melihcatal's picture
Add files using upload-large-folder tool
076fd74 verified
2026-03-28 13:46:52,362 [INFO] new_opacus_codex.train_steps: epoch=1 step=5 loss=2.0000
2026-03-28 13:47:22,723 [INFO] new_opacus_codex.train_steps: epoch=1 step=10 loss=2.0224
2026-03-28 13:47:36,695 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=10 eval_loss=0.8438 duration_sec=13.96
2026-03-28 13:48:06,703 [INFO] new_opacus_codex.train_steps: epoch=1 step=15 loss=2.0530
2026-03-28 13:48:36,284 [INFO] new_opacus_codex.train_steps: epoch=1 step=20 loss=2.0700
2026-03-28 13:48:50,412 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=20 eval_loss=0.8438 duration_sec=14.12
2026-03-28 13:49:19,956 [INFO] new_opacus_codex.train_steps: epoch=1 step=25 loss=2.2083
2026-03-28 13:49:49,615 [INFO] new_opacus_codex.train_steps: epoch=1 step=30 loss=2.0944
2026-03-28 13:50:03,761 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=30 eval_loss=0.8438 duration_sec=14.13
2026-03-28 13:50:34,163 [INFO] new_opacus_codex.train_steps: epoch=1 step=35 loss=1.8190
2026-03-28 13:51:03,817 [INFO] new_opacus_codex.train_steps: epoch=1 step=40 loss=1.9959
2026-03-28 13:51:17,969 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=40 eval_loss=0.8439 duration_sec=14.14
2026-03-28 13:51:48,313 [INFO] new_opacus_codex.train_steps: epoch=1 step=45 loss=2.2167
2026-03-28 13:52:17,847 [INFO] new_opacus_codex.train_steps: epoch=1 step=50 loss=2.0240
2026-03-28 13:52:31,973 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=50 eval_loss=0.8441 duration_sec=14.11
2026-03-28 13:53:01,934 [INFO] new_opacus_codex.train_steps: epoch=1 step=55 loss=1.8414
2026-03-28 13:53:32,673 [INFO] new_opacus_codex.train_steps: epoch=1 step=60 loss=1.9628
2026-03-28 13:53:46,836 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=60 eval_loss=0.8443 duration_sec=14.15
2026-03-28 13:54:17,406 [INFO] new_opacus_codex.train_steps: epoch=1 step=65 loss=2.1801
2026-03-28 13:54:47,378 [INFO] new_opacus_codex.train_steps: epoch=1 step=70 loss=2.2154
2026-03-28 13:55:01,597 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=70 eval_loss=0.8444 duration_sec=14.20
2026-03-28 13:55:32,703 [INFO] new_opacus_codex.train_steps: epoch=1 step=75 loss=2.2674
2026-03-28 13:56:03,545 [INFO] new_opacus_codex.train_steps: epoch=1 step=80 loss=2.1890
2026-03-28 13:56:17,754 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=80 eval_loss=0.8447 duration_sec=14.20
2026-03-28 13:56:49,218 [INFO] new_opacus_codex.train_steps: epoch=1 step=85 loss=1.9198
2026-03-28 13:57:19,298 [INFO] new_opacus_codex.train_steps: epoch=1 step=90 loss=2.0059
2026-03-28 13:57:33,403 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=90 eval_loss=0.8449 duration_sec=14.09
2026-03-28 13:58:03,127 [INFO] new_opacus_codex.train_steps: epoch=1 step=95 loss=2.1694
2026-03-28 13:58:33,252 [INFO] new_opacus_codex.train_steps: epoch=1 step=100 loss=2.2044
2026-03-28 13:58:47,401 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=100 eval_loss=0.8451 duration_sec=14.13
2026-03-28 13:59:18,375 [INFO] new_opacus_codex.train_steps: epoch=1 step=105 loss=2.2893
2026-03-28 13:59:48,885 [INFO] new_opacus_codex.train_steps: epoch=1 step=110 loss=2.2133
2026-03-28 14:00:03,098 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=110 eval_loss=0.8452 duration_sec=14.20
2026-03-28 14:00:33,376 [INFO] new_opacus_codex.train_steps: epoch=1 step=115 loss=1.9634
2026-03-28 14:01:04,215 [INFO] new_opacus_codex.train_steps: epoch=1 step=120 loss=2.0020
2026-03-28 14:01:18,373 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=120 eval_loss=0.8454 duration_sec=14.14
2026-03-28 14:01:48,793 [INFO] new_opacus_codex.train_steps: epoch=1 step=125 loss=2.1730
2026-03-28 14:02:19,279 [INFO] new_opacus_codex.train_steps: epoch=1 step=130 loss=1.9881
2026-03-28 14:02:33,488 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=130 eval_loss=0.8456 duration_sec=14.20
2026-03-28 14:03:04,612 [INFO] new_opacus_codex.train_steps: epoch=1 step=135 loss=2.0044
2026-03-28 14:03:34,206 [INFO] new_opacus_codex.train_steps: epoch=1 step=140 loss=2.2351
2026-03-28 14:03:49,235 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=140 eval_loss=0.8458 duration_sec=15.02
2026-03-28 14:04:19,029 [INFO] new_opacus_codex.train_steps: epoch=1 step=145 loss=2.0495
2026-03-28 14:04:50,029 [INFO] new_opacus_codex.train_steps: epoch=1 step=150 loss=1.9837
2026-03-28 14:05:04,200 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=150 eval_loss=0.8459 duration_sec=14.16
2026-03-28 14:05:34,356 [INFO] new_opacus_codex.train_steps: epoch=1 step=155 loss=1.8646
2026-03-28 14:06:04,083 [INFO] new_opacus_codex.train_steps: epoch=1 step=160 loss=1.7710
2026-03-28 14:06:18,233 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=160 eval_loss=0.8461 duration_sec=14.13
2026-03-28 14:06:48,746 [INFO] new_opacus_codex.train_steps: epoch=1 step=165 loss=2.0928
2026-03-28 14:07:19,680 [INFO] new_opacus_codex.train_steps: epoch=1 step=170 loss=2.0982
2026-03-28 14:07:33,796 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=170 eval_loss=0.8462 duration_sec=14.10
2026-03-28 14:08:04,035 [INFO] new_opacus_codex.train_steps: epoch=1 step=175 loss=1.8781
2026-03-28 14:08:34,159 [INFO] new_opacus_codex.train_steps: epoch=1 step=180 loss=2.0760
2026-03-28 14:08:48,358 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=180 eval_loss=0.8463 duration_sec=14.19
2026-03-28 14:09:19,269 [INFO] new_opacus_codex.train_steps: epoch=1 step=185 loss=2.1449
2026-03-28 14:09:50,552 [INFO] new_opacus_codex.train_steps: epoch=1 step=190 loss=2.1119
2026-03-28 14:10:04,688 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=190 eval_loss=0.8465 duration_sec=14.13
2026-03-28 14:10:35,379 [INFO] new_opacus_codex.train_steps: epoch=1 step=195 loss=2.2016
2026-03-28 14:11:05,919 [INFO] new_opacus_codex.train_steps: epoch=1 step=200 loss=2.0013
2026-03-28 14:11:20,104 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=200 eval_loss=0.8467 duration_sec=14.17
2026-03-28 14:11:50,118 [INFO] new_opacus_codex.train_steps: epoch=1 step=205 loss=1.9258
2026-03-28 14:12:40,314 [INFO] new_opacus_codex.train_steps: epoch=2 step=210 loss=1.6090
2026-03-28 14:12:54,471 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=210 eval_loss=0.8467 duration_sec=14.15
2026-03-28 14:13:26,978 [INFO] new_opacus_codex.train_steps: epoch=2 step=215 loss=1.9422
2026-03-28 14:13:57,250 [INFO] new_opacus_codex.train_steps: epoch=2 step=220 loss=2.0564
2026-03-28 14:14:11,390 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=220 eval_loss=0.8468 duration_sec=14.13
2026-03-28 14:14:42,678 [INFO] new_opacus_codex.train_steps: epoch=2 step=225 loss=1.9391
2026-03-28 14:15:12,450 [INFO] new_opacus_codex.train_steps: epoch=2 step=230 loss=1.9634
2026-03-28 14:15:26,613 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=230 eval_loss=0.8470 duration_sec=14.14
2026-03-28 14:15:57,025 [INFO] new_opacus_codex.train_steps: epoch=2 step=235 loss=2.1452
2026-03-28 14:16:28,948 [INFO] new_opacus_codex.train_steps: epoch=2 step=240 loss=2.1719
2026-03-28 14:16:43,098 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=240 eval_loss=0.8470 duration_sec=14.14
2026-03-28 14:17:13,839 [INFO] new_opacus_codex.train_steps: epoch=2 step=245 loss=1.9842
2026-03-28 14:17:44,865 [INFO] new_opacus_codex.train_steps: epoch=2 step=250 loss=1.9807
2026-03-28 14:17:58,997 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=250 eval_loss=0.8472 duration_sec=14.12
2026-03-28 14:18:30,223 [INFO] new_opacus_codex.train_steps: epoch=2 step=255 loss=2.0436
2026-03-28 14:19:00,057 [INFO] new_opacus_codex.train_steps: epoch=2 step=260 loss=1.8950
2026-03-28 14:19:14,094 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=260 eval_loss=0.8472 duration_sec=14.02
2026-03-28 14:19:44,005 [INFO] new_opacus_codex.train_steps: epoch=2 step=265 loss=1.8954
2026-03-28 14:20:13,743 [INFO] new_opacus_codex.train_steps: epoch=2 step=270 loss=2.0074
2026-03-28 14:20:27,850 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=270 eval_loss=0.8473 duration_sec=14.10
2026-03-28 14:20:58,268 [INFO] new_opacus_codex.train_steps: epoch=2 step=275 loss=1.9900
2026-03-28 14:21:29,469 [INFO] new_opacus_codex.train_steps: epoch=2 step=280 loss=1.9760
2026-03-28 14:21:43,525 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=280 eval_loss=0.8474 duration_sec=14.04
2026-03-28 14:22:14,566 [INFO] new_opacus_codex.train_steps: epoch=2 step=285 loss=2.0315
2026-03-28 14:22:44,614 [INFO] new_opacus_codex.train_steps: epoch=2 step=290 loss=2.0358
2026-03-28 14:22:58,771 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=290 eval_loss=0.8474 duration_sec=14.15
2026-03-28 14:23:29,215 [INFO] new_opacus_codex.train_steps: epoch=2 step=295 loss=2.0550
2026-03-28 14:23:59,596 [INFO] new_opacus_codex.train_steps: epoch=2 step=300 loss=2.1625
2026-03-28 14:24:13,809 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=300 eval_loss=0.8475 duration_sec=14.20
2026-03-28 14:24:44,843 [INFO] new_opacus_codex.train_steps: epoch=2 step=305 loss=2.1874
2026-03-28 14:25:15,876 [INFO] new_opacus_codex.train_steps: epoch=2 step=310 loss=2.1630
2026-03-28 14:25:29,974 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=310 eval_loss=0.8475 duration_sec=14.08
2026-03-28 14:26:00,626 [INFO] new_opacus_codex.train_steps: epoch=2 step=315 loss=2.1411
2026-03-28 14:26:32,132 [INFO] new_opacus_codex.train_steps: epoch=2 step=320 loss=2.1864
2026-03-28 14:26:46,297 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=320 eval_loss=0.8476 duration_sec=14.16
2026-03-28 14:27:16,642 [INFO] new_opacus_codex.train_steps: epoch=2 step=325 loss=2.1609
2026-03-28 14:27:46,662 [INFO] new_opacus_codex.train_steps: epoch=2 step=330 loss=2.1494
2026-03-28 14:28:00,861 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=330 eval_loss=0.8476 duration_sec=14.18
2026-03-28 14:28:30,640 [INFO] new_opacus_codex.train_steps: epoch=2 step=335 loss=2.0035
2026-03-28 14:29:00,654 [INFO] new_opacus_codex.train_steps: epoch=2 step=340 loss=1.8306
2026-03-28 14:29:14,793 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=340 eval_loss=0.8476 duration_sec=14.12
2026-03-28 14:29:44,667 [INFO] new_opacus_codex.train_steps: epoch=2 step=345 loss=1.7689
2026-03-28 14:30:16,121 [INFO] new_opacus_codex.train_steps: epoch=2 step=350 loss=1.8432
2026-03-28 14:30:30,269 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=350 eval_loss=0.8476 duration_sec=14.14
2026-03-28 14:31:00,750 [INFO] new_opacus_codex.train_steps: epoch=2 step=355 loss=2.2141
2026-03-28 14:31:31,197 [INFO] new_opacus_codex.train_steps: epoch=2 step=360 loss=2.3017
2026-03-28 14:31:45,330 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=360 eval_loss=0.8476 duration_sec=14.12
2026-03-28 14:32:15,222 [INFO] new_opacus_codex.train_steps: epoch=2 step=365 loss=2.0737
2026-03-28 14:32:46,351 [INFO] new_opacus_codex.train_steps: epoch=2 step=370 loss=1.9857
2026-03-28 14:33:00,524 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=370 eval_loss=0.8476 duration_sec=14.16
2026-03-28 14:33:31,482 [INFO] new_opacus_codex.train_steps: epoch=2 step=375 loss=1.9109
2026-03-28 14:34:01,972 [INFO] new_opacus_codex.train_steps: epoch=2 step=380 loss=1.9104
2026-03-28 14:34:15,959 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=380 eval_loss=0.8476 duration_sec=13.97
2026-03-28 14:34:46,862 [INFO] new_opacus_codex.train_steps: epoch=2 step=385 loss=2.0383
2026-03-28 14:35:17,497 [INFO] new_opacus_codex.train_steps: epoch=2 step=390 loss=1.9764
2026-03-28 14:35:31,508 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=390 eval_loss=0.8476 duration_sec=13.99
2026-03-28 14:36:01,762 [INFO] new_opacus_codex.train_steps: epoch=2 step=395 loss=1.9234
2026-03-28 14:36:32,780 [INFO] new_opacus_codex.train_steps: epoch=2 step=400 loss=1.8848
2026-03-28 14:36:46,780 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=400 eval_loss=0.8476 duration_sec=13.99
2026-03-28 14:37:17,364 [INFO] new_opacus_codex.train_steps: epoch=2 step=405 loss=1.8410
2026-03-28 14:37:47,966 [INFO] new_opacus_codex.train_steps: epoch=2 step=410 loss=2.0221
2026-03-28 14:38:01,985 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=410 eval_loss=0.8476 duration_sec=14.01
2026-03-28 14:38:32,105 [INFO] new_opacus_codex.train_steps: epoch=2 step=415 loss=2.0193
2026-03-28 14:39:24,711 [INFO] new_opacus_codex.train_steps: epoch=3 step=420 loss=2.1418
2026-03-28 14:39:38,835 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=420 eval_loss=0.8476 duration_sec=14.11
2026-03-28 14:40:10,632 [INFO] new_opacus_codex.train_steps: epoch=3 step=425 loss=1.9398
2026-03-28 14:40:40,648 [INFO] new_opacus_codex.train_steps: epoch=3 step=430 loss=1.9176
2026-03-28 14:40:54,798 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=430 eval_loss=0.8476 duration_sec=14.14
2026-03-28 14:41:25,847 [INFO] new_opacus_codex.train_steps: epoch=3 step=435 loss=1.9367
2026-03-28 14:41:55,833 [INFO] new_opacus_codex.train_steps: epoch=3 step=440 loss=1.7610
2026-03-28 14:42:10,034 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=440 eval_loss=0.8476 duration_sec=14.19
2026-03-28 14:42:41,536 [INFO] new_opacus_codex.train_steps: epoch=3 step=445 loss=1.8304
2026-03-28 14:43:11,903 [INFO] new_opacus_codex.train_steps: epoch=3 step=450 loss=2.0404
2026-03-28 14:43:26,057 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=450 eval_loss=0.8476 duration_sec=14.14
2026-03-28 14:43:56,177 [INFO] new_opacus_codex.train_steps: epoch=3 step=455 loss=2.1372
2026-03-28 14:44:26,324 [INFO] new_opacus_codex.train_steps: epoch=3 step=460 loss=2.0198
2026-03-28 14:44:40,457 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=460 eval_loss=0.8476 duration_sec=14.12
2026-03-28 14:45:10,561 [INFO] new_opacus_codex.train_steps: epoch=3 step=465 loss=1.9766
2026-03-28 14:45:40,691 [INFO] new_opacus_codex.train_steps: epoch=3 step=470 loss=2.1046
2026-03-28 14:45:54,866 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=470 eval_loss=0.8476 duration_sec=14.16
2026-03-28 14:46:25,437 [INFO] new_opacus_codex.train_steps: epoch=3 step=475 loss=2.1352
2026-03-28 14:46:55,892 [INFO] new_opacus_codex.train_steps: epoch=3 step=480 loss=2.0696
2026-03-28 14:47:10,029 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=480 eval_loss=0.8476 duration_sec=14.12
2026-03-28 14:47:41,139 [INFO] new_opacus_codex.train_steps: epoch=3 step=485 loss=1.9125
2026-03-28 14:48:11,693 [INFO] new_opacus_codex.train_steps: epoch=3 step=490 loss=1.9852
2026-03-28 14:48:25,860 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=490 eval_loss=0.8476 duration_sec=14.16
2026-03-28 14:48:56,264 [INFO] new_opacus_codex.train_steps: epoch=3 step=495 loss=2.2147
2026-03-28 14:49:27,874 [INFO] new_opacus_codex.train_steps: epoch=3 step=500 loss=2.2509
2026-03-28 14:49:42,031 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=500 eval_loss=0.8476 duration_sec=14.14
2026-03-28 14:50:13,378 [INFO] new_opacus_codex.train_steps: epoch=3 step=505 loss=2.1189
2026-03-28 14:50:44,123 [INFO] new_opacus_codex.train_steps: epoch=3 step=510 loss=2.1145
2026-03-28 14:50:58,296 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=510 eval_loss=0.8476 duration_sec=14.16
2026-03-28 14:51:30,061 [INFO] new_opacus_codex.train_steps: epoch=3 step=515 loss=2.0307
2026-03-28 14:52:01,588 [INFO] new_opacus_codex.train_steps: epoch=3 step=520 loss=1.9990
2026-03-28 14:52:15,705 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=520 eval_loss=0.8476 duration_sec=14.10
2026-03-28 14:52:45,894 [INFO] new_opacus_codex.train_steps: epoch=3 step=525 loss=1.9065
2026-03-28 14:53:16,664 [INFO] new_opacus_codex.train_steps: epoch=3 step=530 loss=1.8146
2026-03-28 14:53:30,927 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=530 eval_loss=0.8476 duration_sec=14.25
2026-03-28 14:54:01,938 [INFO] new_opacus_codex.train_steps: epoch=3 step=535 loss=2.1911
2026-03-28 14:54:34,635 [INFO] new_opacus_codex.train_steps: epoch=3 step=540 loss=2.2505
2026-03-28 14:54:48,805 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=540 eval_loss=0.8476 duration_sec=14.16
2026-03-28 14:55:19,498 [INFO] new_opacus_codex.train_steps: epoch=3 step=545 loss=2.1405
2026-03-28 14:55:50,406 [INFO] new_opacus_codex.train_steps: epoch=3 step=550 loss=2.1064
2026-03-28 14:56:04,600 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=550 eval_loss=0.8476 duration_sec=14.18
2026-03-28 14:56:35,236 [INFO] new_opacus_codex.train_steps: epoch=3 step=555 loss=1.9452
2026-03-28 14:57:06,871 [INFO] new_opacus_codex.train_steps: epoch=3 step=560 loss=1.9163
2026-03-28 14:57:21,059 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=560 eval_loss=0.8477 duration_sec=14.17
2026-03-28 14:57:51,471 [INFO] new_opacus_codex.train_steps: epoch=3 step=565 loss=2.0204
2026-03-28 14:58:22,662 [INFO] new_opacus_codex.train_steps: epoch=3 step=570 loss=2.1022
2026-03-28 14:58:36,804 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=570 eval_loss=0.8476 duration_sec=14.13
2026-03-28 14:59:07,943 [INFO] new_opacus_codex.train_steps: epoch=3 step=575 loss=2.0387
2026-03-28 14:59:39,328 [INFO] new_opacus_codex.train_steps: epoch=3 step=580 loss=1.9491
2026-03-28 14:59:53,496 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=580 eval_loss=0.8476 duration_sec=14.15
2026-03-28 15:00:24,809 [INFO] new_opacus_codex.train_steps: epoch=3 step=585 loss=2.0822
2026-03-28 15:00:55,766 [INFO] new_opacus_codex.train_steps: epoch=3 step=590 loss=2.2217
2026-03-28 15:01:09,912 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=590 eval_loss=0.8476 duration_sec=14.14
2026-03-28 15:01:40,636 [INFO] new_opacus_codex.train_steps: epoch=3 step=595 loss=2.1237
2026-03-28 15:02:12,473 [INFO] new_opacus_codex.train_steps: epoch=3 step=600 loss=1.8769
2026-03-28 15:02:26,650 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=600 eval_loss=0.8476 duration_sec=14.16
2026-03-28 15:02:57,223 [INFO] new_opacus_codex.train_steps: epoch=3 step=605 loss=2.0249
2026-03-28 15:03:28,511 [INFO] new_opacus_codex.train_steps: epoch=3 step=610 loss=2.1331
2026-03-28 15:03:42,699 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=610 eval_loss=0.8476 duration_sec=14.18
2026-03-28 15:04:14,184 [INFO] new_opacus_codex.train_steps: epoch=3 step=615 loss=2.0302
2026-03-28 15:04:43,849 [INFO] new_opacus_codex.train_steps: epoch=3 step=620 loss=2.0770
2026-03-28 15:04:57,979 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=620 eval_loss=0.8476 duration_sec=14.12