opacus_codex.train_steps: epoch=3 step=550 loss=0.7656
2026-03-26 21:21:04,790 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=550 eval_loss=0.7177 duration_sec=14.35
2026-03-26 21:21:25,570 [INFO] new_opacus_codex.train_steps: epoch=3 step=555 loss=0.7428
2026-03-26 21:21:46,108 [INFO] new_opacus_codex.train_steps: epoch=3 step=560 loss=0.7736
2026-03-26 21:22:00,532 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=560 eval_loss=0.7174 duration_sec=14.42
2026-03-26 21:22:20,782 [INFO] new_opacus_codex.train_steps: epoch=3 step=565 loss=0.7934
2026-03-26 21:22:41,317 [INFO] new_opacus_codex.train_steps: epoch=3 step=570 loss=0.7694
2026-03-26 21:22:55,693 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=570 eval_loss=0.7173 duration_sec=14.36
2026-03-26 21:23:16,365 [INFO] new_opacus_codex.train_steps: epoch=3 step=575 loss=0.7937
2026-03-26 21:23:36,789 [INFO] new_opacus_codex.train_steps: epoch=3 step=580 loss=0.7859
2026-03-26 21:23:51,230 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=580 eval_loss=0.7172 duration_sec=14.41
2026-03-26 21:24:11,870 [INFO] new_opacus_codex.train_steps: epoch=3 step=585 loss=0.7798
2026-03-26 21:24:32,432 [INFO] new_opacus_codex.train_steps: epoch=3 step=590 loss=0.7814
2026-03-26 21:24:46,765 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=590 eval_loss=0.7172 duration_sec=14.32
2026-03-26 21:25:06,859 [INFO] new_opacus_codex.train_steps: epoch=3 step=595 loss=0.7611
2026-03-26 21:25:27,657 [INFO] new_opacus_codex.train_steps: epoch=3 step=600 loss=0.7559
2026-03-26 21:25:42,044 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=600 eval_loss=0.7174 duration_sec=14.37
2026-03-26 21:26:02,268 [INFO] new_opacus_codex.train_steps: epoch=3 step=605 loss=0.7663
2026-03-26 21:26:23,378 [INFO] new_opacus_codex.train_steps: epoch=3 step=610 loss=0.7494
2026-03-26 21:26:37,766 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=610 eval_loss=0.7172 duration_sec=14.38
2026-03-26 21:26:58,297 [INFO] new_opacus_codex.train_steps: epoch=3 step=615 loss=0.7487
2026-03-26 21:27:18,563 [INFO] new_opacus_codex.train_steps: epoch=3 step=620 loss=0.7728
2026-03-26 21:27:32,973 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=620 eval_loss=0.7171 duration_sec=14.39