melihcatal's picture
Add files using upload-large-folder tool
45b1c92 verified
Raw History Blame Contribute Delete
28.9 kB
2026-03-29 14:40:28,617 [INFO] new_opacus_codex.train_steps: epoch=1 step=5 loss=2.1414
2026-03-29 14:41:02,542 [INFO] new_opacus_codex.train_steps: epoch=1 step=10 loss=2.0935
2026-03-29 14:41:10,560 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=10 eval_loss=1.0783 duration_sec=8.00
2026-03-29 14:41:45,028 [INFO] new_opacus_codex.train_steps: epoch=1 step=15 loss=2.0745
2026-03-29 14:42:17,956 [INFO] new_opacus_codex.train_steps: epoch=1 step=20 loss=2.0791
2026-03-29 14:42:25,942 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=20 eval_loss=1.0784 duration_sec=7.97
2026-03-29 14:43:00,324 [INFO] new_opacus_codex.train_steps: epoch=1 step=25 loss=2.2613
2026-03-29 14:43:34,583 [INFO] new_opacus_codex.train_steps: epoch=1 step=30 loss=2.2417
2026-03-29 14:43:42,623 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=30 eval_loss=1.0789 duration_sec=8.03
2026-03-29 14:44:15,666 [INFO] new_opacus_codex.train_steps: epoch=1 step=35 loss=1.9412
2026-03-29 14:44:49,513 [INFO] new_opacus_codex.train_steps: epoch=1 step=40 loss=2.1127
2026-03-29 14:44:57,492 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=40 eval_loss=1.0800 duration_sec=7.97
2026-03-29 14:45:31,420 [INFO] new_opacus_codex.train_steps: epoch=1 step=45 loss=2.3502
2026-03-29 14:46:04,991 [INFO] new_opacus_codex.train_steps: epoch=1 step=50 loss=2.0822
2026-03-29 14:46:12,946 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=50 eval_loss=1.0823 duration_sec=7.93
2026-03-29 14:46:46,595 [INFO] new_opacus_codex.train_steps: epoch=1 step=55 loss=1.8522
2026-03-29 14:47:20,086 [INFO] new_opacus_codex.train_steps: epoch=1 step=60 loss=2.0068
2026-03-29 14:47:28,120 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=60 eval_loss=1.0852 duration_sec=8.03
2026-03-29 14:48:01,411 [INFO] new_opacus_codex.train_steps: epoch=1 step=65 loss=2.2600
2026-03-29 14:48:34,644 [INFO] new_opacus_codex.train_steps: epoch=1 step=70 loss=2.3432
2026-03-29 14:48:42,652 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=70 eval_loss=1.0881 duration_sec=7.99
2026-03-29 14:49:17,476 [INFO] new_opacus_codex.train_steps: epoch=1 step=75 loss=2.4698
2026-03-29 14:49:51,576 [INFO] new_opacus_codex.train_steps: epoch=1 step=80 loss=2.3352
2026-03-29 14:49:59,600 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=80 eval_loss=1.0910 duration_sec=8.01
2026-03-29 14:50:33,465 [INFO] new_opacus_codex.train_steps: epoch=1 step=85 loss=2.0012
2026-03-29 14:51:07,868 [INFO] new_opacus_codex.train_steps: epoch=1 step=90 loss=2.1392
2026-03-29 14:51:15,890 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=90 eval_loss=1.0943 duration_sec=8.01
2026-03-29 14:51:49,585 [INFO] new_opacus_codex.train_steps: epoch=1 step=95 loss=2.3206
2026-03-29 14:52:22,999 [INFO] new_opacus_codex.train_steps: epoch=1 step=100 loss=2.3747
2026-03-29 14:52:31,042 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=100 eval_loss=1.0976 duration_sec=8.03
2026-03-29 14:53:06,283 [INFO] new_opacus_codex.train_steps: epoch=1 step=105 loss=2.4666
2026-03-29 14:53:39,187 [INFO] new_opacus_codex.train_steps: epoch=1 step=110 loss=2.3795
2026-03-29 14:53:47,163 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=110 eval_loss=1.1010 duration_sec=7.96
2026-03-29 14:54:20,659 [INFO] new_opacus_codex.train_steps: epoch=1 step=115 loss=2.0618
2026-03-29 14:54:53,946 [INFO] new_opacus_codex.train_steps: epoch=1 step=120 loss=2.0909
2026-03-29 14:55:01,944 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=120 eval_loss=1.1043 duration_sec=7.98
2026-03-29 14:55:35,560 [INFO] new_opacus_codex.train_steps: epoch=1 step=125 loss=2.2700
2026-03-29 14:56:09,664 [INFO] new_opacus_codex.train_steps: epoch=1 step=130 loss=2.0091
2026-03-29 14:56:17,676 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=130 eval_loss=1.1074 duration_sec=8.00
2026-03-29 14:56:51,051 [INFO] new_opacus_codex.train_steps: epoch=1 step=135 loss=2.0236
2026-03-29 14:57:24,122 [INFO] new_opacus_codex.train_steps: epoch=1 step=140 loss=2.2649
2026-03-29 14:57:32,120 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=140 eval_loss=1.1104 duration_sec=7.99
2026-03-29 14:58:05,778 [INFO] new_opacus_codex.train_steps: epoch=1 step=145 loss=2.1158
2026-03-29 14:58:39,723 [INFO] new_opacus_codex.train_steps: epoch=1 step=150 loss=2.1272
2026-03-29 14:58:47,775 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=150 eval_loss=1.1134 duration_sec=8.04
2026-03-29 14:59:21,046 [INFO] new_opacus_codex.train_steps: epoch=1 step=155 loss=1.9310
2026-03-29 14:59:53,220 [INFO] new_opacus_codex.train_steps: epoch=1 step=160 loss=1.7493
2026-03-29 15:00:01,310 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=160 eval_loss=1.1162 duration_sec=8.08
2026-03-29 15:00:35,761 [INFO] new_opacus_codex.train_steps: epoch=1 step=165 loss=2.1870
2026-03-29 15:01:09,268 [INFO] new_opacus_codex.train_steps: epoch=1 step=170 loss=2.2112
2026-03-29 15:01:17,323 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=170 eval_loss=1.1190 duration_sec=8.04
2026-03-29 15:01:51,096 [INFO] new_opacus_codex.train_steps: epoch=1 step=175 loss=1.9143
2026-03-29 15:02:26,350 [INFO] new_opacus_codex.train_steps: epoch=1 step=180 loss=2.1619
2026-03-29 15:02:34,353 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=1 step=180 eval_loss=1.1218 duration_sec=7.98
2026-03-29 15:03:22,422 [INFO] new_opacus_codex.train_steps: epoch=2 step=185 loss=2.3164
2026-03-29 15:03:57,714 [INFO] new_opacus_codex.train_steps: epoch=2 step=190 loss=2.3553
2026-03-29 15:04:05,731 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=190 eval_loss=1.1245 duration_sec=7.96
2026-03-29 15:04:39,939 [INFO] new_opacus_codex.train_steps: epoch=2 step=195 loss=2.3014
2026-03-29 15:05:13,901 [INFO] new_opacus_codex.train_steps: epoch=2 step=200 loss=2.0436
2026-03-29 15:05:21,967 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=200 eval_loss=1.1270 duration_sec=8.00
2026-03-29 15:05:55,408 [INFO] new_opacus_codex.train_steps: epoch=2 step=205 loss=1.9309
2026-03-29 15:06:28,378 [INFO] new_opacus_codex.train_steps: epoch=2 step=210 loss=1.9684
2026-03-29 15:06:36,390 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=210 eval_loss=1.1294 duration_sec=8.00
2026-03-29 15:07:10,532 [INFO] new_opacus_codex.train_steps: epoch=2 step=215 loss=2.0520
2026-03-29 15:07:44,537 [INFO] new_opacus_codex.train_steps: epoch=2 step=220 loss=2.1553
2026-03-29 15:07:52,660 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=220 eval_loss=1.1316 duration_sec=8.11
2026-03-29 15:08:25,859 [INFO] new_opacus_codex.train_steps: epoch=2 step=225 loss=1.9728
2026-03-29 15:08:59,374 [INFO] new_opacus_codex.train_steps: epoch=2 step=230 loss=1.9685
2026-03-29 15:09:07,448 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=230 eval_loss=1.1340 duration_sec=8.06
2026-03-29 15:09:40,238 [INFO] new_opacus_codex.train_steps: epoch=2 step=235 loss=2.2364
2026-03-29 15:10:14,120 [INFO] new_opacus_codex.train_steps: epoch=2 step=240 loss=2.2879
2026-03-29 15:10:22,135 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=240 eval_loss=1.1365 duration_sec=7.99
2026-03-29 15:10:56,109 [INFO] new_opacus_codex.train_steps: epoch=2 step=245 loss=2.0293
2026-03-29 15:11:31,207 [INFO] new_opacus_codex.train_steps: epoch=2 step=250 loss=2.0180
2026-03-29 15:11:39,385 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=250 eval_loss=1.1391 duration_sec=8.17
2026-03-29 15:12:13,377 [INFO] new_opacus_codex.train_steps: epoch=2 step=255 loss=2.0215
2026-03-29 15:12:46,964 [INFO] new_opacus_codex.train_steps: epoch=2 step=260 loss=1.8573
2026-03-29 15:12:55,025 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=260 eval_loss=1.1420 duration_sec=8.05
2026-03-29 15:13:29,303 [INFO] new_opacus_codex.train_steps: epoch=2 step=265 loss=1.9312
2026-03-29 15:14:02,191 [INFO] new_opacus_codex.train_steps: epoch=2 step=270 loss=2.0497
2026-03-29 15:14:10,237 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=270 eval_loss=1.1445 duration_sec=8.04
2026-03-29 15:14:44,710 [INFO] new_opacus_codex.train_steps: epoch=2 step=275 loss=2.0730
2026-03-29 15:15:20,460 [INFO] new_opacus_codex.train_steps: epoch=2 step=280 loss=2.0573
2026-03-29 15:15:28,507 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=280 eval_loss=1.1466 duration_sec=8.04
2026-03-29 15:16:00,937 [INFO] new_opacus_codex.train_steps: epoch=2 step=285 loss=2.0489
2026-03-29 15:16:34,485 [INFO] new_opacus_codex.train_steps: epoch=2 step=290 loss=2.0293
2026-03-29 15:16:42,527 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=290 eval_loss=1.1485 duration_sec=8.03
2026-03-29 15:17:17,068 [INFO] new_opacus_codex.train_steps: epoch=2 step=295 loss=2.0242
2026-03-29 15:17:50,338 [INFO] new_opacus_codex.train_steps: epoch=2 step=300 loss=2.1534
2026-03-29 15:17:58,351 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=300 eval_loss=1.1502 duration_sec=8.00
2026-03-29 15:18:31,915 [INFO] new_opacus_codex.train_steps: epoch=2 step=305 loss=2.2027
2026-03-29 15:19:06,223 [INFO] new_opacus_codex.train_steps: epoch=2 step=310 loss=2.1801
2026-03-29 15:19:14,244 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=310 eval_loss=1.1519 duration_sec=8.01
2026-03-29 15:19:48,707 [INFO] new_opacus_codex.train_steps: epoch=2 step=315 loss=2.1617
2026-03-29 15:20:23,331 [INFO] new_opacus_codex.train_steps: epoch=2 step=320 loss=2.2360
2026-03-29 15:20:31,347 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=320 eval_loss=1.1537 duration_sec=8.00
2026-03-29 15:21:04,417 [INFO] new_opacus_codex.train_steps: epoch=2 step=325 loss=2.1544
2026-03-29 15:21:37,791 [INFO] new_opacus_codex.train_steps: epoch=2 step=330 loss=2.0713
2026-03-29 15:21:45,763 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=330 eval_loss=1.1557 duration_sec=7.96
2026-03-29 15:22:18,195 [INFO] new_opacus_codex.train_steps: epoch=2 step=335 loss=1.9553
2026-03-29 15:22:52,284 [INFO] new_opacus_codex.train_steps: epoch=2 step=340 loss=1.7221
2026-03-29 15:23:00,303 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=340 eval_loss=1.1575 duration_sec=8.00
2026-03-29 15:23:33,870 [INFO] new_opacus_codex.train_steps: epoch=2 step=345 loss=1.6666
2026-03-29 15:24:07,712 [INFO] new_opacus_codex.train_steps: epoch=2 step=350 loss=1.8008
2026-03-29 15:24:15,688 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=350 eval_loss=1.1592 duration_sec=7.97
2026-03-29 15:24:48,828 [INFO] new_opacus_codex.train_steps: epoch=2 step=355 loss=2.1062
2026-03-29 15:25:22,947 [INFO] new_opacus_codex.train_steps: epoch=2 step=360 loss=2.1706
2026-03-29 15:25:30,972 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=2 step=360 eval_loss=1.1608 duration_sec=7.99
2026-03-29 15:26:04,136 [INFO] new_opacus_codex.train_steps: epoch=2 step=365 loss=2.0002
2026-03-29 15:26:54,204 [INFO] new_opacus_codex.train_steps: epoch=3 step=370 loss=1.9981
2026-03-29 15:27:02,269 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=370 eval_loss=1.1622 duration_sec=8.00
2026-03-29 15:27:36,951 [INFO] new_opacus_codex.train_steps: epoch=3 step=375 loss=1.7358
2026-03-29 15:28:11,259 [INFO] new_opacus_codex.train_steps: epoch=3 step=380 loss=1.8355
2026-03-29 15:28:19,263 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=380 eval_loss=1.1635 duration_sec=7.97
2026-03-29 15:28:53,727 [INFO] new_opacus_codex.train_steps: epoch=3 step=385 loss=2.0328
2026-03-29 15:29:28,504 [INFO] new_opacus_codex.train_steps: epoch=3 step=390 loss=2.0250
2026-03-29 15:29:36,536 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=390 eval_loss=1.1650 duration_sec=8.00
2026-03-29 15:30:10,370 [INFO] new_opacus_codex.train_steps: epoch=3 step=395 loss=1.8838
2026-03-29 15:30:43,633 [INFO] new_opacus_codex.train_steps: epoch=3 step=400 loss=1.8066
2026-03-29 15:30:51,626 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=400 eval_loss=1.1663 duration_sec=7.96
2026-03-29 15:31:24,654 [INFO] new_opacus_codex.train_steps: epoch=3 step=405 loss=1.8368
2026-03-29 15:31:58,905 [INFO] new_opacus_codex.train_steps: epoch=3 step=410 loss=1.9429
2026-03-29 15:32:06,916 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=410 eval_loss=1.1677 duration_sec=7.97
2026-03-29 15:32:40,112 [INFO] new_opacus_codex.train_steps: epoch=3 step=415 loss=1.9044
2026-03-29 15:33:14,570 [INFO] new_opacus_codex.train_steps: epoch=3 step=420 loss=1.8619
2026-03-29 15:33:22,582 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=420 eval_loss=1.1691 duration_sec=7.97
2026-03-29 15:33:57,570 [INFO] new_opacus_codex.train_steps: epoch=3 step=425 loss=1.8899
2026-03-29 15:34:31,143 [INFO] new_opacus_codex.train_steps: epoch=3 step=430 loss=1.9005
2026-03-29 15:34:39,155 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=430 eval_loss=1.1705 duration_sec=7.97
2026-03-29 15:35:13,881 [INFO] new_opacus_codex.train_steps: epoch=3 step=435 loss=1.8550
2026-03-29 15:35:46,710 [INFO] new_opacus_codex.train_steps: epoch=3 step=440 loss=1.6927
2026-03-29 15:35:54,822 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=440 eval_loss=1.1716 duration_sec=8.09
2026-03-29 15:36:28,823 [INFO] new_opacus_codex.train_steps: epoch=3 step=445 loss=1.7674
2026-03-29 15:37:02,215 [INFO] new_opacus_codex.train_steps: epoch=3 step=450 loss=1.9073
2026-03-29 15:37:10,236 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=450 eval_loss=1.1727 duration_sec=7.97
2026-03-29 15:37:43,851 [INFO] new_opacus_codex.train_steps: epoch=3 step=455 loss=2.0746
2026-03-29 15:38:17,555 [INFO] new_opacus_codex.train_steps: epoch=3 step=460 loss=1.9686
2026-03-29 15:38:25,614 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=460 eval_loss=1.1737 duration_sec=8.02
2026-03-29 15:38:59,080 [INFO] new_opacus_codex.train_steps: epoch=3 step=465 loss=1.8463
2026-03-29 15:39:33,500 [INFO] new_opacus_codex.train_steps: epoch=3 step=470 loss=1.9412
2026-03-29 15:39:41,511 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=470 eval_loss=1.1746 duration_sec=7.99
2026-03-29 15:40:14,188 [INFO] new_opacus_codex.train_steps: epoch=3 step=475 loss=1.9543
2026-03-29 15:40:48,075 [INFO] new_opacus_codex.train_steps: epoch=3 step=480 loss=1.9504
2026-03-29 15:40:56,109 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=480 eval_loss=1.1755 duration_sec=7.98
2026-03-29 15:41:29,504 [INFO] new_opacus_codex.train_steps: epoch=3 step=485 loss=1.8114
2026-03-29 15:42:02,786 [INFO] new_opacus_codex.train_steps: epoch=3 step=490 loss=1.8265
2026-03-29 15:42:10,802 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=490 eval_loss=1.1764 duration_sec=7.99
2026-03-29 15:42:44,776 [INFO] new_opacus_codex.train_steps: epoch=3 step=495 loss=2.0872
2026-03-29 15:43:18,693 [INFO] new_opacus_codex.train_steps: epoch=3 step=500 loss=2.1572
2026-03-29 15:43:26,747 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=500 eval_loss=1.1772 duration_sec=8.04
2026-03-29 15:44:01,024 [INFO] new_opacus_codex.train_steps: epoch=3 step=505 loss=1.9968
2026-03-29 15:44:34,324 [INFO] new_opacus_codex.train_steps: epoch=3 step=510 loss=1.9690
2026-03-29 15:44:42,359 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=510 eval_loss=1.1778 duration_sec=8.00
2026-03-29 15:45:16,283 [INFO] new_opacus_codex.train_steps: epoch=3 step=515 loss=1.8516
2026-03-29 15:45:50,152 [INFO] new_opacus_codex.train_steps: epoch=3 step=520 loss=1.8793
2026-03-29 15:45:58,187 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=520 eval_loss=1.1783 duration_sec=8.02
2026-03-29 15:46:31,211 [INFO] new_opacus_codex.train_steps: epoch=3 step=525 loss=1.8633
2026-03-29 15:47:06,197 [INFO] new_opacus_codex.train_steps: epoch=3 step=530 loss=1.7285
2026-03-29 15:47:14,228 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=530 eval_loss=1.1790 duration_sec=8.01
2026-03-29 15:47:47,734 [INFO] new_opacus_codex.train_steps: epoch=3 step=535 loss=2.0342
2026-03-29 15:48:21,774 [INFO] new_opacus_codex.train_steps: epoch=3 step=540 loss=2.0236
2026-03-29 15:48:29,894 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=540 eval_loss=1.1796 duration_sec=8.05
2026-03-29 15:49:03,946 [INFO] new_opacus_codex.train_steps: epoch=3 step=545 loss=1.9373
2026-03-29 15:49:38,642 [INFO] new_opacus_codex.train_steps: epoch=3 step=550 loss=1.9613
2026-03-29 15:49:46,685 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=3 step=550 eval_loss=1.1801 duration_sec=8.01
2026-03-29 15:50:36,795 [INFO] new_opacus_codex.train_steps: epoch=4 step=555 loss=1.6932
2026-03-29 15:51:11,063 [INFO] new_opacus_codex.train_steps: epoch=4 step=560 loss=1.7306
2026-03-29 15:51:19,157 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=4 step=560 eval_loss=1.1807 duration_sec=8.07
2026-03-29 15:51:52,471 [INFO] new_opacus_codex.train_steps: epoch=4 step=565 loss=1.8125
2026-03-29 15:52:27,558 [INFO] new_opacus_codex.train_steps: epoch=4 step=570 loss=1.9290
2026-03-29 15:52:35,613 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=4 step=570 eval_loss=1.1812 duration_sec=8.03
2026-03-29 15:53:10,103 [INFO] new_opacus_codex.train_steps: epoch=4 step=575 loss=1.9205
2026-03-29 15:53:44,768 [INFO] new_opacus_codex.train_steps: epoch=4 step=580 loss=1.8356
2026-03-29 15:53:52,914 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=4 step=580 eval_loss=1.1816 duration_sec=8.11
2026-03-29 15:54:28,040 [INFO] new_opacus_codex.train_steps: epoch=4 step=585 loss=1.9324
2026-03-29 15:55:01,132 [INFO] new_opacus_codex.train_steps: epoch=4 step=590 loss=2.0742
2026-03-29 15:55:09,191 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=4 step=590 eval_loss=1.1819 duration_sec=8.04
2026-03-29 15:55:43,364 [INFO] new_opacus_codex.train_steps: epoch=4 step=595 loss=2.0244
2026-03-29 15:56:18,690 [INFO] new_opacus_codex.train_steps: epoch=4 step=600 loss=1.8508
2026-03-29 15:56:26,743 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=4 step=600 eval_loss=1.1822 duration_sec=8.03
2026-03-29 15:57:00,115 [INFO] new_opacus_codex.train_steps: epoch=4 step=605 loss=1.9173
2026-03-29 15:57:34,142 [INFO] new_opacus_codex.train_steps: epoch=4 step=610 loss=1.9976
2026-03-29 15:57:42,142 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=4 step=610 eval_loss=1.1825 duration_sec=7.98
2026-03-29 15:58:16,160 [INFO] new_opacus_codex.train_steps: epoch=4 step=615 loss=1.9604
2026-03-29 15:58:49,797 [INFO] new_opacus_codex.train_steps: epoch=4 step=620 loss=1.9538
2026-03-29 15:58:57,782 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=4 step=620 eval_loss=1.1827 duration_sec=7.92
2026-03-29 15:59:32,408 [INFO] new_opacus_codex.train_steps: epoch=4 step=625 loss=1.9968
2026-03-29 16:00:06,800 [INFO] new_opacus_codex.train_steps: epoch=4 step=630 loss=2.1502
2026-03-29 16:00:14,793 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=4 step=630 eval_loss=1.1829 duration_sec=7.98
2026-03-29 16:00:50,841 [INFO] new_opacus_codex.train_steps: epoch=4 step=635 loss=2.0891
2026-03-29 16:01:24,059 [INFO] new_opacus_codex.train_steps: epoch=4 step=640 loss=1.9672
2026-03-29 16:01:32,127 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=4 step=640 eval_loss=1.1829 duration_sec=8.01
2026-03-29 16:02:06,661 [INFO] new_opacus_codex.train_steps: epoch=4 step=645 loss=1.9396
2026-03-29 16:02:41,943 [INFO] new_opacus_codex.train_steps: epoch=4 step=650 loss=1.8636
2026-03-29 16:02:49,998 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=4 step=650 eval_loss=1.1829 duration_sec=8.03
2026-03-29 16:03:22,927 [INFO] new_opacus_codex.train_steps: epoch=4 step=655 loss=1.8956
2026-03-29 16:03:57,852 [INFO] new_opacus_codex.train_steps: epoch=4 step=660 loss=1.8366
2026-03-29 16:04:05,886 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=4 step=660 eval_loss=1.1829 duration_sec=7.99
2026-03-29 16:04:39,355 [INFO] new_opacus_codex.train_steps: epoch=4 step=665 loss=1.8729
2026-03-29 16:05:13,042 [INFO] new_opacus_codex.train_steps: epoch=4 step=670 loss=2.0241
2026-03-29 16:05:21,053 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=4 step=670 eval_loss=1.1830 duration_sec=7.97
2026-03-29 16:05:56,954 [INFO] new_opacus_codex.train_steps: epoch=4 step=675 loss=1.9730
2026-03-29 16:06:30,701 [INFO] new_opacus_codex.train_steps: epoch=4 step=680 loss=1.8117
2026-03-29 16:06:38,717 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=4 step=680 eval_loss=1.1829 duration_sec=8.00
2026-03-29 16:07:11,997 [INFO] new_opacus_codex.train_steps: epoch=4 step=685 loss=1.7015
2026-03-29 16:07:47,745 [INFO] new_opacus_codex.train_steps: epoch=4 step=690 loss=1.8039
2026-03-29 16:07:55,770 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=4 step=690 eval_loss=1.1830 duration_sec=7.97
2026-03-29 16:08:30,201 [INFO] new_opacus_codex.train_steps: epoch=4 step=695 loss=1.9623
2026-03-29 16:09:05,156 [INFO] new_opacus_codex.train_steps: epoch=4 step=700 loss=1.9227
2026-03-29 16:09:13,246 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=4 step=700 eval_loss=1.1830 duration_sec=8.06
2026-03-29 16:09:47,067 [INFO] new_opacus_codex.train_steps: epoch=4 step=705 loss=1.8109
2026-03-29 16:10:21,298 [INFO] new_opacus_codex.train_steps: epoch=4 step=710 loss=1.9834
2026-03-29 16:10:29,331 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=4 step=710 eval_loss=1.1830 duration_sec=7.97
2026-03-29 16:11:02,953 [INFO] new_opacus_codex.train_steps: epoch=4 step=715 loss=1.9458
2026-03-29 16:11:38,400 [INFO] new_opacus_codex.train_steps: epoch=4 step=720 loss=1.9122
2026-03-29 16:11:46,439 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=4 step=720 eval_loss=1.1831 duration_sec=8.00
2026-03-29 16:12:21,300 [INFO] new_opacus_codex.train_steps: epoch=4 step=725 loss=1.9665
2026-03-29 16:12:56,873 [INFO] new_opacus_codex.train_steps: epoch=4 step=730 loss=1.9190
2026-03-29 16:13:04,909 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=4 step=730 eval_loss=1.1831 duration_sec=7.98
2026-03-29 16:13:40,215 [INFO] new_opacus_codex.train_steps: epoch=4 step=735 loss=1.9355
2026-03-29 16:14:31,359 [INFO] new_opacus_codex.train_steps: epoch=5 step=740 loss=1.9797
2026-03-29 16:14:39,428 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=5 step=740 eval_loss=1.1833 duration_sec=8.05
2026-03-29 16:15:13,298 [INFO] new_opacus_codex.train_steps: epoch=5 step=745 loss=2.0497
2026-03-29 16:15:48,230 [INFO] new_opacus_codex.train_steps: epoch=5 step=750 loss=1.8886
2026-03-29 16:15:56,277 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=5 step=750 eval_loss=1.1833 duration_sec=8.00
2026-03-29 16:16:31,337 [INFO] new_opacus_codex.train_steps: epoch=5 step=755 loss=1.7880
2026-03-29 16:17:06,579 [INFO] new_opacus_codex.train_steps: epoch=5 step=760 loss=1.9316
2026-03-29 16:17:14,589 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=5 step=760 eval_loss=1.1834 duration_sec=7.99
2026-03-29 16:17:49,119 [INFO] new_opacus_codex.train_steps: epoch=5 step=765 loss=1.9121
2026-03-29 16:18:22,475 [INFO] new_opacus_codex.train_steps: epoch=5 step=770 loss=1.7984
2026-03-29 16:18:30,499 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=5 step=770 eval_loss=1.1834 duration_sec=8.00
2026-03-29 16:19:04,959 [INFO] new_opacus_codex.train_steps: epoch=5 step=775 loss=1.9144
2026-03-29 16:19:39,741 [INFO] new_opacus_codex.train_steps: epoch=5 step=780 loss=2.0859
2026-03-29 16:19:47,791 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=5 step=780 eval_loss=1.1834 duration_sec=8.03
2026-03-29 16:20:22,371 [INFO] new_opacus_codex.train_steps: epoch=5 step=785 loss=1.9557
2026-03-29 16:20:56,913 [INFO] new_opacus_codex.train_steps: epoch=5 step=790 loss=1.8655
2026-03-29 16:21:04,934 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=5 step=790 eval_loss=1.1834 duration_sec=8.00
2026-03-29 16:21:39,336 [INFO] new_opacus_codex.train_steps: epoch=5 step=795 loss=1.9166
2026-03-29 16:22:12,306 [INFO] new_opacus_codex.train_steps: epoch=5 step=800 loss=2.0511
2026-03-29 16:22:20,336 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=5 step=800 eval_loss=1.1833 duration_sec=7.97
2026-03-29 16:22:54,177 [INFO] new_opacus_codex.train_steps: epoch=5 step=805 loss=2.0982
2026-03-29 16:23:28,617 [INFO] new_opacus_codex.train_steps: epoch=5 step=810 loss=1.9265
2026-03-29 16:23:36,696 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=5 step=810 eval_loss=1.1833 duration_sec=8.06
2026-03-29 16:24:10,582 [INFO] new_opacus_codex.train_steps: epoch=5 step=815 loss=1.7885
2026-03-29 16:24:45,585 [INFO] new_opacus_codex.train_steps: epoch=5 step=820 loss=1.7281
2026-03-29 16:24:53,630 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=5 step=820 eval_loss=1.1833 duration_sec=8.03
2026-03-29 16:25:27,022 [INFO] new_opacus_codex.train_steps: epoch=5 step=825 loss=1.7224
2026-03-29 16:26:00,874 [INFO] new_opacus_codex.train_steps: epoch=5 step=830 loss=1.7060
2026-03-29 16:26:08,928 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=5 step=830 eval_loss=1.1832 duration_sec=8.03
2026-03-29 16:26:44,988 [INFO] new_opacus_codex.train_steps: epoch=5 step=835 loss=1.6241
2026-03-29 16:27:18,165 [INFO] new_opacus_codex.train_steps: epoch=5 step=840 loss=1.7794
2026-03-29 16:27:26,212 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=5 step=840 eval_loss=1.1833 duration_sec=8.02
2026-03-29 16:27:59,742 [INFO] new_opacus_codex.train_steps: epoch=5 step=845 loss=1.8294
2026-03-29 16:28:32,968 [INFO] new_opacus_codex.train_steps: epoch=5 step=850 loss=1.7679
2026-03-29 16:28:41,006 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=5 step=850 eval_loss=1.1832 duration_sec=7.92
2026-03-29 16:29:16,042 [INFO] new_opacus_codex.train_steps: epoch=5 step=855 loss=1.8773
2026-03-29 16:29:50,511 [INFO] new_opacus_codex.train_steps: epoch=5 step=860 loss=1.8138
2026-03-29 16:29:58,556 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=5 step=860 eval_loss=1.1832 duration_sec=8.00
2026-03-29 16:30:32,298 [INFO] new_opacus_codex.train_steps: epoch=5 step=865 loss=1.7132
2026-03-29 16:31:06,127 [INFO] new_opacus_codex.train_steps: epoch=5 step=870 loss=1.7080
2026-03-29 16:31:14,113 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=5 step=870 eval_loss=1.1832 duration_sec=7.95
2026-03-29 16:31:49,491 [INFO] new_opacus_codex.train_steps: epoch=5 step=875 loss=1.8123
2026-03-29 16:32:24,519 [INFO] new_opacus_codex.train_steps: epoch=5 step=880 loss=1.8756
2026-03-29 16:32:32,571 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=5 step=880 eval_loss=1.1832 duration_sec=8.03
2026-03-29 16:33:07,371 [INFO] new_opacus_codex.train_steps: epoch=5 step=885 loss=1.8807
2026-03-29 16:33:41,237 [INFO] new_opacus_codex.train_steps: epoch=5 step=890 loss=1.7793
2026-03-29 16:33:49,264 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=5 step=890 eval_loss=1.1831 duration_sec=8.01
2026-03-29 16:34:25,025 [INFO] new_opacus_codex.train_steps: epoch=5 step=895 loss=1.7540
2026-03-29 16:35:00,209 [INFO] new_opacus_codex.train_steps: epoch=5 step=900 loss=1.8691
2026-03-29 16:35:08,235 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=5 step=900 eval_loss=1.1831 duration_sec=8.02
2026-03-29 16:35:42,551 [INFO] new_opacus_codex.train_steps: epoch=5 step=905 loss=2.0625
2026-03-29 16:36:17,590 [INFO] new_opacus_codex.train_steps: epoch=5 step=910 loss=2.0510
2026-03-29 16:36:25,648 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=5 step=910 eval_loss=1.1832 duration_sec=8.03
2026-03-29 16:37:00,874 [INFO] new_opacus_codex.train_steps: epoch=5 step=915 loss=1.8987
2026-03-29 16:37:29,685 [INFO] new_opacus_codex.train_steps: epoch=5 step=920 loss=2.1796
2026-03-29 16:37:37,789 [INFO] new_opacus_codex.train_steps: eval event=eval_step epoch=5 step=920 eval_loss=1.1832 duration_sec=8.06