| [2026-05-24 00:08:54] CUDA_VISIBLE_DEVICES: 0 |
| [2026-05-24 00:08:54] Number of processes: 1 |
| [2026-05-24 00:08:54] Mixed precision: bf16 |
| [2026-05-24 00:08:54] ============================================================ |
| [2026-05-24 00:08:54] Routing Evolution Experiment | N=4.0 |
| [2026-05-24 00:08:54] ============================================================ |
| [2026-05-24 00:08:54] Config: |
| model: |
| config_path: /workspace/byte-llms-code/hnet_project/configs/hnet_2stage_XL_code.json |
| checkpoint_path: /workspace/byte-llms-code/hnet_project/checkpoints/hnet_2stage_XL_code.pt |
| training: |
| epochs: 3 |
| max_steps: null |
| batch_size: 8 |
| eval_batch_size: 24 |
| gradient_accumulation_steps: 4 |
| lr: 0.0001 |
| weight_decay: 0.1 |
| betas: |
| - 0.9 |
| - 0.95 |
| eps: 1.0e-08 |
| lr_scheduler: wsd |
| warmup_ratio: 0.1 |
| decay_ratio: 0.2 |
| warmup_steps: 100 |
| min_lr_ratio: 0.1 |
| lr_multiplier: |
| - 2.0 |
| - 1.5 |
| - 1.0 |
| load_balancing_weight: 0.5 |
| load_balancing_N: 4.0 |
| max_grad_norm: 1.0 |
| use_amp: true |
| resume: false |
| resume_checkpoint: null |
| warmup_model: true |
| data: |
| path: /workspace/byte-llms-code/code_completion_exp/datasets/data_V4_full |
| max_context_len: 4096 |
| max_target_len: 256 |
| num_workers: 0 |
| pin_memory: true |
| max_train_samples: 150000 |
| max_val_samples: null |
| logging: |
| log_interval: 10 |
| save_interval: 3000 |
| eval_interval: 1000 |
| save_every_epoch: false |
| model_only_checkpoints: true |
| tracking: |
| enabled: true |
| backend: wandb |
| project: routing-evolution |
| run_name: routing_N4.0 |
| entity: null |
| base_url: https://wandb.platun0v.ru |
| local_dir: outputs/2026-05-24/N_4.0 |
| paths: |
| output_dir: outputs/2026-05-24/N_4.0 |
| seed: 42 |
| device: cuda |
|
|
| [2026-05-24 00:08:57] Loading model... |
| [2026-05-24 00:09:02] Loaded pretrained: /workspace/byte-llms-code/hnet_project/checkpoints/hnet_2stage_XL_code.pt |
| [2026-05-24 00:09:02] Applied LR multipliers: [2.0, 1.5, 1.0] |
| [2026-05-24 00:09:02] Warming up model... |
| [2026-05-24 00:09:50] Total params: 1,654,090,112 |
| [2026-05-24 00:09:50] Trainable params: 1,654,090,112 |
| [2026-05-24 00:09:50] Creating dataloaders... |
| [2026-05-24 00:09:50] Train dataset size: 150000 (max_train_samples=150000) | Epochs: 3 |
| [2026-05-24 00:09:50] Max steps: 14062, Steps per epoch: 18750 |
| [2026-05-24 00:09:50] Starting training... |
| [2026-05-24 00:09:50] |
| ============================================================ |
| [2026-05-24 00:09:50] EPOCH 1/3 (step 0) |
| [2026-05-24 00:09:50] ============================================================ |
| [2026-05-24 00:10:29] Epoch 1 | Step 10 | Loss: 1.1969 | LM: 0.6792 | LB: 1.1489 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.354 | HR1: 0.471/SR1: 0.448 | LR: 1.06e-05 |
| [2026-05-24 00:10:43] Epoch 1 | Step 20 | Loss: 1.1923 | LM: 0.6309 | LB: 1.1518 | CL0: 2.8 | CL1: 2.1 | HR0: 0.355/SR0: 0.354 | HR1: 0.474/SR1: 0.451 | LR: 1.13e-05 |
| [2026-05-24 00:10:55] Epoch 1 | Step 30 | Loss: 1.1797 | LM: 0.6220 | LB: 1.1493 | CL0: 2.9 | CL1: 2.1 | HR0: 0.350/SR0: 0.350 | HR1: 0.474/SR1: 0.451 | LR: 1.19e-05 |
| [2026-05-24 00:11:08] Epoch 1 | Step 40 | Loss: 1.1722 | LM: 0.6122 | LB: 1.1531 | CL0: 2.9 | CL1: 2.1 | HR0: 0.352/SR0: 0.351 | HR1: 0.476/SR1: 0.453 | LR: 1.26e-05 |
| [2026-05-24 00:11:21] Epoch 1 | Step 50 | Loss: 1.1547 | LM: 0.5952 | LB: 1.1511 | CL0: 2.9 | CL1: 2.1 | HR0: 0.352/SR0: 0.351 | HR1: 0.474/SR1: 0.451 | LR: 1.32e-05 |
| [2026-05-24 00:11:33] Epoch 1 | Step 60 | Loss: 1.1328 | LM: 0.5726 | LB: 1.1532 | CL0: 2.9 | CL1: 2.1 | HR0: 0.352/SR0: 0.351 | HR1: 0.476/SR1: 0.453 | LR: 1.38e-05 |
| [2026-05-24 00:11:45] Epoch 1 | Step 70 | Loss: 1.1206 | LM: 0.5536 | LB: 1.1516 | CL0: 2.9 | CL1: 2.1 | HR0: 0.352/SR0: 0.351 | HR1: 0.475/SR1: 0.452 | LR: 1.45e-05 |
| [2026-05-24 00:11:57] Epoch 1 | Step 80 | Loss: 1.1030 | LM: 0.5295 | LB: 1.1519 | CL0: 2.8 | CL1: 2.1 | HR0: 0.353/SR0: 0.352 | HR1: 0.474/SR1: 0.452 | LR: 1.51e-05 |
| [2026-05-24 00:12:09] Epoch 1 | Step 90 | Loss: 1.0942 | LM: 0.5218 | LB: 1.1525 | CL0: 2.8 | CL1: 2.1 | HR0: 0.353/SR0: 0.352 | HR1: 0.475/SR1: 0.452 | LR: 1.58e-05 |
| [2026-05-24 00:12:22] Epoch 1 | Step 100 | Loss: 1.0804 | LM: 0.5090 | LB: 1.1528 | CL0: 2.8 | CL1: 2.1 | HR0: 0.353/SR0: 0.352 | HR1: 0.476/SR1: 0.453 | LR: 1.64e-05 |
| [2026-05-24 00:12:34] Epoch 1 | Step 110 | Loss: 1.0710 | LM: 0.4944 | LB: 1.1528 | CL0: 2.8 | CL1: 2.1 | HR0: 0.354/SR0: 0.353 | HR1: 0.475/SR1: 0.452 | LR: 1.70e-05 |
| [2026-05-24 00:12:46] Epoch 1 | Step 120 | Loss: 1.0616 | LM: 0.4876 | LB: 1.1532 | CL0: 2.8 | CL1: 2.1 | HR0: 0.354/SR0: 0.353 | HR1: 0.475/SR1: 0.453 | LR: 1.77e-05 |
| [2026-05-24 00:12:58] Epoch 1 | Step 130 | Loss: 1.0499 | LM: 0.4755 | LB: 1.1518 | CL0: 2.8 | CL1: 2.1 | HR0: 0.354/SR0: 0.353 | HR1: 0.474/SR1: 0.451 | LR: 1.83e-05 |
| [2026-05-24 00:13:09] Epoch 1 | Step 140 | Loss: 1.0409 | LM: 0.4617 | LB: 1.1512 | CL0: 2.8 | CL1: 2.1 | HR0: 0.355/SR0: 0.354 | HR1: 0.473/SR1: 0.451 | LR: 1.90e-05 |
| [2026-05-24 00:13:21] Epoch 1 | Step 150 | Loss: 1.0319 | LM: 0.4536 | LB: 1.1509 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.354 | HR1: 0.472/SR1: 0.450 | LR: 1.96e-05 |
| [2026-05-24 00:13:33] Epoch 1 | Step 160 | Loss: 1.0261 | LM: 0.4517 | LB: 1.1496 | CL0: 2.8 | CL1: 2.1 | HR0: 0.355/SR0: 0.354 | HR1: 0.471/SR1: 0.449 | LR: 2.02e-05 |
| [2026-05-24 00:13:45] Epoch 1 | Step 170 | Loss: 1.0191 | LM: 0.4454 | LB: 1.1492 | CL0: 2.8 | CL1: 2.1 | HR0: 0.355/SR0: 0.354 | HR1: 0.471/SR1: 0.449 | LR: 2.09e-05 |
| [2026-05-24 00:13:56] Epoch 1 | Step 180 | Loss: 1.0109 | LM: 0.4392 | LB: 1.1474 | CL0: 2.8 | CL1: 2.1 | HR0: 0.355/SR0: 0.354 | HR1: 0.469/SR1: 0.447 | LR: 2.15e-05 |
| [2026-05-24 00:14:08] Epoch 1 | Step 190 | Loss: 1.0056 | LM: 0.4341 | LB: 1.1472 | CL0: 2.8 | CL1: 2.1 | HR0: 0.355/SR0: 0.354 | HR1: 0.469/SR1: 0.447 | LR: 2.22e-05 |
| [2026-05-24 00:14:19] Epoch 1 | Step 200 | Loss: 1.0013 | LM: 0.4308 | LB: 1.1461 | CL0: 2.8 | CL1: 2.1 | HR0: 0.355/SR0: 0.353 | HR1: 0.468/SR1: 0.446 | LR: 2.28e-05 |
| [2026-05-24 00:14:30] Epoch 1 | Step 210 | Loss: 0.9961 | LM: 0.4242 | LB: 1.1454 | CL0: 2.8 | CL1: 2.1 | HR0: 0.354/SR0: 0.353 | HR1: 0.468/SR1: 0.446 | LR: 2.34e-05 |
| [2026-05-24 00:14:41] Epoch 1 | Step 220 | Loss: 0.9926 | LM: 0.4225 | LB: 1.1446 | CL0: 2.8 | CL1: 2.1 | HR0: 0.355/SR0: 0.353 | HR1: 0.467/SR1: 0.445 | LR: 2.41e-05 |
| [2026-05-24 00:14:53] Epoch 1 | Step 230 | Loss: 0.9870 | LM: 0.4183 | LB: 1.1438 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.354 | HR1: 0.466/SR1: 0.444 | LR: 2.47e-05 |
| [2026-05-24 00:15:05] Epoch 1 | Step 240 | Loss: 0.9837 | LM: 0.4174 | LB: 1.1430 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.465/SR1: 0.444 | LR: 2.54e-05 |
| [2026-05-24 00:15:17] Epoch 1 | Step 250 | Loss: 0.9788 | LM: 0.4136 | LB: 1.1421 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.464/SR1: 0.443 | LR: 2.60e-05 |
| [2026-05-24 00:15:29] Epoch 1 | Step 260 | Loss: 0.9750 | LM: 0.4092 | LB: 1.1412 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.353 | HR1: 0.464/SR1: 0.442 | LR: 2.66e-05 |
| [2026-05-24 00:15:41] Epoch 1 | Step 270 | Loss: 0.9717 | LM: 0.4063 | LB: 1.1403 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.353 | HR1: 0.463/SR1: 0.442 | LR: 2.73e-05 |
| [2026-05-24 00:15:54] Epoch 1 | Step 280 | Loss: 0.9680 | LM: 0.4014 | LB: 1.1395 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.462/SR1: 0.441 | LR: 2.79e-05 |
| [2026-05-24 00:16:07] Epoch 1 | Step 290 | Loss: 0.9656 | LM: 0.4000 | LB: 1.1386 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.461/SR1: 0.439 | LR: 2.86e-05 |
| [2026-05-24 00:16:20] Epoch 1 | Step 300 | Loss: 0.9638 | LM: 0.3991 | LB: 1.1377 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.460/SR1: 0.439 | LR: 2.92e-05 |
| [2026-05-24 00:16:32] Epoch 1 | Step 310 | Loss: 0.9607 | LM: 0.3962 | LB: 1.1367 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.353 | HR1: 0.459/SR1: 0.438 | LR: 2.98e-05 |
| [2026-05-24 00:16:44] Epoch 1 | Step 320 | Loss: 0.9584 | LM: 0.3945 | LB: 1.1360 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.459/SR1: 0.437 | LR: 3.05e-05 |
| [2026-05-24 00:16:55] Epoch 1 | Step 330 | Loss: 0.9564 | LM: 0.3940 | LB: 1.1353 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.458/SR1: 0.436 | LR: 3.11e-05 |
| [2026-05-24 00:17:07] Epoch 1 | Step 340 | Loss: 0.9530 | LM: 0.3906 | LB: 1.1346 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.458/SR1: 0.436 | LR: 3.18e-05 |
| [2026-05-24 00:17:18] Epoch 1 | Step 350 | Loss: 0.9508 | LM: 0.3902 | LB: 1.1336 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.457/SR1: 0.435 | LR: 3.24e-05 |
| [2026-05-24 00:17:31] Epoch 1 | Step 360 | Loss: 0.9490 | LM: 0.3885 | LB: 1.1328 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.456/SR1: 0.434 | LR: 3.30e-05 |
| [2026-05-24 00:17:43] Epoch 1 | Step 370 | Loss: 0.9468 | LM: 0.3863 | LB: 1.1320 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.455/SR1: 0.433 | LR: 3.37e-05 |
| [2026-05-24 00:17:55] Epoch 1 | Step 380 | Loss: 0.9442 | LM: 0.3838 | LB: 1.1310 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.454/SR1: 0.432 | LR: 3.43e-05 |
| [2026-05-24 00:18:07] Epoch 1 | Step 390 | Loss: 0.9417 | LM: 0.3810 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.453/SR1: 0.431 | LR: 3.50e-05 |
| [2026-05-24 00:18:20] Epoch 1 | Step 400 | Loss: 0.9402 | LM: 0.3802 | LB: 1.1291 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.452/SR1: 0.430 | LR: 3.56e-05 |
| [2026-05-24 00:18:31] Epoch 1 | Step 410 | Loss: 0.9388 | LM: 0.3801 | LB: 1.1283 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.451/SR1: 0.429 | LR: 3.62e-05 |
| [2026-05-24 00:18:44] Epoch 1 | Step 420 | Loss: 0.9376 | LM: 0.3789 | LB: 1.1277 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.450/SR1: 0.428 | LR: 3.69e-05 |
| [2026-05-24 00:18:56] Epoch 1 | Step 430 | Loss: 0.9367 | LM: 0.3793 | LB: 1.1269 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.450/SR1: 0.427 | LR: 3.75e-05 |
| [2026-05-24 00:19:08] Epoch 1 | Step 440 | Loss: 0.9346 | LM: 0.3765 | LB: 1.1259 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.449/SR1: 0.426 | LR: 3.82e-05 |
| [2026-05-24 00:19:21] Epoch 1 | Step 450 | Loss: 0.9325 | LM: 0.3751 | LB: 1.1252 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.448/SR1: 0.425 | LR: 3.88e-05 |
| [2026-05-24 00:19:33] Epoch 1 | Step 460 | Loss: 0.9311 | LM: 0.3737 | LB: 1.1244 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.447/SR1: 0.424 | LR: 3.94e-05 |
| [2026-05-24 00:19:46] Epoch 1 | Step 470 | Loss: 0.9296 | LM: 0.3723 | LB: 1.1235 | CL0: 2.8 | CL1: 2.3 | HR0: 0.355/SR0: 0.353 | HR1: 0.446/SR1: 0.423 | LR: 4.01e-05 |
| [2026-05-24 00:19:58] Epoch 1 | Step 480 | Loss: 0.9274 | LM: 0.3700 | LB: 1.1227 | CL0: 2.8 | CL1: 2.3 | HR0: 0.355/SR0: 0.353 | HR1: 0.445/SR1: 0.422 | LR: 4.07e-05 |
| [2026-05-24 00:20:11] Epoch 1 | Step 490 | Loss: 0.9251 | LM: 0.3695 | LB: 1.1218 | CL0: 2.8 | CL1: 2.3 | HR0: 0.355/SR0: 0.353 | HR1: 0.444/SR1: 0.421 | LR: 4.14e-05 |
| [2026-05-24 00:20:23] Epoch 1 | Step 500 | Loss: 0.9241 | LM: 0.3684 | LB: 1.1211 | CL0: 2.8 | CL1: 2.3 | HR0: 0.356/SR0: 0.354 | HR1: 0.443/SR1: 0.420 | LR: 4.20e-05 |
| [2026-05-24 00:20:35] Epoch 1 | Step 510 | Loss: 0.9229 | LM: 0.3673 | LB: 1.1204 | CL0: 2.8 | CL1: 2.3 | HR0: 0.356/SR0: 0.354 | HR1: 0.443/SR1: 0.419 | LR: 4.26e-05 |
| [2026-05-24 00:20:48] Epoch 1 | Step 520 | Loss: 0.9213 | LM: 0.3652 | LB: 1.1197 | CL0: 2.8 | CL1: 2.3 | HR0: 0.356/SR0: 0.354 | HR1: 0.442/SR1: 0.418 | LR: 4.33e-05 |
| [2026-05-24 00:21:00] Epoch 1 | Step 530 | Loss: 0.9197 | LM: 0.3640 | LB: 1.1186 | CL0: 2.8 | CL1: 2.3 | HR0: 0.356/SR0: 0.354 | HR1: 0.441/SR1: 0.417 | LR: 4.39e-05 |
| [2026-05-24 00:21:12] Epoch 1 | Step 540 | Loss: 0.9173 | LM: 0.3622 | LB: 1.1176 | CL0: 2.8 | CL1: 2.3 | HR0: 0.356/SR0: 0.354 | HR1: 0.439/SR1: 0.416 | LR: 4.46e-05 |
| [2026-05-24 00:21:25] Epoch 1 | Step 550 | Loss: 0.9154 | LM: 0.3603 | LB: 1.1165 | CL0: 2.8 | CL1: 2.3 | HR0: 0.356/SR0: 0.354 | HR1: 0.438/SR1: 0.414 | LR: 4.52e-05 |
| [2026-05-24 00:21:37] Epoch 1 | Step 560 | Loss: 0.9137 | LM: 0.3587 | LB: 1.1155 | CL0: 2.8 | CL1: 2.3 | HR0: 0.356/SR0: 0.353 | HR1: 0.437/SR1: 0.413 | LR: 4.58e-05 |
| [2026-05-24 00:21:49] Epoch 1 | Step 570 | Loss: 0.9128 | LM: 0.3578 | LB: 1.1148 | CL0: 2.8 | CL1: 2.3 | HR0: 0.356/SR0: 0.354 | HR1: 0.436/SR1: 0.412 | LR: 4.65e-05 |
| [2026-05-24 00:22:02] Epoch 1 | Step 580 | Loss: 0.9119 | LM: 0.3582 | LB: 1.1140 | CL0: 2.8 | CL1: 2.3 | HR0: 0.356/SR0: 0.354 | HR1: 0.436/SR1: 0.411 | LR: 4.71e-05 |
| [2026-05-24 00:22:15] Epoch 1 | Step 590 | Loss: 0.9108 | LM: 0.3567 | LB: 1.1129 | CL0: 2.8 | CL1: 2.3 | HR0: 0.356/SR0: 0.353 | HR1: 0.434/SR1: 0.410 | LR: 4.78e-05 |
| [2026-05-24 00:22:27] Epoch 1 | Step 600 | Loss: 0.9100 | LM: 0.3567 | LB: 1.1119 | CL0: 2.8 | CL1: 2.3 | HR0: 0.355/SR0: 0.353 | HR1: 0.433/SR1: 0.409 | LR: 4.84e-05 |
| [2026-05-24 00:22:39] Epoch 1 | Step 610 | Loss: 0.9084 | LM: 0.3554 | LB: 1.1110 | CL0: 2.8 | CL1: 2.3 | HR0: 0.356/SR0: 0.353 | HR1: 0.432/SR1: 0.407 | LR: 4.90e-05 |
| [2026-05-24 00:22:51] Epoch 1 | Step 620 | Loss: 0.9069 | LM: 0.3539 | LB: 1.1100 | CL0: 2.8 | CL1: 2.3 | HR0: 0.355/SR0: 0.353 | HR1: 0.431/SR1: 0.406 | LR: 4.97e-05 |
| [2026-05-24 00:23:03] Epoch 1 | Step 630 | Loss: 0.9053 | LM: 0.3531 | LB: 1.1093 | CL0: 2.8 | CL1: 2.3 | HR0: 0.356/SR0: 0.353 | HR1: 0.430/SR1: 0.405 | LR: 5.03e-05 |
| [2026-05-24 00:23:15] Epoch 1 | Step 640 | Loss: 0.9040 | LM: 0.3528 | LB: 1.1084 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.353 | HR1: 0.429/SR1: 0.404 | LR: 5.10e-05 |
| [2026-05-24 00:23:27] Epoch 1 | Step 650 | Loss: 0.9026 | LM: 0.3514 | LB: 1.1077 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.353 | HR1: 0.428/SR1: 0.402 | LR: 5.16e-05 |
| [2026-05-24 00:23:40] Epoch 1 | Step 660 | Loss: 0.9016 | LM: 0.3514 | LB: 1.1067 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.353 | HR1: 0.427/SR1: 0.401 | LR: 5.22e-05 |
| [2026-05-24 00:23:51] Epoch 1 | Step 670 | Loss: 0.9004 | LM: 0.3508 | LB: 1.1059 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.353 | HR1: 0.425/SR1: 0.400 | LR: 5.29e-05 |
| [2026-05-24 00:24:03] Epoch 1 | Step 680 | Loss: 0.8993 | LM: 0.3507 | LB: 1.1050 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.353 | HR1: 0.424/SR1: 0.399 | LR: 5.35e-05 |
| [2026-05-24 00:24:16] Epoch 1 | Step 690 | Loss: 0.8985 | LM: 0.3497 | LB: 1.1042 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.353 | HR1: 0.423/SR1: 0.398 | LR: 5.42e-05 |
| [2026-05-24 00:24:27] Epoch 1 | Step 700 | Loss: 0.8971 | LM: 0.3483 | LB: 1.1034 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.353 | HR1: 0.422/SR1: 0.396 | LR: 5.48e-05 |
| [2026-05-24 00:24:38] Epoch 1 | Step 710 | Loss: 0.8962 | LM: 0.3478 | LB: 1.1025 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.353 | HR1: 0.421/SR1: 0.395 | LR: 5.54e-05 |
| [2026-05-24 00:24:50] Epoch 1 | Step 720 | Loss: 0.8952 | LM: 0.3471 | LB: 1.1017 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.353 | HR1: 0.420/SR1: 0.394 | LR: 5.61e-05 |
| [2026-05-24 00:25:01] Epoch 1 | Step 730 | Loss: 0.8946 | LM: 0.3470 | LB: 1.1009 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.353 | HR1: 0.419/SR1: 0.393 | LR: 5.67e-05 |
| [2026-05-24 00:25:13] Epoch 1 | Step 740 | Loss: 0.8934 | LM: 0.3458 | LB: 1.1000 | CL0: 2.8 | CL1: 2.4 | HR0: 0.355/SR0: 0.353 | HR1: 0.418/SR1: 0.392 | LR: 5.74e-05 |
| [2026-05-24 00:25:25] Epoch 1 | Step 750 | Loss: 0.8928 | LM: 0.3454 | LB: 1.0991 | CL0: 2.8 | CL1: 2.4 | HR0: 0.355/SR0: 0.353 | HR1: 0.417/SR1: 0.390 | LR: 5.80e-05 |
| [2026-05-24 00:25:37] Epoch 1 | Step 760 | Loss: 0.8921 | LM: 0.3452 | LB: 1.0983 | CL0: 2.8 | CL1: 2.4 | HR0: 0.355/SR0: 0.352 | HR1: 0.416/SR1: 0.389 | LR: 5.86e-05 |
| [2026-05-24 00:25:49] Epoch 1 | Step 770 | Loss: 0.8905 | LM: 0.3440 | LB: 1.0976 | CL0: 2.8 | CL1: 2.4 | HR0: 0.355/SR0: 0.352 | HR1: 0.415/SR1: 0.388 | LR: 5.93e-05 |
| [2026-05-24 00:26:01] Epoch 1 | Step 780 | Loss: 0.8895 | LM: 0.3433 | LB: 1.0967 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.352 | HR1: 0.414/SR1: 0.387 | LR: 5.99e-05 |
| [2026-05-24 00:26:13] Epoch 1 | Step 790 | Loss: 0.8887 | LM: 0.3428 | LB: 1.0960 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.352 | HR1: 0.412/SR1: 0.385 | LR: 6.06e-05 |
| [2026-05-24 00:26:26] Epoch 1 | Step 800 | Loss: 0.8882 | LM: 0.3430 | LB: 1.0952 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.352 | HR1: 0.411/SR1: 0.384 | LR: 6.12e-05 |
| [2026-05-24 00:26:39] Epoch 1 | Step 810 | Loss: 0.8876 | LM: 0.3432 | LB: 1.0946 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.352 | HR1: 0.410/SR1: 0.383 | LR: 6.18e-05 |
| [2026-05-24 00:26:51] Epoch 1 | Step 820 | Loss: 0.8873 | LM: 0.3433 | LB: 1.0939 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.352 | HR1: 0.409/SR1: 0.382 | LR: 6.25e-05 |
| [2026-05-24 00:27:03] Epoch 1 | Step 830 | Loss: 0.8863 | LM: 0.3426 | LB: 1.0932 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.352 | HR1: 0.408/SR1: 0.381 | LR: 6.31e-05 |
| [2026-05-24 00:27:15] Epoch 1 | Step 840 | Loss: 0.8856 | LM: 0.3425 | LB: 1.0924 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.352 | HR1: 0.407/SR1: 0.379 | LR: 6.38e-05 |
| [2026-05-24 00:27:28] Epoch 1 | Step 850 | Loss: 0.8849 | LM: 0.3419 | LB: 1.0917 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.352 | HR1: 0.406/SR1: 0.378 | LR: 6.44e-05 |
| [2026-05-24 00:27:40] Epoch 1 | Step 860 | Loss: 0.8842 | LM: 0.3420 | LB: 1.0910 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.352 | HR1: 0.405/SR1: 0.377 | LR: 6.50e-05 |
| [2026-05-24 00:27:51] Epoch 1 | Step 870 | Loss: 0.8833 | LM: 0.3409 | LB: 1.0904 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.352 | HR1: 0.404/SR1: 0.376 | LR: 6.57e-05 |
| [2026-05-24 00:28:04] Epoch 1 | Step 880 | Loss: 0.8824 | LM: 0.3404 | LB: 1.0896 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.351 | HR1: 0.403/SR1: 0.375 | LR: 6.63e-05 |
| [2026-05-24 00:28:16] Epoch 1 | Step 890 | Loss: 0.8820 | LM: 0.3401 | LB: 1.0889 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.351 | HR1: 0.402/SR1: 0.374 | LR: 6.70e-05 |
| [2026-05-24 00:28:28] Epoch 1 | Step 900 | Loss: 0.8811 | LM: 0.3390 | LB: 1.0883 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.351 | HR1: 0.401/SR1: 0.372 | LR: 6.76e-05 |
| [2026-05-24 00:28:40] Epoch 1 | Step 910 | Loss: 0.8803 | LM: 0.3386 | LB: 1.0877 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.351 | HR1: 0.400/SR1: 0.371 | LR: 6.83e-05 |
| [2026-05-24 00:28:52] Epoch 1 | Step 920 | Loss: 0.8795 | LM: 0.3383 | LB: 1.0871 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.351 | HR1: 0.398/SR1: 0.370 | LR: 6.89e-05 |
| [2026-05-24 00:29:04] Epoch 1 | Step 930 | Loss: 0.8790 | LM: 0.3376 | LB: 1.0865 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.351 | HR1: 0.398/SR1: 0.369 | LR: 6.95e-05 |
| [2026-05-24 00:29:16] Epoch 1 | Step 940 | Loss: 0.8781 | LM: 0.3368 | LB: 1.0859 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.351 | HR1: 0.396/SR1: 0.368 | LR: 7.02e-05 |
| [2026-05-24 00:29:28] Epoch 1 | Step 950 | Loss: 0.8777 | LM: 0.3369 | LB: 1.0853 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.351 | HR1: 0.395/SR1: 0.367 | LR: 7.08e-05 |
| [2026-05-24 00:29:40] Epoch 1 | Step 960 | Loss: 0.8775 | LM: 0.3366 | LB: 1.0847 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.351 | HR1: 0.394/SR1: 0.366 | LR: 7.15e-05 |
| [2026-05-24 00:29:52] Epoch 1 | Step 970 | Loss: 0.8769 | LM: 0.3358 | LB: 1.0841 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.351 | HR1: 0.394/SR1: 0.365 | LR: 7.21e-05 |
| [2026-05-24 00:30:04] Epoch 1 | Step 980 | Loss: 0.8764 | LM: 0.3356 | LB: 1.0836 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.351 | HR1: 0.393/SR1: 0.364 | LR: 7.27e-05 |
| [2026-05-24 00:30:16] Epoch 1 | Step 990 | Loss: 0.8757 | LM: 0.3350 | LB: 1.0830 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.351 | HR1: 0.392/SR1: 0.363 | LR: 7.34e-05 |
| [2026-05-24 00:30:28] Epoch 1 | Step 1000 | Loss: 0.8750 | LM: 0.3352 | LB: 1.0825 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.351 | HR1: 0.391/SR1: 0.362 | LR: 7.40e-05 |
| [2026-05-24 00:30:30] Validation | Batch 10/1463 | Loss: 0.7844 | LM_LOSS: 0.2729 | LB_LOSS: 1.0230 |
| [2026-05-24 00:30:32] Validation | Batch 20/1463 | Loss: 0.7963 | LM_LOSS: 0.2832 | LB_LOSS: 1.0262 |
| [2026-05-24 00:30:35] Validation | Batch 30/1463 | Loss: 0.8021 | LM_LOSS: 0.2887 | LB_LOSS: 1.0269 |
| [2026-05-24 00:30:37] Validation | Batch 40/1463 | Loss: 0.8101 | LM_LOSS: 0.2961 | LB_LOSS: 1.0281 |
| [2026-05-24 00:30:39] Validation | Batch 50/1463 | Loss: 0.8170 | LM_LOSS: 0.3033 | LB_LOSS: 1.0274 |
| [2026-05-24 00:30:42] Validation | Batch 60/1463 | Loss: 0.8160 | LM_LOSS: 0.3025 | LB_LOSS: 1.0272 |
| [2026-05-24 00:30:45] Validation | Batch 70/1463 | Loss: 0.8165 | LM_LOSS: 0.3029 | LB_LOSS: 1.0273 |
| [2026-05-24 00:30:48] Validation | Batch 80/1463 | Loss: 0.8182 | LM_LOSS: 0.3046 | LB_LOSS: 1.0273 |
| [2026-05-24 00:30:50] Validation | Batch 90/1463 | Loss: 0.8178 | LM_LOSS: 0.3042 | LB_LOSS: 1.0272 |
| [2026-05-24 00:30:52] Validation | Batch 100/1463 | Loss: 0.8185 | LM_LOSS: 0.3049 | LB_LOSS: 1.0272 |
| [2026-05-24 00:30:55] Validation | Batch 110/1463 | Loss: 0.8178 | LM_LOSS: 0.3041 | LB_LOSS: 1.0275 |
| [2026-05-24 00:30:56] Validation | Batch 120/1463 | Loss: 0.8194 | LM_LOSS: 0.3057 | LB_LOSS: 1.0276 |
| [2026-05-24 00:30:59] Validation | Batch 130/1463 | Loss: 0.8212 | LM_LOSS: 0.3073 | LB_LOSS: 1.0277 |
| [2026-05-24 00:31:01] Validation | Batch 140/1463 | Loss: 0.8219 | LM_LOSS: 0.3081 | LB_LOSS: 1.0276 |
| [2026-05-24 00:31:04] Validation | Batch 150/1463 | Loss: 0.8200 | LM_LOSS: 0.3061 | LB_LOSS: 1.0277 |
| [2026-05-24 00:31:06] Validation | Batch 160/1463 | Loss: 0.8199 | LM_LOSS: 0.3061 | LB_LOSS: 1.0275 |
| [2026-05-24 00:31:09] Validation | Batch 170/1463 | Loss: 0.8194 | LM_LOSS: 0.3056 | LB_LOSS: 1.0275 |
| [2026-05-24 00:31:11] Validation | Batch 180/1463 | Loss: 0.8201 | LM_LOSS: 0.3064 | LB_LOSS: 1.0275 |
| [2026-05-24 00:31:14] Validation | Batch 190/1463 | Loss: 0.8208 | LM_LOSS: 0.3071 | LB_LOSS: 1.0275 |
| [2026-05-24 00:31:16] Validation | Batch 200/1463 | Loss: 0.8208 | LM_LOSS: 0.3071 | LB_LOSS: 1.0275 |
| [2026-05-24 00:31:18] Validation | Batch 210/1463 | Loss: 0.8214 | LM_LOSS: 0.3076 | LB_LOSS: 1.0275 |
| [2026-05-24 00:31:21] Validation | Batch 220/1463 | Loss: 0.8206 | LM_LOSS: 0.3068 | LB_LOSS: 1.0275 |
| [2026-05-24 00:31:23] Validation | Batch 230/1463 | Loss: 0.8221 | LM_LOSS: 0.3084 | LB_LOSS: 1.0274 |
| [2026-05-24 00:31:26] Validation | Batch 240/1463 | Loss: 0.8235 | LM_LOSS: 0.3098 | LB_LOSS: 1.0274 |
| [2026-05-24 00:31:28] Validation | Batch 250/1463 | Loss: 0.8228 | LM_LOSS: 0.3091 | LB_LOSS: 1.0274 |
| [2026-05-24 00:31:31] Validation | Batch 260/1463 | Loss: 0.8243 | LM_LOSS: 0.3105 | LB_LOSS: 1.0276 |
| [2026-05-24 00:31:33] Validation | Batch 270/1463 | Loss: 0.8229 | LM_LOSS: 0.3091 | LB_LOSS: 1.0276 |
| [2026-05-24 00:31:35] Validation | Batch 280/1463 | Loss: 0.8234 | LM_LOSS: 0.3096 | LB_LOSS: 1.0277 |
| [2026-05-24 00:31:38] Validation | Batch 290/1463 | Loss: 0.8227 | LM_LOSS: 0.3089 | LB_LOSS: 1.0277 |
| [2026-05-24 00:31:40] Validation | Batch 300/1463 | Loss: 0.8227 | LM_LOSS: 0.3088 | LB_LOSS: 1.0278 |
| [2026-05-24 00:31:43] Validation | Batch 310/1463 | Loss: 0.8237 | LM_LOSS: 0.3099 | LB_LOSS: 1.0278 |
| [2026-05-24 00:31:45] Validation | Batch 320/1463 | Loss: 0.8222 | LM_LOSS: 0.3084 | LB_LOSS: 1.0276 |
| [2026-05-24 00:31:47] Validation | Batch 330/1463 | Loss: 0.8222 | LM_LOSS: 0.3084 | LB_LOSS: 1.0275 |
| [2026-05-24 00:31:49] Validation | Batch 340/1463 | Loss: 0.8219 | LM_LOSS: 0.3081 | LB_LOSS: 1.0276 |
| [2026-05-24 00:31:52] Validation | Batch 350/1463 | Loss: 0.8227 | LM_LOSS: 0.3089 | LB_LOSS: 1.0275 |
| [2026-05-24 00:31:54] Validation | Batch 360/1463 | Loss: 0.8223 | LM_LOSS: 0.3085 | LB_LOSS: 1.0276 |
| [2026-05-24 00:31:56] Validation | Batch 370/1463 | Loss: 0.8220 | LM_LOSS: 0.3082 | LB_LOSS: 1.0277 |
| [2026-05-24 00:31:58] Validation | Batch 380/1463 | Loss: 0.8219 | LM_LOSS: 0.3081 | LB_LOSS: 1.0275 |
| [2026-05-24 00:32:01] Validation | Batch 390/1463 | Loss: 0.8226 | LM_LOSS: 0.3088 | LB_LOSS: 1.0276 |
| [2026-05-24 00:32:03] Validation | Batch 400/1463 | Loss: 0.8224 | LM_LOSS: 0.3086 | LB_LOSS: 1.0276 |
| [2026-05-24 00:32:05] Validation | Batch 410/1463 | Loss: 0.8221 | LM_LOSS: 0.3082 | LB_LOSS: 1.0277 |
| [2026-05-24 00:32:08] Validation | Batch 420/1463 | Loss: 0.8221 | LM_LOSS: 0.3082 | LB_LOSS: 1.0277 |
| [2026-05-24 00:32:11] Validation | Batch 430/1463 | Loss: 0.8216 | LM_LOSS: 0.3077 | LB_LOSS: 1.0277 |
| [2026-05-24 00:32:13] Validation | Batch 440/1463 | Loss: 0.8218 | LM_LOSS: 0.3079 | LB_LOSS: 1.0278 |
| [2026-05-24 00:32:15] Validation | Batch 450/1463 | Loss: 0.8216 | LM_LOSS: 0.3077 | LB_LOSS: 1.0278 |
| [2026-05-24 00:32:17] Validation | Batch 460/1463 | Loss: 0.8217 | LM_LOSS: 0.3078 | LB_LOSS: 1.0278 |
| [2026-05-24 00:32:20] Validation | Batch 470/1463 | Loss: 0.8224 | LM_LOSS: 0.3085 | LB_LOSS: 1.0277 |
| [2026-05-24 00:32:22] Validation | Batch 480/1463 | Loss: 0.8223 | LM_LOSS: 0.3084 | LB_LOSS: 1.0277 |
| [2026-05-24 00:32:25] Validation | Batch 490/1463 | Loss: 0.8222 | LM_LOSS: 0.3083 | LB_LOSS: 1.0277 |
| [2026-05-24 00:32:28] Validation | Batch 500/1463 | Loss: 0.8221 | LM_LOSS: 0.3082 | LB_LOSS: 1.0277 |
| [2026-05-24 00:32:30] Validation | Batch 510/1463 | Loss: 0.8215 | LM_LOSS: 0.3076 | LB_LOSS: 1.0277 |
| [2026-05-24 00:32:32] Validation | Batch 520/1463 | Loss: 0.8211 | LM_LOSS: 0.3072 | LB_LOSS: 1.0278 |
| [2026-05-24 00:32:34] Validation | Batch 530/1463 | Loss: 0.8213 | LM_LOSS: 0.3074 | LB_LOSS: 1.0277 |
| [2026-05-24 00:32:36] Validation | Batch 540/1463 | Loss: 0.8216 | LM_LOSS: 0.3077 | LB_LOSS: 1.0278 |
| [2026-05-24 00:32:38] Validation | Batch 550/1463 | Loss: 0.8213 | LM_LOSS: 0.3074 | LB_LOSS: 1.0278 |
| [2026-05-24 00:32:41] Validation | Batch 560/1463 | Loss: 0.8216 | LM_LOSS: 0.3076 | LB_LOSS: 1.0279 |
| [2026-05-24 00:32:43] Validation | Batch 570/1463 | Loss: 0.8216 | LM_LOSS: 0.3076 | LB_LOSS: 1.0279 |
| [2026-05-24 00:32:46] Validation | Batch 580/1463 | Loss: 0.8214 | LM_LOSS: 0.3075 | LB_LOSS: 1.0279 |
| [2026-05-24 00:32:49] Validation | Batch 590/1463 | Loss: 0.8212 | LM_LOSS: 0.3073 | LB_LOSS: 1.0279 |
| [2026-05-24 00:32:51] Validation | Batch 600/1463 | Loss: 0.8216 | LM_LOSS: 0.3076 | LB_LOSS: 1.0280 |
| [2026-05-24 00:32:54] Validation | Batch 610/1463 | Loss: 0.8217 | LM_LOSS: 0.3077 | LB_LOSS: 1.0280 |
| [2026-05-24 00:32:56] Validation | Batch 620/1463 | Loss: 0.8212 | LM_LOSS: 0.3072 | LB_LOSS: 1.0280 |
| [2026-05-24 00:32:59] Validation | Batch 630/1463 | Loss: 0.8206 | LM_LOSS: 0.3066 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:01] Validation | Batch 640/1463 | Loss: 0.8204 | LM_LOSS: 0.3064 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:03] Validation | Batch 650/1463 | Loss: 0.8199 | LM_LOSS: 0.3059 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:05] Validation | Batch 660/1463 | Loss: 0.8195 | LM_LOSS: 0.3055 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:07] Validation | Batch 670/1463 | Loss: 0.8192 | LM_LOSS: 0.3052 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:09] Validation | Batch 680/1463 | Loss: 0.8192 | LM_LOSS: 0.3052 | LB_LOSS: 1.0279 |
| [2026-05-24 00:33:12] Validation | Batch 690/1463 | Loss: 0.8195 | LM_LOSS: 0.3055 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:14] Validation | Batch 700/1463 | Loss: 0.8193 | LM_LOSS: 0.3053 | LB_LOSS: 1.0279 |
| [2026-05-24 00:33:16] Validation | Batch 710/1463 | Loss: 0.8198 | LM_LOSS: 0.3058 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:19] Validation | Batch 720/1463 | Loss: 0.8206 | LM_LOSS: 0.3066 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:21] Validation | Batch 730/1463 | Loss: 0.8204 | LM_LOSS: 0.3063 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:23] Validation | Batch 740/1463 | Loss: 0.8200 | LM_LOSS: 0.3060 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:25] Validation | Batch 750/1463 | Loss: 0.8199 | LM_LOSS: 0.3059 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:27] Validation | Batch 760/1463 | Loss: 0.8198 | LM_LOSS: 0.3058 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:29] Validation | Batch 770/1463 | Loss: 0.8196 | LM_LOSS: 0.3056 | LB_LOSS: 1.0281 |
| [2026-05-24 00:33:31] Validation | Batch 780/1463 | Loss: 0.8194 | LM_LOSS: 0.3054 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:33] Validation | Batch 790/1463 | Loss: 0.8196 | LM_LOSS: 0.3056 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:35] Validation | Batch 800/1463 | Loss: 0.8195 | LM_LOSS: 0.3055 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:37] Validation | Batch 810/1463 | Loss: 0.8191 | LM_LOSS: 0.3052 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:39] Validation | Batch 820/1463 | Loss: 0.8193 | LM_LOSS: 0.3054 | LB_LOSS: 1.0279 |
| [2026-05-24 00:33:42] Validation | Batch 830/1463 | Loss: 0.8197 | LM_LOSS: 0.3057 | LB_LOSS: 1.0279 |
| [2026-05-24 00:33:45] Validation | Batch 840/1463 | Loss: 0.8197 | LM_LOSS: 0.3057 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:47] Validation | Batch 850/1463 | Loss: 0.8200 | LM_LOSS: 0.3060 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:50] Validation | Batch 860/1463 | Loss: 0.8200 | LM_LOSS: 0.3060 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:52] Validation | Batch 870/1463 | Loss: 0.8200 | LM_LOSS: 0.3060 | LB_LOSS: 1.0281 |
| [2026-05-24 00:33:54] Validation | Batch 880/1463 | Loss: 0.8192 | LM_LOSS: 0.3052 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:56] Validation | Batch 890/1463 | Loss: 0.8192 | LM_LOSS: 0.3053 | LB_LOSS: 1.0280 |
| [2026-05-24 00:33:59] Validation | Batch 900/1463 | Loss: 0.8189 | LM_LOSS: 0.3049 | LB_LOSS: 1.0280 |
| [2026-05-24 00:34:01] Validation | Batch 910/1463 | Loss: 0.8188 | LM_LOSS: 0.3048 | LB_LOSS: 1.0280 |
| [2026-05-24 00:34:04] Validation | Batch 920/1463 | Loss: 0.8189 | LM_LOSS: 0.3049 | LB_LOSS: 1.0280 |
| [2026-05-24 00:34:06] Validation | Batch 930/1463 | Loss: 0.8187 | LM_LOSS: 0.3047 | LB_LOSS: 1.0280 |
| [2026-05-24 00:34:08] Validation | Batch 940/1463 | Loss: 0.8184 | LM_LOSS: 0.3044 | LB_LOSS: 1.0279 |
| [2026-05-24 00:34:11] Validation | Batch 950/1463 | Loss: 0.8186 | LM_LOSS: 0.3046 | LB_LOSS: 1.0279 |
| [2026-05-24 00:34:13] Validation | Batch 960/1463 | Loss: 0.8187 | LM_LOSS: 0.3047 | LB_LOSS: 1.0279 |
| [2026-05-24 00:34:16] Validation | Batch 970/1463 | Loss: 0.8188 | LM_LOSS: 0.3048 | LB_LOSS: 1.0279 |
| [2026-05-24 00:34:19] Validation | Batch 980/1463 | Loss: 0.8191 | LM_LOSS: 0.3051 | LB_LOSS: 1.0279 |
| [2026-05-24 00:34:21] Validation | Batch 990/1463 | Loss: 0.8193 | LM_LOSS: 0.3054 | LB_LOSS: 1.0279 |
| [2026-05-24 00:34:23] Validation | Batch 1000/1463 | Loss: 0.8199 | LM_LOSS: 0.3060 | LB_LOSS: 1.0279 |
| [2026-05-24 00:34:26] Validation | Batch 1010/1463 | Loss: 0.8199 | LM_LOSS: 0.3060 | LB_LOSS: 1.0279 |
| [2026-05-24 00:34:28] Validation | Batch 1020/1463 | Loss: 0.8200 | LM_LOSS: 0.3060 | LB_LOSS: 1.0280 |
| [2026-05-24 00:34:31] Validation | Batch 1030/1463 | Loss: 0.8204 | LM_LOSS: 0.3064 | LB_LOSS: 1.0280 |
| [2026-05-24 00:34:33] Validation | Batch 1040/1463 | Loss: 0.8200 | LM_LOSS: 0.3060 | LB_LOSS: 1.0280 |
| [2026-05-24 00:34:36] Validation | Batch 1050/1463 | Loss: 0.8199 | LM_LOSS: 0.3059 | LB_LOSS: 1.0279 |
| [2026-05-24 00:34:38] Validation | Batch 1060/1463 | Loss: 0.8199 | LM_LOSS: 0.3060 | LB_LOSS: 1.0279 |
| [2026-05-24 00:34:41] Validation | Batch 1070/1463 | Loss: 0.8199 | LM_LOSS: 0.3059 | LB_LOSS: 1.0279 |
| [2026-05-24 00:34:43] Validation | Batch 1080/1463 | Loss: 0.8197 | LM_LOSS: 0.3057 | LB_LOSS: 1.0280 |
| [2026-05-24 00:34:45] Validation | Batch 1090/1463 | Loss: 0.8197 | LM_LOSS: 0.3058 | LB_LOSS: 1.0279 |
| [2026-05-24 00:34:47] Validation | Batch 1100/1463 | Loss: 0.8196 | LM_LOSS: 0.3056 | LB_LOSS: 1.0279 |
| [2026-05-24 00:34:49] Validation | Batch 1110/1463 | Loss: 0.8195 | LM_LOSS: 0.3056 | LB_LOSS: 1.0279 |
| [2026-05-24 00:34:52] Validation | Batch 1120/1463 | Loss: 0.8194 | LM_LOSS: 0.3054 | LB_LOSS: 1.0279 |
| [2026-05-24 00:34:55] Validation | Batch 1130/1463 | Loss: 0.8192 | LM_LOSS: 0.3053 | LB_LOSS: 1.0279 |
| [2026-05-24 00:34:57] Validation | Batch 1140/1463 | Loss: 0.8194 | LM_LOSS: 0.3054 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:00] Validation | Batch 1150/1463 | Loss: 0.8193 | LM_LOSS: 0.3054 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:02] Validation | Batch 1160/1463 | Loss: 0.8193 | LM_LOSS: 0.3053 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:04] Validation | Batch 1170/1463 | Loss: 0.8193 | LM_LOSS: 0.3054 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:07] Validation | Batch 1180/1463 | Loss: 0.8193 | LM_LOSS: 0.3054 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:09] Validation | Batch 1190/1463 | Loss: 0.8194 | LM_LOSS: 0.3055 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:12] Validation | Batch 1200/1463 | Loss: 0.8195 | LM_LOSS: 0.3055 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:14] Validation | Batch 1210/1463 | Loss: 0.8197 | LM_LOSS: 0.3057 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:16] Validation | Batch 1220/1463 | Loss: 0.8201 | LM_LOSS: 0.3061 | LB_LOSS: 1.0280 |
| [2026-05-24 00:35:19] Validation | Batch 1230/1463 | Loss: 0.8201 | LM_LOSS: 0.3061 | LB_LOSS: 1.0280 |
| [2026-05-24 00:35:21] Validation | Batch 1240/1463 | Loss: 0.8204 | LM_LOSS: 0.3064 | LB_LOSS: 1.0280 |
| [2026-05-24 00:35:23] Validation | Batch 1250/1463 | Loss: 0.8206 | LM_LOSS: 0.3067 | LB_LOSS: 1.0280 |
| [2026-05-24 00:35:26] Validation | Batch 1260/1463 | Loss: 0.8206 | LM_LOSS: 0.3066 | LB_LOSS: 1.0280 |
| [2026-05-24 00:35:28] Validation | Batch 1270/1463 | Loss: 0.8204 | LM_LOSS: 0.3064 | LB_LOSS: 1.0280 |
| [2026-05-24 00:35:31] Validation | Batch 1280/1463 | Loss: 0.8203 | LM_LOSS: 0.3063 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:33] Validation | Batch 1290/1463 | Loss: 0.8203 | LM_LOSS: 0.3063 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:36] Validation | Batch 1300/1463 | Loss: 0.8202 | LM_LOSS: 0.3062 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:38] Validation | Batch 1310/1463 | Loss: 0.8201 | LM_LOSS: 0.3061 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:40] Validation | Batch 1320/1463 | Loss: 0.8201 | LM_LOSS: 0.3061 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:42] Validation | Batch 1330/1463 | Loss: 0.8201 | LM_LOSS: 0.3062 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:44] Validation | Batch 1340/1463 | Loss: 0.8204 | LM_LOSS: 0.3064 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:46] Validation | Batch 1350/1463 | Loss: 0.8204 | LM_LOSS: 0.3065 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:49] Validation | Batch 1360/1463 | Loss: 0.8207 | LM_LOSS: 0.3067 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:52] Validation | Batch 1370/1463 | Loss: 0.8209 | LM_LOSS: 0.3070 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:54] Validation | Batch 1380/1463 | Loss: 0.8207 | LM_LOSS: 0.3068 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:56] Validation | Batch 1390/1463 | Loss: 0.8206 | LM_LOSS: 0.3067 | LB_LOSS: 1.0279 |
| [2026-05-24 00:35:59] Validation | Batch 1400/1463 | Loss: 0.8210 | LM_LOSS: 0.3070 | LB_LOSS: 1.0279 |
| [2026-05-24 00:36:01] Validation | Batch 1410/1463 | Loss: 0.8212 | LM_LOSS: 0.3072 | LB_LOSS: 1.0279 |
| [2026-05-24 00:36:03] Validation | Batch 1420/1463 | Loss: 0.8211 | LM_LOSS: 0.3072 | LB_LOSS: 1.0279 |
| [2026-05-24 00:36:06] Validation | Batch 1430/1463 | Loss: 0.8212 | LM_LOSS: 0.3073 | LB_LOSS: 1.0279 |
| [2026-05-24 00:36:08] Validation | Batch 1440/1463 | Loss: 0.8216 | LM_LOSS: 0.3076 | LB_LOSS: 1.0279 |
| [2026-05-24 00:36:11] Validation | Batch 1450/1463 | Loss: 0.8213 | LM_LOSS: 0.3073 | LB_LOSS: 1.0279 |
| [2026-05-24 00:36:13] Validation | Batch 1460/1463 | Loss: 0.8216 | LM_LOSS: 0.3076 | LB_LOSS: 1.0279 |
| [2026-05-24 00:36:14] Validation | Batch 1463/1463 | Loss: 0.8215 | LM_LOSS: 0.3076 | LB_LOSS: 1.0279 |
| [2026-05-24 00:36:14] Validation | Loss: 0.8215 | LM_LOSS: 0.3076 | LB_LOSS: 1.0279 | PPL: 1.36 | Time: 345.90s |
| [2026-05-24 00:36:18] New best model saved! Val loss: 0.8215 |
| [2026-05-24 00:36:30] Epoch 1 | Step 1010 | Loss: 0.8745 | LM: 0.3352 | LB: 1.0820 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.350 | HR1: 0.390/SR1: 0.361 | LR: 7.47e-05 |
| [2026-05-24 00:36:42] Epoch 1 | Step 1020 | Loss: 0.8739 | LM: 0.3347 | LB: 1.0815 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.350 | HR1: 0.389/SR1: 0.360 | LR: 7.53e-05 |
| [2026-05-24 00:36:54] Epoch 1 | Step 1030 | Loss: 0.8734 | LM: 0.3351 | LB: 1.0809 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.350 | HR1: 0.388/SR1: 0.359 | LR: 7.59e-05 |
| [2026-05-24 00:37:06] Epoch 1 | Step 1040 | Loss: 0.8729 | LM: 0.3353 | LB: 1.0804 | CL0: 2.8 | CL1: 2.7 | HR0: 0.354/SR0: 0.350 | HR1: 0.388/SR1: 0.358 | LR: 7.66e-05 |
| [2026-05-24 00:37:18] Epoch 1 | Step 1050 | Loss: 0.8726 | LM: 0.3351 | LB: 1.0800 | CL0: 2.8 | CL1: 2.7 | HR0: 0.354/SR0: 0.350 | HR1: 0.387/SR1: 0.357 | LR: 7.72e-05 |
| [2026-05-24 00:37:30] Epoch 1 | Step 1060 | Loss: 0.8721 | LM: 0.3351 | LB: 1.0795 | CL0: 2.8 | CL1: 2.7 | HR0: 0.354/SR0: 0.350 | HR1: 0.386/SR1: 0.356 | LR: 7.79e-05 |
| [2026-05-24 00:37:42] Epoch 1 | Step 1070 | Loss: 0.8716 | LM: 0.3343 | LB: 1.0790 | CL0: 2.8 | CL1: 2.7 | HR0: 0.354/SR0: 0.350 | HR1: 0.385/SR1: 0.355 | LR: 7.85e-05 |
| [2026-05-24 00:37:54] Epoch 1 | Step 1080 | Loss: 0.8710 | LM: 0.3336 | LB: 1.0785 | CL0: 2.8 | CL1: 2.7 | HR0: 0.354/SR0: 0.350 | HR1: 0.384/SR1: 0.354 | LR: 7.91e-05 |
| [2026-05-24 00:38:06] Epoch 1 | Step 1090 | Loss: 0.8704 | LM: 0.3331 | LB: 1.0780 | CL0: 2.8 | CL1: 2.7 | HR0: 0.354/SR0: 0.350 | HR1: 0.384/SR1: 0.354 | LR: 7.98e-05 |
| [2026-05-24 00:38:18] Epoch 1 | Step 1100 | Loss: 0.8699 | LM: 0.3328 | LB: 1.0776 | CL0: 2.8 | CL1: 2.7 | HR0: 0.354/SR0: 0.350 | HR1: 0.383/SR1: 0.353 | LR: 8.04e-05 |
| [2026-05-24 00:38:30] Epoch 1 | Step 1110 | Loss: 0.8694 | LM: 0.3325 | LB: 1.0771 | CL0: 2.8 | CL1: 2.7 | HR0: 0.354/SR0: 0.350 | HR1: 0.382/SR1: 0.352 | LR: 8.11e-05 |
| [2026-05-24 00:38:41] Epoch 1 | Step 1120 | Loss: 0.8693 | LM: 0.3327 | LB: 1.0766 | CL0: 2.8 | CL1: 2.7 | HR0: 0.354/SR0: 0.349 | HR1: 0.381/SR1: 0.351 | LR: 8.17e-05 |
| [2026-05-24 00:38:53] Epoch 1 | Step 1130 | Loss: 0.8688 | LM: 0.3321 | LB: 1.0763 | CL0: 2.8 | CL1: 2.7 | HR0: 0.354/SR0: 0.349 | HR1: 0.381/SR1: 0.350 | LR: 8.23e-05 |
| [2026-05-24 00:39:06] Epoch 1 | Step 1140 | Loss: 0.8685 | LM: 0.3321 | LB: 1.0759 | CL0: 2.8 | CL1: 2.7 | HR0: 0.354/SR0: 0.349 | HR1: 0.380/SR1: 0.350 | LR: 8.30e-05 |
| [2026-05-24 00:39:18] Epoch 1 | Step 1150 | Loss: 0.8683 | LM: 0.3320 | LB: 1.0754 | CL0: 2.8 | CL1: 2.7 | HR0: 0.354/SR0: 0.349 | HR1: 0.379/SR1: 0.349 | LR: 8.36e-05 |
| [2026-05-24 00:39:30] Epoch 1 | Step 1160 | Loss: 0.8678 | LM: 0.3316 | LB: 1.0750 | CL0: 2.8 | CL1: 2.7 | HR0: 0.354/SR0: 0.349 | HR1: 0.378/SR1: 0.348 | LR: 8.43e-05 |
| [2026-05-24 00:39:41] Epoch 1 | Step 1170 | Loss: 0.8675 | LM: 0.3316 | LB: 1.0746 | CL0: 2.8 | CL1: 2.7 | HR0: 0.354/SR0: 0.349 | HR1: 0.378/SR1: 0.347 | LR: 8.49e-05 |
| [2026-05-24 00:39:53] Epoch 1 | Step 1180 | Loss: 0.8672 | LM: 0.3316 | LB: 1.0742 | CL0: 2.8 | CL1: 2.7 | HR0: 0.354/SR0: 0.349 | HR1: 0.377/SR1: 0.346 | LR: 8.55e-05 |
| [2026-05-24 00:40:05] Epoch 1 | Step 1190 | Loss: 0.8669 | LM: 0.3316 | LB: 1.0738 | CL0: 2.8 | CL1: 2.7 | HR0: 0.354/SR0: 0.349 | HR1: 0.376/SR1: 0.346 | LR: 8.62e-05 |
| [2026-05-24 00:40:18] Epoch 1 | Step 1200 | Loss: 0.8664 | LM: 0.3313 | LB: 1.0734 | CL0: 2.8 | CL1: 2.7 | HR0: 0.354/SR0: 0.349 | HR1: 0.376/SR1: 0.345 | LR: 8.68e-05 |
| [2026-05-24 00:40:30] Epoch 1 | Step 1210 | Loss: 0.8662 | LM: 0.3315 | LB: 1.0730 | CL0: 2.8 | CL1: 2.8 | HR0: 0.354/SR0: 0.349 | HR1: 0.375/SR1: 0.344 | LR: 8.75e-05 |
| [2026-05-24 00:40:42] Epoch 1 | Step 1220 | Loss: 0.8658 | LM: 0.3317 | LB: 1.0726 | CL0: 2.8 | CL1: 2.8 | HR0: 0.354/SR0: 0.349 | HR1: 0.374/SR1: 0.344 | LR: 8.81e-05 |
| [2026-05-24 00:40:54] Epoch 1 | Step 1230 | Loss: 0.8655 | LM: 0.3316 | LB: 1.0722 | CL0: 2.8 | CL1: 2.8 | HR0: 0.353/SR0: 0.348 | HR1: 0.374/SR1: 0.343 | LR: 8.87e-05 |
| [2026-05-24 00:41:06] Epoch 1 | Step 1240 | Loss: 0.8653 | LM: 0.3315 | LB: 1.0718 | CL0: 2.8 | CL1: 2.8 | HR0: 0.353/SR0: 0.348 | HR1: 0.373/SR1: 0.342 | LR: 8.94e-05 |
| [2026-05-24 00:41:18] Epoch 1 | Step 1250 | Loss: 0.8651 | LM: 0.3316 | LB: 1.0715 | CL0: 2.8 | CL1: 2.8 | HR0: 0.353/SR0: 0.348 | HR1: 0.373/SR1: 0.341 | LR: 9.00e-05 |
| [2026-05-24 00:41:30] Epoch 1 | Step 1260 | Loss: 0.8645 | LM: 0.3310 | LB: 1.0711 | CL0: 2.8 | CL1: 2.8 | HR0: 0.353/SR0: 0.348 | HR1: 0.372/SR1: 0.341 | LR: 9.07e-05 |
| [2026-05-24 00:41:42] Epoch 1 | Step 1270 | Loss: 0.8641 | LM: 0.3306 | LB: 1.0708 | CL0: 2.8 | CL1: 2.8 | HR0: 0.353/SR0: 0.348 | HR1: 0.371/SR1: 0.340 | LR: 9.13e-05 |
| [2026-05-24 00:41:54] Epoch 1 | Step 1280 | Loss: 0.8636 | LM: 0.3309 | LB: 1.0705 | CL0: 2.8 | CL1: 2.8 | HR0: 0.353/SR0: 0.348 | HR1: 0.371/SR1: 0.339 | LR: 9.19e-05 |
| [2026-05-24 00:42:06] Epoch 1 | Step 1290 | Loss: 0.8634 | LM: 0.3309 | LB: 1.0701 | CL0: 2.8 | CL1: 2.8 | HR0: 0.353/SR0: 0.348 | HR1: 0.370/SR1: 0.339 | LR: 9.26e-05 |
| [2026-05-24 00:42:18] Epoch 1 | Step 1300 | Loss: 0.8633 | LM: 0.3312 | LB: 1.0698 | CL0: 2.8 | CL1: 2.8 | HR0: 0.353/SR0: 0.348 | HR1: 0.369/SR1: 0.338 | LR: 9.32e-05 |
| [2026-05-24 00:42:30] Epoch 1 | Step 1310 | Loss: 0.8631 | LM: 0.3321 | LB: 1.0694 | CL0: 2.8 | CL1: 2.8 | HR0: 0.353/SR0: 0.348 | HR1: 0.369/SR1: 0.337 | LR: 9.39e-05 |
| [2026-05-24 00:42:42] Epoch 1 | Step 1320 | Loss: 0.8628 | LM: 0.3321 | LB: 1.0690 | CL0: 2.8 | CL1: 2.8 | HR0: 0.353/SR0: 0.348 | HR1: 0.368/SR1: 0.337 | LR: 9.45e-05 |
| [2026-05-24 00:42:54] Epoch 1 | Step 1330 | Loss: 0.8625 | LM: 0.3318 | LB: 1.0687 | CL0: 2.8 | CL1: 2.8 | HR0: 0.353/SR0: 0.348 | HR1: 0.368/SR1: 0.336 | LR: 9.51e-05 |
| [2026-05-24 00:43:06] Epoch 1 | Step 1340 | Loss: 0.8622 | LM: 0.3315 | LB: 1.0684 | CL0: 2.8 | CL1: 2.8 | HR0: 0.353/SR0: 0.348 | HR1: 0.367/SR1: 0.335 | LR: 9.58e-05 |
| [2026-05-24 00:43:17] Epoch 1 | Step 1350 | Loss: 0.8618 | LM: 0.3312 | LB: 1.0680 | CL0: 2.8 | CL1: 2.8 | HR0: 0.353/SR0: 0.347 | HR1: 0.366/SR1: 0.335 | LR: 9.64e-05 |
| [2026-05-24 00:43:29] Epoch 1 | Step 1360 | Loss: 0.8617 | LM: 0.3312 | LB: 1.0677 | CL0: 2.8 | CL1: 2.8 | HR0: 0.353/SR0: 0.347 | HR1: 0.366/SR1: 0.334 | LR: 9.71e-05 |
| [2026-05-24 00:43:40] Epoch 1 | Step 1370 | Loss: 0.8613 | LM: 0.3308 | LB: 1.0674 | CL0: 2.8 | CL1: 2.8 | HR0: 0.353/SR0: 0.347 | HR1: 0.366/SR1: 0.334 | LR: 9.77e-05 |
| [2026-05-24 00:43:51] Epoch 1 | Step 1380 | Loss: 0.8609 | LM: 0.3308 | LB: 1.0670 | CL0: 2.8 | CL1: 2.8 | HR0: 0.353/SR0: 0.347 | HR1: 0.365/SR1: 0.333 | LR: 9.83e-05 |
| [2026-05-24 00:44:02] Epoch 1 | Step 1390 | Loss: 0.8605 | LM: 0.3307 | LB: 1.0667 | CL0: 2.8 | CL1: 2.8 | HR0: 0.353/SR0: 0.347 | HR1: 0.364/SR1: 0.333 | LR: 9.90e-05 |
| [2026-05-24 00:44:14] Epoch 1 | Step 1400 | Loss: 0.8603 | LM: 0.3310 | LB: 1.0663 | CL0: 2.9 | CL1: 2.8 | HR0: 0.352/SR0: 0.347 | HR1: 0.364/SR1: 0.332 | LR: 9.96e-05 |
| [2026-05-24 00:44:26] Epoch 1 | Step 1410 | Loss: 0.8600 | LM: 0.3314 | LB: 1.0660 | CL0: 2.9 | CL1: 2.8 | HR0: 0.352/SR0: 0.347 | HR1: 0.363/SR1: 0.331 | LR: 1.00e-04 |
| [2026-05-24 00:44:38] Epoch 1 | Step 1420 | Loss: 0.8598 | LM: 0.3312 | LB: 1.0657 | CL0: 2.9 | CL1: 2.9 | HR0: 0.352/SR0: 0.346 | HR1: 0.363/SR1: 0.331 | LR: 1.00e-04 |
| [2026-05-24 00:44:50] Epoch 1 | Step 1430 | Loss: 0.8594 | LM: 0.3306 | LB: 1.0654 | CL0: 2.9 | CL1: 2.9 | HR0: 0.352/SR0: 0.346 | HR1: 0.363/SR1: 0.330 | LR: 1.00e-04 |
| [2026-05-24 00:45:02] Epoch 1 | Step 1440 | Loss: 0.8590 | LM: 0.3304 | LB: 1.0651 | CL0: 2.9 | CL1: 2.9 | HR0: 0.352/SR0: 0.346 | HR1: 0.362/SR1: 0.330 | LR: 1.00e-04 |
| [2026-05-24 00:45:14] Epoch 1 | Step 1450 | Loss: 0.8589 | LM: 0.3305 | LB: 1.0648 | CL0: 2.9 | CL1: 2.9 | HR0: 0.352/SR0: 0.346 | HR1: 0.362/SR1: 0.329 | LR: 1.00e-04 |
| [2026-05-24 00:45:26] Epoch 1 | Step 1460 | Loss: 0.8587 | LM: 0.3307 | LB: 1.0645 | CL0: 2.9 | CL1: 2.9 | HR0: 0.352/SR0: 0.346 | HR1: 0.361/SR1: 0.329 | LR: 1.00e-04 |
| [2026-05-24 00:45:38] Epoch 1 | Step 1470 | Loss: 0.8584 | LM: 0.3303 | LB: 1.0642 | CL0: 2.9 | CL1: 2.9 | HR0: 0.352/SR0: 0.346 | HR1: 0.361/SR1: 0.328 | LR: 1.00e-04 |
| [2026-05-24 00:45:49] Epoch 1 | Step 1480 | Loss: 0.8583 | LM: 0.3304 | LB: 1.0639 | CL0: 2.9 | CL1: 2.9 | HR0: 0.352/SR0: 0.346 | HR1: 0.360/SR1: 0.328 | LR: 1.00e-04 |
| [2026-05-24 00:46:00] Epoch 1 | Step 1490 | Loss: 0.8581 | LM: 0.3306 | LB: 1.0636 | CL0: 2.9 | CL1: 2.9 | HR0: 0.352/SR0: 0.346 | HR1: 0.360/SR1: 0.327 | LR: 1.00e-04 |
| [2026-05-24 00:46:11] Epoch 1 | Step 1500 | Loss: 0.8578 | LM: 0.3303 | LB: 1.0633 | CL0: 2.9 | CL1: 2.9 | HR0: 0.351/SR0: 0.345 | HR1: 0.359/SR1: 0.327 | LR: 1.00e-04 |
| [2026-05-24 00:46:22] Epoch 1 | Step 1510 | Loss: 0.8576 | LM: 0.3301 | LB: 1.0630 | CL0: 2.9 | CL1: 2.9 | HR0: 0.351/SR0: 0.345 | HR1: 0.359/SR1: 0.326 | LR: 1.00e-04 |
| [2026-05-24 00:46:33] Epoch 1 | Step 1520 | Loss: 0.8572 | LM: 0.3298 | LB: 1.0628 | CL0: 2.9 | CL1: 2.9 | HR0: 0.351/SR0: 0.345 | HR1: 0.358/SR1: 0.326 | LR: 1.00e-04 |
| [2026-05-24 00:46:44] Epoch 1 | Step 1530 | Loss: 0.8568 | LM: 0.3293 | LB: 1.0624 | CL0: 2.9 | CL1: 2.9 | HR0: 0.351/SR0: 0.345 | HR1: 0.358/SR1: 0.325 | LR: 1.00e-04 |
| [2026-05-24 00:46:56] Epoch 1 | Step 1540 | Loss: 0.8565 | LM: 0.3290 | LB: 1.0622 | CL0: 2.9 | CL1: 2.9 | HR0: 0.351/SR0: 0.345 | HR1: 0.357/SR1: 0.325 | LR: 1.00e-04 |
| [2026-05-24 00:47:07] Epoch 1 | Step 1550 | Loss: 0.8563 | LM: 0.3289 | LB: 1.0619 | CL0: 2.9 | CL1: 2.9 | HR0: 0.351/SR0: 0.345 | HR1: 0.357/SR1: 0.324 | LR: 1.00e-04 |
| [2026-05-24 00:47:19] Epoch 1 | Step 1560 | Loss: 0.8562 | LM: 0.3289 | LB: 1.0616 | CL0: 2.9 | CL1: 2.9 | HR0: 0.351/SR0: 0.345 | HR1: 0.357/SR1: 0.324 | LR: 1.00e-04 |
| [2026-05-24 00:47:31] Epoch 1 | Step 1570 | Loss: 0.8559 | LM: 0.3283 | LB: 1.0614 | CL0: 2.9 | CL1: 2.9 | HR0: 0.351/SR0: 0.344 | HR1: 0.356/SR1: 0.323 | LR: 1.00e-04 |
| [2026-05-24 00:47:42] Epoch 1 | Step 1580 | Loss: 0.8557 | LM: 0.3284 | LB: 1.0611 | CL0: 2.9 | CL1: 2.9 | HR0: 0.351/SR0: 0.344 | HR1: 0.356/SR1: 0.323 | LR: 1.00e-04 |
| [2026-05-24 00:47:52] Epoch 1 | Step 1590 | Loss: 0.8553 | LM: 0.3281 | LB: 1.0608 | CL0: 2.9 | CL1: 2.9 | HR0: 0.351/SR0: 0.344 | HR1: 0.356/SR1: 0.322 | LR: 1.00e-04 |
| [2026-05-24 00:48:04] Epoch 1 | Step 1600 | Loss: 0.8550 | LM: 0.3283 | LB: 1.0605 | CL0: 2.9 | CL1: 2.9 | HR0: 0.350/SR0: 0.344 | HR1: 0.355/SR1: 0.322 | LR: 1.00e-04 |
| [2026-05-24 00:48:15] Epoch 1 | Step 1610 | Loss: 0.8548 | LM: 0.3283 | LB: 1.0603 | CL0: 2.9 | CL1: 2.9 | HR0: 0.350/SR0: 0.344 | HR1: 0.355/SR1: 0.321 | LR: 1.00e-04 |
| [2026-05-24 00:48:27] Epoch 1 | Step 1620 | Loss: 0.8544 | LM: 0.3285 | LB: 1.0600 | CL0: 2.9 | CL1: 2.9 | HR0: 0.350/SR0: 0.344 | HR1: 0.354/SR1: 0.321 | LR: 1.00e-04 |
| [2026-05-24 00:48:38] Epoch 1 | Step 1630 | Loss: 0.8543 | LM: 0.3283 | LB: 1.0598 | CL0: 2.9 | CL1: 2.9 | HR0: 0.350/SR0: 0.343 | HR1: 0.354/SR1: 0.321 | LR: 1.00e-04 |
| [2026-05-24 00:48:49] Epoch 1 | Step 1640 | Loss: 0.8541 | LM: 0.3281 | LB: 1.0596 | CL0: 2.9 | CL1: 2.9 | HR0: 0.350/SR0: 0.343 | HR1: 0.354/SR1: 0.320 | LR: 1.00e-04 |
| [2026-05-24 00:49:00] Epoch 1 | Step 1650 | Loss: 0.8538 | LM: 0.3276 | LB: 1.0593 | CL0: 2.9 | CL1: 2.9 | HR0: 0.350/SR0: 0.343 | HR1: 0.353/SR1: 0.320 | LR: 1.00e-04 |
| [2026-05-24 00:49:11] Epoch 1 | Step 1660 | Loss: 0.8534 | LM: 0.3272 | LB: 1.0591 | CL0: 2.9 | CL1: 2.9 | HR0: 0.350/SR0: 0.343 | HR1: 0.353/SR1: 0.319 | LR: 1.00e-04 |
| [2026-05-24 00:49:22] Epoch 1 | Step 1670 | Loss: 0.8532 | LM: 0.3271 | LB: 1.0588 | CL0: 2.9 | CL1: 2.9 | HR0: 0.350/SR0: 0.343 | HR1: 0.352/SR1: 0.319 | LR: 1.00e-04 |
| [2026-05-24 00:49:33] Epoch 1 | Step 1680 | Loss: 0.8529 | LM: 0.3269 | LB: 1.0586 | CL0: 2.9 | CL1: 2.9 | HR0: 0.350/SR0: 0.343 | HR1: 0.352/SR1: 0.318 | LR: 1.00e-04 |
| [2026-05-24 00:49:43] Epoch 1 | Step 1690 | Loss: 0.8527 | LM: 0.3269 | LB: 1.0584 | CL0: 2.9 | CL1: 2.9 | HR0: 0.350/SR0: 0.343 | HR1: 0.352/SR1: 0.318 | LR: 1.00e-04 |
| [2026-05-24 00:49:55] Epoch 1 | Step 1700 | Loss: 0.8522 | LM: 0.3264 | LB: 1.0581 | CL0: 2.9 | CL1: 2.9 | HR0: 0.350/SR0: 0.343 | HR1: 0.352/SR1: 0.318 | LR: 1.00e-04 |
| [2026-05-24 00:50:06] Epoch 1 | Step 1710 | Loss: 0.8519 | LM: 0.3262 | LB: 1.0579 | CL0: 2.9 | CL1: 2.9 | HR0: 0.349/SR0: 0.343 | HR1: 0.351/SR1: 0.318 | LR: 1.00e-04 |
| [2026-05-24 00:50:17] Epoch 1 | Step 1720 | Loss: 0.8519 | LM: 0.3262 | LB: 1.0577 | CL0: 2.9 | CL1: 3.0 | HR0: 0.349/SR0: 0.342 | HR1: 0.351/SR1: 0.317 | LR: 1.00e-04 |
| [2026-05-24 00:50:28] Epoch 1 | Step 1730 | Loss: 0.8519 | LM: 0.3262 | LB: 1.0574 | CL0: 2.9 | CL1: 3.0 | HR0: 0.349/SR0: 0.342 | HR1: 0.351/SR1: 0.317 | LR: 1.00e-04 |
| [2026-05-24 00:50:39] Epoch 1 | Step 1740 | Loss: 0.8514 | LM: 0.3260 | LB: 1.0572 | CL0: 2.9 | CL1: 3.0 | HR0: 0.349/SR0: 0.342 | HR1: 0.350/SR1: 0.316 | LR: 1.00e-04 |
| [2026-05-24 00:50:50] Epoch 1 | Step 1750 | Loss: 0.8512 | LM: 0.3260 | LB: 1.0569 | CL0: 2.9 | CL1: 3.0 | HR0: 0.349/SR0: 0.342 | HR1: 0.350/SR1: 0.316 | LR: 1.00e-04 |
| [2026-05-24 00:51:02] Epoch 1 | Step 1760 | Loss: 0.8508 | LM: 0.3258 | LB: 1.0567 | CL0: 2.9 | CL1: 3.0 | HR0: 0.349/SR0: 0.342 | HR1: 0.350/SR1: 0.315 | LR: 1.00e-04 |
| [2026-05-24 00:51:12] Epoch 1 | Step 1770 | Loss: 0.8506 | LM: 0.3260 | LB: 1.0564 | CL0: 2.9 | CL1: 3.0 | HR0: 0.349/SR0: 0.342 | HR1: 0.349/SR1: 0.315 | LR: 1.00e-04 |
| [2026-05-24 00:51:23] Epoch 1 | Step 1780 | Loss: 0.8505 | LM: 0.3261 | LB: 1.0562 | CL0: 2.9 | CL1: 3.0 | HR0: 0.349/SR0: 0.341 | HR1: 0.349/SR1: 0.315 | LR: 1.00e-04 |
| [2026-05-24 00:51:35] Epoch 1 | Step 1790 | Loss: 0.8505 | LM: 0.3261 | LB: 1.0560 | CL0: 2.9 | CL1: 3.0 | HR0: 0.349/SR0: 0.341 | HR1: 0.349/SR1: 0.314 | LR: 1.00e-04 |
| [2026-05-24 00:51:46] Epoch 1 | Step 1800 | Loss: 0.8503 | LM: 0.3262 | LB: 1.0558 | CL0: 2.9 | CL1: 3.0 | HR0: 0.348/SR0: 0.341 | HR1: 0.348/SR1: 0.314 | LR: 1.00e-04 |
| [2026-05-24 00:51:58] Epoch 1 | Step 1810 | Loss: 0.8500 | LM: 0.3257 | LB: 1.0556 | CL0: 2.9 | CL1: 3.0 | HR0: 0.348/SR0: 0.341 | HR1: 0.348/SR1: 0.313 | LR: 1.00e-04 |
| [2026-05-24 00:52:09] Epoch 1 | Step 1820 | Loss: 0.8499 | LM: 0.3258 | LB: 1.0553 | CL0: 2.9 | CL1: 3.0 | HR0: 0.348/SR0: 0.341 | HR1: 0.348/SR1: 0.313 | LR: 1.00e-04 |
| [2026-05-24 00:52:20] Epoch 1 | Step 1830 | Loss: 0.8496 | LM: 0.3259 | LB: 1.0551 | CL0: 2.9 | CL1: 3.0 | HR0: 0.348/SR0: 0.341 | HR1: 0.347/SR1: 0.313 | LR: 1.00e-04 |
| [2026-05-24 00:52:31] Epoch 1 | Step 1840 | Loss: 0.8495 | LM: 0.3259 | LB: 1.0549 | CL0: 2.9 | CL1: 3.0 | HR0: 0.348/SR0: 0.341 | HR1: 0.347/SR1: 0.312 | LR: 1.00e-04 |
| [2026-05-24 00:52:43] Epoch 1 | Step 1850 | Loss: 0.8494 | LM: 0.3259 | LB: 1.0547 | CL0: 2.9 | CL1: 3.0 | HR0: 0.348/SR0: 0.341 | HR1: 0.347/SR1: 0.312 | LR: 1.00e-04 |
| [2026-05-24 00:52:54] Epoch 1 | Step 1860 | Loss: 0.8493 | LM: 0.3256 | LB: 1.0545 | CL0: 2.9 | CL1: 3.0 | HR0: 0.348/SR0: 0.340 | HR1: 0.346/SR1: 0.311 | LR: 1.00e-04 |
| [2026-05-24 00:53:05] Epoch 1 | Step 1870 | Loss: 0.8491 | LM: 0.3254 | LB: 1.0543 | CL0: 2.9 | CL1: 3.0 | HR0: 0.348/SR0: 0.340 | HR1: 0.346/SR1: 0.311 | LR: 1.00e-04 |
| [2026-05-24 00:53:16] Epoch 1 | Step 1880 | Loss: 0.8488 | LM: 0.3254 | LB: 1.0541 | CL0: 2.9 | CL1: 3.0 | HR0: 0.348/SR0: 0.340 | HR1: 0.345/SR1: 0.311 | LR: 1.00e-04 |
| [2026-05-24 00:53:27] Epoch 1 | Step 1890 | Loss: 0.8488 | LM: 0.3254 | LB: 1.0539 | CL0: 2.9 | CL1: 3.0 | HR0: 0.348/SR0: 0.340 | HR1: 0.345/SR1: 0.310 | LR: 1.00e-04 |
| [2026-05-24 00:53:38] Epoch 1 | Step 1900 | Loss: 0.8487 | LM: 0.3256 | LB: 1.0537 | CL0: 2.9 | CL1: 3.0 | HR0: 0.348/SR0: 0.340 | HR1: 0.345/SR1: 0.310 | LR: 1.00e-04 |
| [2026-05-24 00:53:50] Epoch 1 | Step 1910 | Loss: 0.8485 | LM: 0.3258 | LB: 1.0535 | CL0: 2.9 | CL1: 3.0 | HR0: 0.347/SR0: 0.340 | HR1: 0.344/SR1: 0.310 | LR: 1.00e-04 |
| [2026-05-24 00:54:01] Epoch 1 | Step 1920 | Loss: 0.8482 | LM: 0.3263 | LB: 1.0533 | CL0: 2.9 | CL1: 3.0 | HR0: 0.347/SR0: 0.340 | HR1: 0.344/SR1: 0.309 | LR: 1.00e-04 |
| [2026-05-24 00:54:11] Epoch 1 | Step 1930 | Loss: 0.8481 | LM: 0.3262 | LB: 1.0531 | CL0: 2.9 | CL1: 3.0 | HR0: 0.347/SR0: 0.340 | HR1: 0.344/SR1: 0.309 | LR: 1.00e-04 |
| [2026-05-24 00:54:22] Epoch 1 | Step 1940 | Loss: 0.8480 | LM: 0.3264 | LB: 1.0529 | CL0: 2.9 | CL1: 3.0 | HR0: 0.347/SR0: 0.339 | HR1: 0.343/SR1: 0.308 | LR: 1.00e-04 |
| [2026-05-24 00:54:33] Epoch 1 | Step 1950 | Loss: 0.8479 | LM: 0.3263 | LB: 1.0527 | CL0: 2.9 | CL1: 3.0 | HR0: 0.347/SR0: 0.339 | HR1: 0.343/SR1: 0.308 | LR: 1.00e-04 |
| [2026-05-24 00:54:44] Epoch 1 | Step 1960 | Loss: 0.8476 | LM: 0.3261 | LB: 1.0525 | CL0: 2.9 | CL1: 3.0 | HR0: 0.347/SR0: 0.339 | HR1: 0.343/SR1: 0.308 | LR: 1.00e-04 |
| [2026-05-24 00:54:55] Epoch 1 | Step 1970 | Loss: 0.8474 | LM: 0.3261 | LB: 1.0523 | CL0: 2.9 | CL1: 3.0 | HR0: 0.347/SR0: 0.339 | HR1: 0.343/SR1: 0.307 | LR: 1.00e-04 |
| [2026-05-24 00:55:06] Epoch 1 | Step 1980 | Loss: 0.8471 | LM: 0.3259 | LB: 1.0521 | CL0: 2.9 | CL1: 3.0 | HR0: 0.347/SR0: 0.339 | HR1: 0.342/SR1: 0.307 | LR: 1.00e-04 |
| [2026-05-24 00:55:17] Epoch 1 | Step 1990 | Loss: 0.8469 | LM: 0.3260 | LB: 1.0519 | CL0: 2.9 | CL1: 3.0 | HR0: 0.347/SR0: 0.339 | HR1: 0.342/SR1: 0.307 | LR: 1.00e-04 |
| [2026-05-24 00:55:28] Epoch 1 | Step 2000 | Loss: 0.8467 | LM: 0.3257 | LB: 1.0518 | CL0: 2.9 | CL1: 3.0 | HR0: 0.347/SR0: 0.339 | HR1: 0.342/SR1: 0.306 | LR: 1.00e-04 |
| [2026-05-24 00:55:30] Validation | Batch 10/1463 | Loss: 0.7827 | LM_LOSS: 0.2780 | LB_LOSS: 1.0093 |
| [2026-05-24 00:55:32] Validation | Batch 20/1463 | Loss: 0.7927 | LM_LOSS: 0.2870 | LB_LOSS: 1.0114 |
| [2026-05-24 00:55:34] Validation | Batch 30/1463 | Loss: 0.7982 | LM_LOSS: 0.2923 | LB_LOSS: 1.0119 |
| [2026-05-24 00:55:36] Validation | Batch 40/1463 | Loss: 0.8052 | LM_LOSS: 0.2989 | LB_LOSS: 1.0127 |
| [2026-05-24 00:55:38] Validation | Batch 50/1463 | Loss: 0.8131 | LM_LOSS: 0.3071 | LB_LOSS: 1.0121 |
| [2026-05-24 00:55:41] Validation | Batch 60/1463 | Loss: 0.8120 | LM_LOSS: 0.3060 | LB_LOSS: 1.0120 |
| [2026-05-24 00:55:44] Validation | Batch 70/1463 | Loss: 0.8117 | LM_LOSS: 0.3057 | LB_LOSS: 1.0120 |
| [2026-05-24 00:55:47] Validation | Batch 80/1463 | Loss: 0.8132 | LM_LOSS: 0.3072 | LB_LOSS: 1.0121 |
| [2026-05-24 00:55:49] Validation | Batch 90/1463 | Loss: 0.8124 | LM_LOSS: 0.3064 | LB_LOSS: 1.0120 |
| [2026-05-24 00:55:51] Validation | Batch 100/1463 | Loss: 0.8129 | LM_LOSS: 0.3069 | LB_LOSS: 1.0120 |
| [2026-05-24 00:55:53] Validation | Batch 110/1463 | Loss: 0.8118 | LM_LOSS: 0.3056 | LB_LOSS: 1.0122 |
| [2026-05-24 00:55:55] Validation | Batch 120/1463 | Loss: 0.8136 | LM_LOSS: 0.3074 | LB_LOSS: 1.0123 |
| [2026-05-24 00:55:57] Validation | Batch 130/1463 | Loss: 0.8155 | LM_LOSS: 0.3092 | LB_LOSS: 1.0124 |
| [2026-05-24 00:55:59] Validation | Batch 140/1463 | Loss: 0.8164 | LM_LOSS: 0.3102 | LB_LOSS: 1.0123 |
| [2026-05-24 00:56:02] Validation | Batch 150/1463 | Loss: 0.8148 | LM_LOSS: 0.3086 | LB_LOSS: 1.0125 |
| [2026-05-24 00:56:04] Validation | Batch 160/1463 | Loss: 0.8148 | LM_LOSS: 0.3086 | LB_LOSS: 1.0123 |
| [2026-05-24 00:56:06] Validation | Batch 170/1463 | Loss: 0.8145 | LM_LOSS: 0.3083 | LB_LOSS: 1.0124 |
| [2026-05-24 00:56:08] Validation | Batch 180/1463 | Loss: 0.8154 | LM_LOSS: 0.3092 | LB_LOSS: 1.0123 |
| [2026-05-24 00:56:11] Validation | Batch 190/1463 | Loss: 0.8164 | LM_LOSS: 0.3102 | LB_LOSS: 1.0124 |
| [2026-05-24 00:56:13] Validation | Batch 200/1463 | Loss: 0.8164 | LM_LOSS: 0.3102 | LB_LOSS: 1.0124 |
| [2026-05-24 00:56:15] Validation | Batch 210/1463 | Loss: 0.8169 | LM_LOSS: 0.3107 | LB_LOSS: 1.0124 |
| [2026-05-24 00:56:18] Validation | Batch 220/1463 | Loss: 0.8160 | LM_LOSS: 0.3098 | LB_LOSS: 1.0124 |
| [2026-05-24 00:56:20] Validation | Batch 230/1463 | Loss: 0.8176 | LM_LOSS: 0.3114 | LB_LOSS: 1.0123 |
| [2026-05-24 00:56:22] Validation | Batch 240/1463 | Loss: 0.8189 | LM_LOSS: 0.3127 | LB_LOSS: 1.0123 |
| [2026-05-24 00:56:25] Validation | Batch 250/1463 | Loss: 0.8181 | LM_LOSS: 0.3120 | LB_LOSS: 1.0123 |
| [2026-05-24 00:56:27] Validation | Batch 260/1463 | Loss: 0.8197 | LM_LOSS: 0.3135 | LB_LOSS: 1.0125 |
| [2026-05-24 00:56:29] Validation | Batch 270/1463 | Loss: 0.8184 | LM_LOSS: 0.3121 | LB_LOSS: 1.0125 |
| [2026-05-24 00:56:31] Validation | Batch 280/1463 | Loss: 0.8191 | LM_LOSS: 0.3128 | LB_LOSS: 1.0125 |
| [2026-05-24 00:56:34] Validation | Batch 290/1463 | Loss: 0.8184 | LM_LOSS: 0.3121 | LB_LOSS: 1.0125 |
| [2026-05-24 00:56:35] Validation | Batch 300/1463 | Loss: 0.8185 | LM_LOSS: 0.3122 | LB_LOSS: 1.0126 |
| [2026-05-24 00:56:38] Validation | Batch 310/1463 | Loss: 0.8196 | LM_LOSS: 0.3133 | LB_LOSS: 1.0126 |
| [2026-05-24 00:56:40] Validation | Batch 320/1463 | Loss: 0.8181 | LM_LOSS: 0.3119 | LB_LOSS: 1.0125 |
| [2026-05-24 00:56:42] Validation | Batch 330/1463 | Loss: 0.8181 | LM_LOSS: 0.3119 | LB_LOSS: 1.0125 |
| [2026-05-24 00:56:44] Validation | Batch 340/1463 | Loss: 0.8177 | LM_LOSS: 0.3114 | LB_LOSS: 1.0125 |
| [2026-05-24 00:56:46] Validation | Batch 350/1463 | Loss: 0.8183 | LM_LOSS: 0.3121 | LB_LOSS: 1.0125 |
| [2026-05-24 00:56:48] Validation | Batch 360/1463 | Loss: 0.8180 | LM_LOSS: 0.3117 | LB_LOSS: 1.0125 |
| [2026-05-24 00:56:50] Validation | Batch 370/1463 | Loss: 0.8176 | LM_LOSS: 0.3114 | LB_LOSS: 1.0125 |
| [2026-05-24 00:56:52] Validation | Batch 380/1463 | Loss: 0.8176 | LM_LOSS: 0.3113 | LB_LOSS: 1.0124 |
| [2026-05-24 00:56:55] Validation | Batch 390/1463 | Loss: 0.8184 | LM_LOSS: 0.3121 | LB_LOSS: 1.0125 |
| [2026-05-24 00:56:57] Validation | Batch 400/1463 | Loss: 0.8183 | LM_LOSS: 0.3120 | LB_LOSS: 1.0125 |
| [2026-05-24 00:56:59] Validation | Batch 410/1463 | Loss: 0.8180 | LM_LOSS: 0.3118 | LB_LOSS: 1.0125 |
| [2026-05-24 00:57:01] Validation | Batch 420/1463 | Loss: 0.8181 | LM_LOSS: 0.3118 | LB_LOSS: 1.0126 |
| [2026-05-24 00:57:04] Validation | Batch 430/1463 | Loss: 0.8176 | LM_LOSS: 0.3113 | LB_LOSS: 1.0126 |
| [2026-05-24 00:57:06] Validation | Batch 440/1463 | Loss: 0.8177 | LM_LOSS: 0.3114 | LB_LOSS: 1.0126 |
| [2026-05-24 00:57:08] Validation | Batch 450/1463 | Loss: 0.8176 | LM_LOSS: 0.3113 | LB_LOSS: 1.0126 |
| [2026-05-24 00:57:10] Validation | Batch 460/1463 | Loss: 0.8176 | LM_LOSS: 0.3113 | LB_LOSS: 1.0126 |
| [2026-05-24 00:57:13] Validation | Batch 470/1463 | Loss: 0.8183 | LM_LOSS: 0.3120 | LB_LOSS: 1.0126 |
| [2026-05-24 00:57:15] Validation | Batch 480/1463 | Loss: 0.8182 | LM_LOSS: 0.3119 | LB_LOSS: 1.0125 |
| [2026-05-24 00:57:17] Validation | Batch 490/1463 | Loss: 0.8181 | LM_LOSS: 0.3118 | LB_LOSS: 1.0125 |
| [2026-05-24 00:57:20] Validation | Batch 500/1463 | Loss: 0.8179 | LM_LOSS: 0.3117 | LB_LOSS: 1.0125 |
| [2026-05-24 00:57:22] Validation | Batch 510/1463 | Loss: 0.8174 | LM_LOSS: 0.3111 | LB_LOSS: 1.0125 |
| [2026-05-24 00:57:24] Validation | Batch 520/1463 | Loss: 0.8170 | LM_LOSS: 0.3107 | LB_LOSS: 1.0126 |
| [2026-05-24 00:57:26] Validation | Batch 530/1463 | Loss: 0.8173 | LM_LOSS: 0.3110 | LB_LOSS: 1.0125 |
| [2026-05-24 00:57:28] Validation | Batch 540/1463 | Loss: 0.8176 | LM_LOSS: 0.3113 | LB_LOSS: 1.0126 |
| [2026-05-24 00:57:30] Validation | Batch 550/1463 | Loss: 0.8173 | LM_LOSS: 0.3110 | LB_LOSS: 1.0126 |
| [2026-05-24 00:57:32] Validation | Batch 560/1463 | Loss: 0.8175 | LM_LOSS: 0.3112 | LB_LOSS: 1.0127 |
| [2026-05-24 00:57:35] Validation | Batch 570/1463 | Loss: 0.8175 | LM_LOSS: 0.3112 | LB_LOSS: 1.0127 |
| [2026-05-24 00:57:37] Validation | Batch 580/1463 | Loss: 0.8173 | LM_LOSS: 0.3110 | LB_LOSS: 1.0126 |
| [2026-05-24 00:57:40] Validation | Batch 590/1463 | Loss: 0.8171 | LM_LOSS: 0.3107 | LB_LOSS: 1.0127 |
| [2026-05-24 00:57:42] Validation | Batch 600/1463 | Loss: 0.8174 | LM_LOSS: 0.3110 | LB_LOSS: 1.0127 |
| [2026-05-24 00:57:44] Validation | Batch 610/1463 | Loss: 0.8175 | LM_LOSS: 0.3111 | LB_LOSS: 1.0127 |
| [2026-05-24 00:57:47] Validation | Batch 620/1463 | Loss: 0.8169 | LM_LOSS: 0.3106 | LB_LOSS: 1.0127 |
| [2026-05-24 00:57:49] Validation | Batch 630/1463 | Loss: 0.8164 | LM_LOSS: 0.3101 | LB_LOSS: 1.0127 |
| [2026-05-24 00:57:51] Validation | Batch 640/1463 | Loss: 0.8164 | LM_LOSS: 0.3100 | LB_LOSS: 1.0128 |
| [2026-05-24 00:57:53] Validation | Batch 650/1463 | Loss: 0.8158 | LM_LOSS: 0.3095 | LB_LOSS: 1.0128 |
| [2026-05-24 00:57:55] Validation | Batch 660/1463 | Loss: 0.8154 | LM_LOSS: 0.3090 | LB_LOSS: 1.0127 |
| [2026-05-24 00:57:57] Validation | Batch 670/1463 | Loss: 0.8151 | LM_LOSS: 0.3087 | LB_LOSS: 1.0127 |
| [2026-05-24 00:57:59] Validation | Batch 680/1463 | Loss: 0.8151 | LM_LOSS: 0.3087 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:01] Validation | Batch 690/1463 | Loss: 0.8154 | LM_LOSS: 0.3091 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:03] Validation | Batch 700/1463 | Loss: 0.8152 | LM_LOSS: 0.3089 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:05] Validation | Batch 710/1463 | Loss: 0.8157 | LM_LOSS: 0.3093 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:08] Validation | Batch 720/1463 | Loss: 0.8165 | LM_LOSS: 0.3101 | LB_LOSS: 1.0128 |
| [2026-05-24 00:58:10] Validation | Batch 730/1463 | Loss: 0.8163 | LM_LOSS: 0.3099 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:12] Validation | Batch 740/1463 | Loss: 0.8160 | LM_LOSS: 0.3096 | LB_LOSS: 1.0128 |
| [2026-05-24 00:58:13] Validation | Batch 750/1463 | Loss: 0.8159 | LM_LOSS: 0.3095 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:15] Validation | Batch 760/1463 | Loss: 0.8157 | LM_LOSS: 0.3094 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:17] Validation | Batch 770/1463 | Loss: 0.8156 | LM_LOSS: 0.3092 | LB_LOSS: 1.0128 |
| [2026-05-24 00:58:19] Validation | Batch 780/1463 | Loss: 0.8154 | LM_LOSS: 0.3090 | LB_LOSS: 1.0128 |
| [2026-05-24 00:58:21] Validation | Batch 790/1463 | Loss: 0.8157 | LM_LOSS: 0.3093 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:23] Validation | Batch 800/1463 | Loss: 0.8156 | LM_LOSS: 0.3092 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:25] Validation | Batch 810/1463 | Loss: 0.8152 | LM_LOSS: 0.3088 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:27] Validation | Batch 820/1463 | Loss: 0.8154 | LM_LOSS: 0.3091 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:29] Validation | Batch 830/1463 | Loss: 0.8157 | LM_LOSS: 0.3094 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:32] Validation | Batch 840/1463 | Loss: 0.8158 | LM_LOSS: 0.3094 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:34] Validation | Batch 850/1463 | Loss: 0.8160 | LM_LOSS: 0.3096 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:37] Validation | Batch 860/1463 | Loss: 0.8160 | LM_LOSS: 0.3097 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:39] Validation | Batch 870/1463 | Loss: 0.8160 | LM_LOSS: 0.3097 | LB_LOSS: 1.0128 |
| [2026-05-24 00:58:41] Validation | Batch 880/1463 | Loss: 0.8154 | LM_LOSS: 0.3090 | LB_LOSS: 1.0128 |
| [2026-05-24 00:58:43] Validation | Batch 890/1463 | Loss: 0.8154 | LM_LOSS: 0.3091 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:45] Validation | Batch 900/1463 | Loss: 0.8151 | LM_LOSS: 0.3088 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:47] Validation | Batch 910/1463 | Loss: 0.8150 | LM_LOSS: 0.3087 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:50] Validation | Batch 920/1463 | Loss: 0.8152 | LM_LOSS: 0.3088 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:52] Validation | Batch 930/1463 | Loss: 0.8149 | LM_LOSS: 0.3086 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:54] Validation | Batch 940/1463 | Loss: 0.8146 | LM_LOSS: 0.3083 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:57] Validation | Batch 950/1463 | Loss: 0.8149 | LM_LOSS: 0.3086 | LB_LOSS: 1.0127 |
| [2026-05-24 00:58:59] Validation | Batch 960/1463 | Loss: 0.8149 | LM_LOSS: 0.3086 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:01] Validation | Batch 970/1463 | Loss: 0.8150 | LM_LOSS: 0.3086 | LB_LOSS: 1.0126 |
| [2026-05-24 00:59:04] Validation | Batch 980/1463 | Loss: 0.8153 | LM_LOSS: 0.3090 | LB_LOSS: 1.0126 |
| [2026-05-24 00:59:06] Validation | Batch 990/1463 | Loss: 0.8155 | LM_LOSS: 0.3092 | LB_LOSS: 1.0126 |
| [2026-05-24 00:59:08] Validation | Batch 1000/1463 | Loss: 0.8161 | LM_LOSS: 0.3098 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:10] Validation | Batch 1010/1463 | Loss: 0.8161 | LM_LOSS: 0.3098 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:13] Validation | Batch 1020/1463 | Loss: 0.8162 | LM_LOSS: 0.3099 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:15] Validation | Batch 1030/1463 | Loss: 0.8166 | LM_LOSS: 0.3103 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:17] Validation | Batch 1040/1463 | Loss: 0.8162 | LM_LOSS: 0.3099 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:20] Validation | Batch 1050/1463 | Loss: 0.8161 | LM_LOSS: 0.3098 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:22] Validation | Batch 1060/1463 | Loss: 0.8161 | LM_LOSS: 0.3098 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:24] Validation | Batch 1070/1463 | Loss: 0.8161 | LM_LOSS: 0.3097 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:26] Validation | Batch 1080/1463 | Loss: 0.8159 | LM_LOSS: 0.3095 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:28] Validation | Batch 1090/1463 | Loss: 0.8159 | LM_LOSS: 0.3096 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:30] Validation | Batch 1100/1463 | Loss: 0.8158 | LM_LOSS: 0.3094 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:32] Validation | Batch 1110/1463 | Loss: 0.8157 | LM_LOSS: 0.3094 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:35] Validation | Batch 1120/1463 | Loss: 0.8156 | LM_LOSS: 0.3092 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:37] Validation | Batch 1130/1463 | Loss: 0.8154 | LM_LOSS: 0.3090 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:39] Validation | Batch 1140/1463 | Loss: 0.8156 | LM_LOSS: 0.3092 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:42] Validation | Batch 1150/1463 | Loss: 0.8155 | LM_LOSS: 0.3092 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:44] Validation | Batch 1160/1463 | Loss: 0.8154 | LM_LOSS: 0.3091 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:46] Validation | Batch 1170/1463 | Loss: 0.8154 | LM_LOSS: 0.3091 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:48] Validation | Batch 1180/1463 | Loss: 0.8155 | LM_LOSS: 0.3091 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:51] Validation | Batch 1190/1463 | Loss: 0.8156 | LM_LOSS: 0.3092 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:53] Validation | Batch 1200/1463 | Loss: 0.8156 | LM_LOSS: 0.3093 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:55] Validation | Batch 1210/1463 | Loss: 0.8158 | LM_LOSS: 0.3095 | LB_LOSS: 1.0127 |
| [2026-05-24 00:59:58] Validation | Batch 1220/1463 | Loss: 0.8162 | LM_LOSS: 0.3099 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:00] Validation | Batch 1230/1463 | Loss: 0.8162 | LM_LOSS: 0.3098 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:02] Validation | Batch 1240/1463 | Loss: 0.8165 | LM_LOSS: 0.3102 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:04] Validation | Batch 1250/1463 | Loss: 0.8167 | LM_LOSS: 0.3104 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:07] Validation | Batch 1260/1463 | Loss: 0.8167 | LM_LOSS: 0.3103 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:09] Validation | Batch 1270/1463 | Loss: 0.8165 | LM_LOSS: 0.3101 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:11] Validation | Batch 1280/1463 | Loss: 0.8163 | LM_LOSS: 0.3100 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:13] Validation | Batch 1290/1463 | Loss: 0.8163 | LM_LOSS: 0.3100 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:16] Validation | Batch 1300/1463 | Loss: 0.8161 | LM_LOSS: 0.3098 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:18] Validation | Batch 1310/1463 | Loss: 0.8160 | LM_LOSS: 0.3097 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:20] Validation | Batch 1320/1463 | Loss: 0.8161 | LM_LOSS: 0.3097 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:21] Validation | Batch 1330/1463 | Loss: 0.8161 | LM_LOSS: 0.3098 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:23] Validation | Batch 1340/1463 | Loss: 0.8164 | LM_LOSS: 0.3100 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:26] Validation | Batch 1350/1463 | Loss: 0.8164 | LM_LOSS: 0.3101 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:29] Validation | Batch 1360/1463 | Loss: 0.8167 | LM_LOSS: 0.3104 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:31] Validation | Batch 1370/1463 | Loss: 0.8170 | LM_LOSS: 0.3106 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:33] Validation | Batch 1380/1463 | Loss: 0.8167 | LM_LOSS: 0.3104 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:35] Validation | Batch 1390/1463 | Loss: 0.8167 | LM_LOSS: 0.3103 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:37] Validation | Batch 1400/1463 | Loss: 0.8169 | LM_LOSS: 0.3106 | LB_LOSS: 1.0126 |
| [2026-05-24 01:00:39] Validation | Batch 1410/1463 | Loss: 0.8171 | LM_LOSS: 0.3108 | LB_LOSS: 1.0126 |
| [2026-05-24 01:00:41] Validation | Batch 1420/1463 | Loss: 0.8171 | LM_LOSS: 0.3107 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:44] Validation | Batch 1430/1463 | Loss: 0.8171 | LM_LOSS: 0.3108 | LB_LOSS: 1.0126 |
| [2026-05-24 01:00:46] Validation | Batch 1440/1463 | Loss: 0.8175 | LM_LOSS: 0.3112 | LB_LOSS: 1.0127 |
| [2026-05-24 01:00:48] Validation | Batch 1450/1463 | Loss: 0.8172 | LM_LOSS: 0.3109 | LB_LOSS: 1.0126 |
| [2026-05-24 01:00:51] Validation | Batch 1460/1463 | Loss: 0.8175 | LM_LOSS: 0.3112 | LB_LOSS: 1.0126 |
| [2026-05-24 01:00:51] Validation | Batch 1463/1463 | Loss: 0.8174 | LM_LOSS: 0.3111 | LB_LOSS: 1.0126 |
| [2026-05-24 01:00:51] Validation | Loss: 0.8174 | LM_LOSS: 0.3111 | LB_LOSS: 1.0126 | PPL: 1.37 | Time: 323.38s |
| [2026-05-24 01:00:58] New best model saved! Val loss: 0.8174 |
| [2026-05-24 01:01:10] Epoch 1 | Step 2010 | Loss: 0.8466 | LM: 0.3256 | LB: 1.0516 | CL0: 2.9 | CL1: 3.0 | HR0: 0.347/SR0: 0.339 | HR1: 0.341/SR1: 0.306 | LR: 1.00e-04 |
| [2026-05-24 01:01:21] Epoch 1 | Step 2020 | Loss: 0.8466 | LM: 0.3257 | LB: 1.0514 | CL0: 2.9 | CL1: 3.0 | HR0: 0.347/SR0: 0.339 | HR1: 0.341/SR1: 0.306 | LR: 1.00e-04 |
| [2026-05-24 01:01:32] Epoch 1 | Step 2030 | Loss: 0.8462 | LM: 0.3253 | LB: 1.0512 | CL0: 2.9 | CL1: 3.0 | HR0: 0.346/SR0: 0.338 | HR1: 0.341/SR1: 0.305 | LR: 1.00e-04 |
| [2026-05-24 01:01:43] Epoch 1 | Step 2040 | Loss: 0.8461 | LM: 0.3257 | LB: 1.0510 | CL0: 2.9 | CL1: 3.0 | HR0: 0.346/SR0: 0.338 | HR1: 0.341/SR1: 0.305 | LR: 1.00e-04 |
| [2026-05-24 01:01:54] Epoch 1 | Step 2050 | Loss: 0.8461 | LM: 0.3253 | LB: 1.0508 | CL0: 2.9 | CL1: 3.0 | HR0: 0.346/SR0: 0.338 | HR1: 0.340/SR1: 0.305 | LR: 1.00e-04 |
| [2026-05-24 01:02:05] Epoch 1 | Step 2060 | Loss: 0.8459 | LM: 0.3255 | LB: 1.0506 | CL0: 2.9 | CL1: 3.0 | HR0: 0.346/SR0: 0.338 | HR1: 0.340/SR1: 0.304 | LR: 1.00e-04 |
| [2026-05-24 01:02:16] Epoch 1 | Step 2070 | Loss: 0.8457 | LM: 0.3257 | LB: 1.0505 | CL0: 2.9 | CL1: 3.1 | HR0: 0.346/SR0: 0.338 | HR1: 0.340/SR1: 0.304 | LR: 1.00e-04 |
| [2026-05-24 01:02:27] Epoch 1 | Step 2080 | Loss: 0.8457 | LM: 0.3259 | LB: 1.0503 | CL0: 2.9 | CL1: 3.1 | HR0: 0.346/SR0: 0.338 | HR1: 0.339/SR1: 0.304 | LR: 1.00e-04 |
| [2026-05-24 01:02:39] Epoch 1 | Step 2090 | Loss: 0.8453 | LM: 0.3254 | LB: 1.0501 | CL0: 2.9 | CL1: 3.1 | HR0: 0.346/SR0: 0.338 | HR1: 0.339/SR1: 0.303 | LR: 1.00e-04 |
| [2026-05-24 01:02:50] Epoch 1 | Step 2100 | Loss: 0.8452 | LM: 0.3255 | LB: 1.0500 | CL0: 2.9 | CL1: 3.1 | HR0: 0.346/SR0: 0.337 | HR1: 0.339/SR1: 0.303 | LR: 1.00e-04 |
| [2026-05-24 01:03:01] Epoch 1 | Step 2110 | Loss: 0.8450 | LM: 0.3255 | LB: 1.0498 | CL0: 2.9 | CL1: 3.1 | HR0: 0.346/SR0: 0.337 | HR1: 0.339/SR1: 0.303 | LR: 1.00e-04 |
| [2026-05-24 01:03:11] Epoch 1 | Step 2120 | Loss: 0.8448 | LM: 0.3252 | LB: 1.0496 | CL0: 2.9 | CL1: 3.1 | HR0: 0.346/SR0: 0.337 | HR1: 0.338/SR1: 0.303 | LR: 1.00e-04 |
| [2026-05-24 01:03:23] Epoch 1 | Step 2130 | Loss: 0.8448 | LM: 0.3253 | LB: 1.0495 | CL0: 2.9 | CL1: 3.1 | HR0: 0.346/SR0: 0.337 | HR1: 0.338/SR1: 0.302 | LR: 1.00e-04 |
| [2026-05-24 01:03:33] Epoch 1 | Step 2140 | Loss: 0.8444 | LM: 0.3251 | LB: 1.0493 | CL0: 2.9 | CL1: 3.1 | HR0: 0.345/SR0: 0.337 | HR1: 0.338/SR1: 0.302 | LR: 1.00e-04 |
| [2026-05-24 01:03:44] Epoch 1 | Step 2150 | Loss: 0.8443 | LM: 0.3250 | LB: 1.0492 | CL0: 2.9 | CL1: 3.1 | HR0: 0.345/SR0: 0.337 | HR1: 0.337/SR1: 0.302 | LR: 1.00e-04 |
| [2026-05-24 01:03:55] Epoch 1 | Step 2160 | Loss: 0.8442 | LM: 0.3249 | LB: 1.0490 | CL0: 2.9 | CL1: 3.1 | HR0: 0.345/SR0: 0.337 | HR1: 0.337/SR1: 0.301 | LR: 1.00e-04 |
| [2026-05-24 01:04:07] Epoch 1 | Step 2170 | Loss: 0.8441 | LM: 0.3249 | LB: 1.0489 | CL0: 2.9 | CL1: 3.1 | HR0: 0.345/SR0: 0.337 | HR1: 0.337/SR1: 0.301 | LR: 1.00e-04 |
| [2026-05-24 01:04:18] Epoch 1 | Step 2180 | Loss: 0.8438 | LM: 0.3247 | LB: 1.0487 | CL0: 2.9 | CL1: 3.1 | HR0: 0.345/SR0: 0.337 | HR1: 0.337/SR1: 0.301 | LR: 1.00e-04 |
| [2026-05-24 01:04:30] Epoch 1 | Step 2190 | Loss: 0.8438 | LM: 0.3247 | LB: 1.0485 | CL0: 2.9 | CL1: 3.1 | HR0: 0.345/SR0: 0.336 | HR1: 0.336/SR1: 0.300 | LR: 1.00e-04 |
| [2026-05-24 01:04:42] Epoch 1 | Step 2200 | Loss: 0.8436 | LM: 0.3245 | LB: 1.0484 | CL0: 2.9 | CL1: 3.1 | HR0: 0.345/SR0: 0.336 | HR1: 0.336/SR1: 0.300 | LR: 1.00e-04 |
| [2026-05-24 01:04:53] Epoch 1 | Step 2210 | Loss: 0.8435 | LM: 0.3245 | LB: 1.0482 | CL0: 2.9 | CL1: 3.1 | HR0: 0.345/SR0: 0.336 | HR1: 0.336/SR1: 0.300 | LR: 1.00e-04 |
| [2026-05-24 01:05:04] Epoch 1 | Step 2220 | Loss: 0.8433 | LM: 0.3246 | LB: 1.0480 | CL0: 2.9 | CL1: 3.1 | HR0: 0.345/SR0: 0.336 | HR1: 0.336/SR1: 0.300 | LR: 1.00e-04 |
| [2026-05-24 01:05:16] Epoch 1 | Step 2230 | Loss: 0.8433 | LM: 0.3246 | LB: 1.0479 | CL0: 2.9 | CL1: 3.1 | HR0: 0.345/SR0: 0.336 | HR1: 0.335/SR1: 0.299 | LR: 1.00e-04 |
| [2026-05-24 01:05:28] Epoch 1 | Step 2240 | Loss: 0.8431 | LM: 0.3243 | LB: 1.0478 | CL0: 2.9 | CL1: 3.1 | HR0: 0.345/SR0: 0.336 | HR1: 0.335/SR1: 0.299 | LR: 1.00e-04 |
| [2026-05-24 01:05:40] Epoch 1 | Step 2250 | Loss: 0.8431 | LM: 0.3243 | LB: 1.0476 | CL0: 2.9 | CL1: 3.1 | HR0: 0.345/SR0: 0.336 | HR1: 0.335/SR1: 0.299 | LR: 1.00e-04 |
| [2026-05-24 01:05:52] Epoch 1 | Step 2260 | Loss: 0.8429 | LM: 0.3244 | LB: 1.0474 | CL0: 2.9 | CL1: 3.1 | HR0: 0.345/SR0: 0.336 | HR1: 0.335/SR1: 0.298 | LR: 1.00e-04 |
| [2026-05-24 01:06:03] Epoch 1 | Step 2270 | Loss: 0.8428 | LM: 0.3242 | LB: 1.0473 | CL0: 2.9 | CL1: 3.1 | HR0: 0.344/SR0: 0.336 | HR1: 0.334/SR1: 0.298 | LR: 1.00e-04 |
| [2026-05-24 01:06:14] Epoch 1 | Step 2280 | Loss: 0.8428 | LM: 0.3244 | LB: 1.0472 | CL0: 2.9 | CL1: 3.1 | HR0: 0.344/SR0: 0.336 | HR1: 0.334/SR1: 0.298 | LR: 1.00e-04 |
| [2026-05-24 01:06:25] Epoch 1 | Step 2290 | Loss: 0.8427 | LM: 0.3244 | LB: 1.0470 | CL0: 2.9 | CL1: 3.1 | HR0: 0.344/SR0: 0.335 | HR1: 0.334/SR1: 0.298 | LR: 1.00e-04 |
| [2026-05-24 01:06:37] Epoch 1 | Step 2300 | Loss: 0.8427 | LM: 0.3243 | LB: 1.0469 | CL0: 2.9 | CL1: 3.1 | HR0: 0.344/SR0: 0.335 | HR1: 0.334/SR1: 0.297 | LR: 1.00e-04 |
| [2026-05-24 01:06:48] Epoch 1 | Step 2310 | Loss: 0.8426 | LM: 0.3242 | LB: 1.0467 | CL0: 2.9 | CL1: 3.1 | HR0: 0.344/SR0: 0.335 | HR1: 0.333/SR1: 0.297 | LR: 1.00e-04 |
| [2026-05-24 01:07:00] Epoch 1 | Step 2320 | Loss: 0.8425 | LM: 0.3240 | LB: 1.0466 | CL0: 2.9 | CL1: 3.1 | HR0: 0.344/SR0: 0.335 | HR1: 0.333/SR1: 0.297 | LR: 1.00e-04 |
| [2026-05-24 01:07:11] Epoch 1 | Step 2330 | Loss: 0.8424 | LM: 0.3237 | LB: 1.0464 | CL0: 2.9 | CL1: 3.1 | HR0: 0.344/SR0: 0.335 | HR1: 0.333/SR1: 0.296 | LR: 1.00e-04 |
| [2026-05-24 01:07:22] Epoch 1 | Step 2340 | Loss: 0.8423 | LM: 0.3238 | LB: 1.0463 | CL0: 2.9 | CL1: 3.1 | HR0: 0.344/SR0: 0.335 | HR1: 0.333/SR1: 0.296 | LR: 1.00e-04 |
| [2026-05-24 01:07:33] Epoch 1 | Step 2350 | Loss: 0.8422 | LM: 0.3235 | LB: 1.0462 | CL0: 2.9 | CL1: 3.1 | HR0: 0.344/SR0: 0.335 | HR1: 0.332/SR1: 0.296 | LR: 1.00e-04 |
| [2026-05-24 01:07:45] Epoch 1 | Step 2360 | Loss: 0.8422 | LM: 0.3234 | LB: 1.0460 | CL0: 2.9 | CL1: 3.1 | HR0: 0.344/SR0: 0.335 | HR1: 0.332/SR1: 0.296 | LR: 1.00e-04 |
| [2026-05-24 01:07:56] Epoch 1 | Step 2370 | Loss: 0.8419 | LM: 0.3232 | LB: 1.0459 | CL0: 2.9 | CL1: 3.1 | HR0: 0.344/SR0: 0.335 | HR1: 0.332/SR1: 0.296 | LR: 1.00e-04 |
| [2026-05-24 01:08:08] Epoch 1 | Step 2380 | Loss: 0.8419 | LM: 0.3232 | LB: 1.0458 | CL0: 2.9 | CL1: 3.1 | HR0: 0.344/SR0: 0.335 | HR1: 0.332/SR1: 0.295 | LR: 1.00e-04 |
| [2026-05-24 01:08:19] Epoch 1 | Step 2390 | Loss: 0.8417 | LM: 0.3231 | LB: 1.0456 | CL0: 2.9 | CL1: 3.1 | HR0: 0.344/SR0: 0.334 | HR1: 0.332/SR1: 0.295 | LR: 1.00e-04 |
| [2026-05-24 01:08:30] Epoch 1 | Step 2400 | Loss: 0.8416 | LM: 0.3229 | LB: 1.0455 | CL0: 2.9 | CL1: 3.1 | HR0: 0.344/SR0: 0.334 | HR1: 0.331/SR1: 0.295 | LR: 1.00e-04 |
| [2026-05-24 01:08:42] Epoch 1 | Step 2410 | Loss: 0.8414 | LM: 0.3230 | LB: 1.0454 | CL0: 2.9 | CL1: 3.1 | HR0: 0.343/SR0: 0.334 | HR1: 0.331/SR1: 0.295 | LR: 1.00e-04 |
| [2026-05-24 01:08:53] Epoch 1 | Step 2420 | Loss: 0.8413 | LM: 0.3228 | LB: 1.0452 | CL0: 2.9 | CL1: 3.1 | HR0: 0.343/SR0: 0.334 | HR1: 0.331/SR1: 0.294 | LR: 1.00e-04 |
| [2026-05-24 01:09:04] Epoch 1 | Step 2430 | Loss: 0.8412 | LM: 0.3229 | LB: 1.0451 | CL0: 2.9 | CL1: 3.1 | HR0: 0.343/SR0: 0.334 | HR1: 0.331/SR1: 0.294 | LR: 1.00e-04 |
| [2026-05-24 01:09:15] Epoch 1 | Step 2440 | Loss: 0.8412 | LM: 0.3227 | LB: 1.0450 | CL0: 2.9 | CL1: 3.1 | HR0: 0.343/SR0: 0.334 | HR1: 0.330/SR1: 0.294 | LR: 1.00e-04 |
| [2026-05-24 01:09:27] Epoch 1 | Step 2450 | Loss: 0.8411 | LM: 0.3226 | LB: 1.0448 | CL0: 2.9 | CL1: 3.1 | HR0: 0.343/SR0: 0.334 | HR1: 0.330/SR1: 0.294 | LR: 1.00e-04 |
| [2026-05-24 01:09:37] Epoch 1 | Step 2460 | Loss: 0.8408 | LM: 0.3224 | LB: 1.0447 | CL0: 2.9 | CL1: 3.1 | HR0: 0.343/SR0: 0.334 | HR1: 0.330/SR1: 0.293 | LR: 1.00e-04 |
| [2026-05-24 01:09:48] Epoch 1 | Step 2470 | Loss: 0.8405 | LM: 0.3220 | LB: 1.0446 | CL0: 2.9 | CL1: 3.1 | HR0: 0.343/SR0: 0.334 | HR1: 0.330/SR1: 0.293 | LR: 1.00e-04 |
| [2026-05-24 01:10:00] Epoch 1 | Step 2480 | Loss: 0.8405 | LM: 0.3222 | LB: 1.0444 | CL0: 2.9 | CL1: 3.1 | HR0: 0.343/SR0: 0.334 | HR1: 0.330/SR1: 0.293 | LR: 1.00e-04 |
| [2026-05-24 01:10:11] Epoch 1 | Step 2490 | Loss: 0.8404 | LM: 0.3222 | LB: 1.0443 | CL0: 2.9 | CL1: 3.1 | HR0: 0.343/SR0: 0.334 | HR1: 0.329/SR1: 0.293 | LR: 1.00e-04 |
| [2026-05-24 01:10:23] Epoch 1 | Step 2500 | Loss: 0.8402 | LM: 0.3219 | LB: 1.0442 | CL0: 2.9 | CL1: 3.1 | HR0: 0.343/SR0: 0.333 | HR1: 0.329/SR1: 0.293 | LR: 1.00e-04 |
| [2026-05-24 01:10:34] Epoch 1 | Step 2510 | Loss: 0.8401 | LM: 0.3219 | LB: 1.0441 | CL0: 2.9 | CL1: 3.1 | HR0: 0.343/SR0: 0.333 | HR1: 0.329/SR1: 0.292 | LR: 1.00e-04 |
| [2026-05-24 01:10:46] Epoch 1 | Step 2520 | Loss: 0.8401 | LM: 0.3219 | LB: 1.0439 | CL0: 2.9 | CL1: 3.2 | HR0: 0.343/SR0: 0.333 | HR1: 0.329/SR1: 0.292 | LR: 1.00e-04 |
| [2026-05-24 01:10:58] Epoch 1 | Step 2530 | Loss: 0.8400 | LM: 0.3218 | LB: 1.0438 | CL0: 2.9 | CL1: 3.2 | HR0: 0.343/SR0: 0.333 | HR1: 0.329/SR1: 0.292 | LR: 1.00e-04 |
| [2026-05-24 01:11:09] Epoch 1 | Step 2540 | Loss: 0.8400 | LM: 0.3219 | LB: 1.0437 | CL0: 2.9 | CL1: 3.2 | HR0: 0.343/SR0: 0.333 | HR1: 0.328/SR1: 0.292 | LR: 1.00e-04 |
| [2026-05-24 01:11:20] Epoch 1 | Step 2550 | Loss: 0.8399 | LM: 0.3219 | LB: 1.0435 | CL0: 2.9 | CL1: 3.2 | HR0: 0.342/SR0: 0.333 | HR1: 0.328/SR1: 0.291 | LR: 1.00e-04 |
| [2026-05-24 01:11:31] Epoch 1 | Step 2560 | Loss: 0.8398 | LM: 0.3220 | LB: 1.0434 | CL0: 2.9 | CL1: 3.2 | HR0: 0.342/SR0: 0.333 | HR1: 0.328/SR1: 0.291 | LR: 1.00e-04 |
| [2026-05-24 01:11:42] Epoch 1 | Step 2570 | Loss: 0.8398 | LM: 0.3218 | LB: 1.0433 | CL0: 2.9 | CL1: 3.2 | HR0: 0.342/SR0: 0.333 | HR1: 0.328/SR1: 0.291 | LR: 1.00e-04 |
| [2026-05-24 01:11:53] Epoch 1 | Step 2580 | Loss: 0.8397 | LM: 0.3219 | LB: 1.0432 | CL0: 2.9 | CL1: 3.2 | HR0: 0.342/SR0: 0.333 | HR1: 0.328/SR1: 0.291 | LR: 1.00e-04 |
| [2026-05-24 01:12:04] Epoch 1 | Step 2590 | Loss: 0.8397 | LM: 0.3220 | LB: 1.0431 | CL0: 2.9 | CL1: 3.2 | HR0: 0.342/SR0: 0.332 | HR1: 0.327/SR1: 0.291 | LR: 1.00e-04 |
| [2026-05-24 01:12:15] Epoch 1 | Step 2600 | Loss: 0.8395 | LM: 0.3218 | LB: 1.0429 | CL0: 2.9 | CL1: 3.2 | HR0: 0.342/SR0: 0.332 | HR1: 0.327/SR1: 0.290 | LR: 1.00e-04 |
| [2026-05-24 01:12:26] Epoch 1 | Step 2610 | Loss: 0.8393 | LM: 0.3215 | LB: 1.0428 | CL0: 2.9 | CL1: 3.2 | HR0: 0.342/SR0: 0.332 | HR1: 0.327/SR1: 0.290 | LR: 1.00e-04 |
| [2026-05-24 01:12:37] Epoch 1 | Step 2620 | Loss: 0.8390 | LM: 0.3212 | LB: 1.0427 | CL0: 2.9 | CL1: 3.2 | HR0: 0.342/SR0: 0.332 | HR1: 0.327/SR1: 0.290 | LR: 1.00e-04 |
| [2026-05-24 01:12:48] Epoch 1 | Step 2630 | Loss: 0.8390 | LM: 0.3213 | LB: 1.0426 | CL0: 2.9 | CL1: 3.2 | HR0: 0.342/SR0: 0.332 | HR1: 0.327/SR1: 0.290 | LR: 1.00e-04 |
| [2026-05-24 01:13:00] Epoch 1 | Step 2640 | Loss: 0.8389 | LM: 0.3211 | LB: 1.0425 | CL0: 2.9 | CL1: 3.2 | HR0: 0.342/SR0: 0.332 | HR1: 0.327/SR1: 0.290 | LR: 1.00e-04 |
| [2026-05-24 01:13:11] Epoch 1 | Step 2650 | Loss: 0.8389 | LM: 0.3213 | LB: 1.0423 | CL0: 2.9 | CL1: 3.2 | HR0: 0.342/SR0: 0.332 | HR1: 0.326/SR1: 0.289 | LR: 1.00e-04 |
| [2026-05-24 01:13:22] Epoch 1 | Step 2660 | Loss: 0.8389 | LM: 0.3212 | LB: 1.0422 | CL0: 2.9 | CL1: 3.2 | HR0: 0.342/SR0: 0.332 | HR1: 0.326/SR1: 0.289 | LR: 1.00e-04 |
| [2026-05-24 01:13:33] Epoch 1 | Step 2670 | Loss: 0.8388 | LM: 0.3213 | LB: 1.0421 | CL0: 2.9 | CL1: 3.2 | HR0: 0.342/SR0: 0.332 | HR1: 0.326/SR1: 0.289 | LR: 1.00e-04 |
| [2026-05-24 01:13:45] Epoch 1 | Step 2680 | Loss: 0.8387 | LM: 0.3213 | LB: 1.0420 | CL0: 2.9 | CL1: 3.2 | HR0: 0.341/SR0: 0.331 | HR1: 0.326/SR1: 0.289 | LR: 1.00e-04 |
| [2026-05-24 01:13:56] Epoch 1 | Step 2690 | Loss: 0.8386 | LM: 0.3215 | LB: 1.0419 | CL0: 2.9 | CL1: 3.2 | HR0: 0.341/SR0: 0.331 | HR1: 0.326/SR1: 0.289 | LR: 1.00e-04 |
| [2026-05-24 01:14:07] Epoch 1 | Step 2700 | Loss: 0.8384 | LM: 0.3212 | LB: 1.0418 | CL0: 2.9 | CL1: 3.2 | HR0: 0.341/SR0: 0.331 | HR1: 0.326/SR1: 0.289 | LR: 1.00e-04 |
| [2026-05-24 01:14:17] Epoch 1 | Step 2710 | Loss: 0.8382 | LM: 0.3212 | LB: 1.0417 | CL0: 2.9 | CL1: 3.2 | HR0: 0.341/SR0: 0.331 | HR1: 0.325/SR1: 0.288 | LR: 1.00e-04 |
| [2026-05-24 01:14:28] Epoch 1 | Step 2720 | Loss: 0.8380 | LM: 0.3210 | LB: 1.0416 | CL0: 2.9 | CL1: 3.2 | HR0: 0.341/SR0: 0.331 | HR1: 0.325/SR1: 0.288 | LR: 1.00e-04 |
| [2026-05-24 01:14:39] Epoch 1 | Step 2730 | Loss: 0.8380 | LM: 0.3210 | LB: 1.0415 | CL0: 2.9 | CL1: 3.2 | HR0: 0.341/SR0: 0.331 | HR1: 0.325/SR1: 0.288 | LR: 1.00e-04 |
| [2026-05-24 01:14:50] Epoch 1 | Step 2740 | Loss: 0.8378 | LM: 0.3210 | LB: 1.0414 | CL0: 2.9 | CL1: 3.2 | HR0: 0.341/SR0: 0.331 | HR1: 0.325/SR1: 0.288 | LR: 1.00e-04 |
| [2026-05-24 01:15:01] Epoch 1 | Step 2750 | Loss: 0.8377 | LM: 0.3208 | LB: 1.0413 | CL0: 3.0 | CL1: 3.2 | HR0: 0.341/SR0: 0.331 | HR1: 0.325/SR1: 0.288 | LR: 1.00e-04 |
| [2026-05-24 01:15:12] Epoch 1 | Step 2760 | Loss: 0.8376 | LM: 0.3206 | LB: 1.0411 | CL0: 3.0 | CL1: 3.2 | HR0: 0.341/SR0: 0.331 | HR1: 0.325/SR1: 0.287 | LR: 1.00e-04 |
| [2026-05-24 01:15:24] Epoch 1 | Step 2770 | Loss: 0.8375 | LM: 0.3205 | LB: 1.0410 | CL0: 3.0 | CL1: 3.2 | HR0: 0.341/SR0: 0.331 | HR1: 0.324/SR1: 0.287 | LR: 1.00e-04 |
| [2026-05-24 01:15:35] Epoch 1 | Step 2780 | Loss: 0.8375 | LM: 0.3206 | LB: 1.0409 | CL0: 3.0 | CL1: 3.2 | HR0: 0.341/SR0: 0.331 | HR1: 0.324/SR1: 0.287 | LR: 1.00e-04 |
| [2026-05-24 01:15:46] Epoch 1 | Step 2790 | Loss: 0.8374 | LM: 0.3205 | LB: 1.0408 | CL0: 3.0 | CL1: 3.2 | HR0: 0.341/SR0: 0.330 | HR1: 0.324/SR1: 0.287 | LR: 1.00e-04 |
| [2026-05-24 01:15:57] Epoch 1 | Step 2800 | Loss: 0.8374 | LM: 0.3207 | LB: 1.0407 | CL0: 3.0 | CL1: 3.2 | HR0: 0.341/SR0: 0.330 | HR1: 0.324/SR1: 0.287 | LR: 1.00e-04 |
| [2026-05-24 01:16:08] Epoch 1 | Step 2810 | Loss: 0.8373 | LM: 0.3205 | LB: 1.0406 | CL0: 3.0 | CL1: 3.2 | HR0: 0.341/SR0: 0.330 | HR1: 0.324/SR1: 0.286 | LR: 1.00e-04 |
| [2026-05-24 01:16:18] Epoch 1 | Step 2820 | Loss: 0.8372 | LM: 0.3204 | LB: 1.0405 | CL0: 3.0 | CL1: 3.2 | HR0: 0.340/SR0: 0.330 | HR1: 0.324/SR1: 0.286 | LR: 1.00e-04 |
| [2026-05-24 01:16:30] Epoch 1 | Step 2830 | Loss: 0.8372 | LM: 0.3204 | LB: 1.0404 | CL0: 3.0 | CL1: 3.2 | HR0: 0.340/SR0: 0.330 | HR1: 0.323/SR1: 0.286 | LR: 1.00e-04 |
| [2026-05-24 01:16:41] Epoch 1 | Step 2840 | Loss: 0.8371 | LM: 0.3203 | LB: 1.0403 | CL0: 3.0 | CL1: 3.2 | HR0: 0.340/SR0: 0.330 | HR1: 0.323/SR1: 0.286 | LR: 1.00e-04 |
| [2026-05-24 01:16:52] Epoch 1 | Step 2850 | Loss: 0.8370 | LM: 0.3204 | LB: 1.0402 | CL0: 3.0 | CL1: 3.2 | HR0: 0.340/SR0: 0.330 | HR1: 0.323/SR1: 0.286 | LR: 1.00e-04 |
| [2026-05-24 01:17:04] Epoch 1 | Step 2860 | Loss: 0.8369 | LM: 0.3203 | LB: 1.0401 | CL0: 3.0 | CL1: 3.2 | HR0: 0.340/SR0: 0.330 | HR1: 0.323/SR1: 0.286 | LR: 1.00e-04 |
| [2026-05-24 01:17:15] Epoch 1 | Step 2870 | Loss: 0.8368 | LM: 0.3201 | LB: 1.0400 | CL0: 3.0 | CL1: 3.2 | HR0: 0.340/SR0: 0.330 | HR1: 0.323/SR1: 0.285 | LR: 1.00e-04 |
| [2026-05-24 01:17:26] Epoch 1 | Step 2880 | Loss: 0.8368 | LM: 0.3204 | LB: 1.0399 | CL0: 3.0 | CL1: 3.2 | HR0: 0.340/SR0: 0.330 | HR1: 0.323/SR1: 0.285 | LR: 1.00e-04 |
| [2026-05-24 01:17:37] Epoch 1 | Step 2890 | Loss: 0.8366 | LM: 0.3203 | LB: 1.0398 | CL0: 3.0 | CL1: 3.2 | HR0: 0.340/SR0: 0.330 | HR1: 0.323/SR1: 0.285 | LR: 1.00e-04 |
| [2026-05-24 01:17:48] Epoch 1 | Step 2900 | Loss: 0.8365 | LM: 0.3201 | LB: 1.0397 | CL0: 3.0 | CL1: 3.2 | HR0: 0.340/SR0: 0.330 | HR1: 0.322/SR1: 0.285 | LR: 1.00e-04 |
| [2026-05-24 01:18:00] Epoch 1 | Step 2910 | Loss: 0.8364 | LM: 0.3200 | LB: 1.0396 | CL0: 3.0 | CL1: 3.2 | HR0: 0.340/SR0: 0.329 | HR1: 0.322/SR1: 0.285 | LR: 1.00e-04 |
| [2026-05-24 01:18:11] Epoch 1 | Step 2920 | Loss: 0.8363 | LM: 0.3200 | LB: 1.0395 | CL0: 3.0 | CL1: 3.2 | HR0: 0.340/SR0: 0.329 | HR1: 0.322/SR1: 0.285 | LR: 1.00e-04 |
| [2026-05-24 01:18:22] Epoch 1 | Step 2930 | Loss: 0.8362 | LM: 0.3198 | LB: 1.0394 | CL0: 3.0 | CL1: 3.2 | HR0: 0.340/SR0: 0.329 | HR1: 0.322/SR1: 0.285 | LR: 1.00e-04 |
| [2026-05-24 01:18:33] Epoch 1 | Step 2940 | Loss: 0.8362 | LM: 0.3198 | LB: 1.0393 | CL0: 3.0 | CL1: 3.2 | HR0: 0.340/SR0: 0.329 | HR1: 0.322/SR1: 0.284 | LR: 1.00e-04 |
| [2026-05-24 01:18:44] Epoch 1 | Step 2950 | Loss: 0.8361 | LM: 0.3196 | LB: 1.0392 | CL0: 3.0 | CL1: 3.2 | HR0: 0.340/SR0: 0.329 | HR1: 0.322/SR1: 0.284 | LR: 1.00e-04 |
| [2026-05-24 01:18:55] Epoch 1 | Step 2960 | Loss: 0.8360 | LM: 0.3195 | LB: 1.0391 | CL0: 3.0 | CL1: 3.2 | HR0: 0.339/SR0: 0.329 | HR1: 0.321/SR1: 0.284 | LR: 1.00e-04 |
| [2026-05-24 01:19:06] Epoch 1 | Step 2970 | Loss: 0.8358 | LM: 0.3193 | LB: 1.0390 | CL0: 3.0 | CL1: 3.2 | HR0: 0.339/SR0: 0.329 | HR1: 0.321/SR1: 0.284 | LR: 1.00e-04 |
| [2026-05-24 01:19:18] Epoch 1 | Step 2980 | Loss: 0.8357 | LM: 0.3194 | LB: 1.0389 | CL0: 3.0 | CL1: 3.2 | HR0: 0.339/SR0: 0.329 | HR1: 0.321/SR1: 0.284 | LR: 1.00e-04 |
| [2026-05-24 01:19:28] Epoch 1 | Step 2990 | Loss: 0.8356 | LM: 0.3193 | LB: 1.0388 | CL0: 3.0 | CL1: 3.2 | HR0: 0.339/SR0: 0.329 | HR1: 0.321/SR1: 0.283 | LR: 1.00e-04 |
| [2026-05-24 01:19:39] Epoch 1 | Step 3000 | Loss: 0.8355 | LM: 0.3193 | LB: 1.0387 | CL0: 3.0 | CL1: 3.2 | HR0: 0.339/SR0: 0.329 | HR1: 0.321/SR1: 0.283 | LR: 1.00e-04 |
| [2026-05-24 01:19:43] Checkpoint saved: outputs/2026-05-24/N_4.0/checkpoints/checkpoint_step_3000.pt |
| [2026-05-24 01:19:49] Validation | Batch 10/1463 | Loss: 0.7772 | LM_LOSS: 0.2738 | LB_LOSS: 1.0068 |
| [2026-05-24 01:19:51] Validation | Batch 20/1463 | Loss: 0.7893 | LM_LOSS: 0.2850 | LB_LOSS: 1.0085 |
| [2026-05-24 01:19:54] Validation | Batch 30/1463 | Loss: 0.7946 | LM_LOSS: 0.2902 | LB_LOSS: 1.0089 |
| [2026-05-24 01:19:56] Validation | Batch 40/1463 | Loss: 0.8026 | LM_LOSS: 0.2978 | LB_LOSS: 1.0097 |
| [2026-05-24 01:19:58] Validation | Batch 50/1463 | Loss: 0.8098 | LM_LOSS: 0.3052 | LB_LOSS: 1.0092 |
| [2026-05-24 01:20:01] Validation | Batch 60/1463 | Loss: 0.8087 | LM_LOSS: 0.3042 | LB_LOSS: 1.0091 |
| [2026-05-24 01:20:03] Validation | Batch 70/1463 | Loss: 0.8086 | LM_LOSS: 0.3041 | LB_LOSS: 1.0091 |
| [2026-05-24 01:20:06] Validation | Batch 80/1463 | Loss: 0.8099 | LM_LOSS: 0.3053 | LB_LOSS: 1.0092 |
| [2026-05-24 01:20:08] Validation | Batch 90/1463 | Loss: 0.8093 | LM_LOSS: 0.3048 | LB_LOSS: 1.0091 |
| [2026-05-24 01:20:10] Validation | Batch 100/1463 | Loss: 0.8096 | LM_LOSS: 0.3050 | LB_LOSS: 1.0091 |
| [2026-05-24 01:20:12] Validation | Batch 110/1463 | Loss: 0.8088 | LM_LOSS: 0.3042 | LB_LOSS: 1.0093 |
| [2026-05-24 01:20:14] Validation | Batch 120/1463 | Loss: 0.8106 | LM_LOSS: 0.3060 | LB_LOSS: 1.0094 |
| [2026-05-24 01:20:16] Validation | Batch 130/1463 | Loss: 0.8125 | LM_LOSS: 0.3078 | LB_LOSS: 1.0094 |
| [2026-05-24 01:20:18] Validation | Batch 140/1463 | Loss: 0.8135 | LM_LOSS: 0.3088 | LB_LOSS: 1.0094 |
| [2026-05-24 01:20:21] Validation | Batch 150/1463 | Loss: 0.8117 | LM_LOSS: 0.3069 | LB_LOSS: 1.0095 |
| [2026-05-24 01:20:23] Validation | Batch 160/1463 | Loss: 0.8119 | LM_LOSS: 0.3072 | LB_LOSS: 1.0094 |
| [2026-05-24 01:20:25] Validation | Batch 170/1463 | Loss: 0.8114 | LM_LOSS: 0.3067 | LB_LOSS: 1.0094 |
| [2026-05-24 01:20:28] Validation | Batch 180/1463 | Loss: 0.8122 | LM_LOSS: 0.3075 | LB_LOSS: 1.0094 |
| [2026-05-24 01:20:30] Validation | Batch 190/1463 | Loss: 0.8133 | LM_LOSS: 0.3085 | LB_LOSS: 1.0094 |
| [2026-05-24 01:20:32] Validation | Batch 200/1463 | Loss: 0.8133 | LM_LOSS: 0.3086 | LB_LOSS: 1.0094 |
| [2026-05-24 01:20:34] Validation | Batch 210/1463 | Loss: 0.8138 | LM_LOSS: 0.3091 | LB_LOSS: 1.0094 |
| [2026-05-24 01:20:37] Validation | Batch 220/1463 | Loss: 0.8130 | LM_LOSS: 0.3082 | LB_LOSS: 1.0094 |
| [2026-05-24 01:20:39] Validation | Batch 230/1463 | Loss: 0.8144 | LM_LOSS: 0.3097 | LB_LOSS: 1.0094 |
| [2026-05-24 01:20:41] Validation | Batch 240/1463 | Loss: 0.8157 | LM_LOSS: 0.3111 | LB_LOSS: 1.0094 |
| [2026-05-24 01:20:44] Validation | Batch 250/1463 | Loss: 0.8149 | LM_LOSS: 0.3102 | LB_LOSS: 1.0094 |
| [2026-05-24 01:20:46] Validation | Batch 260/1463 | Loss: 0.8163 | LM_LOSS: 0.3116 | LB_LOSS: 1.0095 |
| [2026-05-24 01:20:48] Validation | Batch 270/1463 | Loss: 0.8150 | LM_LOSS: 0.3102 | LB_LOSS: 1.0095 |
| [2026-05-24 01:20:50] Validation | Batch 280/1463 | Loss: 0.8156 | LM_LOSS: 0.3108 | LB_LOSS: 1.0096 |
| [2026-05-24 01:20:53] Validation | Batch 290/1463 | Loss: 0.8149 | LM_LOSS: 0.3101 | LB_LOSS: 1.0096 |
| [2026-05-24 01:20:55] Validation | Batch 300/1463 | Loss: 0.8151 | LM_LOSS: 0.3103 | LB_LOSS: 1.0097 |
| [2026-05-24 01:20:57] Validation | Batch 310/1463 | Loss: 0.8161 | LM_LOSS: 0.3113 | LB_LOSS: 1.0096 |
| [2026-05-24 01:20:59] Validation | Batch 320/1463 | Loss: 0.8147 | LM_LOSS: 0.3099 | LB_LOSS: 1.0095 |
| [2026-05-24 01:21:01] Validation | Batch 330/1463 | Loss: 0.8146 | LM_LOSS: 0.3098 | LB_LOSS: 1.0095 |
| [2026-05-24 01:21:03] Validation | Batch 340/1463 | Loss: 0.8142 | LM_LOSS: 0.3095 | LB_LOSS: 1.0095 |
| [2026-05-24 01:21:06] Validation | Batch 350/1463 | Loss: 0.8148 | LM_LOSS: 0.3101 | LB_LOSS: 1.0095 |
| [2026-05-24 01:21:08] Validation | Batch 360/1463 | Loss: 0.8145 | LM_LOSS: 0.3098 | LB_LOSS: 1.0095 |
| [2026-05-24 01:21:09] Validation | Batch 370/1463 | Loss: 0.8142 | LM_LOSS: 0.3094 | LB_LOSS: 1.0096 |
| [2026-05-24 01:21:12] Validation | Batch 380/1463 | Loss: 0.8141 | LM_LOSS: 0.3094 | LB_LOSS: 1.0095 |
| [2026-05-24 01:21:14] Validation | Batch 390/1463 | Loss: 0.8148 | LM_LOSS: 0.3100 | LB_LOSS: 1.0095 |
| [2026-05-24 01:21:16] Validation | Batch 400/1463 | Loss: 0.8147 | LM_LOSS: 0.3100 | LB_LOSS: 1.0095 |
| [2026-05-24 01:21:18] Validation | Batch 410/1463 | Loss: 0.8145 | LM_LOSS: 0.3097 | LB_LOSS: 1.0096 |
| [2026-05-24 01:21:20] Validation | Batch 420/1463 | Loss: 0.8146 | LM_LOSS: 0.3098 | LB_LOSS: 1.0096 |
| [2026-05-24 01:21:23] Validation | Batch 430/1463 | Loss: 0.8140 | LM_LOSS: 0.3092 | LB_LOSS: 1.0096 |
| [2026-05-24 01:21:25] Validation | Batch 440/1463 | Loss: 0.8142 | LM_LOSS: 0.3094 | LB_LOSS: 1.0096 |
| [2026-05-24 01:21:27] Validation | Batch 450/1463 | Loss: 0.8140 | LM_LOSS: 0.3092 | LB_LOSS: 1.0097 |
| [2026-05-24 01:21:29] Validation | Batch 460/1463 | Loss: 0.8140 | LM_LOSS: 0.3092 | LB_LOSS: 1.0096 |
| [2026-05-24 01:21:32] Validation | Batch 470/1463 | Loss: 0.8147 | LM_LOSS: 0.3099 | LB_LOSS: 1.0096 |
| [2026-05-24 01:21:34] Validation | Batch 480/1463 | Loss: 0.8146 | LM_LOSS: 0.3098 | LB_LOSS: 1.0096 |
| [2026-05-24 01:21:36] Validation | Batch 490/1463 | Loss: 0.8145 | LM_LOSS: 0.3097 | LB_LOSS: 1.0096 |
| [2026-05-24 01:21:39] Validation | Batch 500/1463 | Loss: 0.8143 | LM_LOSS: 0.3095 | LB_LOSS: 1.0095 |
| [2026-05-24 01:21:41] Validation | Batch 510/1463 | Loss: 0.8138 | LM_LOSS: 0.3090 | LB_LOSS: 1.0096 |
| [2026-05-24 01:21:43] Validation | Batch 520/1463 | Loss: 0.8135 | LM_LOSS: 0.3087 | LB_LOSS: 1.0096 |
| [2026-05-24 01:21:45] Validation | Batch 530/1463 | Loss: 0.8137 | LM_LOSS: 0.3089 | LB_LOSS: 1.0096 |
| [2026-05-24 01:21:47] Validation | Batch 540/1463 | Loss: 0.8141 | LM_LOSS: 0.3093 | LB_LOSS: 1.0096 |
| [2026-05-24 01:21:49] Validation | Batch 550/1463 | Loss: 0.8137 | LM_LOSS: 0.3089 | LB_LOSS: 1.0096 |
| [2026-05-24 01:21:51] Validation | Batch 560/1463 | Loss: 0.8140 | LM_LOSS: 0.3091 | LB_LOSS: 1.0097 |
| [2026-05-24 01:21:54] Validation | Batch 570/1463 | Loss: 0.8139 | LM_LOSS: 0.3090 | LB_LOSS: 1.0097 |
| [2026-05-24 01:21:56] Validation | Batch 580/1463 | Loss: 0.8135 | LM_LOSS: 0.3087 | LB_LOSS: 1.0097 |
| [2026-05-24 01:21:59] Validation | Batch 590/1463 | Loss: 0.8134 | LM_LOSS: 0.3085 | LB_LOSS: 1.0097 |
| [2026-05-24 01:22:01] Validation | Batch 600/1463 | Loss: 0.8137 | LM_LOSS: 0.3088 | LB_LOSS: 1.0097 |
| [2026-05-24 01:22:03] Validation | Batch 610/1463 | Loss: 0.8138 | LM_LOSS: 0.3089 | LB_LOSS: 1.0097 |
| [2026-05-24 01:22:06] Validation | Batch 620/1463 | Loss: 0.8132 | LM_LOSS: 0.3083 | LB_LOSS: 1.0097 |
| [2026-05-24 01:22:08] Validation | Batch 630/1463 | Loss: 0.8127 | LM_LOSS: 0.3078 | LB_LOSS: 1.0098 |
| [2026-05-24 01:22:10] Validation | Batch 640/1463 | Loss: 0.8126 | LM_LOSS: 0.3077 | LB_LOSS: 1.0098 |
| [2026-05-24 01:22:12] Validation | Batch 650/1463 | Loss: 0.8120 | LM_LOSS: 0.3072 | LB_LOSS: 1.0098 |
| [2026-05-24 01:22:14] Validation | Batch 660/1463 | Loss: 0.8115 | LM_LOSS: 0.3066 | LB_LOSS: 1.0097 |
| [2026-05-24 01:22:16] Validation | Batch 670/1463 | Loss: 0.8112 | LM_LOSS: 0.3063 | LB_LOSS: 1.0097 |
| [2026-05-24 01:22:18] Validation | Batch 680/1463 | Loss: 0.8111 | LM_LOSS: 0.3063 | LB_LOSS: 1.0097 |
| [2026-05-24 01:22:20] Validation | Batch 690/1463 | Loss: 0.8115 | LM_LOSS: 0.3067 | LB_LOSS: 1.0097 |
| [2026-05-24 01:22:22] Validation | Batch 700/1463 | Loss: 0.8114 | LM_LOSS: 0.3065 | LB_LOSS: 1.0097 |
| [2026-05-24 01:22:24] Validation | Batch 710/1463 | Loss: 0.8117 | LM_LOSS: 0.3068 | LB_LOSS: 1.0097 |
| [2026-05-24 01:22:27] Validation | Batch 720/1463 | Loss: 0.8124 | LM_LOSS: 0.3075 | LB_LOSS: 1.0098 |
| [2026-05-24 01:22:29] Validation | Batch 730/1463 | Loss: 0.8123 | LM_LOSS: 0.3074 | LB_LOSS: 1.0098 |
| [2026-05-24 01:22:30] Validation | Batch 740/1463 | Loss: 0.8120 | LM_LOSS: 0.3071 | LB_LOSS: 1.0098 |
| [2026-05-24 01:22:32] Validation | Batch 750/1463 | Loss: 0.8119 | LM_LOSS: 0.3070 | LB_LOSS: 1.0098 |
| [2026-05-24 01:22:34] Validation | Batch 760/1463 | Loss: 0.8117 | LM_LOSS: 0.3068 | LB_LOSS: 1.0098 |
| [2026-05-24 01:22:36] Validation | Batch 770/1463 | Loss: 0.8116 | LM_LOSS: 0.3067 | LB_LOSS: 1.0098 |
| [2026-05-24 01:22:38] Validation | Batch 780/1463 | Loss: 0.8115 | LM_LOSS: 0.3066 | LB_LOSS: 1.0098 |
| [2026-05-24 01:22:40] Validation | Batch 790/1463 | Loss: 0.8117 | LM_LOSS: 0.3069 | LB_LOSS: 1.0098 |
| [2026-05-24 01:22:42] Validation | Batch 800/1463 | Loss: 0.8117 | LM_LOSS: 0.3068 | LB_LOSS: 1.0098 |
| [2026-05-24 01:22:44] Validation | Batch 810/1463 | Loss: 0.8113 | LM_LOSS: 0.3064 | LB_LOSS: 1.0097 |
| [2026-05-24 01:22:46] Validation | Batch 820/1463 | Loss: 0.8115 | LM_LOSS: 0.3067 | LB_LOSS: 1.0097 |
| [2026-05-24 01:22:48] Validation | Batch 830/1463 | Loss: 0.8118 | LM_LOSS: 0.3070 | LB_LOSS: 1.0097 |
| [2026-05-24 01:22:51] Validation | Batch 840/1463 | Loss: 0.8119 | LM_LOSS: 0.3070 | LB_LOSS: 1.0097 |
| [2026-05-24 01:22:53] Validation | Batch 850/1463 | Loss: 0.8122 | LM_LOSS: 0.3073 | LB_LOSS: 1.0097 |
| [2026-05-24 01:22:55] Validation | Batch 860/1463 | Loss: 0.8122 | LM_LOSS: 0.3074 | LB_LOSS: 1.0098 |
| [2026-05-24 01:22:57] Validation | Batch 870/1463 | Loss: 0.8123 | LM_LOSS: 0.3074 | LB_LOSS: 1.0098 |
| [2026-05-24 01:23:00] Validation | Batch 880/1463 | Loss: 0.8115 | LM_LOSS: 0.3066 | LB_LOSS: 1.0098 |
| [2026-05-24 01:23:02] Validation | Batch 890/1463 | Loss: 0.8116 | LM_LOSS: 0.3067 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:04] Validation | Batch 900/1463 | Loss: 0.8112 | LM_LOSS: 0.3063 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:06] Validation | Batch 910/1463 | Loss: 0.8111 | LM_LOSS: 0.3063 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:09] Validation | Batch 920/1463 | Loss: 0.8112 | LM_LOSS: 0.3064 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:11] Validation | Batch 930/1463 | Loss: 0.8110 | LM_LOSS: 0.3061 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:13] Validation | Batch 940/1463 | Loss: 0.8107 | LM_LOSS: 0.3059 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:15] Validation | Batch 950/1463 | Loss: 0.8110 | LM_LOSS: 0.3061 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:18] Validation | Batch 960/1463 | Loss: 0.8111 | LM_LOSS: 0.3062 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:20] Validation | Batch 970/1463 | Loss: 0.8111 | LM_LOSS: 0.3063 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:23] Validation | Batch 980/1463 | Loss: 0.8114 | LM_LOSS: 0.3066 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:24] Validation | Batch 990/1463 | Loss: 0.8117 | LM_LOSS: 0.3068 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:27] Validation | Batch 1000/1463 | Loss: 0.8123 | LM_LOSS: 0.3075 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:29] Validation | Batch 1010/1463 | Loss: 0.8124 | LM_LOSS: 0.3075 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:31] Validation | Batch 1020/1463 | Loss: 0.8124 | LM_LOSS: 0.3076 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:34] Validation | Batch 1030/1463 | Loss: 0.8129 | LM_LOSS: 0.3080 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:36] Validation | Batch 1040/1463 | Loss: 0.8125 | LM_LOSS: 0.3076 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:38] Validation | Batch 1050/1463 | Loss: 0.8124 | LM_LOSS: 0.3075 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:41] Validation | Batch 1060/1463 | Loss: 0.8123 | LM_LOSS: 0.3075 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:43] Validation | Batch 1070/1463 | Loss: 0.8123 | LM_LOSS: 0.3074 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:45] Validation | Batch 1080/1463 | Loss: 0.8121 | LM_LOSS: 0.3072 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:47] Validation | Batch 1090/1463 | Loss: 0.8122 | LM_LOSS: 0.3073 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:49] Validation | Batch 1100/1463 | Loss: 0.8120 | LM_LOSS: 0.3072 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:51] Validation | Batch 1110/1463 | Loss: 0.8120 | LM_LOSS: 0.3071 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:53] Validation | Batch 1120/1463 | Loss: 0.8118 | LM_LOSS: 0.3069 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:56] Validation | Batch 1130/1463 | Loss: 0.8116 | LM_LOSS: 0.3067 | LB_LOSS: 1.0097 |
| [2026-05-24 01:23:58] Validation | Batch 1140/1463 | Loss: 0.8118 | LM_LOSS: 0.3070 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:01] Validation | Batch 1150/1463 | Loss: 0.8117 | LM_LOSS: 0.3069 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:03] Validation | Batch 1160/1463 | Loss: 0.8117 | LM_LOSS: 0.3068 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:05] Validation | Batch 1170/1463 | Loss: 0.8117 | LM_LOSS: 0.3068 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:07] Validation | Batch 1180/1463 | Loss: 0.8117 | LM_LOSS: 0.3069 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:09] Validation | Batch 1190/1463 | Loss: 0.8118 | LM_LOSS: 0.3070 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:12] Validation | Batch 1200/1463 | Loss: 0.8118 | LM_LOSS: 0.3070 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:14] Validation | Batch 1210/1463 | Loss: 0.8120 | LM_LOSS: 0.3072 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:16] Validation | Batch 1220/1463 | Loss: 0.8124 | LM_LOSS: 0.3076 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:18] Validation | Batch 1230/1463 | Loss: 0.8124 | LM_LOSS: 0.3076 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:20] Validation | Batch 1240/1463 | Loss: 0.8127 | LM_LOSS: 0.3078 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:23] Validation | Batch 1250/1463 | Loss: 0.8129 | LM_LOSS: 0.3080 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:25] Validation | Batch 1260/1463 | Loss: 0.8128 | LM_LOSS: 0.3079 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:27] Validation | Batch 1270/1463 | Loss: 0.8126 | LM_LOSS: 0.3078 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:30] Validation | Batch 1280/1463 | Loss: 0.8125 | LM_LOSS: 0.3077 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:32] Validation | Batch 1290/1463 | Loss: 0.8125 | LM_LOSS: 0.3076 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:34] Validation | Batch 1300/1463 | Loss: 0.8123 | LM_LOSS: 0.3075 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:36] Validation | Batch 1310/1463 | Loss: 0.8122 | LM_LOSS: 0.3074 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:38] Validation | Batch 1320/1463 | Loss: 0.8123 | LM_LOSS: 0.3074 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:40] Validation | Batch 1330/1463 | Loss: 0.8123 | LM_LOSS: 0.3075 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:42] Validation | Batch 1340/1463 | Loss: 0.8126 | LM_LOSS: 0.3077 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:44] Validation | Batch 1350/1463 | Loss: 0.8126 | LM_LOSS: 0.3077 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:47] Validation | Batch 1360/1463 | Loss: 0.8129 | LM_LOSS: 0.3080 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:49] Validation | Batch 1370/1463 | Loss: 0.8131 | LM_LOSS: 0.3083 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:51] Validation | Batch 1380/1463 | Loss: 0.8129 | LM_LOSS: 0.3080 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:53] Validation | Batch 1390/1463 | Loss: 0.8128 | LM_LOSS: 0.3080 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:56] Validation | Batch 1400/1463 | Loss: 0.8131 | LM_LOSS: 0.3082 | LB_LOSS: 1.0097 |
| [2026-05-24 01:24:57] Validation | Batch 1410/1463 | Loss: 0.8133 | LM_LOSS: 0.3084 | LB_LOSS: 1.0097 |
| [2026-05-24 01:25:00] Validation | Batch 1420/1463 | Loss: 0.8132 | LM_LOSS: 0.3084 | LB_LOSS: 1.0097 |
| [2026-05-24 01:25:02] Validation | Batch 1430/1463 | Loss: 0.8133 | LM_LOSS: 0.3085 | LB_LOSS: 1.0097 |
| [2026-05-24 01:25:04] Validation | Batch 1440/1463 | Loss: 0.8137 | LM_LOSS: 0.3089 | LB_LOSS: 1.0097 |
| [2026-05-24 01:25:07] Validation | Batch 1450/1463 | Loss: 0.8134 | LM_LOSS: 0.3086 | LB_LOSS: 1.0097 |
| [2026-05-24 01:25:09] Validation | Batch 1460/1463 | Loss: 0.8137 | LM_LOSS: 0.3089 | LB_LOSS: 1.0097 |
| [2026-05-24 01:25:10] Validation | Batch 1463/1463 | Loss: 0.8136 | LM_LOSS: 0.3087 | LB_LOSS: 1.0097 |
| [2026-05-24 01:25:10] Validation | Loss: 0.8136 | LM_LOSS: 0.3087 | LB_LOSS: 1.0097 | PPL: 1.36 | Time: 321.99s |
| [2026-05-24 01:25:15] New best model saved! Val loss: 0.8136 |
| [2026-05-24 01:25:26] Epoch 1 | Step 3010 | Loss: 0.8355 | LM: 0.3193 | LB: 1.0387 | CL0: 3.0 | CL1: 3.2 | HR0: 0.339/SR0: 0.328 | HR1: 0.321/SR1: 0.283 | LR: 1.00e-04 |
| [2026-05-24 01:25:37] Epoch 1 | Step 3020 | Loss: 0.8354 | LM: 0.3192 | LB: 1.0386 | CL0: 3.0 | CL1: 3.2 | HR0: 0.339/SR0: 0.328 | HR1: 0.321/SR1: 0.283 | LR: 1.00e-04 |
| [2026-05-24 01:25:49] Epoch 1 | Step 3030 | Loss: 0.8351 | LM: 0.3192 | LB: 1.0385 | CL0: 3.0 | CL1: 3.2 | HR0: 0.339/SR0: 0.328 | HR1: 0.320/SR1: 0.283 | LR: 1.00e-04 |
| [2026-05-24 01:26:01] Epoch 1 | Step 3040 | Loss: 0.8351 | LM: 0.3191 | LB: 1.0384 | CL0: 3.0 | CL1: 3.2 | HR0: 0.339/SR0: 0.328 | HR1: 0.320/SR1: 0.283 | LR: 1.00e-04 |
| [2026-05-24 01:26:13] Epoch 1 | Step 3050 | Loss: 0.8349 | LM: 0.3191 | LB: 1.0383 | CL0: 3.0 | CL1: 3.2 | HR0: 0.339/SR0: 0.328 | HR1: 0.320/SR1: 0.283 | LR: 1.00e-04 |
| [2026-05-24 01:26:24] Epoch 1 | Step 3060 | Loss: 0.8348 | LM: 0.3192 | LB: 1.0382 | CL0: 3.0 | CL1: 3.2 | HR0: 0.339/SR0: 0.328 | HR1: 0.320/SR1: 0.282 | LR: 1.00e-04 |
| [2026-05-24 01:26:36] Epoch 1 | Step 3070 | Loss: 0.8346 | LM: 0.3190 | LB: 1.0381 | CL0: 3.0 | CL1: 3.2 | HR0: 0.339/SR0: 0.328 | HR1: 0.320/SR1: 0.282 | LR: 1.00e-04 |
| [2026-05-24 01:26:47] Epoch 1 | Step 3080 | Loss: 0.8346 | LM: 0.3189 | LB: 1.0380 | CL0: 3.0 | CL1: 3.2 | HR0: 0.339/SR0: 0.328 | HR1: 0.320/SR1: 0.282 | LR: 1.00e-04 |
| [2026-05-24 01:26:59] Epoch 1 | Step 3090 | Loss: 0.8346 | LM: 0.3188 | LB: 1.0379 | CL0: 3.0 | CL1: 3.2 | HR0: 0.339/SR0: 0.328 | HR1: 0.320/SR1: 0.282 | LR: 1.00e-04 |
| [2026-05-24 01:27:11] Epoch 1 | Step 3100 | Loss: 0.8344 | LM: 0.3185 | LB: 1.0378 | CL0: 3.0 | CL1: 3.2 | HR0: 0.339/SR0: 0.328 | HR1: 0.320/SR1: 0.282 | LR: 1.00e-04 |
| [2026-05-24 01:27:23] Epoch 1 | Step 3110 | Loss: 0.8343 | LM: 0.3183 | LB: 1.0378 | CL0: 3.0 | CL1: 3.2 | HR0: 0.339/SR0: 0.328 | HR1: 0.320/SR1: 0.282 | LR: 1.00e-04 |
| [2026-05-24 01:27:35] Epoch 1 | Step 3120 | Loss: 0.8344 | LM: 0.3184 | LB: 1.0377 | CL0: 3.0 | CL1: 3.2 | HR0: 0.339/SR0: 0.328 | HR1: 0.319/SR1: 0.282 | LR: 1.00e-04 |
| [2026-05-24 01:27:46] Epoch 1 | Step 3130 | Loss: 0.8343 | LM: 0.3184 | LB: 1.0376 | CL0: 3.0 | CL1: 3.2 | HR0: 0.338/SR0: 0.327 | HR1: 0.319/SR1: 0.281 | LR: 1.00e-04 |
| [2026-05-24 01:27:58] Epoch 1 | Step 3140 | Loss: 0.8342 | LM: 0.3181 | LB: 1.0375 | CL0: 3.0 | CL1: 3.2 | HR0: 0.338/SR0: 0.327 | HR1: 0.319/SR1: 0.281 | LR: 1.00e-04 |
| [2026-05-24 01:28:10] Epoch 1 | Step 3150 | Loss: 0.8341 | LM: 0.3181 | LB: 1.0374 | CL0: 3.0 | CL1: 3.2 | HR0: 0.338/SR0: 0.327 | HR1: 0.319/SR1: 0.281 | LR: 1.00e-04 |
| [2026-05-24 01:28:21] Epoch 1 | Step 3160 | Loss: 0.8341 | LM: 0.3180 | LB: 1.0373 | CL0: 3.0 | CL1: 3.2 | HR0: 0.338/SR0: 0.327 | HR1: 0.319/SR1: 0.281 | LR: 1.00e-04 |
| [2026-05-24 01:28:33] Epoch 1 | Step 3170 | Loss: 0.8342 | LM: 0.3182 | LB: 1.0373 | CL0: 3.0 | CL1: 3.2 | HR0: 0.338/SR0: 0.327 | HR1: 0.319/SR1: 0.281 | LR: 1.00e-04 |
| [2026-05-24 01:28:44] Epoch 1 | Step 3180 | Loss: 0.8341 | LM: 0.3181 | LB: 1.0372 | CL0: 3.0 | CL1: 3.2 | HR0: 0.338/SR0: 0.327 | HR1: 0.318/SR1: 0.281 | LR: 1.00e-04 |
| [2026-05-24 01:28:56] Epoch 1 | Step 3190 | Loss: 0.8341 | LM: 0.3181 | LB: 1.0371 | CL0: 3.0 | CL1: 3.2 | HR0: 0.338/SR0: 0.327 | HR1: 0.318/SR1: 0.281 | LR: 1.00e-04 |
| [2026-05-24 01:29:08] Epoch 1 | Step 3200 | Loss: 0.8339 | LM: 0.3178 | LB: 1.0370 | CL0: 3.0 | CL1: 3.2 | HR0: 0.338/SR0: 0.327 | HR1: 0.318/SR1: 0.280 | LR: 1.00e-04 |
| [2026-05-24 01:29:19] Epoch 1 | Step 3210 | Loss: 0.8338 | LM: 0.3178 | LB: 1.0369 | CL0: 3.0 | CL1: 3.2 | HR0: 0.338/SR0: 0.327 | HR1: 0.318/SR1: 0.280 | LR: 1.00e-04 |
| [2026-05-24 01:29:30] Epoch 1 | Step 3220 | Loss: 0.8338 | LM: 0.3180 | LB: 1.0368 | CL0: 3.0 | CL1: 3.3 | HR0: 0.338/SR0: 0.327 | HR1: 0.318/SR1: 0.280 | LR: 1.00e-04 |
| [2026-05-24 01:29:42] Epoch 1 | Step 3230 | Loss: 0.8337 | LM: 0.3179 | LB: 1.0367 | CL0: 3.0 | CL1: 3.3 | HR0: 0.338/SR0: 0.327 | HR1: 0.318/SR1: 0.280 | LR: 1.00e-04 |
| [2026-05-24 01:29:54] Epoch 1 | Step 3240 | Loss: 0.8337 | LM: 0.3179 | LB: 1.0366 | CL0: 3.0 | CL1: 3.3 | HR0: 0.338/SR0: 0.327 | HR1: 0.318/SR1: 0.280 | LR: 1.00e-04 |
| [2026-05-24 01:30:05] Epoch 1 | Step 3250 | Loss: 0.8336 | LM: 0.3178 | LB: 1.0366 | CL0: 3.0 | CL1: 3.3 | HR0: 0.338/SR0: 0.326 | HR1: 0.318/SR1: 0.280 | LR: 1.00e-04 |
| [2026-05-24 01:30:17] Epoch 1 | Step 3260 | Loss: 0.8335 | LM: 0.3178 | LB: 1.0365 | CL0: 3.0 | CL1: 3.3 | HR0: 0.338/SR0: 0.326 | HR1: 0.318/SR1: 0.280 | LR: 1.00e-04 |
| [2026-05-24 01:30:28] Epoch 1 | Step 3270 | Loss: 0.8333 | LM: 0.3178 | LB: 1.0364 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.326 | HR1: 0.318/SR1: 0.280 | LR: 1.00e-04 |
| [2026-05-24 01:30:40] Epoch 1 | Step 3280 | Loss: 0.8333 | LM: 0.3177 | LB: 1.0363 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.326 | HR1: 0.317/SR1: 0.280 | LR: 1.00e-04 |
| [2026-05-24 01:30:51] Epoch 1 | Step 3290 | Loss: 0.8332 | LM: 0.3174 | LB: 1.0362 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.326 | HR1: 0.317/SR1: 0.279 | LR: 1.00e-04 |
| [2026-05-24 01:31:03] Epoch 1 | Step 3300 | Loss: 0.8331 | LM: 0.3174 | LB: 1.0362 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.326 | HR1: 0.317/SR1: 0.279 | LR: 1.00e-04 |
| [2026-05-24 01:31:14] Epoch 1 | Step 3310 | Loss: 0.8331 | LM: 0.3175 | LB: 1.0361 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.326 | HR1: 0.317/SR1: 0.279 | LR: 1.00e-04 |
| [2026-05-24 01:31:26] Epoch 1 | Step 3320 | Loss: 0.8330 | LM: 0.3176 | LB: 1.0360 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.326 | HR1: 0.317/SR1: 0.279 | LR: 1.00e-04 |
| [2026-05-24 01:31:37] Epoch 1 | Step 3330 | Loss: 0.8329 | LM: 0.3175 | LB: 1.0359 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.326 | HR1: 0.317/SR1: 0.279 | LR: 1.00e-04 |
| [2026-05-24 01:31:48] Epoch 1 | Step 3340 | Loss: 0.8328 | LM: 0.3175 | LB: 1.0359 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.326 | HR1: 0.317/SR1: 0.279 | LR: 1.00e-04 |
| [2026-05-24 01:32:00] Epoch 1 | Step 3350 | Loss: 0.8329 | LM: 0.3177 | LB: 1.0358 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.326 | HR1: 0.317/SR1: 0.279 | LR: 1.00e-04 |
| [2026-05-24 01:32:11] Epoch 1 | Step 3360 | Loss: 0.8328 | LM: 0.3175 | LB: 1.0357 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.326 | HR1: 0.316/SR1: 0.279 | LR: 1.00e-04 |
| [2026-05-24 01:32:22] Epoch 1 | Step 3370 | Loss: 0.8327 | LM: 0.3174 | LB: 1.0357 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.326 | HR1: 0.316/SR1: 0.278 | LR: 1.00e-04 |
| [2026-05-24 01:32:34] Epoch 1 | Step 3380 | Loss: 0.8327 | LM: 0.3173 | LB: 1.0356 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.325 | HR1: 0.316/SR1: 0.278 | LR: 1.00e-04 |
| [2026-05-24 01:32:45] Epoch 1 | Step 3390 | Loss: 0.8326 | LM: 0.3171 | LB: 1.0355 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.325 | HR1: 0.316/SR1: 0.278 | LR: 1.00e-04 |
| [2026-05-24 01:32:58] Epoch 1 | Step 3400 | Loss: 0.8324 | LM: 0.3171 | LB: 1.0354 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.325 | HR1: 0.316/SR1: 0.278 | LR: 1.00e-04 |
| [2026-05-24 01:33:09] Epoch 1 | Step 3410 | Loss: 0.8324 | LM: 0.3171 | LB: 1.0353 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.325 | HR1: 0.316/SR1: 0.278 | LR: 1.00e-04 |
| [2026-05-24 01:33:20] Epoch 1 | Step 3420 | Loss: 0.8323 | LM: 0.3171 | LB: 1.0353 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.325 | HR1: 0.316/SR1: 0.278 | LR: 1.00e-04 |
| [2026-05-24 01:33:32] Epoch 1 | Step 3430 | Loss: 0.8322 | LM: 0.3169 | LB: 1.0352 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.325 | HR1: 0.316/SR1: 0.278 | LR: 1.00e-04 |
| [2026-05-24 01:33:43] Epoch 1 | Step 3440 | Loss: 0.8321 | LM: 0.3168 | LB: 1.0351 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.325 | HR1: 0.316/SR1: 0.278 | LR: 1.00e-04 |
| [2026-05-24 01:33:54] Epoch 1 | Step 3450 | Loss: 0.8320 | LM: 0.3166 | LB: 1.0351 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.325 | HR1: 0.316/SR1: 0.277 | LR: 1.00e-04 |
| [2026-05-24 01:34:06] Epoch 1 | Step 3460 | Loss: 0.8320 | LM: 0.3166 | LB: 1.0350 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.325 | HR1: 0.315/SR1: 0.277 | LR: 1.00e-04 |
| [2026-05-24 01:34:18] Epoch 1 | Step 3470 | Loss: 0.8319 | LM: 0.3166 | LB: 1.0349 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.325 | HR1: 0.315/SR1: 0.277 | LR: 1.00e-04 |
| [2026-05-24 01:34:29] Epoch 1 | Step 3480 | Loss: 0.8319 | LM: 0.3167 | LB: 1.0349 | CL0: 3.0 | CL1: 3.3 | HR0: 0.337/SR0: 0.325 | HR1: 0.315/SR1: 0.277 | LR: 1.00e-04 |
| [2026-05-24 01:34:41] Epoch 1 | Step 3490 | Loss: 0.8319 | LM: 0.3167 | LB: 1.0348 | CL0: 3.0 | CL1: 3.3 | HR0: 0.336/SR0: 0.325 | HR1: 0.315/SR1: 0.277 | LR: 1.00e-04 |
| [2026-05-24 01:34:52] Epoch 1 | Step 3500 | Loss: 0.8320 | LM: 0.3169 | LB: 1.0347 | CL0: 3.0 | CL1: 3.3 | HR0: 0.336/SR0: 0.325 | HR1: 0.315/SR1: 0.277 | LR: 1.00e-04 |
| [2026-05-24 01:35:04] Epoch 1 | Step 3510 | Loss: 0.8320 | LM: 0.3169 | LB: 1.0347 | CL0: 3.0 | CL1: 3.3 | HR0: 0.336/SR0: 0.325 | HR1: 0.315/SR1: 0.277 | LR: 1.00e-04 |
| [2026-05-24 01:35:15] Epoch 1 | Step 3520 | Loss: 0.8319 | LM: 0.3169 | LB: 1.0346 | CL0: 3.0 | CL1: 3.3 | HR0: 0.336/SR0: 0.325 | HR1: 0.315/SR1: 0.277 | LR: 1.00e-04 |
| [2026-05-24 01:35:27] Epoch 1 | Step 3530 | Loss: 0.8319 | LM: 0.3169 | LB: 1.0345 | CL0: 3.0 | CL1: 3.3 | HR0: 0.336/SR0: 0.324 | HR1: 0.315/SR1: 0.276 | LR: 1.00e-04 |
| [2026-05-24 01:35:39] Epoch 1 | Step 3540 | Loss: 0.8318 | LM: 0.3168 | LB: 1.0345 | CL0: 3.0 | CL1: 3.3 | HR0: 0.336/SR0: 0.324 | HR1: 0.315/SR1: 0.276 | LR: 1.00e-04 |
| [2026-05-24 01:35:51] Epoch 1 | Step 3550 | Loss: 0.8318 | LM: 0.3167 | LB: 1.0344 | CL0: 3.0 | CL1: 3.3 | HR0: 0.336/SR0: 0.324 | HR1: 0.314/SR1: 0.276 | LR: 1.00e-04 |
| [2026-05-24 01:36:02] Epoch 1 | Step 3560 | Loss: 0.8317 | LM: 0.3168 | LB: 1.0343 | CL0: 3.0 | CL1: 3.3 | HR0: 0.336/SR0: 0.324 | HR1: 0.314/SR1: 0.276 | LR: 1.00e-04 |
| [2026-05-24 01:36:14] Epoch 1 | Step 3570 | Loss: 0.8317 | LM: 0.3168 | LB: 1.0342 | CL0: 3.0 | CL1: 3.3 | HR0: 0.336/SR0: 0.324 | HR1: 0.314/SR1: 0.276 | LR: 1.00e-04 |
| [2026-05-24 01:36:26] Epoch 1 | Step 3580 | Loss: 0.8315 | LM: 0.3167 | LB: 1.0342 | CL0: 3.0 | CL1: 3.3 | HR0: 0.336/SR0: 0.324 | HR1: 0.314/SR1: 0.276 | LR: 1.00e-04 |
| [2026-05-24 01:36:38] Epoch 1 | Step 3590 | Loss: 0.8315 | LM: 0.3169 | LB: 1.0341 | CL0: 3.0 | CL1: 3.3 | HR0: 0.336/SR0: 0.324 | HR1: 0.314/SR1: 0.276 | LR: 1.00e-04 |
| [2026-05-24 01:36:49] Epoch 1 | Step 3600 | Loss: 0.8314 | LM: 0.3166 | LB: 1.0340 | CL0: 3.0 | CL1: 3.3 | HR0: 0.336/SR0: 0.324 | HR1: 0.314/SR1: 0.276 | LR: 1.00e-04 |
| [2026-05-24 01:37:01] Epoch 1 | Step 3610 | Loss: 0.8313 | LM: 0.3166 | LB: 1.0339 | CL0: 3.0 | CL1: 3.3 | HR0: 0.336/SR0: 0.324 | HR1: 0.314/SR1: 0.275 | LR: 1.00e-04 |
| [2026-05-24 01:37:12] Epoch 1 | Step 3620 | Loss: 0.8312 | LM: 0.3166 | LB: 1.0339 | CL0: 3.0 | CL1: 3.3 | HR0: 0.336/SR0: 0.324 | HR1: 0.314/SR1: 0.275 | LR: 1.00e-04 |
| [2026-05-24 01:37:24] Epoch 1 | Step 3630 | Loss: 0.8311 | LM: 0.3166 | LB: 1.0338 | CL0: 3.0 | CL1: 3.3 | HR0: 0.336/SR0: 0.324 | HR1: 0.313/SR1: 0.275 | LR: 1.00e-04 |
| [2026-05-24 01:37:36] Epoch 1 | Step 3640 | Loss: 0.8311 | LM: 0.3168 | LB: 1.0338 | CL0: 3.0 | CL1: 3.3 | HR0: 0.336/SR0: 0.324 | HR1: 0.313/SR1: 0.275 | LR: 1.00e-04 |
| [2026-05-24 01:37:47] Epoch 1 | Step 3650 | Loss: 0.8311 | LM: 0.3169 | LB: 1.0337 | CL0: 3.0 | CL1: 3.3 | HR0: 0.336/SR0: 0.324 | HR1: 0.313/SR1: 0.275 | LR: 1.00e-04 |
| [2026-05-24 01:37:58] Epoch 1 | Step 3660 | Loss: 0.8311 | LM: 0.3169 | LB: 1.0336 | CL0: 3.0 | CL1: 3.3 | HR0: 0.336/SR0: 0.324 | HR1: 0.313/SR1: 0.275 | LR: 1.00e-04 |
| [2026-05-24 01:38:09] Epoch 1 | Step 3670 | Loss: 0.8310 | LM: 0.3169 | LB: 1.0336 | CL0: 3.0 | CL1: 3.3 | HR0: 0.336/SR0: 0.323 | HR1: 0.313/SR1: 0.275 | LR: 1.00e-04 |
| [2026-05-24 01:38:20] Epoch 1 | Step 3680 | Loss: 0.8309 | LM: 0.3169 | LB: 1.0335 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.323 | HR1: 0.313/SR1: 0.275 | LR: 1.00e-04 |
| [2026-05-24 01:38:31] Epoch 1 | Step 3690 | Loss: 0.8308 | LM: 0.3169 | LB: 1.0334 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.323 | HR1: 0.313/SR1: 0.275 | LR: 1.00e-04 |
| [2026-05-24 01:38:43] Epoch 1 | Step 3700 | Loss: 0.8308 | LM: 0.3169 | LB: 1.0334 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.323 | HR1: 0.313/SR1: 0.275 | LR: 1.00e-04 |
| [2026-05-24 01:38:54] Epoch 1 | Step 3710 | Loss: 0.8307 | LM: 0.3169 | LB: 1.0333 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.323 | HR1: 0.313/SR1: 0.274 | LR: 1.00e-04 |
| [2026-05-24 01:39:05] Epoch 1 | Step 3720 | Loss: 0.8308 | LM: 0.3169 | LB: 1.0332 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.323 | HR1: 0.313/SR1: 0.274 | LR: 1.00e-04 |
| [2026-05-24 01:39:17] Epoch 1 | Step 3730 | Loss: 0.8307 | LM: 0.3167 | LB: 1.0332 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.323 | HR1: 0.312/SR1: 0.274 | LR: 1.00e-04 |
| [2026-05-24 01:39:29] Epoch 1 | Step 3740 | Loss: 0.8306 | LM: 0.3167 | LB: 1.0331 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.323 | HR1: 0.312/SR1: 0.274 | LR: 1.00e-04 |
| [2026-05-24 01:39:40] Epoch 1 | Step 3750 | Loss: 0.8306 | LM: 0.3167 | LB: 1.0330 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.323 | HR1: 0.312/SR1: 0.274 | LR: 1.00e-04 |
| [2026-05-24 01:39:52] Epoch 1 | Step 3760 | Loss: 0.8305 | LM: 0.3167 | LB: 1.0330 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.323 | HR1: 0.312/SR1: 0.274 | LR: 1.00e-04 |
| [2026-05-24 01:40:04] Epoch 1 | Step 3770 | Loss: 0.8304 | LM: 0.3167 | LB: 1.0329 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.323 | HR1: 0.312/SR1: 0.274 | LR: 1.00e-04 |
| [2026-05-24 01:40:16] Epoch 1 | Step 3780 | Loss: 0.8304 | LM: 0.3166 | LB: 1.0329 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.323 | HR1: 0.312/SR1: 0.274 | LR: 1.00e-04 |
| [2026-05-24 01:40:27] Epoch 1 | Step 3790 | Loss: 0.8304 | LM: 0.3167 | LB: 1.0328 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.323 | HR1: 0.312/SR1: 0.274 | LR: 1.00e-04 |
| [2026-05-24 01:40:39] Epoch 1 | Step 3800 | Loss: 0.8303 | LM: 0.3166 | LB: 1.0328 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.323 | HR1: 0.312/SR1: 0.273 | LR: 1.00e-04 |
| [2026-05-24 01:40:50] Epoch 1 | Step 3810 | Loss: 0.8302 | LM: 0.3166 | LB: 1.0327 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.323 | HR1: 0.312/SR1: 0.273 | LR: 1.00e-04 |
| [2026-05-24 01:41:02] Epoch 1 | Step 3820 | Loss: 0.8301 | LM: 0.3165 | LB: 1.0326 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.323 | HR1: 0.312/SR1: 0.273 | LR: 1.00e-04 |
| [2026-05-24 01:41:13] Epoch 1 | Step 3830 | Loss: 0.8300 | LM: 0.3164 | LB: 1.0326 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.322 | HR1: 0.312/SR1: 0.273 | LR: 1.00e-04 |
| [2026-05-24 01:41:24] Epoch 1 | Step 3840 | Loss: 0.8299 | LM: 0.3163 | LB: 1.0325 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.322 | HR1: 0.312/SR1: 0.273 | LR: 1.00e-04 |
| [2026-05-24 01:41:36] Epoch 1 | Step 3850 | Loss: 0.8299 | LM: 0.3163 | LB: 1.0325 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.322 | HR1: 0.311/SR1: 0.273 | LR: 1.00e-04 |
| [2026-05-24 01:41:48] Epoch 1 | Step 3860 | Loss: 0.8299 | LM: 0.3164 | LB: 1.0324 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.322 | HR1: 0.311/SR1: 0.273 | LR: 1.00e-04 |
| [2026-05-24 01:41:59] Epoch 1 | Step 3870 | Loss: 0.8298 | LM: 0.3162 | LB: 1.0323 | CL0: 3.0 | CL1: 3.3 | HR0: 0.335/SR0: 0.322 | HR1: 0.311/SR1: 0.273 | LR: 1.00e-04 |
| [2026-05-24 01:42:11] Epoch 1 | Step 3880 | Loss: 0.8298 | LM: 0.3162 | LB: 1.0323 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.322 | HR1: 0.311/SR1: 0.273 | LR: 1.00e-04 |
| [2026-05-24 01:42:22] Epoch 1 | Step 3890 | Loss: 0.8298 | LM: 0.3162 | LB: 1.0322 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.322 | HR1: 0.311/SR1: 0.273 | LR: 1.00e-04 |
| [2026-05-24 01:42:34] Epoch 1 | Step 3900 | Loss: 0.8298 | LM: 0.3162 | LB: 1.0321 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.322 | HR1: 0.311/SR1: 0.272 | LR: 1.00e-04 |
| [2026-05-24 01:42:46] Epoch 1 | Step 3910 | Loss: 0.8297 | LM: 0.3159 | LB: 1.0321 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.322 | HR1: 0.311/SR1: 0.272 | LR: 1.00e-04 |
| [2026-05-24 01:42:57] Epoch 1 | Step 3920 | Loss: 0.8296 | LM: 0.3157 | LB: 1.0320 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.322 | HR1: 0.311/SR1: 0.272 | LR: 1.00e-04 |
| [2026-05-24 01:43:09] Epoch 1 | Step 3930 | Loss: 0.8296 | LM: 0.3157 | LB: 1.0320 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.322 | HR1: 0.311/SR1: 0.272 | LR: 1.00e-04 |
| [2026-05-24 01:43:20] Epoch 1 | Step 3940 | Loss: 0.8295 | LM: 0.3156 | LB: 1.0319 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.322 | HR1: 0.311/SR1: 0.272 | LR: 1.00e-04 |
| [2026-05-24 01:43:31] Epoch 1 | Step 3950 | Loss: 0.8294 | LM: 0.3155 | LB: 1.0319 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.322 | HR1: 0.311/SR1: 0.272 | LR: 1.00e-04 |
| [2026-05-24 01:43:43] Epoch 1 | Step 3960 | Loss: 0.8295 | LM: 0.3155 | LB: 1.0318 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.322 | HR1: 0.310/SR1: 0.272 | LR: 1.00e-04 |
| [2026-05-24 01:43:54] Epoch 1 | Step 3970 | Loss: 0.8294 | LM: 0.3155 | LB: 1.0317 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.322 | HR1: 0.310/SR1: 0.272 | LR: 1.00e-04 |
| [2026-05-24 01:44:06] Epoch 1 | Step 3980 | Loss: 0.8294 | LM: 0.3155 | LB: 1.0317 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.321 | HR1: 0.310/SR1: 0.272 | LR: 1.00e-04 |
| [2026-05-24 01:44:17] Epoch 1 | Step 3990 | Loss: 0.8293 | LM: 0.3156 | LB: 1.0316 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.321 | HR1: 0.310/SR1: 0.272 | LR: 1.00e-04 |
| [2026-05-24 01:44:29] Epoch 1 | Step 4000 | Loss: 0.8293 | LM: 0.3155 | LB: 1.0316 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.321 | HR1: 0.310/SR1: 0.272 | LR: 1.00e-04 |
| [2026-05-24 01:44:31] Validation | Batch 10/1463 | Loss: 0.7795 | LM_LOSS: 0.2768 | LB_LOSS: 1.0053 |
| [2026-05-24 01:44:32] Validation | Batch 20/1463 | Loss: 0.7883 | LM_LOSS: 0.2848 | LB_LOSS: 1.0068 |
| [2026-05-24 01:44:35] Validation | Batch 30/1463 | Loss: 0.7926 | LM_LOSS: 0.2890 | LB_LOSS: 1.0072 |
| [2026-05-24 01:44:37] Validation | Batch 40/1463 | Loss: 0.8004 | LM_LOSS: 0.2964 | LB_LOSS: 1.0079 |
| [2026-05-24 01:44:39] Validation | Batch 50/1463 | Loss: 0.8072 | LM_LOSS: 0.3035 | LB_LOSS: 1.0075 |
| [2026-05-24 01:44:42] Validation | Batch 60/1463 | Loss: 0.8069 | LM_LOSS: 0.3032 | LB_LOSS: 1.0074 |
| [2026-05-24 01:44:45] Validation | Batch 70/1463 | Loss: 0.8064 | LM_LOSS: 0.3027 | LB_LOSS: 1.0074 |
| [2026-05-24 01:44:47] Validation | Batch 80/1463 | Loss: 0.8083 | LM_LOSS: 0.3046 | LB_LOSS: 1.0074 |
| [2026-05-24 01:44:49] Validation | Batch 90/1463 | Loss: 0.8073 | LM_LOSS: 0.3037 | LB_LOSS: 1.0073 |
| [2026-05-24 01:44:51] Validation | Batch 100/1463 | Loss: 0.8075 | LM_LOSS: 0.3039 | LB_LOSS: 1.0073 |
| [2026-05-24 01:44:54] Validation | Batch 110/1463 | Loss: 0.8062 | LM_LOSS: 0.3024 | LB_LOSS: 1.0075 |
| [2026-05-24 01:44:55] Validation | Batch 120/1463 | Loss: 0.8078 | LM_LOSS: 0.3040 | LB_LOSS: 1.0076 |
| [2026-05-24 01:44:57] Validation | Batch 130/1463 | Loss: 0.8098 | LM_LOSS: 0.3059 | LB_LOSS: 1.0077 |
| [2026-05-24 01:45:00] Validation | Batch 140/1463 | Loss: 0.8108 | LM_LOSS: 0.3070 | LB_LOSS: 1.0076 |
| [2026-05-24 01:45:02] Validation | Batch 150/1463 | Loss: 0.8093 | LM_LOSS: 0.3054 | LB_LOSS: 1.0078 |
| [2026-05-24 01:45:04] Validation | Batch 160/1463 | Loss: 0.8095 | LM_LOSS: 0.3056 | LB_LOSS: 1.0077 |
| [2026-05-24 01:45:07] Validation | Batch 170/1463 | Loss: 0.8091 | LM_LOSS: 0.3053 | LB_LOSS: 1.0077 |
| [2026-05-24 01:45:09] Validation | Batch 180/1463 | Loss: 0.8100 | LM_LOSS: 0.3061 | LB_LOSS: 1.0077 |
| [2026-05-24 01:45:11] Validation | Batch 190/1463 | Loss: 0.8109 | LM_LOSS: 0.3070 | LB_LOSS: 1.0077 |
| [2026-05-24 01:45:13] Validation | Batch 200/1463 | Loss: 0.8110 | LM_LOSS: 0.3072 | LB_LOSS: 1.0077 |
| [2026-05-24 01:45:15] Validation | Batch 210/1463 | Loss: 0.8116 | LM_LOSS: 0.3078 | LB_LOSS: 1.0077 |
| [2026-05-24 01:45:18] Validation | Batch 220/1463 | Loss: 0.8108 | LM_LOSS: 0.3070 | LB_LOSS: 1.0077 |
| [2026-05-24 01:45:20] Validation | Batch 230/1463 | Loss: 0.8125 | LM_LOSS: 0.3086 | LB_LOSS: 1.0076 |
| [2026-05-24 01:45:22] Validation | Batch 240/1463 | Loss: 0.8138 | LM_LOSS: 0.3100 | LB_LOSS: 1.0076 |
| [2026-05-24 01:45:25] Validation | Batch 250/1463 | Loss: 0.8131 | LM_LOSS: 0.3093 | LB_LOSS: 1.0076 |
| [2026-05-24 01:45:27] Validation | Batch 260/1463 | Loss: 0.8145 | LM_LOSS: 0.3106 | LB_LOSS: 1.0078 |
| [2026-05-24 01:45:29] Validation | Batch 270/1463 | Loss: 0.8130 | LM_LOSS: 0.3091 | LB_LOSS: 1.0078 |
| [2026-05-24 01:45:31] Validation | Batch 280/1463 | Loss: 0.8137 | LM_LOSS: 0.3098 | LB_LOSS: 1.0078 |
| [2026-05-24 01:45:34] Validation | Batch 290/1463 | Loss: 0.8129 | LM_LOSS: 0.3090 | LB_LOSS: 1.0078 |
| [2026-05-24 01:45:35] Validation | Batch 300/1463 | Loss: 0.8131 | LM_LOSS: 0.3092 | LB_LOSS: 1.0079 |
| [2026-05-24 01:45:38] Validation | Batch 310/1463 | Loss: 0.8141 | LM_LOSS: 0.3101 | LB_LOSS: 1.0079 |
| [2026-05-24 01:45:40] Validation | Batch 320/1463 | Loss: 0.8127 | LM_LOSS: 0.3088 | LB_LOSS: 1.0078 |
| [2026-05-24 01:45:42] Validation | Batch 330/1463 | Loss: 0.8126 | LM_LOSS: 0.3087 | LB_LOSS: 1.0078 |
| [2026-05-24 01:45:44] Validation | Batch 340/1463 | Loss: 0.8123 | LM_LOSS: 0.3084 | LB_LOSS: 1.0078 |
| [2026-05-24 01:45:46] Validation | Batch 350/1463 | Loss: 0.8129 | LM_LOSS: 0.3090 | LB_LOSS: 1.0078 |
| [2026-05-24 01:45:48] Validation | Batch 360/1463 | Loss: 0.8126 | LM_LOSS: 0.3087 | LB_LOSS: 1.0078 |
| [2026-05-24 01:45:50] Validation | Batch 370/1463 | Loss: 0.8123 | LM_LOSS: 0.3084 | LB_LOSS: 1.0078 |
| [2026-05-24 01:45:52] Validation | Batch 380/1463 | Loss: 0.8122 | LM_LOSS: 0.3083 | LB_LOSS: 1.0077 |
| [2026-05-24 01:45:55] Validation | Batch 390/1463 | Loss: 0.8129 | LM_LOSS: 0.3090 | LB_LOSS: 1.0077 |
| [2026-05-24 01:45:57] Validation | Batch 400/1463 | Loss: 0.8127 | LM_LOSS: 0.3088 | LB_LOSS: 1.0078 |
| [2026-05-24 01:45:59] Validation | Batch 410/1463 | Loss: 0.8125 | LM_LOSS: 0.3086 | LB_LOSS: 1.0078 |
| [2026-05-24 01:46:01] Validation | Batch 420/1463 | Loss: 0.8125 | LM_LOSS: 0.3086 | LB_LOSS: 1.0078 |
| [2026-05-24 01:46:04] Validation | Batch 430/1463 | Loss: 0.8120 | LM_LOSS: 0.3080 | LB_LOSS: 1.0079 |
| [2026-05-24 01:46:05] Validation | Batch 440/1463 | Loss: 0.8121 | LM_LOSS: 0.3082 | LB_LOSS: 1.0079 |
| [2026-05-24 01:46:07] Validation | Batch 450/1463 | Loss: 0.8119 | LM_LOSS: 0.3080 | LB_LOSS: 1.0079 |
| [2026-05-24 01:46:10] Validation | Batch 460/1463 | Loss: 0.8119 | LM_LOSS: 0.3079 | LB_LOSS: 1.0079 |
| [2026-05-24 01:46:12] Validation | Batch 470/1463 | Loss: 0.8125 | LM_LOSS: 0.3086 | LB_LOSS: 1.0078 |
| [2026-05-24 01:46:15] Validation | Batch 480/1463 | Loss: 0.8123 | LM_LOSS: 0.3084 | LB_LOSS: 1.0078 |
| [2026-05-24 01:46:17] Validation | Batch 490/1463 | Loss: 0.8122 | LM_LOSS: 0.3083 | LB_LOSS: 1.0078 |
| [2026-05-24 01:46:19] Validation | Batch 500/1463 | Loss: 0.8121 | LM_LOSS: 0.3082 | LB_LOSS: 1.0078 |
| [2026-05-24 01:46:22] Validation | Batch 510/1463 | Loss: 0.8115 | LM_LOSS: 0.3076 | LB_LOSS: 1.0078 |
| [2026-05-24 01:46:24] Validation | Batch 520/1463 | Loss: 0.8112 | LM_LOSS: 0.3073 | LB_LOSS: 1.0078 |
| [2026-05-24 01:46:26] Validation | Batch 530/1463 | Loss: 0.8115 | LM_LOSS: 0.3076 | LB_LOSS: 1.0078 |
| [2026-05-24 01:46:27] Validation | Batch 540/1463 | Loss: 0.8119 | LM_LOSS: 0.3079 | LB_LOSS: 1.0078 |
| [2026-05-24 01:46:29] Validation | Batch 550/1463 | Loss: 0.8114 | LM_LOSS: 0.3075 | LB_LOSS: 1.0079 |
| [2026-05-24 01:46:31] Validation | Batch 560/1463 | Loss: 0.8116 | LM_LOSS: 0.3076 | LB_LOSS: 1.0079 |
| [2026-05-24 01:46:34] Validation | Batch 570/1463 | Loss: 0.8115 | LM_LOSS: 0.3075 | LB_LOSS: 1.0079 |
| [2026-05-24 01:46:36] Validation | Batch 580/1463 | Loss: 0.8111 | LM_LOSS: 0.3071 | LB_LOSS: 1.0079 |
| [2026-05-24 01:46:39] Validation | Batch 590/1463 | Loss: 0.8109 | LM_LOSS: 0.3070 | LB_LOSS: 1.0079 |
| [2026-05-24 01:46:41] Validation | Batch 600/1463 | Loss: 0.8112 | LM_LOSS: 0.3072 | LB_LOSS: 1.0080 |
| [2026-05-24 01:46:44] Validation | Batch 610/1463 | Loss: 0.8113 | LM_LOSS: 0.3074 | LB_LOSS: 1.0080 |
| [2026-05-24 01:46:46] Validation | Batch 620/1463 | Loss: 0.8108 | LM_LOSS: 0.3069 | LB_LOSS: 1.0080 |
| [2026-05-24 01:46:48] Validation | Batch 630/1463 | Loss: 0.8104 | LM_LOSS: 0.3064 | LB_LOSS: 1.0080 |
| [2026-05-24 01:46:50] Validation | Batch 640/1463 | Loss: 0.8102 | LM_LOSS: 0.3062 | LB_LOSS: 1.0080 |
| [2026-05-24 01:46:52] Validation | Batch 650/1463 | Loss: 0.8097 | LM_LOSS: 0.3057 | LB_LOSS: 1.0080 |
| [2026-05-24 01:46:54] Validation | Batch 660/1463 | Loss: 0.8092 | LM_LOSS: 0.3053 | LB_LOSS: 1.0080 |
| [2026-05-24 01:46:56] Validation | Batch 670/1463 | Loss: 0.8089 | LM_LOSS: 0.3050 | LB_LOSS: 1.0079 |
| [2026-05-24 01:46:58] Validation | Batch 680/1463 | Loss: 0.8088 | LM_LOSS: 0.3049 | LB_LOSS: 1.0079 |
| [2026-05-24 01:47:00] Validation | Batch 690/1463 | Loss: 0.8092 | LM_LOSS: 0.3052 | LB_LOSS: 1.0079 |
| [2026-05-24 01:47:02] Validation | Batch 700/1463 | Loss: 0.8090 | LM_LOSS: 0.3050 | LB_LOSS: 1.0079 |
| [2026-05-24 01:47:04] Validation | Batch 710/1463 | Loss: 0.8093 | LM_LOSS: 0.3053 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:07] Validation | Batch 720/1463 | Loss: 0.8101 | LM_LOSS: 0.3061 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:08] Validation | Batch 730/1463 | Loss: 0.8099 | LM_LOSS: 0.3059 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:10] Validation | Batch 740/1463 | Loss: 0.8096 | LM_LOSS: 0.3056 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:12] Validation | Batch 750/1463 | Loss: 0.8095 | LM_LOSS: 0.3055 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:14] Validation | Batch 760/1463 | Loss: 0.8094 | LM_LOSS: 0.3054 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:16] Validation | Batch 770/1463 | Loss: 0.8092 | LM_LOSS: 0.3052 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:18] Validation | Batch 780/1463 | Loss: 0.8091 | LM_LOSS: 0.3051 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:19] Validation | Batch 790/1463 | Loss: 0.8093 | LM_LOSS: 0.3053 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:21] Validation | Batch 800/1463 | Loss: 0.8093 | LM_LOSS: 0.3053 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:23] Validation | Batch 810/1463 | Loss: 0.8089 | LM_LOSS: 0.3049 | LB_LOSS: 1.0079 |
| [2026-05-24 01:47:25] Validation | Batch 820/1463 | Loss: 0.8091 | LM_LOSS: 0.3051 | LB_LOSS: 1.0079 |
| [2026-05-24 01:47:28] Validation | Batch 830/1463 | Loss: 0.8093 | LM_LOSS: 0.3054 | LB_LOSS: 1.0079 |
| [2026-05-24 01:47:30] Validation | Batch 840/1463 | Loss: 0.8094 | LM_LOSS: 0.3054 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:32] Validation | Batch 850/1463 | Loss: 0.8096 | LM_LOSS: 0.3057 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:35] Validation | Batch 860/1463 | Loss: 0.8097 | LM_LOSS: 0.3058 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:37] Validation | Batch 870/1463 | Loss: 0.8098 | LM_LOSS: 0.3058 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:39] Validation | Batch 880/1463 | Loss: 0.8091 | LM_LOSS: 0.3051 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:41] Validation | Batch 890/1463 | Loss: 0.8092 | LM_LOSS: 0.3052 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:43] Validation | Batch 900/1463 | Loss: 0.8089 | LM_LOSS: 0.3049 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:46] Validation | Batch 910/1463 | Loss: 0.8088 | LM_LOSS: 0.3048 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:48] Validation | Batch 920/1463 | Loss: 0.8089 | LM_LOSS: 0.3050 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:50] Validation | Batch 930/1463 | Loss: 0.8087 | LM_LOSS: 0.3047 | LB_LOSS: 1.0080 |
| [2026-05-24 01:47:52] Validation | Batch 940/1463 | Loss: 0.8084 | LM_LOSS: 0.3044 | LB_LOSS: 1.0079 |
| [2026-05-24 01:47:55] Validation | Batch 950/1463 | Loss: 0.8086 | LM_LOSS: 0.3047 | LB_LOSS: 1.0079 |
| [2026-05-24 01:47:57] Validation | Batch 960/1463 | Loss: 0.8087 | LM_LOSS: 0.3047 | LB_LOSS: 1.0079 |
| [2026-05-24 01:47:59] Validation | Batch 970/1463 | Loss: 0.8087 | LM_LOSS: 0.3048 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:02] Validation | Batch 980/1463 | Loss: 0.8090 | LM_LOSS: 0.3051 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:03] Validation | Batch 990/1463 | Loss: 0.8093 | LM_LOSS: 0.3053 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:06] Validation | Batch 1000/1463 | Loss: 0.8098 | LM_LOSS: 0.3059 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:08] Validation | Batch 1010/1463 | Loss: 0.8099 | LM_LOSS: 0.3059 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:10] Validation | Batch 1020/1463 | Loss: 0.8100 | LM_LOSS: 0.3060 | LB_LOSS: 1.0080 |
| [2026-05-24 01:48:13] Validation | Batch 1030/1463 | Loss: 0.8105 | LM_LOSS: 0.3065 | LB_LOSS: 1.0080 |
| [2026-05-24 01:48:15] Validation | Batch 1040/1463 | Loss: 0.8101 | LM_LOSS: 0.3061 | LB_LOSS: 1.0080 |
| [2026-05-24 01:48:17] Validation | Batch 1050/1463 | Loss: 0.8099 | LM_LOSS: 0.3060 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:19] Validation | Batch 1060/1463 | Loss: 0.8099 | LM_LOSS: 0.3059 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:22] Validation | Batch 1070/1463 | Loss: 0.8099 | LM_LOSS: 0.3059 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:24] Validation | Batch 1080/1463 | Loss: 0.8097 | LM_LOSS: 0.3057 | LB_LOSS: 1.0080 |
| [2026-05-24 01:48:26] Validation | Batch 1090/1463 | Loss: 0.8098 | LM_LOSS: 0.3058 | LB_LOSS: 1.0080 |
| [2026-05-24 01:48:28] Validation | Batch 1100/1463 | Loss: 0.8096 | LM_LOSS: 0.3056 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:30] Validation | Batch 1110/1463 | Loss: 0.8095 | LM_LOSS: 0.3056 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:32] Validation | Batch 1120/1463 | Loss: 0.8094 | LM_LOSS: 0.3054 | LB_LOSS: 1.0080 |
| [2026-05-24 01:48:34] Validation | Batch 1130/1463 | Loss: 0.8091 | LM_LOSS: 0.3052 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:36] Validation | Batch 1140/1463 | Loss: 0.8093 | LM_LOSS: 0.3054 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:39] Validation | Batch 1150/1463 | Loss: 0.8093 | LM_LOSS: 0.3053 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:41] Validation | Batch 1160/1463 | Loss: 0.8092 | LM_LOSS: 0.3052 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:43] Validation | Batch 1170/1463 | Loss: 0.8092 | LM_LOSS: 0.3052 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:45] Validation | Batch 1180/1463 | Loss: 0.8093 | LM_LOSS: 0.3053 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:48] Validation | Batch 1190/1463 | Loss: 0.8094 | LM_LOSS: 0.3054 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:50] Validation | Batch 1200/1463 | Loss: 0.8094 | LM_LOSS: 0.3054 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:52] Validation | Batch 1210/1463 | Loss: 0.8096 | LM_LOSS: 0.3056 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:54] Validation | Batch 1220/1463 | Loss: 0.8100 | LM_LOSS: 0.3060 | LB_LOSS: 1.0080 |
| [2026-05-24 01:48:56] Validation | Batch 1230/1463 | Loss: 0.8100 | LM_LOSS: 0.3060 | LB_LOSS: 1.0079 |
| [2026-05-24 01:48:58] Validation | Batch 1240/1463 | Loss: 0.8103 | LM_LOSS: 0.3063 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:01] Validation | Batch 1250/1463 | Loss: 0.8104 | LM_LOSS: 0.3065 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:03] Validation | Batch 1260/1463 | Loss: 0.8104 | LM_LOSS: 0.3064 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:05] Validation | Batch 1270/1463 | Loss: 0.8102 | LM_LOSS: 0.3062 | LB_LOSS: 1.0080 |
| [2026-05-24 01:49:08] Validation | Batch 1280/1463 | Loss: 0.8100 | LM_LOSS: 0.3061 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:10] Validation | Batch 1290/1463 | Loss: 0.8100 | LM_LOSS: 0.3060 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:12] Validation | Batch 1300/1463 | Loss: 0.8098 | LM_LOSS: 0.3059 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:14] Validation | Batch 1310/1463 | Loss: 0.8097 | LM_LOSS: 0.3057 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:16] Validation | Batch 1320/1463 | Loss: 0.8098 | LM_LOSS: 0.3058 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:18] Validation | Batch 1330/1463 | Loss: 0.8098 | LM_LOSS: 0.3059 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:20] Validation | Batch 1340/1463 | Loss: 0.8101 | LM_LOSS: 0.3061 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:22] Validation | Batch 1350/1463 | Loss: 0.8101 | LM_LOSS: 0.3061 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:25] Validation | Batch 1360/1463 | Loss: 0.8104 | LM_LOSS: 0.3064 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:27] Validation | Batch 1370/1463 | Loss: 0.8106 | LM_LOSS: 0.3067 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:29] Validation | Batch 1380/1463 | Loss: 0.8104 | LM_LOSS: 0.3065 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:31] Validation | Batch 1390/1463 | Loss: 0.8103 | LM_LOSS: 0.3064 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:33] Validation | Batch 1400/1463 | Loss: 0.8106 | LM_LOSS: 0.3066 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:35] Validation | Batch 1410/1463 | Loss: 0.8108 | LM_LOSS: 0.3069 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:37] Validation | Batch 1420/1463 | Loss: 0.8108 | LM_LOSS: 0.3068 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:40] Validation | Batch 1430/1463 | Loss: 0.8108 | LM_LOSS: 0.3069 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:42] Validation | Batch 1440/1463 | Loss: 0.8112 | LM_LOSS: 0.3073 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:44] Validation | Batch 1450/1463 | Loss: 0.8110 | LM_LOSS: 0.3070 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:47] Validation | Batch 1460/1463 | Loss: 0.8113 | LM_LOSS: 0.3073 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:47] Validation | Batch 1463/1463 | Loss: 0.8111 | LM_LOSS: 0.3072 | LB_LOSS: 1.0079 |
| [2026-05-24 01:49:47] Validation | Loss: 0.8111 | LM_LOSS: 0.3072 | LB_LOSS: 1.0079 | PPL: 1.36 | Time: 318.46s |
| [2026-05-24 01:49:53] New best model saved! Val loss: 0.8111 |
| [2026-05-24 01:50:04] Epoch 1 | Step 4010 | Loss: 0.8292 | LM: 0.3154 | LB: 1.0315 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.321 | HR1: 0.310/SR1: 0.271 | LR: 1.00e-04 |
| [2026-05-24 01:50:16] Epoch 1 | Step 4020 | Loss: 0.8292 | LM: 0.3154 | LB: 1.0315 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.321 | HR1: 0.310/SR1: 0.271 | LR: 1.00e-04 |
| [2026-05-24 01:50:27] Epoch 1 | Step 4030 | Loss: 0.8292 | LM: 0.3153 | LB: 1.0314 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.321 | HR1: 0.310/SR1: 0.271 | LR: 1.00e-04 |
| [2026-05-24 01:50:38] Epoch 1 | Step 4040 | Loss: 0.8292 | LM: 0.3153 | LB: 1.0314 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.321 | HR1: 0.310/SR1: 0.271 | LR: 1.00e-04 |
| [2026-05-24 01:50:49] Epoch 1 | Step 4050 | Loss: 0.8291 | LM: 0.3151 | LB: 1.0313 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.321 | HR1: 0.310/SR1: 0.271 | LR: 1.00e-04 |
| [2026-05-24 01:51:00] Epoch 1 | Step 4060 | Loss: 0.8291 | LM: 0.3152 | LB: 1.0312 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.321 | HR1: 0.309/SR1: 0.271 | LR: 1.00e-04 |
| [2026-05-24 01:51:11] Epoch 1 | Step 4070 | Loss: 0.8291 | LM: 0.3152 | LB: 1.0312 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.321 | HR1: 0.309/SR1: 0.271 | LR: 1.00e-04 |
| [2026-05-24 01:51:22] Epoch 1 | Step 4080 | Loss: 0.8290 | LM: 0.3153 | LB: 1.0311 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.321 | HR1: 0.309/SR1: 0.271 | LR: 1.00e-04 |
| [2026-05-24 01:51:33] Epoch 1 | Step 4090 | Loss: 0.8290 | LM: 0.3153 | LB: 1.0311 | CL0: 3.0 | CL1: 3.3 | HR0: 0.334/SR0: 0.321 | HR1: 0.309/SR1: 0.271 | LR: 1.00e-04 |
| [2026-05-24 01:51:44] Epoch 1 | Step 4100 | Loss: 0.8290 | LM: 0.3152 | LB: 1.0310 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.321 | HR1: 0.309/SR1: 0.271 | LR: 1.00e-04 |
| [2026-05-24 01:51:55] Epoch 1 | Step 4110 | Loss: 0.8290 | LM: 0.3154 | LB: 1.0310 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.321 | HR1: 0.309/SR1: 0.271 | LR: 1.00e-04 |
| [2026-05-24 01:52:06] Epoch 1 | Step 4120 | Loss: 0.8289 | LM: 0.3153 | LB: 1.0309 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.321 | HR1: 0.309/SR1: 0.270 | LR: 1.00e-04 |
| [2026-05-24 01:52:17] Epoch 1 | Step 4130 | Loss: 0.8288 | LM: 0.3153 | LB: 1.0309 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.321 | HR1: 0.309/SR1: 0.270 | LR: 1.00e-04 |
| [2026-05-24 01:52:29] Epoch 1 | Step 4140 | Loss: 0.8287 | LM: 0.3152 | LB: 1.0308 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.321 | HR1: 0.309/SR1: 0.270 | LR: 1.00e-04 |
| [2026-05-24 01:52:40] Epoch 1 | Step 4150 | Loss: 0.8287 | LM: 0.3153 | LB: 1.0308 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.320 | HR1: 0.309/SR1: 0.270 | LR: 1.00e-04 |
| [2026-05-24 01:52:51] Epoch 1 | Step 4160 | Loss: 0.8287 | LM: 0.3153 | LB: 1.0307 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.320 | HR1: 0.309/SR1: 0.270 | LR: 1.00e-04 |
| [2026-05-24 01:53:02] Epoch 1 | Step 4170 | Loss: 0.8287 | LM: 0.3153 | LB: 1.0307 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.320 | HR1: 0.309/SR1: 0.270 | LR: 1.00e-04 |
| [2026-05-24 01:53:12] Epoch 1 | Step 4180 | Loss: 0.8286 | LM: 0.3154 | LB: 1.0306 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.320 | HR1: 0.308/SR1: 0.270 | LR: 1.00e-04 |
| [2026-05-24 01:53:24] Epoch 1 | Step 4190 | Loss: 0.8286 | LM: 0.3153 | LB: 1.0306 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.320 | HR1: 0.308/SR1: 0.270 | LR: 1.00e-04 |
| [2026-05-24 01:53:35] Epoch 1 | Step 4200 | Loss: 0.8286 | LM: 0.3154 | LB: 1.0305 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.320 | HR1: 0.308/SR1: 0.270 | LR: 1.00e-04 |
| [2026-05-24 01:53:46] Epoch 1 | Step 4210 | Loss: 0.8285 | LM: 0.3155 | LB: 1.0304 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.320 | HR1: 0.308/SR1: 0.270 | LR: 1.00e-04 |
| [2026-05-24 01:53:57] Epoch 1 | Step 4220 | Loss: 0.8284 | LM: 0.3153 | LB: 1.0304 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.320 | HR1: 0.308/SR1: 0.270 | LR: 1.00e-04 |
| [2026-05-24 01:54:09] Epoch 1 | Step 4230 | Loss: 0.8284 | LM: 0.3152 | LB: 1.0304 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.320 | HR1: 0.308/SR1: 0.269 | LR: 1.00e-04 |
| [2026-05-24 01:54:19] Epoch 1 | Step 4240 | Loss: 0.8284 | LM: 0.3152 | LB: 1.0303 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.320 | HR1: 0.308/SR1: 0.269 | LR: 1.00e-04 |
| [2026-05-24 01:54:31] Epoch 1 | Step 4250 | Loss: 0.8283 | LM: 0.3151 | LB: 1.0303 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.320 | HR1: 0.308/SR1: 0.269 | LR: 1.00e-04 |
| [2026-05-24 01:54:42] Epoch 1 | Step 4260 | Loss: 0.8282 | LM: 0.3148 | LB: 1.0302 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.320 | HR1: 0.308/SR1: 0.269 | LR: 1.00e-04 |
| [2026-05-24 01:54:53] Epoch 1 | Step 4270 | Loss: 0.8282 | LM: 0.3147 | LB: 1.0302 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.320 | HR1: 0.308/SR1: 0.269 | LR: 1.00e-04 |
| [2026-05-24 01:55:04] Epoch 1 | Step 4280 | Loss: 0.8281 | LM: 0.3146 | LB: 1.0301 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.320 | HR1: 0.308/SR1: 0.269 | LR: 1.00e-04 |
| [2026-05-24 01:55:16] Epoch 1 | Step 4290 | Loss: 0.8282 | LM: 0.3146 | LB: 1.0301 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.320 | HR1: 0.307/SR1: 0.269 | LR: 1.00e-04 |
| [2026-05-24 01:55:28] Epoch 1 | Step 4300 | Loss: 0.8281 | LM: 0.3147 | LB: 1.0300 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.320 | HR1: 0.307/SR1: 0.269 | LR: 1.00e-04 |
| [2026-05-24 01:55:40] Epoch 1 | Step 4310 | Loss: 0.8281 | LM: 0.3147 | LB: 1.0300 | CL0: 3.0 | CL1: 3.3 | HR0: 0.333/SR0: 0.320 | HR1: 0.307/SR1: 0.269 | LR: 1.00e-04 |
| [2026-05-24 01:55:52] Epoch 1 | Step 4320 | Loss: 0.8281 | LM: 0.3147 | LB: 1.0299 | CL0: 3.0 | CL1: 3.4 | HR0: 0.333/SR0: 0.320 | HR1: 0.307/SR1: 0.269 | LR: 1.00e-04 |
| [2026-05-24 01:56:04] Epoch 1 | Step 4330 | Loss: 0.8280 | LM: 0.3148 | LB: 1.0299 | CL0: 3.0 | CL1: 3.4 | HR0: 0.333/SR0: 0.319 | HR1: 0.307/SR1: 0.269 | LR: 1.00e-04 |
| [2026-05-24 01:56:16] Epoch 1 | Step 4340 | Loss: 0.8280 | LM: 0.3148 | LB: 1.0298 | CL0: 3.0 | CL1: 3.4 | HR0: 0.333/SR0: 0.319 | HR1: 0.307/SR1: 0.268 | LR: 1.00e-04 |
| [2026-05-24 01:56:28] Epoch 1 | Step 4350 | Loss: 0.8280 | LM: 0.3148 | LB: 1.0298 | CL0: 3.0 | CL1: 3.4 | HR0: 0.333/SR0: 0.319 | HR1: 0.307/SR1: 0.268 | LR: 1.00e-04 |
| [2026-05-24 01:56:40] Epoch 1 | Step 4360 | Loss: 0.8279 | LM: 0.3147 | LB: 1.0297 | CL0: 3.0 | CL1: 3.4 | HR0: 0.333/SR0: 0.319 | HR1: 0.307/SR1: 0.268 | LR: 1.00e-04 |
| [2026-05-24 01:56:52] Epoch 1 | Step 4370 | Loss: 0.8278 | LM: 0.3146 | LB: 1.0297 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.319 | HR1: 0.307/SR1: 0.268 | LR: 1.00e-04 |
| [2026-05-24 01:57:04] Epoch 1 | Step 4380 | Loss: 0.8277 | LM: 0.3145 | LB: 1.0296 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.319 | HR1: 0.307/SR1: 0.268 | LR: 1.00e-04 |
| [2026-05-24 01:57:15] Epoch 1 | Step 4390 | Loss: 0.8277 | LM: 0.3143 | LB: 1.0296 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.319 | HR1: 0.307/SR1: 0.268 | LR: 1.00e-04 |
| [2026-05-24 01:57:27] Epoch 1 | Step 4400 | Loss: 0.8277 | LM: 0.3143 | LB: 1.0295 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.319 | HR1: 0.307/SR1: 0.268 | LR: 1.00e-04 |
| [2026-05-24 01:57:39] Epoch 1 | Step 4410 | Loss: 0.8275 | LM: 0.3141 | LB: 1.0295 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.319 | HR1: 0.307/SR1: 0.268 | LR: 1.00e-04 |
| [2026-05-24 01:57:50] Epoch 1 | Step 4420 | Loss: 0.8275 | LM: 0.3140 | LB: 1.0294 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.319 | HR1: 0.306/SR1: 0.268 | LR: 1.00e-04 |
| [2026-05-24 01:58:01] Epoch 1 | Step 4430 | Loss: 0.8274 | LM: 0.3139 | LB: 1.0294 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.319 | HR1: 0.306/SR1: 0.268 | LR: 1.00e-04 |
| [2026-05-24 01:58:12] Epoch 1 | Step 4440 | Loss: 0.8274 | LM: 0.3139 | LB: 1.0294 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.319 | HR1: 0.306/SR1: 0.268 | LR: 1.00e-04 |
| [2026-05-24 01:58:23] Epoch 1 | Step 4450 | Loss: 0.8274 | LM: 0.3139 | LB: 1.0293 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.319 | HR1: 0.306/SR1: 0.268 | LR: 1.00e-04 |
| [2026-05-24 01:58:34] Epoch 1 | Step 4460 | Loss: 0.8272 | LM: 0.3138 | LB: 1.0293 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.319 | HR1: 0.306/SR1: 0.267 | LR: 1.00e-04 |
| [2026-05-24 01:58:45] Epoch 1 | Step 4470 | Loss: 0.8272 | LM: 0.3138 | LB: 1.0292 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.319 | HR1: 0.306/SR1: 0.267 | LR: 1.00e-04 |
| [2026-05-24 01:58:56] Epoch 1 | Step 4480 | Loss: 0.8272 | LM: 0.3139 | LB: 1.0292 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.319 | HR1: 0.306/SR1: 0.267 | LR: 1.00e-04 |
| [2026-05-24 01:59:07] Epoch 1 | Step 4490 | Loss: 0.8271 | LM: 0.3139 | LB: 1.0291 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.319 | HR1: 0.306/SR1: 0.267 | LR: 1.00e-04 |
| [2026-05-24 01:59:18] Epoch 1 | Step 4500 | Loss: 0.8271 | LM: 0.3137 | LB: 1.0291 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.319 | HR1: 0.306/SR1: 0.267 | LR: 1.00e-04 |
| [2026-05-24 01:59:29] Epoch 1 | Step 4510 | Loss: 0.8271 | LM: 0.3136 | LB: 1.0290 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.318 | HR1: 0.306/SR1: 0.267 | LR: 1.00e-04 |
| [2026-05-24 01:59:40] Epoch 1 | Step 4520 | Loss: 0.8270 | LM: 0.3137 | LB: 1.0290 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.318 | HR1: 0.306/SR1: 0.267 | LR: 1.00e-04 |
| [2026-05-24 01:59:51] Epoch 1 | Step 4530 | Loss: 0.8270 | LM: 0.3136 | LB: 1.0289 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.318 | HR1: 0.306/SR1: 0.267 | LR: 1.00e-04 |
| [2026-05-24 02:00:02] Epoch 1 | Step 4540 | Loss: 0.8269 | LM: 0.3136 | LB: 1.0289 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.318 | HR1: 0.306/SR1: 0.267 | LR: 1.00e-04 |
| [2026-05-24 02:00:13] Epoch 1 | Step 4550 | Loss: 0.8269 | LM: 0.3136 | LB: 1.0288 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.318 | HR1: 0.305/SR1: 0.267 | LR: 1.00e-04 |
| [2026-05-24 02:00:24] Epoch 1 | Step 4560 | Loss: 0.8268 | LM: 0.3134 | LB: 1.0288 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.318 | HR1: 0.305/SR1: 0.267 | LR: 1.00e-04 |
| [2026-05-24 02:00:34] Epoch 1 | Step 4570 | Loss: 0.8268 | LM: 0.3136 | LB: 1.0287 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.318 | HR1: 0.305/SR1: 0.267 | LR: 1.00e-04 |
| [2026-05-24 02:00:45] Epoch 1 | Step 4580 | Loss: 0.8267 | LM: 0.3136 | LB: 1.0287 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.318 | HR1: 0.305/SR1: 0.267 | LR: 1.00e-04 |
| [2026-05-24 02:00:56] Epoch 1 | Step 4590 | Loss: 0.8267 | LM: 0.3135 | LB: 1.0286 | CL0: 3.0 | CL1: 3.4 | HR0: 0.332/SR0: 0.318 | HR1: 0.305/SR1: 0.267 | LR: 1.00e-04 |
| [2026-05-24 02:01:07] Epoch 1 | Step 4600 | Loss: 0.8267 | LM: 0.3134 | LB: 1.0286 | CL0: 3.0 | CL1: 3.4 | HR0: 0.331/SR0: 0.318 | HR1: 0.305/SR1: 0.266 | LR: 1.00e-04 |
| [2026-05-24 02:01:18] Epoch 1 | Step 4610 | Loss: 0.8266 | LM: 0.3134 | LB: 1.0286 | CL0: 3.0 | CL1: 3.4 | HR0: 0.331/SR0: 0.318 | HR1: 0.305/SR1: 0.266 | LR: 1.00e-04 |
| [2026-05-24 02:01:29] Epoch 1 | Step 4620 | Loss: 0.8266 | LM: 0.3134 | LB: 1.0285 | CL0: 3.0 | CL1: 3.4 | HR0: 0.331/SR0: 0.318 | HR1: 0.305/SR1: 0.266 | LR: 1.00e-04 |
| [2026-05-24 02:01:40] Epoch 1 | Step 4630 | Loss: 0.8265 | LM: 0.3134 | LB: 1.0285 | CL0: 3.0 | CL1: 3.4 | HR0: 0.331/SR0: 0.318 | HR1: 0.305/SR1: 0.266 | LR: 1.00e-04 |
| [2026-05-24 02:01:51] Epoch 1 | Step 4640 | Loss: 0.8265 | LM: 0.3133 | LB: 1.0284 | CL0: 3.0 | CL1: 3.4 | HR0: 0.331/SR0: 0.318 | HR1: 0.305/SR1: 0.266 | LR: 1.00e-04 |
| [2026-05-24 02:02:02] Epoch 1 | Step 4650 | Loss: 0.8264 | LM: 0.3132 | LB: 1.0284 | CL0: 3.0 | CL1: 3.4 | HR0: 0.331/SR0: 0.318 | HR1: 0.305/SR1: 0.266 | LR: 1.00e-04 |
| [2026-05-24 02:02:13] Epoch 1 | Step 4660 | Loss: 0.8263 | LM: 0.3131 | LB: 1.0284 | CL0: 3.0 | CL1: 3.4 | HR0: 0.331/SR0: 0.318 | HR1: 0.305/SR1: 0.266 | LR: 1.00e-04 |
| [2026-05-24 02:02:23] Epoch 1 | Step 4670 | Loss: 0.8263 | LM: 0.3130 | LB: 1.0283 | CL0: 3.0 | CL1: 3.4 | HR0: 0.331/SR0: 0.318 | HR1: 0.304/SR1: 0.266 | LR: 1.00e-04 |
| [2026-05-24 02:02:34] Epoch 1 | Step 4680 | Loss: 0.8262 | LM: 0.3130 | LB: 1.0283 | CL0: 3.0 | CL1: 3.4 | HR0: 0.331/SR0: 0.318 | HR1: 0.304/SR1: 0.266 | LR: 1.00e-04 |
| [2026-05-24 02:02:43] Epoch 1 completed in 6773.03s | Loss: 0.8262 | CL0: 3.0 | CL1: 3.4 |
| [2026-05-24 02:02:43] |
| ============================================================ |
| [2026-05-24 02:02:43] EPOCH 2/3 (step 4687) |
| [2026-05-24 02:02:43] ============================================================ |
| [2026-05-24 02:02:47] Epoch 2 | Step 4690 | Loss: 0.7577 | LM: 0.2284 | LB: 1.0065 | CL0: 3.2 | CL1: 3.7 | HR0: 0.315/SR0: 0.293 | HR1: 0.271/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:02:59] Epoch 2 | Step 4700 | Loss: 0.7717 | LM: 0.2857 | LB: 1.0088 | CL0: 3.2 | CL1: 3.9 | HR0: 0.316/SR0: 0.295 | HR1: 0.261/SR1: 0.222 | LR: 1.00e-04 |
| [2026-05-24 02:03:10] Epoch 2 | Step 4710 | Loss: 0.7705 | LM: 0.2909 | LB: 1.0116 | CL0: 3.1 | CL1: 3.9 | HR0: 0.323/SR0: 0.302 | HR1: 0.260/SR1: 0.222 | LR: 1.00e-04 |
| [2026-05-24 02:03:22] Epoch 2 | Step 4720 | Loss: 0.7648 | LM: 0.2828 | LB: 1.0119 | CL0: 3.1 | CL1: 3.8 | HR0: 0.324/SR0: 0.302 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:03:34] Epoch 2 | Step 4730 | Loss: 0.7625 | LM: 0.2807 | LB: 1.0107 | CL0: 3.1 | CL1: 3.7 | HR0: 0.320/SR0: 0.299 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:03:46] Epoch 2 | Step 4740 | Loss: 0.7583 | LM: 0.2697 | LB: 1.0107 | CL0: 3.1 | CL1: 3.8 | HR0: 0.320/SR0: 0.299 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:03:58] Epoch 2 | Step 4750 | Loss: 0.7551 | LM: 0.2702 | LB: 1.0108 | CL0: 3.1 | CL1: 3.7 | HR0: 0.321/SR0: 0.300 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:04:10] Epoch 2 | Step 4760 | Loss: 0.7555 | LM: 0.2707 | LB: 1.0103 | CL0: 3.1 | CL1: 3.7 | HR0: 0.319/SR0: 0.299 | HR1: 0.269/SR1: 0.231 | LR: 1.00e-04 |
| [2026-05-24 02:04:22] Epoch 2 | Step 4770 | Loss: 0.7546 | LM: 0.2731 | LB: 1.0102 | CL0: 3.2 | CL1: 3.7 | HR0: 0.319/SR0: 0.298 | HR1: 0.269/SR1: 0.231 | LR: 1.00e-04 |
| [2026-05-24 02:04:34] Epoch 2 | Step 4780 | Loss: 0.7529 | LM: 0.2750 | LB: 1.0104 | CL0: 3.1 | CL1: 3.7 | HR0: 0.320/SR0: 0.299 | HR1: 0.269/SR1: 0.231 | LR: 1.00e-04 |
| [2026-05-24 02:04:46] Epoch 2 | Step 4790 | Loss: 0.7533 | LM: 0.2721 | LB: 1.0101 | CL0: 3.2 | CL1: 3.7 | HR0: 0.319/SR0: 0.298 | HR1: 0.270/SR1: 0.231 | LR: 1.00e-04 |
| [2026-05-24 02:04:57] Epoch 2 | Step 4800 | Loss: 0.7534 | LM: 0.2733 | LB: 1.0097 | CL0: 3.2 | CL1: 3.7 | HR0: 0.318/SR0: 0.297 | HR1: 0.270/SR1: 0.231 | LR: 1.00e-04 |
| [2026-05-24 02:05:09] Epoch 2 | Step 4810 | Loss: 0.7553 | LM: 0.2729 | LB: 1.0101 | CL0: 3.2 | CL1: 3.7 | HR0: 0.319/SR0: 0.298 | HR1: 0.269/SR1: 0.231 | LR: 1.00e-04 |
| [2026-05-24 02:05:20] Epoch 2 | Step 4820 | Loss: 0.7537 | LM: 0.2698 | LB: 1.0101 | CL0: 3.2 | CL1: 3.7 | HR0: 0.319/SR0: 0.298 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:05:31] Epoch 2 | Step 4830 | Loss: 0.7546 | LM: 0.2674 | LB: 1.0099 | CL0: 3.2 | CL1: 3.7 | HR0: 0.318/SR0: 0.297 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:05:42] Epoch 2 | Step 4840 | Loss: 0.7549 | LM: 0.2683 | LB: 1.0102 | CL0: 3.2 | CL1: 3.8 | HR0: 0.319/SR0: 0.298 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:05:53] Epoch 2 | Step 4850 | Loss: 0.7541 | LM: 0.2665 | LB: 1.0101 | CL0: 3.2 | CL1: 3.8 | HR0: 0.319/SR0: 0.298 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:06:05] Epoch 2 | Step 4860 | Loss: 0.7550 | LM: 0.2647 | LB: 1.0100 | CL0: 3.2 | CL1: 3.7 | HR0: 0.319/SR0: 0.298 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:06:16] Epoch 2 | Step 4870 | Loss: 0.7563 | LM: 0.2644 | LB: 1.0100 | CL0: 3.2 | CL1: 3.8 | HR0: 0.319/SR0: 0.298 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:06:27] Epoch 2 | Step 4880 | Loss: 0.7575 | LM: 0.2650 | LB: 1.0098 | CL0: 3.2 | CL1: 3.8 | HR0: 0.319/SR0: 0.298 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:06:38] Epoch 2 | Step 4890 | Loss: 0.7566 | LM: 0.2641 | LB: 1.0097 | CL0: 3.2 | CL1: 3.7 | HR0: 0.318/SR0: 0.298 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:06:49] Epoch 2 | Step 4900 | Loss: 0.7564 | LM: 0.2642 | LB: 1.0096 | CL0: 3.2 | CL1: 3.7 | HR0: 0.318/SR0: 0.297 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:07:00] Epoch 2 | Step 4910 | Loss: 0.7567 | LM: 0.2633 | LB: 1.0094 | CL0: 3.2 | CL1: 3.7 | HR0: 0.318/SR0: 0.297 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:07:11] Epoch 2 | Step 4920 | Loss: 0.7565 | LM: 0.2631 | LB: 1.0094 | CL0: 3.2 | CL1: 3.7 | HR0: 0.318/SR0: 0.297 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:07:22] Epoch 2 | Step 4930 | Loss: 0.7560 | LM: 0.2620 | LB: 1.0094 | CL0: 3.2 | CL1: 3.7 | HR0: 0.318/SR0: 0.297 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:07:34] Epoch 2 | Step 4940 | Loss: 0.7568 | LM: 0.2616 | LB: 1.0093 | CL0: 3.2 | CL1: 3.8 | HR0: 0.317/SR0: 0.296 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:07:45] Epoch 2 | Step 4950 | Loss: 0.7558 | LM: 0.2607 | LB: 1.0093 | CL0: 3.2 | CL1: 3.7 | HR0: 0.317/SR0: 0.296 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:07:56] Epoch 2 | Step 4960 | Loss: 0.7566 | LM: 0.2630 | LB: 1.0091 | CL0: 3.2 | CL1: 3.8 | HR0: 0.317/SR0: 0.296 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:08:07] Epoch 2 | Step 4970 | Loss: 0.7565 | LM: 0.2617 | LB: 1.0091 | CL0: 3.2 | CL1: 3.8 | HR0: 0.316/SR0: 0.296 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:08:18] Epoch 2 | Step 4980 | Loss: 0.7561 | LM: 0.2607 | LB: 1.0091 | CL0: 3.2 | CL1: 3.8 | HR0: 0.316/SR0: 0.296 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:08:29] Epoch 2 | Step 4990 | Loss: 0.7560 | LM: 0.2604 | LB: 1.0091 | CL0: 3.2 | CL1: 3.8 | HR0: 0.316/SR0: 0.296 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:08:41] Epoch 2 | Step 5000 | Loss: 0.7561 | LM: 0.2605 | LB: 1.0090 | CL0: 3.2 | CL1: 3.8 | HR0: 0.316/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:08:42] Validation | Batch 10/1463 | Loss: 0.7923 | LM_LOSS: 0.2901 | LB_LOSS: 1.0044 |
| [2026-05-24 02:08:44] Validation | Batch 20/1463 | Loss: 0.8001 | LM_LOSS: 0.2972 | LB_LOSS: 1.0057 |
| [2026-05-24 02:08:47] Validation | Batch 30/1463 | Loss: 0.8026 | LM_LOSS: 0.2995 | LB_LOSS: 1.0061 |
| [2026-05-24 02:08:49] Validation | Batch 40/1463 | Loss: 0.8102 | LM_LOSS: 0.3069 | LB_LOSS: 1.0067 |
| [2026-05-24 02:08:51] Validation | Batch 50/1463 | Loss: 0.8179 | LM_LOSS: 0.3147 | LB_LOSS: 1.0064 |
| [2026-05-24 02:08:53] Validation | Batch 60/1463 | Loss: 0.8168 | LM_LOSS: 0.3137 | LB_LOSS: 1.0062 |
| [2026-05-24 02:08:56] Validation | Batch 70/1463 | Loss: 0.8161 | LM_LOSS: 0.3130 | LB_LOSS: 1.0063 |
| [2026-05-24 02:08:59] Validation | Batch 80/1463 | Loss: 0.8181 | LM_LOSS: 0.3149 | LB_LOSS: 1.0063 |
| [2026-05-24 02:09:00] Validation | Batch 90/1463 | Loss: 0.8172 | LM_LOSS: 0.3141 | LB_LOSS: 1.0062 |
| [2026-05-24 02:09:02] Validation | Batch 100/1463 | Loss: 0.8173 | LM_LOSS: 0.3142 | LB_LOSS: 1.0062 |
| [2026-05-24 02:09:05] Validation | Batch 110/1463 | Loss: 0.8157 | LM_LOSS: 0.3125 | LB_LOSS: 1.0064 |
| [2026-05-24 02:09:06] Validation | Batch 120/1463 | Loss: 0.8173 | LM_LOSS: 0.3141 | LB_LOSS: 1.0065 |
| [2026-05-24 02:09:08] Validation | Batch 130/1463 | Loss: 0.8190 | LM_LOSS: 0.3157 | LB_LOSS: 1.0066 |
| [2026-05-24 02:09:11] Validation | Batch 140/1463 | Loss: 0.8202 | LM_LOSS: 0.3170 | LB_LOSS: 1.0065 |
| [2026-05-24 02:09:13] Validation | Batch 150/1463 | Loss: 0.8185 | LM_LOSS: 0.3152 | LB_LOSS: 1.0066 |
| [2026-05-24 02:09:15] Validation | Batch 160/1463 | Loss: 0.8188 | LM_LOSS: 0.3155 | LB_LOSS: 1.0066 |
| [2026-05-24 02:09:18] Validation | Batch 170/1463 | Loss: 0.8181 | LM_LOSS: 0.3148 | LB_LOSS: 1.0066 |
| [2026-05-24 02:09:20] Validation | Batch 180/1463 | Loss: 0.8188 | LM_LOSS: 0.3155 | LB_LOSS: 1.0066 |
| [2026-05-24 02:09:22] Validation | Batch 190/1463 | Loss: 0.8200 | LM_LOSS: 0.3167 | LB_LOSS: 1.0066 |
| [2026-05-24 02:09:24] Validation | Batch 200/1463 | Loss: 0.8199 | LM_LOSS: 0.3166 | LB_LOSS: 1.0066 |
| [2026-05-24 02:09:26] Validation | Batch 210/1463 | Loss: 0.8206 | LM_LOSS: 0.3173 | LB_LOSS: 1.0066 |
| [2026-05-24 02:09:29] Validation | Batch 220/1463 | Loss: 0.8199 | LM_LOSS: 0.3166 | LB_LOSS: 1.0066 |
| [2026-05-24 02:09:31] Validation | Batch 230/1463 | Loss: 0.8216 | LM_LOSS: 0.3183 | LB_LOSS: 1.0065 |
| [2026-05-24 02:09:33] Validation | Batch 240/1463 | Loss: 0.8228 | LM_LOSS: 0.3196 | LB_LOSS: 1.0065 |
| [2026-05-24 02:09:36] Validation | Batch 250/1463 | Loss: 0.8221 | LM_LOSS: 0.3188 | LB_LOSS: 1.0065 |
| [2026-05-24 02:09:38] Validation | Batch 260/1463 | Loss: 0.8234 | LM_LOSS: 0.3201 | LB_LOSS: 1.0066 |
| [2026-05-24 02:09:40] Validation | Batch 270/1463 | Loss: 0.8218 | LM_LOSS: 0.3185 | LB_LOSS: 1.0067 |
| [2026-05-24 02:09:42] Validation | Batch 280/1463 | Loss: 0.8224 | LM_LOSS: 0.3191 | LB_LOSS: 1.0067 |
| [2026-05-24 02:09:44] Validation | Batch 290/1463 | Loss: 0.8216 | LM_LOSS: 0.3182 | LB_LOSS: 1.0067 |
| [2026-05-24 02:09:46] Validation | Batch 300/1463 | Loss: 0.8218 | LM_LOSS: 0.3185 | LB_LOSS: 1.0068 |
| [2026-05-24 02:09:48] Validation | Batch 310/1463 | Loss: 0.8228 | LM_LOSS: 0.3194 | LB_LOSS: 1.0067 |
| [2026-05-24 02:09:50] Validation | Batch 320/1463 | Loss: 0.8214 | LM_LOSS: 0.3180 | LB_LOSS: 1.0067 |
| [2026-05-24 02:09:52] Validation | Batch 330/1463 | Loss: 0.8212 | LM_LOSS: 0.3179 | LB_LOSS: 1.0066 |
| [2026-05-24 02:09:54] Validation | Batch 340/1463 | Loss: 0.8208 | LM_LOSS: 0.3175 | LB_LOSS: 1.0066 |
| [2026-05-24 02:09:57] Validation | Batch 350/1463 | Loss: 0.8214 | LM_LOSS: 0.3180 | LB_LOSS: 1.0066 |
| [2026-05-24 02:09:59] Validation | Batch 360/1463 | Loss: 0.8210 | LM_LOSS: 0.3177 | LB_LOSS: 1.0067 |
| [2026-05-24 02:10:00] Validation | Batch 370/1463 | Loss: 0.8206 | LM_LOSS: 0.3173 | LB_LOSS: 1.0067 |
| [2026-05-24 02:10:03] Validation | Batch 380/1463 | Loss: 0.8205 | LM_LOSS: 0.3172 | LB_LOSS: 1.0066 |
| [2026-05-24 02:10:05] Validation | Batch 390/1463 | Loss: 0.8212 | LM_LOSS: 0.3179 | LB_LOSS: 1.0066 |
| [2026-05-24 02:10:07] Validation | Batch 400/1463 | Loss: 0.8210 | LM_LOSS: 0.3177 | LB_LOSS: 1.0067 |
| [2026-05-24 02:10:09] Validation | Batch 410/1463 | Loss: 0.8209 | LM_LOSS: 0.3175 | LB_LOSS: 1.0067 |
| [2026-05-24 02:10:11] Validation | Batch 420/1463 | Loss: 0.8210 | LM_LOSS: 0.3176 | LB_LOSS: 1.0067 |
| [2026-05-24 02:10:14] Validation | Batch 430/1463 | Loss: 0.8204 | LM_LOSS: 0.3170 | LB_LOSS: 1.0067 |
| [2026-05-24 02:10:16] Validation | Batch 440/1463 | Loss: 0.8206 | LM_LOSS: 0.3172 | LB_LOSS: 1.0067 |
| [2026-05-24 02:10:17] Validation | Batch 450/1463 | Loss: 0.8203 | LM_LOSS: 0.3170 | LB_LOSS: 1.0068 |
| [2026-05-24 02:10:20] Validation | Batch 460/1463 | Loss: 0.8203 | LM_LOSS: 0.3169 | LB_LOSS: 1.0067 |
| [2026-05-24 02:10:22] Validation | Batch 470/1463 | Loss: 0.8210 | LM_LOSS: 0.3176 | LB_LOSS: 1.0067 |
| [2026-05-24 02:10:25] Validation | Batch 480/1463 | Loss: 0.8207 | LM_LOSS: 0.3173 | LB_LOSS: 1.0067 |
| [2026-05-24 02:10:27] Validation | Batch 490/1463 | Loss: 0.8205 | LM_LOSS: 0.3171 | LB_LOSS: 1.0067 |
| [2026-05-24 02:10:29] Validation | Batch 500/1463 | Loss: 0.8203 | LM_LOSS: 0.3170 | LB_LOSS: 1.0067 |
| [2026-05-24 02:10:32] Validation | Batch 510/1463 | Loss: 0.8197 | LM_LOSS: 0.3164 | LB_LOSS: 1.0067 |
| [2026-05-24 02:10:33] Validation | Batch 520/1463 | Loss: 0.8194 | LM_LOSS: 0.3161 | LB_LOSS: 1.0067 |
| [2026-05-24 02:10:35] Validation | Batch 530/1463 | Loss: 0.8199 | LM_LOSS: 0.3166 | LB_LOSS: 1.0067 |
| [2026-05-24 02:10:37] Validation | Batch 540/1463 | Loss: 0.8202 | LM_LOSS: 0.3168 | LB_LOSS: 1.0067 |
| [2026-05-24 02:10:39] Validation | Batch 550/1463 | Loss: 0.8197 | LM_LOSS: 0.3163 | LB_LOSS: 1.0067 |
| [2026-05-24 02:10:41] Validation | Batch 560/1463 | Loss: 0.8199 | LM_LOSS: 0.3165 | LB_LOSS: 1.0068 |
| [2026-05-24 02:10:44] Validation | Batch 570/1463 | Loss: 0.8198 | LM_LOSS: 0.3164 | LB_LOSS: 1.0068 |
| [2026-05-24 02:10:46] Validation | Batch 580/1463 | Loss: 0.8195 | LM_LOSS: 0.3161 | LB_LOSS: 1.0068 |
| [2026-05-24 02:10:48] Validation | Batch 590/1463 | Loss: 0.8192 | LM_LOSS: 0.3158 | LB_LOSS: 1.0068 |
| [2026-05-24 02:10:51] Validation | Batch 600/1463 | Loss: 0.8194 | LM_LOSS: 0.3160 | LB_LOSS: 1.0068 |
| [2026-05-24 02:10:53] Validation | Batch 610/1463 | Loss: 0.8196 | LM_LOSS: 0.3162 | LB_LOSS: 1.0068 |
| [2026-05-24 02:10:55] Validation | Batch 620/1463 | Loss: 0.8190 | LM_LOSS: 0.3156 | LB_LOSS: 1.0068 |
| [2026-05-24 02:10:58] Validation | Batch 630/1463 | Loss: 0.8184 | LM_LOSS: 0.3150 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:00] Validation | Batch 640/1463 | Loss: 0.8183 | LM_LOSS: 0.3149 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:01] Validation | Batch 650/1463 | Loss: 0.8178 | LM_LOSS: 0.3144 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:03] Validation | Batch 660/1463 | Loss: 0.8173 | LM_LOSS: 0.3139 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:06] Validation | Batch 670/1463 | Loss: 0.8170 | LM_LOSS: 0.3136 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:07] Validation | Batch 680/1463 | Loss: 0.8169 | LM_LOSS: 0.3135 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:10] Validation | Batch 690/1463 | Loss: 0.8172 | LM_LOSS: 0.3138 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:12] Validation | Batch 700/1463 | Loss: 0.8171 | LM_LOSS: 0.3137 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:14] Validation | Batch 710/1463 | Loss: 0.8174 | LM_LOSS: 0.3140 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:16] Validation | Batch 720/1463 | Loss: 0.8182 | LM_LOSS: 0.3148 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:18] Validation | Batch 730/1463 | Loss: 0.8182 | LM_LOSS: 0.3148 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:20] Validation | Batch 740/1463 | Loss: 0.8178 | LM_LOSS: 0.3144 | LB_LOSS: 1.0069 |
| [2026-05-24 02:11:22] Validation | Batch 750/1463 | Loss: 0.8177 | LM_LOSS: 0.3143 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:23] Validation | Batch 760/1463 | Loss: 0.8176 | LM_LOSS: 0.3142 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:25] Validation | Batch 770/1463 | Loss: 0.8175 | LM_LOSS: 0.3141 | LB_LOSS: 1.0069 |
| [2026-05-24 02:11:27] Validation | Batch 780/1463 | Loss: 0.8174 | LM_LOSS: 0.3140 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:29] Validation | Batch 790/1463 | Loss: 0.8177 | LM_LOSS: 0.3143 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:31] Validation | Batch 800/1463 | Loss: 0.8176 | LM_LOSS: 0.3142 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:33] Validation | Batch 810/1463 | Loss: 0.8173 | LM_LOSS: 0.3139 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:35] Validation | Batch 820/1463 | Loss: 0.8175 | LM_LOSS: 0.3141 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:37] Validation | Batch 830/1463 | Loss: 0.8177 | LM_LOSS: 0.3143 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:40] Validation | Batch 840/1463 | Loss: 0.8177 | LM_LOSS: 0.3143 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:42] Validation | Batch 850/1463 | Loss: 0.8180 | LM_LOSS: 0.3146 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:44] Validation | Batch 860/1463 | Loss: 0.8181 | LM_LOSS: 0.3147 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:46] Validation | Batch 870/1463 | Loss: 0.8182 | LM_LOSS: 0.3147 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:48] Validation | Batch 880/1463 | Loss: 0.8174 | LM_LOSS: 0.3140 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:50] Validation | Batch 890/1463 | Loss: 0.8175 | LM_LOSS: 0.3141 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:53] Validation | Batch 900/1463 | Loss: 0.8171 | LM_LOSS: 0.3137 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:55] Validation | Batch 910/1463 | Loss: 0.8171 | LM_LOSS: 0.3137 | LB_LOSS: 1.0068 |
| [2026-05-24 02:11:58] Validation | Batch 920/1463 | Loss: 0.8172 | LM_LOSS: 0.3138 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:00] Validation | Batch 930/1463 | Loss: 0.8169 | LM_LOSS: 0.3135 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:02] Validation | Batch 940/1463 | Loss: 0.8166 | LM_LOSS: 0.3132 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:04] Validation | Batch 950/1463 | Loss: 0.8169 | LM_LOSS: 0.3135 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:06] Validation | Batch 960/1463 | Loss: 0.8170 | LM_LOSS: 0.3136 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:09] Validation | Batch 970/1463 | Loss: 0.8170 | LM_LOSS: 0.3136 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:11] Validation | Batch 980/1463 | Loss: 0.8174 | LM_LOSS: 0.3140 | LB_LOSS: 1.0067 |
| [2026-05-24 02:12:13] Validation | Batch 990/1463 | Loss: 0.8176 | LM_LOSS: 0.3142 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:15] Validation | Batch 1000/1463 | Loss: 0.8182 | LM_LOSS: 0.3148 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:18] Validation | Batch 1010/1463 | Loss: 0.8182 | LM_LOSS: 0.3148 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:20] Validation | Batch 1020/1463 | Loss: 0.8183 | LM_LOSS: 0.3149 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:22] Validation | Batch 1030/1463 | Loss: 0.8188 | LM_LOSS: 0.3154 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:24] Validation | Batch 1040/1463 | Loss: 0.8184 | LM_LOSS: 0.3150 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:27] Validation | Batch 1050/1463 | Loss: 0.8182 | LM_LOSS: 0.3148 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:29] Validation | Batch 1060/1463 | Loss: 0.8182 | LM_LOSS: 0.3148 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:31] Validation | Batch 1070/1463 | Loss: 0.8181 | LM_LOSS: 0.3147 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:33] Validation | Batch 1080/1463 | Loss: 0.8179 | LM_LOSS: 0.3145 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:35] Validation | Batch 1090/1463 | Loss: 0.8179 | LM_LOSS: 0.3145 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:37] Validation | Batch 1100/1463 | Loss: 0.8178 | LM_LOSS: 0.3144 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:39] Validation | Batch 1110/1463 | Loss: 0.8178 | LM_LOSS: 0.3144 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:41] Validation | Batch 1120/1463 | Loss: 0.8177 | LM_LOSS: 0.3142 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:44] Validation | Batch 1130/1463 | Loss: 0.8174 | LM_LOSS: 0.3140 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:46] Validation | Batch 1140/1463 | Loss: 0.8176 | LM_LOSS: 0.3142 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:49] Validation | Batch 1150/1463 | Loss: 0.8175 | LM_LOSS: 0.3141 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:51] Validation | Batch 1160/1463 | Loss: 0.8174 | LM_LOSS: 0.3140 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:53] Validation | Batch 1170/1463 | Loss: 0.8174 | LM_LOSS: 0.3140 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:55] Validation | Batch 1180/1463 | Loss: 0.8175 | LM_LOSS: 0.3141 | LB_LOSS: 1.0068 |
| [2026-05-24 02:12:57] Validation | Batch 1190/1463 | Loss: 0.8176 | LM_LOSS: 0.3142 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:00] Validation | Batch 1200/1463 | Loss: 0.8176 | LM_LOSS: 0.3142 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:02] Validation | Batch 1210/1463 | Loss: 0.8178 | LM_LOSS: 0.3144 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:04] Validation | Batch 1220/1463 | Loss: 0.8182 | LM_LOSS: 0.3148 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:06] Validation | Batch 1230/1463 | Loss: 0.8182 | LM_LOSS: 0.3148 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:08] Validation | Batch 1240/1463 | Loss: 0.8185 | LM_LOSS: 0.3151 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:10] Validation | Batch 1250/1463 | Loss: 0.8187 | LM_LOSS: 0.3153 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:13] Validation | Batch 1260/1463 | Loss: 0.8186 | LM_LOSS: 0.3152 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:15] Validation | Batch 1270/1463 | Loss: 0.8184 | LM_LOSS: 0.3150 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:17] Validation | Batch 1280/1463 | Loss: 0.8182 | LM_LOSS: 0.3148 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:19] Validation | Batch 1290/1463 | Loss: 0.8182 | LM_LOSS: 0.3148 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:21] Validation | Batch 1300/1463 | Loss: 0.8180 | LM_LOSS: 0.3146 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:24] Validation | Batch 1310/1463 | Loss: 0.8179 | LM_LOSS: 0.3145 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:25] Validation | Batch 1320/1463 | Loss: 0.8179 | LM_LOSS: 0.3145 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:27] Validation | Batch 1330/1463 | Loss: 0.8180 | LM_LOSS: 0.3146 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:29] Validation | Batch 1340/1463 | Loss: 0.8183 | LM_LOSS: 0.3149 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:31] Validation | Batch 1350/1463 | Loss: 0.8183 | LM_LOSS: 0.3149 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:34] Validation | Batch 1360/1463 | Loss: 0.8186 | LM_LOSS: 0.3152 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:36] Validation | Batch 1370/1463 | Loss: 0.8189 | LM_LOSS: 0.3155 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:38] Validation | Batch 1380/1463 | Loss: 0.8186 | LM_LOSS: 0.3153 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:40] Validation | Batch 1390/1463 | Loss: 0.8186 | LM_LOSS: 0.3152 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:43] Validation | Batch 1400/1463 | Loss: 0.8188 | LM_LOSS: 0.3155 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:44] Validation | Batch 1410/1463 | Loss: 0.8191 | LM_LOSS: 0.3157 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:47] Validation | Batch 1420/1463 | Loss: 0.8191 | LM_LOSS: 0.3157 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:49] Validation | Batch 1430/1463 | Loss: 0.8191 | LM_LOSS: 0.3157 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:51] Validation | Batch 1440/1463 | Loss: 0.8195 | LM_LOSS: 0.3161 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:54] Validation | Batch 1450/1463 | Loss: 0.8192 | LM_LOSS: 0.3158 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:56] Validation | Batch 1460/1463 | Loss: 0.8195 | LM_LOSS: 0.3162 | LB_LOSS: 1.0068 |
| [2026-05-24 02:13:57] Validation | Batch 1463/1463 | Loss: 0.8194 | LM_LOSS: 0.3160 | LB_LOSS: 1.0067 |
| [2026-05-24 02:13:57] Validation | Loss: 0.8194 | LM_LOSS: 0.3160 | LB_LOSS: 1.0067 | PPL: 1.37 | Time: 315.99s |
| [2026-05-24 02:14:08] Epoch 2 | Step 5010 | Loss: 0.7556 | LM: 0.2594 | LB: 1.0090 | CL0: 3.2 | CL1: 3.8 | HR0: 0.316/SR0: 0.295 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:14:20] Epoch 2 | Step 5020 | Loss: 0.7559 | LM: 0.2589 | LB: 1.0090 | CL0: 3.2 | CL1: 3.8 | HR0: 0.316/SR0: 0.295 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:14:31] Epoch 2 | Step 5030 | Loss: 0.7561 | LM: 0.2591 | LB: 1.0090 | CL0: 3.2 | CL1: 3.8 | HR0: 0.316/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:14:43] Epoch 2 | Step 5040 | Loss: 0.7555 | LM: 0.2580 | LB: 1.0090 | CL0: 3.2 | CL1: 3.8 | HR0: 0.316/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:14:54] Epoch 2 | Step 5050 | Loss: 0.7550 | LM: 0.2576 | LB: 1.0090 | CL0: 3.2 | CL1: 3.8 | HR0: 0.316/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:15:06] Epoch 2 | Step 5060 | Loss: 0.7548 | LM: 0.2581 | LB: 1.0089 | CL0: 3.2 | CL1: 3.8 | HR0: 0.316/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:15:17] Epoch 2 | Step 5070 | Loss: 0.7543 | LM: 0.2580 | LB: 1.0089 | CL0: 3.2 | CL1: 3.8 | HR0: 0.316/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:15:29] Epoch 2 | Step 5080 | Loss: 0.7541 | LM: 0.2590 | LB: 1.0090 | CL0: 3.2 | CL1: 3.8 | HR0: 0.316/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:15:41] Epoch 2 | Step 5090 | Loss: 0.7542 | LM: 0.2594 | LB: 1.0090 | CL0: 3.2 | CL1: 3.8 | HR0: 0.316/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:15:52] Epoch 2 | Step 5100 | Loss: 0.7543 | LM: 0.2596 | LB: 1.0090 | CL0: 3.2 | CL1: 3.8 | HR0: 0.316/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:16:04] Epoch 2 | Step 5110 | Loss: 0.7545 | LM: 0.2579 | LB: 1.0089 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:16:15] Epoch 2 | Step 5120 | Loss: 0.7547 | LM: 0.2596 | LB: 1.0089 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:16:26] Epoch 2 | Step 5130 | Loss: 0.7549 | LM: 0.2610 | LB: 1.0089 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:16:38] Epoch 2 | Step 5140 | Loss: 0.7549 | LM: 0.2614 | LB: 1.0089 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:16:49] Epoch 2 | Step 5150 | Loss: 0.7543 | LM: 0.2605 | LB: 1.0089 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:17:01] Epoch 2 | Step 5160 | Loss: 0.7539 | LM: 0.2604 | LB: 1.0089 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:17:12] Epoch 2 | Step 5170 | Loss: 0.7536 | LM: 0.2592 | LB: 1.0089 | CL0: 3.2 | CL1: 3.8 | HR0: 0.316/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:17:24] Epoch 2 | Step 5180 | Loss: 0.7539 | LM: 0.2590 | LB: 1.0089 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:17:35] Epoch 2 | Step 5190 | Loss: 0.7537 | LM: 0.2586 | LB: 1.0089 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:17:46] Epoch 2 | Step 5200 | Loss: 0.7541 | LM: 0.2588 | LB: 1.0088 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:17:57] Epoch 2 | Step 5210 | Loss: 0.7541 | LM: 0.2577 | LB: 1.0088 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:18:09] Epoch 2 | Step 5220 | Loss: 0.7543 | LM: 0.2583 | LB: 1.0088 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:18:21] Epoch 2 | Step 5230 | Loss: 0.7547 | LM: 0.2588 | LB: 1.0088 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:18:32] Epoch 2 | Step 5240 | Loss: 0.7547 | LM: 0.2591 | LB: 1.0088 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:18:43] Epoch 2 | Step 5250 | Loss: 0.7548 | LM: 0.2593 | LB: 1.0088 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:18:55] Epoch 2 | Step 5260 | Loss: 0.7550 | LM: 0.2598 | LB: 1.0088 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:19:06] Epoch 2 | Step 5270 | Loss: 0.7550 | LM: 0.2595 | LB: 1.0088 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.294 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:19:18] Epoch 2 | Step 5280 | Loss: 0.7553 | LM: 0.2605 | LB: 1.0088 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.294 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:19:30] Epoch 2 | Step 5290 | Loss: 0.7556 | LM: 0.2596 | LB: 1.0088 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.295 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:19:41] Epoch 2 | Step 5300 | Loss: 0.7556 | LM: 0.2600 | LB: 1.0088 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.294 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:19:52] Epoch 2 | Step 5310 | Loss: 0.7558 | LM: 0.2603 | LB: 1.0087 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.294 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:20:04] Epoch 2 | Step 5320 | Loss: 0.7559 | LM: 0.2597 | LB: 1.0087 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.294 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:20:16] Epoch 2 | Step 5330 | Loss: 0.7556 | LM: 0.2596 | LB: 1.0087 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.294 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:20:27] Epoch 2 | Step 5340 | Loss: 0.7554 | LM: 0.2596 | LB: 1.0087 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.294 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:20:39] Epoch 2 | Step 5350 | Loss: 0.7551 | LM: 0.2591 | LB: 1.0086 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.294 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:20:50] Epoch 2 | Step 5360 | Loss: 0.7551 | LM: 0.2584 | LB: 1.0086 | CL0: 3.2 | CL1: 3.8 | HR0: 0.315/SR0: 0.294 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:21:01] Epoch 2 | Step 5370 | Loss: 0.7556 | LM: 0.2585 | LB: 1.0085 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.294 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:21:12] Epoch 2 | Step 5380 | Loss: 0.7553 | LM: 0.2585 | LB: 1.0085 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.294 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:21:24] Epoch 2 | Step 5390 | Loss: 0.7552 | LM: 0.2585 | LB: 1.0085 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.294 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:21:36] Epoch 2 | Step 5400 | Loss: 0.7553 | LM: 0.2576 | LB: 1.0085 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:21:47] Epoch 2 | Step 5410 | Loss: 0.7555 | LM: 0.2576 | LB: 1.0085 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:22:00] Epoch 2 | Step 5420 | Loss: 0.7554 | LM: 0.2577 | LB: 1.0084 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:22:11] Epoch 2 | Step 5430 | Loss: 0.7556 | LM: 0.2576 | LB: 1.0084 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:22:23] Epoch 2 | Step 5440 | Loss: 0.7553 | LM: 0.2572 | LB: 1.0083 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:22:34] Epoch 2 | Step 5450 | Loss: 0.7553 | LM: 0.2571 | LB: 1.0083 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:22:46] Epoch 2 | Step 5460 | Loss: 0.7552 | LM: 0.2570 | LB: 1.0084 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 02:22:57] Epoch 2 | Step 5470 | Loss: 0.7552 | LM: 0.2566 | LB: 1.0083 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:23:08] Epoch 2 | Step 5480 | Loss: 0.7550 | LM: 0.2565 | LB: 1.0083 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:23:20] Epoch 2 | Step 5490 | Loss: 0.7547 | LM: 0.2565 | LB: 1.0083 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:23:32] Epoch 2 | Step 5500 | Loss: 0.7548 | LM: 0.2567 | LB: 1.0083 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:23:43] Epoch 2 | Step 5510 | Loss: 0.7547 | LM: 0.2563 | LB: 1.0083 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:23:55] Epoch 2 | Step 5520 | Loss: 0.7550 | LM: 0.2561 | LB: 1.0083 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:24:06] Epoch 2 | Step 5530 | Loss: 0.7548 | LM: 0.2560 | LB: 1.0083 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:24:18] Epoch 2 | Step 5540 | Loss: 0.7545 | LM: 0.2558 | LB: 1.0084 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:24:30] Epoch 2 | Step 5550 | Loss: 0.7545 | LM: 0.2563 | LB: 1.0084 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:24:41] Epoch 2 | Step 5560 | Loss: 0.7544 | LM: 0.2557 | LB: 1.0083 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:24:53] Epoch 2 | Step 5570 | Loss: 0.7542 | LM: 0.2552 | LB: 1.0083 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:25:05] Epoch 2 | Step 5580 | Loss: 0.7542 | LM: 0.2551 | LB: 1.0083 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:25:16] Epoch 2 | Step 5590 | Loss: 0.7543 | LM: 0.2552 | LB: 1.0083 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:25:27] Epoch 2 | Step 5600 | Loss: 0.7543 | LM: 0.2554 | LB: 1.0083 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:25:38] Epoch 2 | Step 5610 | Loss: 0.7545 | LM: 0.2559 | LB: 1.0083 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:25:49] Epoch 2 | Step 5620 | Loss: 0.7544 | LM: 0.2560 | LB: 1.0083 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:26:01] Epoch 2 | Step 5630 | Loss: 0.7545 | LM: 0.2559 | LB: 1.0082 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:26:12] Epoch 2 | Step 5640 | Loss: 0.7547 | LM: 0.2560 | LB: 1.0083 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:26:22] Epoch 2 | Step 5650 | Loss: 0.7547 | LM: 0.2558 | LB: 1.0082 | CL0: 3.2 | CL1: 3.8 | HR0: 0.314/SR0: 0.293 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:26:33] Epoch 2 | Step 5660 | Loss: 0.7545 | LM: 0.2550 | LB: 1.0082 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.293 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:26:44] Epoch 2 | Step 5670 | Loss: 0.7542 | LM: 0.2546 | LB: 1.0082 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:26:55] Epoch 2 | Step 5680 | Loss: 0.7544 | LM: 0.2546 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:27:06] Epoch 2 | Step 5690 | Loss: 0.7543 | LM: 0.2541 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:27:17] Epoch 2 | Step 5700 | Loss: 0.7542 | LM: 0.2541 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:27:29] Epoch 2 | Step 5710 | Loss: 0.7544 | LM: 0.2543 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:27:41] Epoch 2 | Step 5720 | Loss: 0.7548 | LM: 0.2551 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:27:53] Epoch 2 | Step 5730 | Loss: 0.7549 | LM: 0.2552 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:28:05] Epoch 2 | Step 5740 | Loss: 0.7550 | LM: 0.2550 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:28:16] Epoch 2 | Step 5750 | Loss: 0.7551 | LM: 0.2547 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:28:28] Epoch 2 | Step 5760 | Loss: 0.7554 | LM: 0.2550 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:28:40] Epoch 2 | Step 5770 | Loss: 0.7553 | LM: 0.2551 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:28:52] Epoch 2 | Step 5780 | Loss: 0.7554 | LM: 0.2551 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:29:04] Epoch 2 | Step 5790 | Loss: 0.7556 | LM: 0.2553 | LB: 1.0081 | CL0: 3.2 | CL1: 3.7 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:29:16] Epoch 2 | Step 5800 | Loss: 0.7557 | LM: 0.2554 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:29:27] Epoch 2 | Step 5810 | Loss: 0.7556 | LM: 0.2554 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:29:39] Epoch 2 | Step 5820 | Loss: 0.7559 | LM: 0.2555 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:29:51] Epoch 2 | Step 5830 | Loss: 0.7560 | LM: 0.2552 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:30:03] Epoch 2 | Step 5840 | Loss: 0.7562 | LM: 0.2551 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:30:14] Epoch 2 | Step 5850 | Loss: 0.7564 | LM: 0.2548 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:30:24] Epoch 2 | Step 5860 | Loss: 0.7562 | LM: 0.2545 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:30:36] Epoch 2 | Step 5870 | Loss: 0.7561 | LM: 0.2547 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:30:47] Epoch 2 | Step 5880 | Loss: 0.7560 | LM: 0.2543 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:30:57] Epoch 2 | Step 5890 | Loss: 0.7560 | LM: 0.2540 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:31:08] Epoch 2 | Step 5900 | Loss: 0.7561 | LM: 0.2542 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:31:19] Epoch 2 | Step 5910 | Loss: 0.7560 | LM: 0.2538 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:31:30] Epoch 2 | Step 5920 | Loss: 0.7560 | LM: 0.2537 | LB: 1.0081 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:31:41] Epoch 2 | Step 5930 | Loss: 0.7561 | LM: 0.2539 | LB: 1.0081 | CL0: 3.2 | CL1: 3.7 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:31:53] Epoch 2 | Step 5940 | Loss: 0.7563 | LM: 0.2537 | LB: 1.0081 | CL0: 3.2 | CL1: 3.7 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:32:04] Epoch 2 | Step 5950 | Loss: 0.7563 | LM: 0.2537 | LB: 1.0080 | CL0: 3.2 | CL1: 3.7 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:32:15] Epoch 2 | Step 5960 | Loss: 0.7562 | LM: 0.2538 | LB: 1.0080 | CL0: 3.2 | CL1: 3.7 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:32:26] Epoch 2 | Step 5970 | Loss: 0.7561 | LM: 0.2536 | LB: 1.0080 | CL0: 3.2 | CL1: 3.7 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:32:36] Epoch 2 | Step 5980 | Loss: 0.7562 | LM: 0.2536 | LB: 1.0080 | CL0: 3.2 | CL1: 3.7 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:32:47] Epoch 2 | Step 5990 | Loss: 0.7562 | LM: 0.2535 | LB: 1.0080 | CL0: 3.2 | CL1: 3.7 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:32:58] Epoch 2 | Step 6000 | Loss: 0.7562 | LM: 0.2537 | LB: 1.0080 | CL0: 3.2 | CL1: 3.7 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:33:03] Checkpoint saved: outputs/2026-05-24/N_4.0/checkpoints/checkpoint_step_6000.pt |
| [2026-05-24 02:33:12] Validation | Batch 10/1463 | Loss: 0.7880 | LM_LOSS: 0.2862 | LB_LOSS: 1.0036 |
| [2026-05-24 02:33:13] Validation | Batch 20/1463 | Loss: 0.7972 | LM_LOSS: 0.2949 | LB_LOSS: 1.0047 |
| [2026-05-24 02:33:16] Validation | Batch 30/1463 | Loss: 0.7998 | LM_LOSS: 0.2972 | LB_LOSS: 1.0051 |
| [2026-05-24 02:33:18] Validation | Batch 40/1463 | Loss: 0.8073 | LM_LOSS: 0.3044 | LB_LOSS: 1.0057 |
| [2026-05-24 02:33:20] Validation | Batch 50/1463 | Loss: 0.8151 | LM_LOSS: 0.3124 | LB_LOSS: 1.0054 |
| [2026-05-24 02:33:23] Validation | Batch 60/1463 | Loss: 0.8145 | LM_LOSS: 0.3119 | LB_LOSS: 1.0053 |
| [2026-05-24 02:33:25] Validation | Batch 70/1463 | Loss: 0.8146 | LM_LOSS: 0.3119 | LB_LOSS: 1.0053 |
| [2026-05-24 02:33:28] Validation | Batch 80/1463 | Loss: 0.8166 | LM_LOSS: 0.3139 | LB_LOSS: 1.0053 |
| [2026-05-24 02:33:30] Validation | Batch 90/1463 | Loss: 0.8156 | LM_LOSS: 0.3130 | LB_LOSS: 1.0052 |
| [2026-05-24 02:33:32] Validation | Batch 100/1463 | Loss: 0.8155 | LM_LOSS: 0.3129 | LB_LOSS: 1.0052 |
| [2026-05-24 02:33:34] Validation | Batch 110/1463 | Loss: 0.8137 | LM_LOSS: 0.3110 | LB_LOSS: 1.0054 |
| [2026-05-24 02:33:36] Validation | Batch 120/1463 | Loss: 0.8155 | LM_LOSS: 0.3128 | LB_LOSS: 1.0055 |
| [2026-05-24 02:33:38] Validation | Batch 130/1463 | Loss: 0.8170 | LM_LOSS: 0.3142 | LB_LOSS: 1.0056 |
| [2026-05-24 02:33:40] Validation | Batch 140/1463 | Loss: 0.8183 | LM_LOSS: 0.3155 | LB_LOSS: 1.0055 |
| [2026-05-24 02:33:42] Validation | Batch 150/1463 | Loss: 0.8165 | LM_LOSS: 0.3136 | LB_LOSS: 1.0056 |
| [2026-05-24 02:33:45] Validation | Batch 160/1463 | Loss: 0.8168 | LM_LOSS: 0.3140 | LB_LOSS: 1.0056 |
| [2026-05-24 02:33:47] Validation | Batch 170/1463 | Loss: 0.8159 | LM_LOSS: 0.3131 | LB_LOSS: 1.0056 |
| [2026-05-24 02:33:49] Validation | Batch 180/1463 | Loss: 0.8168 | LM_LOSS: 0.3140 | LB_LOSS: 1.0056 |
| [2026-05-24 02:33:51] Validation | Batch 190/1463 | Loss: 0.8183 | LM_LOSS: 0.3155 | LB_LOSS: 1.0056 |
| [2026-05-24 02:33:53] Validation | Batch 200/1463 | Loss: 0.8182 | LM_LOSS: 0.3154 | LB_LOSS: 1.0056 |
| [2026-05-24 02:33:56] Validation | Batch 210/1463 | Loss: 0.8187 | LM_LOSS: 0.3159 | LB_LOSS: 1.0056 |
| [2026-05-24 02:33:58] Validation | Batch 220/1463 | Loss: 0.8181 | LM_LOSS: 0.3153 | LB_LOSS: 1.0056 |
| [2026-05-24 02:34:00] Validation | Batch 230/1463 | Loss: 0.8197 | LM_LOSS: 0.3169 | LB_LOSS: 1.0055 |
| [2026-05-24 02:34:02] Validation | Batch 240/1463 | Loss: 0.8211 | LM_LOSS: 0.3183 | LB_LOSS: 1.0055 |
| [2026-05-24 02:34:05] Validation | Batch 250/1463 | Loss: 0.8203 | LM_LOSS: 0.3175 | LB_LOSS: 1.0055 |
| [2026-05-24 02:34:07] Validation | Batch 260/1463 | Loss: 0.8219 | LM_LOSS: 0.3191 | LB_LOSS: 1.0056 |
| [2026-05-24 02:34:09] Validation | Batch 270/1463 | Loss: 0.8203 | LM_LOSS: 0.3174 | LB_LOSS: 1.0057 |
| [2026-05-24 02:34:11] Validation | Batch 280/1463 | Loss: 0.8207 | LM_LOSS: 0.3179 | LB_LOSS: 1.0057 |
| [2026-05-24 02:34:14] Validation | Batch 290/1463 | Loss: 0.8198 | LM_LOSS: 0.3170 | LB_LOSS: 1.0057 |
| [2026-05-24 02:34:15] Validation | Batch 300/1463 | Loss: 0.8202 | LM_LOSS: 0.3174 | LB_LOSS: 1.0058 |
| [2026-05-24 02:34:18] Validation | Batch 310/1463 | Loss: 0.8211 | LM_LOSS: 0.3182 | LB_LOSS: 1.0057 |
| [2026-05-24 02:34:20] Validation | Batch 320/1463 | Loss: 0.8198 | LM_LOSS: 0.3170 | LB_LOSS: 1.0057 |
| [2026-05-24 02:34:22] Validation | Batch 330/1463 | Loss: 0.8196 | LM_LOSS: 0.3168 | LB_LOSS: 1.0056 |
| [2026-05-24 02:34:24] Validation | Batch 340/1463 | Loss: 0.8193 | LM_LOSS: 0.3164 | LB_LOSS: 1.0056 |
| [2026-05-24 02:34:26] Validation | Batch 350/1463 | Loss: 0.8197 | LM_LOSS: 0.3169 | LB_LOSS: 1.0056 |
| [2026-05-24 02:34:28] Validation | Batch 360/1463 | Loss: 0.8196 | LM_LOSS: 0.3167 | LB_LOSS: 1.0057 |
| [2026-05-24 02:34:30] Validation | Batch 370/1463 | Loss: 0.8192 | LM_LOSS: 0.3164 | LB_LOSS: 1.0057 |
| [2026-05-24 02:34:32] Validation | Batch 380/1463 | Loss: 0.8191 | LM_LOSS: 0.3163 | LB_LOSS: 1.0056 |
| [2026-05-24 02:34:34] Validation | Batch 390/1463 | Loss: 0.8198 | LM_LOSS: 0.3170 | LB_LOSS: 1.0056 |
| [2026-05-24 02:34:36] Validation | Batch 400/1463 | Loss: 0.8196 | LM_LOSS: 0.3168 | LB_LOSS: 1.0057 |
| [2026-05-24 02:34:38] Validation | Batch 410/1463 | Loss: 0.8195 | LM_LOSS: 0.3167 | LB_LOSS: 1.0057 |
| [2026-05-24 02:34:41] Validation | Batch 420/1463 | Loss: 0.8196 | LM_LOSS: 0.3168 | LB_LOSS: 1.0057 |
| [2026-05-24 02:34:43] Validation | Batch 430/1463 | Loss: 0.8190 | LM_LOSS: 0.3162 | LB_LOSS: 1.0057 |
| [2026-05-24 02:34:45] Validation | Batch 440/1463 | Loss: 0.8193 | LM_LOSS: 0.3165 | LB_LOSS: 1.0057 |
| [2026-05-24 02:34:47] Validation | Batch 450/1463 | Loss: 0.8191 | LM_LOSS: 0.3162 | LB_LOSS: 1.0058 |
| [2026-05-24 02:34:49] Validation | Batch 460/1463 | Loss: 0.8191 | LM_LOSS: 0.3162 | LB_LOSS: 1.0057 |
| [2026-05-24 02:34:52] Validation | Batch 470/1463 | Loss: 0.8197 | LM_LOSS: 0.3169 | LB_LOSS: 1.0057 |
| [2026-05-24 02:34:54] Validation | Batch 480/1463 | Loss: 0.8194 | LM_LOSS: 0.3166 | LB_LOSS: 1.0057 |
| [2026-05-24 02:34:56] Validation | Batch 490/1463 | Loss: 0.8193 | LM_LOSS: 0.3165 | LB_LOSS: 1.0057 |
| [2026-05-24 02:34:59] Validation | Batch 500/1463 | Loss: 0.8191 | LM_LOSS: 0.3163 | LB_LOSS: 1.0057 |
| [2026-05-24 02:35:01] Validation | Batch 510/1463 | Loss: 0.8185 | LM_LOSS: 0.3157 | LB_LOSS: 1.0057 |
| [2026-05-24 02:35:03] Validation | Batch 520/1463 | Loss: 0.8182 | LM_LOSS: 0.3154 | LB_LOSS: 1.0057 |
| [2026-05-24 02:35:05] Validation | Batch 530/1463 | Loss: 0.8187 | LM_LOSS: 0.3158 | LB_LOSS: 1.0057 |
| [2026-05-24 02:35:07] Validation | Batch 540/1463 | Loss: 0.8189 | LM_LOSS: 0.3161 | LB_LOSS: 1.0057 |
| [2026-05-24 02:35:08] Validation | Batch 550/1463 | Loss: 0.8184 | LM_LOSS: 0.3156 | LB_LOSS: 1.0057 |
| [2026-05-24 02:35:11] Validation | Batch 560/1463 | Loss: 0.8187 | LM_LOSS: 0.3158 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:13] Validation | Batch 570/1463 | Loss: 0.8187 | LM_LOSS: 0.3158 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:15] Validation | Batch 580/1463 | Loss: 0.8182 | LM_LOSS: 0.3154 | LB_LOSS: 1.0057 |
| [2026-05-24 02:35:18] Validation | Batch 590/1463 | Loss: 0.8180 | LM_LOSS: 0.3151 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:20] Validation | Batch 600/1463 | Loss: 0.8182 | LM_LOSS: 0.3153 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:23] Validation | Batch 610/1463 | Loss: 0.8184 | LM_LOSS: 0.3155 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:25] Validation | Batch 620/1463 | Loss: 0.8178 | LM_LOSS: 0.3149 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:27] Validation | Batch 630/1463 | Loss: 0.8173 | LM_LOSS: 0.3143 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:29] Validation | Batch 640/1463 | Loss: 0.8171 | LM_LOSS: 0.3142 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:31] Validation | Batch 650/1463 | Loss: 0.8166 | LM_LOSS: 0.3137 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:33] Validation | Batch 660/1463 | Loss: 0.8161 | LM_LOSS: 0.3132 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:35] Validation | Batch 670/1463 | Loss: 0.8158 | LM_LOSS: 0.3129 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:37] Validation | Batch 680/1463 | Loss: 0.8157 | LM_LOSS: 0.3128 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:39] Validation | Batch 690/1463 | Loss: 0.8160 | LM_LOSS: 0.3131 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:41] Validation | Batch 700/1463 | Loss: 0.8159 | LM_LOSS: 0.3130 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:43] Validation | Batch 710/1463 | Loss: 0.8162 | LM_LOSS: 0.3133 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:46] Validation | Batch 720/1463 | Loss: 0.8170 | LM_LOSS: 0.3141 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:47] Validation | Batch 730/1463 | Loss: 0.8169 | LM_LOSS: 0.3140 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:49] Validation | Batch 740/1463 | Loss: 0.8165 | LM_LOSS: 0.3136 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:51] Validation | Batch 750/1463 | Loss: 0.8164 | LM_LOSS: 0.3135 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:53] Validation | Batch 760/1463 | Loss: 0.8163 | LM_LOSS: 0.3134 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:55] Validation | Batch 770/1463 | Loss: 0.8162 | LM_LOSS: 0.3133 | LB_LOSS: 1.0059 |
| [2026-05-24 02:35:57] Validation | Batch 780/1463 | Loss: 0.8161 | LM_LOSS: 0.3132 | LB_LOSS: 1.0058 |
| [2026-05-24 02:35:58] Validation | Batch 790/1463 | Loss: 0.8164 | LM_LOSS: 0.3135 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:00] Validation | Batch 800/1463 | Loss: 0.8164 | LM_LOSS: 0.3135 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:02] Validation | Batch 810/1463 | Loss: 0.8160 | LM_LOSS: 0.3131 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:04] Validation | Batch 820/1463 | Loss: 0.8162 | LM_LOSS: 0.3133 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:06] Validation | Batch 830/1463 | Loss: 0.8164 | LM_LOSS: 0.3135 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:09] Validation | Batch 840/1463 | Loss: 0.8165 | LM_LOSS: 0.3136 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:11] Validation | Batch 850/1463 | Loss: 0.8168 | LM_LOSS: 0.3139 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:13] Validation | Batch 860/1463 | Loss: 0.8170 | LM_LOSS: 0.3141 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:16] Validation | Batch 870/1463 | Loss: 0.8170 | LM_LOSS: 0.3141 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:18] Validation | Batch 880/1463 | Loss: 0.8162 | LM_LOSS: 0.3133 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:20] Validation | Batch 890/1463 | Loss: 0.8163 | LM_LOSS: 0.3134 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:22] Validation | Batch 900/1463 | Loss: 0.8159 | LM_LOSS: 0.3130 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:24] Validation | Batch 910/1463 | Loss: 0.8159 | LM_LOSS: 0.3130 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:27] Validation | Batch 920/1463 | Loss: 0.8160 | LM_LOSS: 0.3131 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:29] Validation | Batch 930/1463 | Loss: 0.8156 | LM_LOSS: 0.3127 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:31] Validation | Batch 940/1463 | Loss: 0.8154 | LM_LOSS: 0.3125 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:33] Validation | Batch 950/1463 | Loss: 0.8156 | LM_LOSS: 0.3127 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:35] Validation | Batch 960/1463 | Loss: 0.8156 | LM_LOSS: 0.3127 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:38] Validation | Batch 970/1463 | Loss: 0.8157 | LM_LOSS: 0.3128 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:40] Validation | Batch 980/1463 | Loss: 0.8160 | LM_LOSS: 0.3131 | LB_LOSS: 1.0057 |
| [2026-05-24 02:36:42] Validation | Batch 990/1463 | Loss: 0.8163 | LM_LOSS: 0.3134 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:44] Validation | Batch 1000/1463 | Loss: 0.8168 | LM_LOSS: 0.3140 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:46] Validation | Batch 1010/1463 | Loss: 0.8169 | LM_LOSS: 0.3140 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:49] Validation | Batch 1020/1463 | Loss: 0.8169 | LM_LOSS: 0.3140 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:51] Validation | Batch 1030/1463 | Loss: 0.8174 | LM_LOSS: 0.3145 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:53] Validation | Batch 1040/1463 | Loss: 0.8171 | LM_LOSS: 0.3142 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:55] Validation | Batch 1050/1463 | Loss: 0.8170 | LM_LOSS: 0.3141 | LB_LOSS: 1.0058 |
| [2026-05-24 02:36:58] Validation | Batch 1060/1463 | Loss: 0.8170 | LM_LOSS: 0.3141 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:00] Validation | Batch 1070/1463 | Loss: 0.8169 | LM_LOSS: 0.3140 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:02] Validation | Batch 1080/1463 | Loss: 0.8168 | LM_LOSS: 0.3138 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:04] Validation | Batch 1090/1463 | Loss: 0.8167 | LM_LOSS: 0.3138 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:06] Validation | Batch 1100/1463 | Loss: 0.8166 | LM_LOSS: 0.3137 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:08] Validation | Batch 1110/1463 | Loss: 0.8165 | LM_LOSS: 0.3136 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:10] Validation | Batch 1120/1463 | Loss: 0.8164 | LM_LOSS: 0.3134 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:13] Validation | Batch 1130/1463 | Loss: 0.8161 | LM_LOSS: 0.3132 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:15] Validation | Batch 1140/1463 | Loss: 0.8163 | LM_LOSS: 0.3134 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:17] Validation | Batch 1150/1463 | Loss: 0.8162 | LM_LOSS: 0.3133 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:19] Validation | Batch 1160/1463 | Loss: 0.8161 | LM_LOSS: 0.3132 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:21] Validation | Batch 1170/1463 | Loss: 0.8161 | LM_LOSS: 0.3132 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:24] Validation | Batch 1180/1463 | Loss: 0.8162 | LM_LOSS: 0.3133 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:26] Validation | Batch 1190/1463 | Loss: 0.8163 | LM_LOSS: 0.3134 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:28] Validation | Batch 1200/1463 | Loss: 0.8163 | LM_LOSS: 0.3134 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:30] Validation | Batch 1210/1463 | Loss: 0.8164 | LM_LOSS: 0.3135 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:32] Validation | Batch 1220/1463 | Loss: 0.8169 | LM_LOSS: 0.3140 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:34] Validation | Batch 1230/1463 | Loss: 0.8169 | LM_LOSS: 0.3140 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:36] Validation | Batch 1240/1463 | Loss: 0.8171 | LM_LOSS: 0.3142 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:39] Validation | Batch 1250/1463 | Loss: 0.8173 | LM_LOSS: 0.3144 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:41] Validation | Batch 1260/1463 | Loss: 0.8172 | LM_LOSS: 0.3143 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:43] Validation | Batch 1270/1463 | Loss: 0.8170 | LM_LOSS: 0.3141 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:46] Validation | Batch 1280/1463 | Loss: 0.8168 | LM_LOSS: 0.3139 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:48] Validation | Batch 1290/1463 | Loss: 0.8168 | LM_LOSS: 0.3139 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:50] Validation | Batch 1300/1463 | Loss: 0.8166 | LM_LOSS: 0.3137 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:52] Validation | Batch 1310/1463 | Loss: 0.8164 | LM_LOSS: 0.3135 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:54] Validation | Batch 1320/1463 | Loss: 0.8165 | LM_LOSS: 0.3136 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:55] Validation | Batch 1330/1463 | Loss: 0.8166 | LM_LOSS: 0.3137 | LB_LOSS: 1.0058 |
| [2026-05-24 02:37:57] Validation | Batch 1340/1463 | Loss: 0.8169 | LM_LOSS: 0.3140 | LB_LOSS: 1.0058 |
| [2026-05-24 02:38:00] Validation | Batch 1350/1463 | Loss: 0.8169 | LM_LOSS: 0.3140 | LB_LOSS: 1.0058 |
| [2026-05-24 02:38:02] Validation | Batch 1360/1463 | Loss: 0.8172 | LM_LOSS: 0.3143 | LB_LOSS: 1.0058 |
| [2026-05-24 02:38:05] Validation | Batch 1370/1463 | Loss: 0.8175 | LM_LOSS: 0.3146 | LB_LOSS: 1.0058 |
| [2026-05-24 02:38:07] Validation | Batch 1380/1463 | Loss: 0.8172 | LM_LOSS: 0.3143 | LB_LOSS: 1.0058 |
| [2026-05-24 02:38:09] Validation | Batch 1390/1463 | Loss: 0.8172 | LM_LOSS: 0.3143 | LB_LOSS: 1.0058 |
| [2026-05-24 02:38:11] Validation | Batch 1400/1463 | Loss: 0.8175 | LM_LOSS: 0.3146 | LB_LOSS: 1.0058 |
| [2026-05-24 02:38:13] Validation | Batch 1410/1463 | Loss: 0.8177 | LM_LOSS: 0.3148 | LB_LOSS: 1.0058 |
| [2026-05-24 02:38:15] Validation | Batch 1420/1463 | Loss: 0.8177 | LM_LOSS: 0.3148 | LB_LOSS: 1.0058 |
| [2026-05-24 02:38:17] Validation | Batch 1430/1463 | Loss: 0.8177 | LM_LOSS: 0.3148 | LB_LOSS: 1.0058 |
| [2026-05-24 02:38:20] Validation | Batch 1440/1463 | Loss: 0.8181 | LM_LOSS: 0.3152 | LB_LOSS: 1.0058 |
| [2026-05-24 02:38:22] Validation | Batch 1450/1463 | Loss: 0.8178 | LM_LOSS: 0.3149 | LB_LOSS: 1.0058 |
| [2026-05-24 02:38:24] Validation | Batch 1460/1463 | Loss: 0.8181 | LM_LOSS: 0.3153 | LB_LOSS: 1.0058 |
| [2026-05-24 02:38:25] Validation | Batch 1463/1463 | Loss: 0.8180 | LM_LOSS: 0.3151 | LB_LOSS: 1.0058 |
| [2026-05-24 02:38:25] Validation | Loss: 0.8180 | LM_LOSS: 0.3151 | LB_LOSS: 1.0058 | PPL: 1.37 | Time: 314.92s |
| [2026-05-24 02:38:36] Epoch 2 | Step 6010 | Loss: 0.7561 | LM: 0.2536 | LB: 1.0080 | CL0: 3.2 | CL1: 3.7 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:38:46] Epoch 2 | Step 6020 | Loss: 0.7559 | LM: 0.2535 | LB: 1.0079 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:38:57] Epoch 2 | Step 6030 | Loss: 0.7559 | LM: 0.2536 | LB: 1.0079 | CL0: 3.2 | CL1: 3.7 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:39:08] Epoch 2 | Step 6040 | Loss: 0.7561 | LM: 0.2533 | LB: 1.0080 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:39:20] Epoch 2 | Step 6050 | Loss: 0.7562 | LM: 0.2538 | LB: 1.0080 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:39:31] Epoch 2 | Step 6060 | Loss: 0.7562 | LM: 0.2539 | LB: 1.0080 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:39:42] Epoch 2 | Step 6070 | Loss: 0.7561 | LM: 0.2538 | LB: 1.0080 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:39:53] Epoch 2 | Step 6080 | Loss: 0.7564 | LM: 0.2540 | LB: 1.0080 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:40:04] Epoch 2 | Step 6090 | Loss: 0.7564 | LM: 0.2540 | LB: 1.0080 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:40:14] Epoch 2 | Step 6100 | Loss: 0.7565 | LM: 0.2542 | LB: 1.0080 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:40:26] Epoch 2 | Step 6110 | Loss: 0.7564 | LM: 0.2545 | LB: 1.0080 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:40:36] Epoch 2 | Step 6120 | Loss: 0.7564 | LM: 0.2544 | LB: 1.0080 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:40:48] Epoch 2 | Step 6130 | Loss: 0.7564 | LM: 0.2545 | LB: 1.0080 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:40:59] Epoch 2 | Step 6140 | Loss: 0.7562 | LM: 0.2544 | LB: 1.0080 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:41:11] Epoch 2 | Step 6150 | Loss: 0.7563 | LM: 0.2544 | LB: 1.0080 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:41:22] Epoch 2 | Step 6160 | Loss: 0.7562 | LM: 0.2543 | LB: 1.0080 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:41:33] Epoch 2 | Step 6170 | Loss: 0.7562 | LM: 0.2540 | LB: 1.0079 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:41:44] Epoch 2 | Step 6180 | Loss: 0.7564 | LM: 0.2540 | LB: 1.0079 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:41:55] Epoch 2 | Step 6190 | Loss: 0.7562 | LM: 0.2537 | LB: 1.0079 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:42:06] Epoch 2 | Step 6200 | Loss: 0.7563 | LM: 0.2538 | LB: 1.0079 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.292 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:42:17] Epoch 2 | Step 6210 | Loss: 0.7563 | LM: 0.2538 | LB: 1.0079 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:42:28] Epoch 2 | Step 6220 | Loss: 0.7564 | LM: 0.2541 | LB: 1.0079 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:42:40] Epoch 2 | Step 6230 | Loss: 0.7564 | LM: 0.2541 | LB: 1.0079 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:42:52] Epoch 2 | Step 6240 | Loss: 0.7565 | LM: 0.2542 | LB: 1.0079 | CL0: 3.2 | CL1: 3.8 | HR0: 0.313/SR0: 0.291 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:43:04] Epoch 2 | Step 6250 | Loss: 0.7565 | LM: 0.2544 | LB: 1.0079 | CL0: 3.2 | CL1: 3.7 | HR0: 0.313/SR0: 0.291 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:43:16] Epoch 2 | Step 6260 | Loss: 0.7564 | LM: 0.2545 | LB: 1.0079 | CL0: 3.2 | CL1: 3.7 | HR0: 0.313/SR0: 0.291 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:43:28] Epoch 2 | Step 6270 | Loss: 0.7565 | LM: 0.2545 | LB: 1.0078 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:43:40] Epoch 2 | Step 6280 | Loss: 0.7564 | LM: 0.2541 | LB: 1.0078 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:43:52] Epoch 2 | Step 6290 | Loss: 0.7564 | LM: 0.2545 | LB: 1.0078 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:44:04] Epoch 2 | Step 6300 | Loss: 0.7564 | LM: 0.2543 | LB: 1.0078 | CL0: 3.2 | CL1: 3.8 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:44:15] Epoch 2 | Step 6310 | Loss: 0.7563 | LM: 0.2541 | LB: 1.0078 | CL0: 3.2 | CL1: 3.8 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:44:27] Epoch 2 | Step 6320 | Loss: 0.7564 | LM: 0.2539 | LB: 1.0078 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:44:39] Epoch 2 | Step 6330 | Loss: 0.7563 | LM: 0.2538 | LB: 1.0078 | CL0: 3.2 | CL1: 3.8 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:44:51] Epoch 2 | Step 6340 | Loss: 0.7564 | LM: 0.2537 | LB: 1.0078 | CL0: 3.2 | CL1: 3.8 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:45:03] Epoch 2 | Step 6350 | Loss: 0.7566 | LM: 0.2539 | LB: 1.0078 | CL0: 3.2 | CL1: 3.8 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:45:15] Epoch 2 | Step 6360 | Loss: 0.7565 | LM: 0.2539 | LB: 1.0078 | CL0: 3.2 | CL1: 3.8 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:45:27] Epoch 2 | Step 6370 | Loss: 0.7565 | LM: 0.2537 | LB: 1.0078 | CL0: 3.2 | CL1: 3.8 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:45:39] Epoch 2 | Step 6380 | Loss: 0.7565 | LM: 0.2537 | LB: 1.0078 | CL0: 3.2 | CL1: 3.8 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:45:50] Epoch 2 | Step 6390 | Loss: 0.7564 | LM: 0.2536 | LB: 1.0078 | CL0: 3.2 | CL1: 3.8 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:46:03] Epoch 2 | Step 6400 | Loss: 0.7566 | LM: 0.2538 | LB: 1.0078 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:46:15] Epoch 2 | Step 6410 | Loss: 0.7565 | LM: 0.2536 | LB: 1.0078 | CL0: 3.2 | CL1: 3.8 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:46:26] Epoch 2 | Step 6420 | Loss: 0.7566 | LM: 0.2537 | LB: 1.0078 | CL0: 3.2 | CL1: 3.8 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:46:38] Epoch 2 | Step 6430 | Loss: 0.7564 | LM: 0.2531 | LB: 1.0078 | CL0: 3.2 | CL1: 3.8 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:46:50] Epoch 2 | Step 6440 | Loss: 0.7564 | LM: 0.2531 | LB: 1.0078 | CL0: 3.2 | CL1: 3.8 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:47:02] Epoch 2 | Step 6450 | Loss: 0.7564 | LM: 0.2527 | LB: 1.0078 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:47:14] Epoch 2 | Step 6460 | Loss: 0.7564 | LM: 0.2524 | LB: 1.0078 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:47:26] Epoch 2 | Step 6470 | Loss: 0.7564 | LM: 0.2526 | LB: 1.0078 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:47:37] Epoch 2 | Step 6480 | Loss: 0.7565 | LM: 0.2525 | LB: 1.0078 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:47:48] Epoch 2 | Step 6490 | Loss: 0.7564 | LM: 0.2523 | LB: 1.0078 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:48:00] Epoch 2 | Step 6500 | Loss: 0.7564 | LM: 0.2522 | LB: 1.0078 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:48:11] Epoch 2 | Step 6510 | Loss: 0.7565 | LM: 0.2523 | LB: 1.0078 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:48:22] Epoch 2 | Step 6520 | Loss: 0.7565 | LM: 0.2522 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:48:34] Epoch 2 | Step 6530 | Loss: 0.7564 | LM: 0.2518 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:48:45] Epoch 2 | Step 6540 | Loss: 0.7563 | LM: 0.2518 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:48:57] Epoch 2 | Step 6550 | Loss: 0.7563 | LM: 0.2519 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:49:09] Epoch 2 | Step 6560 | Loss: 0.7562 | LM: 0.2518 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:49:21] Epoch 2 | Step 6570 | Loss: 0.7561 | LM: 0.2513 | LB: 1.0077 | CL0: 3.2 | CL1: 3.8 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:49:32] Epoch 2 | Step 6580 | Loss: 0.7561 | LM: 0.2517 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:49:44] Epoch 2 | Step 6590 | Loss: 0.7562 | LM: 0.2516 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:49:56] Epoch 2 | Step 6600 | Loss: 0.7562 | LM: 0.2514 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:50:07] Epoch 2 | Step 6610 | Loss: 0.7563 | LM: 0.2516 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:50:18] Epoch 2 | Step 6620 | Loss: 0.7563 | LM: 0.2515 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:50:30] Epoch 2 | Step 6630 | Loss: 0.7563 | LM: 0.2516 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:50:41] Epoch 2 | Step 6640 | Loss: 0.7563 | LM: 0.2516 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:50:54] Epoch 2 | Step 6650 | Loss: 0.7563 | LM: 0.2516 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.268/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 02:51:05] Epoch 2 | Step 6660 | Loss: 0.7562 | LM: 0.2515 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:51:17] Epoch 2 | Step 6670 | Loss: 0.7562 | LM: 0.2512 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:51:28] Epoch 2 | Step 6680 | Loss: 0.7563 | LM: 0.2516 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:51:39] Epoch 2 | Step 6690 | Loss: 0.7564 | LM: 0.2514 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:51:51] Epoch 2 | Step 6700 | Loss: 0.7565 | LM: 0.2517 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:52:03] Epoch 2 | Step 6710 | Loss: 0.7564 | LM: 0.2517 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:52:15] Epoch 2 | Step 6720 | Loss: 0.7563 | LM: 0.2515 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:52:26] Epoch 2 | Step 6730 | Loss: 0.7564 | LM: 0.2515 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:52:38] Epoch 2 | Step 6740 | Loss: 0.7562 | LM: 0.2515 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:52:49] Epoch 2 | Step 6750 | Loss: 0.7563 | LM: 0.2517 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:53:00] Epoch 2 | Step 6760 | Loss: 0.7562 | LM: 0.2516 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:53:11] Epoch 2 | Step 6770 | Loss: 0.7561 | LM: 0.2515 | LB: 1.0077 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:53:22] Epoch 2 | Step 6780 | Loss: 0.7560 | LM: 0.2512 | LB: 1.0076 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.291 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:53:33] Epoch 2 | Step 6790 | Loss: 0.7561 | LM: 0.2514 | LB: 1.0076 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:53:44] Epoch 2 | Step 6800 | Loss: 0.7561 | LM: 0.2515 | LB: 1.0076 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:53:55] Epoch 2 | Step 6810 | Loss: 0.7561 | LM: 0.2517 | LB: 1.0076 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:54:06] Epoch 2 | Step 6820 | Loss: 0.7560 | LM: 0.2516 | LB: 1.0076 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:54:17] Epoch 2 | Step 6830 | Loss: 0.7560 | LM: 0.2515 | LB: 1.0076 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:54:28] Epoch 2 | Step 6840 | Loss: 0.7559 | LM: 0.2514 | LB: 1.0076 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:54:40] Epoch 2 | Step 6850 | Loss: 0.7558 | LM: 0.2517 | LB: 1.0076 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:54:51] Epoch 2 | Step 6860 | Loss: 0.7559 | LM: 0.2517 | LB: 1.0076 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:55:02] Epoch 2 | Step 6870 | Loss: 0.7559 | LM: 0.2517 | LB: 1.0076 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:55:13] Epoch 2 | Step 6880 | Loss: 0.7560 | LM: 0.2516 | LB: 1.0076 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:55:24] Epoch 2 | Step 6890 | Loss: 0.7558 | LM: 0.2517 | LB: 1.0076 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:55:35] Epoch 2 | Step 6900 | Loss: 0.7558 | LM: 0.2515 | LB: 1.0076 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:55:46] Epoch 2 | Step 6910 | Loss: 0.7557 | LM: 0.2515 | LB: 1.0076 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:55:57] Epoch 2 | Step 6920 | Loss: 0.7558 | LM: 0.2515 | LB: 1.0076 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:56:08] Epoch 2 | Step 6930 | Loss: 0.7559 | LM: 0.2516 | LB: 1.0076 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:56:19] Epoch 2 | Step 6940 | Loss: 0.7559 | LM: 0.2515 | LB: 1.0075 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:56:30] Epoch 2 | Step 6950 | Loss: 0.7559 | LM: 0.2516 | LB: 1.0075 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:56:41] Epoch 2 | Step 6960 | Loss: 0.7560 | LM: 0.2516 | LB: 1.0075 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:56:52] Epoch 2 | Step 6970 | Loss: 0.7560 | LM: 0.2518 | LB: 1.0075 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:57:03] Epoch 2 | Step 6980 | Loss: 0.7560 | LM: 0.2518 | LB: 1.0075 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:57:14] Epoch 2 | Step 6990 | Loss: 0.7559 | LM: 0.2516 | LB: 1.0075 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:57:25] Epoch 2 | Step 7000 | Loss: 0.7558 | LM: 0.2515 | LB: 1.0075 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 02:57:27] Validation | Batch 10/1463 | Loss: 0.7910 | LM_LOSS: 0.2894 | LB_LOSS: 1.0032 |
| [2026-05-24 02:57:29] Validation | Batch 20/1463 | Loss: 0.8012 | LM_LOSS: 0.2991 | LB_LOSS: 1.0043 |
| [2026-05-24 02:57:31] Validation | Batch 30/1463 | Loss: 0.8026 | LM_LOSS: 0.3003 | LB_LOSS: 1.0046 |
| [2026-05-24 02:57:33] Validation | Batch 40/1463 | Loss: 0.8090 | LM_LOSS: 0.3064 | LB_LOSS: 1.0051 |
| [2026-05-24 02:57:35] Validation | Batch 50/1463 | Loss: 0.8163 | LM_LOSS: 0.3139 | LB_LOSS: 1.0048 |
| [2026-05-24 02:57:38] Validation | Batch 60/1463 | Loss: 0.8156 | LM_LOSS: 0.3133 | LB_LOSS: 1.0047 |
| [2026-05-24 02:57:40] Validation | Batch 70/1463 | Loss: 0.8153 | LM_LOSS: 0.3130 | LB_LOSS: 1.0047 |
| [2026-05-24 02:57:43] Validation | Batch 80/1463 | Loss: 0.8177 | LM_LOSS: 0.3153 | LB_LOSS: 1.0047 |
| [2026-05-24 02:57:45] Validation | Batch 90/1463 | Loss: 0.8172 | LM_LOSS: 0.3149 | LB_LOSS: 1.0047 |
| [2026-05-24 02:57:47] Validation | Batch 100/1463 | Loss: 0.8171 | LM_LOSS: 0.3148 | LB_LOSS: 1.0047 |
| [2026-05-24 02:57:49] Validation | Batch 110/1463 | Loss: 0.8159 | LM_LOSS: 0.3135 | LB_LOSS: 1.0048 |
| [2026-05-24 02:57:51] Validation | Batch 120/1463 | Loss: 0.8178 | LM_LOSS: 0.3154 | LB_LOSS: 1.0049 |
| [2026-05-24 02:57:52] Validation | Batch 130/1463 | Loss: 0.8198 | LM_LOSS: 0.3173 | LB_LOSS: 1.0050 |
| [2026-05-24 02:57:55] Validation | Batch 140/1463 | Loss: 0.8208 | LM_LOSS: 0.3183 | LB_LOSS: 1.0049 |
| [2026-05-24 02:57:57] Validation | Batch 150/1463 | Loss: 0.8192 | LM_LOSS: 0.3167 | LB_LOSS: 1.0051 |
| [2026-05-24 02:57:59] Validation | Batch 160/1463 | Loss: 0.8195 | LM_LOSS: 0.3170 | LB_LOSS: 1.0050 |
| [2026-05-24 02:58:02] Validation | Batch 170/1463 | Loss: 0.8187 | LM_LOSS: 0.3162 | LB_LOSS: 1.0050 |
| [2026-05-24 02:58:04] Validation | Batch 180/1463 | Loss: 0.8193 | LM_LOSS: 0.3168 | LB_LOSS: 1.0050 |
| [2026-05-24 02:58:06] Validation | Batch 190/1463 | Loss: 0.8206 | LM_LOSS: 0.3181 | LB_LOSS: 1.0050 |
| [2026-05-24 02:58:08] Validation | Batch 200/1463 | Loss: 0.8205 | LM_LOSS: 0.3180 | LB_LOSS: 1.0050 |
| [2026-05-24 02:58:10] Validation | Batch 210/1463 | Loss: 0.8212 | LM_LOSS: 0.3187 | LB_LOSS: 1.0050 |
| [2026-05-24 02:58:13] Validation | Batch 220/1463 | Loss: 0.8205 | LM_LOSS: 0.3180 | LB_LOSS: 1.0050 |
| [2026-05-24 02:58:15] Validation | Batch 230/1463 | Loss: 0.8220 | LM_LOSS: 0.3195 | LB_LOSS: 1.0049 |
| [2026-05-24 02:58:17] Validation | Batch 240/1463 | Loss: 0.8232 | LM_LOSS: 0.3207 | LB_LOSS: 1.0049 |
| [2026-05-24 02:58:19] Validation | Batch 250/1463 | Loss: 0.8224 | LM_LOSS: 0.3200 | LB_LOSS: 1.0049 |
| [2026-05-24 02:58:21] Validation | Batch 260/1463 | Loss: 0.8240 | LM_LOSS: 0.3214 | LB_LOSS: 1.0051 |
| [2026-05-24 02:58:24] Validation | Batch 270/1463 | Loss: 0.8223 | LM_LOSS: 0.3198 | LB_LOSS: 1.0051 |
| [2026-05-24 02:58:26] Validation | Batch 280/1463 | Loss: 0.8229 | LM_LOSS: 0.3203 | LB_LOSS: 1.0051 |
| [2026-05-24 02:58:28] Validation | Batch 290/1463 | Loss: 0.8220 | LM_LOSS: 0.3194 | LB_LOSS: 1.0051 |
| [2026-05-24 02:58:30] Validation | Batch 300/1463 | Loss: 0.8225 | LM_LOSS: 0.3199 | LB_LOSS: 1.0052 |
| [2026-05-24 02:58:32] Validation | Batch 310/1463 | Loss: 0.8234 | LM_LOSS: 0.3208 | LB_LOSS: 1.0052 |
| [2026-05-24 02:58:34] Validation | Batch 320/1463 | Loss: 0.8220 | LM_LOSS: 0.3195 | LB_LOSS: 1.0051 |
| [2026-05-24 02:58:36] Validation | Batch 330/1463 | Loss: 0.8218 | LM_LOSS: 0.3193 | LB_LOSS: 1.0051 |
| [2026-05-24 02:58:38] Validation | Batch 340/1463 | Loss: 0.8214 | LM_LOSS: 0.3188 | LB_LOSS: 1.0051 |
| [2026-05-24 02:58:40] Validation | Batch 350/1463 | Loss: 0.8219 | LM_LOSS: 0.3194 | LB_LOSS: 1.0051 |
| [2026-05-24 02:58:42] Validation | Batch 360/1463 | Loss: 0.8216 | LM_LOSS: 0.3191 | LB_LOSS: 1.0051 |
| [2026-05-24 02:58:44] Validation | Batch 370/1463 | Loss: 0.8213 | LM_LOSS: 0.3187 | LB_LOSS: 1.0051 |
| [2026-05-24 02:58:46] Validation | Batch 380/1463 | Loss: 0.8210 | LM_LOSS: 0.3185 | LB_LOSS: 1.0050 |
| [2026-05-24 02:58:48] Validation | Batch 390/1463 | Loss: 0.8215 | LM_LOSS: 0.3190 | LB_LOSS: 1.0050 |
| [2026-05-24 02:58:50] Validation | Batch 400/1463 | Loss: 0.8215 | LM_LOSS: 0.3189 | LB_LOSS: 1.0051 |
| [2026-05-24 02:58:52] Validation | Batch 410/1463 | Loss: 0.8212 | LM_LOSS: 0.3186 | LB_LOSS: 1.0051 |
| [2026-05-24 02:58:55] Validation | Batch 420/1463 | Loss: 0.8212 | LM_LOSS: 0.3187 | LB_LOSS: 1.0051 |
| [2026-05-24 02:58:57] Validation | Batch 430/1463 | Loss: 0.8207 | LM_LOSS: 0.3181 | LB_LOSS: 1.0051 |
| [2026-05-24 02:58:59] Validation | Batch 440/1463 | Loss: 0.8210 | LM_LOSS: 0.3184 | LB_LOSS: 1.0051 |
| [2026-05-24 02:59:01] Validation | Batch 450/1463 | Loss: 0.8208 | LM_LOSS: 0.3182 | LB_LOSS: 1.0051 |
| [2026-05-24 02:59:03] Validation | Batch 460/1463 | Loss: 0.8207 | LM_LOSS: 0.3181 | LB_LOSS: 1.0051 |
| [2026-05-24 02:59:06] Validation | Batch 470/1463 | Loss: 0.8213 | LM_LOSS: 0.3188 | LB_LOSS: 1.0051 |
| [2026-05-24 02:59:08] Validation | Batch 480/1463 | Loss: 0.8211 | LM_LOSS: 0.3186 | LB_LOSS: 1.0051 |
| [2026-05-24 02:59:10] Validation | Batch 490/1463 | Loss: 0.8209 | LM_LOSS: 0.3184 | LB_LOSS: 1.0051 |
| [2026-05-24 02:59:13] Validation | Batch 500/1463 | Loss: 0.8207 | LM_LOSS: 0.3182 | LB_LOSS: 1.0051 |
| [2026-05-24 02:59:15] Validation | Batch 510/1463 | Loss: 0.8202 | LM_LOSS: 0.3176 | LB_LOSS: 1.0051 |
| [2026-05-24 02:59:17] Validation | Batch 520/1463 | Loss: 0.8197 | LM_LOSS: 0.3172 | LB_LOSS: 1.0051 |
| [2026-05-24 02:59:19] Validation | Batch 530/1463 | Loss: 0.8201 | LM_LOSS: 0.3176 | LB_LOSS: 1.0051 |
| [2026-05-24 02:59:21] Validation | Batch 540/1463 | Loss: 0.8204 | LM_LOSS: 0.3179 | LB_LOSS: 1.0051 |
| [2026-05-24 02:59:22] Validation | Batch 550/1463 | Loss: 0.8199 | LM_LOSS: 0.3173 | LB_LOSS: 1.0051 |
| [2026-05-24 02:59:25] Validation | Batch 560/1463 | Loss: 0.8200 | LM_LOSS: 0.3175 | LB_LOSS: 1.0052 |
| [2026-05-24 02:59:27] Validation | Batch 570/1463 | Loss: 0.8199 | LM_LOSS: 0.3174 | LB_LOSS: 1.0051 |
| [2026-05-24 02:59:29] Validation | Batch 580/1463 | Loss: 0.8195 | LM_LOSS: 0.3170 | LB_LOSS: 1.0051 |
| [2026-05-24 02:59:32] Validation | Batch 590/1463 | Loss: 0.8193 | LM_LOSS: 0.3167 | LB_LOSS: 1.0052 |
| [2026-05-24 02:59:34] Validation | Batch 600/1463 | Loss: 0.8196 | LM_LOSS: 0.3170 | LB_LOSS: 1.0052 |
| [2026-05-24 02:59:36] Validation | Batch 610/1463 | Loss: 0.8197 | LM_LOSS: 0.3171 | LB_LOSS: 1.0052 |
| [2026-05-24 02:59:38] Validation | Batch 620/1463 | Loss: 0.8192 | LM_LOSS: 0.3166 | LB_LOSS: 1.0052 |
| [2026-05-24 02:59:41] Validation | Batch 630/1463 | Loss: 0.8187 | LM_LOSS: 0.3161 | LB_LOSS: 1.0052 |
| [2026-05-24 02:59:43] Validation | Batch 640/1463 | Loss: 0.8186 | LM_LOSS: 0.3160 | LB_LOSS: 1.0052 |
| [2026-05-24 02:59:44] Validation | Batch 650/1463 | Loss: 0.8181 | LM_LOSS: 0.3155 | LB_LOSS: 1.0052 |
| [2026-05-24 02:59:46] Validation | Batch 660/1463 | Loss: 0.8176 | LM_LOSS: 0.3150 | LB_LOSS: 1.0052 |
| [2026-05-24 02:59:48] Validation | Batch 670/1463 | Loss: 0.8173 | LM_LOSS: 0.3147 | LB_LOSS: 1.0052 |
| [2026-05-24 02:59:50] Validation | Batch 680/1463 | Loss: 0.8172 | LM_LOSS: 0.3146 | LB_LOSS: 1.0051 |
| [2026-05-24 02:59:53] Validation | Batch 690/1463 | Loss: 0.8175 | LM_LOSS: 0.3149 | LB_LOSS: 1.0052 |
| [2026-05-24 02:59:55] Validation | Batch 700/1463 | Loss: 0.8175 | LM_LOSS: 0.3149 | LB_LOSS: 1.0052 |
| [2026-05-24 02:59:56] Validation | Batch 710/1463 | Loss: 0.8177 | LM_LOSS: 0.3151 | LB_LOSS: 1.0052 |
| [2026-05-24 02:59:59] Validation | Batch 720/1463 | Loss: 0.8184 | LM_LOSS: 0.3158 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:01] Validation | Batch 730/1463 | Loss: 0.8183 | LM_LOSS: 0.3157 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:02] Validation | Batch 740/1463 | Loss: 0.8179 | LM_LOSS: 0.3153 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:04] Validation | Batch 750/1463 | Loss: 0.8178 | LM_LOSS: 0.3152 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:06] Validation | Batch 760/1463 | Loss: 0.8177 | LM_LOSS: 0.3151 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:08] Validation | Batch 770/1463 | Loss: 0.8176 | LM_LOSS: 0.3149 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:10] Validation | Batch 780/1463 | Loss: 0.8175 | LM_LOSS: 0.3149 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:11] Validation | Batch 790/1463 | Loss: 0.8177 | LM_LOSS: 0.3151 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:13] Validation | Batch 800/1463 | Loss: 0.8177 | LM_LOSS: 0.3151 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:15] Validation | Batch 810/1463 | Loss: 0.8173 | LM_LOSS: 0.3147 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:17] Validation | Batch 820/1463 | Loss: 0.8176 | LM_LOSS: 0.3150 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:19] Validation | Batch 830/1463 | Loss: 0.8179 | LM_LOSS: 0.3153 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:22] Validation | Batch 840/1463 | Loss: 0.8179 | LM_LOSS: 0.3153 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:24] Validation | Batch 850/1463 | Loss: 0.8182 | LM_LOSS: 0.3156 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:26] Validation | Batch 860/1463 | Loss: 0.8183 | LM_LOSS: 0.3157 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:28] Validation | Batch 870/1463 | Loss: 0.8184 | LM_LOSS: 0.3158 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:30] Validation | Batch 880/1463 | Loss: 0.8177 | LM_LOSS: 0.3151 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:32] Validation | Batch 890/1463 | Loss: 0.8177 | LM_LOSS: 0.3151 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:35] Validation | Batch 900/1463 | Loss: 0.8173 | LM_LOSS: 0.3147 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:37] Validation | Batch 910/1463 | Loss: 0.8173 | LM_LOSS: 0.3147 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:39] Validation | Batch 920/1463 | Loss: 0.8174 | LM_LOSS: 0.3148 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:41] Validation | Batch 930/1463 | Loss: 0.8172 | LM_LOSS: 0.3146 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:43] Validation | Batch 940/1463 | Loss: 0.8169 | LM_LOSS: 0.3143 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:46] Validation | Batch 950/1463 | Loss: 0.8171 | LM_LOSS: 0.3146 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:48] Validation | Batch 960/1463 | Loss: 0.8172 | LM_LOSS: 0.3146 | LB_LOSS: 1.0052 |
| [2026-05-24 03:00:50] Validation | Batch 970/1463 | Loss: 0.8173 | LM_LOSS: 0.3147 | LB_LOSS: 1.0051 |
| [2026-05-24 03:00:53] Validation | Batch 980/1463 | Loss: 0.8176 | LM_LOSS: 0.3150 | LB_LOSS: 1.0051 |
| [2026-05-24 03:00:54] Validation | Batch 990/1463 | Loss: 0.8178 | LM_LOSS: 0.3152 | LB_LOSS: 1.0051 |
| [2026-05-24 03:00:56] Validation | Batch 1000/1463 | Loss: 0.8184 | LM_LOSS: 0.3158 | LB_LOSS: 1.0051 |
| [2026-05-24 03:00:59] Validation | Batch 1010/1463 | Loss: 0.8184 | LM_LOSS: 0.3159 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:01] Validation | Batch 1020/1463 | Loss: 0.8185 | LM_LOSS: 0.3160 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:04] Validation | Batch 1030/1463 | Loss: 0.8191 | LM_LOSS: 0.3165 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:05] Validation | Batch 1040/1463 | Loss: 0.8187 | LM_LOSS: 0.3161 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:08] Validation | Batch 1050/1463 | Loss: 0.8185 | LM_LOSS: 0.3160 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:10] Validation | Batch 1060/1463 | Loss: 0.8185 | LM_LOSS: 0.3159 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:12] Validation | Batch 1070/1463 | Loss: 0.8185 | LM_LOSS: 0.3159 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:14] Validation | Batch 1080/1463 | Loss: 0.8183 | LM_LOSS: 0.3157 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:16] Validation | Batch 1090/1463 | Loss: 0.8183 | LM_LOSS: 0.3157 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:18] Validation | Batch 1100/1463 | Loss: 0.8181 | LM_LOSS: 0.3155 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:20] Validation | Batch 1110/1463 | Loss: 0.8181 | LM_LOSS: 0.3155 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:22] Validation | Batch 1120/1463 | Loss: 0.8180 | LM_LOSS: 0.3154 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:25] Validation | Batch 1130/1463 | Loss: 0.8177 | LM_LOSS: 0.3151 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:27] Validation | Batch 1140/1463 | Loss: 0.8179 | LM_LOSS: 0.3153 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:29] Validation | Batch 1150/1463 | Loss: 0.8178 | LM_LOSS: 0.3152 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:31] Validation | Batch 1160/1463 | Loss: 0.8177 | LM_LOSS: 0.3151 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:33] Validation | Batch 1170/1463 | Loss: 0.8177 | LM_LOSS: 0.3151 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:35] Validation | Batch 1180/1463 | Loss: 0.8178 | LM_LOSS: 0.3152 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:38] Validation | Batch 1190/1463 | Loss: 0.8179 | LM_LOSS: 0.3153 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:40] Validation | Batch 1200/1463 | Loss: 0.8179 | LM_LOSS: 0.3153 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:42] Validation | Batch 1210/1463 | Loss: 0.8181 | LM_LOSS: 0.3155 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:44] Validation | Batch 1220/1463 | Loss: 0.8186 | LM_LOSS: 0.3160 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:46] Validation | Batch 1230/1463 | Loss: 0.8185 | LM_LOSS: 0.3159 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:48] Validation | Batch 1240/1463 | Loss: 0.8188 | LM_LOSS: 0.3162 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:50] Validation | Batch 1250/1463 | Loss: 0.8189 | LM_LOSS: 0.3164 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:53] Validation | Batch 1260/1463 | Loss: 0.8188 | LM_LOSS: 0.3162 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:55] Validation | Batch 1270/1463 | Loss: 0.8186 | LM_LOSS: 0.3160 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:57] Validation | Batch 1280/1463 | Loss: 0.8184 | LM_LOSS: 0.3158 | LB_LOSS: 1.0052 |
| [2026-05-24 03:01:59] Validation | Batch 1290/1463 | Loss: 0.8183 | LM_LOSS: 0.3158 | LB_LOSS: 1.0052 |
| [2026-05-24 03:02:01] Validation | Batch 1300/1463 | Loss: 0.8181 | LM_LOSS: 0.3155 | LB_LOSS: 1.0052 |
| [2026-05-24 03:02:04] Validation | Batch 1310/1463 | Loss: 0.8180 | LM_LOSS: 0.3154 | LB_LOSS: 1.0052 |
| [2026-05-24 03:02:05] Validation | Batch 1320/1463 | Loss: 0.8180 | LM_LOSS: 0.3154 | LB_LOSS: 1.0052 |
| [2026-05-24 03:02:07] Validation | Batch 1330/1463 | Loss: 0.8181 | LM_LOSS: 0.3155 | LB_LOSS: 1.0052 |
| [2026-05-24 03:02:09] Validation | Batch 1340/1463 | Loss: 0.8184 | LM_LOSS: 0.3158 | LB_LOSS: 1.0052 |
| [2026-05-24 03:02:11] Validation | Batch 1350/1463 | Loss: 0.8184 | LM_LOSS: 0.3158 | LB_LOSS: 1.0052 |
| [2026-05-24 03:02:14] Validation | Batch 1360/1463 | Loss: 0.8187 | LM_LOSS: 0.3161 | LB_LOSS: 1.0052 |
| [2026-05-24 03:02:16] Validation | Batch 1370/1463 | Loss: 0.8190 | LM_LOSS: 0.3165 | LB_LOSS: 1.0052 |
| [2026-05-24 03:02:18] Validation | Batch 1380/1463 | Loss: 0.8187 | LM_LOSS: 0.3162 | LB_LOSS: 1.0052 |
| [2026-05-24 03:02:20] Validation | Batch 1390/1463 | Loss: 0.8187 | LM_LOSS: 0.3161 | LB_LOSS: 1.0052 |
| [2026-05-24 03:02:22] Validation | Batch 1400/1463 | Loss: 0.8189 | LM_LOSS: 0.3164 | LB_LOSS: 1.0051 |
| [2026-05-24 03:02:24] Validation | Batch 1410/1463 | Loss: 0.8192 | LM_LOSS: 0.3166 | LB_LOSS: 1.0052 |
| [2026-05-24 03:02:26] Validation | Batch 1420/1463 | Loss: 0.8192 | LM_LOSS: 0.3166 | LB_LOSS: 1.0052 |
| [2026-05-24 03:02:28] Validation | Batch 1430/1463 | Loss: 0.8192 | LM_LOSS: 0.3167 | LB_LOSS: 1.0052 |
| [2026-05-24 03:02:31] Validation | Batch 1440/1463 | Loss: 0.8196 | LM_LOSS: 0.3171 | LB_LOSS: 1.0052 |
| [2026-05-24 03:02:33] Validation | Batch 1450/1463 | Loss: 0.8194 | LM_LOSS: 0.3168 | LB_LOSS: 1.0051 |
| [2026-05-24 03:02:35] Validation | Batch 1460/1463 | Loss: 0.8197 | LM_LOSS: 0.3171 | LB_LOSS: 1.0051 |
| [2026-05-24 03:02:36] Validation | Batch 1463/1463 | Loss: 0.8196 | LM_LOSS: 0.3170 | LB_LOSS: 1.0051 |
| [2026-05-24 03:02:36] Validation | Loss: 0.8196 | LM_LOSS: 0.3170 | LB_LOSS: 1.0051 | PPL: 1.37 | Time: 310.59s |
| [2026-05-24 03:02:47] Epoch 2 | Step 7010 | Loss: 0.7559 | LM: 0.2520 | LB: 1.0075 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:02:58] Epoch 2 | Step 7020 | Loss: 0.7560 | LM: 0.2521 | LB: 1.0075 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:03:09] Epoch 2 | Step 7030 | Loss: 0.7560 | LM: 0.2523 | LB: 1.0075 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:03:20] Epoch 2 | Step 7040 | Loss: 0.7560 | LM: 0.2523 | LB: 1.0075 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:03:32] Epoch 2 | Step 7050 | Loss: 0.7561 | LM: 0.2524 | LB: 1.0075 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:03:42] Epoch 2 | Step 7060 | Loss: 0.7560 | LM: 0.2524 | LB: 1.0075 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:03:54] Epoch 2 | Step 7070 | Loss: 0.7559 | LM: 0.2524 | LB: 1.0075 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:04:05] Epoch 2 | Step 7080 | Loss: 0.7560 | LM: 0.2525 | LB: 1.0075 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:04:16] Epoch 2 | Step 7090 | Loss: 0.7559 | LM: 0.2524 | LB: 1.0075 | CL0: 3.2 | CL1: 3.7 | HR0: 0.312/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:04:27] Epoch 2 | Step 7100 | Loss: 0.7560 | LM: 0.2523 | LB: 1.0075 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:04:38] Epoch 2 | Step 7110 | Loss: 0.7559 | LM: 0.2520 | LB: 1.0075 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:04:49] Epoch 2 | Step 7120 | Loss: 0.7558 | LM: 0.2518 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:05:00] Epoch 2 | Step 7130 | Loss: 0.7557 | LM: 0.2517 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:05:11] Epoch 2 | Step 7140 | Loss: 0.7558 | LM: 0.2516 | LB: 1.0075 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:05:22] Epoch 2 | Step 7150 | Loss: 0.7558 | LM: 0.2517 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:05:33] Epoch 2 | Step 7160 | Loss: 0.7559 | LM: 0.2517 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:05:44] Epoch 2 | Step 7170 | Loss: 0.7558 | LM: 0.2516 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:05:55] Epoch 2 | Step 7180 | Loss: 0.7558 | LM: 0.2514 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:06:06] Epoch 2 | Step 7190 | Loss: 0.7558 | LM: 0.2513 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:06:17] Epoch 2 | Step 7200 | Loss: 0.7557 | LM: 0.2512 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:06:29] Epoch 2 | Step 7210 | Loss: 0.7557 | LM: 0.2512 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:06:40] Epoch 2 | Step 7220 | Loss: 0.7557 | LM: 0.2515 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:06:52] Epoch 2 | Step 7230 | Loss: 0.7557 | LM: 0.2514 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:07:04] Epoch 2 | Step 7240 | Loss: 0.7557 | LM: 0.2516 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:07:16] Epoch 2 | Step 7250 | Loss: 0.7557 | LM: 0.2516 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:07:28] Epoch 2 | Step 7260 | Loss: 0.7558 | LM: 0.2519 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:07:40] Epoch 2 | Step 7270 | Loss: 0.7558 | LM: 0.2518 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:07:52] Epoch 2 | Step 7280 | Loss: 0.7558 | LM: 0.2519 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:08:03] Epoch 2 | Step 7290 | Loss: 0.7559 | LM: 0.2520 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:08:14] Epoch 2 | Step 7300 | Loss: 0.7559 | LM: 0.2521 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:08:25] Epoch 2 | Step 7310 | Loss: 0.7559 | LM: 0.2518 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:08:36] Epoch 2 | Step 7320 | Loss: 0.7558 | LM: 0.2519 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.290 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:08:47] Epoch 2 | Step 7330 | Loss: 0.7557 | LM: 0.2517 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:08:57] Epoch 2 | Step 7340 | Loss: 0.7557 | LM: 0.2517 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:09:09] Epoch 2 | Step 7350 | Loss: 0.7556 | LM: 0.2518 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:09:20] Epoch 2 | Step 7360 | Loss: 0.7556 | LM: 0.2519 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:09:31] Epoch 2 | Step 7370 | Loss: 0.7556 | LM: 0.2519 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:09:42] Epoch 2 | Step 7380 | Loss: 0.7556 | LM: 0.2519 | LB: 1.0074 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:09:54] Epoch 2 | Step 7390 | Loss: 0.7557 | LM: 0.2522 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:10:06] Epoch 2 | Step 7400 | Loss: 0.7558 | LM: 0.2521 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:10:18] Epoch 2 | Step 7410 | Loss: 0.7557 | LM: 0.2520 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:10:29] Epoch 2 | Step 7420 | Loss: 0.7557 | LM: 0.2519 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:10:41] Epoch 2 | Step 7430 | Loss: 0.7557 | LM: 0.2521 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:10:52] Epoch 2 | Step 7440 | Loss: 0.7557 | LM: 0.2520 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:11:03] Epoch 2 | Step 7450 | Loss: 0.7557 | LM: 0.2518 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:11:15] Epoch 2 | Step 7460 | Loss: 0.7557 | LM: 0.2519 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:11:26] Epoch 2 | Step 7470 | Loss: 0.7557 | LM: 0.2520 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:11:37] Epoch 2 | Step 7480 | Loss: 0.7557 | LM: 0.2520 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:11:48] Epoch 2 | Step 7490 | Loss: 0.7557 | LM: 0.2521 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:12:00] Epoch 2 | Step 7500 | Loss: 0.7557 | LM: 0.2522 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:12:11] Epoch 2 | Step 7510 | Loss: 0.7557 | LM: 0.2519 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:12:23] Epoch 2 | Step 7520 | Loss: 0.7557 | LM: 0.2519 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:12:35] Epoch 2 | Step 7530 | Loss: 0.7556 | LM: 0.2518 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:12:46] Epoch 2 | Step 7540 | Loss: 0.7556 | LM: 0.2519 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:12:58] Epoch 2 | Step 7550 | Loss: 0.7557 | LM: 0.2520 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:13:10] Epoch 2 | Step 7560 | Loss: 0.7557 | LM: 0.2520 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:13:21] Epoch 2 | Step 7570 | Loss: 0.7556 | LM: 0.2519 | LB: 1.0073 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:13:32] Epoch 2 | Step 7580 | Loss: 0.7555 | LM: 0.2520 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:13:44] Epoch 2 | Step 7590 | Loss: 0.7556 | LM: 0.2523 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:13:55] Epoch 2 | Step 7600 | Loss: 0.7557 | LM: 0.2522 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:14:07] Epoch 2 | Step 7610 | Loss: 0.7556 | LM: 0.2522 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:14:18] Epoch 2 | Step 7620 | Loss: 0.7556 | LM: 0.2522 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:14:29] Epoch 2 | Step 7630 | Loss: 0.7556 | LM: 0.2521 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:14:40] Epoch 2 | Step 7640 | Loss: 0.7555 | LM: 0.2522 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:14:51] Epoch 2 | Step 7650 | Loss: 0.7556 | LM: 0.2524 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:15:03] Epoch 2 | Step 7660 | Loss: 0.7556 | LM: 0.2522 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:15:14] Epoch 2 | Step 7670 | Loss: 0.7555 | LM: 0.2521 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:15:25] Epoch 2 | Step 7680 | Loss: 0.7554 | LM: 0.2520 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:15:36] Epoch 2 | Step 7690 | Loss: 0.7554 | LM: 0.2521 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:15:47] Epoch 2 | Step 7700 | Loss: 0.7555 | LM: 0.2520 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:15:58] Epoch 2 | Step 7710 | Loss: 0.7554 | LM: 0.2521 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:16:09] Epoch 2 | Step 7720 | Loss: 0.7555 | LM: 0.2522 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:16:21] Epoch 2 | Step 7730 | Loss: 0.7555 | LM: 0.2521 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:16:32] Epoch 2 | Step 7740 | Loss: 0.7556 | LM: 0.2522 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:16:43] Epoch 2 | Step 7750 | Loss: 0.7557 | LM: 0.2524 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:16:55] Epoch 2 | Step 7760 | Loss: 0.7557 | LM: 0.2525 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:17:07] Epoch 2 | Step 7770 | Loss: 0.7557 | LM: 0.2525 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:17:19] Epoch 2 | Step 7780 | Loss: 0.7557 | LM: 0.2526 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:17:30] Epoch 2 | Step 7790 | Loss: 0.7558 | LM: 0.2527 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:17:42] Epoch 2 | Step 7800 | Loss: 0.7558 | LM: 0.2526 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:17:54] Epoch 2 | Step 7810 | Loss: 0.7558 | LM: 0.2527 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:18:06] Epoch 2 | Step 7820 | Loss: 0.7559 | LM: 0.2527 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:18:18] Epoch 2 | Step 7830 | Loss: 0.7559 | LM: 0.2528 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:18:29] Epoch 2 | Step 7840 | Loss: 0.7560 | LM: 0.2528 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:18:40] Epoch 2 | Step 7850 | Loss: 0.7560 | LM: 0.2529 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:18:51] Epoch 2 | Step 7860 | Loss: 0.7559 | LM: 0.2527 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:19:02] Epoch 2 | Step 7870 | Loss: 0.7559 | LM: 0.2528 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:19:13] Epoch 2 | Step 7880 | Loss: 0.7559 | LM: 0.2529 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:19:24] Epoch 2 | Step 7890 | Loss: 0.7558 | LM: 0.2526 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:19:35] Epoch 2 | Step 7900 | Loss: 0.7558 | LM: 0.2527 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:19:46] Epoch 2 | Step 7910 | Loss: 0.7558 | LM: 0.2527 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:19:57] Epoch 2 | Step 7920 | Loss: 0.7557 | LM: 0.2528 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:20:08] Epoch 2 | Step 7930 | Loss: 0.7556 | LM: 0.2526 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:20:19] Epoch 2 | Step 7940 | Loss: 0.7556 | LM: 0.2526 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:20:29] Epoch 2 | Step 7950 | Loss: 0.7556 | LM: 0.2526 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:20:40] Epoch 2 | Step 7960 | Loss: 0.7557 | LM: 0.2528 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:20:52] Epoch 2 | Step 7970 | Loss: 0.7558 | LM: 0.2528 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:21:02] Epoch 2 | Step 7980 | Loss: 0.7557 | LM: 0.2529 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:21:13] Epoch 2 | Step 7990 | Loss: 0.7557 | LM: 0.2526 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:21:24] Epoch 2 | Step 8000 | Loss: 0.7557 | LM: 0.2526 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:21:26] Validation | Batch 10/1463 | Loss: 0.7851 | LM_LOSS: 0.2837 | LB_LOSS: 1.0027 |
| [2026-05-24 03:21:28] Validation | Batch 20/1463 | Loss: 0.7965 | LM_LOSS: 0.2946 | LB_LOSS: 1.0038 |
| [2026-05-24 03:21:30] Validation | Batch 30/1463 | Loss: 0.7983 | LM_LOSS: 0.2963 | LB_LOSS: 1.0041 |
| [2026-05-24 03:21:32] Validation | Batch 40/1463 | Loss: 0.8048 | LM_LOSS: 0.3025 | LB_LOSS: 1.0046 |
| [2026-05-24 03:21:34] Validation | Batch 50/1463 | Loss: 0.8133 | LM_LOSS: 0.3111 | LB_LOSS: 1.0043 |
| [2026-05-24 03:21:37] Validation | Batch 60/1463 | Loss: 0.8126 | LM_LOSS: 0.3105 | LB_LOSS: 1.0042 |
| [2026-05-24 03:21:39] Validation | Batch 70/1463 | Loss: 0.8112 | LM_LOSS: 0.3090 | LB_LOSS: 1.0043 |
| [2026-05-24 03:21:42] Validation | Batch 80/1463 | Loss: 0.8136 | LM_LOSS: 0.3115 | LB_LOSS: 1.0043 |
| [2026-05-24 03:21:44] Validation | Batch 90/1463 | Loss: 0.8133 | LM_LOSS: 0.3112 | LB_LOSS: 1.0042 |
| [2026-05-24 03:21:46] Validation | Batch 100/1463 | Loss: 0.8135 | LM_LOSS: 0.3114 | LB_LOSS: 1.0042 |
| [2026-05-24 03:21:48] Validation | Batch 110/1463 | Loss: 0.8118 | LM_LOSS: 0.3096 | LB_LOSS: 1.0044 |
| [2026-05-24 03:21:50] Validation | Batch 120/1463 | Loss: 0.8137 | LM_LOSS: 0.3115 | LB_LOSS: 1.0044 |
| [2026-05-24 03:21:52] Validation | Batch 130/1463 | Loss: 0.8156 | LM_LOSS: 0.3133 | LB_LOSS: 1.0045 |
| [2026-05-24 03:21:54] Validation | Batch 140/1463 | Loss: 0.8168 | LM_LOSS: 0.3146 | LB_LOSS: 1.0044 |
| [2026-05-24 03:21:56] Validation | Batch 150/1463 | Loss: 0.8150 | LM_LOSS: 0.3127 | LB_LOSS: 1.0046 |
| [2026-05-24 03:21:58] Validation | Batch 160/1463 | Loss: 0.8152 | LM_LOSS: 0.3130 | LB_LOSS: 1.0045 |
| [2026-05-24 03:22:01] Validation | Batch 170/1463 | Loss: 0.8147 | LM_LOSS: 0.3124 | LB_LOSS: 1.0045 |
| [2026-05-24 03:22:03] Validation | Batch 180/1463 | Loss: 0.8153 | LM_LOSS: 0.3131 | LB_LOSS: 1.0045 |
| [2026-05-24 03:22:05] Validation | Batch 190/1463 | Loss: 0.8167 | LM_LOSS: 0.3145 | LB_LOSS: 1.0045 |
| [2026-05-24 03:22:07] Validation | Batch 200/1463 | Loss: 0.8168 | LM_LOSS: 0.3145 | LB_LOSS: 1.0045 |
| [2026-05-24 03:22:09] Validation | Batch 210/1463 | Loss: 0.8175 | LM_LOSS: 0.3153 | LB_LOSS: 1.0045 |
| [2026-05-24 03:22:12] Validation | Batch 220/1463 | Loss: 0.8169 | LM_LOSS: 0.3146 | LB_LOSS: 1.0045 |
| [2026-05-24 03:22:14] Validation | Batch 230/1463 | Loss: 0.8184 | LM_LOSS: 0.3162 | LB_LOSS: 1.0045 |
| [2026-05-24 03:22:16] Validation | Batch 240/1463 | Loss: 0.8198 | LM_LOSS: 0.3176 | LB_LOSS: 1.0044 |
| [2026-05-24 03:22:18] Validation | Batch 250/1463 | Loss: 0.8191 | LM_LOSS: 0.3168 | LB_LOSS: 1.0044 |
| [2026-05-24 03:22:20] Validation | Batch 260/1463 | Loss: 0.8208 | LM_LOSS: 0.3185 | LB_LOSS: 1.0046 |
| [2026-05-24 03:22:23] Validation | Batch 270/1463 | Loss: 0.8193 | LM_LOSS: 0.3170 | LB_LOSS: 1.0046 |
| [2026-05-24 03:22:25] Validation | Batch 280/1463 | Loss: 0.8199 | LM_LOSS: 0.3176 | LB_LOSS: 1.0046 |
| [2026-05-24 03:22:27] Validation | Batch 290/1463 | Loss: 0.8190 | LM_LOSS: 0.3167 | LB_LOSS: 1.0046 |
| [2026-05-24 03:22:29] Validation | Batch 300/1463 | Loss: 0.8194 | LM_LOSS: 0.3171 | LB_LOSS: 1.0047 |
| [2026-05-24 03:22:31] Validation | Batch 310/1463 | Loss: 0.8202 | LM_LOSS: 0.3179 | LB_LOSS: 1.0046 |
| [2026-05-24 03:22:33] Validation | Batch 320/1463 | Loss: 0.8190 | LM_LOSS: 0.3167 | LB_LOSS: 1.0046 |
| [2026-05-24 03:22:35] Validation | Batch 330/1463 | Loss: 0.8188 | LM_LOSS: 0.3165 | LB_LOSS: 1.0045 |
| [2026-05-24 03:22:37] Validation | Batch 340/1463 | Loss: 0.8184 | LM_LOSS: 0.3161 | LB_LOSS: 1.0046 |
| [2026-05-24 03:22:39] Validation | Batch 350/1463 | Loss: 0.8191 | LM_LOSS: 0.3168 | LB_LOSS: 1.0045 |
| [2026-05-24 03:22:41] Validation | Batch 360/1463 | Loss: 0.8189 | LM_LOSS: 0.3166 | LB_LOSS: 1.0046 |
| [2026-05-24 03:22:43] Validation | Batch 370/1463 | Loss: 0.8185 | LM_LOSS: 0.3163 | LB_LOSS: 1.0046 |
| [2026-05-24 03:22:45] Validation | Batch 380/1463 | Loss: 0.8182 | LM_LOSS: 0.3160 | LB_LOSS: 1.0045 |
| [2026-05-24 03:22:47] Validation | Batch 390/1463 | Loss: 0.8189 | LM_LOSS: 0.3166 | LB_LOSS: 1.0045 |
| [2026-05-24 03:22:49] Validation | Batch 400/1463 | Loss: 0.8189 | LM_LOSS: 0.3166 | LB_LOSS: 1.0046 |
| [2026-05-24 03:22:51] Validation | Batch 410/1463 | Loss: 0.8186 | LM_LOSS: 0.3163 | LB_LOSS: 1.0046 |
| [2026-05-24 03:22:54] Validation | Batch 420/1463 | Loss: 0.8187 | LM_LOSS: 0.3164 | LB_LOSS: 1.0046 |
| [2026-05-24 03:22:56] Validation | Batch 430/1463 | Loss: 0.8181 | LM_LOSS: 0.3158 | LB_LOSS: 1.0046 |
| [2026-05-24 03:22:58] Validation | Batch 440/1463 | Loss: 0.8183 | LM_LOSS: 0.3160 | LB_LOSS: 1.0046 |
| [2026-05-24 03:23:00] Validation | Batch 450/1463 | Loss: 0.8181 | LM_LOSS: 0.3157 | LB_LOSS: 1.0046 |
| [2026-05-24 03:23:02] Validation | Batch 460/1463 | Loss: 0.8179 | LM_LOSS: 0.3156 | LB_LOSS: 1.0046 |
| [2026-05-24 03:23:04] Validation | Batch 470/1463 | Loss: 0.8186 | LM_LOSS: 0.3163 | LB_LOSS: 1.0046 |
| [2026-05-24 03:23:07] Validation | Batch 480/1463 | Loss: 0.8184 | LM_LOSS: 0.3161 | LB_LOSS: 1.0046 |
| [2026-05-24 03:23:09] Validation | Batch 490/1463 | Loss: 0.8183 | LM_LOSS: 0.3160 | LB_LOSS: 1.0046 |
| [2026-05-24 03:23:12] Validation | Batch 500/1463 | Loss: 0.8181 | LM_LOSS: 0.3158 | LB_LOSS: 1.0046 |
| [2026-05-24 03:23:14] Validation | Batch 510/1463 | Loss: 0.8175 | LM_LOSS: 0.3152 | LB_LOSS: 1.0046 |
| [2026-05-24 03:23:16] Validation | Batch 520/1463 | Loss: 0.8172 | LM_LOSS: 0.3149 | LB_LOSS: 1.0046 |
| [2026-05-24 03:23:18] Validation | Batch 530/1463 | Loss: 0.8177 | LM_LOSS: 0.3154 | LB_LOSS: 1.0046 |
| [2026-05-24 03:23:19] Validation | Batch 540/1463 | Loss: 0.8180 | LM_LOSS: 0.3157 | LB_LOSS: 1.0046 |
| [2026-05-24 03:23:21] Validation | Batch 550/1463 | Loss: 0.8175 | LM_LOSS: 0.3152 | LB_LOSS: 1.0046 |
| [2026-05-24 03:23:23] Validation | Batch 560/1463 | Loss: 0.8176 | LM_LOSS: 0.3153 | LB_LOSS: 1.0047 |
| [2026-05-24 03:23:26] Validation | Batch 570/1463 | Loss: 0.8175 | LM_LOSS: 0.3152 | LB_LOSS: 1.0046 |
| [2026-05-24 03:23:28] Validation | Batch 580/1463 | Loss: 0.8171 | LM_LOSS: 0.3148 | LB_LOSS: 1.0046 |
| [2026-05-24 03:23:30] Validation | Batch 590/1463 | Loss: 0.8170 | LM_LOSS: 0.3146 | LB_LOSS: 1.0047 |
| [2026-05-24 03:23:33] Validation | Batch 600/1463 | Loss: 0.8171 | LM_LOSS: 0.3148 | LB_LOSS: 1.0047 |
| [2026-05-24 03:23:35] Validation | Batch 610/1463 | Loss: 0.8173 | LM_LOSS: 0.3149 | LB_LOSS: 1.0047 |
| [2026-05-24 03:23:37] Validation | Batch 620/1463 | Loss: 0.8167 | LM_LOSS: 0.3143 | LB_LOSS: 1.0047 |
| [2026-05-24 03:23:39] Validation | Batch 630/1463 | Loss: 0.8162 | LM_LOSS: 0.3139 | LB_LOSS: 1.0047 |
| [2026-05-24 03:23:41] Validation | Batch 640/1463 | Loss: 0.8161 | LM_LOSS: 0.3137 | LB_LOSS: 1.0047 |
| [2026-05-24 03:23:43] Validation | Batch 650/1463 | Loss: 0.8156 | LM_LOSS: 0.3133 | LB_LOSS: 1.0047 |
| [2026-05-24 03:23:45] Validation | Batch 660/1463 | Loss: 0.8151 | LM_LOSS: 0.3128 | LB_LOSS: 1.0047 |
| [2026-05-24 03:23:47] Validation | Batch 670/1463 | Loss: 0.8147 | LM_LOSS: 0.3124 | LB_LOSS: 1.0047 |
| [2026-05-24 03:23:49] Validation | Batch 680/1463 | Loss: 0.8146 | LM_LOSS: 0.3123 | LB_LOSS: 1.0047 |
| [2026-05-24 03:23:51] Validation | Batch 690/1463 | Loss: 0.8149 | LM_LOSS: 0.3125 | LB_LOSS: 1.0047 |
| [2026-05-24 03:23:53] Validation | Batch 700/1463 | Loss: 0.8147 | LM_LOSS: 0.3124 | LB_LOSS: 1.0047 |
| [2026-05-24 03:23:55] Validation | Batch 710/1463 | Loss: 0.8150 | LM_LOSS: 0.3126 | LB_LOSS: 1.0047 |
| [2026-05-24 03:23:58] Validation | Batch 720/1463 | Loss: 0.8157 | LM_LOSS: 0.3134 | LB_LOSS: 1.0047 |
| [2026-05-24 03:23:59] Validation | Batch 730/1463 | Loss: 0.8156 | LM_LOSS: 0.3133 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:01] Validation | Batch 740/1463 | Loss: 0.8152 | LM_LOSS: 0.3129 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:03] Validation | Batch 750/1463 | Loss: 0.8152 | LM_LOSS: 0.3128 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:05] Validation | Batch 760/1463 | Loss: 0.8150 | LM_LOSS: 0.3126 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:06] Validation | Batch 770/1463 | Loss: 0.8149 | LM_LOSS: 0.3125 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:08] Validation | Batch 780/1463 | Loss: 0.8148 | LM_LOSS: 0.3124 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:10] Validation | Batch 790/1463 | Loss: 0.8150 | LM_LOSS: 0.3127 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:12] Validation | Batch 800/1463 | Loss: 0.8150 | LM_LOSS: 0.3126 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:14] Validation | Batch 810/1463 | Loss: 0.8146 | LM_LOSS: 0.3123 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:16] Validation | Batch 820/1463 | Loss: 0.8148 | LM_LOSS: 0.3125 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:18] Validation | Batch 830/1463 | Loss: 0.8151 | LM_LOSS: 0.3128 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:21] Validation | Batch 840/1463 | Loss: 0.8151 | LM_LOSS: 0.3128 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:23] Validation | Batch 850/1463 | Loss: 0.8155 | LM_LOSS: 0.3131 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:25] Validation | Batch 860/1463 | Loss: 0.8156 | LM_LOSS: 0.3133 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:27] Validation | Batch 870/1463 | Loss: 0.8157 | LM_LOSS: 0.3134 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:29] Validation | Batch 880/1463 | Loss: 0.8150 | LM_LOSS: 0.3127 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:31] Validation | Batch 890/1463 | Loss: 0.8150 | LM_LOSS: 0.3127 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:33] Validation | Batch 900/1463 | Loss: 0.8147 | LM_LOSS: 0.3123 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:36] Validation | Batch 910/1463 | Loss: 0.8146 | LM_LOSS: 0.3123 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:38] Validation | Batch 920/1463 | Loss: 0.8148 | LM_LOSS: 0.3124 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:40] Validation | Batch 930/1463 | Loss: 0.8144 | LM_LOSS: 0.3121 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:42] Validation | Batch 940/1463 | Loss: 0.8142 | LM_LOSS: 0.3118 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:44] Validation | Batch 950/1463 | Loss: 0.8144 | LM_LOSS: 0.3121 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:46] Validation | Batch 960/1463 | Loss: 0.8145 | LM_LOSS: 0.3122 | LB_LOSS: 1.0047 |
| [2026-05-24 03:24:49] Validation | Batch 970/1463 | Loss: 0.8145 | LM_LOSS: 0.3122 | LB_LOSS: 1.0046 |
| [2026-05-24 03:24:51] Validation | Batch 980/1463 | Loss: 0.8149 | LM_LOSS: 0.3126 | LB_LOSS: 1.0046 |
| [2026-05-24 03:24:53] Validation | Batch 990/1463 | Loss: 0.8151 | LM_LOSS: 0.3128 | LB_LOSS: 1.0046 |
| [2026-05-24 03:24:55] Validation | Batch 1000/1463 | Loss: 0.8158 | LM_LOSS: 0.3134 | LB_LOSS: 1.0046 |
| [2026-05-24 03:24:57] Validation | Batch 1010/1463 | Loss: 0.8158 | LM_LOSS: 0.3135 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:00] Validation | Batch 1020/1463 | Loss: 0.8159 | LM_LOSS: 0.3135 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:02] Validation | Batch 1030/1463 | Loss: 0.8164 | LM_LOSS: 0.3140 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:04] Validation | Batch 1040/1463 | Loss: 0.8160 | LM_LOSS: 0.3136 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:06] Validation | Batch 1050/1463 | Loss: 0.8159 | LM_LOSS: 0.3136 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:09] Validation | Batch 1060/1463 | Loss: 0.8159 | LM_LOSS: 0.3135 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:11] Validation | Batch 1070/1463 | Loss: 0.8159 | LM_LOSS: 0.3135 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:13] Validation | Batch 1080/1463 | Loss: 0.8157 | LM_LOSS: 0.3134 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:15] Validation | Batch 1090/1463 | Loss: 0.8156 | LM_LOSS: 0.3133 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:17] Validation | Batch 1100/1463 | Loss: 0.8155 | LM_LOSS: 0.3131 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:19] Validation | Batch 1110/1463 | Loss: 0.8155 | LM_LOSS: 0.3131 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:21] Validation | Batch 1120/1463 | Loss: 0.8153 | LM_LOSS: 0.3129 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:23] Validation | Batch 1130/1463 | Loss: 0.8151 | LM_LOSS: 0.3127 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:25] Validation | Batch 1140/1463 | Loss: 0.8153 | LM_LOSS: 0.3129 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:28] Validation | Batch 1150/1463 | Loss: 0.8152 | LM_LOSS: 0.3128 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:30] Validation | Batch 1160/1463 | Loss: 0.8151 | LM_LOSS: 0.3128 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:32] Validation | Batch 1170/1463 | Loss: 0.8151 | LM_LOSS: 0.3128 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:34] Validation | Batch 1180/1463 | Loss: 0.8152 | LM_LOSS: 0.3129 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:36] Validation | Batch 1190/1463 | Loss: 0.8154 | LM_LOSS: 0.3130 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:39] Validation | Batch 1200/1463 | Loss: 0.8153 | LM_LOSS: 0.3130 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:41] Validation | Batch 1210/1463 | Loss: 0.8155 | LM_LOSS: 0.3132 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:43] Validation | Batch 1220/1463 | Loss: 0.8159 | LM_LOSS: 0.3136 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:45] Validation | Batch 1230/1463 | Loss: 0.8159 | LM_LOSS: 0.3136 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:47] Validation | Batch 1240/1463 | Loss: 0.8162 | LM_LOSS: 0.3138 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:49] Validation | Batch 1250/1463 | Loss: 0.8163 | LM_LOSS: 0.3140 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:52] Validation | Batch 1260/1463 | Loss: 0.8162 | LM_LOSS: 0.3139 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:54] Validation | Batch 1270/1463 | Loss: 0.8160 | LM_LOSS: 0.3136 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:56] Validation | Batch 1280/1463 | Loss: 0.8158 | LM_LOSS: 0.3134 | LB_LOSS: 1.0047 |
| [2026-05-24 03:25:58] Validation | Batch 1290/1463 | Loss: 0.8157 | LM_LOSS: 0.3134 | LB_LOSS: 1.0047 |
| [2026-05-24 03:26:00] Validation | Batch 1300/1463 | Loss: 0.8155 | LM_LOSS: 0.3132 | LB_LOSS: 1.0047 |
| [2026-05-24 03:26:02] Validation | Batch 1310/1463 | Loss: 0.8154 | LM_LOSS: 0.3130 | LB_LOSS: 1.0047 |
| [2026-05-24 03:26:04] Validation | Batch 1320/1463 | Loss: 0.8154 | LM_LOSS: 0.3131 | LB_LOSS: 1.0047 |
| [2026-05-24 03:26:05] Validation | Batch 1330/1463 | Loss: 0.8154 | LM_LOSS: 0.3131 | LB_LOSS: 1.0047 |
| [2026-05-24 03:26:07] Validation | Batch 1340/1463 | Loss: 0.8157 | LM_LOSS: 0.3134 | LB_LOSS: 1.0047 |
| [2026-05-24 03:26:10] Validation | Batch 1350/1463 | Loss: 0.8157 | LM_LOSS: 0.3134 | LB_LOSS: 1.0047 |
| [2026-05-24 03:26:12] Validation | Batch 1360/1463 | Loss: 0.8160 | LM_LOSS: 0.3137 | LB_LOSS: 1.0047 |
| [2026-05-24 03:26:15] Validation | Batch 1370/1463 | Loss: 0.8163 | LM_LOSS: 0.3140 | LB_LOSS: 1.0047 |
| [2026-05-24 03:26:17] Validation | Batch 1380/1463 | Loss: 0.8160 | LM_LOSS: 0.3137 | LB_LOSS: 1.0047 |
| [2026-05-24 03:26:19] Validation | Batch 1390/1463 | Loss: 0.8160 | LM_LOSS: 0.3136 | LB_LOSS: 1.0047 |
| [2026-05-24 03:26:21] Validation | Batch 1400/1463 | Loss: 0.8163 | LM_LOSS: 0.3139 | LB_LOSS: 1.0046 |
| [2026-05-24 03:26:22] Validation | Batch 1410/1463 | Loss: 0.8165 | LM_LOSS: 0.3142 | LB_LOSS: 1.0046 |
| [2026-05-24 03:26:25] Validation | Batch 1420/1463 | Loss: 0.8166 | LM_LOSS: 0.3142 | LB_LOSS: 1.0047 |
| [2026-05-24 03:26:27] Validation | Batch 1430/1463 | Loss: 0.8166 | LM_LOSS: 0.3142 | LB_LOSS: 1.0046 |
| [2026-05-24 03:26:29] Validation | Batch 1440/1463 | Loss: 0.8170 | LM_LOSS: 0.3146 | LB_LOSS: 1.0047 |
| [2026-05-24 03:26:31] Validation | Batch 1450/1463 | Loss: 0.8167 | LM_LOSS: 0.3144 | LB_LOSS: 1.0046 |
| [2026-05-24 03:26:34] Validation | Batch 1460/1463 | Loss: 0.8170 | LM_LOSS: 0.3147 | LB_LOSS: 1.0046 |
| [2026-05-24 03:26:34] Validation | Batch 1463/1463 | Loss: 0.8169 | LM_LOSS: 0.3146 | LB_LOSS: 1.0046 |
| [2026-05-24 03:26:34] Validation | Loss: 0.8169 | LM_LOSS: 0.3146 | LB_LOSS: 1.0046 | PPL: 1.37 | Time: 310.26s |
| [2026-05-24 03:26:46] Epoch 2 | Step 8010 | Loss: 0.7557 | LM: 0.2525 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:26:57] Epoch 2 | Step 8020 | Loss: 0.7557 | LM: 0.2526 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:27:08] Epoch 2 | Step 8030 | Loss: 0.7557 | LM: 0.2526 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:27:19] Epoch 2 | Step 8040 | Loss: 0.7558 | LM: 0.2527 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:27:30] Epoch 2 | Step 8050 | Loss: 0.7557 | LM: 0.2526 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:27:41] Epoch 2 | Step 8060 | Loss: 0.7558 | LM: 0.2525 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:27:52] Epoch 2 | Step 8070 | Loss: 0.7557 | LM: 0.2525 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:28:03] Epoch 2 | Step 8080 | Loss: 0.7558 | LM: 0.2525 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:28:14] Epoch 2 | Step 8090 | Loss: 0.7558 | LM: 0.2524 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:28:24] Epoch 2 | Step 8100 | Loss: 0.7557 | LM: 0.2524 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:28:35] Epoch 2 | Step 8110 | Loss: 0.7557 | LM: 0.2525 | LB: 1.0072 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:28:46] Epoch 2 | Step 8120 | Loss: 0.7557 | LM: 0.2525 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:28:58] Epoch 2 | Step 8130 | Loss: 0.7558 | LM: 0.2524 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:29:09] Epoch 2 | Step 8140 | Loss: 0.7558 | LM: 0.2525 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:29:20] Epoch 2 | Step 8150 | Loss: 0.7558 | LM: 0.2524 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:29:31] Epoch 2 | Step 8160 | Loss: 0.7558 | LM: 0.2525 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:29:42] Epoch 2 | Step 8170 | Loss: 0.7558 | LM: 0.2527 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:29:53] Epoch 2 | Step 8180 | Loss: 0.7558 | LM: 0.2528 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:30:04] Epoch 2 | Step 8190 | Loss: 0.7559 | LM: 0.2529 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:30:16] Epoch 2 | Step 8200 | Loss: 0.7560 | LM: 0.2529 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:30:27] Epoch 2 | Step 8210 | Loss: 0.7560 | LM: 0.2531 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:30:38] Epoch 2 | Step 8220 | Loss: 0.7560 | LM: 0.2530 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:30:50] Epoch 2 | Step 8230 | Loss: 0.7560 | LM: 0.2530 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:31:01] Epoch 2 | Step 8240 | Loss: 0.7559 | LM: 0.2530 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:31:12] Epoch 2 | Step 8250 | Loss: 0.7560 | LM: 0.2531 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:31:24] Epoch 2 | Step 8260 | Loss: 0.7561 | LM: 0.2531 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.289 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:31:36] Epoch 2 | Step 8270 | Loss: 0.7561 | LM: 0.2531 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:31:48] Epoch 2 | Step 8280 | Loss: 0.7562 | LM: 0.2532 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:31:59] Epoch 2 | Step 8290 | Loss: 0.7562 | LM: 0.2532 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:32:11] Epoch 2 | Step 8300 | Loss: 0.7561 | LM: 0.2532 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:32:22] Epoch 2 | Step 8310 | Loss: 0.7561 | LM: 0.2532 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:32:33] Epoch 2 | Step 8320 | Loss: 0.7561 | LM: 0.2532 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:32:45] Epoch 2 | Step 8330 | Loss: 0.7561 | LM: 0.2533 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:32:57] Epoch 2 | Step 8340 | Loss: 0.7561 | LM: 0.2531 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:33:08] Epoch 2 | Step 8350 | Loss: 0.7561 | LM: 0.2531 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:33:19] Epoch 2 | Step 8360 | Loss: 0.7562 | LM: 0.2534 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:33:30] Epoch 2 | Step 8370 | Loss: 0.7563 | LM: 0.2532 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:33:41] Epoch 2 | Step 8380 | Loss: 0.7562 | LM: 0.2531 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:33:52] Epoch 2 | Step 8390 | Loss: 0.7563 | LM: 0.2531 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:34:03] Epoch 2 | Step 8400 | Loss: 0.7563 | LM: 0.2532 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:34:15] Epoch 2 | Step 8410 | Loss: 0.7563 | LM: 0.2531 | LB: 1.0071 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:34:26] Epoch 2 | Step 8420 | Loss: 0.7563 | LM: 0.2531 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:34:37] Epoch 2 | Step 8430 | Loss: 0.7563 | LM: 0.2531 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:34:48] Epoch 2 | Step 8440 | Loss: 0.7563 | LM: 0.2533 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:34:59] Epoch 2 | Step 8450 | Loss: 0.7563 | LM: 0.2533 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:35:10] Epoch 2 | Step 8460 | Loss: 0.7564 | LM: 0.2533 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.311/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:35:21] Epoch 2 | Step 8470 | Loss: 0.7563 | LM: 0.2532 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:35:32] Epoch 2 | Step 8480 | Loss: 0.7562 | LM: 0.2530 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:35:43] Epoch 2 | Step 8490 | Loss: 0.7563 | LM: 0.2531 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 03:35:54] Epoch 2 | Step 8500 | Loss: 0.7563 | LM: 0.2532 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 03:36:04] Epoch 2 | Step 8510 | Loss: 0.7564 | LM: 0.2533 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 03:36:16] Epoch 2 | Step 8520 | Loss: 0.7564 | LM: 0.2534 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 03:36:27] Epoch 2 | Step 8530 | Loss: 0.7564 | LM: 0.2535 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 03:36:38] Epoch 2 | Step 8540 | Loss: 0.7564 | LM: 0.2533 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 03:36:49] Epoch 2 | Step 8550 | Loss: 0.7564 | LM: 0.2533 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 03:37:00] Epoch 2 | Step 8560 | Loss: 0.7563 | LM: 0.2532 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 03:37:12] Epoch 2 | Step 8570 | Loss: 0.7563 | LM: 0.2532 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:37:24] Epoch 2 | Step 8580 | Loss: 0.7563 | LM: 0.2532 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 03:37:35] Epoch 2 | Step 8590 | Loss: 0.7563 | LM: 0.2533 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 03:37:46] Epoch 2 | Step 8600 | Loss: 0.7563 | LM: 0.2533 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 03:37:58] Epoch 2 | Step 8610 | Loss: 0.7563 | LM: 0.2533 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:38:10] Epoch 2 | Step 8620 | Loss: 0.7564 | LM: 0.2535 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 03:38:21] Epoch 2 | Step 8630 | Loss: 0.7564 | LM: 0.2535 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 03:38:32] Epoch 2 | Step 8640 | Loss: 0.7564 | LM: 0.2534 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 03:38:44] Epoch 2 | Step 8650 | Loss: 0.7564 | LM: 0.2534 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:38:55] Epoch 2 | Step 8660 | Loss: 0.7563 | LM: 0.2534 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:39:07] Epoch 2 | Step 8670 | Loss: 0.7563 | LM: 0.2533 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:39:18] Epoch 2 | Step 8680 | Loss: 0.7563 | LM: 0.2531 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:39:30] Epoch 2 | Step 8690 | Loss: 0.7563 | LM: 0.2531 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:39:41] Epoch 2 | Step 8700 | Loss: 0.7563 | LM: 0.2534 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:39:53] Epoch 2 | Step 8710 | Loss: 0.7564 | LM: 0.2534 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:40:04] Epoch 2 | Step 8720 | Loss: 0.7564 | LM: 0.2534 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:40:15] Epoch 2 | Step 8730 | Loss: 0.7564 | LM: 0.2536 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:40:27] Epoch 2 | Step 8740 | Loss: 0.7564 | LM: 0.2536 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:40:38] Epoch 2 | Step 8750 | Loss: 0.7565 | LM: 0.2536 | LB: 1.0070 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:40:50] Epoch 2 | Step 8760 | Loss: 0.7565 | LM: 0.2536 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:41:02] Epoch 2 | Step 8770 | Loss: 0.7566 | LM: 0.2537 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:41:13] Epoch 2 | Step 8780 | Loss: 0.7566 | LM: 0.2535 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:41:24] Epoch 2 | Step 8790 | Loss: 0.7566 | LM: 0.2536 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:41:36] Epoch 2 | Step 8800 | Loss: 0.7567 | LM: 0.2537 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:41:47] Epoch 2 | Step 8810 | Loss: 0.7566 | LM: 0.2538 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:41:58] Epoch 2 | Step 8820 | Loss: 0.7567 | LM: 0.2540 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:42:09] Epoch 2 | Step 8830 | Loss: 0.7567 | LM: 0.2541 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:42:20] Epoch 2 | Step 8840 | Loss: 0.7567 | LM: 0.2542 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:42:31] Epoch 2 | Step 8850 | Loss: 0.7567 | LM: 0.2542 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:42:43] Epoch 2 | Step 8860 | Loss: 0.7567 | LM: 0.2543 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:42:54] Epoch 2 | Step 8870 | Loss: 0.7567 | LM: 0.2542 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:43:05] Epoch 2 | Step 8880 | Loss: 0.7568 | LM: 0.2543 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:43:16] Epoch 2 | Step 8890 | Loss: 0.7567 | LM: 0.2544 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:43:27] Epoch 2 | Step 8900 | Loss: 0.7567 | LM: 0.2544 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:43:38] Epoch 2 | Step 8910 | Loss: 0.7568 | LM: 0.2546 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:43:49] Epoch 2 | Step 8920 | Loss: 0.7567 | LM: 0.2546 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:44:01] Epoch 2 | Step 8930 | Loss: 0.7567 | LM: 0.2546 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:44:11] Epoch 2 | Step 8940 | Loss: 0.7567 | LM: 0.2545 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:44:23] Epoch 2 | Step 8950 | Loss: 0.7567 | LM: 0.2544 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:44:34] Epoch 2 | Step 8960 | Loss: 0.7566 | LM: 0.2544 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.288 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:44:45] Epoch 2 | Step 8970 | Loss: 0.7567 | LM: 0.2545 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:44:56] Epoch 2 | Step 8980 | Loss: 0.7568 | LM: 0.2547 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:45:07] Epoch 2 | Step 8990 | Loss: 0.7568 | LM: 0.2546 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:45:18] Epoch 2 | Step 9000 | Loss: 0.7568 | LM: 0.2546 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:45:22] Checkpoint saved: outputs/2026-05-24/N_4.0/checkpoints/checkpoint_step_9000.pt |
| [2026-05-24 03:45:28] Validation | Batch 10/1463 | Loss: 0.7911 | LM_LOSS: 0.2899 | LB_LOSS: 1.0024 |
| [2026-05-24 03:45:30] Validation | Batch 20/1463 | Loss: 0.7983 | LM_LOSS: 0.2966 | LB_LOSS: 1.0034 |
| [2026-05-24 03:45:32] Validation | Batch 30/1463 | Loss: 0.7984 | LM_LOSS: 0.2965 | LB_LOSS: 1.0038 |
| [2026-05-24 03:45:34] Validation | Batch 40/1463 | Loss: 0.8058 | LM_LOSS: 0.3037 | LB_LOSS: 1.0042 |
| [2026-05-24 03:45:36] Validation | Batch 50/1463 | Loss: 0.8136 | LM_LOSS: 0.3116 | LB_LOSS: 1.0040 |
| [2026-05-24 03:45:39] Validation | Batch 60/1463 | Loss: 0.8131 | LM_LOSS: 0.3112 | LB_LOSS: 1.0039 |
| [2026-05-24 03:45:41] Validation | Batch 70/1463 | Loss: 0.8123 | LM_LOSS: 0.3103 | LB_LOSS: 1.0039 |
| [2026-05-24 03:45:44] Validation | Batch 80/1463 | Loss: 0.8144 | LM_LOSS: 0.3124 | LB_LOSS: 1.0039 |
| [2026-05-24 03:45:46] Validation | Batch 90/1463 | Loss: 0.8145 | LM_LOSS: 0.3126 | LB_LOSS: 1.0038 |
| [2026-05-24 03:45:48] Validation | Batch 100/1463 | Loss: 0.8145 | LM_LOSS: 0.3126 | LB_LOSS: 1.0038 |
| [2026-05-24 03:45:50] Validation | Batch 110/1463 | Loss: 0.8126 | LM_LOSS: 0.3106 | LB_LOSS: 1.0040 |
| [2026-05-24 03:45:52] Validation | Batch 120/1463 | Loss: 0.8143 | LM_LOSS: 0.3123 | LB_LOSS: 1.0041 |
| [2026-05-24 03:45:53] Validation | Batch 130/1463 | Loss: 0.8161 | LM_LOSS: 0.3140 | LB_LOSS: 1.0041 |
| [2026-05-24 03:45:56] Validation | Batch 140/1463 | Loss: 0.8170 | LM_LOSS: 0.3149 | LB_LOSS: 1.0041 |
| [2026-05-24 03:45:58] Validation | Batch 150/1463 | Loss: 0.8153 | LM_LOSS: 0.3131 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:00] Validation | Batch 160/1463 | Loss: 0.8154 | LM_LOSS: 0.3134 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:03] Validation | Batch 170/1463 | Loss: 0.8150 | LM_LOSS: 0.3129 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:05] Validation | Batch 180/1463 | Loss: 0.8155 | LM_LOSS: 0.3135 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:07] Validation | Batch 190/1463 | Loss: 0.8169 | LM_LOSS: 0.3148 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:09] Validation | Batch 200/1463 | Loss: 0.8167 | LM_LOSS: 0.3146 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:11] Validation | Batch 210/1463 | Loss: 0.8174 | LM_LOSS: 0.3153 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:14] Validation | Batch 220/1463 | Loss: 0.8169 | LM_LOSS: 0.3148 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:16] Validation | Batch 230/1463 | Loss: 0.8183 | LM_LOSS: 0.3163 | LB_LOSS: 1.0041 |
| [2026-05-24 03:46:18] Validation | Batch 240/1463 | Loss: 0.8197 | LM_LOSS: 0.3177 | LB_LOSS: 1.0041 |
| [2026-05-24 03:46:20] Validation | Batch 250/1463 | Loss: 0.8188 | LM_LOSS: 0.3168 | LB_LOSS: 1.0041 |
| [2026-05-24 03:46:22] Validation | Batch 260/1463 | Loss: 0.8205 | LM_LOSS: 0.3184 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:25] Validation | Batch 270/1463 | Loss: 0.8190 | LM_LOSS: 0.3169 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:27] Validation | Batch 280/1463 | Loss: 0.8195 | LM_LOSS: 0.3174 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:29] Validation | Batch 290/1463 | Loss: 0.8186 | LM_LOSS: 0.3165 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:31] Validation | Batch 300/1463 | Loss: 0.8189 | LM_LOSS: 0.3167 | LB_LOSS: 1.0043 |
| [2026-05-24 03:46:33] Validation | Batch 310/1463 | Loss: 0.8198 | LM_LOSS: 0.3177 | LB_LOSS: 1.0043 |
| [2026-05-24 03:46:35] Validation | Batch 320/1463 | Loss: 0.8185 | LM_LOSS: 0.3164 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:37] Validation | Batch 330/1463 | Loss: 0.8183 | LM_LOSS: 0.3162 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:39] Validation | Batch 340/1463 | Loss: 0.8178 | LM_LOSS: 0.3157 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:41] Validation | Batch 350/1463 | Loss: 0.8184 | LM_LOSS: 0.3163 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:43] Validation | Batch 360/1463 | Loss: 0.8182 | LM_LOSS: 0.3161 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:45] Validation | Batch 370/1463 | Loss: 0.8178 | LM_LOSS: 0.3157 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:47] Validation | Batch 380/1463 | Loss: 0.8176 | LM_LOSS: 0.3155 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:49] Validation | Batch 390/1463 | Loss: 0.8182 | LM_LOSS: 0.3161 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:51] Validation | Batch 400/1463 | Loss: 0.8181 | LM_LOSS: 0.3160 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:53] Validation | Batch 410/1463 | Loss: 0.8178 | LM_LOSS: 0.3157 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:56] Validation | Batch 420/1463 | Loss: 0.8179 | LM_LOSS: 0.3158 | LB_LOSS: 1.0042 |
| [2026-05-24 03:46:58] Validation | Batch 430/1463 | Loss: 0.8174 | LM_LOSS: 0.3153 | LB_LOSS: 1.0043 |
| [2026-05-24 03:47:00] Validation | Batch 440/1463 | Loss: 0.8177 | LM_LOSS: 0.3156 | LB_LOSS: 1.0043 |
| [2026-05-24 03:47:02] Validation | Batch 450/1463 | Loss: 0.8174 | LM_LOSS: 0.3153 | LB_LOSS: 1.0043 |
| [2026-05-24 03:47:04] Validation | Batch 460/1463 | Loss: 0.8173 | LM_LOSS: 0.3152 | LB_LOSS: 1.0043 |
| [2026-05-24 03:47:07] Validation | Batch 470/1463 | Loss: 0.8180 | LM_LOSS: 0.3159 | LB_LOSS: 1.0042 |
| [2026-05-24 03:47:09] Validation | Batch 480/1463 | Loss: 0.8177 | LM_LOSS: 0.3156 | LB_LOSS: 1.0042 |
| [2026-05-24 03:47:11] Validation | Batch 490/1463 | Loss: 0.8176 | LM_LOSS: 0.3154 | LB_LOSS: 1.0042 |
| [2026-05-24 03:47:14] Validation | Batch 500/1463 | Loss: 0.8174 | LM_LOSS: 0.3153 | LB_LOSS: 1.0042 |
| [2026-05-24 03:47:16] Validation | Batch 510/1463 | Loss: 0.8168 | LM_LOSS: 0.3147 | LB_LOSS: 1.0042 |
| [2026-05-24 03:47:18] Validation | Batch 520/1463 | Loss: 0.8164 | LM_LOSS: 0.3143 | LB_LOSS: 1.0042 |
| [2026-05-24 03:47:20] Validation | Batch 530/1463 | Loss: 0.8169 | LM_LOSS: 0.3148 | LB_LOSS: 1.0042 |
| [2026-05-24 03:47:22] Validation | Batch 540/1463 | Loss: 0.8172 | LM_LOSS: 0.3151 | LB_LOSS: 1.0042 |
| [2026-05-24 03:47:23] Validation | Batch 550/1463 | Loss: 0.8168 | LM_LOSS: 0.3146 | LB_LOSS: 1.0043 |
| [2026-05-24 03:47:25] Validation | Batch 560/1463 | Loss: 0.8169 | LM_LOSS: 0.3148 | LB_LOSS: 1.0043 |
| [2026-05-24 03:47:28] Validation | Batch 570/1463 | Loss: 0.8168 | LM_LOSS: 0.3147 | LB_LOSS: 1.0043 |
| [2026-05-24 03:47:30] Validation | Batch 580/1463 | Loss: 0.8164 | LM_LOSS: 0.3143 | LB_LOSS: 1.0043 |
| [2026-05-24 03:47:32] Validation | Batch 590/1463 | Loss: 0.8162 | LM_LOSS: 0.3141 | LB_LOSS: 1.0043 |
| [2026-05-24 03:47:35] Validation | Batch 600/1463 | Loss: 0.8164 | LM_LOSS: 0.3143 | LB_LOSS: 1.0043 |
| [2026-05-24 03:47:37] Validation | Batch 610/1463 | Loss: 0.8166 | LM_LOSS: 0.3144 | LB_LOSS: 1.0043 |
| [2026-05-24 03:47:39] Validation | Batch 620/1463 | Loss: 0.8160 | LM_LOSS: 0.3138 | LB_LOSS: 1.0043 |
| [2026-05-24 03:47:41] Validation | Batch 630/1463 | Loss: 0.8156 | LM_LOSS: 0.3134 | LB_LOSS: 1.0043 |
| [2026-05-24 03:47:43] Validation | Batch 640/1463 | Loss: 0.8155 | LM_LOSS: 0.3133 | LB_LOSS: 1.0044 |
| [2026-05-24 03:47:45] Validation | Batch 650/1463 | Loss: 0.8150 | LM_LOSS: 0.3128 | LB_LOSS: 1.0043 |
| [2026-05-24 03:47:47] Validation | Batch 660/1463 | Loss: 0.8145 | LM_LOSS: 0.3123 | LB_LOSS: 1.0043 |
| [2026-05-24 03:47:49] Validation | Batch 670/1463 | Loss: 0.8140 | LM_LOSS: 0.3119 | LB_LOSS: 1.0043 |
| [2026-05-24 03:47:51] Validation | Batch 680/1463 | Loss: 0.8140 | LM_LOSS: 0.3118 | LB_LOSS: 1.0043 |
| [2026-05-24 03:47:53] Validation | Batch 690/1463 | Loss: 0.8142 | LM_LOSS: 0.3121 | LB_LOSS: 1.0043 |
| [2026-05-24 03:47:55] Validation | Batch 700/1463 | Loss: 0.8141 | LM_LOSS: 0.3120 | LB_LOSS: 1.0043 |
| [2026-05-24 03:47:57] Validation | Batch 710/1463 | Loss: 0.8144 | LM_LOSS: 0.3122 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:00] Validation | Batch 720/1463 | Loss: 0.8151 | LM_LOSS: 0.3129 | LB_LOSS: 1.0044 |
| [2026-05-24 03:48:01] Validation | Batch 730/1463 | Loss: 0.8149 | LM_LOSS: 0.3128 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:03] Validation | Batch 740/1463 | Loss: 0.8146 | LM_LOSS: 0.3124 | LB_LOSS: 1.0044 |
| [2026-05-24 03:48:05] Validation | Batch 750/1463 | Loss: 0.8145 | LM_LOSS: 0.3123 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:07] Validation | Batch 760/1463 | Loss: 0.8143 | LM_LOSS: 0.3121 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:09] Validation | Batch 770/1463 | Loss: 0.8142 | LM_LOSS: 0.3120 | LB_LOSS: 1.0044 |
| [2026-05-24 03:48:11] Validation | Batch 780/1463 | Loss: 0.8141 | LM_LOSS: 0.3119 | LB_LOSS: 1.0044 |
| [2026-05-24 03:48:12] Validation | Batch 790/1463 | Loss: 0.8143 | LM_LOSS: 0.3122 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:14] Validation | Batch 800/1463 | Loss: 0.8143 | LM_LOSS: 0.3121 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:16] Validation | Batch 810/1463 | Loss: 0.8140 | LM_LOSS: 0.3118 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:18] Validation | Batch 820/1463 | Loss: 0.8142 | LM_LOSS: 0.3121 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:20] Validation | Batch 830/1463 | Loss: 0.8145 | LM_LOSS: 0.3124 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:23] Validation | Batch 840/1463 | Loss: 0.8146 | LM_LOSS: 0.3124 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:25] Validation | Batch 850/1463 | Loss: 0.8149 | LM_LOSS: 0.3127 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:27] Validation | Batch 860/1463 | Loss: 0.8150 | LM_LOSS: 0.3128 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:29] Validation | Batch 870/1463 | Loss: 0.8151 | LM_LOSS: 0.3129 | LB_LOSS: 1.0044 |
| [2026-05-24 03:48:31] Validation | Batch 880/1463 | Loss: 0.8144 | LM_LOSS: 0.3122 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:33] Validation | Batch 890/1463 | Loss: 0.8144 | LM_LOSS: 0.3122 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:35] Validation | Batch 900/1463 | Loss: 0.8140 | LM_LOSS: 0.3119 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:38] Validation | Batch 910/1463 | Loss: 0.8140 | LM_LOSS: 0.3118 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:40] Validation | Batch 920/1463 | Loss: 0.8141 | LM_LOSS: 0.3120 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:42] Validation | Batch 930/1463 | Loss: 0.8138 | LM_LOSS: 0.3117 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:44] Validation | Batch 940/1463 | Loss: 0.8136 | LM_LOSS: 0.3114 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:47] Validation | Batch 950/1463 | Loss: 0.8138 | LM_LOSS: 0.3117 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:49] Validation | Batch 960/1463 | Loss: 0.8139 | LM_LOSS: 0.3117 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:51] Validation | Batch 970/1463 | Loss: 0.8139 | LM_LOSS: 0.3118 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:53] Validation | Batch 980/1463 | Loss: 0.8142 | LM_LOSS: 0.3121 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:55] Validation | Batch 990/1463 | Loss: 0.8145 | LM_LOSS: 0.3124 | LB_LOSS: 1.0043 |
| [2026-05-24 03:48:57] Validation | Batch 1000/1463 | Loss: 0.8150 | LM_LOSS: 0.3129 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:00] Validation | Batch 1010/1463 | Loss: 0.8151 | LM_LOSS: 0.3129 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:02] Validation | Batch 1020/1463 | Loss: 0.8152 | LM_LOSS: 0.3130 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:04] Validation | Batch 1030/1463 | Loss: 0.8157 | LM_LOSS: 0.3135 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:06] Validation | Batch 1040/1463 | Loss: 0.8153 | LM_LOSS: 0.3132 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:09] Validation | Batch 1050/1463 | Loss: 0.8152 | LM_LOSS: 0.3131 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:11] Validation | Batch 1060/1463 | Loss: 0.8152 | LM_LOSS: 0.3131 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:13] Validation | Batch 1070/1463 | Loss: 0.8152 | LM_LOSS: 0.3130 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:15] Validation | Batch 1080/1463 | Loss: 0.8150 | LM_LOSS: 0.3129 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:17] Validation | Batch 1090/1463 | Loss: 0.8150 | LM_LOSS: 0.3128 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:19] Validation | Batch 1100/1463 | Loss: 0.8148 | LM_LOSS: 0.3127 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:21] Validation | Batch 1110/1463 | Loss: 0.8148 | LM_LOSS: 0.3127 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:23] Validation | Batch 1120/1463 | Loss: 0.8146 | LM_LOSS: 0.3125 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:25] Validation | Batch 1130/1463 | Loss: 0.8144 | LM_LOSS: 0.3122 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:28] Validation | Batch 1140/1463 | Loss: 0.8146 | LM_LOSS: 0.3124 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:30] Validation | Batch 1150/1463 | Loss: 0.8145 | LM_LOSS: 0.3123 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:32] Validation | Batch 1160/1463 | Loss: 0.8144 | LM_LOSS: 0.3123 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:34] Validation | Batch 1170/1463 | Loss: 0.8144 | LM_LOSS: 0.3122 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:36] Validation | Batch 1180/1463 | Loss: 0.8145 | LM_LOSS: 0.3123 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:39] Validation | Batch 1190/1463 | Loss: 0.8146 | LM_LOSS: 0.3125 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:41] Validation | Batch 1200/1463 | Loss: 0.8146 | LM_LOSS: 0.3124 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:43] Validation | Batch 1210/1463 | Loss: 0.8148 | LM_LOSS: 0.3127 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:45] Validation | Batch 1220/1463 | Loss: 0.8152 | LM_LOSS: 0.3131 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:47] Validation | Batch 1230/1463 | Loss: 0.8152 | LM_LOSS: 0.3130 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:49] Validation | Batch 1240/1463 | Loss: 0.8155 | LM_LOSS: 0.3133 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:51] Validation | Batch 1250/1463 | Loss: 0.8156 | LM_LOSS: 0.3134 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:54] Validation | Batch 1260/1463 | Loss: 0.8155 | LM_LOSS: 0.3133 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:56] Validation | Batch 1270/1463 | Loss: 0.8153 | LM_LOSS: 0.3131 | LB_LOSS: 1.0043 |
| [2026-05-24 03:49:58] Validation | Batch 1280/1463 | Loss: 0.8151 | LM_LOSS: 0.3129 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:00] Validation | Batch 1290/1463 | Loss: 0.8151 | LM_LOSS: 0.3129 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:02] Validation | Batch 1300/1463 | Loss: 0.8148 | LM_LOSS: 0.3127 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:05] Validation | Batch 1310/1463 | Loss: 0.8147 | LM_LOSS: 0.3126 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:06] Validation | Batch 1320/1463 | Loss: 0.8148 | LM_LOSS: 0.3126 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:08] Validation | Batch 1330/1463 | Loss: 0.8148 | LM_LOSS: 0.3127 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:10] Validation | Batch 1340/1463 | Loss: 0.8151 | LM_LOSS: 0.3130 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:12] Validation | Batch 1350/1463 | Loss: 0.8151 | LM_LOSS: 0.3129 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:15] Validation | Batch 1360/1463 | Loss: 0.8153 | LM_LOSS: 0.3132 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:17] Validation | Batch 1370/1463 | Loss: 0.8156 | LM_LOSS: 0.3135 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:19] Validation | Batch 1380/1463 | Loss: 0.8154 | LM_LOSS: 0.3132 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:21] Validation | Batch 1390/1463 | Loss: 0.8153 | LM_LOSS: 0.3132 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:23] Validation | Batch 1400/1463 | Loss: 0.8156 | LM_LOSS: 0.3134 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:25] Validation | Batch 1410/1463 | Loss: 0.8158 | LM_LOSS: 0.3137 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:27] Validation | Batch 1420/1463 | Loss: 0.8158 | LM_LOSS: 0.3137 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:29] Validation | Batch 1430/1463 | Loss: 0.8158 | LM_LOSS: 0.3137 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:32] Validation | Batch 1440/1463 | Loss: 0.8162 | LM_LOSS: 0.3141 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:34] Validation | Batch 1450/1463 | Loss: 0.8160 | LM_LOSS: 0.3138 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:36] Validation | Batch 1460/1463 | Loss: 0.8163 | LM_LOSS: 0.3142 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:37] Validation | Batch 1463/1463 | Loss: 0.8162 | LM_LOSS: 0.3141 | LB_LOSS: 1.0043 |
| [2026-05-24 03:50:37] Validation | Loss: 0.8162 | LM_LOSS: 0.3141 | LB_LOSS: 1.0043 | PPL: 1.37 | Time: 310.68s |
| [2026-05-24 03:50:48] Epoch 2 | Step 9010 | Loss: 0.7567 | LM: 0.2545 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:51:00] Epoch 2 | Step 9020 | Loss: 0.7567 | LM: 0.2544 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:51:12] Epoch 2 | Step 9030 | Loss: 0.7566 | LM: 0.2544 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:51:24] Epoch 2 | Step 9040 | Loss: 0.7566 | LM: 0.2543 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:51:36] Epoch 2 | Step 9050 | Loss: 0.7566 | LM: 0.2543 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:51:48] Epoch 2 | Step 9060 | Loss: 0.7566 | LM: 0.2545 | LB: 1.0069 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:51:59] Epoch 2 | Step 9070 | Loss: 0.7566 | LM: 0.2544 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:52:11] Epoch 2 | Step 9080 | Loss: 0.7566 | LM: 0.2544 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:52:23] Epoch 2 | Step 9090 | Loss: 0.7567 | LM: 0.2544 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:52:34] Epoch 2 | Step 9100 | Loss: 0.7567 | LM: 0.2544 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:52:46] Epoch 2 | Step 9110 | Loss: 0.7567 | LM: 0.2544 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:52:57] Epoch 2 | Step 9120 | Loss: 0.7567 | LM: 0.2543 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:53:08] Epoch 2 | Step 9130 | Loss: 0.7566 | LM: 0.2543 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:53:20] Epoch 2 | Step 9140 | Loss: 0.7567 | LM: 0.2545 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:53:31] Epoch 2 | Step 9150 | Loss: 0.7567 | LM: 0.2545 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:53:42] Epoch 2 | Step 9160 | Loss: 0.7566 | LM: 0.2544 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:53:53] Epoch 2 | Step 9170 | Loss: 0.7566 | LM: 0.2544 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:54:04] Epoch 2 | Step 9180 | Loss: 0.7566 | LM: 0.2544 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:54:15] Epoch 2 | Step 9190 | Loss: 0.7567 | LM: 0.2545 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:54:26] Epoch 2 | Step 9200 | Loss: 0.7566 | LM: 0.2545 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:54:37] Epoch 2 | Step 9210 | Loss: 0.7567 | LM: 0.2545 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:54:48] Epoch 2 | Step 9220 | Loss: 0.7567 | LM: 0.2545 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:54:59] Epoch 2 | Step 9230 | Loss: 0.7567 | LM: 0.2544 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:55:10] Epoch 2 | Step 9240 | Loss: 0.7567 | LM: 0.2544 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:55:21] Epoch 2 | Step 9250 | Loss: 0.7567 | LM: 0.2544 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:55:32] Epoch 2 | Step 9260 | Loss: 0.7567 | LM: 0.2544 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:55:43] Epoch 2 | Step 9270 | Loss: 0.7567 | LM: 0.2543 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:55:54] Epoch 2 | Step 9280 | Loss: 0.7567 | LM: 0.2544 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:56:05] Epoch 2 | Step 9290 | Loss: 0.7568 | LM: 0.2544 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:56:17] Epoch 2 | Step 9300 | Loss: 0.7569 | LM: 0.2545 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:56:28] Epoch 2 | Step 9310 | Loss: 0.7569 | LM: 0.2545 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:56:40] Epoch 2 | Step 9320 | Loss: 0.7570 | LM: 0.2546 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:56:51] Epoch 2 | Step 9330 | Loss: 0.7569 | LM: 0.2547 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:57:02] Epoch 2 | Step 9340 | Loss: 0.7570 | LM: 0.2546 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:57:13] Epoch 2 | Step 9350 | Loss: 0.7570 | LM: 0.2546 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:57:24] Epoch 2 | Step 9360 | Loss: 0.7570 | LM: 0.2546 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:57:36] Epoch 2 | Step 9370 | Loss: 0.7570 | LM: 0.2547 | LB: 1.0068 | CL0: 3.2 | CL1: 3.7 | HR0: 0.310/SR0: 0.287 | HR1: 0.269/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 03:57:41] Epoch 2 completed in 6898.03s | Loss: 0.7570 | CL0: 3.2 | CL1: 3.7 |
| [2026-05-24 03:57:41] |
| ============================================================ |
| [2026-05-24 03:57:41] EPOCH 3/3 (step 9374) |
| [2026-05-24 03:57:41] ============================================================ |
| [2026-05-24 03:57:48] Epoch 3 | Step 9380 | Loss: 0.6857 | LM: 0.1771 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.308/SR0: 0.282 | HR1: 0.266/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 03:58:00] Epoch 3 | Step 9390 | Loss: 0.6957 | LM: 0.1788 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.308/SR0: 0.282 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 03:58:11] Epoch 3 | Step 9400 | Loss: 0.6921 | LM: 0.1846 | LB: 1.0045 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 03:58:23] Epoch 3 | Step 9410 | Loss: 0.6916 | LM: 0.1778 | LB: 1.0048 | CL0: 3.3 | CL1: 3.8 | HR0: 0.304/SR0: 0.279 | HR1: 0.262/SR1: 0.224 | LR: 1.00e-04 |
| [2026-05-24 03:58:34] Epoch 3 | Step 9420 | Loss: 0.6787 | LM: 0.1586 | LB: 1.0047 | CL0: 3.3 | CL1: 3.9 | HR0: 0.303/SR0: 0.278 | HR1: 0.261/SR1: 0.223 | LR: 1.00e-04 |
| [2026-05-24 03:58:46] Epoch 3 | Step 9430 | Loss: 0.6771 | LM: 0.1601 | LB: 1.0049 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.264/SR1: 0.226 | LR: 1.00e-04 |
| [2026-05-24 03:58:57] Epoch 3 | Step 9440 | Loss: 0.6738 | LM: 0.1539 | LB: 1.0047 | CL0: 3.3 | CL1: 3.8 | HR0: 0.304/SR0: 0.279 | HR1: 0.264/SR1: 0.226 | LR: 1.00e-04 |
| [2026-05-24 03:59:09] Epoch 3 | Step 9450 | Loss: 0.6775 | LM: 0.1611 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.281 | HR1: 0.265/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 03:59:21] Epoch 3 | Step 9460 | Loss: 0.6747 | LM: 0.1596 | LB: 1.0049 | CL0: 3.3 | CL1: 3.8 | HR0: 0.304/SR0: 0.279 | HR1: 0.265/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 03:59:32] Epoch 3 | Step 9470 | Loss: 0.6727 | LM: 0.1598 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 03:59:44] Epoch 3 | Step 9480 | Loss: 0.6714 | LM: 0.1648 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 03:59:56] Epoch 3 | Step 9490 | Loss: 0.6709 | LM: 0.1632 | LB: 1.0049 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:00:08] Epoch 3 | Step 9500 | Loss: 0.6703 | LM: 0.1640 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:00:20] Epoch 3 | Step 9510 | Loss: 0.6695 | LM: 0.1609 | LB: 1.0058 | CL0: 3.3 | CL1: 3.8 | HR0: 0.307/SR0: 0.282 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:00:32] Epoch 3 | Step 9520 | Loss: 0.6694 | LM: 0.1602 | LB: 1.0060 | CL0: 3.3 | CL1: 3.8 | HR0: 0.308/SR0: 0.282 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:00:43] Epoch 3 | Step 9530 | Loss: 0.6707 | LM: 0.1640 | LB: 1.0061 | CL0: 3.3 | CL1: 3.8 | HR0: 0.308/SR0: 0.282 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:00:55] Epoch 3 | Step 9540 | Loss: 0.6699 | LM: 0.1634 | LB: 1.0060 | CL0: 3.3 | CL1: 3.8 | HR0: 0.307/SR0: 0.282 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:01:08] Epoch 3 | Step 9550 | Loss: 0.6698 | LM: 0.1626 | LB: 1.0060 | CL0: 3.3 | CL1: 3.8 | HR0: 0.307/SR0: 0.282 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:01:20] Epoch 3 | Step 9560 | Loss: 0.6680 | LM: 0.1607 | LB: 1.0059 | CL0: 3.3 | CL1: 3.8 | HR0: 0.307/SR0: 0.281 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:01:32] Epoch 3 | Step 9570 | Loss: 0.6689 | LM: 0.1660 | LB: 1.0060 | CL0: 3.3 | CL1: 3.8 | HR0: 0.307/SR0: 0.282 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:01:44] Epoch 3 | Step 9580 | Loss: 0.6684 | LM: 0.1662 | LB: 1.0061 | CL0: 3.3 | CL1: 3.8 | HR0: 0.307/SR0: 0.282 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:01:55] Epoch 3 | Step 9590 | Loss: 0.6674 | LM: 0.1661 | LB: 1.0060 | CL0: 3.3 | CL1: 3.8 | HR0: 0.307/SR0: 0.282 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:02:07] Epoch 3 | Step 9600 | Loss: 0.6678 | LM: 0.1651 | LB: 1.0059 | CL0: 3.3 | CL1: 3.8 | HR0: 0.307/SR0: 0.281 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:02:19] Epoch 3 | Step 9610 | Loss: 0.6671 | LM: 0.1642 | LB: 1.0059 | CL0: 3.3 | CL1: 3.8 | HR0: 0.307/SR0: 0.281 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:02:31] Epoch 3 | Step 9620 | Loss: 0.6659 | LM: 0.1653 | LB: 1.0058 | CL0: 3.3 | CL1: 3.8 | HR0: 0.307/SR0: 0.281 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:02:42] Epoch 3 | Step 9630 | Loss: 0.6663 | LM: 0.1651 | LB: 1.0058 | CL0: 3.3 | CL1: 3.8 | HR0: 0.307/SR0: 0.281 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:02:54] Epoch 3 | Step 9640 | Loss: 0.6661 | LM: 0.1651 | LB: 1.0058 | CL0: 3.3 | CL1: 3.8 | HR0: 0.307/SR0: 0.281 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:03:06] Epoch 3 | Step 9650 | Loss: 0.6654 | LM: 0.1645 | LB: 1.0057 | CL0: 3.3 | CL1: 3.8 | HR0: 0.307/SR0: 0.281 | HR1: 0.267/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 04:03:18] Epoch 3 | Step 9660 | Loss: 0.6649 | LM: 0.1644 | LB: 1.0057 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.281 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:03:30] Epoch 3 | Step 9670 | Loss: 0.6649 | LM: 0.1641 | LB: 1.0057 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.281 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:03:42] Epoch 3 | Step 9680 | Loss: 0.6648 | LM: 0.1643 | LB: 1.0056 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.281 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:03:54] Epoch 3 | Step 9690 | Loss: 0.6646 | LM: 0.1635 | LB: 1.0055 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:04:06] Epoch 3 | Step 9700 | Loss: 0.6656 | LM: 0.1642 | LB: 1.0056 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.281 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:04:18] Epoch 3 | Step 9710 | Loss: 0.6655 | LM: 0.1639 | LB: 1.0055 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:04:28] Epoch 3 | Step 9720 | Loss: 0.6657 | LM: 0.1630 | LB: 1.0054 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:04:39] Epoch 3 | Step 9730 | Loss: 0.6659 | LM: 0.1638 | LB: 1.0054 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:04:51] Epoch 3 | Step 9740 | Loss: 0.6655 | LM: 0.1641 | LB: 1.0054 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:05:02] Epoch 3 | Step 9750 | Loss: 0.6655 | LM: 0.1634 | LB: 1.0054 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:05:13] Epoch 3 | Step 9760 | Loss: 0.6657 | LM: 0.1637 | LB: 1.0054 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.280 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:05:24] Epoch 3 | Step 9770 | Loss: 0.6661 | LM: 0.1645 | LB: 1.0054 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:05:35] Epoch 3 | Step 9780 | Loss: 0.6665 | LM: 0.1647 | LB: 1.0054 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:05:46] Epoch 3 | Step 9790 | Loss: 0.6660 | LM: 0.1653 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:05:57] Epoch 3 | Step 9800 | Loss: 0.6658 | LM: 0.1651 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:06:08] Epoch 3 | Step 9810 | Loss: 0.6656 | LM: 0.1647 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:06:20] Epoch 3 | Step 9820 | Loss: 0.6654 | LM: 0.1646 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:06:31] Epoch 3 | Step 9830 | Loss: 0.6656 | LM: 0.1651 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:06:41] Epoch 3 | Step 9840 | Loss: 0.6659 | LM: 0.1649 | LB: 1.0054 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:06:53] Epoch 3 | Step 9850 | Loss: 0.6660 | LM: 0.1639 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:07:03] Epoch 3 | Step 9860 | Loss: 0.6663 | LM: 0.1634 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:07:15] Epoch 3 | Step 9870 | Loss: 0.6662 | LM: 0.1628 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:07:26] Epoch 3 | Step 9880 | Loss: 0.6662 | LM: 0.1638 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:07:37] Epoch 3 | Step 9890 | Loss: 0.6660 | LM: 0.1635 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:07:48] Epoch 3 | Step 9900 | Loss: 0.6656 | LM: 0.1633 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:07:59] Epoch 3 | Step 9910 | Loss: 0.6659 | LM: 0.1640 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:08:11] Epoch 3 | Step 9920 | Loss: 0.6657 | LM: 0.1639 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:08:22] Epoch 3 | Step 9930 | Loss: 0.6653 | LM: 0.1630 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:08:32] Epoch 3 | Step 9940 | Loss: 0.6655 | LM: 0.1632 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:08:43] Epoch 3 | Step 9950 | Loss: 0.6659 | LM: 0.1641 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:08:54] Epoch 3 | Step 9960 | Loss: 0.6658 | LM: 0.1641 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:09:05] Epoch 3 | Step 9970 | Loss: 0.6658 | LM: 0.1635 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:09:16] Epoch 3 | Step 9980 | Loss: 0.6654 | LM: 0.1632 | LB: 1.0054 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:09:28] Epoch 3 | Step 9990 | Loss: 0.6656 | LM: 0.1635 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:09:38] Epoch 3 | Step 10000 | Loss: 0.6655 | LM: 0.1632 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:09:40] Validation | Batch 10/1463 | Loss: 0.8390 | LM_LOSS: 0.3378 | LB_LOSS: 1.0022 |
| [2026-05-24 04:09:42] Validation | Batch 20/1463 | Loss: 0.8477 | LM_LOSS: 0.3462 | LB_LOSS: 1.0031 |
| [2026-05-24 04:09:44] Validation | Batch 30/1463 | Loss: 0.8479 | LM_LOSS: 0.3461 | LB_LOSS: 1.0035 |
| [2026-05-24 04:09:46] Validation | Batch 40/1463 | Loss: 0.8552 | LM_LOSS: 0.3533 | LB_LOSS: 1.0039 |
| [2026-05-24 04:09:48] Validation | Batch 50/1463 | Loss: 0.8648 | LM_LOSS: 0.3630 | LB_LOSS: 1.0037 |
| [2026-05-24 04:09:51] Validation | Batch 60/1463 | Loss: 0.8644 | LM_LOSS: 0.3626 | LB_LOSS: 1.0036 |
| [2026-05-24 04:09:53] Validation | Batch 70/1463 | Loss: 0.8632 | LM_LOSS: 0.3614 | LB_LOSS: 1.0036 |
| [2026-05-24 04:09:56] Validation | Batch 80/1463 | Loss: 0.8654 | LM_LOSS: 0.3636 | LB_LOSS: 1.0036 |
| [2026-05-24 04:09:58] Validation | Batch 90/1463 | Loss: 0.8646 | LM_LOSS: 0.3628 | LB_LOSS: 1.0035 |
| [2026-05-24 04:10:00] Validation | Batch 100/1463 | Loss: 0.8649 | LM_LOSS: 0.3631 | LB_LOSS: 1.0035 |
| [2026-05-24 04:10:02] Validation | Batch 110/1463 | Loss: 0.8624 | LM_LOSS: 0.3605 | LB_LOSS: 1.0037 |
| [2026-05-24 04:10:04] Validation | Batch 120/1463 | Loss: 0.8644 | LM_LOSS: 0.3625 | LB_LOSS: 1.0038 |
| [2026-05-24 04:10:05] Validation | Batch 130/1463 | Loss: 0.8663 | LM_LOSS: 0.3644 | LB_LOSS: 1.0038 |
| [2026-05-24 04:10:08] Validation | Batch 140/1463 | Loss: 0.8672 | LM_LOSS: 0.3654 | LB_LOSS: 1.0037 |
| [2026-05-24 04:10:10] Validation | Batch 150/1463 | Loss: 0.8653 | LM_LOSS: 0.3634 | LB_LOSS: 1.0039 |
| [2026-05-24 04:10:12] Validation | Batch 160/1463 | Loss: 0.8655 | LM_LOSS: 0.3636 | LB_LOSS: 1.0038 |
| [2026-05-24 04:10:14] Validation | Batch 170/1463 | Loss: 0.8642 | LM_LOSS: 0.3622 | LB_LOSS: 1.0039 |
| [2026-05-24 04:10:17] Validation | Batch 180/1463 | Loss: 0.8647 | LM_LOSS: 0.3628 | LB_LOSS: 1.0038 |
| [2026-05-24 04:10:19] Validation | Batch 190/1463 | Loss: 0.8663 | LM_LOSS: 0.3644 | LB_LOSS: 1.0039 |
| [2026-05-24 04:10:21] Validation | Batch 200/1463 | Loss: 0.8661 | LM_LOSS: 0.3642 | LB_LOSS: 1.0038 |
| [2026-05-24 04:10:23] Validation | Batch 210/1463 | Loss: 0.8666 | LM_LOSS: 0.3647 | LB_LOSS: 1.0038 |
| [2026-05-24 04:10:25] Validation | Batch 220/1463 | Loss: 0.8658 | LM_LOSS: 0.3639 | LB_LOSS: 1.0038 |
| [2026-05-24 04:10:28] Validation | Batch 230/1463 | Loss: 0.8672 | LM_LOSS: 0.3653 | LB_LOSS: 1.0038 |
| [2026-05-24 04:10:30] Validation | Batch 240/1463 | Loss: 0.8688 | LM_LOSS: 0.3669 | LB_LOSS: 1.0038 |
| [2026-05-24 04:10:32] Validation | Batch 250/1463 | Loss: 0.8680 | LM_LOSS: 0.3661 | LB_LOSS: 1.0038 |
| [2026-05-24 04:10:34] Validation | Batch 260/1463 | Loss: 0.8699 | LM_LOSS: 0.3680 | LB_LOSS: 1.0039 |
| [2026-05-24 04:10:36] Validation | Batch 270/1463 | Loss: 0.8680 | LM_LOSS: 0.3660 | LB_LOSS: 1.0039 |
| [2026-05-24 04:10:39] Validation | Batch 280/1463 | Loss: 0.8685 | LM_LOSS: 0.3665 | LB_LOSS: 1.0039 |
| [2026-05-24 04:10:41] Validation | Batch 290/1463 | Loss: 0.8672 | LM_LOSS: 0.3653 | LB_LOSS: 1.0039 |
| [2026-05-24 04:10:43] Validation | Batch 300/1463 | Loss: 0.8679 | LM_LOSS: 0.3659 | LB_LOSS: 1.0040 |
| [2026-05-24 04:10:45] Validation | Batch 310/1463 | Loss: 0.8688 | LM_LOSS: 0.3668 | LB_LOSS: 1.0040 |
| [2026-05-24 04:10:47] Validation | Batch 320/1463 | Loss: 0.8675 | LM_LOSS: 0.3656 | LB_LOSS: 1.0039 |
| [2026-05-24 04:10:49] Validation | Batch 330/1463 | Loss: 0.8673 | LM_LOSS: 0.3653 | LB_LOSS: 1.0039 |
| [2026-05-24 04:10:51] Validation | Batch 340/1463 | Loss: 0.8670 | LM_LOSS: 0.3650 | LB_LOSS: 1.0039 |
| [2026-05-24 04:10:53] Validation | Batch 350/1463 | Loss: 0.8676 | LM_LOSS: 0.3657 | LB_LOSS: 1.0039 |
| [2026-05-24 04:10:55] Validation | Batch 360/1463 | Loss: 0.8676 | LM_LOSS: 0.3656 | LB_LOSS: 1.0039 |
| [2026-05-24 04:10:57] Validation | Batch 370/1463 | Loss: 0.8671 | LM_LOSS: 0.3652 | LB_LOSS: 1.0039 |
| [2026-05-24 04:10:59] Validation | Batch 380/1463 | Loss: 0.8666 | LM_LOSS: 0.3647 | LB_LOSS: 1.0038 |
| [2026-05-24 04:11:01] Validation | Batch 390/1463 | Loss: 0.8672 | LM_LOSS: 0.3653 | LB_LOSS: 1.0039 |
| [2026-05-24 04:11:03] Validation | Batch 400/1463 | Loss: 0.8672 | LM_LOSS: 0.3652 | LB_LOSS: 1.0039 |
| [2026-05-24 04:11:05] Validation | Batch 410/1463 | Loss: 0.8667 | LM_LOSS: 0.3647 | LB_LOSS: 1.0039 |
| [2026-05-24 04:11:07] Validation | Batch 420/1463 | Loss: 0.8667 | LM_LOSS: 0.3647 | LB_LOSS: 1.0039 |
| [2026-05-24 04:11:10] Validation | Batch 430/1463 | Loss: 0.8661 | LM_LOSS: 0.3642 | LB_LOSS: 1.0039 |
| [2026-05-24 04:11:12] Validation | Batch 440/1463 | Loss: 0.8666 | LM_LOSS: 0.3646 | LB_LOSS: 1.0039 |
| [2026-05-24 04:11:13] Validation | Batch 450/1463 | Loss: 0.8662 | LM_LOSS: 0.3642 | LB_LOSS: 1.0040 |
| [2026-05-24 04:11:16] Validation | Batch 460/1463 | Loss: 0.8660 | LM_LOSS: 0.3640 | LB_LOSS: 1.0039 |
| [2026-05-24 04:11:18] Validation | Batch 470/1463 | Loss: 0.8666 | LM_LOSS: 0.3647 | LB_LOSS: 1.0039 |
| [2026-05-24 04:11:20] Validation | Batch 480/1463 | Loss: 0.8664 | LM_LOSS: 0.3644 | LB_LOSS: 1.0039 |
| [2026-05-24 04:11:23] Validation | Batch 490/1463 | Loss: 0.8660 | LM_LOSS: 0.3641 | LB_LOSS: 1.0039 |
| [2026-05-24 04:11:25] Validation | Batch 500/1463 | Loss: 0.8659 | LM_LOSS: 0.3639 | LB_LOSS: 1.0039 |
| [2026-05-24 04:11:27] Validation | Batch 510/1463 | Loss: 0.8651 | LM_LOSS: 0.3631 | LB_LOSS: 1.0039 |
| [2026-05-24 04:11:29] Validation | Batch 520/1463 | Loss: 0.8648 | LM_LOSS: 0.3628 | LB_LOSS: 1.0039 |
| [2026-05-24 04:11:31] Validation | Batch 530/1463 | Loss: 0.8655 | LM_LOSS: 0.3635 | LB_LOSS: 1.0039 |
| [2026-05-24 04:11:33] Validation | Batch 540/1463 | Loss: 0.8657 | LM_LOSS: 0.3638 | LB_LOSS: 1.0039 |
| [2026-05-24 04:11:35] Validation | Batch 550/1463 | Loss: 0.8652 | LM_LOSS: 0.3632 | LB_LOSS: 1.0039 |
| [2026-05-24 04:11:37] Validation | Batch 560/1463 | Loss: 0.8652 | LM_LOSS: 0.3632 | LB_LOSS: 1.0040 |
| [2026-05-24 04:11:39] Validation | Batch 570/1463 | Loss: 0.8650 | LM_LOSS: 0.3630 | LB_LOSS: 1.0039 |
| [2026-05-24 04:11:41] Validation | Batch 580/1463 | Loss: 0.8646 | LM_LOSS: 0.3626 | LB_LOSS: 1.0039 |
| [2026-05-24 04:11:44] Validation | Batch 590/1463 | Loss: 0.8644 | LM_LOSS: 0.3624 | LB_LOSS: 1.0040 |
| [2026-05-24 04:11:46] Validation | Batch 600/1463 | Loss: 0.8646 | LM_LOSS: 0.3626 | LB_LOSS: 1.0040 |
| [2026-05-24 04:11:49] Validation | Batch 610/1463 | Loss: 0.8648 | LM_LOSS: 0.3628 | LB_LOSS: 1.0040 |
| [2026-05-24 04:11:51] Validation | Batch 620/1463 | Loss: 0.8641 | LM_LOSS: 0.3621 | LB_LOSS: 1.0040 |
| [2026-05-24 04:11:53] Validation | Batch 630/1463 | Loss: 0.8636 | LM_LOSS: 0.3616 | LB_LOSS: 1.0040 |
| [2026-05-24 04:11:55] Validation | Batch 640/1463 | Loss: 0.8634 | LM_LOSS: 0.3614 | LB_LOSS: 1.0040 |
| [2026-05-24 04:11:57] Validation | Batch 650/1463 | Loss: 0.8629 | LM_LOSS: 0.3609 | LB_LOSS: 1.0040 |
| [2026-05-24 04:11:59] Validation | Batch 660/1463 | Loss: 0.8623 | LM_LOSS: 0.3603 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:01] Validation | Batch 670/1463 | Loss: 0.8617 | LM_LOSS: 0.3597 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:02] Validation | Batch 680/1463 | Loss: 0.8617 | LM_LOSS: 0.3597 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:05] Validation | Batch 690/1463 | Loss: 0.8620 | LM_LOSS: 0.3600 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:07] Validation | Batch 700/1463 | Loss: 0.8618 | LM_LOSS: 0.3599 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:09] Validation | Batch 710/1463 | Loss: 0.8622 | LM_LOSS: 0.3603 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:11] Validation | Batch 720/1463 | Loss: 0.8630 | LM_LOSS: 0.3610 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:13] Validation | Batch 730/1463 | Loss: 0.8629 | LM_LOSS: 0.3609 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:14] Validation | Batch 740/1463 | Loss: 0.8625 | LM_LOSS: 0.3605 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:16] Validation | Batch 750/1463 | Loss: 0.8624 | LM_LOSS: 0.3604 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:18] Validation | Batch 760/1463 | Loss: 0.8622 | LM_LOSS: 0.3602 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:20] Validation | Batch 770/1463 | Loss: 0.8621 | LM_LOSS: 0.3601 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:22] Validation | Batch 780/1463 | Loss: 0.8620 | LM_LOSS: 0.3600 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:23] Validation | Batch 790/1463 | Loss: 0.8623 | LM_LOSS: 0.3603 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:25] Validation | Batch 800/1463 | Loss: 0.8623 | LM_LOSS: 0.3603 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:27] Validation | Batch 810/1463 | Loss: 0.8619 | LM_LOSS: 0.3599 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:29] Validation | Batch 820/1463 | Loss: 0.8621 | LM_LOSS: 0.3601 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:31] Validation | Batch 830/1463 | Loss: 0.8624 | LM_LOSS: 0.3605 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:34] Validation | Batch 840/1463 | Loss: 0.8624 | LM_LOSS: 0.3604 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:36] Validation | Batch 850/1463 | Loss: 0.8628 | LM_LOSS: 0.3608 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:38] Validation | Batch 860/1463 | Loss: 0.8630 | LM_LOSS: 0.3610 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:40] Validation | Batch 870/1463 | Loss: 0.8631 | LM_LOSS: 0.3611 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:42] Validation | Batch 880/1463 | Loss: 0.8623 | LM_LOSS: 0.3603 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:44] Validation | Batch 890/1463 | Loss: 0.8624 | LM_LOSS: 0.3604 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:46] Validation | Batch 900/1463 | Loss: 0.8619 | LM_LOSS: 0.3600 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:49] Validation | Batch 910/1463 | Loss: 0.8619 | LM_LOSS: 0.3599 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:51] Validation | Batch 920/1463 | Loss: 0.8622 | LM_LOSS: 0.3602 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:53] Validation | Batch 930/1463 | Loss: 0.8617 | LM_LOSS: 0.3597 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:55] Validation | Batch 940/1463 | Loss: 0.8614 | LM_LOSS: 0.3594 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:57] Validation | Batch 950/1463 | Loss: 0.8617 | LM_LOSS: 0.3597 | LB_LOSS: 1.0040 |
| [2026-05-24 04:12:59] Validation | Batch 960/1463 | Loss: 0.8618 | LM_LOSS: 0.3598 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:02] Validation | Batch 970/1463 | Loss: 0.8619 | LM_LOSS: 0.3599 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:04] Validation | Batch 980/1463 | Loss: 0.8623 | LM_LOSS: 0.3603 | LB_LOSS: 1.0039 |
| [2026-05-24 04:13:06] Validation | Batch 990/1463 | Loss: 0.8625 | LM_LOSS: 0.3605 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:08] Validation | Batch 1000/1463 | Loss: 0.8631 | LM_LOSS: 0.3611 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:10] Validation | Batch 1010/1463 | Loss: 0.8631 | LM_LOSS: 0.3612 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:13] Validation | Batch 1020/1463 | Loss: 0.8632 | LM_LOSS: 0.3612 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:15] Validation | Batch 1030/1463 | Loss: 0.8638 | LM_LOSS: 0.3618 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:17] Validation | Batch 1040/1463 | Loss: 0.8634 | LM_LOSS: 0.3614 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:19] Validation | Batch 1050/1463 | Loss: 0.8633 | LM_LOSS: 0.3613 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:22] Validation | Batch 1060/1463 | Loss: 0.8632 | LM_LOSS: 0.3612 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:24] Validation | Batch 1070/1463 | Loss: 0.8631 | LM_LOSS: 0.3612 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:26] Validation | Batch 1080/1463 | Loss: 0.8629 | LM_LOSS: 0.3609 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:28] Validation | Batch 1090/1463 | Loss: 0.8629 | LM_LOSS: 0.3609 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:29] Validation | Batch 1100/1463 | Loss: 0.8627 | LM_LOSS: 0.3607 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:31] Validation | Batch 1110/1463 | Loss: 0.8627 | LM_LOSS: 0.3608 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:34] Validation | Batch 1120/1463 | Loss: 0.8625 | LM_LOSS: 0.3605 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:36] Validation | Batch 1130/1463 | Loss: 0.8622 | LM_LOSS: 0.3602 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:38] Validation | Batch 1140/1463 | Loss: 0.8625 | LM_LOSS: 0.3605 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:41] Validation | Batch 1150/1463 | Loss: 0.8625 | LM_LOSS: 0.3605 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:43] Validation | Batch 1160/1463 | Loss: 0.8624 | LM_LOSS: 0.3604 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:45] Validation | Batch 1170/1463 | Loss: 0.8624 | LM_LOSS: 0.3604 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:47] Validation | Batch 1180/1463 | Loss: 0.8625 | LM_LOSS: 0.3605 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:49] Validation | Batch 1190/1463 | Loss: 0.8627 | LM_LOSS: 0.3607 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:51] Validation | Batch 1200/1463 | Loss: 0.8627 | LM_LOSS: 0.3607 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:53] Validation | Batch 1210/1463 | Loss: 0.8630 | LM_LOSS: 0.3610 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:55] Validation | Batch 1220/1463 | Loss: 0.8635 | LM_LOSS: 0.3615 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:57] Validation | Batch 1230/1463 | Loss: 0.8634 | LM_LOSS: 0.3614 | LB_LOSS: 1.0040 |
| [2026-05-24 04:13:59] Validation | Batch 1240/1463 | Loss: 0.8637 | LM_LOSS: 0.3617 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:02] Validation | Batch 1250/1463 | Loss: 0.8639 | LM_LOSS: 0.3619 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:04] Validation | Batch 1260/1463 | Loss: 0.8637 | LM_LOSS: 0.3617 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:06] Validation | Batch 1270/1463 | Loss: 0.8635 | LM_LOSS: 0.3615 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:09] Validation | Batch 1280/1463 | Loss: 0.8632 | LM_LOSS: 0.3612 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:11] Validation | Batch 1290/1463 | Loss: 0.8632 | LM_LOSS: 0.3613 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:13] Validation | Batch 1300/1463 | Loss: 0.8630 | LM_LOSS: 0.3610 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:15] Validation | Batch 1310/1463 | Loss: 0.8629 | LM_LOSS: 0.3609 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:16] Validation | Batch 1320/1463 | Loss: 0.8629 | LM_LOSS: 0.3609 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:18] Validation | Batch 1330/1463 | Loss: 0.8629 | LM_LOSS: 0.3610 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:20] Validation | Batch 1340/1463 | Loss: 0.8633 | LM_LOSS: 0.3613 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:22] Validation | Batch 1350/1463 | Loss: 0.8633 | LM_LOSS: 0.3613 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:25] Validation | Batch 1360/1463 | Loss: 0.8636 | LM_LOSS: 0.3616 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:27] Validation | Batch 1370/1463 | Loss: 0.8640 | LM_LOSS: 0.3620 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:29] Validation | Batch 1380/1463 | Loss: 0.8637 | LM_LOSS: 0.3617 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:31] Validation | Batch 1390/1463 | Loss: 0.8636 | LM_LOSS: 0.3616 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:33] Validation | Batch 1400/1463 | Loss: 0.8639 | LM_LOSS: 0.3619 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:35] Validation | Batch 1410/1463 | Loss: 0.8642 | LM_LOSS: 0.3622 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:37] Validation | Batch 1420/1463 | Loss: 0.8642 | LM_LOSS: 0.3622 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:40] Validation | Batch 1430/1463 | Loss: 0.8642 | LM_LOSS: 0.3622 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:42] Validation | Batch 1440/1463 | Loss: 0.8646 | LM_LOSS: 0.3626 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:44] Validation | Batch 1450/1463 | Loss: 0.8643 | LM_LOSS: 0.3624 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:46] Validation | Batch 1460/1463 | Loss: 0.8647 | LM_LOSS: 0.3627 | LB_LOSS: 1.0040 |
| [2026-05-24 04:14:47] Validation | Batch 1463/1463 | Loss: 0.8646 | LM_LOSS: 0.3626 | LB_LOSS: 1.0039 |
| [2026-05-24 04:14:47] Validation | Loss: 0.8646 | LM_LOSS: 0.3626 | LB_LOSS: 1.0039 | PPL: 1.44 | Time: 308.57s |
| [2026-05-24 04:14:58] Epoch 3 | Step 10010 | Loss: 0.6652 | LM: 0.1632 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:15:09] Epoch 3 | Step 10020 | Loss: 0.6650 | LM: 0.1632 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:15:20] Epoch 3 | Step 10030 | Loss: 0.6647 | LM: 0.1627 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:15:31] Epoch 3 | Step 10040 | Loss: 0.6647 | LM: 0.1626 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:15:42] Epoch 3 | Step 10050 | Loss: 0.6644 | LM: 0.1625 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:15:53] Epoch 3 | Step 10060 | Loss: 0.6646 | LM: 0.1628 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:16:04] Epoch 3 | Step 10070 | Loss: 0.6648 | LM: 0.1631 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:16:15] Epoch 3 | Step 10080 | Loss: 0.6653 | LM: 0.1639 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:16:26] Epoch 3 | Step 10090 | Loss: 0.6656 | LM: 0.1640 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:16:37] Epoch 3 | Step 10100 | Loss: 0.6655 | LM: 0.1638 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:16:48] Epoch 3 | Step 10110 | Loss: 0.6657 | LM: 0.1637 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:16:59] Epoch 3 | Step 10120 | Loss: 0.6660 | LM: 0.1638 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:17:10] Epoch 3 | Step 10130 | Loss: 0.6664 | LM: 0.1642 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:17:22] Epoch 3 | Step 10140 | Loss: 0.6661 | LM: 0.1634 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:17:33] Epoch 3 | Step 10150 | Loss: 0.6663 | LM: 0.1632 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:17:45] Epoch 3 | Step 10160 | Loss: 0.6662 | LM: 0.1632 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:17:57] Epoch 3 | Step 10170 | Loss: 0.6663 | LM: 0.1629 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:18:09] Epoch 3 | Step 10180 | Loss: 0.6661 | LM: 0.1630 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:18:21] Epoch 3 | Step 10190 | Loss: 0.6661 | LM: 0.1627 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:18:33] Epoch 3 | Step 10200 | Loss: 0.6659 | LM: 0.1620 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:18:44] Epoch 3 | Step 10210 | Loss: 0.6661 | LM: 0.1619 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:18:56] Epoch 3 | Step 10220 | Loss: 0.6660 | LM: 0.1621 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:19:06] Epoch 3 | Step 10230 | Loss: 0.6662 | LM: 0.1622 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:19:17] Epoch 3 | Step 10240 | Loss: 0.6665 | LM: 0.1625 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:19:28] Epoch 3 | Step 10250 | Loss: 0.6664 | LM: 0.1624 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:19:39] Epoch 3 | Step 10260 | Loss: 0.6664 | LM: 0.1621 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:19:50] Epoch 3 | Step 10270 | Loss: 0.6662 | LM: 0.1621 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:20:02] Epoch 3 | Step 10280 | Loss: 0.6663 | LM: 0.1620 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:20:13] Epoch 3 | Step 10290 | Loss: 0.6665 | LM: 0.1625 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:20:25] Epoch 3 | Step 10300 | Loss: 0.6665 | LM: 0.1626 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.265/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:20:36] Epoch 3 | Step 10310 | Loss: 0.6662 | LM: 0.1623 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.265/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:20:48] Epoch 3 | Step 10320 | Loss: 0.6662 | LM: 0.1627 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.265/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:20:59] Epoch 3 | Step 10330 | Loss: 0.6661 | LM: 0.1626 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.265/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:21:10] Epoch 3 | Step 10340 | Loss: 0.6662 | LM: 0.1627 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:21:21] Epoch 3 | Step 10350 | Loss: 0.6661 | LM: 0.1628 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:21:31] Epoch 3 | Step 10360 | Loss: 0.6660 | LM: 0.1628 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:21:42] Epoch 3 | Step 10370 | Loss: 0.6662 | LM: 0.1627 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.265/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:21:53] Epoch 3 | Step 10380 | Loss: 0.6660 | LM: 0.1623 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.265/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:22:04] Epoch 3 | Step 10390 | Loss: 0.6662 | LM: 0.1623 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.265/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:22:15] Epoch 3 | Step 10400 | Loss: 0.6663 | LM: 0.1630 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.265/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:22:26] Epoch 3 | Step 10410 | Loss: 0.6662 | LM: 0.1631 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.265/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:22:37] Epoch 3 | Step 10420 | Loss: 0.6664 | LM: 0.1637 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.265/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:22:49] Epoch 3 | Step 10430 | Loss: 0.6661 | LM: 0.1636 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.265/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:23:01] Epoch 3 | Step 10440 | Loss: 0.6657 | LM: 0.1633 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.265/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:23:12] Epoch 3 | Step 10450 | Loss: 0.6657 | LM: 0.1632 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.265/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:23:24] Epoch 3 | Step 10460 | Loss: 0.6658 | LM: 0.1633 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.265/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:23:36] Epoch 3 | Step 10470 | Loss: 0.6658 | LM: 0.1632 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.265/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:23:48] Epoch 3 | Step 10480 | Loss: 0.6657 | LM: 0.1629 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:23:59] Epoch 3 | Step 10490 | Loss: 0.6657 | LM: 0.1629 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.265/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:24:11] Epoch 3 | Step 10500 | Loss: 0.6656 | LM: 0.1626 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:24:23] Epoch 3 | Step 10510 | Loss: 0.6655 | LM: 0.1626 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:24:35] Epoch 3 | Step 10520 | Loss: 0.6657 | LM: 0.1628 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:24:47] Epoch 3 | Step 10530 | Loss: 0.6659 | LM: 0.1632 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:24:58] Epoch 3 | Step 10540 | Loss: 0.6658 | LM: 0.1632 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:25:09] Epoch 3 | Step 10550 | Loss: 0.6659 | LM: 0.1635 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:25:20] Epoch 3 | Step 10560 | Loss: 0.6659 | LM: 0.1636 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:25:31] Epoch 3 | Step 10570 | Loss: 0.6660 | LM: 0.1637 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:25:42] Epoch 3 | Step 10580 | Loss: 0.6661 | LM: 0.1637 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:25:53] Epoch 3 | Step 10590 | Loss: 0.6662 | LM: 0.1638 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:26:04] Epoch 3 | Step 10600 | Loss: 0.6661 | LM: 0.1637 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:26:16] Epoch 3 | Step 10610 | Loss: 0.6660 | LM: 0.1637 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:26:27] Epoch 3 | Step 10620 | Loss: 0.6661 | LM: 0.1637 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:26:38] Epoch 3 | Step 10630 | Loss: 0.6662 | LM: 0.1641 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:26:49] Epoch 3 | Step 10640 | Loss: 0.6663 | LM: 0.1647 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:27:00] Epoch 3 | Step 10650 | Loss: 0.6664 | LM: 0.1647 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:27:11] Epoch 3 | Step 10660 | Loss: 0.6663 | LM: 0.1649 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:27:22] Epoch 3 | Step 10670 | Loss: 0.6663 | LM: 0.1650 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:27:34] Epoch 3 | Step 10680 | Loss: 0.6663 | LM: 0.1649 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:27:45] Epoch 3 | Step 10690 | Loss: 0.6663 | LM: 0.1652 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:27:56] Epoch 3 | Step 10700 | Loss: 0.6666 | LM: 0.1656 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:28:07] Epoch 3 | Step 10710 | Loss: 0.6666 | LM: 0.1656 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:28:18] Epoch 3 | Step 10720 | Loss: 0.6666 | LM: 0.1655 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:28:29] Epoch 3 | Step 10730 | Loss: 0.6667 | LM: 0.1655 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:28:40] Epoch 3 | Step 10740 | Loss: 0.6666 | LM: 0.1654 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:28:51] Epoch 3 | Step 10750 | Loss: 0.6666 | LM: 0.1654 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:29:01] Epoch 3 | Step 10760 | Loss: 0.6666 | LM: 0.1653 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:29:13] Epoch 3 | Step 10770 | Loss: 0.6668 | LM: 0.1661 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:29:24] Epoch 3 | Step 10780 | Loss: 0.6667 | LM: 0.1658 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:29:36] Epoch 3 | Step 10790 | Loss: 0.6666 | LM: 0.1657 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:29:47] Epoch 3 | Step 10800 | Loss: 0.6667 | LM: 0.1656 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:29:58] Epoch 3 | Step 10810 | Loss: 0.6666 | LM: 0.1655 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:30:09] Epoch 3 | Step 10820 | Loss: 0.6668 | LM: 0.1654 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:30:21] Epoch 3 | Step 10830 | Loss: 0.6668 | LM: 0.1653 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:30:32] Epoch 3 | Step 10840 | Loss: 0.6667 | LM: 0.1653 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:30:43] Epoch 3 | Step 10850 | Loss: 0.6666 | LM: 0.1652 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:30:55] Epoch 3 | Step 10860 | Loss: 0.6667 | LM: 0.1651 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:31:07] Epoch 3 | Step 10870 | Loss: 0.6667 | LM: 0.1650 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:31:18] Epoch 3 | Step 10880 | Loss: 0.6668 | LM: 0.1649 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:31:29] Epoch 3 | Step 10890 | Loss: 0.6666 | LM: 0.1647 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:31:40] Epoch 3 | Step 10900 | Loss: 0.6666 | LM: 0.1647 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:31:52] Epoch 3 | Step 10910 | Loss: 0.6667 | LM: 0.1646 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:32:03] Epoch 3 | Step 10920 | Loss: 0.6666 | LM: 0.1648 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:32:14] Epoch 3 | Step 10930 | Loss: 0.6666 | LM: 0.1649 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:32:26] Epoch 3 | Step 10940 | Loss: 0.6668 | LM: 0.1650 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:32:37] Epoch 3 | Step 10950 | Loss: 0.6669 | LM: 0.1651 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:32:47] Epoch 3 | Step 10960 | Loss: 0.6670 | LM: 0.1653 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:32:58] Epoch 3 | Step 10970 | Loss: 0.6670 | LM: 0.1652 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:33:09] Epoch 3 | Step 10980 | Loss: 0.6670 | LM: 0.1650 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:33:21] Epoch 3 | Step 10990 | Loss: 0.6670 | LM: 0.1652 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:33:32] Epoch 3 | Step 11000 | Loss: 0.6670 | LM: 0.1650 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:33:33] Validation | Batch 10/1463 | Loss: 0.8401 | LM_LOSS: 0.3392 | LB_LOSS: 1.0019 |
| [2026-05-24 04:33:35] Validation | Batch 20/1463 | Loss: 0.8486 | LM_LOSS: 0.3472 | LB_LOSS: 1.0028 |
| [2026-05-24 04:33:38] Validation | Batch 30/1463 | Loss: 0.8482 | LM_LOSS: 0.3467 | LB_LOSS: 1.0031 |
| [2026-05-24 04:33:39] Validation | Batch 40/1463 | Loss: 0.8554 | LM_LOSS: 0.3536 | LB_LOSS: 1.0035 |
| [2026-05-24 04:33:41] Validation | Batch 50/1463 | Loss: 0.8642 | LM_LOSS: 0.3625 | LB_LOSS: 1.0033 |
| [2026-05-24 04:33:44] Validation | Batch 60/1463 | Loss: 0.8629 | LM_LOSS: 0.3613 | LB_LOSS: 1.0032 |
| [2026-05-24 04:33:47] Validation | Batch 70/1463 | Loss: 0.8627 | LM_LOSS: 0.3611 | LB_LOSS: 1.0032 |
| [2026-05-24 04:33:49] Validation | Batch 80/1463 | Loss: 0.8648 | LM_LOSS: 0.3632 | LB_LOSS: 1.0032 |
| [2026-05-24 04:33:51] Validation | Batch 90/1463 | Loss: 0.8644 | LM_LOSS: 0.3628 | LB_LOSS: 1.0032 |
| [2026-05-24 04:33:53] Validation | Batch 100/1463 | Loss: 0.8645 | LM_LOSS: 0.3629 | LB_LOSS: 1.0032 |
| [2026-05-24 04:33:55] Validation | Batch 110/1463 | Loss: 0.8622 | LM_LOSS: 0.3606 | LB_LOSS: 1.0033 |
| [2026-05-24 04:33:57] Validation | Batch 120/1463 | Loss: 0.8650 | LM_LOSS: 0.3633 | LB_LOSS: 1.0034 |
| [2026-05-24 04:33:59] Validation | Batch 130/1463 | Loss: 0.8671 | LM_LOSS: 0.3654 | LB_LOSS: 1.0034 |
| [2026-05-24 04:34:01] Validation | Batch 140/1463 | Loss: 0.8684 | LM_LOSS: 0.3667 | LB_LOSS: 1.0034 |
| [2026-05-24 04:34:04] Validation | Batch 150/1463 | Loss: 0.8659 | LM_LOSS: 0.3642 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:06] Validation | Batch 160/1463 | Loss: 0.8660 | LM_LOSS: 0.3643 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:08] Validation | Batch 170/1463 | Loss: 0.8647 | LM_LOSS: 0.3629 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:10] Validation | Batch 180/1463 | Loss: 0.8649 | LM_LOSS: 0.3632 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:12] Validation | Batch 190/1463 | Loss: 0.8665 | LM_LOSS: 0.3647 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:14] Validation | Batch 200/1463 | Loss: 0.8664 | LM_LOSS: 0.3647 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:16] Validation | Batch 210/1463 | Loss: 0.8669 | LM_LOSS: 0.3651 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:19] Validation | Batch 220/1463 | Loss: 0.8661 | LM_LOSS: 0.3644 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:21] Validation | Batch 230/1463 | Loss: 0.8676 | LM_LOSS: 0.3659 | LB_LOSS: 1.0034 |
| [2026-05-24 04:34:23] Validation | Batch 240/1463 | Loss: 0.8691 | LM_LOSS: 0.3674 | LB_LOSS: 1.0034 |
| [2026-05-24 04:34:26] Validation | Batch 250/1463 | Loss: 0.8683 | LM_LOSS: 0.3666 | LB_LOSS: 1.0034 |
| [2026-05-24 04:34:28] Validation | Batch 260/1463 | Loss: 0.8704 | LM_LOSS: 0.3686 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:30] Validation | Batch 270/1463 | Loss: 0.8683 | LM_LOSS: 0.3666 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:32] Validation | Batch 280/1463 | Loss: 0.8689 | LM_LOSS: 0.3671 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:34] Validation | Batch 290/1463 | Loss: 0.8677 | LM_LOSS: 0.3659 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:36] Validation | Batch 300/1463 | Loss: 0.8683 | LM_LOSS: 0.3665 | LB_LOSS: 1.0036 |
| [2026-05-24 04:34:38] Validation | Batch 310/1463 | Loss: 0.8692 | LM_LOSS: 0.3674 | LB_LOSS: 1.0036 |
| [2026-05-24 04:34:40] Validation | Batch 320/1463 | Loss: 0.8679 | LM_LOSS: 0.3661 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:42] Validation | Batch 330/1463 | Loss: 0.8677 | LM_LOSS: 0.3659 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:44] Validation | Batch 340/1463 | Loss: 0.8673 | LM_LOSS: 0.3656 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:46] Validation | Batch 350/1463 | Loss: 0.8680 | LM_LOSS: 0.3662 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:48] Validation | Batch 360/1463 | Loss: 0.8676 | LM_LOSS: 0.3659 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:50] Validation | Batch 370/1463 | Loss: 0.8673 | LM_LOSS: 0.3656 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:52] Validation | Batch 380/1463 | Loss: 0.8668 | LM_LOSS: 0.3651 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:54] Validation | Batch 390/1463 | Loss: 0.8675 | LM_LOSS: 0.3657 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:56] Validation | Batch 400/1463 | Loss: 0.8674 | LM_LOSS: 0.3656 | LB_LOSS: 1.0035 |
| [2026-05-24 04:34:58] Validation | Batch 410/1463 | Loss: 0.8667 | LM_LOSS: 0.3649 | LB_LOSS: 1.0035 |
| [2026-05-24 04:35:01] Validation | Batch 420/1463 | Loss: 0.8667 | LM_LOSS: 0.3650 | LB_LOSS: 1.0035 |
| [2026-05-24 04:35:03] Validation | Batch 430/1463 | Loss: 0.8661 | LM_LOSS: 0.3643 | LB_LOSS: 1.0036 |
| [2026-05-24 04:35:05] Validation | Batch 440/1463 | Loss: 0.8666 | LM_LOSS: 0.3648 | LB_LOSS: 1.0036 |
| [2026-05-24 04:35:07] Validation | Batch 450/1463 | Loss: 0.8662 | LM_LOSS: 0.3644 | LB_LOSS: 1.0036 |
| [2026-05-24 04:35:09] Validation | Batch 460/1463 | Loss: 0.8659 | LM_LOSS: 0.3641 | LB_LOSS: 1.0036 |
| [2026-05-24 04:35:12] Validation | Batch 470/1463 | Loss: 0.8667 | LM_LOSS: 0.3649 | LB_LOSS: 1.0035 |
| [2026-05-24 04:35:14] Validation | Batch 480/1463 | Loss: 0.8665 | LM_LOSS: 0.3647 | LB_LOSS: 1.0035 |
| [2026-05-24 04:35:16] Validation | Batch 490/1463 | Loss: 0.8662 | LM_LOSS: 0.3644 | LB_LOSS: 1.0035 |
| [2026-05-24 04:35:19] Validation | Batch 500/1463 | Loss: 0.8661 | LM_LOSS: 0.3643 | LB_LOSS: 1.0035 |
| [2026-05-24 04:35:21] Validation | Batch 510/1463 | Loss: 0.8652 | LM_LOSS: 0.3634 | LB_LOSS: 1.0035 |
| [2026-05-24 04:35:23] Validation | Batch 520/1463 | Loss: 0.8649 | LM_LOSS: 0.3632 | LB_LOSS: 1.0035 |
| [2026-05-24 04:35:25] Validation | Batch 530/1463 | Loss: 0.8656 | LM_LOSS: 0.3638 | LB_LOSS: 1.0035 |
| [2026-05-24 04:35:26] Validation | Batch 540/1463 | Loss: 0.8657 | LM_LOSS: 0.3640 | LB_LOSS: 1.0035 |
| [2026-05-24 04:35:28] Validation | Batch 550/1463 | Loss: 0.8653 | LM_LOSS: 0.3635 | LB_LOSS: 1.0036 |
| [2026-05-24 04:35:30] Validation | Batch 560/1463 | Loss: 0.8654 | LM_LOSS: 0.3636 | LB_LOSS: 1.0036 |
| [2026-05-24 04:35:33] Validation | Batch 570/1463 | Loss: 0.8653 | LM_LOSS: 0.3635 | LB_LOSS: 1.0036 |
| [2026-05-24 04:35:35] Validation | Batch 580/1463 | Loss: 0.8648 | LM_LOSS: 0.3631 | LB_LOSS: 1.0036 |
| [2026-05-24 04:35:37] Validation | Batch 590/1463 | Loss: 0.8646 | LM_LOSS: 0.3628 | LB_LOSS: 1.0036 |
| [2026-05-24 04:35:39] Validation | Batch 600/1463 | Loss: 0.8648 | LM_LOSS: 0.3630 | LB_LOSS: 1.0036 |
| [2026-05-24 04:35:42] Validation | Batch 610/1463 | Loss: 0.8651 | LM_LOSS: 0.3633 | LB_LOSS: 1.0036 |
| [2026-05-24 04:35:44] Validation | Batch 620/1463 | Loss: 0.8644 | LM_LOSS: 0.3626 | LB_LOSS: 1.0036 |
| [2026-05-24 04:35:46] Validation | Batch 630/1463 | Loss: 0.8640 | LM_LOSS: 0.3622 | LB_LOSS: 1.0036 |
| [2026-05-24 04:35:48] Validation | Batch 640/1463 | Loss: 0.8638 | LM_LOSS: 0.3620 | LB_LOSS: 1.0036 |
| [2026-05-24 04:35:50] Validation | Batch 650/1463 | Loss: 0.8634 | LM_LOSS: 0.3615 | LB_LOSS: 1.0036 |
| [2026-05-24 04:35:52] Validation | Batch 660/1463 | Loss: 0.8628 | LM_LOSS: 0.3609 | LB_LOSS: 1.0036 |
| [2026-05-24 04:35:54] Validation | Batch 670/1463 | Loss: 0.8622 | LM_LOSS: 0.3604 | LB_LOSS: 1.0036 |
| [2026-05-24 04:35:56] Validation | Batch 680/1463 | Loss: 0.8621 | LM_LOSS: 0.3604 | LB_LOSS: 1.0036 |
| [2026-05-24 04:35:58] Validation | Batch 690/1463 | Loss: 0.8624 | LM_LOSS: 0.3606 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:00] Validation | Batch 700/1463 | Loss: 0.8623 | LM_LOSS: 0.3605 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:02] Validation | Batch 710/1463 | Loss: 0.8626 | LM_LOSS: 0.3608 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:04] Validation | Batch 720/1463 | Loss: 0.8633 | LM_LOSS: 0.3615 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:06] Validation | Batch 730/1463 | Loss: 0.8633 | LM_LOSS: 0.3615 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:08] Validation | Batch 740/1463 | Loss: 0.8629 | LM_LOSS: 0.3611 | LB_LOSS: 1.0037 |
| [2026-05-24 04:36:10] Validation | Batch 750/1463 | Loss: 0.8629 | LM_LOSS: 0.3611 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:11] Validation | Batch 760/1463 | Loss: 0.8627 | LM_LOSS: 0.3609 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:13] Validation | Batch 770/1463 | Loss: 0.8627 | LM_LOSS: 0.3608 | LB_LOSS: 1.0037 |
| [2026-05-24 04:36:15] Validation | Batch 780/1463 | Loss: 0.8626 | LM_LOSS: 0.3608 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:17] Validation | Batch 790/1463 | Loss: 0.8628 | LM_LOSS: 0.3609 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:19] Validation | Batch 800/1463 | Loss: 0.8628 | LM_LOSS: 0.3610 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:21] Validation | Batch 810/1463 | Loss: 0.8623 | LM_LOSS: 0.3605 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:23] Validation | Batch 820/1463 | Loss: 0.8626 | LM_LOSS: 0.3608 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:25] Validation | Batch 830/1463 | Loss: 0.8629 | LM_LOSS: 0.3611 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:28] Validation | Batch 840/1463 | Loss: 0.8629 | LM_LOSS: 0.3611 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:30] Validation | Batch 850/1463 | Loss: 0.8632 | LM_LOSS: 0.3614 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:32] Validation | Batch 860/1463 | Loss: 0.8635 | LM_LOSS: 0.3617 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:34] Validation | Batch 870/1463 | Loss: 0.8636 | LM_LOSS: 0.3618 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:36] Validation | Batch 880/1463 | Loss: 0.8628 | LM_LOSS: 0.3610 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:38] Validation | Batch 890/1463 | Loss: 0.8629 | LM_LOSS: 0.3611 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:40] Validation | Batch 900/1463 | Loss: 0.8624 | LM_LOSS: 0.3606 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:42] Validation | Batch 910/1463 | Loss: 0.8623 | LM_LOSS: 0.3605 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:45] Validation | Batch 920/1463 | Loss: 0.8626 | LM_LOSS: 0.3608 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:47] Validation | Batch 930/1463 | Loss: 0.8622 | LM_LOSS: 0.3603 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:49] Validation | Batch 940/1463 | Loss: 0.8618 | LM_LOSS: 0.3600 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:51] Validation | Batch 950/1463 | Loss: 0.8621 | LM_LOSS: 0.3603 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:53] Validation | Batch 960/1463 | Loss: 0.8622 | LM_LOSS: 0.3604 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:56] Validation | Batch 970/1463 | Loss: 0.8623 | LM_LOSS: 0.3605 | LB_LOSS: 1.0036 |
| [2026-05-24 04:36:58] Validation | Batch 980/1463 | Loss: 0.8627 | LM_LOSS: 0.3609 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:00] Validation | Batch 990/1463 | Loss: 0.8630 | LM_LOSS: 0.3612 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:02] Validation | Batch 1000/1463 | Loss: 0.8636 | LM_LOSS: 0.3618 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:05] Validation | Batch 1010/1463 | Loss: 0.8637 | LM_LOSS: 0.3619 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:07] Validation | Batch 1020/1463 | Loss: 0.8638 | LM_LOSS: 0.3620 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:09] Validation | Batch 1030/1463 | Loss: 0.8644 | LM_LOSS: 0.3626 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:11] Validation | Batch 1040/1463 | Loss: 0.8639 | LM_LOSS: 0.3621 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:14] Validation | Batch 1050/1463 | Loss: 0.8638 | LM_LOSS: 0.3620 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:16] Validation | Batch 1060/1463 | Loss: 0.8638 | LM_LOSS: 0.3620 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:18] Validation | Batch 1070/1463 | Loss: 0.8637 | LM_LOSS: 0.3619 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:20] Validation | Batch 1080/1463 | Loss: 0.8635 | LM_LOSS: 0.3617 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:22] Validation | Batch 1090/1463 | Loss: 0.8633 | LM_LOSS: 0.3615 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:24] Validation | Batch 1100/1463 | Loss: 0.8631 | LM_LOSS: 0.3613 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:26] Validation | Batch 1110/1463 | Loss: 0.8631 | LM_LOSS: 0.3613 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:28] Validation | Batch 1120/1463 | Loss: 0.8629 | LM_LOSS: 0.3611 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:30] Validation | Batch 1130/1463 | Loss: 0.8626 | LM_LOSS: 0.3608 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:32] Validation | Batch 1140/1463 | Loss: 0.8629 | LM_LOSS: 0.3611 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:35] Validation | Batch 1150/1463 | Loss: 0.8628 | LM_LOSS: 0.3610 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:37] Validation | Batch 1160/1463 | Loss: 0.8627 | LM_LOSS: 0.3609 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:39] Validation | Batch 1170/1463 | Loss: 0.8627 | LM_LOSS: 0.3609 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:41] Validation | Batch 1180/1463 | Loss: 0.8628 | LM_LOSS: 0.3610 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:44] Validation | Batch 1190/1463 | Loss: 0.8629 | LM_LOSS: 0.3611 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:46] Validation | Batch 1200/1463 | Loss: 0.8630 | LM_LOSS: 0.3612 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:48] Validation | Batch 1210/1463 | Loss: 0.8632 | LM_LOSS: 0.3614 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:50] Validation | Batch 1220/1463 | Loss: 0.8636 | LM_LOSS: 0.3618 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:52] Validation | Batch 1230/1463 | Loss: 0.8636 | LM_LOSS: 0.3618 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:54] Validation | Batch 1240/1463 | Loss: 0.8638 | LM_LOSS: 0.3620 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:56] Validation | Batch 1250/1463 | Loss: 0.8640 | LM_LOSS: 0.3622 | LB_LOSS: 1.0036 |
| [2026-05-24 04:37:59] Validation | Batch 1260/1463 | Loss: 0.8639 | LM_LOSS: 0.3621 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:01] Validation | Batch 1270/1463 | Loss: 0.8636 | LM_LOSS: 0.3618 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:03] Validation | Batch 1280/1463 | Loss: 0.8634 | LM_LOSS: 0.3616 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:05] Validation | Batch 1290/1463 | Loss: 0.8633 | LM_LOSS: 0.3615 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:07] Validation | Batch 1300/1463 | Loss: 0.8631 | LM_LOSS: 0.3613 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:10] Validation | Batch 1310/1463 | Loss: 0.8629 | LM_LOSS: 0.3611 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:11] Validation | Batch 1320/1463 | Loss: 0.8630 | LM_LOSS: 0.3612 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:13] Validation | Batch 1330/1463 | Loss: 0.8630 | LM_LOSS: 0.3612 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:15] Validation | Batch 1340/1463 | Loss: 0.8634 | LM_LOSS: 0.3616 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:17] Validation | Batch 1350/1463 | Loss: 0.8634 | LM_LOSS: 0.3616 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:20] Validation | Batch 1360/1463 | Loss: 0.8637 | LM_LOSS: 0.3619 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:22] Validation | Batch 1370/1463 | Loss: 0.8641 | LM_LOSS: 0.3623 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:24] Validation | Batch 1380/1463 | Loss: 0.8638 | LM_LOSS: 0.3620 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:26] Validation | Batch 1390/1463 | Loss: 0.8637 | LM_LOSS: 0.3619 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:28] Validation | Batch 1400/1463 | Loss: 0.8640 | LM_LOSS: 0.3622 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:30] Validation | Batch 1410/1463 | Loss: 0.8643 | LM_LOSS: 0.3625 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:32] Validation | Batch 1420/1463 | Loss: 0.8644 | LM_LOSS: 0.3626 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:35] Validation | Batch 1430/1463 | Loss: 0.8643 | LM_LOSS: 0.3625 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:37] Validation | Batch 1440/1463 | Loss: 0.8647 | LM_LOSS: 0.3629 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:39] Validation | Batch 1450/1463 | Loss: 0.8644 | LM_LOSS: 0.3626 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:41] Validation | Batch 1460/1463 | Loss: 0.8648 | LM_LOSS: 0.3630 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:42] Validation | Batch 1463/1463 | Loss: 0.8647 | LM_LOSS: 0.3629 | LB_LOSS: 1.0036 |
| [2026-05-24 04:38:42] Validation | Loss: 0.8647 | LM_LOSS: 0.3629 | LB_LOSS: 1.0036 | PPL: 1.44 | Time: 310.34s |
| [2026-05-24 04:38:53] Epoch 3 | Step 11010 | Loss: 0.6670 | LM: 0.1650 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:39:05] Epoch 3 | Step 11020 | Loss: 0.6671 | LM: 0.1652 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:39:16] Epoch 3 | Step 11030 | Loss: 0.6671 | LM: 0.1652 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:39:28] Epoch 3 | Step 11040 | Loss: 0.6671 | LM: 0.1655 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:39:39] Epoch 3 | Step 11050 | Loss: 0.6671 | LM: 0.1654 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:39:50] Epoch 3 | Step 11060 | Loss: 0.6672 | LM: 0.1655 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 04:40:02] Epoch 3 | Step 11070 | Loss: 0.6672 | LM: 0.1654 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:40:13] Epoch 3 | Step 11080 | Loss: 0.6673 | LM: 0.1656 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:40:25] Epoch 3 | Step 11090 | Loss: 0.6674 | LM: 0.1657 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:40:37] Epoch 3 | Step 11100 | Loss: 0.6675 | LM: 0.1661 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:40:48] Epoch 3 | Step 11110 | Loss: 0.6675 | LM: 0.1661 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:41:00] Epoch 3 | Step 11120 | Loss: 0.6675 | LM: 0.1662 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:41:11] Epoch 3 | Step 11130 | Loss: 0.6675 | LM: 0.1662 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:41:22] Epoch 3 | Step 11140 | Loss: 0.6676 | LM: 0.1663 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:41:34] Epoch 3 | Step 11150 | Loss: 0.6678 | LM: 0.1665 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:41:45] Epoch 3 | Step 11160 | Loss: 0.6678 | LM: 0.1664 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:41:57] Epoch 3 | Step 11170 | Loss: 0.6679 | LM: 0.1666 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:42:09] Epoch 3 | Step 11180 | Loss: 0.6679 | LM: 0.1666 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:42:20] Epoch 3 | Step 11190 | Loss: 0.6679 | LM: 0.1667 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:42:32] Epoch 3 | Step 11200 | Loss: 0.6679 | LM: 0.1666 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:42:43] Epoch 3 | Step 11210 | Loss: 0.6679 | LM: 0.1665 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:42:55] Epoch 3 | Step 11220 | Loss: 0.6679 | LM: 0.1663 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:43:07] Epoch 3 | Step 11230 | Loss: 0.6678 | LM: 0.1660 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:43:19] Epoch 3 | Step 11240 | Loss: 0.6680 | LM: 0.1660 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:43:31] Epoch 3 | Step 11250 | Loss: 0.6679 | LM: 0.1662 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:43:43] Epoch 3 | Step 11260 | Loss: 0.6680 | LM: 0.1662 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:43:55] Epoch 3 | Step 11270 | Loss: 0.6680 | LM: 0.1661 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.280 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:44:06] Epoch 3 | Step 11280 | Loss: 0.6680 | LM: 0.1661 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:44:17] Epoch 3 | Step 11290 | Loss: 0.6682 | LM: 0.1663 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 04:44:28] Epoch 3 | Step 11300 | Loss: 0.6681 | LM: 0.1663 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.99e-05 |
| [2026-05-24 04:44:40] Epoch 3 | Step 11310 | Loss: 0.6681 | LM: 0.1662 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.99e-05 |
| [2026-05-24 04:44:52] Epoch 3 | Step 11320 | Loss: 0.6680 | LM: 0.1661 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.99e-05 |
| [2026-05-24 04:45:03] Epoch 3 | Step 11330 | Loss: 0.6680 | LM: 0.1664 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.98e-05 |
| [2026-05-24 04:45:15] Epoch 3 | Step 11340 | Loss: 0.6681 | LM: 0.1663 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.98e-05 |
| [2026-05-24 04:45:26] Epoch 3 | Step 11350 | Loss: 0.6680 | LM: 0.1663 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.97e-05 |
| [2026-05-24 04:45:37] Epoch 3 | Step 11360 | Loss: 0.6679 | LM: 0.1662 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.97e-05 |
| [2026-05-24 04:45:48] Epoch 3 | Step 11370 | Loss: 0.6679 | LM: 0.1659 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.96e-05 |
| [2026-05-24 04:45:59] Epoch 3 | Step 11380 | Loss: 0.6679 | LM: 0.1658 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.95e-05 |
| [2026-05-24 04:46:10] Epoch 3 | Step 11390 | Loss: 0.6680 | LM: 0.1661 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.95e-05 |
| [2026-05-24 04:46:21] Epoch 3 | Step 11400 | Loss: 0.6680 | LM: 0.1660 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.94e-05 |
| [2026-05-24 04:46:32] Epoch 3 | Step 11410 | Loss: 0.6682 | LM: 0.1661 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 9.93e-05 |
| [2026-05-24 04:46:43] Epoch 3 | Step 11420 | Loss: 0.6682 | LM: 0.1661 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.92e-05 |
| [2026-05-24 04:46:55] Epoch 3 | Step 11430 | Loss: 0.6682 | LM: 0.1663 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.91e-05 |
| [2026-05-24 04:47:06] Epoch 3 | Step 11440 | Loss: 0.6682 | LM: 0.1665 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.90e-05 |
| [2026-05-24 04:47:18] Epoch 3 | Step 11450 | Loss: 0.6682 | LM: 0.1663 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.89e-05 |
| [2026-05-24 04:47:30] Epoch 3 | Step 11460 | Loss: 0.6683 | LM: 0.1664 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.88e-05 |
| [2026-05-24 04:47:41] Epoch 3 | Step 11470 | Loss: 0.6684 | LM: 0.1665 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.86e-05 |
| [2026-05-24 04:47:53] Epoch 3 | Step 11480 | Loss: 0.6685 | LM: 0.1664 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.85e-05 |
| [2026-05-24 04:48:05] Epoch 3 | Step 11490 | Loss: 0.6685 | LM: 0.1666 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.84e-05 |
| [2026-05-24 04:48:16] Epoch 3 | Step 11500 | Loss: 0.6685 | LM: 0.1667 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.83e-05 |
| [2026-05-24 04:48:27] Epoch 3 | Step 11510 | Loss: 0.6685 | LM: 0.1667 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 9.81e-05 |
| [2026-05-24 04:48:39] Epoch 3 | Step 11520 | Loss: 0.6686 | LM: 0.1667 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 9.80e-05 |
| [2026-05-24 04:48:50] Epoch 3 | Step 11530 | Loss: 0.6688 | LM: 0.1670 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 9.78e-05 |
| [2026-05-24 04:49:02] Epoch 3 | Step 11540 | Loss: 0.6687 | LM: 0.1669 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 9.77e-05 |
| [2026-05-24 04:49:14] Epoch 3 | Step 11550 | Loss: 0.6689 | LM: 0.1670 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 9.75e-05 |
| [2026-05-24 04:49:25] Epoch 3 | Step 11560 | Loss: 0.6689 | LM: 0.1669 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 9.73e-05 |
| [2026-05-24 04:49:37] Epoch 3 | Step 11570 | Loss: 0.6690 | LM: 0.1671 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 9.72e-05 |
| [2026-05-24 04:49:48] Epoch 3 | Step 11580 | Loss: 0.6691 | LM: 0.1673 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 9.70e-05 |
| [2026-05-24 04:50:00] Epoch 3 | Step 11590 | Loss: 0.6692 | LM: 0.1676 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 9.68e-05 |
| [2026-05-24 04:50:12] Epoch 3 | Step 11600 | Loss: 0.6690 | LM: 0.1673 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 9.66e-05 |
| [2026-05-24 04:50:23] Epoch 3 | Step 11610 | Loss: 0.6691 | LM: 0.1673 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 9.64e-05 |
| [2026-05-24 04:50:34] Epoch 3 | Step 11620 | Loss: 0.6691 | LM: 0.1671 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.62e-05 |
| [2026-05-24 04:50:45] Epoch 3 | Step 11630 | Loss: 0.6691 | LM: 0.1673 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.306/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.60e-05 |
| [2026-05-24 04:50:57] Epoch 3 | Step 11640 | Loss: 0.6691 | LM: 0.1672 | LB: 1.0053 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 9.58e-05 |
| [2026-05-24 04:51:08] Epoch 3 | Step 11650 | Loss: 0.6691 | LM: 0.1672 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.227 | LR: 9.56e-05 |
| [2026-05-24 04:51:20] Epoch 3 | Step 11660 | Loss: 0.6691 | LM: 0.1671 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.54e-05 |
| [2026-05-24 04:51:31] Epoch 3 | Step 11670 | Loss: 0.6691 | LM: 0.1670 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.51e-05 |
| [2026-05-24 04:51:43] Epoch 3 | Step 11680 | Loss: 0.6690 | LM: 0.1670 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 9.49e-05 |
| [2026-05-24 04:51:55] Epoch 3 | Step 11690 | Loss: 0.6691 | LM: 0.1670 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.266/SR1: 0.228 | LR: 9.47e-05 |
| [2026-05-24 04:52:06] Epoch 3 | Step 11700 | Loss: 0.6692 | LM: 0.1670 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 9.44e-05 |
| [2026-05-24 04:52:18] Epoch 3 | Step 11710 | Loss: 0.6692 | LM: 0.1669 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 9.42e-05 |
| [2026-05-24 04:52:29] Epoch 3 | Step 11720 | Loss: 0.6693 | LM: 0.1669 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 9.39e-05 |
| [2026-05-24 04:52:40] Epoch 3 | Step 11730 | Loss: 0.6694 | LM: 0.1669 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 9.37e-05 |
| [2026-05-24 04:52:52] Epoch 3 | Step 11740 | Loss: 0.6694 | LM: 0.1668 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 9.34e-05 |
| [2026-05-24 04:53:03] Epoch 3 | Step 11750 | Loss: 0.6695 | LM: 0.1669 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 9.32e-05 |
| [2026-05-24 04:53:15] Epoch 3 | Step 11760 | Loss: 0.6695 | LM: 0.1669 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 9.29e-05 |
| [2026-05-24 04:53:26] Epoch 3 | Step 11770 | Loss: 0.6695 | LM: 0.1671 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 9.26e-05 |
| [2026-05-24 04:53:37] Epoch 3 | Step 11780 | Loss: 0.6696 | LM: 0.1672 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 9.23e-05 |
| [2026-05-24 04:53:48] Epoch 3 | Step 11790 | Loss: 0.6696 | LM: 0.1672 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 9.21e-05 |
| [2026-05-24 04:54:00] Epoch 3 | Step 11800 | Loss: 0.6697 | LM: 0.1674 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 9.18e-05 |
| [2026-05-24 04:54:10] Epoch 3 | Step 11810 | Loss: 0.6696 | LM: 0.1673 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 9.15e-05 |
| [2026-05-24 04:54:22] Epoch 3 | Step 11820 | Loss: 0.6696 | LM: 0.1672 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 9.12e-05 |
| [2026-05-24 04:54:33] Epoch 3 | Step 11830 | Loss: 0.6697 | LM: 0.1672 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 9.09e-05 |
| [2026-05-24 04:54:44] Epoch 3 | Step 11840 | Loss: 0.6696 | LM: 0.1673 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 9.06e-05 |
| [2026-05-24 04:54:56] Epoch 3 | Step 11850 | Loss: 0.6697 | LM: 0.1674 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 9.03e-05 |
| [2026-05-24 04:55:07] Epoch 3 | Step 11860 | Loss: 0.6697 | LM: 0.1673 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.99e-05 |
| [2026-05-24 04:55:18] Epoch 3 | Step 11870 | Loss: 0.6697 | LM: 0.1674 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.96e-05 |
| [2026-05-24 04:55:29] Epoch 3 | Step 11880 | Loss: 0.6697 | LM: 0.1674 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.93e-05 |
| [2026-05-24 04:55:40] Epoch 3 | Step 11890 | Loss: 0.6698 | LM: 0.1675 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.90e-05 |
| [2026-05-24 04:55:51] Epoch 3 | Step 11900 | Loss: 0.6699 | LM: 0.1676 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.86e-05 |
| [2026-05-24 04:56:02] Epoch 3 | Step 11910 | Loss: 0.6699 | LM: 0.1677 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.83e-05 |
| [2026-05-24 04:56:13] Epoch 3 | Step 11920 | Loss: 0.6700 | LM: 0.1677 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.80e-05 |
| [2026-05-24 04:56:24] Epoch 3 | Step 11930 | Loss: 0.6700 | LM: 0.1677 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.76e-05 |
| [2026-05-24 04:56:35] Epoch 3 | Step 11940 | Loss: 0.6700 | LM: 0.1676 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.73e-05 |
| [2026-05-24 04:56:47] Epoch 3 | Step 11950 | Loss: 0.6700 | LM: 0.1675 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.69e-05 |
| [2026-05-24 04:56:59] Epoch 3 | Step 11960 | Loss: 0.6700 | LM: 0.1675 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.66e-05 |
| [2026-05-24 04:57:10] Epoch 3 | Step 11970 | Loss: 0.6700 | LM: 0.1674 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.62e-05 |
| [2026-05-24 04:57:22] Epoch 3 | Step 11980 | Loss: 0.6701 | LM: 0.1678 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.58e-05 |
| [2026-05-24 04:57:33] Epoch 3 | Step 11990 | Loss: 0.6701 | LM: 0.1677 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.55e-05 |
| [2026-05-24 04:57:44] Epoch 3 | Step 12000 | Loss: 0.6701 | LM: 0.1676 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.51e-05 |
| [2026-05-24 04:57:49] Checkpoint saved: outputs/2026-05-24/N_4.0/checkpoints/checkpoint_step_12000.pt |
| [2026-05-24 04:57:56] Validation | Batch 10/1463 | Loss: 0.8357 | LM_LOSS: 0.3349 | LB_LOSS: 1.0017 |
| [2026-05-24 04:57:57] Validation | Batch 20/1463 | Loss: 0.8437 | LM_LOSS: 0.3424 | LB_LOSS: 1.0026 |
| [2026-05-24 04:58:00] Validation | Batch 30/1463 | Loss: 0.8407 | LM_LOSS: 0.3393 | LB_LOSS: 1.0029 |
| [2026-05-24 04:58:02] Validation | Batch 40/1463 | Loss: 0.8486 | LM_LOSS: 0.3469 | LB_LOSS: 1.0033 |
| [2026-05-24 04:58:04] Validation | Batch 50/1463 | Loss: 0.8570 | LM_LOSS: 0.3554 | LB_LOSS: 1.0031 |
| [2026-05-24 04:58:07] Validation | Batch 60/1463 | Loss: 0.8566 | LM_LOSS: 0.3551 | LB_LOSS: 1.0031 |
| [2026-05-24 04:58:09] Validation | Batch 70/1463 | Loss: 0.8570 | LM_LOSS: 0.3555 | LB_LOSS: 1.0031 |
| [2026-05-24 04:58:12] Validation | Batch 80/1463 | Loss: 0.8600 | LM_LOSS: 0.3585 | LB_LOSS: 1.0031 |
| [2026-05-24 04:58:14] Validation | Batch 90/1463 | Loss: 0.8592 | LM_LOSS: 0.3577 | LB_LOSS: 1.0030 |
| [2026-05-24 04:58:15] Validation | Batch 100/1463 | Loss: 0.8591 | LM_LOSS: 0.3576 | LB_LOSS: 1.0030 |
| [2026-05-24 04:58:18] Validation | Batch 110/1463 | Loss: 0.8567 | LM_LOSS: 0.3552 | LB_LOSS: 1.0032 |
| [2026-05-24 04:58:20] Validation | Batch 120/1463 | Loss: 0.8599 | LM_LOSS: 0.3583 | LB_LOSS: 1.0032 |
| [2026-05-24 04:58:21] Validation | Batch 130/1463 | Loss: 0.8619 | LM_LOSS: 0.3603 | LB_LOSS: 1.0033 |
| [2026-05-24 04:58:24] Validation | Batch 140/1463 | Loss: 0.8633 | LM_LOSS: 0.3617 | LB_LOSS: 1.0032 |
| [2026-05-24 04:58:26] Validation | Batch 150/1463 | Loss: 0.8607 | LM_LOSS: 0.3590 | LB_LOSS: 1.0033 |
| [2026-05-24 04:58:28] Validation | Batch 160/1463 | Loss: 0.8609 | LM_LOSS: 0.3592 | LB_LOSS: 1.0033 |
| [2026-05-24 04:58:31] Validation | Batch 170/1463 | Loss: 0.8595 | LM_LOSS: 0.3579 | LB_LOSS: 1.0033 |
| [2026-05-24 04:58:33] Validation | Batch 180/1463 | Loss: 0.8599 | LM_LOSS: 0.3583 | LB_LOSS: 1.0033 |
| [2026-05-24 04:58:35] Validation | Batch 190/1463 | Loss: 0.8618 | LM_LOSS: 0.3602 | LB_LOSS: 1.0033 |
| [2026-05-24 04:58:37] Validation | Batch 200/1463 | Loss: 0.8616 | LM_LOSS: 0.3599 | LB_LOSS: 1.0033 |
| [2026-05-24 04:58:39] Validation | Batch 210/1463 | Loss: 0.8620 | LM_LOSS: 0.3604 | LB_LOSS: 1.0033 |
| [2026-05-24 04:58:42] Validation | Batch 220/1463 | Loss: 0.8614 | LM_LOSS: 0.3598 | LB_LOSS: 1.0033 |
| [2026-05-24 04:58:44] Validation | Batch 230/1463 | Loss: 0.8631 | LM_LOSS: 0.3615 | LB_LOSS: 1.0032 |
| [2026-05-24 04:58:46] Validation | Batch 240/1463 | Loss: 0.8646 | LM_LOSS: 0.3630 | LB_LOSS: 1.0032 |
| [2026-05-24 04:58:49] Validation | Batch 250/1463 | Loss: 0.8637 | LM_LOSS: 0.3621 | LB_LOSS: 1.0032 |
| [2026-05-24 04:58:51] Validation | Batch 260/1463 | Loss: 0.8655 | LM_LOSS: 0.3639 | LB_LOSS: 1.0033 |
| [2026-05-24 04:58:53] Validation | Batch 270/1463 | Loss: 0.8635 | LM_LOSS: 0.3619 | LB_LOSS: 1.0033 |
| [2026-05-24 04:58:55] Validation | Batch 280/1463 | Loss: 0.8642 | LM_LOSS: 0.3625 | LB_LOSS: 1.0033 |
| [2026-05-24 04:58:57] Validation | Batch 290/1463 | Loss: 0.8631 | LM_LOSS: 0.3615 | LB_LOSS: 1.0033 |
| [2026-05-24 04:58:59] Validation | Batch 300/1463 | Loss: 0.8639 | LM_LOSS: 0.3622 | LB_LOSS: 1.0034 |
| [2026-05-24 04:59:01] Validation | Batch 310/1463 | Loss: 0.8647 | LM_LOSS: 0.3630 | LB_LOSS: 1.0034 |
| [2026-05-24 04:59:03] Validation | Batch 320/1463 | Loss: 0.8632 | LM_LOSS: 0.3616 | LB_LOSS: 1.0033 |
| [2026-05-24 04:59:05] Validation | Batch 330/1463 | Loss: 0.8631 | LM_LOSS: 0.3615 | LB_LOSS: 1.0033 |
| [2026-05-24 04:59:07] Validation | Batch 340/1463 | Loss: 0.8629 | LM_LOSS: 0.3612 | LB_LOSS: 1.0033 |
| [2026-05-24 04:59:10] Validation | Batch 350/1463 | Loss: 0.8635 | LM_LOSS: 0.3618 | LB_LOSS: 1.0033 |
| [2026-05-24 04:59:12] Validation | Batch 360/1463 | Loss: 0.8632 | LM_LOSS: 0.3615 | LB_LOSS: 1.0033 |
| [2026-05-24 04:59:13] Validation | Batch 370/1463 | Loss: 0.8629 | LM_LOSS: 0.3612 | LB_LOSS: 1.0033 |
| [2026-05-24 04:59:15] Validation | Batch 380/1463 | Loss: 0.8625 | LM_LOSS: 0.3609 | LB_LOSS: 1.0033 |
| [2026-05-24 04:59:18] Validation | Batch 390/1463 | Loss: 0.8631 | LM_LOSS: 0.3615 | LB_LOSS: 1.0033 |
| [2026-05-24 04:59:20] Validation | Batch 400/1463 | Loss: 0.8630 | LM_LOSS: 0.3613 | LB_LOSS: 1.0033 |
| [2026-05-24 04:59:22] Validation | Batch 410/1463 | Loss: 0.8626 | LM_LOSS: 0.3610 | LB_LOSS: 1.0033 |
| [2026-05-24 04:59:24] Validation | Batch 420/1463 | Loss: 0.8627 | LM_LOSS: 0.3611 | LB_LOSS: 1.0034 |
| [2026-05-24 04:59:27] Validation | Batch 430/1463 | Loss: 0.8620 | LM_LOSS: 0.3603 | LB_LOSS: 1.0034 |
| [2026-05-24 04:59:28] Validation | Batch 440/1463 | Loss: 0.8625 | LM_LOSS: 0.3608 | LB_LOSS: 1.0034 |
| [2026-05-24 04:59:30] Validation | Batch 450/1463 | Loss: 0.8621 | LM_LOSS: 0.3604 | LB_LOSS: 1.0034 |
| [2026-05-24 04:59:33] Validation | Batch 460/1463 | Loss: 0.8619 | LM_LOSS: 0.3602 | LB_LOSS: 1.0034 |
| [2026-05-24 04:59:35] Validation | Batch 470/1463 | Loss: 0.8626 | LM_LOSS: 0.3609 | LB_LOSS: 1.0034 |
| [2026-05-24 04:59:37] Validation | Batch 480/1463 | Loss: 0.8623 | LM_LOSS: 0.3606 | LB_LOSS: 1.0033 |
| [2026-05-24 04:59:39] Validation | Batch 490/1463 | Loss: 0.8620 | LM_LOSS: 0.3603 | LB_LOSS: 1.0033 |
| [2026-05-24 04:59:42] Validation | Batch 500/1463 | Loss: 0.8618 | LM_LOSS: 0.3602 | LB_LOSS: 1.0033 |
| [2026-05-24 04:59:44] Validation | Batch 510/1463 | Loss: 0.8610 | LM_LOSS: 0.3593 | LB_LOSS: 1.0033 |
| [2026-05-24 04:59:46] Validation | Batch 520/1463 | Loss: 0.8608 | LM_LOSS: 0.3591 | LB_LOSS: 1.0034 |
| [2026-05-24 04:59:48] Validation | Batch 530/1463 | Loss: 0.8615 | LM_LOSS: 0.3598 | LB_LOSS: 1.0034 |
| [2026-05-24 04:59:50] Validation | Batch 540/1463 | Loss: 0.8617 | LM_LOSS: 0.3601 | LB_LOSS: 1.0034 |
| [2026-05-24 04:59:52] Validation | Batch 550/1463 | Loss: 0.8613 | LM_LOSS: 0.3596 | LB_LOSS: 1.0034 |
| [2026-05-24 04:59:54] Validation | Batch 560/1463 | Loss: 0.8614 | LM_LOSS: 0.3597 | LB_LOSS: 1.0034 |
| [2026-05-24 04:59:56] Validation | Batch 570/1463 | Loss: 0.8613 | LM_LOSS: 0.3596 | LB_LOSS: 1.0034 |
| [2026-05-24 04:59:59] Validation | Batch 580/1463 | Loss: 0.8608 | LM_LOSS: 0.3591 | LB_LOSS: 1.0034 |
| [2026-05-24 05:00:01] Validation | Batch 590/1463 | Loss: 0.8606 | LM_LOSS: 0.3589 | LB_LOSS: 1.0034 |
| [2026-05-24 05:00:03] Validation | Batch 600/1463 | Loss: 0.8607 | LM_LOSS: 0.3590 | LB_LOSS: 1.0034 |
| [2026-05-24 05:00:06] Validation | Batch 610/1463 | Loss: 0.8610 | LM_LOSS: 0.3593 | LB_LOSS: 1.0034 |
| [2026-05-24 05:00:08] Validation | Batch 620/1463 | Loss: 0.8604 | LM_LOSS: 0.3586 | LB_LOSS: 1.0034 |
| [2026-05-24 05:00:10] Validation | Batch 630/1463 | Loss: 0.8599 | LM_LOSS: 0.3581 | LB_LOSS: 1.0034 |
| [2026-05-24 05:00:12] Validation | Batch 640/1463 | Loss: 0.8596 | LM_LOSS: 0.3579 | LB_LOSS: 1.0035 |
| [2026-05-24 05:00:14] Validation | Batch 650/1463 | Loss: 0.8591 | LM_LOSS: 0.3574 | LB_LOSS: 1.0035 |
| [2026-05-24 05:00:16] Validation | Batch 660/1463 | Loss: 0.8585 | LM_LOSS: 0.3568 | LB_LOSS: 1.0034 |
| [2026-05-24 05:00:18] Validation | Batch 670/1463 | Loss: 0.8580 | LM_LOSS: 0.3563 | LB_LOSS: 1.0034 |
| [2026-05-24 05:00:20] Validation | Batch 680/1463 | Loss: 0.8579 | LM_LOSS: 0.3562 | LB_LOSS: 1.0034 |
| [2026-05-24 05:00:22] Validation | Batch 690/1463 | Loss: 0.8582 | LM_LOSS: 0.3565 | LB_LOSS: 1.0034 |
| [2026-05-24 05:00:24] Validation | Batch 700/1463 | Loss: 0.8581 | LM_LOSS: 0.3564 | LB_LOSS: 1.0034 |
| [2026-05-24 05:00:26] Validation | Batch 710/1463 | Loss: 0.8584 | LM_LOSS: 0.3567 | LB_LOSS: 1.0034 |
| [2026-05-24 05:00:29] Validation | Batch 720/1463 | Loss: 0.8592 | LM_LOSS: 0.3574 | LB_LOSS: 1.0035 |
| [2026-05-24 05:00:30] Validation | Batch 730/1463 | Loss: 0.8591 | LM_LOSS: 0.3574 | LB_LOSS: 1.0035 |
| [2026-05-24 05:00:32] Validation | Batch 740/1463 | Loss: 0.8587 | LM_LOSS: 0.3569 | LB_LOSS: 1.0035 |
| [2026-05-24 05:00:34] Validation | Batch 750/1463 | Loss: 0.8586 | LM_LOSS: 0.3569 | LB_LOSS: 1.0035 |
| [2026-05-24 05:00:36] Validation | Batch 760/1463 | Loss: 0.8584 | LM_LOSS: 0.3566 | LB_LOSS: 1.0035 |
| [2026-05-24 05:00:37] Validation | Batch 770/1463 | Loss: 0.8583 | LM_LOSS: 0.3565 | LB_LOSS: 1.0035 |
| [2026-05-24 05:00:39] Validation | Batch 780/1463 | Loss: 0.8582 | LM_LOSS: 0.3565 | LB_LOSS: 1.0035 |
| [2026-05-24 05:00:41] Validation | Batch 790/1463 | Loss: 0.8584 | LM_LOSS: 0.3567 | LB_LOSS: 1.0034 |
| [2026-05-24 05:00:43] Validation | Batch 800/1463 | Loss: 0.8584 | LM_LOSS: 0.3567 | LB_LOSS: 1.0035 |
| [2026-05-24 05:00:45] Validation | Batch 810/1463 | Loss: 0.8580 | LM_LOSS: 0.3563 | LB_LOSS: 1.0034 |
| [2026-05-24 05:00:47] Validation | Batch 820/1463 | Loss: 0.8583 | LM_LOSS: 0.3566 | LB_LOSS: 1.0034 |
| [2026-05-24 05:00:49] Validation | Batch 830/1463 | Loss: 0.8586 | LM_LOSS: 0.3569 | LB_LOSS: 1.0034 |
| [2026-05-24 05:00:51] Validation | Batch 840/1463 | Loss: 0.8586 | LM_LOSS: 0.3569 | LB_LOSS: 1.0034 |
| [2026-05-24 05:00:54] Validation | Batch 850/1463 | Loss: 0.8590 | LM_LOSS: 0.3573 | LB_LOSS: 1.0034 |
| [2026-05-24 05:00:56] Validation | Batch 860/1463 | Loss: 0.8593 | LM_LOSS: 0.3576 | LB_LOSS: 1.0035 |
| [2026-05-24 05:00:58] Validation | Batch 870/1463 | Loss: 0.8594 | LM_LOSS: 0.3577 | LB_LOSS: 1.0035 |
| [2026-05-24 05:01:00] Validation | Batch 880/1463 | Loss: 0.8586 | LM_LOSS: 0.3569 | LB_LOSS: 1.0035 |
| [2026-05-24 05:01:02] Validation | Batch 890/1463 | Loss: 0.8587 | LM_LOSS: 0.3569 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:04] Validation | Batch 900/1463 | Loss: 0.8583 | LM_LOSS: 0.3566 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:06] Validation | Batch 910/1463 | Loss: 0.8582 | LM_LOSS: 0.3565 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:09] Validation | Batch 920/1463 | Loss: 0.8585 | LM_LOSS: 0.3567 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:11] Validation | Batch 930/1463 | Loss: 0.8580 | LM_LOSS: 0.3563 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:13] Validation | Batch 940/1463 | Loss: 0.8577 | LM_LOSS: 0.3560 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:15] Validation | Batch 950/1463 | Loss: 0.8580 | LM_LOSS: 0.3563 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:17] Validation | Batch 960/1463 | Loss: 0.8580 | LM_LOSS: 0.3563 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:20] Validation | Batch 970/1463 | Loss: 0.8581 | LM_LOSS: 0.3564 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:22] Validation | Batch 980/1463 | Loss: 0.8585 | LM_LOSS: 0.3568 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:24] Validation | Batch 990/1463 | Loss: 0.8587 | LM_LOSS: 0.3570 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:26] Validation | Batch 1000/1463 | Loss: 0.8594 | LM_LOSS: 0.3577 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:28] Validation | Batch 1010/1463 | Loss: 0.8595 | LM_LOSS: 0.3578 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:30] Validation | Batch 1020/1463 | Loss: 0.8596 | LM_LOSS: 0.3579 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:33] Validation | Batch 1030/1463 | Loss: 0.8602 | LM_LOSS: 0.3585 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:35] Validation | Batch 1040/1463 | Loss: 0.8597 | LM_LOSS: 0.3580 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:37] Validation | Batch 1050/1463 | Loss: 0.8596 | LM_LOSS: 0.3579 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:39] Validation | Batch 1060/1463 | Loss: 0.8596 | LM_LOSS: 0.3578 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:42] Validation | Batch 1070/1463 | Loss: 0.8595 | LM_LOSS: 0.3578 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:44] Validation | Batch 1080/1463 | Loss: 0.8593 | LM_LOSS: 0.3576 | LB_LOSS: 1.0035 |
| [2026-05-24 05:01:45] Validation | Batch 1090/1463 | Loss: 0.8592 | LM_LOSS: 0.3575 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:47] Validation | Batch 1100/1463 | Loss: 0.8591 | LM_LOSS: 0.3574 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:49] Validation | Batch 1110/1463 | Loss: 0.8591 | LM_LOSS: 0.3574 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:51] Validation | Batch 1120/1463 | Loss: 0.8589 | LM_LOSS: 0.3571 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:54] Validation | Batch 1130/1463 | Loss: 0.8586 | LM_LOSS: 0.3569 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:56] Validation | Batch 1140/1463 | Loss: 0.8589 | LM_LOSS: 0.3572 | LB_LOSS: 1.0034 |
| [2026-05-24 05:01:58] Validation | Batch 1150/1463 | Loss: 0.8588 | LM_LOSS: 0.3571 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:00] Validation | Batch 1160/1463 | Loss: 0.8588 | LM_LOSS: 0.3570 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:03] Validation | Batch 1170/1463 | Loss: 0.8587 | LM_LOSS: 0.3570 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:05] Validation | Batch 1180/1463 | Loss: 0.8589 | LM_LOSS: 0.3572 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:07] Validation | Batch 1190/1463 | Loss: 0.8590 | LM_LOSS: 0.3573 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:09] Validation | Batch 1200/1463 | Loss: 0.8590 | LM_LOSS: 0.3573 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:11] Validation | Batch 1210/1463 | Loss: 0.8592 | LM_LOSS: 0.3575 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:13] Validation | Batch 1220/1463 | Loss: 0.8597 | LM_LOSS: 0.3579 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:15] Validation | Batch 1230/1463 | Loss: 0.8596 | LM_LOSS: 0.3579 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:17] Validation | Batch 1240/1463 | Loss: 0.8599 | LM_LOSS: 0.3582 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:20] Validation | Batch 1250/1463 | Loss: 0.8601 | LM_LOSS: 0.3584 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:22] Validation | Batch 1260/1463 | Loss: 0.8599 | LM_LOSS: 0.3582 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:24] Validation | Batch 1270/1463 | Loss: 0.8596 | LM_LOSS: 0.3579 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:27] Validation | Batch 1280/1463 | Loss: 0.8594 | LM_LOSS: 0.3577 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:29] Validation | Batch 1290/1463 | Loss: 0.8594 | LM_LOSS: 0.3577 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:31] Validation | Batch 1300/1463 | Loss: 0.8592 | LM_LOSS: 0.3575 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:33] Validation | Batch 1310/1463 | Loss: 0.8590 | LM_LOSS: 0.3573 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:34] Validation | Batch 1320/1463 | Loss: 0.8590 | LM_LOSS: 0.3573 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:36] Validation | Batch 1330/1463 | Loss: 0.8591 | LM_LOSS: 0.3574 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:38] Validation | Batch 1340/1463 | Loss: 0.8595 | LM_LOSS: 0.3578 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:40] Validation | Batch 1350/1463 | Loss: 0.8595 | LM_LOSS: 0.3578 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:43] Validation | Batch 1360/1463 | Loss: 0.8597 | LM_LOSS: 0.3580 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:45] Validation | Batch 1370/1463 | Loss: 0.8601 | LM_LOSS: 0.3584 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:47] Validation | Batch 1380/1463 | Loss: 0.8598 | LM_LOSS: 0.3581 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:49] Validation | Batch 1390/1463 | Loss: 0.8598 | LM_LOSS: 0.3581 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:51] Validation | Batch 1400/1463 | Loss: 0.8601 | LM_LOSS: 0.3584 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:53] Validation | Batch 1410/1463 | Loss: 0.8604 | LM_LOSS: 0.3587 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:55] Validation | Batch 1420/1463 | Loss: 0.8604 | LM_LOSS: 0.3587 | LB_LOSS: 1.0034 |
| [2026-05-24 05:02:58] Validation | Batch 1430/1463 | Loss: 0.8604 | LM_LOSS: 0.3587 | LB_LOSS: 1.0034 |
| [2026-05-24 05:03:00] Validation | Batch 1440/1463 | Loss: 0.8608 | LM_LOSS: 0.3591 | LB_LOSS: 1.0034 |
| [2026-05-24 05:03:02] Validation | Batch 1450/1463 | Loss: 0.8605 | LM_LOSS: 0.3588 | LB_LOSS: 1.0034 |
| [2026-05-24 05:03:04] Validation | Batch 1460/1463 | Loss: 0.8608 | LM_LOSS: 0.3591 | LB_LOSS: 1.0034 |
| [2026-05-24 05:03:05] Validation | Batch 1463/1463 | Loss: 0.8608 | LM_LOSS: 0.3591 | LB_LOSS: 1.0034 |
| [2026-05-24 05:03:05] Validation | Loss: 0.8608 | LM_LOSS: 0.3591 | LB_LOSS: 1.0034 | PPL: 1.43 | Time: 311.02s |
| [2026-05-24 05:03:16] Epoch 3 | Step 12010 | Loss: 0.6700 | LM: 0.1677 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.47e-05 |
| [2026-05-24 05:03:27] Epoch 3 | Step 12020 | Loss: 0.6701 | LM: 0.1678 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.44e-05 |
| [2026-05-24 05:03:38] Epoch 3 | Step 12030 | Loss: 0.6701 | LM: 0.1677 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.40e-05 |
| [2026-05-24 05:03:50] Epoch 3 | Step 12040 | Loss: 0.6702 | LM: 0.1680 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.36e-05 |
| [2026-05-24 05:04:00] Epoch 3 | Step 12050 | Loss: 0.6702 | LM: 0.1679 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.32e-05 |
| [2026-05-24 05:04:12] Epoch 3 | Step 12060 | Loss: 0.6702 | LM: 0.1679 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.28e-05 |
| [2026-05-24 05:04:23] Epoch 3 | Step 12070 | Loss: 0.6701 | LM: 0.1679 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.24e-05 |
| [2026-05-24 05:04:34] Epoch 3 | Step 12080 | Loss: 0.6702 | LM: 0.1680 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.20e-05 |
| [2026-05-24 05:04:45] Epoch 3 | Step 12090 | Loss: 0.6701 | LM: 0.1679 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.16e-05 |
| [2026-05-24 05:04:57] Epoch 3 | Step 12100 | Loss: 0.6700 | LM: 0.1678 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.12e-05 |
| [2026-05-24 05:05:08] Epoch 3 | Step 12110 | Loss: 0.6700 | LM: 0.1679 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.08e-05 |
| [2026-05-24 05:05:19] Epoch 3 | Step 12120 | Loss: 0.6700 | LM: 0.1677 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 8.04e-05 |
| [2026-05-24 05:05:31] Epoch 3 | Step 12130 | Loss: 0.6700 | LM: 0.1677 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.99e-05 |
| [2026-05-24 05:05:42] Epoch 3 | Step 12140 | Loss: 0.6700 | LM: 0.1678 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.95e-05 |
| [2026-05-24 05:05:53] Epoch 3 | Step 12150 | Loss: 0.6701 | LM: 0.1678 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.91e-05 |
| [2026-05-24 05:06:04] Epoch 3 | Step 12160 | Loss: 0.6701 | LM: 0.1677 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.87e-05 |
| [2026-05-24 05:06:15] Epoch 3 | Step 12170 | Loss: 0.6701 | LM: 0.1678 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.83e-05 |
| [2026-05-24 05:06:26] Epoch 3 | Step 12180 | Loss: 0.6701 | LM: 0.1678 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.78e-05 |
| [2026-05-24 05:06:37] Epoch 3 | Step 12190 | Loss: 0.6701 | LM: 0.1677 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.74e-05 |
| [2026-05-24 05:06:48] Epoch 3 | Step 12200 | Loss: 0.6701 | LM: 0.1677 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.69e-05 |
| [2026-05-24 05:06:59] Epoch 3 | Step 12210 | Loss: 0.6702 | LM: 0.1678 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.65e-05 |
| [2026-05-24 05:07:10] Epoch 3 | Step 12220 | Loss: 0.6703 | LM: 0.1680 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.61e-05 |
| [2026-05-24 05:07:21] Epoch 3 | Step 12230 | Loss: 0.6703 | LM: 0.1680 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.56e-05 |
| [2026-05-24 05:07:33] Epoch 3 | Step 12240 | Loss: 0.6703 | LM: 0.1681 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.52e-05 |
| [2026-05-24 05:07:43] Epoch 3 | Step 12250 | Loss: 0.6703 | LM: 0.1681 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.47e-05 |
| [2026-05-24 05:07:54] Epoch 3 | Step 12260 | Loss: 0.6703 | LM: 0.1681 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.43e-05 |
| [2026-05-24 05:08:05] Epoch 3 | Step 12270 | Loss: 0.6703 | LM: 0.1680 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.38e-05 |
| [2026-05-24 05:08:16] Epoch 3 | Step 12280 | Loss: 0.6704 | LM: 0.1680 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.34e-05 |
| [2026-05-24 05:08:27] Epoch 3 | Step 12290 | Loss: 0.6704 | LM: 0.1679 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.29e-05 |
| [2026-05-24 05:08:37] Epoch 3 | Step 12300 | Loss: 0.6704 | LM: 0.1681 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.24e-05 |
| [2026-05-24 05:08:48] Epoch 3 | Step 12310 | Loss: 0.6705 | LM: 0.1683 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.20e-05 |
| [2026-05-24 05:09:00] Epoch 3 | Step 12320 | Loss: 0.6705 | LM: 0.1683 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.15e-05 |
| [2026-05-24 05:09:11] Epoch 3 | Step 12330 | Loss: 0.6705 | LM: 0.1684 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.10e-05 |
| [2026-05-24 05:09:22] Epoch 3 | Step 12340 | Loss: 0.6706 | LM: 0.1686 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.06e-05 |
| [2026-05-24 05:09:33] Epoch 3 | Step 12350 | Loss: 0.6706 | LM: 0.1688 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 7.01e-05 |
| [2026-05-24 05:09:44] Epoch 3 | Step 12360 | Loss: 0.6707 | LM: 0.1688 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.96e-05 |
| [2026-05-24 05:09:55] Epoch 3 | Step 12370 | Loss: 0.6707 | LM: 0.1687 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.91e-05 |
| [2026-05-24 05:10:06] Epoch 3 | Step 12380 | Loss: 0.6707 | LM: 0.1688 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.87e-05 |
| [2026-05-24 05:10:17] Epoch 3 | Step 12390 | Loss: 0.6707 | LM: 0.1688 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.82e-05 |
| [2026-05-24 05:10:28] Epoch 3 | Step 12400 | Loss: 0.6707 | LM: 0.1688 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.77e-05 |
| [2026-05-24 05:10:40] Epoch 3 | Step 12410 | Loss: 0.6707 | LM: 0.1688 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.72e-05 |
| [2026-05-24 05:10:50] Epoch 3 | Step 12420 | Loss: 0.6707 | LM: 0.1689 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.67e-05 |
| [2026-05-24 05:11:01] Epoch 3 | Step 12430 | Loss: 0.6708 | LM: 0.1690 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.62e-05 |
| [2026-05-24 05:11:12] Epoch 3 | Step 12440 | Loss: 0.6707 | LM: 0.1688 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.58e-05 |
| [2026-05-24 05:11:24] Epoch 3 | Step 12450 | Loss: 0.6707 | LM: 0.1688 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.53e-05 |
| [2026-05-24 05:11:36] Epoch 3 | Step 12460 | Loss: 0.6706 | LM: 0.1687 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.48e-05 |
| [2026-05-24 05:11:48] Epoch 3 | Step 12470 | Loss: 0.6707 | LM: 0.1689 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.43e-05 |
| [2026-05-24 05:12:00] Epoch 3 | Step 12480 | Loss: 0.6707 | LM: 0.1689 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.38e-05 |
| [2026-05-24 05:12:12] Epoch 3 | Step 12490 | Loss: 0.6707 | LM: 0.1688 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.33e-05 |
| [2026-05-24 05:12:24] Epoch 3 | Step 12500 | Loss: 0.6707 | LM: 0.1688 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.28e-05 |
| [2026-05-24 05:12:35] Epoch 3 | Step 12510 | Loss: 0.6707 | LM: 0.1688 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.23e-05 |
| [2026-05-24 05:12:47] Epoch 3 | Step 12520 | Loss: 0.6707 | LM: 0.1687 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.18e-05 |
| [2026-05-24 05:12:59] Epoch 3 | Step 12530 | Loss: 0.6707 | LM: 0.1687 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.13e-05 |
| [2026-05-24 05:13:11] Epoch 3 | Step 12540 | Loss: 0.6706 | LM: 0.1686 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.08e-05 |
| [2026-05-24 05:13:23] Epoch 3 | Step 12550 | Loss: 0.6706 | LM: 0.1686 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 6.03e-05 |
| [2026-05-24 05:13:35] Epoch 3 | Step 12560 | Loss: 0.6707 | LM: 0.1686 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.98e-05 |
| [2026-05-24 05:13:47] Epoch 3 | Step 12570 | Loss: 0.6707 | LM: 0.1686 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.93e-05 |
| [2026-05-24 05:13:59] Epoch 3 | Step 12580 | Loss: 0.6707 | LM: 0.1685 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.88e-05 |
| [2026-05-24 05:14:10] Epoch 3 | Step 12590 | Loss: 0.6707 | LM: 0.1685 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.83e-05 |
| [2026-05-24 05:14:22] Epoch 3 | Step 12600 | Loss: 0.6707 | LM: 0.1686 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.78e-05 |
| [2026-05-24 05:14:32] Epoch 3 | Step 12610 | Loss: 0.6707 | LM: 0.1687 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.73e-05 |
| [2026-05-24 05:14:44] Epoch 3 | Step 12620 | Loss: 0.6707 | LM: 0.1687 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.68e-05 |
| [2026-05-24 05:14:55] Epoch 3 | Step 12630 | Loss: 0.6707 | LM: 0.1686 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.63e-05 |
| [2026-05-24 05:15:06] Epoch 3 | Step 12640 | Loss: 0.6708 | LM: 0.1686 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.58e-05 |
| [2026-05-24 05:15:17] Epoch 3 | Step 12650 | Loss: 0.6708 | LM: 0.1686 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.53e-05 |
| [2026-05-24 05:15:28] Epoch 3 | Step 12660 | Loss: 0.6708 | LM: 0.1686 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.48e-05 |
| [2026-05-24 05:15:39] Epoch 3 | Step 12670 | Loss: 0.6708 | LM: 0.1686 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.43e-05 |
| [2026-05-24 05:15:50] Epoch 3 | Step 12680 | Loss: 0.6707 | LM: 0.1686 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.38e-05 |
| [2026-05-24 05:16:01] Epoch 3 | Step 12690 | Loss: 0.6707 | LM: 0.1685 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.33e-05 |
| [2026-05-24 05:16:12] Epoch 3 | Step 12700 | Loss: 0.6707 | LM: 0.1685 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.28e-05 |
| [2026-05-24 05:16:23] Epoch 3 | Step 12710 | Loss: 0.6706 | LM: 0.1685 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.23e-05 |
| [2026-05-24 05:16:34] Epoch 3 | Step 12720 | Loss: 0.6705 | LM: 0.1683 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.18e-05 |
| [2026-05-24 05:16:45] Epoch 3 | Step 12730 | Loss: 0.6706 | LM: 0.1684 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.13e-05 |
| [2026-05-24 05:16:56] Epoch 3 | Step 12740 | Loss: 0.6706 | LM: 0.1684 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.08e-05 |
| [2026-05-24 05:17:07] Epoch 3 | Step 12750 | Loss: 0.6706 | LM: 0.1683 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 5.03e-05 |
| [2026-05-24 05:17:18] Epoch 3 | Step 12760 | Loss: 0.6706 | LM: 0.1684 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 4.98e-05 |
| [2026-05-24 05:17:29] Epoch 3 | Step 12770 | Loss: 0.6706 | LM: 0.1683 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 4.93e-05 |
| [2026-05-24 05:17:40] Epoch 3 | Step 12780 | Loss: 0.6707 | LM: 0.1684 | LB: 1.0052 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 4.88e-05 |
| [2026-05-24 05:17:52] Epoch 3 | Step 12790 | Loss: 0.6707 | LM: 0.1685 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 4.83e-05 |
| [2026-05-24 05:18:03] Epoch 3 | Step 12800 | Loss: 0.6708 | LM: 0.1686 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 4.78e-05 |
| [2026-05-24 05:18:14] Epoch 3 | Step 12810 | Loss: 0.6708 | LM: 0.1685 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 4.73e-05 |
| [2026-05-24 05:18:26] Epoch 3 | Step 12820 | Loss: 0.6708 | LM: 0.1686 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 4.68e-05 |
| [2026-05-24 05:18:37] Epoch 3 | Step 12830 | Loss: 0.6708 | LM: 0.1686 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 4.63e-05 |
| [2026-05-24 05:18:47] Epoch 3 | Step 12840 | Loss: 0.6708 | LM: 0.1686 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 4.58e-05 |
| [2026-05-24 05:18:58] Epoch 3 | Step 12850 | Loss: 0.6709 | LM: 0.1687 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 4.53e-05 |
| [2026-05-24 05:19:09] Epoch 3 | Step 12860 | Loss: 0.6709 | LM: 0.1687 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 4.48e-05 |
| [2026-05-24 05:19:20] Epoch 3 | Step 12870 | Loss: 0.6708 | LM: 0.1685 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 4.43e-05 |
| [2026-05-24 05:19:32] Epoch 3 | Step 12880 | Loss: 0.6709 | LM: 0.1686 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 4.39e-05 |
| [2026-05-24 05:19:43] Epoch 3 | Step 12890 | Loss: 0.6709 | LM: 0.1687 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 4.34e-05 |
| [2026-05-24 05:19:53] Epoch 3 | Step 12900 | Loss: 0.6708 | LM: 0.1687 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 4.29e-05 |
| [2026-05-24 05:20:04] Epoch 3 | Step 12910 | Loss: 0.6709 | LM: 0.1687 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 4.24e-05 |
| [2026-05-24 05:20:16] Epoch 3 | Step 12920 | Loss: 0.6709 | LM: 0.1688 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 4.19e-05 |
| [2026-05-24 05:20:27] Epoch 3 | Step 12930 | Loss: 0.6709 | LM: 0.1688 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 4.14e-05 |
| [2026-05-24 05:20:38] Epoch 3 | Step 12940 | Loss: 0.6709 | LM: 0.1689 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.279 | HR1: 0.267/SR1: 0.228 | LR: 4.10e-05 |
| [2026-05-24 05:20:49] Epoch 3 | Step 12950 | Loss: 0.6709 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 4.05e-05 |
| [2026-05-24 05:21:00] Epoch 3 | Step 12960 | Loss: 0.6709 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 4.00e-05 |
| [2026-05-24 05:21:11] Epoch 3 | Step 12970 | Loss: 0.6709 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.95e-05 |
| [2026-05-24 05:21:22] Epoch 3 | Step 12980 | Loss: 0.6709 | LM: 0.1689 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.91e-05 |
| [2026-05-24 05:21:33] Epoch 3 | Step 12990 | Loss: 0.6708 | LM: 0.1689 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.86e-05 |
| [2026-05-24 05:21:44] Epoch 3 | Step 13000 | Loss: 0.6708 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.81e-05 |
| [2026-05-24 05:21:46] Validation | Batch 10/1463 | Loss: 0.8368 | LM_LOSS: 0.3360 | LB_LOSS: 1.0016 |
| [2026-05-24 05:21:48] Validation | Batch 20/1463 | Loss: 0.8446 | LM_LOSS: 0.3433 | LB_LOSS: 1.0025 |
| [2026-05-24 05:21:50] Validation | Batch 30/1463 | Loss: 0.8423 | LM_LOSS: 0.3409 | LB_LOSS: 1.0029 |
| [2026-05-24 05:21:52] Validation | Batch 40/1463 | Loss: 0.8504 | LM_LOSS: 0.3488 | LB_LOSS: 1.0032 |
| [2026-05-24 05:21:54] Validation | Batch 50/1463 | Loss: 0.8604 | LM_LOSS: 0.3589 | LB_LOSS: 1.0030 |
| [2026-05-24 05:21:57] Validation | Batch 60/1463 | Loss: 0.8608 | LM_LOSS: 0.3593 | LB_LOSS: 1.0029 |
| [2026-05-24 05:21:59] Validation | Batch 70/1463 | Loss: 0.8608 | LM_LOSS: 0.3593 | LB_LOSS: 1.0030 |
| [2026-05-24 05:22:02] Validation | Batch 80/1463 | Loss: 0.8641 | LM_LOSS: 0.3626 | LB_LOSS: 1.0030 |
| [2026-05-24 05:22:04] Validation | Batch 90/1463 | Loss: 0.8635 | LM_LOSS: 0.3620 | LB_LOSS: 1.0029 |
| [2026-05-24 05:22:06] Validation | Batch 100/1463 | Loss: 0.8631 | LM_LOSS: 0.3616 | LB_LOSS: 1.0029 |
| [2026-05-24 05:22:08] Validation | Batch 110/1463 | Loss: 0.8612 | LM_LOSS: 0.3596 | LB_LOSS: 1.0031 |
| [2026-05-24 05:22:10] Validation | Batch 120/1463 | Loss: 0.8644 | LM_LOSS: 0.3628 | LB_LOSS: 1.0031 |
| [2026-05-24 05:22:11] Validation | Batch 130/1463 | Loss: 0.8667 | LM_LOSS: 0.3651 | LB_LOSS: 1.0032 |
| [2026-05-24 05:22:14] Validation | Batch 140/1463 | Loss: 0.8681 | LM_LOSS: 0.3665 | LB_LOSS: 1.0031 |
| [2026-05-24 05:22:16] Validation | Batch 150/1463 | Loss: 0.8656 | LM_LOSS: 0.3640 | LB_LOSS: 1.0032 |
| [2026-05-24 05:22:18] Validation | Batch 160/1463 | Loss: 0.8658 | LM_LOSS: 0.3642 | LB_LOSS: 1.0032 |
| [2026-05-24 05:22:20] Validation | Batch 170/1463 | Loss: 0.8645 | LM_LOSS: 0.3629 | LB_LOSS: 1.0032 |
| [2026-05-24 05:22:23] Validation | Batch 180/1463 | Loss: 0.8649 | LM_LOSS: 0.3633 | LB_LOSS: 1.0032 |
| [2026-05-24 05:22:25] Validation | Batch 190/1463 | Loss: 0.8666 | LM_LOSS: 0.3650 | LB_LOSS: 1.0032 |
| [2026-05-24 05:22:27] Validation | Batch 200/1463 | Loss: 0.8663 | LM_LOSS: 0.3647 | LB_LOSS: 1.0032 |
| [2026-05-24 05:22:29] Validation | Batch 210/1463 | Loss: 0.8669 | LM_LOSS: 0.3653 | LB_LOSS: 1.0032 |
| [2026-05-24 05:22:32] Validation | Batch 220/1463 | Loss: 0.8662 | LM_LOSS: 0.3646 | LB_LOSS: 1.0032 |
| [2026-05-24 05:22:34] Validation | Batch 230/1463 | Loss: 0.8679 | LM_LOSS: 0.3663 | LB_LOSS: 1.0031 |
| [2026-05-24 05:22:36] Validation | Batch 240/1463 | Loss: 0.8694 | LM_LOSS: 0.3678 | LB_LOSS: 1.0031 |
| [2026-05-24 05:22:38] Validation | Batch 250/1463 | Loss: 0.8686 | LM_LOSS: 0.3670 | LB_LOSS: 1.0031 |
| [2026-05-24 05:22:40] Validation | Batch 260/1463 | Loss: 0.8704 | LM_LOSS: 0.3688 | LB_LOSS: 1.0032 |
| [2026-05-24 05:22:42] Validation | Batch 270/1463 | Loss: 0.8683 | LM_LOSS: 0.3666 | LB_LOSS: 1.0032 |
| [2026-05-24 05:22:45] Validation | Batch 280/1463 | Loss: 0.8688 | LM_LOSS: 0.3672 | LB_LOSS: 1.0033 |
| [2026-05-24 05:22:47] Validation | Batch 290/1463 | Loss: 0.8678 | LM_LOSS: 0.3661 | LB_LOSS: 1.0033 |
| [2026-05-24 05:22:48] Validation | Batch 300/1463 | Loss: 0.8684 | LM_LOSS: 0.3668 | LB_LOSS: 1.0033 |
| [2026-05-24 05:22:51] Validation | Batch 310/1463 | Loss: 0.8692 | LM_LOSS: 0.3676 | LB_LOSS: 1.0033 |
| [2026-05-24 05:22:53] Validation | Batch 320/1463 | Loss: 0.8680 | LM_LOSS: 0.3664 | LB_LOSS: 1.0032 |
| [2026-05-24 05:22:55] Validation | Batch 330/1463 | Loss: 0.8678 | LM_LOSS: 0.3662 | LB_LOSS: 1.0032 |
| [2026-05-24 05:22:57] Validation | Batch 340/1463 | Loss: 0.8675 | LM_LOSS: 0.3658 | LB_LOSS: 1.0032 |
| [2026-05-24 05:22:59] Validation | Batch 350/1463 | Loss: 0.8681 | LM_LOSS: 0.3665 | LB_LOSS: 1.0032 |
| [2026-05-24 05:23:01] Validation | Batch 360/1463 | Loss: 0.8679 | LM_LOSS: 0.3662 | LB_LOSS: 1.0032 |
| [2026-05-24 05:23:03] Validation | Batch 370/1463 | Loss: 0.8674 | LM_LOSS: 0.3658 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:05] Validation | Batch 380/1463 | Loss: 0.8669 | LM_LOSS: 0.3653 | LB_LOSS: 1.0032 |
| [2026-05-24 05:23:07] Validation | Batch 390/1463 | Loss: 0.8675 | LM_LOSS: 0.3659 | LB_LOSS: 1.0032 |
| [2026-05-24 05:23:09] Validation | Batch 400/1463 | Loss: 0.8674 | LM_LOSS: 0.3657 | LB_LOSS: 1.0032 |
| [2026-05-24 05:23:11] Validation | Batch 410/1463 | Loss: 0.8669 | LM_LOSS: 0.3653 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:13] Validation | Batch 420/1463 | Loss: 0.8669 | LM_LOSS: 0.3653 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:16] Validation | Batch 430/1463 | Loss: 0.8662 | LM_LOSS: 0.3646 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:18] Validation | Batch 440/1463 | Loss: 0.8666 | LM_LOSS: 0.3649 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:19] Validation | Batch 450/1463 | Loss: 0.8661 | LM_LOSS: 0.3644 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:22] Validation | Batch 460/1463 | Loss: 0.8658 | LM_LOSS: 0.3642 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:24] Validation | Batch 470/1463 | Loss: 0.8666 | LM_LOSS: 0.3649 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:26] Validation | Batch 480/1463 | Loss: 0.8663 | LM_LOSS: 0.3646 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:28] Validation | Batch 490/1463 | Loss: 0.8660 | LM_LOSS: 0.3644 | LB_LOSS: 1.0032 |
| [2026-05-24 05:23:31] Validation | Batch 500/1463 | Loss: 0.8657 | LM_LOSS: 0.3641 | LB_LOSS: 1.0032 |
| [2026-05-24 05:23:33] Validation | Batch 510/1463 | Loss: 0.8649 | LM_LOSS: 0.3633 | LB_LOSS: 1.0032 |
| [2026-05-24 05:23:35] Validation | Batch 520/1463 | Loss: 0.8646 | LM_LOSS: 0.3630 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:37] Validation | Batch 530/1463 | Loss: 0.8653 | LM_LOSS: 0.3637 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:39] Validation | Batch 540/1463 | Loss: 0.8655 | LM_LOSS: 0.3638 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:41] Validation | Batch 550/1463 | Loss: 0.8650 | LM_LOSS: 0.3634 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:43] Validation | Batch 560/1463 | Loss: 0.8650 | LM_LOSS: 0.3634 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:45] Validation | Batch 570/1463 | Loss: 0.8650 | LM_LOSS: 0.3634 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:47] Validation | Batch 580/1463 | Loss: 0.8644 | LM_LOSS: 0.3628 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:50] Validation | Batch 590/1463 | Loss: 0.8642 | LM_LOSS: 0.3625 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:52] Validation | Batch 600/1463 | Loss: 0.8643 | LM_LOSS: 0.3627 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:54] Validation | Batch 610/1463 | Loss: 0.8646 | LM_LOSS: 0.3629 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:57] Validation | Batch 620/1463 | Loss: 0.8639 | LM_LOSS: 0.3622 | LB_LOSS: 1.0033 |
| [2026-05-24 05:23:59] Validation | Batch 630/1463 | Loss: 0.8634 | LM_LOSS: 0.3618 | LB_LOSS: 1.0033 |
| [2026-05-24 05:24:01] Validation | Batch 640/1463 | Loss: 0.8632 | LM_LOSS: 0.3615 | LB_LOSS: 1.0034 |
| [2026-05-24 05:24:02] Validation | Batch 650/1463 | Loss: 0.8627 | LM_LOSS: 0.3611 | LB_LOSS: 1.0034 |
| [2026-05-24 05:24:04] Validation | Batch 660/1463 | Loss: 0.8621 | LM_LOSS: 0.3605 | LB_LOSS: 1.0033 |
| [2026-05-24 05:24:06] Validation | Batch 670/1463 | Loss: 0.8616 | LM_LOSS: 0.3599 | LB_LOSS: 1.0033 |
| [2026-05-24 05:24:08] Validation | Batch 680/1463 | Loss: 0.8615 | LM_LOSS: 0.3598 | LB_LOSS: 1.0033 |
| [2026-05-24 05:24:11] Validation | Batch 690/1463 | Loss: 0.8617 | LM_LOSS: 0.3601 | LB_LOSS: 1.0033 |
| [2026-05-24 05:24:13] Validation | Batch 700/1463 | Loss: 0.8617 | LM_LOSS: 0.3600 | LB_LOSS: 1.0033 |
| [2026-05-24 05:24:14] Validation | Batch 710/1463 | Loss: 0.8619 | LM_LOSS: 0.3602 | LB_LOSS: 1.0033 |
| [2026-05-24 05:24:17] Validation | Batch 720/1463 | Loss: 0.8627 | LM_LOSS: 0.3610 | LB_LOSS: 1.0034 |
| [2026-05-24 05:24:19] Validation | Batch 730/1463 | Loss: 0.8626 | LM_LOSS: 0.3610 | LB_LOSS: 1.0034 |
| [2026-05-24 05:24:20] Validation | Batch 740/1463 | Loss: 0.8622 | LM_LOSS: 0.3605 | LB_LOSS: 1.0034 |
| [2026-05-24 05:24:22] Validation | Batch 750/1463 | Loss: 0.8621 | LM_LOSS: 0.3604 | LB_LOSS: 1.0034 |
| [2026-05-24 05:24:24] Validation | Batch 760/1463 | Loss: 0.8618 | LM_LOSS: 0.3602 | LB_LOSS: 1.0034 |
| [2026-05-24 05:24:26] Validation | Batch 770/1463 | Loss: 0.8617 | LM_LOSS: 0.3600 | LB_LOSS: 1.0034 |
| [2026-05-24 05:24:28] Validation | Batch 780/1463 | Loss: 0.8617 | LM_LOSS: 0.3600 | LB_LOSS: 1.0034 |
| [2026-05-24 05:24:29] Validation | Batch 790/1463 | Loss: 0.8619 | LM_LOSS: 0.3602 | LB_LOSS: 1.0034 |
| [2026-05-24 05:24:31] Validation | Batch 800/1463 | Loss: 0.8619 | LM_LOSS: 0.3602 | LB_LOSS: 1.0034 |
| [2026-05-24 05:24:33] Validation | Batch 810/1463 | Loss: 0.8614 | LM_LOSS: 0.3598 | LB_LOSS: 1.0033 |
| [2026-05-24 05:24:35] Validation | Batch 820/1463 | Loss: 0.8617 | LM_LOSS: 0.3600 | LB_LOSS: 1.0033 |
| [2026-05-24 05:24:37] Validation | Batch 830/1463 | Loss: 0.8620 | LM_LOSS: 0.3603 | LB_LOSS: 1.0033 |
| [2026-05-24 05:24:40] Validation | Batch 840/1463 | Loss: 0.8619 | LM_LOSS: 0.3603 | LB_LOSS: 1.0033 |
| [2026-05-24 05:24:42] Validation | Batch 850/1463 | Loss: 0.8623 | LM_LOSS: 0.3607 | LB_LOSS: 1.0033 |
| [2026-05-24 05:24:44] Validation | Batch 860/1463 | Loss: 0.8626 | LM_LOSS: 0.3609 | LB_LOSS: 1.0033 |
| [2026-05-24 05:24:46] Validation | Batch 870/1463 | Loss: 0.8628 | LM_LOSS: 0.3611 | LB_LOSS: 1.0034 |
| [2026-05-24 05:24:48] Validation | Batch 880/1463 | Loss: 0.8620 | LM_LOSS: 0.3603 | LB_LOSS: 1.0034 |
| [2026-05-24 05:24:50] Validation | Batch 890/1463 | Loss: 0.8620 | LM_LOSS: 0.3603 | LB_LOSS: 1.0033 |
| [2026-05-24 05:24:52] Validation | Batch 900/1463 | Loss: 0.8616 | LM_LOSS: 0.3599 | LB_LOSS: 1.0033 |
| [2026-05-24 05:24:54] Validation | Batch 910/1463 | Loss: 0.8615 | LM_LOSS: 0.3599 | LB_LOSS: 1.0033 |
| [2026-05-24 05:24:57] Validation | Batch 920/1463 | Loss: 0.8618 | LM_LOSS: 0.3601 | LB_LOSS: 1.0033 |
| [2026-05-24 05:24:59] Validation | Batch 930/1463 | Loss: 0.8613 | LM_LOSS: 0.3596 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:01] Validation | Batch 940/1463 | Loss: 0.8610 | LM_LOSS: 0.3593 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:03] Validation | Batch 950/1463 | Loss: 0.8612 | LM_LOSS: 0.3596 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:05] Validation | Batch 960/1463 | Loss: 0.8612 | LM_LOSS: 0.3596 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:08] Validation | Batch 970/1463 | Loss: 0.8613 | LM_LOSS: 0.3596 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:10] Validation | Batch 980/1463 | Loss: 0.8617 | LM_LOSS: 0.3600 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:12] Validation | Batch 990/1463 | Loss: 0.8619 | LM_LOSS: 0.3602 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:14] Validation | Batch 1000/1463 | Loss: 0.8626 | LM_LOSS: 0.3609 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:16] Validation | Batch 1010/1463 | Loss: 0.8626 | LM_LOSS: 0.3610 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:18] Validation | Batch 1020/1463 | Loss: 0.8627 | LM_LOSS: 0.3610 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:21] Validation | Batch 1030/1463 | Loss: 0.8633 | LM_LOSS: 0.3616 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:23] Validation | Batch 1040/1463 | Loss: 0.8628 | LM_LOSS: 0.3612 | LB_LOSS: 1.0034 |
| [2026-05-24 05:25:25] Validation | Batch 1050/1463 | Loss: 0.8627 | LM_LOSS: 0.3610 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:27] Validation | Batch 1060/1463 | Loss: 0.8626 | LM_LOSS: 0.3610 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:30] Validation | Batch 1070/1463 | Loss: 0.8626 | LM_LOSS: 0.3609 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:32] Validation | Batch 1080/1463 | Loss: 0.8624 | LM_LOSS: 0.3607 | LB_LOSS: 1.0034 |
| [2026-05-24 05:25:33] Validation | Batch 1090/1463 | Loss: 0.8623 | LM_LOSS: 0.3606 | LB_LOSS: 1.0034 |
| [2026-05-24 05:25:35] Validation | Batch 1100/1463 | Loss: 0.8621 | LM_LOSS: 0.3604 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:37] Validation | Batch 1110/1463 | Loss: 0.8621 | LM_LOSS: 0.3605 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:39] Validation | Batch 1120/1463 | Loss: 0.8619 | LM_LOSS: 0.3603 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:42] Validation | Batch 1130/1463 | Loss: 0.8617 | LM_LOSS: 0.3600 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:44] Validation | Batch 1140/1463 | Loss: 0.8619 | LM_LOSS: 0.3603 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:46] Validation | Batch 1150/1463 | Loss: 0.8618 | LM_LOSS: 0.3602 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:48] Validation | Batch 1160/1463 | Loss: 0.8617 | LM_LOSS: 0.3601 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:51] Validation | Batch 1170/1463 | Loss: 0.8617 | LM_LOSS: 0.3601 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:53] Validation | Batch 1180/1463 | Loss: 0.8619 | LM_LOSS: 0.3602 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:55] Validation | Batch 1190/1463 | Loss: 0.8620 | LM_LOSS: 0.3604 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:57] Validation | Batch 1200/1463 | Loss: 0.8620 | LM_LOSS: 0.3603 | LB_LOSS: 1.0033 |
| [2026-05-24 05:25:59] Validation | Batch 1210/1463 | Loss: 0.8622 | LM_LOSS: 0.3606 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:01] Validation | Batch 1220/1463 | Loss: 0.8626 | LM_LOSS: 0.3610 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:03] Validation | Batch 1230/1463 | Loss: 0.8625 | LM_LOSS: 0.3609 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:05] Validation | Batch 1240/1463 | Loss: 0.8628 | LM_LOSS: 0.3611 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:07] Validation | Batch 1250/1463 | Loss: 0.8630 | LM_LOSS: 0.3614 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:10] Validation | Batch 1260/1463 | Loss: 0.8629 | LM_LOSS: 0.3612 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:12] Validation | Batch 1270/1463 | Loss: 0.8626 | LM_LOSS: 0.3609 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:14] Validation | Batch 1280/1463 | Loss: 0.8624 | LM_LOSS: 0.3607 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:16] Validation | Batch 1290/1463 | Loss: 0.8623 | LM_LOSS: 0.3606 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:18] Validation | Batch 1300/1463 | Loss: 0.8621 | LM_LOSS: 0.3604 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:21] Validation | Batch 1310/1463 | Loss: 0.8619 | LM_LOSS: 0.3603 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:22] Validation | Batch 1320/1463 | Loss: 0.8619 | LM_LOSS: 0.3603 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:24] Validation | Batch 1330/1463 | Loss: 0.8620 | LM_LOSS: 0.3603 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:26] Validation | Batch 1340/1463 | Loss: 0.8624 | LM_LOSS: 0.3607 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:28] Validation | Batch 1350/1463 | Loss: 0.8624 | LM_LOSS: 0.3607 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:31] Validation | Batch 1360/1463 | Loss: 0.8626 | LM_LOSS: 0.3610 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:33] Validation | Batch 1370/1463 | Loss: 0.8630 | LM_LOSS: 0.3614 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:35] Validation | Batch 1380/1463 | Loss: 0.8627 | LM_LOSS: 0.3610 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:37] Validation | Batch 1390/1463 | Loss: 0.8627 | LM_LOSS: 0.3610 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:39] Validation | Batch 1400/1463 | Loss: 0.8630 | LM_LOSS: 0.3613 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:41] Validation | Batch 1410/1463 | Loss: 0.8633 | LM_LOSS: 0.3616 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:43] Validation | Batch 1420/1463 | Loss: 0.8633 | LM_LOSS: 0.3616 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:45] Validation | Batch 1430/1463 | Loss: 0.8632 | LM_LOSS: 0.3616 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:47] Validation | Batch 1440/1463 | Loss: 0.8637 | LM_LOSS: 0.3620 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:50] Validation | Batch 1450/1463 | Loss: 0.8634 | LM_LOSS: 0.3617 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:52] Validation | Batch 1460/1463 | Loss: 0.8638 | LM_LOSS: 0.3621 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:53] Validation | Batch 1463/1463 | Loss: 0.8637 | LM_LOSS: 0.3620 | LB_LOSS: 1.0033 |
| [2026-05-24 05:26:53] Validation | Loss: 0.8637 | LM_LOSS: 0.3620 | LB_LOSS: 1.0033 | PPL: 1.44 | Time: 308.37s |
| [2026-05-24 05:27:04] Epoch 3 | Step 13010 | Loss: 0.6708 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.77e-05 |
| [2026-05-24 05:27:15] Epoch 3 | Step 13020 | Loss: 0.6708 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.72e-05 |
| [2026-05-24 05:27:26] Epoch 3 | Step 13030 | Loss: 0.6708 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.67e-05 |
| [2026-05-24 05:27:37] Epoch 3 | Step 13040 | Loss: 0.6708 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.63e-05 |
| [2026-05-24 05:27:49] Epoch 3 | Step 13050 | Loss: 0.6707 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.58e-05 |
| [2026-05-24 05:27:59] Epoch 3 | Step 13060 | Loss: 0.6707 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.54e-05 |
| [2026-05-24 05:28:10] Epoch 3 | Step 13070 | Loss: 0.6707 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.49e-05 |
| [2026-05-24 05:28:21] Epoch 3 | Step 13080 | Loss: 0.6706 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.45e-05 |
| [2026-05-24 05:28:32] Epoch 3 | Step 13090 | Loss: 0.6707 | LM: 0.1692 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.40e-05 |
| [2026-05-24 05:28:43] Epoch 3 | Step 13100 | Loss: 0.6707 | LM: 0.1692 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.36e-05 |
| [2026-05-24 05:28:54] Epoch 3 | Step 13110 | Loss: 0.6707 | LM: 0.1693 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.31e-05 |
| [2026-05-24 05:29:06] Epoch 3 | Step 13120 | Loss: 0.6706 | LM: 0.1692 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.27e-05 |
| [2026-05-24 05:29:17] Epoch 3 | Step 13130 | Loss: 0.6706 | LM: 0.1692 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.23e-05 |
| [2026-05-24 05:29:28] Epoch 3 | Step 13140 | Loss: 0.6706 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.18e-05 |
| [2026-05-24 05:29:39] Epoch 3 | Step 13150 | Loss: 0.6706 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.14e-05 |
| [2026-05-24 05:29:50] Epoch 3 | Step 13160 | Loss: 0.6706 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.10e-05 |
| [2026-05-24 05:30:01] Epoch 3 | Step 13170 | Loss: 0.6705 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.06e-05 |
| [2026-05-24 05:30:12] Epoch 3 | Step 13180 | Loss: 0.6705 | LM: 0.1692 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 3.01e-05 |
| [2026-05-24 05:30:24] Epoch 3 | Step 13190 | Loss: 0.6705 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.97e-05 |
| [2026-05-24 05:30:35] Epoch 3 | Step 13200 | Loss: 0.6705 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.93e-05 |
| [2026-05-24 05:30:46] Epoch 3 | Step 13210 | Loss: 0.6705 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.89e-05 |
| [2026-05-24 05:30:57] Epoch 3 | Step 13220 | Loss: 0.6705 | LM: 0.1692 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.85e-05 |
| [2026-05-24 05:31:08] Epoch 3 | Step 13230 | Loss: 0.6706 | LM: 0.1692 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.81e-05 |
| [2026-05-24 05:31:19] Epoch 3 | Step 13240 | Loss: 0.6705 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.77e-05 |
| [2026-05-24 05:31:30] Epoch 3 | Step 13250 | Loss: 0.6705 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.73e-05 |
| [2026-05-24 05:31:41] Epoch 3 | Step 13260 | Loss: 0.6705 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.69e-05 |
| [2026-05-24 05:31:53] Epoch 3 | Step 13270 | Loss: 0.6705 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.65e-05 |
| [2026-05-24 05:32:05] Epoch 3 | Step 13280 | Loss: 0.6704 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.61e-05 |
| [2026-05-24 05:32:16] Epoch 3 | Step 13290 | Loss: 0.6704 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.57e-05 |
| [2026-05-24 05:32:27] Epoch 3 | Step 13300 | Loss: 0.6705 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.53e-05 |
| [2026-05-24 05:32:38] Epoch 3 | Step 13310 | Loss: 0.6705 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.50e-05 |
| [2026-05-24 05:32:49] Epoch 3 | Step 13320 | Loss: 0.6705 | LM: 0.1689 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.46e-05 |
| [2026-05-24 05:33:00] Epoch 3 | Step 13330 | Loss: 0.6705 | LM: 0.1689 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.42e-05 |
| [2026-05-24 05:33:11] Epoch 3 | Step 13340 | Loss: 0.6705 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.39e-05 |
| [2026-05-24 05:33:22] Epoch 3 | Step 13350 | Loss: 0.6705 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.35e-05 |
| [2026-05-24 05:33:33] Epoch 3 | Step 13360 | Loss: 0.6705 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.31e-05 |
| [2026-05-24 05:33:44] Epoch 3 | Step 13370 | Loss: 0.6704 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.28e-05 |
| [2026-05-24 05:33:55] Epoch 3 | Step 13380 | Loss: 0.6705 | LM: 0.1692 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.24e-05 |
| [2026-05-24 05:34:06] Epoch 3 | Step 13390 | Loss: 0.6704 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.21e-05 |
| [2026-05-24 05:34:17] Epoch 3 | Step 13400 | Loss: 0.6705 | LM: 0.1690 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.18e-05 |
| [2026-05-24 05:34:28] Epoch 3 | Step 13410 | Loss: 0.6706 | LM: 0.1692 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.14e-05 |
| [2026-05-24 05:34:39] Epoch 3 | Step 13420 | Loss: 0.6706 | LM: 0.1691 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.11e-05 |
| [2026-05-24 05:34:51] Epoch 3 | Step 13430 | Loss: 0.6705 | LM: 0.1691 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.08e-05 |
| [2026-05-24 05:35:02] Epoch 3 | Step 13440 | Loss: 0.6705 | LM: 0.1690 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.04e-05 |
| [2026-05-24 05:35:13] Epoch 3 | Step 13450 | Loss: 0.6705 | LM: 0.1691 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 2.01e-05 |
| [2026-05-24 05:35:24] Epoch 3 | Step 13460 | Loss: 0.6705 | LM: 0.1690 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.98e-05 |
| [2026-05-24 05:35:35] Epoch 3 | Step 13470 | Loss: 0.6705 | LM: 0.1691 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.95e-05 |
| [2026-05-24 05:35:46] Epoch 3 | Step 13480 | Loss: 0.6705 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.92e-05 |
| [2026-05-24 05:35:57] Epoch 3 | Step 13490 | Loss: 0.6705 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.89e-05 |
| [2026-05-24 05:36:08] Epoch 3 | Step 13500 | Loss: 0.6705 | LM: 0.1691 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.86e-05 |
| [2026-05-24 05:36:19] Epoch 3 | Step 13510 | Loss: 0.6706 | LM: 0.1691 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.83e-05 |
| [2026-05-24 05:36:30] Epoch 3 | Step 13520 | Loss: 0.6706 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.80e-05 |
| [2026-05-24 05:36:41] Epoch 3 | Step 13530 | Loss: 0.6706 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.77e-05 |
| [2026-05-24 05:36:53] Epoch 3 | Step 13540 | Loss: 0.6706 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.74e-05 |
| [2026-05-24 05:37:04] Epoch 3 | Step 13550 | Loss: 0.6706 | LM: 0.1692 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.72e-05 |
| [2026-05-24 05:37:15] Epoch 3 | Step 13560 | Loss: 0.6707 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.69e-05 |
| [2026-05-24 05:37:27] Epoch 3 | Step 13570 | Loss: 0.6706 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.66e-05 |
| [2026-05-24 05:37:38] Epoch 3 | Step 13580 | Loss: 0.6706 | LM: 0.1690 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.64e-05 |
| [2026-05-24 05:37:50] Epoch 3 | Step 13590 | Loss: 0.6706 | LM: 0.1691 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.61e-05 |
| [2026-05-24 05:38:01] Epoch 3 | Step 13600 | Loss: 0.6706 | LM: 0.1691 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.59e-05 |
| [2026-05-24 05:38:12] Epoch 3 | Step 13610 | Loss: 0.6706 | LM: 0.1690 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.56e-05 |
| [2026-05-24 05:38:24] Epoch 3 | Step 13620 | Loss: 0.6707 | LM: 0.1690 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.54e-05 |
| [2026-05-24 05:38:35] Epoch 3 | Step 13630 | Loss: 0.6707 | LM: 0.1690 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.51e-05 |
| [2026-05-24 05:38:46] Epoch 3 | Step 13640 | Loss: 0.6706 | LM: 0.1690 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.49e-05 |
| [2026-05-24 05:38:58] Epoch 3 | Step 13650 | Loss: 0.6706 | LM: 0.1689 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.47e-05 |
| [2026-05-24 05:39:09] Epoch 3 | Step 13660 | Loss: 0.6706 | LM: 0.1689 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.45e-05 |
| [2026-05-24 05:39:21] Epoch 3 | Step 13670 | Loss: 0.6706 | LM: 0.1689 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.42e-05 |
| [2026-05-24 05:39:32] Epoch 3 | Step 13680 | Loss: 0.6707 | LM: 0.1690 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.40e-05 |
| [2026-05-24 05:39:44] Epoch 3 | Step 13690 | Loss: 0.6706 | LM: 0.1689 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.38e-05 |
| [2026-05-24 05:39:56] Epoch 3 | Step 13700 | Loss: 0.6706 | LM: 0.1690 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.36e-05 |
| [2026-05-24 05:40:08] Epoch 3 | Step 13710 | Loss: 0.6706 | LM: 0.1689 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.34e-05 |
| [2026-05-24 05:40:19] Epoch 3 | Step 13720 | Loss: 0.6706 | LM: 0.1690 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.32e-05 |
| [2026-05-24 05:40:31] Epoch 3 | Step 13730 | Loss: 0.6705 | LM: 0.1690 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.31e-05 |
| [2026-05-24 05:40:43] Epoch 3 | Step 13740 | Loss: 0.6706 | LM: 0.1690 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.29e-05 |
| [2026-05-24 05:40:55] Epoch 3 | Step 13750 | Loss: 0.6705 | LM: 0.1689 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.27e-05 |
| [2026-05-24 05:41:06] Epoch 3 | Step 13760 | Loss: 0.6705 | LM: 0.1689 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.25e-05 |
| [2026-05-24 05:41:18] Epoch 3 | Step 13770 | Loss: 0.6706 | LM: 0.1690 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.24e-05 |
| [2026-05-24 05:41:30] Epoch 3 | Step 13780 | Loss: 0.6705 | LM: 0.1691 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.22e-05 |
| [2026-05-24 05:41:41] Epoch 3 | Step 13790 | Loss: 0.6706 | LM: 0.1691 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.21e-05 |
| [2026-05-24 05:41:53] Epoch 3 | Step 13800 | Loss: 0.6705 | LM: 0.1691 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.19e-05 |
| [2026-05-24 05:42:04] Epoch 3 | Step 13810 | Loss: 0.6705 | LM: 0.1691 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.18e-05 |
| [2026-05-24 05:42:17] Epoch 3 | Step 13820 | Loss: 0.6705 | LM: 0.1692 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.16e-05 |
| [2026-05-24 05:42:28] Epoch 3 | Step 13830 | Loss: 0.6706 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.15e-05 |
| [2026-05-24 05:42:40] Epoch 3 | Step 13840 | Loss: 0.6705 | LM: 0.1692 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.14e-05 |
| [2026-05-24 05:42:51] Epoch 3 | Step 13850 | Loss: 0.6705 | LM: 0.1692 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.13e-05 |
| [2026-05-24 05:43:02] Epoch 3 | Step 13860 | Loss: 0.6704 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.11e-05 |
| [2026-05-24 05:43:14] Epoch 3 | Step 13870 | Loss: 0.6704 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.10e-05 |
| [2026-05-24 05:43:25] Epoch 3 | Step 13880 | Loss: 0.6704 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.09e-05 |
| [2026-05-24 05:43:37] Epoch 3 | Step 13890 | Loss: 0.6704 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.08e-05 |
| [2026-05-24 05:43:48] Epoch 3 | Step 13900 | Loss: 0.6703 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.07e-05 |
| [2026-05-24 05:44:00] Epoch 3 | Step 13910 | Loss: 0.6703 | LM: 0.1691 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.06e-05 |
| [2026-05-24 05:44:12] Epoch 3 | Step 13920 | Loss: 0.6703 | LM: 0.1691 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.06e-05 |
| [2026-05-24 05:44:23] Epoch 3 | Step 13930 | Loss: 0.6703 | LM: 0.1691 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.05e-05 |
| [2026-05-24 05:44:35] Epoch 3 | Step 13940 | Loss: 0.6703 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.04e-05 |
| [2026-05-24 05:44:46] Epoch 3 | Step 13950 | Loss: 0.6703 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.04e-05 |
| [2026-05-24 05:44:58] Epoch 3 | Step 13960 | Loss: 0.6703 | LM: 0.1690 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.03e-05 |
| [2026-05-24 05:45:09] Epoch 3 | Step 13970 | Loss: 0.6703 | LM: 0.1689 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.02e-05 |
| [2026-05-24 05:45:21] Epoch 3 | Step 13980 | Loss: 0.6703 | LM: 0.1688 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.02e-05 |
| [2026-05-24 05:45:32] Epoch 3 | Step 13990 | Loss: 0.6703 | LM: 0.1688 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.01e-05 |
| [2026-05-24 05:45:43] Epoch 3 | Step 14000 | Loss: 0.6703 | LM: 0.1688 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.01e-05 |
| [2026-05-24 05:45:45] Validation | Batch 10/1463 | Loss: 0.8359 | LM_LOSS: 0.3351 | LB_LOSS: 1.0016 |
| [2026-05-24 05:45:47] Validation | Batch 20/1463 | Loss: 0.8442 | LM_LOSS: 0.3430 | LB_LOSS: 1.0025 |
| [2026-05-24 05:45:49] Validation | Batch 30/1463 | Loss: 0.8421 | LM_LOSS: 0.3407 | LB_LOSS: 1.0029 |
| [2026-05-24 05:45:51] Validation | Batch 40/1463 | Loss: 0.8497 | LM_LOSS: 0.3481 | LB_LOSS: 1.0032 |
| [2026-05-24 05:45:53] Validation | Batch 50/1463 | Loss: 0.8599 | LM_LOSS: 0.3584 | LB_LOSS: 1.0030 |
| [2026-05-24 05:45:56] Validation | Batch 60/1463 | Loss: 0.8596 | LM_LOSS: 0.3581 | LB_LOSS: 1.0029 |
| [2026-05-24 05:45:59] Validation | Batch 70/1463 | Loss: 0.8598 | LM_LOSS: 0.3583 | LB_LOSS: 1.0030 |
| [2026-05-24 05:46:01] Validation | Batch 80/1463 | Loss: 0.8629 | LM_LOSS: 0.3614 | LB_LOSS: 1.0030 |
| [2026-05-24 05:46:03] Validation | Batch 90/1463 | Loss: 0.8622 | LM_LOSS: 0.3608 | LB_LOSS: 1.0029 |
| [2026-05-24 05:46:05] Validation | Batch 100/1463 | Loss: 0.8618 | LM_LOSS: 0.3604 | LB_LOSS: 1.0029 |
| [2026-05-24 05:46:07] Validation | Batch 110/1463 | Loss: 0.8600 | LM_LOSS: 0.3585 | LB_LOSS: 1.0030 |
| [2026-05-24 05:46:09] Validation | Batch 120/1463 | Loss: 0.8630 | LM_LOSS: 0.3614 | LB_LOSS: 1.0031 |
| [2026-05-24 05:46:11] Validation | Batch 130/1463 | Loss: 0.8653 | LM_LOSS: 0.3637 | LB_LOSS: 1.0032 |
| [2026-05-24 05:46:13] Validation | Batch 140/1463 | Loss: 0.8667 | LM_LOSS: 0.3652 | LB_LOSS: 1.0031 |
| [2026-05-24 05:46:16] Validation | Batch 150/1463 | Loss: 0.8644 | LM_LOSS: 0.3627 | LB_LOSS: 1.0032 |
| [2026-05-24 05:46:18] Validation | Batch 160/1463 | Loss: 0.8644 | LM_LOSS: 0.3628 | LB_LOSS: 1.0032 |
| [2026-05-24 05:46:20] Validation | Batch 170/1463 | Loss: 0.8631 | LM_LOSS: 0.3615 | LB_LOSS: 1.0032 |
| [2026-05-24 05:46:22] Validation | Batch 180/1463 | Loss: 0.8635 | LM_LOSS: 0.3619 | LB_LOSS: 1.0032 |
| [2026-05-24 05:46:24] Validation | Batch 190/1463 | Loss: 0.8651 | LM_LOSS: 0.3635 | LB_LOSS: 1.0032 |
| [2026-05-24 05:46:27] Validation | Batch 200/1463 | Loss: 0.8649 | LM_LOSS: 0.3633 | LB_LOSS: 1.0032 |
| [2026-05-24 05:46:29] Validation | Batch 210/1463 | Loss: 0.8654 | LM_LOSS: 0.3638 | LB_LOSS: 1.0032 |
| [2026-05-24 05:46:31] Validation | Batch 220/1463 | Loss: 0.8647 | LM_LOSS: 0.3631 | LB_LOSS: 1.0032 |
| [2026-05-24 05:46:33] Validation | Batch 230/1463 | Loss: 0.8663 | LM_LOSS: 0.3648 | LB_LOSS: 1.0031 |
| [2026-05-24 05:46:35] Validation | Batch 240/1463 | Loss: 0.8678 | LM_LOSS: 0.3663 | LB_LOSS: 1.0031 |
| [2026-05-24 05:46:38] Validation | Batch 250/1463 | Loss: 0.8670 | LM_LOSS: 0.3655 | LB_LOSS: 1.0031 |
| [2026-05-24 05:46:40] Validation | Batch 260/1463 | Loss: 0.8689 | LM_LOSS: 0.3673 | LB_LOSS: 1.0032 |
| [2026-05-24 05:46:42] Validation | Batch 270/1463 | Loss: 0.8667 | LM_LOSS: 0.3651 | LB_LOSS: 1.0032 |
| [2026-05-24 05:46:44] Validation | Batch 280/1463 | Loss: 0.8673 | LM_LOSS: 0.3657 | LB_LOSS: 1.0033 |
| [2026-05-24 05:46:46] Validation | Batch 290/1463 | Loss: 0.8663 | LM_LOSS: 0.3647 | LB_LOSS: 1.0033 |
| [2026-05-24 05:46:48] Validation | Batch 300/1463 | Loss: 0.8670 | LM_LOSS: 0.3654 | LB_LOSS: 1.0033 |
| [2026-05-24 05:46:50] Validation | Batch 310/1463 | Loss: 0.8679 | LM_LOSS: 0.3662 | LB_LOSS: 1.0033 |
| [2026-05-24 05:46:52] Validation | Batch 320/1463 | Loss: 0.8666 | LM_LOSS: 0.3650 | LB_LOSS: 1.0032 |
| [2026-05-24 05:46:54] Validation | Batch 330/1463 | Loss: 0.8664 | LM_LOSS: 0.3648 | LB_LOSS: 1.0032 |
| [2026-05-24 05:46:56] Validation | Batch 340/1463 | Loss: 0.8660 | LM_LOSS: 0.3644 | LB_LOSS: 1.0032 |
| [2026-05-24 05:46:59] Validation | Batch 350/1463 | Loss: 0.8666 | LM_LOSS: 0.3650 | LB_LOSS: 1.0032 |
| [2026-05-24 05:47:01] Validation | Batch 360/1463 | Loss: 0.8663 | LM_LOSS: 0.3647 | LB_LOSS: 1.0032 |
| [2026-05-24 05:47:02] Validation | Batch 370/1463 | Loss: 0.8659 | LM_LOSS: 0.3643 | LB_LOSS: 1.0032 |
| [2026-05-24 05:47:04] Validation | Batch 380/1463 | Loss: 0.8654 | LM_LOSS: 0.3638 | LB_LOSS: 1.0032 |
| [2026-05-24 05:47:07] Validation | Batch 390/1463 | Loss: 0.8659 | LM_LOSS: 0.3643 | LB_LOSS: 1.0032 |
| [2026-05-24 05:47:09] Validation | Batch 400/1463 | Loss: 0.8658 | LM_LOSS: 0.3642 | LB_LOSS: 1.0032 |
| [2026-05-24 05:47:11] Validation | Batch 410/1463 | Loss: 0.8654 | LM_LOSS: 0.3637 | LB_LOSS: 1.0032 |
| [2026-05-24 05:47:13] Validation | Batch 420/1463 | Loss: 0.8653 | LM_LOSS: 0.3637 | LB_LOSS: 1.0033 |
| [2026-05-24 05:47:15] Validation | Batch 430/1463 | Loss: 0.8646 | LM_LOSS: 0.3629 | LB_LOSS: 1.0033 |
| [2026-05-24 05:47:17] Validation | Batch 440/1463 | Loss: 0.8650 | LM_LOSS: 0.3633 | LB_LOSS: 1.0033 |
| [2026-05-24 05:47:19] Validation | Batch 450/1463 | Loss: 0.8645 | LM_LOSS: 0.3629 | LB_LOSS: 1.0033 |
| [2026-05-24 05:47:21] Validation | Batch 460/1463 | Loss: 0.8643 | LM_LOSS: 0.3626 | LB_LOSS: 1.0033 |
| [2026-05-24 05:47:24] Validation | Batch 470/1463 | Loss: 0.8650 | LM_LOSS: 0.3634 | LB_LOSS: 1.0033 |
| [2026-05-24 05:47:26] Validation | Batch 480/1463 | Loss: 0.8647 | LM_LOSS: 0.3631 | LB_LOSS: 1.0032 |
| [2026-05-24 05:47:28] Validation | Batch 490/1463 | Loss: 0.8644 | LM_LOSS: 0.3628 | LB_LOSS: 1.0032 |
| [2026-05-24 05:47:31] Validation | Batch 500/1463 | Loss: 0.8641 | LM_LOSS: 0.3625 | LB_LOSS: 1.0032 |
| [2026-05-24 05:47:33] Validation | Batch 510/1463 | Loss: 0.8634 | LM_LOSS: 0.3617 | LB_LOSS: 1.0032 |
| [2026-05-24 05:47:35] Validation | Batch 520/1463 | Loss: 0.8631 | LM_LOSS: 0.3615 | LB_LOSS: 1.0033 |
| [2026-05-24 05:47:37] Validation | Batch 530/1463 | Loss: 0.8638 | LM_LOSS: 0.3622 | LB_LOSS: 1.0032 |
| [2026-05-24 05:47:39] Validation | Batch 540/1463 | Loss: 0.8640 | LM_LOSS: 0.3623 | LB_LOSS: 1.0033 |
| [2026-05-24 05:47:40] Validation | Batch 550/1463 | Loss: 0.8635 | LM_LOSS: 0.3619 | LB_LOSS: 1.0033 |
| [2026-05-24 05:47:42] Validation | Batch 560/1463 | Loss: 0.8636 | LM_LOSS: 0.3619 | LB_LOSS: 1.0033 |
| [2026-05-24 05:47:45] Validation | Batch 570/1463 | Loss: 0.8636 | LM_LOSS: 0.3619 | LB_LOSS: 1.0033 |
| [2026-05-24 05:47:47] Validation | Batch 580/1463 | Loss: 0.8630 | LM_LOSS: 0.3613 | LB_LOSS: 1.0033 |
| [2026-05-24 05:47:49] Validation | Batch 590/1463 | Loss: 0.8628 | LM_LOSS: 0.3611 | LB_LOSS: 1.0033 |
| [2026-05-24 05:47:52] Validation | Batch 600/1463 | Loss: 0.8629 | LM_LOSS: 0.3613 | LB_LOSS: 1.0033 |
| [2026-05-24 05:47:54] Validation | Batch 610/1463 | Loss: 0.8632 | LM_LOSS: 0.3615 | LB_LOSS: 1.0033 |
| [2026-05-24 05:47:56] Validation | Batch 620/1463 | Loss: 0.8625 | LM_LOSS: 0.3608 | LB_LOSS: 1.0033 |
| [2026-05-24 05:47:58] Validation | Batch 630/1463 | Loss: 0.8620 | LM_LOSS: 0.3604 | LB_LOSS: 1.0033 |
| [2026-05-24 05:48:00] Validation | Batch 640/1463 | Loss: 0.8618 | LM_LOSS: 0.3602 | LB_LOSS: 1.0034 |
| [2026-05-24 05:48:02] Validation | Batch 650/1463 | Loss: 0.8614 | LM_LOSS: 0.3597 | LB_LOSS: 1.0034 |
| [2026-05-24 05:48:04] Validation | Batch 660/1463 | Loss: 0.8608 | LM_LOSS: 0.3591 | LB_LOSS: 1.0033 |
| [2026-05-24 05:48:06] Validation | Batch 670/1463 | Loss: 0.8602 | LM_LOSS: 0.3586 | LB_LOSS: 1.0033 |
| [2026-05-24 05:48:08] Validation | Batch 680/1463 | Loss: 0.8602 | LM_LOSS: 0.3585 | LB_LOSS: 1.0033 |
| [2026-05-24 05:48:10] Validation | Batch 690/1463 | Loss: 0.8604 | LM_LOSS: 0.3588 | LB_LOSS: 1.0033 |
| [2026-05-24 05:48:12] Validation | Batch 700/1463 | Loss: 0.8604 | LM_LOSS: 0.3587 | LB_LOSS: 1.0033 |
| [2026-05-24 05:48:14] Validation | Batch 710/1463 | Loss: 0.8606 | LM_LOSS: 0.3589 | LB_LOSS: 1.0033 |
| [2026-05-24 05:48:16] Validation | Batch 720/1463 | Loss: 0.8614 | LM_LOSS: 0.3597 | LB_LOSS: 1.0034 |
| [2026-05-24 05:48:18] Validation | Batch 730/1463 | Loss: 0.8613 | LM_LOSS: 0.3596 | LB_LOSS: 1.0034 |
| [2026-05-24 05:48:20] Validation | Batch 740/1463 | Loss: 0.8608 | LM_LOSS: 0.3592 | LB_LOSS: 1.0034 |
| [2026-05-24 05:48:22] Validation | Batch 750/1463 | Loss: 0.8608 | LM_LOSS: 0.3591 | LB_LOSS: 1.0034 |
| [2026-05-24 05:48:24] Validation | Batch 760/1463 | Loss: 0.8605 | LM_LOSS: 0.3589 | LB_LOSS: 1.0034 |
| [2026-05-24 05:48:25] Validation | Batch 770/1463 | Loss: 0.8604 | LM_LOSS: 0.3587 | LB_LOSS: 1.0034 |
| [2026-05-24 05:48:27] Validation | Batch 780/1463 | Loss: 0.8604 | LM_LOSS: 0.3587 | LB_LOSS: 1.0034 |
| [2026-05-24 05:48:29] Validation | Batch 790/1463 | Loss: 0.8606 | LM_LOSS: 0.3589 | LB_LOSS: 1.0033 |
| [2026-05-24 05:48:31] Validation | Batch 800/1463 | Loss: 0.8607 | LM_LOSS: 0.3590 | LB_LOSS: 1.0033 |
| [2026-05-24 05:48:33] Validation | Batch 810/1463 | Loss: 0.8602 | LM_LOSS: 0.3585 | LB_LOSS: 1.0033 |
| [2026-05-24 05:48:35] Validation | Batch 820/1463 | Loss: 0.8605 | LM_LOSS: 0.3588 | LB_LOSS: 1.0033 |
| [2026-05-24 05:48:37] Validation | Batch 830/1463 | Loss: 0.8607 | LM_LOSS: 0.3591 | LB_LOSS: 1.0033 |
| [2026-05-24 05:48:39] Validation | Batch 840/1463 | Loss: 0.8607 | LM_LOSS: 0.3590 | LB_LOSS: 1.0033 |
| [2026-05-24 05:48:41] Validation | Batch 850/1463 | Loss: 0.8611 | LM_LOSS: 0.3594 | LB_LOSS: 1.0033 |
| [2026-05-24 05:48:44] Validation | Batch 860/1463 | Loss: 0.8614 | LM_LOSS: 0.3597 | LB_LOSS: 1.0033 |
| [2026-05-24 05:48:46] Validation | Batch 870/1463 | Loss: 0.8616 | LM_LOSS: 0.3599 | LB_LOSS: 1.0034 |
| [2026-05-24 05:48:48] Validation | Batch 880/1463 | Loss: 0.8607 | LM_LOSS: 0.3591 | LB_LOSS: 1.0034 |
| [2026-05-24 05:48:50] Validation | Batch 890/1463 | Loss: 0.8608 | LM_LOSS: 0.3591 | LB_LOSS: 1.0033 |
| [2026-05-24 05:48:52] Validation | Batch 900/1463 | Loss: 0.8604 | LM_LOSS: 0.3587 | LB_LOSS: 1.0033 |
| [2026-05-24 05:48:54] Validation | Batch 910/1463 | Loss: 0.8603 | LM_LOSS: 0.3587 | LB_LOSS: 1.0033 |
| [2026-05-24 05:48:57] Validation | Batch 920/1463 | Loss: 0.8605 | LM_LOSS: 0.3589 | LB_LOSS: 1.0033 |
| [2026-05-24 05:48:59] Validation | Batch 930/1463 | Loss: 0.8601 | LM_LOSS: 0.3584 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:01] Validation | Batch 940/1463 | Loss: 0.8598 | LM_LOSS: 0.3581 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:03] Validation | Batch 950/1463 | Loss: 0.8600 | LM_LOSS: 0.3584 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:05] Validation | Batch 960/1463 | Loss: 0.8600 | LM_LOSS: 0.3583 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:08] Validation | Batch 970/1463 | Loss: 0.8601 | LM_LOSS: 0.3584 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:10] Validation | Batch 980/1463 | Loss: 0.8604 | LM_LOSS: 0.3588 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:12] Validation | Batch 990/1463 | Loss: 0.8607 | LM_LOSS: 0.3590 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:14] Validation | Batch 1000/1463 | Loss: 0.8613 | LM_LOSS: 0.3597 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:16] Validation | Batch 1010/1463 | Loss: 0.8614 | LM_LOSS: 0.3597 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:19] Validation | Batch 1020/1463 | Loss: 0.8615 | LM_LOSS: 0.3598 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:21] Validation | Batch 1030/1463 | Loss: 0.8621 | LM_LOSS: 0.3604 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:23] Validation | Batch 1040/1463 | Loss: 0.8616 | LM_LOSS: 0.3600 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:25] Validation | Batch 1050/1463 | Loss: 0.8615 | LM_LOSS: 0.3598 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:28] Validation | Batch 1060/1463 | Loss: 0.8614 | LM_LOSS: 0.3598 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:30] Validation | Batch 1070/1463 | Loss: 0.8614 | LM_LOSS: 0.3597 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:32] Validation | Batch 1080/1463 | Loss: 0.8612 | LM_LOSS: 0.3595 | LB_LOSS: 1.0034 |
| [2026-05-24 05:49:34] Validation | Batch 1090/1463 | Loss: 0.8611 | LM_LOSS: 0.3594 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:36] Validation | Batch 1100/1463 | Loss: 0.8609 | LM_LOSS: 0.3592 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:37] Validation | Batch 1110/1463 | Loss: 0.8609 | LM_LOSS: 0.3592 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:40] Validation | Batch 1120/1463 | Loss: 0.8607 | LM_LOSS: 0.3590 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:42] Validation | Batch 1130/1463 | Loss: 0.8605 | LM_LOSS: 0.3588 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:44] Validation | Batch 1140/1463 | Loss: 0.8607 | LM_LOSS: 0.3591 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:47] Validation | Batch 1150/1463 | Loss: 0.8606 | LM_LOSS: 0.3590 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:49] Validation | Batch 1160/1463 | Loss: 0.8606 | LM_LOSS: 0.3589 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:51] Validation | Batch 1170/1463 | Loss: 0.8605 | LM_LOSS: 0.3589 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:53] Validation | Batch 1180/1463 | Loss: 0.8607 | LM_LOSS: 0.3590 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:55] Validation | Batch 1190/1463 | Loss: 0.8608 | LM_LOSS: 0.3591 | LB_LOSS: 1.0033 |
| [2026-05-24 05:49:58] Validation | Batch 1200/1463 | Loss: 0.8608 | LM_LOSS: 0.3591 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:00] Validation | Batch 1210/1463 | Loss: 0.8610 | LM_LOSS: 0.3594 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:02] Validation | Batch 1220/1463 | Loss: 0.8614 | LM_LOSS: 0.3598 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:04] Validation | Batch 1230/1463 | Loss: 0.8614 | LM_LOSS: 0.3597 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:06] Validation | Batch 1240/1463 | Loss: 0.8616 | LM_LOSS: 0.3599 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:08] Validation | Batch 1250/1463 | Loss: 0.8618 | LM_LOSS: 0.3602 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:11] Validation | Batch 1260/1463 | Loss: 0.8617 | LM_LOSS: 0.3600 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:13] Validation | Batch 1270/1463 | Loss: 0.8614 | LM_LOSS: 0.3597 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:15] Validation | Batch 1280/1463 | Loss: 0.8611 | LM_LOSS: 0.3595 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:17] Validation | Batch 1290/1463 | Loss: 0.8611 | LM_LOSS: 0.3594 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:19] Validation | Batch 1300/1463 | Loss: 0.8609 | LM_LOSS: 0.3592 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:21] Validation | Batch 1310/1463 | Loss: 0.8607 | LM_LOSS: 0.3591 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:23] Validation | Batch 1320/1463 | Loss: 0.8607 | LM_LOSS: 0.3591 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:25] Validation | Batch 1330/1463 | Loss: 0.8607 | LM_LOSS: 0.3591 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:27] Validation | Batch 1340/1463 | Loss: 0.8611 | LM_LOSS: 0.3595 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:29] Validation | Batch 1350/1463 | Loss: 0.8612 | LM_LOSS: 0.3595 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:32] Validation | Batch 1360/1463 | Loss: 0.8614 | LM_LOSS: 0.3598 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:34] Validation | Batch 1370/1463 | Loss: 0.8618 | LM_LOSS: 0.3602 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:36] Validation | Batch 1380/1463 | Loss: 0.8615 | LM_LOSS: 0.3598 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:38] Validation | Batch 1390/1463 | Loss: 0.8615 | LM_LOSS: 0.3598 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:40] Validation | Batch 1400/1463 | Loss: 0.8618 | LM_LOSS: 0.3602 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:42] Validation | Batch 1410/1463 | Loss: 0.8621 | LM_LOSS: 0.3604 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:44] Validation | Batch 1420/1463 | Loss: 0.8621 | LM_LOSS: 0.3604 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:46] Validation | Batch 1430/1463 | Loss: 0.8621 | LM_LOSS: 0.3604 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:48] Validation | Batch 1440/1463 | Loss: 0.8625 | LM_LOSS: 0.3609 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:51] Validation | Batch 1450/1463 | Loss: 0.8622 | LM_LOSS: 0.3606 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:53] Validation | Batch 1460/1463 | Loss: 0.8626 | LM_LOSS: 0.3609 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:53] Validation | Batch 1463/1463 | Loss: 0.8625 | LM_LOSS: 0.3608 | LB_LOSS: 1.0033 |
| [2026-05-24 05:50:53] Validation | Loss: 0.8625 | LM_LOSS: 0.3608 | LB_LOSS: 1.0033 | PPL: 1.44 | Time: 310.04s |
| [2026-05-24 05:51:04] Epoch 3 | Step 14010 | Loss: 0.6703 | LM: 0.1688 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.01e-05 |
| [2026-05-24 05:51:15] Epoch 3 | Step 14020 | Loss: 0.6703 | LM: 0.1686 | LB: 1.0051 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-05 |
| [2026-05-24 05:51:27] Epoch 3 | Step 14030 | Loss: 0.6704 | LM: 0.1688 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-05 |
| [2026-05-24 05:51:38] Epoch 3 | Step 14040 | Loss: 0.6704 | LM: 0.1687 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-05 |
| [2026-05-24 05:51:51] Epoch 3 | Step 14050 | Loss: 0.6704 | LM: 0.1687 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-05 |
| [2026-05-24 05:52:02] Epoch 3 | Step 14060 | Loss: 0.6704 | LM: 0.1687 | LB: 1.0050 | CL0: 3.3 | CL1: 3.8 | HR0: 0.305/SR0: 0.278 | HR1: 0.267/SR1: 0.228 | LR: 1.00e-05 |
| [2026-05-24 05:52:04] Epoch 3 completed in 6862.48s | Loss: 0.6704 | CL0: 3.3 | CL1: 3.8 |
| [2026-05-24 05:52:04] |
| Training completed! |
| [2026-05-24 05:52:08] Final model: outputs/2026-05-24/N_4.0/model_final.pt |
|
|