| [2026-05-24 05:52:20] CUDA_VISIBLE_DEVICES: 0 |
| [2026-05-24 05:52:20] Number of processes: 1 |
| [2026-05-24 05:52:20] Mixed precision: bf16 |
| [2026-05-24 05:52:20] ============================================================ |
| [2026-05-24 05:52:20] Routing Evolution Experiment | N=6.0 |
| [2026-05-24 05:52:20] ============================================================ |
| [2026-05-24 05:52:20] 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: 6.0 |
| 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_N6.0 |
| entity: null |
| base_url: https://wandb.platun0v.ru |
| local_dir: outputs/2026-05-24/N_6.0 |
| paths: |
| output_dir: outputs/2026-05-24/N_6.0 |
| seed: 42 |
| device: cuda |
|
|
| [2026-05-24 05:52:23] Loading model... |
| [2026-05-24 05:52:29] Loaded pretrained: /workspace/byte-llms-code/hnet_project/checkpoints/hnet_2stage_XL_code.pt |
| [2026-05-24 05:52:29] Applied LR multipliers: [2.0, 1.5, 1.0] |
| [2026-05-24 05:52:29] Warming up model... |
| [2026-05-24 05:53:16] Total params: 1,654,090,112 |
| [2026-05-24 05:53:16] Trainable params: 1,654,090,112 |
| [2026-05-24 05:53:16] Creating dataloaders... |
| [2026-05-24 05:53:16] Train dataset size: 150000 (max_train_samples=150000) | Epochs: 3 |
| [2026-05-24 05:53:16] Max steps: 14062, Steps per epoch: 18750 |
| [2026-05-24 05:53:16] Starting training... |
| [2026-05-24 05:53:16] |
| ============================================================ |
| [2026-05-24 05:53:16] EPOCH 1/3 (step 0) |
| [2026-05-24 05:53:16] ============================================================ |
| [2026-05-24 05:53:53] Epoch 1 | Step 10 | Loss: 1.3463 | LM: 0.6792 | LB: 1.4395 | 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 05:54:06] Epoch 1 | Step 20 | Loss: 1.3415 | LM: 0.6311 | LB: 1.4446 | 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 05:54:19] Epoch 1 | Step 30 | Loss: 1.3289 | LM: 0.6222 | LB: 1.4382 | CL0: 2.9 | CL1: 2.1 | HR0: 0.350/SR0: 0.350 | HR1: 0.473/SR1: 0.450 | LR: 1.19e-05 |
| [2026-05-24 05:54:32] Epoch 1 | Step 40 | Loss: 1.3215 | LM: 0.6124 | LB: 1.4451 | CL0: 2.9 | CL1: 2.1 | HR0: 0.352/SR0: 0.351 | HR1: 0.475/SR1: 0.453 | LR: 1.26e-05 |
| [2026-05-24 05:54:44] Epoch 1 | Step 50 | Loss: 1.3029 | LM: 0.5954 | LB: 1.4406 | CL0: 2.9 | CL1: 2.1 | HR0: 0.352/SR0: 0.351 | HR1: 0.473/SR1: 0.451 | LR: 1.32e-05 |
| [2026-05-24 05:54:57] Epoch 1 | Step 60 | Loss: 1.2810 | LM: 0.5730 | LB: 1.4444 | CL0: 2.9 | CL1: 2.1 | HR0: 0.352/SR0: 0.351 | HR1: 0.475/SR1: 0.452 | LR: 1.38e-05 |
| [2026-05-24 05:55:09] Epoch 1 | Step 70 | Loss: 1.2686 | LM: 0.5541 | LB: 1.4412 | CL0: 2.9 | CL1: 2.1 | HR0: 0.352/SR0: 0.351 | HR1: 0.474/SR1: 0.451 | LR: 1.45e-05 |
| [2026-05-24 05:55:21] Epoch 1 | Step 80 | Loss: 1.2507 | LM: 0.5299 | LB: 1.4415 | CL0: 2.8 | CL1: 2.1 | HR0: 0.353/SR0: 0.352 | HR1: 0.473/SR1: 0.451 | LR: 1.51e-05 |
| [2026-05-24 05:55:33] Epoch 1 | Step 90 | Loss: 1.2416 | LM: 0.5223 | LB: 1.4423 | CL0: 2.8 | CL1: 2.1 | HR0: 0.353/SR0: 0.352 | HR1: 0.474/SR1: 0.451 | LR: 1.58e-05 |
| [2026-05-24 05:55:45] Epoch 1 | Step 100 | Loss: 1.2271 | LM: 0.5095 | LB: 1.4423 | CL0: 2.8 | CL1: 2.1 | HR0: 0.353/SR0: 0.352 | HR1: 0.474/SR1: 0.451 | LR: 1.64e-05 |
| [2026-05-24 05:55:56] Epoch 1 | Step 110 | Loss: 1.2174 | LM: 0.4949 | LB: 1.4419 | CL0: 2.8 | CL1: 2.1 | HR0: 0.354/SR0: 0.353 | HR1: 0.473/SR1: 0.450 | LR: 1.70e-05 |
| [2026-05-24 05:56:09] Epoch 1 | Step 120 | Loss: 1.2075 | LM: 0.4880 | LB: 1.4423 | CL0: 2.8 | CL1: 2.1 | HR0: 0.354/SR0: 0.353 | HR1: 0.473/SR1: 0.450 | LR: 1.77e-05 |
| [2026-05-24 05:56:20] Epoch 1 | Step 130 | Loss: 1.1953 | LM: 0.4759 | LB: 1.4394 | CL0: 2.8 | CL1: 2.1 | HR0: 0.354/SR0: 0.353 | HR1: 0.471/SR1: 0.449 | LR: 1.83e-05 |
| [2026-05-24 05:56:31] Epoch 1 | Step 140 | Loss: 1.1860 | LM: 0.4621 | LB: 1.4378 | CL0: 2.8 | CL1: 2.1 | HR0: 0.355/SR0: 0.354 | HR1: 0.470/SR1: 0.448 | LR: 1.90e-05 |
| [2026-05-24 05:56:42] Epoch 1 | Step 150 | Loss: 1.1762 | LM: 0.4540 | LB: 1.4369 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.354 | HR1: 0.469/SR1: 0.447 | LR: 1.96e-05 |
| [2026-05-24 05:56:54] Epoch 1 | Step 160 | Loss: 1.1696 | LM: 0.4521 | LB: 1.4336 | CL0: 2.8 | CL1: 2.1 | HR0: 0.355/SR0: 0.354 | HR1: 0.468/SR1: 0.446 | LR: 2.02e-05 |
| [2026-05-24 05:57:06] Epoch 1 | Step 170 | Loss: 1.1620 | LM: 0.4458 | LB: 1.4322 | CL0: 2.8 | CL1: 2.1 | HR0: 0.355/SR0: 0.353 | HR1: 0.468/SR1: 0.445 | LR: 2.09e-05 |
| [2026-05-24 05:57:18] Epoch 1 | Step 180 | Loss: 1.1530 | LM: 0.4396 | LB: 1.4283 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.465/SR1: 0.443 | LR: 2.15e-05 |
| [2026-05-24 05:57:29] Epoch 1 | Step 190 | Loss: 1.1471 | LM: 0.4345 | LB: 1.4273 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.354 | HR1: 0.465/SR1: 0.443 | LR: 2.22e-05 |
| [2026-05-24 05:57:40] Epoch 1 | Step 200 | Loss: 1.1421 | LM: 0.4312 | LB: 1.4244 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.353 | HR1: 0.464/SR1: 0.442 | LR: 2.28e-05 |
| [2026-05-24 05:57:51] Epoch 1 | Step 210 | Loss: 1.1361 | LM: 0.4245 | LB: 1.4225 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.353 | HR1: 0.463/SR1: 0.441 | LR: 2.34e-05 |
| [2026-05-24 05:58:02] Epoch 1 | Step 220 | Loss: 1.1320 | LM: 0.4228 | LB: 1.4207 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.462/SR1: 0.440 | LR: 2.41e-05 |
| [2026-05-24 05:58:14] Epoch 1 | Step 230 | Loss: 1.1257 | LM: 0.4186 | LB: 1.4186 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.461/SR1: 0.439 | LR: 2.47e-05 |
| [2026-05-24 05:58:25] Epoch 1 | Step 240 | Loss: 1.1218 | LM: 0.4178 | LB: 1.4166 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.460/SR1: 0.438 | LR: 2.54e-05 |
| [2026-05-24 05:58:35] Epoch 1 | Step 250 | Loss: 1.1163 | LM: 0.4140 | LB: 1.4142 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.459/SR1: 0.437 | LR: 2.60e-05 |
| [2026-05-24 05:58:47] Epoch 1 | Step 260 | Loss: 1.1118 | LM: 0.4096 | LB: 1.4119 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.353 | HR1: 0.458/SR1: 0.436 | LR: 2.66e-05 |
| [2026-05-24 05:58:58] Epoch 1 | Step 270 | Loss: 1.1079 | LM: 0.4067 | LB: 1.4094 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.353 | HR1: 0.456/SR1: 0.435 | LR: 2.73e-05 |
| [2026-05-24 05:59:10] Epoch 1 | Step 280 | Loss: 1.1036 | LM: 0.4019 | LB: 1.4076 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.455/SR1: 0.434 | LR: 2.79e-05 |
| [2026-05-24 05:59:22] Epoch 1 | Step 290 | Loss: 1.1006 | LM: 0.4005 | LB: 1.4052 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.454/SR1: 0.432 | LR: 2.86e-05 |
| [2026-05-24 05:59:34] Epoch 1 | Step 300 | Loss: 1.0981 | LM: 0.3996 | LB: 1.4031 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.453/SR1: 0.431 | LR: 2.92e-05 |
| [2026-05-24 05:59:45] Epoch 1 | Step 310 | Loss: 1.0943 | LM: 0.3968 | LB: 1.4005 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.352 | HR1: 0.452/SR1: 0.430 | LR: 2.98e-05 |
| [2026-05-24 05:59:57] Epoch 1 | Step 320 | Loss: 1.0913 | LM: 0.3950 | LB: 1.3986 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.352 | HR1: 0.451/SR1: 0.429 | LR: 3.05e-05 |
| [2026-05-24 06:00:09] Epoch 1 | Step 330 | Loss: 1.0887 | LM: 0.3946 | LB: 1.3967 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.352 | HR1: 0.450/SR1: 0.428 | LR: 3.11e-05 |
| [2026-05-24 06:00:19] Epoch 1 | Step 340 | Loss: 1.0846 | LM: 0.3913 | LB: 1.3950 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.352 | HR1: 0.449/SR1: 0.427 | LR: 3.18e-05 |
| [2026-05-24 06:00:30] Epoch 1 | Step 350 | Loss: 1.0818 | LM: 0.3909 | LB: 1.3925 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.352 | HR1: 0.448/SR1: 0.425 | LR: 3.24e-05 |
| [2026-05-24 06:00:42] Epoch 1 | Step 360 | Loss: 1.0794 | LM: 0.3892 | LB: 1.3904 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.353 | HR1: 0.447/SR1: 0.424 | LR: 3.30e-05 |
| [2026-05-24 06:00:53] Epoch 1 | Step 370 | Loss: 1.0765 | LM: 0.3870 | LB: 1.3884 | CL0: 2.8 | CL1: 2.3 | HR0: 0.355/SR0: 0.353 | HR1: 0.446/SR1: 0.423 | LR: 3.37e-05 |
| [2026-05-24 06:01:04] Epoch 1 | Step 380 | Loss: 1.0732 | LM: 0.3846 | LB: 1.3858 | CL0: 2.8 | CL1: 2.3 | HR0: 0.355/SR0: 0.353 | HR1: 0.444/SR1: 0.421 | LR: 3.43e-05 |
| [2026-05-24 06:01:16] Epoch 1 | Step 390 | Loss: 1.0700 | LM: 0.3817 | LB: 1.3832 | CL0: 2.8 | CL1: 2.3 | HR0: 0.355/SR0: 0.353 | HR1: 0.443/SR1: 0.420 | LR: 3.50e-05 |
| [2026-05-24 06:01:27] Epoch 1 | Step 400 | Loss: 1.0676 | LM: 0.3810 | LB: 1.3804 | CL0: 2.8 | CL1: 2.3 | HR0: 0.355/SR0: 0.353 | HR1: 0.441/SR1: 0.418 | LR: 3.56e-05 |
| [2026-05-24 06:01:38] Epoch 1 | Step 410 | Loss: 1.0653 | LM: 0.3810 | LB: 1.3778 | CL0: 2.8 | CL1: 2.3 | HR0: 0.355/SR0: 0.353 | HR1: 0.440/SR1: 0.417 | LR: 3.62e-05 |
| [2026-05-24 06:01:50] Epoch 1 | Step 420 | Loss: 1.0632 | LM: 0.3798 | LB: 1.3752 | CL0: 2.8 | CL1: 2.3 | HR0: 0.355/SR0: 0.353 | HR1: 0.438/SR1: 0.415 | LR: 3.69e-05 |
| [2026-05-24 06:02:01] Epoch 1 | Step 430 | Loss: 1.0613 | LM: 0.3803 | LB: 1.3723 | CL0: 2.8 | CL1: 2.3 | HR0: 0.355/SR0: 0.353 | HR1: 0.437/SR1: 0.413 | LR: 3.75e-05 |
| [2026-05-24 06:02:12] Epoch 1 | Step 440 | Loss: 1.0583 | LM: 0.3775 | LB: 1.3691 | CL0: 2.8 | CL1: 2.3 | HR0: 0.355/SR0: 0.352 | HR1: 0.435/SR1: 0.411 | LR: 3.82e-05 |
| [2026-05-24 06:02:24] Epoch 1 | Step 450 | Loss: 1.0552 | LM: 0.3763 | LB: 1.3662 | CL0: 2.8 | CL1: 2.3 | HR0: 0.355/SR0: 0.352 | HR1: 0.433/SR1: 0.409 | LR: 3.88e-05 |
| [2026-05-24 06:02:35] Epoch 1 | Step 460 | Loss: 1.0528 | LM: 0.3752 | LB: 1.3630 | CL0: 2.8 | CL1: 2.3 | HR0: 0.355/SR0: 0.352 | HR1: 0.431/SR1: 0.407 | LR: 3.94e-05 |
| [2026-05-24 06:02:46] Epoch 1 | Step 470 | Loss: 1.0504 | LM: 0.3742 | LB: 1.3593 | CL0: 2.8 | CL1: 2.4 | HR0: 0.355/SR0: 0.352 | HR1: 0.429/SR1: 0.405 | LR: 4.01e-05 |
| [2026-05-24 06:02:57] Epoch 1 | Step 480 | Loss: 1.0471 | LM: 0.3721 | LB: 1.3560 | CL0: 2.8 | CL1: 2.4 | HR0: 0.355/SR0: 0.352 | HR1: 0.426/SR1: 0.402 | LR: 4.07e-05 |
| [2026-05-24 06:03:09] Epoch 1 | Step 490 | Loss: 1.0440 | LM: 0.3721 | LB: 1.3528 | CL0: 2.8 | CL1: 2.4 | HR0: 0.355/SR0: 0.352 | HR1: 0.424/SR1: 0.400 | LR: 4.14e-05 |
| [2026-05-24 06:03:20] Epoch 1 | Step 500 | Loss: 1.0421 | LM: 0.3715 | LB: 1.3496 | CL0: 2.8 | CL1: 2.4 | HR0: 0.355/SR0: 0.353 | HR1: 0.421/SR1: 0.397 | LR: 4.20e-05 |
| [2026-05-24 06:03:31] Epoch 1 | Step 510 | Loss: 1.0402 | LM: 0.3712 | LB: 1.3465 | CL0: 2.8 | CL1: 2.4 | HR0: 0.355/SR0: 0.353 | HR1: 0.419/SR1: 0.395 | LR: 4.26e-05 |
| [2026-05-24 06:03:43] Epoch 1 | Step 520 | Loss: 1.0378 | LM: 0.3695 | LB: 1.3436 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.353 | HR1: 0.417/SR1: 0.393 | LR: 4.33e-05 |
| [2026-05-24 06:03:54] Epoch 1 | Step 530 | Loss: 1.0354 | LM: 0.3686 | LB: 1.3403 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.353 | HR1: 0.415/SR1: 0.390 | LR: 4.39e-05 |
| [2026-05-24 06:04:06] Epoch 1 | Step 540 | Loss: 1.0322 | LM: 0.3671 | LB: 1.3371 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.353 | HR1: 0.412/SR1: 0.388 | LR: 4.46e-05 |
| [2026-05-24 06:04:17] Epoch 1 | Step 550 | Loss: 1.0295 | LM: 0.3654 | LB: 1.3336 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.352 | HR1: 0.410/SR1: 0.386 | LR: 4.52e-05 |
| [2026-05-24 06:04:28] Epoch 1 | Step 560 | Loss: 1.0272 | LM: 0.3643 | LB: 1.3304 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.352 | HR1: 0.408/SR1: 0.383 | LR: 4.58e-05 |
| [2026-05-24 06:04:40] Epoch 1 | Step 570 | Loss: 1.0256 | LM: 0.3639 | LB: 1.3277 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.352 | HR1: 0.406/SR1: 0.381 | LR: 4.65e-05 |
| [2026-05-24 06:04:51] Epoch 1 | Step 580 | Loss: 1.0241 | LM: 0.3647 | LB: 1.3248 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.352 | HR1: 0.404/SR1: 0.379 | LR: 4.71e-05 |
| [2026-05-24 06:05:03] Epoch 1 | Step 590 | Loss: 1.0224 | LM: 0.3636 | LB: 1.3216 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.352 | HR1: 0.402/SR1: 0.377 | LR: 4.78e-05 |
| [2026-05-24 06:05:15] Epoch 1 | Step 600 | Loss: 1.0210 | LM: 0.3637 | LB: 1.3188 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.352 | HR1: 0.400/SR1: 0.374 | LR: 4.84e-05 |
| [2026-05-24 06:05:25] Epoch 1 | Step 610 | Loss: 1.0188 | LM: 0.3629 | LB: 1.3162 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.352 | HR1: 0.398/SR1: 0.372 | LR: 4.90e-05 |
| [2026-05-24 06:05:37] Epoch 1 | Step 620 | Loss: 1.0167 | LM: 0.3617 | LB: 1.3134 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.351 | HR1: 0.396/SR1: 0.370 | LR: 4.97e-05 |
| [2026-05-24 06:05:48] Epoch 1 | Step 630 | Loss: 1.0148 | LM: 0.3614 | LB: 1.3111 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.352 | HR1: 0.393/SR1: 0.368 | LR: 5.03e-05 |
| [2026-05-24 06:05:59] Epoch 1 | Step 640 | Loss: 1.0131 | LM: 0.3616 | LB: 1.3086 | CL0: 2.8 | CL1: 2.7 | HR0: 0.355/SR0: 0.352 | HR1: 0.391/SR1: 0.366 | LR: 5.10e-05 |
| [2026-05-24 06:06:10] Epoch 1 | Step 650 | Loss: 1.0114 | LM: 0.3606 | LB: 1.3063 | CL0: 2.8 | CL1: 2.7 | HR0: 0.355/SR0: 0.352 | HR1: 0.389/SR1: 0.364 | LR: 5.16e-05 |
| [2026-05-24 06:06:22] Epoch 1 | Step 660 | Loss: 1.0101 | LM: 0.3609 | LB: 1.3037 | CL0: 2.8 | CL1: 2.7 | HR0: 0.355/SR0: 0.352 | HR1: 0.387/SR1: 0.362 | LR: 5.22e-05 |
| [2026-05-24 06:06:32] Epoch 1 | Step 670 | Loss: 1.0085 | LM: 0.3607 | LB: 1.3014 | CL0: 2.8 | CL1: 2.7 | HR0: 0.355/SR0: 0.351 | HR1: 0.386/SR1: 0.360 | LR: 5.29e-05 |
| [2026-05-24 06:06:44] Epoch 1 | Step 680 | Loss: 1.0068 | LM: 0.3608 | LB: 1.2990 | CL0: 2.8 | CL1: 2.7 | HR0: 0.355/SR0: 0.351 | HR1: 0.384/SR1: 0.358 | LR: 5.35e-05 |
| [2026-05-24 06:06:56] Epoch 1 | Step 690 | Loss: 1.0056 | LM: 0.3601 | LB: 1.2968 | CL0: 2.8 | CL1: 2.8 | HR0: 0.355/SR0: 0.351 | HR1: 0.382/SR1: 0.356 | LR: 5.42e-05 |
| [2026-05-24 06:07:07] Epoch 1 | Step 700 | Loss: 1.0037 | LM: 0.3588 | LB: 1.2947 | CL0: 2.8 | CL1: 2.8 | HR0: 0.355/SR0: 0.351 | HR1: 0.380/SR1: 0.354 | LR: 5.48e-05 |
| [2026-05-24 06:07:17] Epoch 1 | Step 710 | Loss: 1.0024 | LM: 0.3586 | LB: 1.2924 | CL0: 2.8 | CL1: 2.8 | HR0: 0.355/SR0: 0.351 | HR1: 0.379/SR1: 0.353 | LR: 5.54e-05 |
| [2026-05-24 06:07:29] Epoch 1 | Step 720 | Loss: 1.0009 | LM: 0.3582 | LB: 1.2903 | CL0: 2.8 | CL1: 2.8 | HR0: 0.354/SR0: 0.351 | HR1: 0.377/SR1: 0.351 | LR: 5.61e-05 |
| [2026-05-24 06:07:40] Epoch 1 | Step 730 | Loss: 0.9999 | LM: 0.3582 | LB: 1.2883 | CL0: 2.8 | CL1: 2.8 | HR0: 0.354/SR0: 0.351 | HR1: 0.376/SR1: 0.349 | LR: 5.67e-05 |
| [2026-05-24 06:07:51] Epoch 1 | Step 740 | Loss: 0.9983 | LM: 0.3574 | LB: 1.2861 | CL0: 2.8 | CL1: 2.8 | HR0: 0.354/SR0: 0.351 | HR1: 0.374/SR1: 0.347 | LR: 5.74e-05 |
| [2026-05-24 06:08:02] Epoch 1 | Step 750 | Loss: 0.9973 | LM: 0.3572 | LB: 1.2839 | CL0: 2.8 | CL1: 2.8 | HR0: 0.354/SR0: 0.350 | HR1: 0.372/SR1: 0.346 | LR: 5.80e-05 |
| [2026-05-24 06:08:13] Epoch 1 | Step 760 | Loss: 0.9963 | LM: 0.3572 | LB: 1.2821 | CL0: 2.8 | CL1: 2.9 | HR0: 0.354/SR0: 0.350 | HR1: 0.371/SR1: 0.344 | LR: 5.86e-05 |
| [2026-05-24 06:08:24] Epoch 1 | Step 770 | Loss: 0.9942 | LM: 0.3562 | LB: 1.2802 | CL0: 2.8 | CL1: 2.9 | HR0: 0.354/SR0: 0.350 | HR1: 0.369/SR1: 0.343 | LR: 5.93e-05 |
| [2026-05-24 06:08:36] Epoch 1 | Step 780 | Loss: 0.9928 | LM: 0.3555 | LB: 1.2783 | CL0: 2.8 | CL1: 2.9 | HR0: 0.354/SR0: 0.350 | HR1: 0.368/SR1: 0.341 | LR: 5.99e-05 |
| [2026-05-24 06:08:47] Epoch 1 | Step 790 | Loss: 0.9917 | LM: 0.3554 | LB: 1.2764 | CL0: 2.8 | CL1: 2.9 | HR0: 0.354/SR0: 0.350 | HR1: 0.366/SR1: 0.339 | LR: 6.06e-05 |
| [2026-05-24 06:08:59] Epoch 1 | Step 800 | Loss: 0.9910 | LM: 0.3559 | LB: 1.2747 | CL0: 2.8 | CL1: 2.9 | HR0: 0.354/SR0: 0.350 | HR1: 0.365/SR1: 0.338 | LR: 6.12e-05 |
| [2026-05-24 06:09:10] Epoch 1 | Step 810 | Loss: 0.9900 | LM: 0.3561 | LB: 1.2730 | CL0: 2.8 | CL1: 2.9 | HR0: 0.354/SR0: 0.350 | HR1: 0.363/SR1: 0.336 | LR: 6.18e-05 |
| [2026-05-24 06:09:21] Epoch 1 | Step 820 | Loss: 0.9893 | LM: 0.3563 | LB: 1.2714 | CL0: 2.8 | CL1: 2.9 | HR0: 0.354/SR0: 0.350 | HR1: 0.362/SR1: 0.335 | LR: 6.25e-05 |
| [2026-05-24 06:09:32] Epoch 1 | Step 830 | Loss: 0.9880 | LM: 0.3559 | LB: 1.2697 | CL0: 2.8 | CL1: 3.0 | HR0: 0.354/SR0: 0.350 | HR1: 0.360/SR1: 0.333 | LR: 6.31e-05 |
| [2026-05-24 06:09:43] Epoch 1 | Step 840 | Loss: 0.9870 | LM: 0.3559 | LB: 1.2679 | CL0: 2.8 | CL1: 3.0 | HR0: 0.354/SR0: 0.349 | HR1: 0.359/SR1: 0.332 | LR: 6.38e-05 |
| [2026-05-24 06:09:55] Epoch 1 | Step 850 | Loss: 0.9860 | LM: 0.3554 | LB: 1.2662 | CL0: 2.8 | CL1: 3.0 | HR0: 0.353/SR0: 0.349 | HR1: 0.358/SR1: 0.331 | LR: 6.44e-05 |
| [2026-05-24 06:10:06] Epoch 1 | Step 860 | Loss: 0.9850 | LM: 0.3556 | LB: 1.2646 | CL0: 2.8 | CL1: 3.0 | HR0: 0.353/SR0: 0.349 | HR1: 0.356/SR1: 0.329 | LR: 6.50e-05 |
| [2026-05-24 06:10:17] Epoch 1 | Step 870 | Loss: 0.9838 | LM: 0.3547 | LB: 1.2631 | CL0: 2.8 | CL1: 3.0 | HR0: 0.354/SR0: 0.349 | HR1: 0.355/SR1: 0.328 | LR: 6.57e-05 |
| [2026-05-24 06:10:28] Epoch 1 | Step 880 | Loss: 0.9826 | LM: 0.3543 | LB: 1.2613 | CL0: 2.8 | CL1: 3.0 | HR0: 0.353/SR0: 0.349 | HR1: 0.353/SR1: 0.326 | LR: 6.63e-05 |
| [2026-05-24 06:10:39] Epoch 1 | Step 890 | Loss: 0.9819 | LM: 0.3543 | LB: 1.2597 | CL0: 2.8 | CL1: 3.0 | HR0: 0.353/SR0: 0.349 | HR1: 0.352/SR1: 0.325 | LR: 6.70e-05 |
| [2026-05-24 06:10:50] Epoch 1 | Step 900 | Loss: 0.9807 | LM: 0.3533 | LB: 1.2583 | CL0: 2.8 | CL1: 3.1 | HR0: 0.353/SR0: 0.349 | HR1: 0.351/SR1: 0.324 | LR: 6.76e-05 |
| [2026-05-24 06:11:01] Epoch 1 | Step 910 | Loss: 0.9797 | LM: 0.3530 | LB: 1.2569 | CL0: 2.8 | CL1: 3.1 | HR0: 0.353/SR0: 0.348 | HR1: 0.350/SR1: 0.323 | LR: 6.83e-05 |
| [2026-05-24 06:11:12] Epoch 1 | Step 920 | Loss: 0.9787 | LM: 0.3529 | LB: 1.2555 | CL0: 2.8 | CL1: 3.1 | HR0: 0.353/SR0: 0.348 | HR1: 0.349/SR1: 0.321 | LR: 6.89e-05 |
| [2026-05-24 06:11:23] Epoch 1 | Step 930 | Loss: 0.9778 | LM: 0.3524 | LB: 1.2541 | CL0: 2.8 | CL1: 3.1 | HR0: 0.353/SR0: 0.348 | HR1: 0.347/SR1: 0.320 | LR: 6.95e-05 |
| [2026-05-24 06:11:34] Epoch 1 | Step 940 | Loss: 0.9766 | LM: 0.3516 | LB: 1.2526 | CL0: 2.8 | CL1: 3.1 | HR0: 0.353/SR0: 0.348 | HR1: 0.346/SR1: 0.319 | LR: 7.02e-05 |
| [2026-05-24 06:11:45] Epoch 1 | Step 950 | Loss: 0.9759 | LM: 0.3516 | LB: 1.2514 | CL0: 2.8 | CL1: 3.1 | HR0: 0.353/SR0: 0.348 | HR1: 0.345/SR1: 0.318 | LR: 7.08e-05 |
| [2026-05-24 06:11:56] Epoch 1 | Step 960 | Loss: 0.9753 | LM: 0.3515 | LB: 1.2499 | CL0: 2.8 | CL1: 3.1 | HR0: 0.353/SR0: 0.348 | HR1: 0.344/SR1: 0.316 | LR: 7.15e-05 |
| [2026-05-24 06:12:07] Epoch 1 | Step 970 | Loss: 0.9744 | LM: 0.3509 | LB: 1.2485 | CL0: 2.8 | CL1: 3.1 | HR0: 0.353/SR0: 0.348 | HR1: 0.343/SR1: 0.315 | LR: 7.21e-05 |
| [2026-05-24 06:12:18] Epoch 1 | Step 980 | Loss: 0.9738 | LM: 0.3510 | LB: 1.2472 | CL0: 2.8 | CL1: 3.2 | HR0: 0.353/SR0: 0.348 | HR1: 0.341/SR1: 0.314 | LR: 7.27e-05 |
| [2026-05-24 06:12:29] Epoch 1 | Step 990 | Loss: 0.9728 | LM: 0.3506 | LB: 1.2458 | CL0: 2.9 | CL1: 3.2 | HR0: 0.352/SR0: 0.347 | HR1: 0.340/SR1: 0.313 | LR: 7.34e-05 |
| [2026-05-24 06:12:40] Epoch 1 | Step 1000 | Loss: 0.9718 | LM: 0.3509 | LB: 1.2446 | CL0: 2.9 | CL1: 3.2 | HR0: 0.352/SR0: 0.347 | HR1: 0.339/SR1: 0.312 | LR: 7.40e-05 |
| [2026-05-24 06:12:42] Validation | Batch 10/1463 | Loss: 0.8504 | LM_LOSS: 0.3009 | LB_LOSS: 1.0989 |
| [2026-05-24 06:12:44] Validation | Batch 20/1463 | Loss: 0.8646 | LM_LOSS: 0.3113 | LB_LOSS: 1.1066 |
| [2026-05-24 06:12:46] Validation | Batch 30/1463 | Loss: 0.8721 | LM_LOSS: 0.3179 | LB_LOSS: 1.1084 |
| [2026-05-24 06:12:48] Validation | Batch 40/1463 | Loss: 0.8818 | LM_LOSS: 0.3261 | LB_LOSS: 1.1113 |
| [2026-05-24 06:12:50] Validation | Batch 50/1463 | Loss: 0.8892 | LM_LOSS: 0.3345 | LB_LOSS: 1.1094 |
| [2026-05-24 06:12:53] Validation | Batch 60/1463 | Loss: 0.8898 | LM_LOSS: 0.3353 | LB_LOSS: 1.1092 |
| [2026-05-24 06:12:56] Validation | Batch 70/1463 | Loss: 0.8902 | LM_LOSS: 0.3354 | LB_LOSS: 1.1096 |
| [2026-05-24 06:12:59] Validation | Batch 80/1463 | Loss: 0.8921 | LM_LOSS: 0.3372 | LB_LOSS: 1.1098 |
| [2026-05-24 06:13:00] Validation | Batch 90/1463 | Loss: 0.8920 | LM_LOSS: 0.3372 | LB_LOSS: 1.1096 |
| [2026-05-24 06:13:02] Validation | Batch 100/1463 | Loss: 0.8923 | LM_LOSS: 0.3374 | LB_LOSS: 1.1096 |
| [2026-05-24 06:13:05] Validation | Batch 110/1463 | Loss: 0.8917 | LM_LOSS: 0.3365 | LB_LOSS: 1.1105 |
| [2026-05-24 06:13:07] Validation | Batch 120/1463 | Loss: 0.8933 | LM_LOSS: 0.3380 | LB_LOSS: 1.1106 |
| [2026-05-24 06:13:09] Validation | Batch 130/1463 | Loss: 0.8952 | LM_LOSS: 0.3398 | LB_LOSS: 1.1108 |
| [2026-05-24 06:13:11] Validation | Batch 140/1463 | Loss: 0.8958 | LM_LOSS: 0.3405 | LB_LOSS: 1.1105 |
| [2026-05-24 06:13:13] Validation | Batch 150/1463 | Loss: 0.8940 | LM_LOSS: 0.3386 | LB_LOSS: 1.1108 |
| [2026-05-24 06:13:16] Validation | Batch 160/1463 | Loss: 0.8939 | LM_LOSS: 0.3387 | LB_LOSS: 1.1103 |
| [2026-05-24 06:13:18] Validation | Batch 170/1463 | Loss: 0.8935 | LM_LOSS: 0.3383 | LB_LOSS: 1.1103 |
| [2026-05-24 06:13:20] Validation | Batch 180/1463 | Loss: 0.8941 | LM_LOSS: 0.3390 | LB_LOSS: 1.1103 |
| [2026-05-24 06:13:23] Validation | Batch 190/1463 | Loss: 0.8949 | LM_LOSS: 0.3397 | LB_LOSS: 1.1105 |
| [2026-05-24 06:13:25] Validation | Batch 200/1463 | Loss: 0.8946 | LM_LOSS: 0.3394 | LB_LOSS: 1.1105 |
| [2026-05-24 06:13:27] Validation | Batch 210/1463 | Loss: 0.8951 | LM_LOSS: 0.3398 | LB_LOSS: 1.1105 |
| [2026-05-24 06:13:29] Validation | Batch 220/1463 | Loss: 0.8945 | LM_LOSS: 0.3392 | LB_LOSS: 1.1106 |
| [2026-05-24 06:13:32] Validation | Batch 230/1463 | Loss: 0.8961 | LM_LOSS: 0.3409 | LB_LOSS: 1.1103 |
| [2026-05-24 06:13:34] Validation | Batch 240/1463 | Loss: 0.8970 | LM_LOSS: 0.3419 | LB_LOSS: 1.1103 |
| [2026-05-24 06:13:36] Validation | Batch 250/1463 | Loss: 0.8964 | LM_LOSS: 0.3412 | LB_LOSS: 1.1104 |
| [2026-05-24 06:13:38] Validation | Batch 260/1463 | Loss: 0.8981 | LM_LOSS: 0.3427 | LB_LOSS: 1.1108 |
| [2026-05-24 06:13:41] Validation | Batch 270/1463 | Loss: 0.8968 | LM_LOSS: 0.3414 | LB_LOSS: 1.1108 |
| [2026-05-24 06:13:43] Validation | Batch 280/1463 | Loss: 0.8977 | LM_LOSS: 0.3422 | LB_LOSS: 1.1109 |
| [2026-05-24 06:13:45] Validation | Batch 290/1463 | Loss: 0.8970 | LM_LOSS: 0.3416 | LB_LOSS: 1.1109 |
| [2026-05-24 06:13:47] Validation | Batch 300/1463 | Loss: 0.8972 | LM_LOSS: 0.3415 | LB_LOSS: 1.1113 |
| [2026-05-24 06:13:49] Validation | Batch 310/1463 | Loss: 0.8980 | LM_LOSS: 0.3424 | LB_LOSS: 1.1112 |
| [2026-05-24 06:13:51] Validation | Batch 320/1463 | Loss: 0.8962 | LM_LOSS: 0.3409 | LB_LOSS: 1.1107 |
| [2026-05-24 06:13:54] Validation | Batch 330/1463 | Loss: 0.8963 | LM_LOSS: 0.3410 | LB_LOSS: 1.1107 |
| [2026-05-24 06:13:55] Validation | Batch 340/1463 | Loss: 0.8961 | LM_LOSS: 0.3407 | LB_LOSS: 1.1107 |
| [2026-05-24 06:13:58] Validation | Batch 350/1463 | Loss: 0.8969 | LM_LOSS: 0.3415 | LB_LOSS: 1.1107 |
| [2026-05-24 06:14:00] Validation | Batch 360/1463 | Loss: 0.8965 | LM_LOSS: 0.3412 | LB_LOSS: 1.1108 |
| [2026-05-24 06:14:02] Validation | Batch 370/1463 | Loss: 0.8965 | LM_LOSS: 0.3410 | LB_LOSS: 1.1109 |
| [2026-05-24 06:14:04] Validation | Batch 380/1463 | Loss: 0.8962 | LM_LOSS: 0.3408 | LB_LOSS: 1.1107 |
| [2026-05-24 06:14:06] Validation | Batch 390/1463 | Loss: 0.8969 | LM_LOSS: 0.3415 | LB_LOSS: 1.1107 |
| [2026-05-24 06:14:08] Validation | Batch 400/1463 | Loss: 0.8970 | LM_LOSS: 0.3415 | LB_LOSS: 1.1109 |
| [2026-05-24 06:14:10] Validation | Batch 410/1463 | Loss: 0.8967 | LM_LOSS: 0.3412 | LB_LOSS: 1.1110 |
| [2026-05-24 06:14:13] Validation | Batch 420/1463 | Loss: 0.8968 | LM_LOSS: 0.3413 | LB_LOSS: 1.1111 |
| [2026-05-24 06:14:15] Validation | Batch 430/1463 | Loss: 0.8963 | LM_LOSS: 0.3407 | LB_LOSS: 1.1111 |
| [2026-05-24 06:14:17] Validation | Batch 440/1463 | Loss: 0.8965 | LM_LOSS: 0.3409 | LB_LOSS: 1.1112 |
| [2026-05-24 06:14:19] Validation | Batch 450/1463 | Loss: 0.8963 | LM_LOSS: 0.3407 | LB_LOSS: 1.1113 |
| [2026-05-24 06:14:22] Validation | Batch 460/1463 | Loss: 0.8965 | LM_LOSS: 0.3409 | LB_LOSS: 1.1112 |
| [2026-05-24 06:14:24] Validation | Batch 470/1463 | Loss: 0.8971 | LM_LOSS: 0.3416 | LB_LOSS: 1.1111 |
| [2026-05-24 06:14:26] Validation | Batch 480/1463 | Loss: 0.8970 | LM_LOSS: 0.3415 | LB_LOSS: 1.1109 |
| [2026-05-24 06:14:29] Validation | Batch 490/1463 | Loss: 0.8969 | LM_LOSS: 0.3414 | LB_LOSS: 1.1109 |
| [2026-05-24 06:14:31] Validation | Batch 500/1463 | Loss: 0.8968 | LM_LOSS: 0.3413 | LB_LOSS: 1.1109 |
| [2026-05-24 06:14:34] Validation | Batch 510/1463 | Loss: 0.8963 | LM_LOSS: 0.3408 | LB_LOSS: 1.1110 |
| [2026-05-24 06:14:36] Validation | Batch 520/1463 | Loss: 0.8958 | LM_LOSS: 0.3402 | LB_LOSS: 1.1111 |
| [2026-05-24 06:14:38] Validation | Batch 530/1463 | Loss: 0.8959 | LM_LOSS: 0.3404 | LB_LOSS: 1.1110 |
| [2026-05-24 06:14:39] Validation | Batch 540/1463 | Loss: 0.8962 | LM_LOSS: 0.3406 | LB_LOSS: 1.1112 |
| [2026-05-24 06:14:41] Validation | Batch 550/1463 | Loss: 0.8959 | LM_LOSS: 0.3403 | LB_LOSS: 1.1113 |
| [2026-05-24 06:14:43] Validation | Batch 560/1463 | Loss: 0.8964 | LM_LOSS: 0.3406 | LB_LOSS: 1.1115 |
| [2026-05-24 06:14:46] Validation | Batch 570/1463 | Loss: 0.8963 | LM_LOSS: 0.3406 | LB_LOSS: 1.1114 |
| [2026-05-24 06:14:48] Validation | Batch 580/1463 | Loss: 0.8962 | LM_LOSS: 0.3405 | LB_LOSS: 1.1114 |
| [2026-05-24 06:14:51] Validation | Batch 590/1463 | Loss: 0.8961 | LM_LOSS: 0.3403 | LB_LOSS: 1.1115 |
| [2026-05-24 06:14:53] Validation | Batch 600/1463 | Loss: 0.8965 | LM_LOSS: 0.3407 | LB_LOSS: 1.1117 |
| [2026-05-24 06:14:56] Validation | Batch 610/1463 | Loss: 0.8966 | LM_LOSS: 0.3408 | LB_LOSS: 1.1117 |
| [2026-05-24 06:14:58] Validation | Batch 620/1463 | Loss: 0.8960 | LM_LOSS: 0.3402 | LB_LOSS: 1.1116 |
| [2026-05-24 06:15:00] Validation | Batch 630/1463 | Loss: 0.8956 | LM_LOSS: 0.3398 | LB_LOSS: 1.1117 |
| [2026-05-24 06:15:02] Validation | Batch 640/1463 | Loss: 0.8955 | LM_LOSS: 0.3396 | LB_LOSS: 1.1118 |
| [2026-05-24 06:15:04] Validation | Batch 650/1463 | Loss: 0.8950 | LM_LOSS: 0.3391 | LB_LOSS: 1.1118 |
| [2026-05-24 06:15:06] Validation | Batch 660/1463 | Loss: 0.8945 | LM_LOSS: 0.3386 | LB_LOSS: 1.1117 |
| [2026-05-24 06:15:08] Validation | Batch 670/1463 | Loss: 0.8941 | LM_LOSS: 0.3383 | LB_LOSS: 1.1116 |
| [2026-05-24 06:15:10] Validation | Batch 680/1463 | Loss: 0.8940 | LM_LOSS: 0.3383 | LB_LOSS: 1.1115 |
| [2026-05-24 06:15:13] Validation | Batch 690/1463 | Loss: 0.8945 | LM_LOSS: 0.3387 | LB_LOSS: 1.1116 |
| [2026-05-24 06:15:15] Validation | Batch 700/1463 | Loss: 0.8942 | LM_LOSS: 0.3385 | LB_LOSS: 1.1115 |
| [2026-05-24 06:15:17] Validation | Batch 710/1463 | Loss: 0.8949 | LM_LOSS: 0.3391 | LB_LOSS: 1.1116 |
| [2026-05-24 06:15:19] Validation | Batch 720/1463 | Loss: 0.8957 | LM_LOSS: 0.3398 | LB_LOSS: 1.1118 |
| [2026-05-24 06:15:21] Validation | Batch 730/1463 | Loss: 0.8954 | LM_LOSS: 0.3395 | LB_LOSS: 1.1117 |
| [2026-05-24 06:15:23] Validation | Batch 740/1463 | Loss: 0.8950 | LM_LOSS: 0.3391 | LB_LOSS: 1.1118 |
| [2026-05-24 06:15:24] Validation | Batch 750/1463 | Loss: 0.8948 | LM_LOSS: 0.3389 | LB_LOSS: 1.1117 |
| [2026-05-24 06:15:26] Validation | Batch 760/1463 | Loss: 0.8945 | LM_LOSS: 0.3387 | LB_LOSS: 1.1117 |
| [2026-05-24 06:15:28] Validation | Batch 770/1463 | Loss: 0.8943 | LM_LOSS: 0.3384 | LB_LOSS: 1.1118 |
| [2026-05-24 06:15:30] Validation | Batch 780/1463 | Loss: 0.8940 | LM_LOSS: 0.3382 | LB_LOSS: 1.1117 |
| [2026-05-24 06:15:32] Validation | Batch 790/1463 | Loss: 0.8941 | LM_LOSS: 0.3383 | LB_LOSS: 1.1116 |
| [2026-05-24 06:15:34] Validation | Batch 800/1463 | Loss: 0.8940 | LM_LOSS: 0.3382 | LB_LOSS: 1.1116 |
| [2026-05-24 06:15:36] Validation | Batch 810/1463 | Loss: 0.8936 | LM_LOSS: 0.3379 | LB_LOSS: 1.1115 |
| [2026-05-24 06:15:38] Validation | Batch 820/1463 | Loss: 0.8938 | LM_LOSS: 0.3381 | LB_LOSS: 1.1114 |
| [2026-05-24 06:15:40] Validation | Batch 830/1463 | Loss: 0.8942 | LM_LOSS: 0.3384 | LB_LOSS: 1.1115 |
| [2026-05-24 06:15:43] Validation | Batch 840/1463 | Loss: 0.8943 | LM_LOSS: 0.3385 | LB_LOSS: 1.1116 |
| [2026-05-24 06:15:45] Validation | Batch 850/1463 | Loss: 0.8945 | LM_LOSS: 0.3387 | LB_LOSS: 1.1116 |
| [2026-05-24 06:15:47] Validation | Batch 860/1463 | Loss: 0.8946 | LM_LOSS: 0.3387 | LB_LOSS: 1.1117 |
| [2026-05-24 06:15:50] Validation | Batch 870/1463 | Loss: 0.8947 | LM_LOSS: 0.3388 | LB_LOSS: 1.1117 |
| [2026-05-24 06:15:52] Validation | Batch 880/1463 | Loss: 0.8939 | LM_LOSS: 0.3380 | LB_LOSS: 1.1117 |
| [2026-05-24 06:15:54] Validation | Batch 890/1463 | Loss: 0.8938 | LM_LOSS: 0.3381 | LB_LOSS: 1.1116 |
| [2026-05-24 06:15:56] Validation | Batch 900/1463 | Loss: 0.8935 | LM_LOSS: 0.3377 | LB_LOSS: 1.1116 |
| [2026-05-24 06:15:58] Validation | Batch 910/1463 | Loss: 0.8933 | LM_LOSS: 0.3375 | LB_LOSS: 1.1116 |
| [2026-05-24 06:16:01] Validation | Batch 920/1463 | Loss: 0.8935 | LM_LOSS: 0.3377 | LB_LOSS: 1.1116 |
| [2026-05-24 06:16:03] Validation | Batch 930/1463 | Loss: 0.8933 | LM_LOSS: 0.3375 | LB_LOSS: 1.1115 |
| [2026-05-24 06:16:05] Validation | Batch 940/1463 | Loss: 0.8929 | LM_LOSS: 0.3372 | LB_LOSS: 1.1114 |
| [2026-05-24 06:16:08] Validation | Batch 950/1463 | Loss: 0.8932 | LM_LOSS: 0.3375 | LB_LOSS: 1.1114 |
| [2026-05-24 06:16:10] Validation | Batch 960/1463 | Loss: 0.8933 | LM_LOSS: 0.3376 | LB_LOSS: 1.1114 |
| [2026-05-24 06:16:12] Validation | Batch 970/1463 | Loss: 0.8934 | LM_LOSS: 0.3377 | LB_LOSS: 1.1113 |
| [2026-05-24 06:16:15] Validation | Batch 980/1463 | Loss: 0.8936 | LM_LOSS: 0.3380 | LB_LOSS: 1.1112 |
| [2026-05-24 06:16:16] Validation | Batch 990/1463 | Loss: 0.8939 | LM_LOSS: 0.3382 | LB_LOSS: 1.1113 |
| [2026-05-24 06:16:19] Validation | Batch 1000/1463 | Loss: 0.8945 | LM_LOSS: 0.3389 | LB_LOSS: 1.1113 |
| [2026-05-24 06:16:21] Validation | Batch 1010/1463 | Loss: 0.8945 | LM_LOSS: 0.3388 | LB_LOSS: 1.1114 |
| [2026-05-24 06:16:23] Validation | Batch 1020/1463 | Loss: 0.8947 | LM_LOSS: 0.3389 | LB_LOSS: 1.1115 |
| [2026-05-24 06:16:26] Validation | Batch 1030/1463 | Loss: 0.8950 | LM_LOSS: 0.3392 | LB_LOSS: 1.1115 |
| [2026-05-24 06:16:28] Validation | Batch 1040/1463 | Loss: 0.8946 | LM_LOSS: 0.3388 | LB_LOSS: 1.1115 |
| [2026-05-24 06:16:30] Validation | Batch 1050/1463 | Loss: 0.8944 | LM_LOSS: 0.3387 | LB_LOSS: 1.1114 |
| [2026-05-24 06:16:33] Validation | Batch 1060/1463 | Loss: 0.8944 | LM_LOSS: 0.3387 | LB_LOSS: 1.1114 |
| [2026-05-24 06:16:35] Validation | Batch 1070/1463 | Loss: 0.8945 | LM_LOSS: 0.3388 | LB_LOSS: 1.1114 |
| [2026-05-24 06:16:37] Validation | Batch 1080/1463 | Loss: 0.8942 | LM_LOSS: 0.3385 | LB_LOSS: 1.1115 |
| [2026-05-24 06:16:39] Validation | Batch 1090/1463 | Loss: 0.8943 | LM_LOSS: 0.3386 | LB_LOSS: 1.1114 |
| [2026-05-24 06:16:41] Validation | Batch 1100/1463 | Loss: 0.8941 | LM_LOSS: 0.3385 | LB_LOSS: 1.1113 |
| [2026-05-24 06:16:43] Validation | Batch 1110/1463 | Loss: 0.8941 | LM_LOSS: 0.3384 | LB_LOSS: 1.1113 |
| [2026-05-24 06:16:45] Validation | Batch 1120/1463 | Loss: 0.8940 | LM_LOSS: 0.3383 | LB_LOSS: 1.1114 |
| [2026-05-24 06:16:48] Validation | Batch 1130/1463 | Loss: 0.8938 | LM_LOSS: 0.3381 | LB_LOSS: 1.1114 |
| [2026-05-24 06:16:50] Validation | Batch 1140/1463 | Loss: 0.8939 | LM_LOSS: 0.3383 | LB_LOSS: 1.1114 |
| [2026-05-24 06:16:52] Validation | Batch 1150/1463 | Loss: 0.8938 | LM_LOSS: 0.3382 | LB_LOSS: 1.1114 |
| [2026-05-24 06:16:54] Validation | Batch 1160/1463 | Loss: 0.8938 | LM_LOSS: 0.3381 | LB_LOSS: 1.1114 |
| [2026-05-24 06:16:57] Validation | Batch 1170/1463 | Loss: 0.8938 | LM_LOSS: 0.3382 | LB_LOSS: 1.1114 |
| [2026-05-24 06:16:59] Validation | Batch 1180/1463 | Loss: 0.8939 | LM_LOSS: 0.3382 | LB_LOSS: 1.1114 |
| [2026-05-24 06:17:01] Validation | Batch 1190/1463 | Loss: 0.8940 | LM_LOSS: 0.3383 | LB_LOSS: 1.1114 |
| [2026-05-24 06:17:04] Validation | Batch 1200/1463 | Loss: 0.8941 | LM_LOSS: 0.3384 | LB_LOSS: 1.1114 |
| [2026-05-24 06:17:06] Validation | Batch 1210/1463 | Loss: 0.8943 | LM_LOSS: 0.3386 | LB_LOSS: 1.1115 |
| [2026-05-24 06:17:08] Validation | Batch 1220/1463 | Loss: 0.8947 | LM_LOSS: 0.3390 | LB_LOSS: 1.1115 |
| [2026-05-24 06:17:10] Validation | Batch 1230/1463 | Loss: 0.8947 | LM_LOSS: 0.3390 | LB_LOSS: 1.1115 |
| [2026-05-24 06:17:12] Validation | Batch 1240/1463 | Loss: 0.8951 | LM_LOSS: 0.3393 | LB_LOSS: 1.1115 |
| [2026-05-24 06:17:14] Validation | Batch 1250/1463 | Loss: 0.8953 | LM_LOSS: 0.3396 | LB_LOSS: 1.1115 |
| [2026-05-24 06:17:17] Validation | Batch 1260/1463 | Loss: 0.8953 | LM_LOSS: 0.3396 | LB_LOSS: 1.1115 |
| [2026-05-24 06:17:19] Validation | Batch 1270/1463 | Loss: 0.8952 | LM_LOSS: 0.3394 | LB_LOSS: 1.1116 |
| [2026-05-24 06:17:22] Validation | Batch 1280/1463 | Loss: 0.8950 | LM_LOSS: 0.3393 | LB_LOSS: 1.1115 |
| [2026-05-24 06:17:24] Validation | Batch 1290/1463 | Loss: 0.8950 | LM_LOSS: 0.3393 | LB_LOSS: 1.1114 |
| [2026-05-24 06:17:26] Validation | Batch 1300/1463 | Loss: 0.8948 | LM_LOSS: 0.3391 | LB_LOSS: 1.1114 |
| [2026-05-24 06:17:28] Validation | Batch 1310/1463 | Loss: 0.8947 | LM_LOSS: 0.3390 | LB_LOSS: 1.1114 |
| [2026-05-24 06:17:30] Validation | Batch 1320/1463 | Loss: 0.8946 | LM_LOSS: 0.3389 | LB_LOSS: 1.1114 |
| [2026-05-24 06:17:31] Validation | Batch 1330/1463 | Loss: 0.8947 | LM_LOSS: 0.3390 | LB_LOSS: 1.1114 |
| [2026-05-24 06:17:33] Validation | Batch 1340/1463 | Loss: 0.8950 | LM_LOSS: 0.3392 | LB_LOSS: 1.1115 |
| [2026-05-24 06:17:36] Validation | Batch 1350/1463 | Loss: 0.8950 | LM_LOSS: 0.3393 | LB_LOSS: 1.1114 |
| [2026-05-24 06:17:39] Validation | Batch 1360/1463 | Loss: 0.8952 | LM_LOSS: 0.3395 | LB_LOSS: 1.1114 |
| [2026-05-24 06:17:41] Validation | Batch 1370/1463 | Loss: 0.8955 | LM_LOSS: 0.3398 | LB_LOSS: 1.1114 |
| [2026-05-24 06:17:43] Validation | Batch 1380/1463 | Loss: 0.8953 | LM_LOSS: 0.3396 | LB_LOSS: 1.1114 |
| [2026-05-24 06:17:45] Validation | Batch 1390/1463 | Loss: 0.8952 | LM_LOSS: 0.3395 | LB_LOSS: 1.1114 |
| [2026-05-24 06:17:47] Validation | Batch 1400/1463 | Loss: 0.8955 | LM_LOSS: 0.3399 | LB_LOSS: 1.1113 |
| [2026-05-24 06:17:49] Validation | Batch 1410/1463 | Loss: 0.8957 | LM_LOSS: 0.3400 | LB_LOSS: 1.1113 |
| [2026-05-24 06:17:51] Validation | Batch 1420/1463 | Loss: 0.8957 | LM_LOSS: 0.3400 | LB_LOSS: 1.1114 |
| [2026-05-24 06:17:54] Validation | Batch 1430/1463 | Loss: 0.8958 | LM_LOSS: 0.3401 | LB_LOSS: 1.1113 |
| [2026-05-24 06:17:56] Validation | Batch 1440/1463 | Loss: 0.8962 | LM_LOSS: 0.3405 | LB_LOSS: 1.1114 |
| [2026-05-24 06:17:58] Validation | Batch 1450/1463 | Loss: 0.8958 | LM_LOSS: 0.3401 | LB_LOSS: 1.1113 |
| [2026-05-24 06:18:01] Validation | Batch 1460/1463 | Loss: 0.8962 | LM_LOSS: 0.3405 | LB_LOSS: 1.1113 |
| [2026-05-24 06:18:01] Validation | Batch 1463/1463 | Loss: 0.8960 | LM_LOSS: 0.3404 | LB_LOSS: 1.1113 |
| [2026-05-24 06:18:01] Validation | Loss: 0.8960 | LM_LOSS: 0.3404 | LB_LOSS: 1.1113 | PPL: 1.41 | Time: 321.36s |
| [2026-05-24 06:18:07] New best model saved! Val loss: 0.8960 |
| [2026-05-24 06:18:18] Epoch 1 | Step 1010 | Loss: 0.9712 | LM: 0.3512 | LB: 1.2432 | CL0: 2.9 | CL1: 3.2 | HR0: 0.352/SR0: 0.347 | HR1: 0.338/SR1: 0.311 | LR: 7.47e-05 |
| [2026-05-24 06:18:29] Epoch 1 | Step 1020 | Loss: 0.9704 | LM: 0.3508 | LB: 1.2420 | CL0: 2.9 | CL1: 3.2 | HR0: 0.352/SR0: 0.347 | HR1: 0.337/SR1: 0.309 | LR: 7.53e-05 |
| [2026-05-24 06:18:40] Epoch 1 | Step 1030 | Loss: 0.9696 | LM: 0.3514 | LB: 1.2407 | CL0: 2.9 | CL1: 3.2 | HR0: 0.352/SR0: 0.347 | HR1: 0.336/SR1: 0.308 | LR: 7.59e-05 |
| [2026-05-24 06:18:51] Epoch 1 | Step 1040 | Loss: 0.9688 | LM: 0.3517 | LB: 1.2395 | CL0: 2.9 | CL1: 3.2 | HR0: 0.352/SR0: 0.347 | HR1: 0.335/SR1: 0.307 | LR: 7.66e-05 |
| [2026-05-24 06:19:02] Epoch 1 | Step 1050 | Loss: 0.9683 | LM: 0.3515 | LB: 1.2384 | CL0: 2.9 | CL1: 3.2 | HR0: 0.352/SR0: 0.346 | HR1: 0.334/SR1: 0.306 | LR: 7.72e-05 |
| [2026-05-24 06:19:13] Epoch 1 | Step 1060 | Loss: 0.9675 | LM: 0.3517 | LB: 1.2372 | CL0: 2.9 | CL1: 3.3 | HR0: 0.352/SR0: 0.346 | HR1: 0.333/SR1: 0.305 | LR: 7.79e-05 |
| [2026-05-24 06:19:24] Epoch 1 | Step 1070 | Loss: 0.9669 | LM: 0.3511 | LB: 1.2361 | CL0: 2.9 | CL1: 3.3 | HR0: 0.352/SR0: 0.346 | HR1: 0.332/SR1: 0.304 | LR: 7.85e-05 |
| [2026-05-24 06:19:35] Epoch 1 | Step 1080 | Loss: 0.9661 | LM: 0.3504 | LB: 1.2349 | CL0: 2.9 | CL1: 3.3 | HR0: 0.352/SR0: 0.346 | HR1: 0.331/SR1: 0.303 | LR: 7.91e-05 |
| [2026-05-24 06:19:46] Epoch 1 | Step 1090 | Loss: 0.9653 | LM: 0.3501 | LB: 1.2337 | CL0: 2.9 | CL1: 3.3 | HR0: 0.352/SR0: 0.346 | HR1: 0.330/SR1: 0.302 | LR: 7.98e-05 |
| [2026-05-24 06:19:57] Epoch 1 | Step 1100 | Loss: 0.9645 | LM: 0.3500 | LB: 1.2325 | CL0: 2.9 | CL1: 3.3 | HR0: 0.351/SR0: 0.346 | HR1: 0.329/SR1: 0.301 | LR: 8.04e-05 |
| [2026-05-24 06:20:08] Epoch 1 | Step 1110 | Loss: 0.9639 | LM: 0.3497 | LB: 1.2314 | CL0: 2.9 | CL1: 3.3 | HR0: 0.351/SR0: 0.345 | HR1: 0.328/SR1: 0.300 | LR: 8.11e-05 |
| [2026-05-24 06:20:18] Epoch 1 | Step 1120 | Loss: 0.9635 | LM: 0.3501 | LB: 1.2303 | CL0: 2.9 | CL1: 3.3 | HR0: 0.351/SR0: 0.345 | HR1: 0.327/SR1: 0.299 | LR: 8.17e-05 |
| [2026-05-24 06:20:29] Epoch 1 | Step 1130 | Loss: 0.9627 | LM: 0.3495 | LB: 1.2294 | CL0: 2.9 | CL1: 3.3 | HR0: 0.351/SR0: 0.345 | HR1: 0.326/SR1: 0.298 | LR: 8.23e-05 |
| [2026-05-24 06:20:41] Epoch 1 | Step 1140 | Loss: 0.9623 | LM: 0.3496 | LB: 1.2284 | CL0: 2.9 | CL1: 3.4 | HR0: 0.351/SR0: 0.345 | HR1: 0.325/SR1: 0.297 | LR: 8.30e-05 |
| [2026-05-24 06:20:52] Epoch 1 | Step 1150 | Loss: 0.9618 | LM: 0.3495 | LB: 1.2273 | CL0: 2.9 | CL1: 3.4 | HR0: 0.351/SR0: 0.345 | HR1: 0.324/SR1: 0.296 | LR: 8.36e-05 |
| [2026-05-24 06:21:03] Epoch 1 | Step 1160 | Loss: 0.9613 | LM: 0.3495 | LB: 1.2263 | CL0: 2.9 | CL1: 3.4 | HR0: 0.351/SR0: 0.345 | HR1: 0.323/SR1: 0.295 | LR: 8.43e-05 |
| [2026-05-24 06:21:13] Epoch 1 | Step 1170 | Loss: 0.9608 | LM: 0.3496 | LB: 1.2252 | CL0: 2.9 | CL1: 3.4 | HR0: 0.351/SR0: 0.344 | HR1: 0.322/SR1: 0.294 | LR: 8.49e-05 |
| [2026-05-24 06:21:24] Epoch 1 | Step 1180 | Loss: 0.9604 | LM: 0.3495 | LB: 1.2242 | CL0: 2.9 | CL1: 3.4 | HR0: 0.351/SR0: 0.344 | HR1: 0.321/SR1: 0.294 | LR: 8.55e-05 |
| [2026-05-24 06:21:35] Epoch 1 | Step 1190 | Loss: 0.9598 | LM: 0.3497 | LB: 1.2232 | CL0: 2.9 | CL1: 3.4 | HR0: 0.351/SR0: 0.344 | HR1: 0.320/SR1: 0.293 | LR: 8.62e-05 |
| [2026-05-24 06:21:47] Epoch 1 | Step 1200 | Loss: 0.9592 | LM: 0.3495 | LB: 1.2223 | CL0: 2.9 | CL1: 3.4 | HR0: 0.350/SR0: 0.344 | HR1: 0.320/SR1: 0.292 | LR: 8.68e-05 |
| [2026-05-24 06:21:58] Epoch 1 | Step 1210 | Loss: 0.9588 | LM: 0.3498 | LB: 1.2214 | CL0: 2.9 | CL1: 3.4 | HR0: 0.350/SR0: 0.344 | HR1: 0.319/SR1: 0.291 | LR: 8.75e-05 |
| [2026-05-24 06:22:09] Epoch 1 | Step 1220 | Loss: 0.9581 | LM: 0.3500 | LB: 1.2205 | CL0: 2.9 | CL1: 3.4 | HR0: 0.350/SR0: 0.344 | HR1: 0.318/SR1: 0.290 | LR: 8.81e-05 |
| [2026-05-24 06:22:20] Epoch 1 | Step 1230 | Loss: 0.9575 | LM: 0.3498 | LB: 1.2195 | CL0: 2.9 | CL1: 3.4 | HR0: 0.350/SR0: 0.343 | HR1: 0.318/SR1: 0.290 | LR: 8.87e-05 |
| [2026-05-24 06:22:31] Epoch 1 | Step 1240 | Loss: 0.9572 | LM: 0.3498 | LB: 1.2187 | CL0: 2.9 | CL1: 3.4 | HR0: 0.350/SR0: 0.343 | HR1: 0.317/SR1: 0.289 | LR: 8.94e-05 |
| [2026-05-24 06:22:42] Epoch 1 | Step 1250 | Loss: 0.9568 | LM: 0.3501 | LB: 1.2179 | CL0: 2.9 | CL1: 3.5 | HR0: 0.350/SR0: 0.343 | HR1: 0.316/SR1: 0.289 | LR: 9.00e-05 |
| [2026-05-24 06:22:53] Epoch 1 | Step 1260 | Loss: 0.9562 | LM: 0.3498 | LB: 1.2170 | CL0: 2.9 | CL1: 3.5 | HR0: 0.350/SR0: 0.343 | HR1: 0.315/SR1: 0.288 | LR: 9.07e-05 |
| [2026-05-24 06:23:04] Epoch 1 | Step 1270 | Loss: 0.9554 | LM: 0.3494 | LB: 1.2161 | CL0: 2.9 | CL1: 3.5 | HR0: 0.350/SR0: 0.343 | HR1: 0.315/SR1: 0.287 | LR: 9.13e-05 |
| [2026-05-24 06:23:15] Epoch 1 | Step 1280 | Loss: 0.9548 | LM: 0.3497 | LB: 1.2153 | CL0: 2.9 | CL1: 3.5 | HR0: 0.350/SR0: 0.343 | HR1: 0.314/SR1: 0.286 | LR: 9.19e-05 |
| [2026-05-24 06:23:25] Epoch 1 | Step 1290 | Loss: 0.9544 | LM: 0.3497 | LB: 1.2145 | CL0: 2.9 | CL1: 3.5 | HR0: 0.350/SR0: 0.343 | HR1: 0.313/SR1: 0.285 | LR: 9.26e-05 |
| [2026-05-24 06:23:36] Epoch 1 | Step 1300 | Loss: 0.9541 | LM: 0.3500 | LB: 1.2136 | CL0: 2.9 | CL1: 3.5 | HR0: 0.350/SR0: 0.342 | HR1: 0.313/SR1: 0.285 | LR: 9.32e-05 |
| [2026-05-24 06:23:47] Epoch 1 | Step 1310 | Loss: 0.9537 | LM: 0.3511 | LB: 1.2127 | CL0: 2.9 | CL1: 3.5 | HR0: 0.349/SR0: 0.342 | HR1: 0.312/SR1: 0.284 | LR: 9.39e-05 |
| [2026-05-24 06:23:58] Epoch 1 | Step 1320 | Loss: 0.9531 | LM: 0.3511 | LB: 1.2117 | CL0: 2.9 | CL1: 3.5 | HR0: 0.349/SR0: 0.342 | HR1: 0.311/SR1: 0.283 | LR: 9.45e-05 |
| [2026-05-24 06:24:10] Epoch 1 | Step 1330 | Loss: 0.9527 | LM: 0.3509 | LB: 1.2109 | CL0: 2.9 | CL1: 3.5 | HR0: 0.349/SR0: 0.342 | HR1: 0.310/SR1: 0.283 | LR: 9.51e-05 |
| [2026-05-24 06:24:20] Epoch 1 | Step 1340 | Loss: 0.9522 | LM: 0.3505 | LB: 1.2100 | CL0: 2.9 | CL1: 3.5 | HR0: 0.349/SR0: 0.342 | HR1: 0.310/SR1: 0.282 | LR: 9.58e-05 |
| [2026-05-24 06:24:31] Epoch 1 | Step 1350 | Loss: 0.9516 | LM: 0.3503 | LB: 1.2091 | CL0: 2.9 | CL1: 3.5 | HR0: 0.349/SR0: 0.341 | HR1: 0.309/SR1: 0.281 | LR: 9.64e-05 |
| [2026-05-24 06:24:42] Epoch 1 | Step 1360 | Loss: 0.9513 | LM: 0.3504 | LB: 1.2083 | CL0: 2.9 | CL1: 3.5 | HR0: 0.349/SR0: 0.341 | HR1: 0.309/SR1: 0.281 | LR: 9.71e-05 |
| [2026-05-24 06:24:52] Epoch 1 | Step 1370 | Loss: 0.9507 | LM: 0.3501 | LB: 1.2075 | CL0: 2.9 | CL1: 3.6 | HR0: 0.349/SR0: 0.341 | HR1: 0.308/SR1: 0.280 | LR: 9.77e-05 |
| [2026-05-24 06:25:03] Epoch 1 | Step 1380 | Loss: 0.9501 | LM: 0.3503 | LB: 1.2066 | CL0: 2.9 | CL1: 3.6 | HR0: 0.348/SR0: 0.341 | HR1: 0.307/SR1: 0.279 | LR: 9.83e-05 |
| [2026-05-24 06:25:14] Epoch 1 | Step 1390 | Loss: 0.9496 | LM: 0.3502 | LB: 1.2058 | CL0: 2.9 | CL1: 3.6 | HR0: 0.348/SR0: 0.341 | HR1: 0.306/SR1: 0.278 | LR: 9.90e-05 |
| [2026-05-24 06:25:25] Epoch 1 | Step 1400 | Loss: 0.9493 | LM: 0.3506 | LB: 1.2049 | CL0: 2.9 | CL1: 3.6 | HR0: 0.348/SR0: 0.340 | HR1: 0.306/SR1: 0.278 | LR: 9.96e-05 |
| [2026-05-24 06:25:36] Epoch 1 | Step 1410 | Loss: 0.9488 | LM: 0.3511 | LB: 1.2040 | CL0: 2.9 | CL1: 3.6 | HR0: 0.348/SR0: 0.340 | HR1: 0.305/SR1: 0.277 | LR: 1.00e-04 |
| [2026-05-24 06:25:47] Epoch 1 | Step 1420 | Loss: 0.9485 | LM: 0.3509 | LB: 1.2032 | CL0: 2.9 | CL1: 3.6 | HR0: 0.348/SR0: 0.340 | HR1: 0.304/SR1: 0.276 | LR: 1.00e-04 |
| [2026-05-24 06:25:57] Epoch 1 | Step 1430 | Loss: 0.9479 | LM: 0.3505 | LB: 1.2024 | CL0: 2.9 | CL1: 3.6 | HR0: 0.348/SR0: 0.340 | HR1: 0.304/SR1: 0.276 | LR: 1.00e-04 |
| [2026-05-24 06:26:08] Epoch 1 | Step 1440 | Loss: 0.9475 | LM: 0.3504 | LB: 1.2017 | CL0: 2.9 | CL1: 3.6 | HR0: 0.347/SR0: 0.339 | HR1: 0.303/SR1: 0.275 | LR: 1.00e-04 |
| [2026-05-24 06:26:19] Epoch 1 | Step 1450 | Loss: 0.9472 | LM: 0.3505 | LB: 1.2009 | CL0: 2.9 | CL1: 3.6 | HR0: 0.347/SR0: 0.339 | HR1: 0.302/SR1: 0.274 | LR: 1.00e-04 |
| [2026-05-24 06:26:30] Epoch 1 | Step 1460 | Loss: 0.9468 | LM: 0.3507 | LB: 1.2001 | CL0: 2.9 | CL1: 3.6 | HR0: 0.347/SR0: 0.339 | HR1: 0.302/SR1: 0.274 | LR: 1.00e-04 |
| [2026-05-24 06:26:41] Epoch 1 | Step 1470 | Loss: 0.9463 | LM: 0.3505 | LB: 1.1994 | CL0: 2.9 | CL1: 3.6 | HR0: 0.347/SR0: 0.339 | HR1: 0.301/SR1: 0.273 | LR: 1.00e-04 |
| [2026-05-24 06:26:52] Epoch 1 | Step 1480 | Loss: 0.9460 | LM: 0.3506 | LB: 1.1986 | CL0: 2.9 | CL1: 3.7 | HR0: 0.347/SR0: 0.339 | HR1: 0.300/SR1: 0.273 | LR: 1.00e-04 |
| [2026-05-24 06:27:03] Epoch 1 | Step 1490 | Loss: 0.9457 | LM: 0.3509 | LB: 1.1978 | CL0: 2.9 | CL1: 3.7 | HR0: 0.347/SR0: 0.338 | HR1: 0.300/SR1: 0.272 | LR: 1.00e-04 |
| [2026-05-24 06:27:14] Epoch 1 | Step 1500 | Loss: 0.9452 | LM: 0.3508 | LB: 1.1970 | CL0: 2.9 | CL1: 3.7 | HR0: 0.346/SR0: 0.338 | HR1: 0.299/SR1: 0.271 | LR: 1.00e-04 |
| [2026-05-24 06:27:24] Epoch 1 | Step 1510 | Loss: 0.9448 | LM: 0.3507 | LB: 1.1962 | CL0: 2.9 | CL1: 3.7 | HR0: 0.346/SR0: 0.338 | HR1: 0.298/SR1: 0.271 | LR: 1.00e-04 |
| [2026-05-24 06:27:35] Epoch 1 | Step 1520 | Loss: 0.9442 | LM: 0.3503 | LB: 1.1955 | CL0: 2.9 | CL1: 3.7 | HR0: 0.346/SR0: 0.338 | HR1: 0.298/SR1: 0.270 | LR: 1.00e-04 |
| [2026-05-24 06:27:46] Epoch 1 | Step 1530 | Loss: 0.9437 | LM: 0.3500 | LB: 1.1947 | CL0: 2.9 | CL1: 3.7 | HR0: 0.346/SR0: 0.337 | HR1: 0.297/SR1: 0.269 | LR: 1.00e-04 |
| [2026-05-24 06:27:57] Epoch 1 | Step 1540 | Loss: 0.9432 | LM: 0.3497 | LB: 1.1941 | CL0: 2.9 | CL1: 3.7 | HR0: 0.346/SR0: 0.337 | HR1: 0.297/SR1: 0.269 | LR: 1.00e-04 |
| [2026-05-24 06:28:08] Epoch 1 | Step 1550 | Loss: 0.9429 | LM: 0.3497 | LB: 1.1933 | CL0: 2.9 | CL1: 3.7 | HR0: 0.346/SR0: 0.337 | HR1: 0.296/SR1: 0.268 | LR: 1.00e-04 |
| [2026-05-24 06:28:19] Epoch 1 | Step 1560 | Loss: 0.9427 | LM: 0.3497 | LB: 1.1926 | CL0: 2.9 | CL1: 3.7 | HR0: 0.346/SR0: 0.337 | HR1: 0.295/SR1: 0.267 | LR: 1.00e-04 |
| [2026-05-24 06:28:31] Epoch 1 | Step 1570 | Loss: 0.9423 | LM: 0.3493 | LB: 1.1918 | CL0: 2.9 | CL1: 3.7 | HR0: 0.345/SR0: 0.337 | HR1: 0.295/SR1: 0.267 | LR: 1.00e-04 |
| [2026-05-24 06:28:41] Epoch 1 | Step 1580 | Loss: 0.9419 | LM: 0.3495 | LB: 1.1911 | CL0: 2.9 | CL1: 3.7 | HR0: 0.345/SR0: 0.336 | HR1: 0.294/SR1: 0.266 | LR: 1.00e-04 |
| [2026-05-24 06:28:52] Epoch 1 | Step 1590 | Loss: 0.9413 | LM: 0.3493 | LB: 1.1903 | CL0: 2.9 | CL1: 3.7 | HR0: 0.345/SR0: 0.336 | HR1: 0.294/SR1: 0.266 | LR: 1.00e-04 |
| [2026-05-24 06:29:03] Epoch 1 | Step 1600 | Loss: 0.9409 | LM: 0.3496 | LB: 1.1896 | CL0: 2.9 | CL1: 3.8 | HR0: 0.345/SR0: 0.336 | HR1: 0.293/SR1: 0.265 | LR: 1.00e-04 |
| [2026-05-24 06:29:14] Epoch 1 | Step 1610 | Loss: 0.9405 | LM: 0.3497 | LB: 1.1889 | CL0: 2.9 | CL1: 3.8 | HR0: 0.345/SR0: 0.336 | HR1: 0.293/SR1: 0.265 | LR: 1.00e-04 |
| [2026-05-24 06:29:24] Epoch 1 | Step 1620 | Loss: 0.9400 | LM: 0.3500 | LB: 1.1883 | CL0: 2.9 | CL1: 3.8 | HR0: 0.345/SR0: 0.335 | HR1: 0.292/SR1: 0.264 | LR: 1.00e-04 |
| [2026-05-24 06:29:35] Epoch 1 | Step 1630 | Loss: 0.9397 | LM: 0.3498 | LB: 1.1876 | CL0: 2.9 | CL1: 3.8 | HR0: 0.344/SR0: 0.335 | HR1: 0.292/SR1: 0.264 | LR: 1.00e-04 |
| [2026-05-24 06:29:46] Epoch 1 | Step 1640 | Loss: 0.9394 | LM: 0.3497 | LB: 1.1870 | CL0: 2.9 | CL1: 3.8 | HR0: 0.344/SR0: 0.335 | HR1: 0.291/SR1: 0.263 | LR: 1.00e-04 |
| [2026-05-24 06:29:57] Epoch 1 | Step 1650 | Loss: 0.9390 | LM: 0.3493 | LB: 1.1864 | CL0: 2.9 | CL1: 3.8 | HR0: 0.344/SR0: 0.335 | HR1: 0.290/SR1: 0.262 | LR: 1.00e-04 |
| [2026-05-24 06:30:08] Epoch 1 | Step 1660 | Loss: 0.9385 | LM: 0.3491 | LB: 1.1858 | CL0: 2.9 | CL1: 3.8 | HR0: 0.344/SR0: 0.335 | HR1: 0.290/SR1: 0.262 | LR: 1.00e-04 |
| [2026-05-24 06:30:18] Epoch 1 | Step 1670 | Loss: 0.9382 | LM: 0.3490 | LB: 1.1851 | CL0: 2.9 | CL1: 3.8 | HR0: 0.344/SR0: 0.335 | HR1: 0.289/SR1: 0.261 | LR: 1.00e-04 |
| [2026-05-24 06:30:29] Epoch 1 | Step 1680 | Loss: 0.9378 | LM: 0.3489 | LB: 1.1845 | CL0: 2.9 | CL1: 3.8 | HR0: 0.344/SR0: 0.334 | HR1: 0.289/SR1: 0.261 | LR: 1.00e-04 |
| [2026-05-24 06:30:39] Epoch 1 | Step 1690 | Loss: 0.9374 | LM: 0.3491 | LB: 1.1839 | CL0: 2.9 | CL1: 3.8 | HR0: 0.344/SR0: 0.334 | HR1: 0.288/SR1: 0.260 | LR: 1.00e-04 |
| [2026-05-24 06:30:51] Epoch 1 | Step 1700 | Loss: 0.9368 | LM: 0.3486 | LB: 1.1832 | CL0: 2.9 | CL1: 3.8 | HR0: 0.343/SR0: 0.334 | HR1: 0.288/SR1: 0.260 | LR: 1.00e-04 |
| [2026-05-24 06:31:02] Epoch 1 | Step 1710 | Loss: 0.9364 | LM: 0.3485 | LB: 1.1826 | CL0: 2.9 | CL1: 3.8 | HR0: 0.343/SR0: 0.334 | HR1: 0.288/SR1: 0.260 | LR: 1.00e-04 |
| [2026-05-24 06:31:13] Epoch 1 | Step 1720 | Loss: 0.9363 | LM: 0.3485 | LB: 1.1820 | CL0: 2.9 | CL1: 3.8 | HR0: 0.343/SR0: 0.333 | HR1: 0.287/SR1: 0.259 | LR: 1.00e-04 |
| [2026-05-24 06:31:23] Epoch 1 | Step 1730 | Loss: 0.9361 | LM: 0.3485 | LB: 1.1814 | CL0: 2.9 | CL1: 3.8 | HR0: 0.343/SR0: 0.333 | HR1: 0.287/SR1: 0.259 | LR: 1.00e-04 |
| [2026-05-24 06:31:34] Epoch 1 | Step 1740 | Loss: 0.9355 | LM: 0.3484 | LB: 1.1807 | CL0: 2.9 | CL1: 3.9 | HR0: 0.343/SR0: 0.333 | HR1: 0.286/SR1: 0.258 | LR: 1.00e-04 |
| [2026-05-24 06:31:45] Epoch 1 | Step 1750 | Loss: 0.9351 | LM: 0.3484 | LB: 1.1801 | CL0: 2.9 | CL1: 3.9 | HR0: 0.343/SR0: 0.333 | HR1: 0.286/SR1: 0.258 | LR: 1.00e-04 |
| [2026-05-24 06:31:56] Epoch 1 | Step 1760 | Loss: 0.9346 | LM: 0.3483 | LB: 1.1794 | CL0: 2.9 | CL1: 3.9 | HR0: 0.342/SR0: 0.333 | HR1: 0.285/SR1: 0.257 | LR: 1.00e-04 |
| [2026-05-24 06:32:07] Epoch 1 | Step 1770 | Loss: 0.9343 | LM: 0.3486 | LB: 1.1788 | CL0: 2.9 | CL1: 3.9 | HR0: 0.342/SR0: 0.332 | HR1: 0.285/SR1: 0.257 | LR: 1.00e-04 |
| [2026-05-24 06:32:17] Epoch 1 | Step 1780 | Loss: 0.9341 | LM: 0.3487 | LB: 1.1783 | CL0: 2.9 | CL1: 3.9 | HR0: 0.342/SR0: 0.332 | HR1: 0.284/SR1: 0.256 | LR: 1.00e-04 |
| [2026-05-24 06:32:28] Epoch 1 | Step 1790 | Loss: 0.9339 | LM: 0.3488 | LB: 1.1777 | CL0: 2.9 | CL1: 3.9 | HR0: 0.342/SR0: 0.332 | HR1: 0.284/SR1: 0.256 | LR: 1.00e-04 |
| [2026-05-24 06:32:39] Epoch 1 | Step 1800 | Loss: 0.9336 | LM: 0.3490 | LB: 1.1771 | CL0: 2.9 | CL1: 3.9 | HR0: 0.342/SR0: 0.332 | HR1: 0.284/SR1: 0.256 | LR: 1.00e-04 |
| [2026-05-24 06:32:50] Epoch 1 | Step 1810 | Loss: 0.9332 | LM: 0.3486 | LB: 1.1765 | CL0: 2.9 | CL1: 3.9 | HR0: 0.342/SR0: 0.331 | HR1: 0.283/SR1: 0.255 | LR: 1.00e-04 |
| [2026-05-24 06:33:01] Epoch 1 | Step 1820 | Loss: 0.9329 | LM: 0.3487 | LB: 1.1759 | CL0: 2.9 | CL1: 3.9 | HR0: 0.342/SR0: 0.331 | HR1: 0.283/SR1: 0.255 | LR: 1.00e-04 |
| [2026-05-24 06:33:11] Epoch 1 | Step 1830 | Loss: 0.9326 | LM: 0.3488 | LB: 1.1754 | CL0: 2.9 | CL1: 3.9 | HR0: 0.341/SR0: 0.331 | HR1: 0.282/SR1: 0.254 | LR: 1.00e-04 |
| [2026-05-24 06:33:22] Epoch 1 | Step 1840 | Loss: 0.9323 | LM: 0.3488 | LB: 1.1748 | CL0: 2.9 | CL1: 3.9 | HR0: 0.341/SR0: 0.331 | HR1: 0.282/SR1: 0.254 | LR: 1.00e-04 |
| [2026-05-24 06:33:33] Epoch 1 | Step 1850 | Loss: 0.9321 | LM: 0.3488 | LB: 1.1743 | CL0: 3.0 | CL1: 3.9 | HR0: 0.341/SR0: 0.331 | HR1: 0.282/SR1: 0.253 | LR: 1.00e-04 |
| [2026-05-24 06:33:44] Epoch 1 | Step 1860 | Loss: 0.9318 | LM: 0.3486 | LB: 1.1737 | CL0: 3.0 | CL1: 3.9 | HR0: 0.341/SR0: 0.330 | HR1: 0.281/SR1: 0.253 | LR: 1.00e-04 |
| [2026-05-24 06:33:56] Epoch 1 | Step 1870 | Loss: 0.9315 | LM: 0.3485 | LB: 1.1732 | CL0: 3.0 | CL1: 3.9 | HR0: 0.341/SR0: 0.330 | HR1: 0.281/SR1: 0.253 | LR: 1.00e-04 |
| [2026-05-24 06:34:06] Epoch 1 | Step 1880 | Loss: 0.9311 | LM: 0.3485 | LB: 1.1727 | CL0: 3.0 | CL1: 3.9 | HR0: 0.341/SR0: 0.330 | HR1: 0.280/SR1: 0.252 | LR: 1.00e-04 |
| [2026-05-24 06:34:17] Epoch 1 | Step 1890 | Loss: 0.9309 | LM: 0.3486 | LB: 1.1722 | CL0: 3.0 | CL1: 3.9 | HR0: 0.341/SR0: 0.330 | HR1: 0.280/SR1: 0.252 | LR: 1.00e-04 |
| [2026-05-24 06:34:28] Epoch 1 | Step 1900 | Loss: 0.9307 | LM: 0.3488 | LB: 1.1716 | CL0: 3.0 | CL1: 3.9 | HR0: 0.340/SR0: 0.330 | HR1: 0.279/SR1: 0.251 | LR: 1.00e-04 |
| [2026-05-24 06:34:39] Epoch 1 | Step 1910 | Loss: 0.9305 | LM: 0.3490 | LB: 1.1710 | CL0: 3.0 | CL1: 3.9 | HR0: 0.340/SR0: 0.329 | HR1: 0.279/SR1: 0.251 | LR: 1.00e-04 |
| [2026-05-24 06:34:50] Epoch 1 | Step 1920 | Loss: 0.9300 | LM: 0.3495 | LB: 1.1705 | CL0: 3.0 | CL1: 4.0 | HR0: 0.340/SR0: 0.329 | HR1: 0.279/SR1: 0.250 | LR: 1.00e-04 |
| [2026-05-24 06:35:00] Epoch 1 | Step 1930 | Loss: 0.9298 | LM: 0.3495 | LB: 1.1700 | CL0: 3.0 | CL1: 4.0 | HR0: 0.340/SR0: 0.329 | HR1: 0.278/SR1: 0.250 | LR: 1.00e-04 |
| [2026-05-24 06:35:11] Epoch 1 | Step 1940 | Loss: 0.9296 | LM: 0.3497 | LB: 1.1695 | CL0: 3.0 | CL1: 4.0 | HR0: 0.340/SR0: 0.329 | HR1: 0.278/SR1: 0.250 | LR: 1.00e-04 |
| [2026-05-24 06:35:22] Epoch 1 | Step 1950 | Loss: 0.9293 | LM: 0.3496 | LB: 1.1690 | CL0: 3.0 | CL1: 4.0 | HR0: 0.340/SR0: 0.329 | HR1: 0.277/SR1: 0.249 | LR: 1.00e-04 |
| [2026-05-24 06:35:32] Epoch 1 | Step 1960 | Loss: 0.9289 | LM: 0.3495 | LB: 1.1685 | CL0: 3.0 | CL1: 4.0 | HR0: 0.340/SR0: 0.329 | HR1: 0.277/SR1: 0.249 | LR: 1.00e-04 |
| [2026-05-24 06:35:43] Epoch 1 | Step 1970 | Loss: 0.9285 | LM: 0.3496 | LB: 1.1680 | CL0: 3.0 | CL1: 4.0 | HR0: 0.339/SR0: 0.328 | HR1: 0.277/SR1: 0.249 | LR: 1.00e-04 |
| [2026-05-24 06:35:54] Epoch 1 | Step 1980 | Loss: 0.9281 | LM: 0.3494 | LB: 1.1674 | CL0: 3.0 | CL1: 4.0 | HR0: 0.339/SR0: 0.328 | HR1: 0.276/SR1: 0.248 | LR: 1.00e-04 |
| [2026-05-24 06:36:05] Epoch 1 | Step 1990 | Loss: 0.9279 | LM: 0.3496 | LB: 1.1670 | CL0: 3.0 | CL1: 4.0 | HR0: 0.339/SR0: 0.328 | HR1: 0.276/SR1: 0.248 | LR: 1.00e-04 |
| [2026-05-24 06:36:15] Epoch 1 | Step 2000 | Loss: 0.9275 | LM: 0.3494 | LB: 1.1665 | CL0: 3.0 | CL1: 4.0 | HR0: 0.339/SR0: 0.328 | HR1: 0.276/SR1: 0.247 | LR: 1.00e-04 |
| [2026-05-24 06:36:17] Validation | Batch 10/1463 | Loss: 0.8276 | LM_LOSS: 0.2997 | LB_LOSS: 1.0559 |
| [2026-05-24 06:36:18] Validation | Batch 20/1463 | Loss: 0.8399 | LM_LOSS: 0.3095 | LB_LOSS: 1.0609 |
| [2026-05-24 06:36:21] Validation | Batch 30/1463 | Loss: 0.8488 | LM_LOSS: 0.3177 | LB_LOSS: 1.0621 |
| [2026-05-24 06:36:23] Validation | Batch 40/1463 | Loss: 0.8587 | LM_LOSS: 0.3266 | LB_LOSS: 1.0642 |
| [2026-05-24 06:36:25] Validation | Batch 50/1463 | Loss: 0.8661 | LM_LOSS: 0.3346 | LB_LOSS: 1.0630 |
| [2026-05-24 06:36:27] Validation | Batch 60/1463 | Loss: 0.8661 | LM_LOSS: 0.3348 | LB_LOSS: 1.0627 |
| [2026-05-24 06:36:30] Validation | Batch 70/1463 | Loss: 0.8664 | LM_LOSS: 0.3349 | LB_LOSS: 1.0630 |
| [2026-05-24 06:36:32] Validation | Batch 80/1463 | Loss: 0.8682 | LM_LOSS: 0.3367 | LB_LOSS: 1.0630 |
| [2026-05-24 06:36:34] Validation | Batch 90/1463 | Loss: 0.8678 | LM_LOSS: 0.3364 | LB_LOSS: 1.0628 |
| [2026-05-24 06:36:36] Validation | Batch 100/1463 | Loss: 0.8682 | LM_LOSS: 0.3368 | LB_LOSS: 1.0628 |
| [2026-05-24 06:36:38] Validation | Batch 110/1463 | Loss: 0.8669 | LM_LOSS: 0.3352 | LB_LOSS: 1.0635 |
| [2026-05-24 06:36:39] Validation | Batch 120/1463 | Loss: 0.8685 | LM_LOSS: 0.3367 | LB_LOSS: 1.0637 |
| [2026-05-24 06:36:41] Validation | Batch 130/1463 | Loss: 0.8711 | LM_LOSS: 0.3392 | LB_LOSS: 1.0638 |
| [2026-05-24 06:36:44] Validation | Batch 140/1463 | Loss: 0.8718 | LM_LOSS: 0.3400 | LB_LOSS: 1.0636 |
| [2026-05-24 06:36:46] Validation | Batch 150/1463 | Loss: 0.8703 | LM_LOSS: 0.3383 | LB_LOSS: 1.0639 |
| [2026-05-24 06:36:48] Validation | Batch 160/1463 | Loss: 0.8707 | LM_LOSS: 0.3389 | LB_LOSS: 1.0636 |
| [2026-05-24 06:36:50] Validation | Batch 170/1463 | Loss: 0.8705 | LM_LOSS: 0.3387 | LB_LOSS: 1.0637 |
| [2026-05-24 06:36:52] Validation | Batch 180/1463 | Loss: 0.8713 | LM_LOSS: 0.3395 | LB_LOSS: 1.0637 |
| [2026-05-24 06:36:54] Validation | Batch 190/1463 | Loss: 0.8721 | LM_LOSS: 0.3402 | LB_LOSS: 1.0638 |
| [2026-05-24 06:36:56] Validation | Batch 200/1463 | Loss: 0.8721 | LM_LOSS: 0.3402 | LB_LOSS: 1.0638 |
| [2026-05-24 06:36:58] Validation | Batch 210/1463 | Loss: 0.8724 | LM_LOSS: 0.3405 | LB_LOSS: 1.0638 |
| [2026-05-24 06:37:00] Validation | Batch 220/1463 | Loss: 0.8718 | LM_LOSS: 0.3399 | LB_LOSS: 1.0639 |
| [2026-05-24 06:37:02] Validation | Batch 230/1463 | Loss: 0.8737 | LM_LOSS: 0.3419 | LB_LOSS: 1.0637 |
| [2026-05-24 06:37:04] Validation | Batch 240/1463 | Loss: 0.8747 | LM_LOSS: 0.3429 | LB_LOSS: 1.0636 |
| [2026-05-24 06:37:07] Validation | Batch 250/1463 | Loss: 0.8738 | LM_LOSS: 0.3420 | LB_LOSS: 1.0637 |
| [2026-05-24 06:37:08] Validation | Batch 260/1463 | Loss: 0.8757 | LM_LOSS: 0.3437 | LB_LOSS: 1.0640 |
| [2026-05-24 06:37:10] Validation | Batch 270/1463 | Loss: 0.8743 | LM_LOSS: 0.3423 | LB_LOSS: 1.0641 |
| [2026-05-24 06:37:12] Validation | Batch 280/1463 | Loss: 0.8753 | LM_LOSS: 0.3432 | LB_LOSS: 1.0642 |
| [2026-05-24 06:37:15] Validation | Batch 290/1463 | Loss: 0.8747 | LM_LOSS: 0.3426 | LB_LOSS: 1.0642 |
| [2026-05-24 06:37:16] Validation | Batch 300/1463 | Loss: 0.8749 | LM_LOSS: 0.3427 | LB_LOSS: 1.0644 |
| [2026-05-24 06:37:18] Validation | Batch 310/1463 | Loss: 0.8759 | LM_LOSS: 0.3438 | LB_LOSS: 1.0643 |
| [2026-05-24 06:37:20] Validation | Batch 320/1463 | Loss: 0.8741 | LM_LOSS: 0.3421 | LB_LOSS: 1.0640 |
| [2026-05-24 06:37:22] Validation | Batch 330/1463 | Loss: 0.8741 | LM_LOSS: 0.3421 | LB_LOSS: 1.0640 |
| [2026-05-24 06:37:24] Validation | Batch 340/1463 | Loss: 0.8737 | LM_LOSS: 0.3417 | LB_LOSS: 1.0640 |
| [2026-05-24 06:37:26] Validation | Batch 350/1463 | Loss: 0.8743 | LM_LOSS: 0.3423 | LB_LOSS: 1.0640 |
| [2026-05-24 06:37:28] Validation | Batch 360/1463 | Loss: 0.8740 | LM_LOSS: 0.3420 | LB_LOSS: 1.0641 |
| [2026-05-24 06:37:30] Validation | Batch 370/1463 | Loss: 0.8739 | LM_LOSS: 0.3419 | LB_LOSS: 1.0642 |
| [2026-05-24 06:37:32] Validation | Batch 380/1463 | Loss: 0.8738 | LM_LOSS: 0.3418 | LB_LOSS: 1.0640 |
| [2026-05-24 06:37:34] Validation | Batch 390/1463 | Loss: 0.8745 | LM_LOSS: 0.3425 | LB_LOSS: 1.0640 |
| [2026-05-24 06:37:36] Validation | Batch 400/1463 | Loss: 0.8744 | LM_LOSS: 0.3424 | LB_LOSS: 1.0641 |
| [2026-05-24 06:37:38] Validation | Batch 410/1463 | Loss: 0.8742 | LM_LOSS: 0.3420 | LB_LOSS: 1.0642 |
| [2026-05-24 06:37:40] Validation | Batch 420/1463 | Loss: 0.8743 | LM_LOSS: 0.3421 | LB_LOSS: 1.0643 |
| [2026-05-24 06:37:42] Validation | Batch 430/1463 | Loss: 0.8738 | LM_LOSS: 0.3416 | LB_LOSS: 1.0644 |
| [2026-05-24 06:37:44] Validation | Batch 440/1463 | Loss: 0.8741 | LM_LOSS: 0.3418 | LB_LOSS: 1.0644 |
| [2026-05-24 06:37:46] Validation | Batch 450/1463 | Loss: 0.8739 | LM_LOSS: 0.3416 | LB_LOSS: 1.0645 |
| [2026-05-24 06:37:48] Validation | Batch 460/1463 | Loss: 0.8740 | LM_LOSS: 0.3418 | LB_LOSS: 1.0645 |
| [2026-05-24 06:37:50] Validation | Batch 470/1463 | Loss: 0.8747 | LM_LOSS: 0.3425 | LB_LOSS: 1.0643 |
| [2026-05-24 06:37:52] Validation | Batch 480/1463 | Loss: 0.8745 | LM_LOSS: 0.3424 | LB_LOSS: 1.0643 |
| [2026-05-24 06:37:54] Validation | Batch 490/1463 | Loss: 0.8745 | LM_LOSS: 0.3424 | LB_LOSS: 1.0642 |
| [2026-05-24 06:37:57] Validation | Batch 500/1463 | Loss: 0.8743 | LM_LOSS: 0.3422 | LB_LOSS: 1.0642 |
| [2026-05-24 06:37:59] Validation | Batch 510/1463 | Loss: 0.8739 | LM_LOSS: 0.3417 | LB_LOSS: 1.0642 |
| [2026-05-24 06:38:01] Validation | Batch 520/1463 | Loss: 0.8734 | LM_LOSS: 0.3413 | LB_LOSS: 1.0643 |
| [2026-05-24 06:38:02] Validation | Batch 530/1463 | Loss: 0.8737 | LM_LOSS: 0.3415 | LB_LOSS: 1.0643 |
| [2026-05-24 06:38:04] Validation | Batch 540/1463 | Loss: 0.8740 | LM_LOSS: 0.3418 | LB_LOSS: 1.0644 |
| [2026-05-24 06:38:06] Validation | Batch 550/1463 | Loss: 0.8737 | LM_LOSS: 0.3415 | LB_LOSS: 1.0644 |
| [2026-05-24 06:38:08] Validation | Batch 560/1463 | Loss: 0.8741 | LM_LOSS: 0.3418 | LB_LOSS: 1.0646 |
| [2026-05-24 06:38:10] Validation | Batch 570/1463 | Loss: 0.8741 | LM_LOSS: 0.3418 | LB_LOSS: 1.0645 |
| [2026-05-24 06:38:12] Validation | Batch 580/1463 | Loss: 0.8739 | LM_LOSS: 0.3416 | LB_LOSS: 1.0645 |
| [2026-05-24 06:38:14] Validation | Batch 590/1463 | Loss: 0.8737 | LM_LOSS: 0.3414 | LB_LOSS: 1.0646 |
| [2026-05-24 06:38:17] Validation | Batch 600/1463 | Loss: 0.8741 | LM_LOSS: 0.3417 | LB_LOSS: 1.0647 |
| [2026-05-24 06:38:19] Validation | Batch 610/1463 | Loss: 0.8741 | LM_LOSS: 0.3417 | LB_LOSS: 1.0648 |
| [2026-05-24 06:38:21] Validation | Batch 620/1463 | Loss: 0.8735 | LM_LOSS: 0.3412 | LB_LOSS: 1.0647 |
| [2026-05-24 06:38:23] Validation | Batch 630/1463 | Loss: 0.8732 | LM_LOSS: 0.3408 | LB_LOSS: 1.0648 |
| [2026-05-24 06:38:25] Validation | Batch 640/1463 | Loss: 0.8730 | LM_LOSS: 0.3406 | LB_LOSS: 1.0649 |
| [2026-05-24 06:38:27] Validation | Batch 650/1463 | Loss: 0.8724 | LM_LOSS: 0.3400 | LB_LOSS: 1.0648 |
| [2026-05-24 06:38:28] Validation | Batch 660/1463 | Loss: 0.8719 | LM_LOSS: 0.3396 | LB_LOSS: 1.0648 |
| [2026-05-24 06:38:30] Validation | Batch 670/1463 | Loss: 0.8716 | LM_LOSS: 0.3393 | LB_LOSS: 1.0647 |
| [2026-05-24 06:38:32] Validation | Batch 680/1463 | Loss: 0.8715 | LM_LOSS: 0.3392 | LB_LOSS: 1.0646 |
| [2026-05-24 06:38:34] Validation | Batch 690/1463 | Loss: 0.8719 | LM_LOSS: 0.3396 | LB_LOSS: 1.0647 |
| [2026-05-24 06:38:36] Validation | Batch 700/1463 | Loss: 0.8717 | LM_LOSS: 0.3394 | LB_LOSS: 1.0646 |
| [2026-05-24 06:38:38] Validation | Batch 710/1463 | Loss: 0.8723 | LM_LOSS: 0.3400 | LB_LOSS: 1.0647 |
| [2026-05-24 06:38:40] Validation | Batch 720/1463 | Loss: 0.8731 | LM_LOSS: 0.3407 | LB_LOSS: 1.0648 |
| [2026-05-24 06:38:42] Validation | Batch 730/1463 | Loss: 0.8729 | LM_LOSS: 0.3405 | LB_LOSS: 1.0648 |
| [2026-05-24 06:38:44] Validation | Batch 740/1463 | Loss: 0.8726 | LM_LOSS: 0.3402 | LB_LOSS: 1.0648 |
| [2026-05-24 06:38:45] Validation | Batch 750/1463 | Loss: 0.8724 | LM_LOSS: 0.3401 | LB_LOSS: 1.0648 |
| [2026-05-24 06:38:47] Validation | Batch 760/1463 | Loss: 0.8722 | LM_LOSS: 0.3398 | LB_LOSS: 1.0648 |
| [2026-05-24 06:38:49] Validation | Batch 770/1463 | Loss: 0.8719 | LM_LOSS: 0.3395 | LB_LOSS: 1.0649 |
| [2026-05-24 06:38:50] Validation | Batch 780/1463 | Loss: 0.8717 | LM_LOSS: 0.3393 | LB_LOSS: 1.0648 |
| [2026-05-24 06:38:52] Validation | Batch 790/1463 | Loss: 0.8719 | LM_LOSS: 0.3395 | LB_LOSS: 1.0647 |
| [2026-05-24 06:38:54] Validation | Batch 800/1463 | Loss: 0.8718 | LM_LOSS: 0.3394 | LB_LOSS: 1.0647 |
| [2026-05-24 06:38:56] Validation | Batch 810/1463 | Loss: 0.8713 | LM_LOSS: 0.3390 | LB_LOSS: 1.0646 |
| [2026-05-24 06:38:58] Validation | Batch 820/1463 | Loss: 0.8716 | LM_LOSS: 0.3393 | LB_LOSS: 1.0646 |
| [2026-05-24 06:39:00] Validation | Batch 830/1463 | Loss: 0.8718 | LM_LOSS: 0.3395 | LB_LOSS: 1.0646 |
| [2026-05-24 06:39:02] Validation | Batch 840/1463 | Loss: 0.8718 | LM_LOSS: 0.3394 | LB_LOSS: 1.0647 |
| [2026-05-24 06:39:04] Validation | Batch 850/1463 | Loss: 0.8721 | LM_LOSS: 0.3397 | LB_LOSS: 1.0647 |
| [2026-05-24 06:39:06] Validation | Batch 860/1463 | Loss: 0.8721 | LM_LOSS: 0.3397 | LB_LOSS: 1.0647 |
| [2026-05-24 06:39:08] Validation | Batch 870/1463 | Loss: 0.8720 | LM_LOSS: 0.3396 | LB_LOSS: 1.0648 |
| [2026-05-24 06:39:10] Validation | Batch 880/1463 | Loss: 0.8713 | LM_LOSS: 0.3390 | LB_LOSS: 1.0648 |
| [2026-05-24 06:39:12] Validation | Batch 890/1463 | Loss: 0.8713 | LM_LOSS: 0.3390 | LB_LOSS: 1.0647 |
| [2026-05-24 06:39:14] Validation | Batch 900/1463 | Loss: 0.8710 | LM_LOSS: 0.3387 | LB_LOSS: 1.0647 |
| [2026-05-24 06:39:16] Validation | Batch 910/1463 | Loss: 0.8709 | LM_LOSS: 0.3385 | LB_LOSS: 1.0647 |
| [2026-05-24 06:39:19] Validation | Batch 920/1463 | Loss: 0.8710 | LM_LOSS: 0.3387 | LB_LOSS: 1.0647 |
| [2026-05-24 06:39:20] Validation | Batch 930/1463 | Loss: 0.8707 | LM_LOSS: 0.3384 | LB_LOSS: 1.0647 |
| [2026-05-24 06:39:22] Validation | Batch 940/1463 | Loss: 0.8704 | LM_LOSS: 0.3381 | LB_LOSS: 1.0646 |
| [2026-05-24 06:39:25] Validation | Batch 950/1463 | Loss: 0.8707 | LM_LOSS: 0.3384 | LB_LOSS: 1.0646 |
| [2026-05-24 06:39:26] Validation | Batch 960/1463 | Loss: 0.8708 | LM_LOSS: 0.3385 | LB_LOSS: 1.0645 |
| [2026-05-24 06:39:29] Validation | Batch 970/1463 | Loss: 0.8708 | LM_LOSS: 0.3386 | LB_LOSS: 1.0645 |
| [2026-05-24 06:39:31] Validation | Batch 980/1463 | Loss: 0.8711 | LM_LOSS: 0.3389 | LB_LOSS: 1.0644 |
| [2026-05-24 06:39:33] Validation | Batch 990/1463 | Loss: 0.8713 | LM_LOSS: 0.3391 | LB_LOSS: 1.0645 |
| [2026-05-24 06:39:35] Validation | Batch 1000/1463 | Loss: 0.8719 | LM_LOSS: 0.3397 | LB_LOSS: 1.0645 |
| [2026-05-24 06:39:37] Validation | Batch 1010/1463 | Loss: 0.8720 | LM_LOSS: 0.3397 | LB_LOSS: 1.0646 |
| [2026-05-24 06:39:39] Validation | Batch 1020/1463 | Loss: 0.8721 | LM_LOSS: 0.3398 | LB_LOSS: 1.0646 |
| [2026-05-24 06:39:41] Validation | Batch 1030/1463 | Loss: 0.8726 | LM_LOSS: 0.3402 | LB_LOSS: 1.0646 |
| [2026-05-24 06:39:43] Validation | Batch 1040/1463 | Loss: 0.8721 | LM_LOSS: 0.3398 | LB_LOSS: 1.0646 |
| [2026-05-24 06:39:45] Validation | Batch 1050/1463 | Loss: 0.8720 | LM_LOSS: 0.3397 | LB_LOSS: 1.0646 |
| [2026-05-24 06:39:47] Validation | Batch 1060/1463 | Loss: 0.8720 | LM_LOSS: 0.3397 | LB_LOSS: 1.0646 |
| [2026-05-24 06:39:50] Validation | Batch 1070/1463 | Loss: 0.8721 | LM_LOSS: 0.3398 | LB_LOSS: 1.0646 |
| [2026-05-24 06:39:51] Validation | Batch 1080/1463 | Loss: 0.8718 | LM_LOSS: 0.3395 | LB_LOSS: 1.0647 |
| [2026-05-24 06:39:53] Validation | Batch 1090/1463 | Loss: 0.8718 | LM_LOSS: 0.3395 | LB_LOSS: 1.0646 |
| [2026-05-24 06:39:55] Validation | Batch 1100/1463 | Loss: 0.8717 | LM_LOSS: 0.3394 | LB_LOSS: 1.0645 |
| [2026-05-24 06:39:57] Validation | Batch 1110/1463 | Loss: 0.8717 | LM_LOSS: 0.3394 | LB_LOSS: 1.0645 |
| [2026-05-24 06:39:59] Validation | Batch 1120/1463 | Loss: 0.8716 | LM_LOSS: 0.3393 | LB_LOSS: 1.0646 |
| [2026-05-24 06:40:01] Validation | Batch 1130/1463 | Loss: 0.8714 | LM_LOSS: 0.3391 | LB_LOSS: 1.0645 |
| [2026-05-24 06:40:03] Validation | Batch 1140/1463 | Loss: 0.8716 | LM_LOSS: 0.3393 | LB_LOSS: 1.0645 |
| [2026-05-24 06:40:06] Validation | Batch 1150/1463 | Loss: 0.8714 | LM_LOSS: 0.3392 | LB_LOSS: 1.0645 |
| [2026-05-24 06:40:07] Validation | Batch 1160/1463 | Loss: 0.8714 | LM_LOSS: 0.3391 | LB_LOSS: 1.0645 |
| [2026-05-24 06:40:09] Validation | Batch 1170/1463 | Loss: 0.8714 | LM_LOSS: 0.3391 | LB_LOSS: 1.0645 |
| [2026-05-24 06:40:11] Validation | Batch 1180/1463 | Loss: 0.8715 | LM_LOSS: 0.3392 | LB_LOSS: 1.0645 |
| [2026-05-24 06:40:14] Validation | Batch 1190/1463 | Loss: 0.8716 | LM_LOSS: 0.3393 | LB_LOSS: 1.0645 |
| [2026-05-24 06:40:16] Validation | Batch 1200/1463 | Loss: 0.8717 | LM_LOSS: 0.3394 | LB_LOSS: 1.0646 |
| [2026-05-24 06:40:18] Validation | Batch 1210/1463 | Loss: 0.8719 | LM_LOSS: 0.3396 | LB_LOSS: 1.0646 |
| [2026-05-24 06:40:20] Validation | Batch 1220/1463 | Loss: 0.8724 | LM_LOSS: 0.3401 | LB_LOSS: 1.0646 |
| [2026-05-24 06:40:21] Validation | Batch 1230/1463 | Loss: 0.8723 | LM_LOSS: 0.3400 | LB_LOSS: 1.0646 |
| [2026-05-24 06:40:23] Validation | Batch 1240/1463 | Loss: 0.8726 | LM_LOSS: 0.3404 | LB_LOSS: 1.0646 |
| [2026-05-24 06:40:26] Validation | Batch 1250/1463 | Loss: 0.8729 | LM_LOSS: 0.3406 | LB_LOSS: 1.0646 |
| [2026-05-24 06:40:28] Validation | Batch 1260/1463 | Loss: 0.8728 | LM_LOSS: 0.3405 | LB_LOSS: 1.0646 |
| [2026-05-24 06:40:30] Validation | Batch 1270/1463 | Loss: 0.8726 | LM_LOSS: 0.3403 | LB_LOSS: 1.0646 |
| [2026-05-24 06:40:32] Validation | Batch 1280/1463 | Loss: 0.8724 | LM_LOSS: 0.3401 | LB_LOSS: 1.0646 |
| [2026-05-24 06:40:34] Validation | Batch 1290/1463 | Loss: 0.8724 | LM_LOSS: 0.3401 | LB_LOSS: 1.0646 |
| [2026-05-24 06:40:36] Validation | Batch 1300/1463 | Loss: 0.8722 | LM_LOSS: 0.3399 | LB_LOSS: 1.0645 |
| [2026-05-24 06:40:38] Validation | Batch 1310/1463 | Loss: 0.8721 | LM_LOSS: 0.3398 | LB_LOSS: 1.0645 |
| [2026-05-24 06:40:40] Validation | Batch 1320/1463 | Loss: 0.8721 | LM_LOSS: 0.3399 | LB_LOSS: 1.0645 |
| [2026-05-24 06:40:41] Validation | Batch 1330/1463 | Loss: 0.8722 | LM_LOSS: 0.3400 | LB_LOSS: 1.0645 |
| [2026-05-24 06:40:43] Validation | Batch 1340/1463 | Loss: 0.8725 | LM_LOSS: 0.3402 | LB_LOSS: 1.0646 |
| [2026-05-24 06:40:45] Validation | Batch 1350/1463 | Loss: 0.8726 | LM_LOSS: 0.3403 | LB_LOSS: 1.0645 |
| [2026-05-24 06:40:48] Validation | Batch 1360/1463 | Loss: 0.8728 | LM_LOSS: 0.3405 | LB_LOSS: 1.0645 |
| [2026-05-24 06:40:50] Validation | Batch 1370/1463 | Loss: 0.8731 | LM_LOSS: 0.3408 | LB_LOSS: 1.0645 |
| [2026-05-24 06:40:52] Validation | Batch 1380/1463 | Loss: 0.8728 | LM_LOSS: 0.3406 | LB_LOSS: 1.0645 |
| [2026-05-24 06:40:54] Validation | Batch 1390/1463 | Loss: 0.8728 | LM_LOSS: 0.3405 | LB_LOSS: 1.0645 |
| [2026-05-24 06:40:56] Validation | Batch 1400/1463 | Loss: 0.8730 | LM_LOSS: 0.3408 | LB_LOSS: 1.0645 |
| [2026-05-24 06:40:57] Validation | Batch 1410/1463 | Loss: 0.8732 | LM_LOSS: 0.3410 | LB_LOSS: 1.0645 |
| [2026-05-24 06:40:59] Validation | Batch 1420/1463 | Loss: 0.8732 | LM_LOSS: 0.3410 | LB_LOSS: 1.0645 |
| [2026-05-24 06:41:02] Validation | Batch 1430/1463 | Loss: 0.8734 | LM_LOSS: 0.3411 | LB_LOSS: 1.0645 |
| [2026-05-24 06:41:04] Validation | Batch 1440/1463 | Loss: 0.8737 | LM_LOSS: 0.3415 | LB_LOSS: 1.0645 |
| [2026-05-24 06:41:06] Validation | Batch 1450/1463 | Loss: 0.8734 | LM_LOSS: 0.3412 | LB_LOSS: 1.0645 |
| [2026-05-24 06:41:08] Validation | Batch 1460/1463 | Loss: 0.8738 | LM_LOSS: 0.3415 | LB_LOSS: 1.0645 |
| [2026-05-24 06:41:09] Validation | Batch 1463/1463 | Loss: 0.8736 | LM_LOSS: 0.3414 | LB_LOSS: 1.0644 |
| [2026-05-24 06:41:09] Validation | Loss: 0.8736 | LM_LOSS: 0.3414 | LB_LOSS: 1.0644 | PPL: 1.41 | Time: 293.44s |
| [2026-05-24 06:41:15] New best model saved! Val loss: 0.8736 |
| [2026-05-24 06:41:26] Epoch 1 | Step 2010 | Loss: 0.9273 | LM: 0.3493 | LB: 1.1660 | CL0: 3.0 | CL1: 4.0 | HR0: 0.339/SR0: 0.328 | HR1: 0.275/SR1: 0.247 | LR: 1.00e-04 |
| [2026-05-24 06:41:37] Epoch 1 | Step 2020 | Loss: 0.9271 | LM: 0.3493 | LB: 1.1656 | CL0: 3.0 | CL1: 4.0 | HR0: 0.339/SR0: 0.327 | HR1: 0.275/SR1: 0.247 | LR: 1.00e-04 |
| [2026-05-24 06:41:48] Epoch 1 | Step 2030 | Loss: 0.9267 | LM: 0.3490 | LB: 1.1651 | CL0: 3.0 | CL1: 4.0 | HR0: 0.339/SR0: 0.327 | HR1: 0.275/SR1: 0.247 | LR: 1.00e-04 |
| [2026-05-24 06:41:59] Epoch 1 | Step 2040 | Loss: 0.9265 | LM: 0.3495 | LB: 1.1646 | CL0: 3.0 | CL1: 4.0 | HR0: 0.339/SR0: 0.327 | HR1: 0.274/SR1: 0.246 | LR: 1.00e-04 |
| [2026-05-24 06:42:10] Epoch 1 | Step 2050 | Loss: 0.9263 | LM: 0.3491 | LB: 1.1641 | CL0: 3.0 | CL1: 4.0 | HR0: 0.338/SR0: 0.327 | HR1: 0.274/SR1: 0.246 | LR: 1.00e-04 |
| [2026-05-24 06:42:21] Epoch 1 | Step 2060 | Loss: 0.9260 | LM: 0.3493 | LB: 1.1635 | CL0: 3.0 | CL1: 4.0 | HR0: 0.338/SR0: 0.326 | HR1: 0.274/SR1: 0.246 | LR: 1.00e-04 |
| [2026-05-24 06:42:31] Epoch 1 | Step 2070 | Loss: 0.9257 | LM: 0.3495 | LB: 1.1631 | CL0: 3.0 | CL1: 4.0 | HR0: 0.338/SR0: 0.326 | HR1: 0.273/SR1: 0.245 | LR: 1.00e-04 |
| [2026-05-24 06:42:42] Epoch 1 | Step 2080 | Loss: 0.9255 | LM: 0.3498 | LB: 1.1626 | CL0: 3.0 | CL1: 4.0 | HR0: 0.338/SR0: 0.326 | HR1: 0.273/SR1: 0.245 | LR: 1.00e-04 |
| [2026-05-24 06:42:53] Epoch 1 | Step 2090 | Loss: 0.9251 | LM: 0.3494 | LB: 1.1621 | CL0: 3.0 | CL1: 4.0 | HR0: 0.338/SR0: 0.326 | HR1: 0.273/SR1: 0.244 | LR: 1.00e-04 |
| [2026-05-24 06:43:04] Epoch 1 | Step 2100 | Loss: 0.9249 | LM: 0.3495 | LB: 1.1617 | CL0: 3.0 | CL1: 4.0 | HR0: 0.338/SR0: 0.326 | HR1: 0.272/SR1: 0.244 | LR: 1.00e-04 |
| [2026-05-24 06:43:15] Epoch 1 | Step 2110 | Loss: 0.9246 | LM: 0.3495 | LB: 1.1613 | CL0: 3.0 | CL1: 4.0 | HR0: 0.338/SR0: 0.326 | HR1: 0.272/SR1: 0.244 | LR: 1.00e-04 |
| [2026-05-24 06:43:25] Epoch 1 | Step 2120 | Loss: 0.9243 | LM: 0.3492 | LB: 1.1608 | CL0: 3.0 | CL1: 4.1 | HR0: 0.337/SR0: 0.325 | HR1: 0.272/SR1: 0.243 | LR: 1.00e-04 |
| [2026-05-24 06:43:37] Epoch 1 | Step 2130 | Loss: 0.9242 | LM: 0.3494 | LB: 1.1604 | CL0: 3.0 | CL1: 4.1 | HR0: 0.337/SR0: 0.325 | HR1: 0.271/SR1: 0.243 | LR: 1.00e-04 |
| [2026-05-24 06:43:47] Epoch 1 | Step 2140 | Loss: 0.9237 | LM: 0.3493 | LB: 1.1600 | CL0: 3.0 | CL1: 4.1 | HR0: 0.337/SR0: 0.325 | HR1: 0.271/SR1: 0.243 | LR: 1.00e-04 |
| [2026-05-24 06:43:58] Epoch 1 | Step 2150 | Loss: 0.9235 | LM: 0.3492 | LB: 1.1596 | CL0: 3.0 | CL1: 4.1 | HR0: 0.337/SR0: 0.325 | HR1: 0.271/SR1: 0.243 | LR: 1.00e-04 |
| [2026-05-24 06:44:10] Epoch 1 | Step 2160 | Loss: 0.9233 | LM: 0.3491 | LB: 1.1592 | CL0: 3.0 | CL1: 4.1 | HR0: 0.337/SR0: 0.325 | HR1: 0.270/SR1: 0.242 | LR: 1.00e-04 |
| [2026-05-24 06:44:21] Epoch 1 | Step 2170 | Loss: 0.9231 | LM: 0.3492 | LB: 1.1587 | CL0: 3.0 | CL1: 4.1 | HR0: 0.337/SR0: 0.325 | HR1: 0.270/SR1: 0.242 | LR: 1.00e-04 |
| [2026-05-24 06:44:32] Epoch 1 | Step 2180 | Loss: 0.9227 | LM: 0.3490 | LB: 1.1583 | CL0: 3.0 | CL1: 4.1 | HR0: 0.337/SR0: 0.324 | HR1: 0.270/SR1: 0.242 | LR: 1.00e-04 |
| [2026-05-24 06:44:44] Epoch 1 | Step 2190 | Loss: 0.9226 | LM: 0.3490 | LB: 1.1578 | CL0: 3.0 | CL1: 4.1 | HR0: 0.337/SR0: 0.324 | HR1: 0.269/SR1: 0.241 | LR: 1.00e-04 |
| [2026-05-24 06:44:55] Epoch 1 | Step 2200 | Loss: 0.9223 | LM: 0.3488 | LB: 1.1574 | CL0: 3.0 | CL1: 4.1 | HR0: 0.336/SR0: 0.324 | HR1: 0.269/SR1: 0.241 | LR: 1.00e-04 |
| [2026-05-24 06:45:06] Epoch 1 | Step 2210 | Loss: 0.9220 | LM: 0.3487 | LB: 1.1570 | CL0: 3.0 | CL1: 4.1 | HR0: 0.336/SR0: 0.324 | HR1: 0.269/SR1: 0.241 | LR: 1.00e-04 |
| [2026-05-24 06:45:18] Epoch 1 | Step 2220 | Loss: 0.9217 | LM: 0.3489 | LB: 1.1565 | CL0: 3.0 | CL1: 4.1 | HR0: 0.336/SR0: 0.324 | HR1: 0.269/SR1: 0.240 | LR: 1.00e-04 |
| [2026-05-24 06:45:29] Epoch 1 | Step 2230 | Loss: 0.9216 | LM: 0.3489 | LB: 1.1561 | CL0: 3.0 | CL1: 4.1 | HR0: 0.336/SR0: 0.323 | HR1: 0.268/SR1: 0.240 | LR: 1.00e-04 |
| [2026-05-24 06:45:40] Epoch 1 | Step 2240 | Loss: 0.9214 | LM: 0.3486 | LB: 1.1557 | CL0: 3.0 | CL1: 4.1 | HR0: 0.336/SR0: 0.323 | HR1: 0.268/SR1: 0.240 | LR: 1.00e-04 |
| [2026-05-24 06:45:51] Epoch 1 | Step 2250 | Loss: 0.9212 | LM: 0.3486 | LB: 1.1553 | CL0: 3.0 | CL1: 4.1 | HR0: 0.336/SR0: 0.323 | HR1: 0.268/SR1: 0.240 | LR: 1.00e-04 |
| [2026-05-24 06:46:02] Epoch 1 | Step 2260 | Loss: 0.9209 | LM: 0.3488 | LB: 1.1549 | CL0: 3.0 | CL1: 4.1 | HR0: 0.336/SR0: 0.323 | HR1: 0.267/SR1: 0.239 | LR: 1.00e-04 |
| [2026-05-24 06:46:13] Epoch 1 | Step 2270 | Loss: 0.9207 | LM: 0.3486 | LB: 1.1545 | CL0: 3.0 | CL1: 4.1 | HR0: 0.336/SR0: 0.323 | HR1: 0.267/SR1: 0.239 | LR: 1.00e-04 |
| [2026-05-24 06:46:23] Epoch 1 | Step 2280 | Loss: 0.9207 | LM: 0.3488 | LB: 1.1541 | CL0: 3.0 | CL1: 4.1 | HR0: 0.335/SR0: 0.323 | HR1: 0.267/SR1: 0.239 | LR: 1.00e-04 |
| [2026-05-24 06:46:34] Epoch 1 | Step 2290 | Loss: 0.9204 | LM: 0.3488 | LB: 1.1537 | CL0: 3.0 | CL1: 4.1 | HR0: 0.335/SR0: 0.322 | HR1: 0.267/SR1: 0.238 | LR: 1.00e-04 |
| [2026-05-24 06:46:45] Epoch 1 | Step 2300 | Loss: 0.9203 | LM: 0.3488 | LB: 1.1534 | CL0: 3.0 | CL1: 4.1 | HR0: 0.335/SR0: 0.322 | HR1: 0.266/SR1: 0.238 | LR: 1.00e-04 |
| [2026-05-24 06:46:56] Epoch 1 | Step 2310 | Loss: 0.9202 | LM: 0.3488 | LB: 1.1530 | CL0: 3.0 | CL1: 4.1 | HR0: 0.335/SR0: 0.322 | HR1: 0.266/SR1: 0.238 | LR: 1.00e-04 |
| [2026-05-24 06:47:06] Epoch 1 | Step 2320 | Loss: 0.9200 | LM: 0.3486 | LB: 1.1525 | CL0: 3.0 | CL1: 4.1 | HR0: 0.335/SR0: 0.322 | HR1: 0.266/SR1: 0.237 | LR: 1.00e-04 |
| [2026-05-24 06:47:17] Epoch 1 | Step 2330 | Loss: 0.9198 | LM: 0.3484 | LB: 1.1521 | CL0: 3.0 | CL1: 4.1 | HR0: 0.335/SR0: 0.322 | HR1: 0.265/SR1: 0.237 | LR: 1.00e-04 |
| [2026-05-24 06:47:28] Epoch 1 | Step 2340 | Loss: 0.9196 | LM: 0.3484 | LB: 1.1518 | CL0: 3.0 | CL1: 4.1 | HR0: 0.335/SR0: 0.322 | HR1: 0.265/SR1: 0.237 | LR: 1.00e-04 |
| [2026-05-24 06:47:39] Epoch 1 | Step 2350 | Loss: 0.9194 | LM: 0.3482 | LB: 1.1514 | CL0: 3.0 | CL1: 4.1 | HR0: 0.335/SR0: 0.321 | HR1: 0.265/SR1: 0.237 | LR: 1.00e-04 |
| [2026-05-24 06:47:49] Epoch 1 | Step 2360 | Loss: 0.9193 | LM: 0.3481 | LB: 1.1510 | CL0: 3.0 | CL1: 4.1 | HR0: 0.335/SR0: 0.321 | HR1: 0.265/SR1: 0.236 | LR: 1.00e-04 |
| [2026-05-24 06:48:00] Epoch 1 | Step 2370 | Loss: 0.9189 | LM: 0.3479 | LB: 1.1507 | CL0: 3.0 | CL1: 4.1 | HR0: 0.334/SR0: 0.321 | HR1: 0.264/SR1: 0.236 | LR: 1.00e-04 |
| [2026-05-24 06:48:11] Epoch 1 | Step 2380 | Loss: 0.9188 | LM: 0.3480 | LB: 1.1503 | CL0: 3.0 | CL1: 4.1 | HR0: 0.334/SR0: 0.321 | HR1: 0.264/SR1: 0.236 | LR: 1.00e-04 |
| [2026-05-24 06:48:22] Epoch 1 | Step 2390 | Loss: 0.9186 | LM: 0.3480 | LB: 1.1499 | CL0: 3.0 | CL1: 4.2 | HR0: 0.334/SR0: 0.321 | HR1: 0.264/SR1: 0.236 | LR: 1.00e-04 |
| [2026-05-24 06:48:34] Epoch 1 | Step 2400 | Loss: 0.9184 | LM: 0.3479 | LB: 1.1495 | CL0: 3.0 | CL1: 4.2 | HR0: 0.334/SR0: 0.321 | HR1: 0.264/SR1: 0.235 | LR: 1.00e-04 |
| [2026-05-24 06:48:45] Epoch 1 | Step 2410 | Loss: 0.9181 | LM: 0.3480 | LB: 1.1492 | CL0: 3.0 | CL1: 4.2 | HR0: 0.334/SR0: 0.320 | HR1: 0.263/SR1: 0.235 | LR: 1.00e-04 |
| [2026-05-24 06:48:57] Epoch 1 | Step 2420 | Loss: 0.9179 | LM: 0.3478 | LB: 1.1489 | CL0: 3.0 | CL1: 4.2 | HR0: 0.334/SR0: 0.320 | HR1: 0.263/SR1: 0.235 | LR: 1.00e-04 |
| [2026-05-24 06:49:08] Epoch 1 | Step 2430 | Loss: 0.9178 | LM: 0.3479 | LB: 1.1485 | CL0: 3.0 | CL1: 4.2 | HR0: 0.334/SR0: 0.320 | HR1: 0.263/SR1: 0.235 | LR: 1.00e-04 |
| [2026-05-24 06:49:19] Epoch 1 | Step 2440 | Loss: 0.9177 | LM: 0.3477 | LB: 1.1482 | CL0: 3.0 | CL1: 4.2 | HR0: 0.334/SR0: 0.320 | HR1: 0.263/SR1: 0.234 | LR: 1.00e-04 |
| [2026-05-24 06:49:30] Epoch 1 | Step 2450 | Loss: 0.9174 | LM: 0.3476 | LB: 1.1478 | CL0: 3.0 | CL1: 4.2 | HR0: 0.333/SR0: 0.320 | HR1: 0.263/SR1: 0.234 | LR: 1.00e-04 |
| [2026-05-24 06:49:41] Epoch 1 | Step 2460 | Loss: 0.9171 | LM: 0.3475 | LB: 1.1474 | CL0: 3.0 | CL1: 4.2 | HR0: 0.333/SR0: 0.320 | HR1: 0.262/SR1: 0.234 | LR: 1.00e-04 |
| [2026-05-24 06:49:51] Epoch 1 | Step 2470 | Loss: 0.9168 | LM: 0.3471 | LB: 1.1470 | CL0: 3.0 | CL1: 4.2 | HR0: 0.333/SR0: 0.319 | HR1: 0.262/SR1: 0.234 | LR: 1.00e-04 |
| [2026-05-24 06:50:03] Epoch 1 | Step 2480 | Loss: 0.9166 | LM: 0.3473 | LB: 1.1467 | CL0: 3.0 | CL1: 4.2 | HR0: 0.333/SR0: 0.319 | HR1: 0.262/SR1: 0.233 | LR: 1.00e-04 |
| [2026-05-24 06:50:14] Epoch 1 | Step 2490 | Loss: 0.9164 | LM: 0.3474 | LB: 1.1464 | CL0: 3.0 | CL1: 4.2 | HR0: 0.333/SR0: 0.319 | HR1: 0.261/SR1: 0.233 | LR: 1.00e-04 |
| [2026-05-24 06:50:25] Epoch 1 | Step 2500 | Loss: 0.9162 | LM: 0.3471 | LB: 1.1460 | CL0: 3.0 | CL1: 4.2 | HR0: 0.333/SR0: 0.319 | HR1: 0.261/SR1: 0.233 | LR: 1.00e-04 |
| [2026-05-24 06:50:36] Epoch 1 | Step 2510 | Loss: 0.9160 | LM: 0.3472 | LB: 1.1457 | CL0: 3.0 | CL1: 4.2 | HR0: 0.333/SR0: 0.319 | HR1: 0.261/SR1: 0.233 | LR: 1.00e-04 |
| [2026-05-24 06:50:48] Epoch 1 | Step 2520 | Loss: 0.9159 | LM: 0.3473 | LB: 1.1453 | CL0: 3.0 | CL1: 4.2 | HR0: 0.333/SR0: 0.319 | HR1: 0.261/SR1: 0.232 | LR: 1.00e-04 |
| [2026-05-24 06:50:59] Epoch 1 | Step 2530 | Loss: 0.9157 | LM: 0.3472 | LB: 1.1449 | CL0: 3.0 | CL1: 4.2 | HR0: 0.333/SR0: 0.318 | HR1: 0.260/SR1: 0.232 | LR: 1.00e-04 |
| [2026-05-24 06:51:10] Epoch 1 | Step 2540 | Loss: 0.9156 | LM: 0.3474 | LB: 1.1446 | CL0: 3.0 | CL1: 4.2 | HR0: 0.332/SR0: 0.318 | HR1: 0.260/SR1: 0.232 | LR: 1.00e-04 |
| [2026-05-24 06:51:21] Epoch 1 | Step 2550 | Loss: 0.9154 | LM: 0.3474 | LB: 1.1442 | CL0: 3.0 | CL1: 4.2 | HR0: 0.332/SR0: 0.318 | HR1: 0.260/SR1: 0.232 | LR: 1.00e-04 |
| [2026-05-24 06:51:32] Epoch 1 | Step 2560 | Loss: 0.9152 | LM: 0.3474 | LB: 1.1438 | CL0: 3.0 | CL1: 4.2 | HR0: 0.332/SR0: 0.318 | HR1: 0.260/SR1: 0.232 | LR: 1.00e-04 |
| [2026-05-24 06:51:43] Epoch 1 | Step 2570 | Loss: 0.9151 | LM: 0.3473 | LB: 1.1435 | CL0: 3.0 | CL1: 4.2 | HR0: 0.332/SR0: 0.318 | HR1: 0.259/SR1: 0.231 | LR: 1.00e-04 |
| [2026-05-24 06:51:54] Epoch 1 | Step 2580 | Loss: 0.9149 | LM: 0.3474 | LB: 1.1432 | CL0: 3.0 | CL1: 4.2 | HR0: 0.332/SR0: 0.318 | HR1: 0.259/SR1: 0.231 | LR: 1.00e-04 |
| [2026-05-24 06:52:05] Epoch 1 | Step 2590 | Loss: 0.9148 | LM: 0.3475 | LB: 1.1429 | CL0: 3.0 | CL1: 4.2 | HR0: 0.332/SR0: 0.317 | HR1: 0.259/SR1: 0.231 | LR: 1.00e-04 |
| [2026-05-24 06:52:15] Epoch 1 | Step 2600 | Loss: 0.9146 | LM: 0.3473 | LB: 1.1425 | CL0: 3.0 | CL1: 4.2 | HR0: 0.332/SR0: 0.317 | HR1: 0.259/SR1: 0.231 | LR: 1.00e-04 |
| [2026-05-24 06:52:26] Epoch 1 | Step 2610 | Loss: 0.9142 | LM: 0.3471 | LB: 1.1422 | CL0: 3.0 | CL1: 4.2 | HR0: 0.332/SR0: 0.317 | HR1: 0.259/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 06:52:36] Epoch 1 | Step 2620 | Loss: 0.9139 | LM: 0.3468 | LB: 1.1418 | CL0: 3.0 | CL1: 4.2 | HR0: 0.331/SR0: 0.317 | HR1: 0.258/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 06:52:47] Epoch 1 | Step 2630 | Loss: 0.9138 | LM: 0.3468 | LB: 1.1415 | CL0: 3.0 | CL1: 4.2 | HR0: 0.331/SR0: 0.317 | HR1: 0.258/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 06:52:59] Epoch 1 | Step 2640 | Loss: 0.9135 | LM: 0.3467 | LB: 1.1412 | CL0: 3.0 | CL1: 4.2 | HR0: 0.331/SR0: 0.317 | HR1: 0.258/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 06:53:10] Epoch 1 | Step 2650 | Loss: 0.9134 | LM: 0.3468 | LB: 1.1409 | CL0: 3.0 | CL1: 4.2 | HR0: 0.331/SR0: 0.316 | HR1: 0.258/SR1: 0.230 | LR: 1.00e-04 |
| [2026-05-24 06:53:22] Epoch 1 | Step 2660 | Loss: 0.9134 | LM: 0.3468 | LB: 1.1405 | CL0: 3.0 | CL1: 4.2 | HR0: 0.331/SR0: 0.316 | HR1: 0.258/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 06:53:33] Epoch 1 | Step 2670 | Loss: 0.9132 | LM: 0.3470 | LB: 1.1402 | CL0: 3.0 | CL1: 4.2 | HR0: 0.331/SR0: 0.316 | HR1: 0.257/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 06:53:45] Epoch 1 | Step 2680 | Loss: 0.9131 | LM: 0.3470 | LB: 1.1399 | CL0: 3.0 | CL1: 4.2 | HR0: 0.331/SR0: 0.316 | HR1: 0.257/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 06:53:56] Epoch 1 | Step 2690 | Loss: 0.9130 | LM: 0.3472 | LB: 1.1396 | CL0: 3.0 | CL1: 4.3 | HR0: 0.331/SR0: 0.316 | HR1: 0.257/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 06:54:07] Epoch 1 | Step 2700 | Loss: 0.9126 | LM: 0.3469 | LB: 1.1393 | CL0: 3.1 | CL1: 4.3 | HR0: 0.331/SR0: 0.316 | HR1: 0.257/SR1: 0.229 | LR: 1.00e-04 |
| [2026-05-24 06:54:18] Epoch 1 | Step 2710 | Loss: 0.9124 | LM: 0.3469 | LB: 1.1390 | CL0: 3.1 | CL1: 4.3 | HR0: 0.330/SR0: 0.315 | HR1: 0.257/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 06:54:29] Epoch 1 | Step 2720 | Loss: 0.9121 | LM: 0.3468 | LB: 1.1387 | CL0: 3.1 | CL1: 4.3 | HR0: 0.330/SR0: 0.315 | HR1: 0.256/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 06:54:40] Epoch 1 | Step 2730 | Loss: 0.9120 | LM: 0.3468 | LB: 1.1384 | CL0: 3.1 | CL1: 4.3 | HR0: 0.330/SR0: 0.315 | HR1: 0.256/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 06:54:52] Epoch 1 | Step 2740 | Loss: 0.9117 | LM: 0.3468 | LB: 1.1381 | CL0: 3.1 | CL1: 4.3 | HR0: 0.330/SR0: 0.315 | HR1: 0.256/SR1: 0.228 | LR: 1.00e-04 |
| [2026-05-24 06:55:03] Epoch 1 | Step 2750 | Loss: 0.9116 | LM: 0.3466 | LB: 1.1378 | CL0: 3.1 | CL1: 4.3 | HR0: 0.330/SR0: 0.315 | HR1: 0.256/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 06:55:13] Epoch 1 | Step 2760 | Loss: 0.9113 | LM: 0.3465 | LB: 1.1374 | CL0: 3.1 | CL1: 4.3 | HR0: 0.330/SR0: 0.315 | HR1: 0.256/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 06:55:25] Epoch 1 | Step 2770 | Loss: 0.9112 | LM: 0.3464 | LB: 1.1371 | CL0: 3.1 | CL1: 4.3 | HR0: 0.330/SR0: 0.315 | HR1: 0.255/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 06:55:35] Epoch 1 | Step 2780 | Loss: 0.9111 | LM: 0.3465 | LB: 1.1368 | CL0: 3.1 | CL1: 4.3 | HR0: 0.330/SR0: 0.314 | HR1: 0.255/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 06:55:46] Epoch 1 | Step 2790 | Loss: 0.9110 | LM: 0.3466 | LB: 1.1365 | CL0: 3.1 | CL1: 4.3 | HR0: 0.330/SR0: 0.314 | HR1: 0.255/SR1: 0.227 | LR: 1.00e-04 |
| [2026-05-24 06:55:57] Epoch 1 | Step 2800 | Loss: 0.9109 | LM: 0.3467 | LB: 1.1362 | CL0: 3.1 | CL1: 4.3 | HR0: 0.329/SR0: 0.314 | HR1: 0.255/SR1: 0.226 | LR: 1.00e-04 |
| [2026-05-24 06:56:08] Epoch 1 | Step 2810 | Loss: 0.9107 | LM: 0.3465 | LB: 1.1359 | CL0: 3.1 | CL1: 4.3 | HR0: 0.329/SR0: 0.314 | HR1: 0.255/SR1: 0.226 | LR: 1.00e-04 |
| [2026-05-24 06:56:18] Epoch 1 | Step 2820 | Loss: 0.9106 | LM: 0.3464 | LB: 1.1356 | CL0: 3.1 | CL1: 4.3 | HR0: 0.329/SR0: 0.314 | HR1: 0.254/SR1: 0.226 | LR: 1.00e-04 |
| [2026-05-24 06:56:29] Epoch 1 | Step 2830 | Loss: 0.9105 | LM: 0.3465 | LB: 1.1354 | CL0: 3.1 | CL1: 4.3 | HR0: 0.329/SR0: 0.314 | HR1: 0.254/SR1: 0.226 | LR: 1.00e-04 |
| [2026-05-24 06:56:40] Epoch 1 | Step 2840 | Loss: 0.9103 | LM: 0.3465 | LB: 1.1351 | CL0: 3.1 | CL1: 4.3 | HR0: 0.329/SR0: 0.313 | HR1: 0.254/SR1: 0.226 | LR: 1.00e-04 |
| [2026-05-24 06:56:51] Epoch 1 | Step 2850 | Loss: 0.9101 | LM: 0.3465 | LB: 1.1348 | CL0: 3.1 | CL1: 4.3 | HR0: 0.329/SR0: 0.313 | HR1: 0.254/SR1: 0.226 | LR: 1.00e-04 |
| [2026-05-24 06:57:03] Epoch 1 | Step 2860 | Loss: 0.9099 | LM: 0.3464 | LB: 1.1345 | CL0: 3.1 | CL1: 4.3 | HR0: 0.329/SR0: 0.313 | HR1: 0.254/SR1: 0.225 | LR: 1.00e-04 |
| [2026-05-24 06:57:13] Epoch 1 | Step 2870 | Loss: 0.9098 | LM: 0.3463 | LB: 1.1342 | CL0: 3.1 | CL1: 4.3 | HR0: 0.329/SR0: 0.313 | HR1: 0.253/SR1: 0.225 | LR: 1.00e-04 |
| [2026-05-24 06:57:24] Epoch 1 | Step 2880 | Loss: 0.9097 | LM: 0.3466 | LB: 1.1340 | CL0: 3.1 | CL1: 4.3 | HR0: 0.329/SR0: 0.313 | HR1: 0.253/SR1: 0.225 | LR: 1.00e-04 |
| [2026-05-24 06:57:35] Epoch 1 | Step 2890 | Loss: 0.9095 | LM: 0.3465 | LB: 1.1337 | CL0: 3.1 | CL1: 4.3 | HR0: 0.329/SR0: 0.313 | HR1: 0.253/SR1: 0.225 | LR: 1.00e-04 |
| [2026-05-24 06:57:46] Epoch 1 | Step 2900 | Loss: 0.9093 | LM: 0.3463 | LB: 1.1334 | CL0: 3.1 | CL1: 4.3 | HR0: 0.328/SR0: 0.313 | HR1: 0.253/SR1: 0.225 | LR: 1.00e-04 |
| [2026-05-24 06:57:57] Epoch 1 | Step 2910 | Loss: 0.9091 | LM: 0.3463 | LB: 1.1330 | CL0: 3.1 | CL1: 4.3 | HR0: 0.328/SR0: 0.312 | HR1: 0.253/SR1: 0.224 | LR: 1.00e-04 |
| [2026-05-24 06:58:07] Epoch 1 | Step 2920 | Loss: 0.9090 | LM: 0.3463 | LB: 1.1328 | CL0: 3.1 | CL1: 4.3 | HR0: 0.328/SR0: 0.312 | HR1: 0.253/SR1: 0.224 | LR: 1.00e-04 |
| [2026-05-24 06:58:18] Epoch 1 | Step 2930 | Loss: 0.9088 | LM: 0.3461 | LB: 1.1325 | CL0: 3.1 | CL1: 4.3 | HR0: 0.328/SR0: 0.312 | HR1: 0.252/SR1: 0.224 | LR: 1.00e-04 |
| [2026-05-24 06:58:29] Epoch 1 | Step 2940 | Loss: 0.9087 | LM: 0.3461 | LB: 1.1322 | CL0: 3.1 | CL1: 4.3 | HR0: 0.328/SR0: 0.312 | HR1: 0.252/SR1: 0.224 | LR: 1.00e-04 |
| [2026-05-24 06:58:39] Epoch 1 | Step 2950 | Loss: 0.9085 | LM: 0.3460 | LB: 1.1319 | CL0: 3.1 | CL1: 4.3 | HR0: 0.328/SR0: 0.312 | HR1: 0.252/SR1: 0.224 | LR: 1.00e-04 |
| [2026-05-24 06:58:50] Epoch 1 | Step 2960 | Loss: 0.9084 | LM: 0.3459 | LB: 1.1316 | CL0: 3.1 | CL1: 4.3 | HR0: 0.328/SR0: 0.312 | HR1: 0.252/SR1: 0.224 | LR: 1.00e-04 |
| [2026-05-24 06:59:01] Epoch 1 | Step 2970 | Loss: 0.9081 | LM: 0.3457 | LB: 1.1314 | CL0: 3.1 | CL1: 4.3 | HR0: 0.328/SR0: 0.311 | HR1: 0.252/SR1: 0.223 | LR: 1.00e-04 |
| [2026-05-24 06:59:12] Epoch 1 | Step 2980 | Loss: 0.9079 | LM: 0.3457 | LB: 1.1311 | CL0: 3.1 | CL1: 4.3 | HR0: 0.327/SR0: 0.311 | HR1: 0.251/SR1: 0.223 | LR: 1.00e-04 |
| [2026-05-24 06:59:22] Epoch 1 | Step 2990 | Loss: 0.9078 | LM: 0.3457 | LB: 1.1308 | CL0: 3.1 | CL1: 4.3 | HR0: 0.327/SR0: 0.311 | HR1: 0.251/SR1: 0.223 | LR: 1.00e-04 |
| [2026-05-24 06:59:33] Epoch 1 | Step 3000 | Loss: 0.9076 | LM: 0.3458 | LB: 1.1305 | CL0: 3.1 | CL1: 4.3 | HR0: 0.327/SR0: 0.311 | HR1: 0.251/SR1: 0.223 | LR: 1.00e-04 |
| [2026-05-24 06:59:38] Checkpoint saved: outputs/2026-05-24/N_6.0/checkpoints/checkpoint_step_3000.pt |
| [2026-05-24 06:59:45] Validation | Batch 10/1463 | Loss: 0.8184 | LM_LOSS: 0.2967 | LB_LOSS: 1.0434 |
| [2026-05-24 06:59:46] Validation | Batch 20/1463 | Loss: 0.8332 | LM_LOSS: 0.3092 | LB_LOSS: 1.0479 |
| [2026-05-24 06:59:48] Validation | Batch 30/1463 | Loss: 0.8394 | LM_LOSS: 0.3149 | LB_LOSS: 1.0490 |
| [2026-05-24 06:59:50] Validation | Batch 40/1463 | Loss: 0.8489 | LM_LOSS: 0.3236 | LB_LOSS: 1.0507 |
| [2026-05-24 06:59:52] Validation | Batch 50/1463 | Loss: 0.8559 | LM_LOSS: 0.3310 | LB_LOSS: 1.0497 |
| [2026-05-24 06:59:55] Validation | Batch 60/1463 | Loss: 0.8555 | LM_LOSS: 0.3306 | LB_LOSS: 1.0496 |
| [2026-05-24 06:59:57] Validation | Batch 70/1463 | Loss: 0.8554 | LM_LOSS: 0.3304 | LB_LOSS: 1.0499 |
| [2026-05-24 06:59:59] Validation | Batch 80/1463 | Loss: 0.8574 | LM_LOSS: 0.3325 | LB_LOSS: 1.0499 |
| [2026-05-24 07:00:01] Validation | Batch 90/1463 | Loss: 0.8573 | LM_LOSS: 0.3325 | LB_LOSS: 1.0497 |
| [2026-05-24 07:00:03] Validation | Batch 100/1463 | Loss: 0.8578 | LM_LOSS: 0.3330 | LB_LOSS: 1.0497 |
| [2026-05-24 07:00:05] Validation | Batch 110/1463 | Loss: 0.8563 | LM_LOSS: 0.3311 | LB_LOSS: 1.0503 |
| [2026-05-24 07:00:07] Validation | Batch 120/1463 | Loss: 0.8580 | LM_LOSS: 0.3328 | LB_LOSS: 1.0505 |
| [2026-05-24 07:00:08] Validation | Batch 130/1463 | Loss: 0.8602 | LM_LOSS: 0.3350 | LB_LOSS: 1.0505 |
| [2026-05-24 07:00:11] Validation | Batch 140/1463 | Loss: 0.8609 | LM_LOSS: 0.3357 | LB_LOSS: 1.0504 |
| [2026-05-24 07:00:13] Validation | Batch 150/1463 | Loss: 0.8594 | LM_LOSS: 0.3341 | LB_LOSS: 1.0506 |
| [2026-05-24 07:00:15] Validation | Batch 160/1463 | Loss: 0.8602 | LM_LOSS: 0.3350 | LB_LOSS: 1.0504 |
| [2026-05-24 07:00:17] Validation | Batch 170/1463 | Loss: 0.8599 | LM_LOSS: 0.3347 | LB_LOSS: 1.0504 |
| [2026-05-24 07:00:19] Validation | Batch 180/1463 | Loss: 0.8607 | LM_LOSS: 0.3355 | LB_LOSS: 1.0505 |
| [2026-05-24 07:00:21] Validation | Batch 190/1463 | Loss: 0.8617 | LM_LOSS: 0.3364 | LB_LOSS: 1.0506 |
| [2026-05-24 07:00:23] Validation | Batch 200/1463 | Loss: 0.8618 | LM_LOSS: 0.3365 | LB_LOSS: 1.0506 |
| [2026-05-24 07:00:25] Validation | Batch 210/1463 | Loss: 0.8621 | LM_LOSS: 0.3368 | LB_LOSS: 1.0506 |
| [2026-05-24 07:00:27] Validation | Batch 220/1463 | Loss: 0.8611 | LM_LOSS: 0.3358 | LB_LOSS: 1.0506 |
| [2026-05-24 07:00:29] Validation | Batch 230/1463 | Loss: 0.8626 | LM_LOSS: 0.3374 | LB_LOSS: 1.0504 |
| [2026-05-24 07:00:31] Validation | Batch 240/1463 | Loss: 0.8638 | LM_LOSS: 0.3386 | LB_LOSS: 1.0503 |
| [2026-05-24 07:00:33] Validation | Batch 250/1463 | Loss: 0.8627 | LM_LOSS: 0.3375 | LB_LOSS: 1.0504 |
| [2026-05-24 07:00:35] Validation | Batch 260/1463 | Loss: 0.8644 | LM_LOSS: 0.3390 | LB_LOSS: 1.0507 |
| [2026-05-24 07:00:37] Validation | Batch 270/1463 | Loss: 0.8630 | LM_LOSS: 0.3377 | LB_LOSS: 1.0507 |
| [2026-05-24 07:00:39] Validation | Batch 280/1463 | Loss: 0.8640 | LM_LOSS: 0.3386 | LB_LOSS: 1.0508 |
| [2026-05-24 07:00:41] Validation | Batch 290/1463 | Loss: 0.8633 | LM_LOSS: 0.3379 | LB_LOSS: 1.0508 |
| [2026-05-24 07:00:42] Validation | Batch 300/1463 | Loss: 0.8638 | LM_LOSS: 0.3383 | LB_LOSS: 1.0510 |
| [2026-05-24 07:00:45] Validation | Batch 310/1463 | Loss: 0.8647 | LM_LOSS: 0.3392 | LB_LOSS: 1.0509 |
| [2026-05-24 07:00:46] Validation | Batch 320/1463 | Loss: 0.8630 | LM_LOSS: 0.3377 | LB_LOSS: 1.0506 |
| [2026-05-24 07:00:48] Validation | Batch 330/1463 | Loss: 0.8630 | LM_LOSS: 0.3377 | LB_LOSS: 1.0506 |
| [2026-05-24 07:00:50] Validation | Batch 340/1463 | Loss: 0.8626 | LM_LOSS: 0.3373 | LB_LOSS: 1.0506 |
| [2026-05-24 07:00:52] Validation | Batch 350/1463 | Loss: 0.8631 | LM_LOSS: 0.3378 | LB_LOSS: 1.0506 |
| [2026-05-24 07:00:54] Validation | Batch 360/1463 | Loss: 0.8627 | LM_LOSS: 0.3374 | LB_LOSS: 1.0507 |
| [2026-05-24 07:00:56] Validation | Batch 370/1463 | Loss: 0.8625 | LM_LOSS: 0.3371 | LB_LOSS: 1.0508 |
| [2026-05-24 07:00:58] Validation | Batch 380/1463 | Loss: 0.8625 | LM_LOSS: 0.3371 | LB_LOSS: 1.0506 |
| [2026-05-24 07:01:00] Validation | Batch 390/1463 | Loss: 0.8632 | LM_LOSS: 0.3378 | LB_LOSS: 1.0507 |
| [2026-05-24 07:01:01] Validation | Batch 400/1463 | Loss: 0.8631 | LM_LOSS: 0.3378 | LB_LOSS: 1.0508 |
| [2026-05-24 07:01:03] Validation | Batch 410/1463 | Loss: 0.8630 | LM_LOSS: 0.3375 | LB_LOSS: 1.0509 |
| [2026-05-24 07:01:06] Validation | Batch 420/1463 | Loss: 0.8631 | LM_LOSS: 0.3376 | LB_LOSS: 1.0509 |
| [2026-05-24 07:01:08] Validation | Batch 430/1463 | Loss: 0.8627 | LM_LOSS: 0.3372 | LB_LOSS: 1.0510 |
| [2026-05-24 07:01:09] Validation | Batch 440/1463 | Loss: 0.8629 | LM_LOSS: 0.3374 | LB_LOSS: 1.0511 |
| [2026-05-24 07:01:11] Validation | Batch 450/1463 | Loss: 0.8627 | LM_LOSS: 0.3371 | LB_LOSS: 1.0511 |
| [2026-05-24 07:01:13] Validation | Batch 460/1463 | Loss: 0.8626 | LM_LOSS: 0.3371 | LB_LOSS: 1.0511 |
| [2026-05-24 07:01:16] Validation | Batch 470/1463 | Loss: 0.8633 | LM_LOSS: 0.3378 | LB_LOSS: 1.0510 |
| [2026-05-24 07:01:18] Validation | Batch 480/1463 | Loss: 0.8631 | LM_LOSS: 0.3376 | LB_LOSS: 1.0509 |
| [2026-05-24 07:01:20] Validation | Batch 490/1463 | Loss: 0.8629 | LM_LOSS: 0.3374 | LB_LOSS: 1.0509 |
| [2026-05-24 07:01:22] Validation | Batch 500/1463 | Loss: 0.8627 | LM_LOSS: 0.3373 | LB_LOSS: 1.0509 |
| [2026-05-24 07:01:24] Validation | Batch 510/1463 | Loss: 0.8622 | LM_LOSS: 0.3367 | LB_LOSS: 1.0509 |
| [2026-05-24 07:01:26] Validation | Batch 520/1463 | Loss: 0.8618 | LM_LOSS: 0.3364 | LB_LOSS: 1.0510 |
| [2026-05-24 07:01:28] Validation | Batch 530/1463 | Loss: 0.8622 | LM_LOSS: 0.3367 | LB_LOSS: 1.0510 |
| [2026-05-24 07:01:29] Validation | Batch 540/1463 | Loss: 0.8625 | LM_LOSS: 0.3369 | LB_LOSS: 1.0510 |
| [2026-05-24 07:01:31] Validation | Batch 550/1463 | Loss: 0.8620 | LM_LOSS: 0.3365 | LB_LOSS: 1.0511 |
| [2026-05-24 07:01:33] Validation | Batch 560/1463 | Loss: 0.8623 | LM_LOSS: 0.3367 | LB_LOSS: 1.0512 |
| [2026-05-24 07:01:35] Validation | Batch 570/1463 | Loss: 0.8623 | LM_LOSS: 0.3367 | LB_LOSS: 1.0512 |
| [2026-05-24 07:01:37] Validation | Batch 580/1463 | Loss: 0.8621 | LM_LOSS: 0.3365 | LB_LOSS: 1.0512 |
| [2026-05-24 07:01:40] Validation | Batch 590/1463 | Loss: 0.8619 | LM_LOSS: 0.3363 | LB_LOSS: 1.0513 |
| [2026-05-24 07:01:42] Validation | Batch 600/1463 | Loss: 0.8623 | LM_LOSS: 0.3366 | LB_LOSS: 1.0513 |
| [2026-05-24 07:01:44] Validation | Batch 610/1463 | Loss: 0.8624 | LM_LOSS: 0.3367 | LB_LOSS: 1.0514 |
| [2026-05-24 07:01:46] Validation | Batch 620/1463 | Loss: 0.8618 | LM_LOSS: 0.3361 | LB_LOSS: 1.0513 |
| [2026-05-24 07:01:48] Validation | Batch 630/1463 | Loss: 0.8614 | LM_LOSS: 0.3357 | LB_LOSS: 1.0514 |
| [2026-05-24 07:01:50] Validation | Batch 640/1463 | Loss: 0.8613 | LM_LOSS: 0.3355 | LB_LOSS: 1.0514 |
| [2026-05-24 07:01:51] Validation | Batch 650/1463 | Loss: 0.8606 | LM_LOSS: 0.3349 | LB_LOSS: 1.0514 |
| [2026-05-24 07:01:53] Validation | Batch 660/1463 | Loss: 0.8601 | LM_LOSS: 0.3344 | LB_LOSS: 1.0514 |
| [2026-05-24 07:01:55] Validation | Batch 670/1463 | Loss: 0.8597 | LM_LOSS: 0.3341 | LB_LOSS: 1.0513 |
| [2026-05-24 07:01:57] Validation | Batch 680/1463 | Loss: 0.8597 | LM_LOSS: 0.3341 | LB_LOSS: 1.0512 |
| [2026-05-24 07:01:59] Validation | Batch 690/1463 | Loss: 0.8601 | LM_LOSS: 0.3345 | LB_LOSS: 1.0513 |
| [2026-05-24 07:02:01] Validation | Batch 700/1463 | Loss: 0.8600 | LM_LOSS: 0.3343 | LB_LOSS: 1.0513 |
| [2026-05-24 07:02:02] Validation | Batch 710/1463 | Loss: 0.8603 | LM_LOSS: 0.3347 | LB_LOSS: 1.0514 |
| [2026-05-24 07:02:05] Validation | Batch 720/1463 | Loss: 0.8611 | LM_LOSS: 0.3354 | LB_LOSS: 1.0514 |
| [2026-05-24 07:02:06] Validation | Batch 730/1463 | Loss: 0.8609 | LM_LOSS: 0.3352 | LB_LOSS: 1.0514 |
| [2026-05-24 07:02:08] Validation | Batch 740/1463 | Loss: 0.8607 | LM_LOSS: 0.3349 | LB_LOSS: 1.0514 |
| [2026-05-24 07:02:09] Validation | Batch 750/1463 | Loss: 0.8605 | LM_LOSS: 0.3348 | LB_LOSS: 1.0514 |
| [2026-05-24 07:02:11] Validation | Batch 760/1463 | Loss: 0.8603 | LM_LOSS: 0.3346 | LB_LOSS: 1.0514 |
| [2026-05-24 07:02:13] Validation | Batch 770/1463 | Loss: 0.8601 | LM_LOSS: 0.3343 | LB_LOSS: 1.0515 |
| [2026-05-24 07:02:15] Validation | Batch 780/1463 | Loss: 0.8598 | LM_LOSS: 0.3341 | LB_LOSS: 1.0514 |
| [2026-05-24 07:02:16] Validation | Batch 790/1463 | Loss: 0.8600 | LM_LOSS: 0.3343 | LB_LOSS: 1.0513 |
| [2026-05-24 07:02:18] Validation | Batch 800/1463 | Loss: 0.8599 | LM_LOSS: 0.3343 | LB_LOSS: 1.0514 |
| [2026-05-24 07:02:20] Validation | Batch 810/1463 | Loss: 0.8595 | LM_LOSS: 0.3339 | LB_LOSS: 1.0513 |
| [2026-05-24 07:02:22] Validation | Batch 820/1463 | Loss: 0.8598 | LM_LOSS: 0.3341 | LB_LOSS: 1.0512 |
| [2026-05-24 07:02:24] Validation | Batch 830/1463 | Loss: 0.8600 | LM_LOSS: 0.3343 | LB_LOSS: 1.0513 |
| [2026-05-24 07:02:26] Validation | Batch 840/1463 | Loss: 0.8600 | LM_LOSS: 0.3343 | LB_LOSS: 1.0513 |
| [2026-05-24 07:02:28] Validation | Batch 850/1463 | Loss: 0.8603 | LM_LOSS: 0.3346 | LB_LOSS: 1.0513 |
| [2026-05-24 07:02:30] Validation | Batch 860/1463 | Loss: 0.8603 | LM_LOSS: 0.3346 | LB_LOSS: 1.0514 |
| [2026-05-24 07:02:32] Validation | Batch 870/1463 | Loss: 0.8603 | LM_LOSS: 0.3346 | LB_LOSS: 1.0514 |
| [2026-05-24 07:02:34] Validation | Batch 880/1463 | Loss: 0.8595 | LM_LOSS: 0.3338 | LB_LOSS: 1.0514 |
| [2026-05-24 07:02:36] Validation | Batch 890/1463 | Loss: 0.8595 | LM_LOSS: 0.3339 | LB_LOSS: 1.0513 |
| [2026-05-24 07:02:38] Validation | Batch 900/1463 | Loss: 0.8592 | LM_LOSS: 0.3336 | LB_LOSS: 1.0513 |
| [2026-05-24 07:02:40] Validation | Batch 910/1463 | Loss: 0.8592 | LM_LOSS: 0.3335 | LB_LOSS: 1.0513 |
| [2026-05-24 07:02:42] Validation | Batch 920/1463 | Loss: 0.8593 | LM_LOSS: 0.3336 | LB_LOSS: 1.0513 |
| [2026-05-24 07:02:44] Validation | Batch 930/1463 | Loss: 0.8590 | LM_LOSS: 0.3334 | LB_LOSS: 1.0513 |
| [2026-05-24 07:02:46] Validation | Batch 940/1463 | Loss: 0.8587 | LM_LOSS: 0.3331 | LB_LOSS: 1.0512 |
| [2026-05-24 07:02:48] Validation | Batch 950/1463 | Loss: 0.8590 | LM_LOSS: 0.3334 | LB_LOSS: 1.0512 |
| [2026-05-24 07:02:50] Validation | Batch 960/1463 | Loss: 0.8591 | LM_LOSS: 0.3335 | LB_LOSS: 1.0512 |
| [2026-05-24 07:02:52] Validation | Batch 970/1463 | Loss: 0.8592 | LM_LOSS: 0.3337 | LB_LOSS: 1.0511 |
| [2026-05-24 07:02:54] Validation | Batch 980/1463 | Loss: 0.8595 | LM_LOSS: 0.3340 | LB_LOSS: 1.0511 |
| [2026-05-24 07:02:56] Validation | Batch 990/1463 | Loss: 0.8598 | LM_LOSS: 0.3342 | LB_LOSS: 1.0511 |
| [2026-05-24 07:02:58] Validation | Batch 1000/1463 | Loss: 0.8604 | LM_LOSS: 0.3348 | LB_LOSS: 1.0511 |
| [2026-05-24 07:03:00] Validation | Batch 1010/1463 | Loss: 0.8604 | LM_LOSS: 0.3348 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:02] Validation | Batch 1020/1463 | Loss: 0.8605 | LM_LOSS: 0.3349 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:04] Validation | Batch 1030/1463 | Loss: 0.8609 | LM_LOSS: 0.3353 | LB_LOSS: 1.0513 |
| [2026-05-24 07:03:06] Validation | Batch 1040/1463 | Loss: 0.8605 | LM_LOSS: 0.3349 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:08] Validation | Batch 1050/1463 | Loss: 0.8604 | LM_LOSS: 0.3348 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:10] Validation | Batch 1060/1463 | Loss: 0.8603 | LM_LOSS: 0.3347 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:12] Validation | Batch 1070/1463 | Loss: 0.8603 | LM_LOSS: 0.3347 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:14] Validation | Batch 1080/1463 | Loss: 0.8601 | LM_LOSS: 0.3345 | LB_LOSS: 1.0513 |
| [2026-05-24 07:03:16] Validation | Batch 1090/1463 | Loss: 0.8602 | LM_LOSS: 0.3346 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:18] Validation | Batch 1100/1463 | Loss: 0.8601 | LM_LOSS: 0.3345 | LB_LOSS: 1.0511 |
| [2026-05-24 07:03:19] Validation | Batch 1110/1463 | Loss: 0.8600 | LM_LOSS: 0.3345 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:21] Validation | Batch 1120/1463 | Loss: 0.8599 | LM_LOSS: 0.3343 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:24] Validation | Batch 1130/1463 | Loss: 0.8597 | LM_LOSS: 0.3341 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:26] Validation | Batch 1140/1463 | Loss: 0.8599 | LM_LOSS: 0.3343 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:28] Validation | Batch 1150/1463 | Loss: 0.8598 | LM_LOSS: 0.3342 | LB_LOSS: 1.0511 |
| [2026-05-24 07:03:30] Validation | Batch 1160/1463 | Loss: 0.8597 | LM_LOSS: 0.3342 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:32] Validation | Batch 1170/1463 | Loss: 0.8598 | LM_LOSS: 0.3342 | LB_LOSS: 1.0511 |
| [2026-05-24 07:03:34] Validation | Batch 1180/1463 | Loss: 0.8598 | LM_LOSS: 0.3342 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:36] Validation | Batch 1190/1463 | Loss: 0.8599 | LM_LOSS: 0.3344 | LB_LOSS: 1.0511 |
| [2026-05-24 07:03:38] Validation | Batch 1200/1463 | Loss: 0.8600 | LM_LOSS: 0.3344 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:40] Validation | Batch 1210/1463 | Loss: 0.8602 | LM_LOSS: 0.3346 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:42] Validation | Batch 1220/1463 | Loss: 0.8606 | LM_LOSS: 0.3350 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:44] Validation | Batch 1230/1463 | Loss: 0.8606 | LM_LOSS: 0.3350 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:46] Validation | Batch 1240/1463 | Loss: 0.8609 | LM_LOSS: 0.3353 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:48] Validation | Batch 1250/1463 | Loss: 0.8611 | LM_LOSS: 0.3355 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:50] Validation | Batch 1260/1463 | Loss: 0.8610 | LM_LOSS: 0.3354 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:52] Validation | Batch 1270/1463 | Loss: 0.8608 | LM_LOSS: 0.3352 | LB_LOSS: 1.0513 |
| [2026-05-24 07:03:54] Validation | Batch 1280/1463 | Loss: 0.8606 | LM_LOSS: 0.3350 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:56] Validation | Batch 1290/1463 | Loss: 0.8606 | LM_LOSS: 0.3350 | LB_LOSS: 1.0512 |
| [2026-05-24 07:03:58] Validation | Batch 1300/1463 | Loss: 0.8604 | LM_LOSS: 0.3349 | LB_LOSS: 1.0512 |
| [2026-05-24 07:04:00] Validation | Batch 1310/1463 | Loss: 0.8603 | LM_LOSS: 0.3348 | LB_LOSS: 1.0512 |
| [2026-05-24 07:04:01] Validation | Batch 1320/1463 | Loss: 0.8604 | LM_LOSS: 0.3348 | LB_LOSS: 1.0511 |
| [2026-05-24 07:04:03] Validation | Batch 1330/1463 | Loss: 0.8605 | LM_LOSS: 0.3349 | LB_LOSS: 1.0511 |
| [2026-05-24 07:04:05] Validation | Batch 1340/1463 | Loss: 0.8607 | LM_LOSS: 0.3351 | LB_LOSS: 1.0512 |
| [2026-05-24 07:04:07] Validation | Batch 1350/1463 | Loss: 0.8608 | LM_LOSS: 0.3352 | LB_LOSS: 1.0511 |
| [2026-05-24 07:04:09] Validation | Batch 1360/1463 | Loss: 0.8610 | LM_LOSS: 0.3354 | LB_LOSS: 1.0511 |
| [2026-05-24 07:04:11] Validation | Batch 1370/1463 | Loss: 0.8613 | LM_LOSS: 0.3357 | LB_LOSS: 1.0512 |
| [2026-05-24 07:04:13] Validation | Batch 1380/1463 | Loss: 0.8611 | LM_LOSS: 0.3355 | LB_LOSS: 1.0511 |
| [2026-05-24 07:04:15] Validation | Batch 1390/1463 | Loss: 0.8610 | LM_LOSS: 0.3355 | LB_LOSS: 1.0512 |
| [2026-05-24 07:04:17] Validation | Batch 1400/1463 | Loss: 0.8613 | LM_LOSS: 0.3358 | LB_LOSS: 1.0511 |
| [2026-05-24 07:04:19] Validation | Batch 1410/1463 | Loss: 0.8615 | LM_LOSS: 0.3360 | LB_LOSS: 1.0511 |
| [2026-05-24 07:04:21] Validation | Batch 1420/1463 | Loss: 0.8615 | LM_LOSS: 0.3359 | LB_LOSS: 1.0511 |
| [2026-05-24 07:04:23] Validation | Batch 1430/1463 | Loss: 0.8616 | LM_LOSS: 0.3360 | LB_LOSS: 1.0511 |
| [2026-05-24 07:04:25] Validation | Batch 1440/1463 | Loss: 0.8620 | LM_LOSS: 0.3364 | LB_LOSS: 1.0511 |
| [2026-05-24 07:04:27] Validation | Batch 1450/1463 | Loss: 0.8617 | LM_LOSS: 0.3362 | LB_LOSS: 1.0511 |
| [2026-05-24 07:04:29] Validation | Batch 1460/1463 | Loss: 0.8620 | LM_LOSS: 0.3365 | LB_LOSS: 1.0511 |
| [2026-05-24 07:04:30] Validation | Batch 1463/1463 | Loss: 0.8619 | LM_LOSS: 0.3363 | LB_LOSS: 1.0511 |
| [2026-05-24 07:04:30] Validation | Loss: 0.8619 | LM_LOSS: 0.3363 | LB_LOSS: 1.0511 | PPL: 1.40 | Time: 286.53s |
| [2026-05-24 07:04:33] New best model saved! Val loss: 0.8619 |
| [2026-05-24 07:04:44] Epoch 1 | Step 3010 | Loss: 0.9076 | LM: 0.3458 | LB: 1.1303 | CL0: 3.1 | CL1: 4.3 | HR0: 0.327/SR0: 0.311 | HR1: 0.251/SR1: 0.223 | LR: 1.00e-04 |
| [2026-05-24 07:04:55] Epoch 1 | Step 3020 | Loss: 0.9074 | LM: 0.3458 | LB: 1.1300 | CL0: 3.1 | CL1: 4.3 | HR0: 0.327/SR0: 0.311 | HR1: 0.251/SR1: 0.222 | LR: 1.00e-04 |
| [2026-05-24 07:05:05] Epoch 1 | Step 3030 | Loss: 0.9071 | LM: 0.3458 | LB: 1.1298 | CL0: 3.1 | CL1: 4.3 | HR0: 0.327/SR0: 0.311 | HR1: 0.251/SR1: 0.222 | LR: 1.00e-04 |
| [2026-05-24 07:05:16] Epoch 1 | Step 3040 | Loss: 0.9070 | LM: 0.3457 | LB: 1.1295 | CL0: 3.1 | CL1: 4.3 | HR0: 0.327/SR0: 0.310 | HR1: 0.250/SR1: 0.222 | LR: 1.00e-04 |
| [2026-05-24 07:05:27] Epoch 1 | Step 3050 | Loss: 0.9068 | LM: 0.3458 | LB: 1.1292 | CL0: 3.1 | CL1: 4.3 | HR0: 0.327/SR0: 0.310 | HR1: 0.250/SR1: 0.222 | LR: 1.00e-04 |
| [2026-05-24 07:05:38] Epoch 1 | Step 3060 | Loss: 0.9067 | LM: 0.3459 | LB: 1.1290 | CL0: 3.1 | CL1: 4.4 | HR0: 0.327/SR0: 0.310 | HR1: 0.250/SR1: 0.222 | LR: 1.00e-04 |
| [2026-05-24 07:05:49] Epoch 1 | Step 3070 | Loss: 0.9064 | LM: 0.3458 | LB: 1.1287 | CL0: 3.1 | CL1: 4.4 | HR0: 0.327/SR0: 0.310 | HR1: 0.250/SR1: 0.222 | LR: 1.00e-04 |
| [2026-05-24 07:05:59] Epoch 1 | Step 3080 | Loss: 0.9063 | LM: 0.3457 | LB: 1.1284 | CL0: 3.1 | CL1: 4.4 | HR0: 0.326/SR0: 0.310 | HR1: 0.250/SR1: 0.221 | LR: 1.00e-04 |
| [2026-05-24 07:06:10] Epoch 1 | Step 3090 | Loss: 0.9062 | LM: 0.3456 | LB: 1.1282 | CL0: 3.1 | CL1: 4.4 | HR0: 0.326/SR0: 0.310 | HR1: 0.250/SR1: 0.221 | LR: 1.00e-04 |
| [2026-05-24 07:06:21] Epoch 1 | Step 3100 | Loss: 0.9060 | LM: 0.3453 | LB: 1.1279 | CL0: 3.1 | CL1: 4.4 | HR0: 0.326/SR0: 0.310 | HR1: 0.249/SR1: 0.221 | LR: 1.00e-04 |
| [2026-05-24 07:06:32] Epoch 1 | Step 3110 | Loss: 0.9058 | LM: 0.3452 | LB: 1.1276 | CL0: 3.1 | CL1: 4.4 | HR0: 0.326/SR0: 0.309 | HR1: 0.249/SR1: 0.221 | LR: 1.00e-04 |
| [2026-05-24 07:06:43] Epoch 1 | Step 3120 | Loss: 0.9058 | LM: 0.3453 | LB: 1.1274 | CL0: 3.1 | CL1: 4.4 | HR0: 0.326/SR0: 0.309 | HR1: 0.249/SR1: 0.221 | LR: 1.00e-04 |
| [2026-05-24 07:06:54] Epoch 1 | Step 3130 | Loss: 0.9057 | LM: 0.3453 | LB: 1.1272 | CL0: 3.1 | CL1: 4.4 | HR0: 0.326/SR0: 0.309 | HR1: 0.249/SR1: 0.221 | LR: 1.00e-04 |
| [2026-05-24 07:07:05] Epoch 1 | Step 3140 | Loss: 0.9055 | LM: 0.3450 | LB: 1.1269 | CL0: 3.1 | CL1: 4.4 | HR0: 0.326/SR0: 0.309 | HR1: 0.249/SR1: 0.220 | LR: 1.00e-04 |
| [2026-05-24 07:07:16] Epoch 1 | Step 3150 | Loss: 0.9054 | LM: 0.3450 | LB: 1.1266 | CL0: 3.1 | CL1: 4.4 | HR0: 0.326/SR0: 0.309 | HR1: 0.249/SR1: 0.220 | LR: 1.00e-04 |
| [2026-05-24 07:07:26] Epoch 1 | Step 3160 | Loss: 0.9053 | LM: 0.3450 | LB: 1.1264 | CL0: 3.1 | CL1: 4.4 | HR0: 0.326/SR0: 0.309 | HR1: 0.249/SR1: 0.220 | LR: 1.00e-04 |
| [2026-05-24 07:07:37] Epoch 1 | Step 3170 | Loss: 0.9053 | LM: 0.3452 | LB: 1.1262 | CL0: 3.1 | CL1: 4.4 | HR0: 0.325/SR0: 0.309 | HR1: 0.248/SR1: 0.220 | LR: 1.00e-04 |
| [2026-05-24 07:07:48] Epoch 1 | Step 3180 | Loss: 0.9052 | LM: 0.3452 | LB: 1.1259 | CL0: 3.1 | CL1: 4.4 | HR0: 0.325/SR0: 0.308 | HR1: 0.248/SR1: 0.220 | LR: 1.00e-04 |
| [2026-05-24 07:07:59] Epoch 1 | Step 3190 | Loss: 0.9051 | LM: 0.3452 | LB: 1.1256 | CL0: 3.1 | CL1: 4.4 | HR0: 0.325/SR0: 0.308 | HR1: 0.248/SR1: 0.220 | LR: 1.00e-04 |
| [2026-05-24 07:08:10] Epoch 1 | Step 3200 | Loss: 0.9049 | LM: 0.3449 | LB: 1.1254 | CL0: 3.1 | CL1: 4.4 | HR0: 0.325/SR0: 0.308 | HR1: 0.248/SR1: 0.220 | LR: 1.00e-04 |
| [2026-05-24 07:08:20] Epoch 1 | Step 3210 | Loss: 0.9047 | LM: 0.3449 | LB: 1.1251 | CL0: 3.1 | CL1: 4.4 | HR0: 0.325/SR0: 0.308 | HR1: 0.248/SR1: 0.219 | LR: 1.00e-04 |
| [2026-05-24 07:08:31] Epoch 1 | Step 3220 | Loss: 0.9047 | LM: 0.3452 | LB: 1.1249 | CL0: 3.1 | CL1: 4.4 | HR0: 0.325/SR0: 0.308 | HR1: 0.248/SR1: 0.219 | LR: 1.00e-04 |
| [2026-05-24 07:08:42] Epoch 1 | Step 3230 | Loss: 0.9046 | LM: 0.3451 | LB: 1.1246 | CL0: 3.1 | CL1: 4.4 | HR0: 0.325/SR0: 0.308 | HR1: 0.247/SR1: 0.219 | LR: 1.00e-04 |
| [2026-05-24 07:08:53] Epoch 1 | Step 3240 | Loss: 0.9045 | LM: 0.3451 | LB: 1.1244 | CL0: 3.1 | CL1: 4.4 | HR0: 0.325/SR0: 0.308 | HR1: 0.247/SR1: 0.219 | LR: 1.00e-04 |
| [2026-05-24 07:09:04] Epoch 1 | Step 3250 | Loss: 0.9043 | LM: 0.3450 | LB: 1.1242 | CL0: 3.1 | CL1: 4.4 | HR0: 0.325/SR0: 0.307 | HR1: 0.247/SR1: 0.219 | LR: 1.00e-04 |
| [2026-05-24 07:09:14] Epoch 1 | Step 3260 | Loss: 0.9041 | LM: 0.3450 | LB: 1.1239 | CL0: 3.1 | CL1: 4.4 | HR0: 0.324/SR0: 0.307 | HR1: 0.247/SR1: 0.219 | LR: 1.00e-04 |
| [2026-05-24 07:09:25] Epoch 1 | Step 3270 | Loss: 0.9040 | LM: 0.3450 | LB: 1.1237 | CL0: 3.1 | CL1: 4.4 | HR0: 0.324/SR0: 0.307 | HR1: 0.247/SR1: 0.219 | LR: 1.00e-04 |
| [2026-05-24 07:09:36] Epoch 1 | Step 3280 | Loss: 0.9039 | LM: 0.3449 | LB: 1.1235 | CL0: 3.1 | CL1: 4.4 | HR0: 0.324/SR0: 0.307 | HR1: 0.247/SR1: 0.219 | LR: 1.00e-04 |
| [2026-05-24 07:09:46] Epoch 1 | Step 3290 | Loss: 0.9037 | LM: 0.3447 | LB: 1.1232 | CL0: 3.1 | CL1: 4.4 | HR0: 0.324/SR0: 0.307 | HR1: 0.247/SR1: 0.218 | LR: 1.00e-04 |
| [2026-05-24 07:09:57] Epoch 1 | Step 3300 | Loss: 0.9036 | LM: 0.3447 | LB: 1.1230 | CL0: 3.1 | CL1: 4.4 | HR0: 0.324/SR0: 0.307 | HR1: 0.247/SR1: 0.218 | LR: 1.00e-04 |
| [2026-05-24 07:10:08] Epoch 1 | Step 3310 | Loss: 0.9035 | LM: 0.3449 | LB: 1.1227 | CL0: 3.1 | CL1: 4.4 | HR0: 0.324/SR0: 0.307 | HR1: 0.246/SR1: 0.218 | LR: 1.00e-04 |
| [2026-05-24 07:10:18] Epoch 1 | Step 3320 | Loss: 0.9034 | LM: 0.3450 | LB: 1.1225 | CL0: 3.1 | CL1: 4.4 | HR0: 0.324/SR0: 0.306 | HR1: 0.246/SR1: 0.218 | LR: 1.00e-04 |
| [2026-05-24 07:10:29] Epoch 1 | Step 3330 | Loss: 0.9033 | LM: 0.3449 | LB: 1.1223 | CL0: 3.1 | CL1: 4.4 | HR0: 0.324/SR0: 0.306 | HR1: 0.246/SR1: 0.218 | LR: 1.00e-04 |
| [2026-05-24 07:10:40] Epoch 1 | Step 3340 | Loss: 0.9032 | LM: 0.3450 | LB: 1.1221 | CL0: 3.1 | CL1: 4.4 | HR0: 0.324/SR0: 0.306 | HR1: 0.246/SR1: 0.218 | LR: 1.00e-04 |
| [2026-05-24 07:10:50] Epoch 1 | Step 3350 | Loss: 0.9031 | LM: 0.3452 | LB: 1.1219 | CL0: 3.1 | CL1: 4.4 | HR0: 0.324/SR0: 0.306 | HR1: 0.246/SR1: 0.218 | LR: 1.00e-04 |
| [2026-05-24 07:11:01] Epoch 1 | Step 3360 | Loss: 0.9030 | LM: 0.3451 | LB: 1.1217 | CL0: 3.1 | CL1: 4.4 | HR0: 0.324/SR0: 0.306 | HR1: 0.246/SR1: 0.217 | LR: 1.00e-04 |
| [2026-05-24 07:11:11] Epoch 1 | Step 3370 | Loss: 0.9029 | LM: 0.3450 | LB: 1.1215 | CL0: 3.1 | CL1: 4.4 | HR0: 0.323/SR0: 0.306 | HR1: 0.246/SR1: 0.217 | LR: 1.00e-04 |
| [2026-05-24 07:11:22] Epoch 1 | Step 3380 | Loss: 0.9028 | LM: 0.3449 | LB: 1.1212 | CL0: 3.1 | CL1: 4.4 | HR0: 0.323/SR0: 0.306 | HR1: 0.245/SR1: 0.217 | LR: 1.00e-04 |
| [2026-05-24 07:11:33] Epoch 1 | Step 3390 | Loss: 0.9026 | LM: 0.3448 | LB: 1.1210 | CL0: 3.1 | CL1: 4.4 | HR0: 0.323/SR0: 0.306 | HR1: 0.245/SR1: 0.217 | LR: 1.00e-04 |
| [2026-05-24 07:11:44] Epoch 1 | Step 3400 | Loss: 0.9025 | LM: 0.3447 | LB: 1.1208 | CL0: 3.1 | CL1: 4.4 | HR0: 0.323/SR0: 0.305 | HR1: 0.245/SR1: 0.217 | LR: 1.00e-04 |
| [2026-05-24 07:11:54] Epoch 1 | Step 3410 | Loss: 0.9024 | LM: 0.3447 | LB: 1.1205 | CL0: 3.1 | CL1: 4.4 | HR0: 0.323/SR0: 0.305 | HR1: 0.245/SR1: 0.217 | LR: 1.00e-04 |
| [2026-05-24 07:12:05] Epoch 1 | Step 3420 | Loss: 0.9022 | LM: 0.3447 | LB: 1.1203 | CL0: 3.1 | CL1: 4.4 | HR0: 0.323/SR0: 0.305 | HR1: 0.245/SR1: 0.217 | LR: 1.00e-04 |
| [2026-05-24 07:12:16] Epoch 1 | Step 3430 | Loss: 0.9020 | LM: 0.3445 | LB: 1.1201 | CL0: 3.1 | CL1: 4.4 | HR0: 0.323/SR0: 0.305 | HR1: 0.245/SR1: 0.216 | LR: 1.00e-04 |
| [2026-05-24 07:12:26] Epoch 1 | Step 3440 | Loss: 0.9020 | LM: 0.3444 | LB: 1.1199 | CL0: 3.1 | CL1: 4.4 | HR0: 0.323/SR0: 0.305 | HR1: 0.245/SR1: 0.216 | LR: 1.00e-04 |
| [2026-05-24 07:12:37] Epoch 1 | Step 3450 | Loss: 0.9018 | LM: 0.3443 | LB: 1.1197 | CL0: 3.1 | CL1: 4.4 | HR0: 0.323/SR0: 0.305 | HR1: 0.244/SR1: 0.216 | LR: 1.00e-04 |
| [2026-05-24 07:12:48] Epoch 1 | Step 3460 | Loss: 0.9017 | LM: 0.3443 | LB: 1.1195 | CL0: 3.1 | CL1: 4.4 | HR0: 0.323/SR0: 0.305 | HR1: 0.244/SR1: 0.216 | LR: 1.00e-04 |
| [2026-05-24 07:12:58] Epoch 1 | Step 3470 | Loss: 0.9016 | LM: 0.3443 | LB: 1.1193 | CL0: 3.1 | CL1: 4.4 | HR0: 0.323/SR0: 0.305 | HR1: 0.244/SR1: 0.216 | LR: 1.00e-04 |
| [2026-05-24 07:13:09] Epoch 1 | Step 3480 | Loss: 0.9015 | LM: 0.3444 | LB: 1.1191 | CL0: 3.1 | CL1: 4.4 | HR0: 0.322/SR0: 0.304 | HR1: 0.244/SR1: 0.216 | LR: 1.00e-04 |
| [2026-05-24 07:13:20] Epoch 1 | Step 3490 | Loss: 0.9015 | LM: 0.3445 | LB: 1.1189 | CL0: 3.1 | CL1: 4.4 | HR0: 0.322/SR0: 0.304 | HR1: 0.244/SR1: 0.216 | LR: 1.00e-04 |
| [2026-05-24 07:13:30] Epoch 1 | Step 3500 | Loss: 0.9015 | LM: 0.3447 | LB: 1.1186 | CL0: 3.1 | CL1: 4.4 | HR0: 0.322/SR0: 0.304 | HR1: 0.244/SR1: 0.215 | LR: 1.00e-04 |
| [2026-05-24 07:13:41] Epoch 1 | Step 3510 | Loss: 0.9015 | LM: 0.3447 | LB: 1.1185 | CL0: 3.1 | CL1: 4.4 | HR0: 0.322/SR0: 0.304 | HR1: 0.244/SR1: 0.215 | LR: 1.00e-04 |
| [2026-05-24 07:13:52] Epoch 1 | Step 3520 | Loss: 0.9014 | LM: 0.3447 | LB: 1.1182 | CL0: 3.1 | CL1: 4.4 | HR0: 0.322/SR0: 0.304 | HR1: 0.244/SR1: 0.215 | LR: 1.00e-04 |
| [2026-05-24 07:14:03] Epoch 1 | Step 3530 | Loss: 0.9013 | LM: 0.3447 | LB: 1.1180 | CL0: 3.1 | CL1: 4.4 | HR0: 0.322/SR0: 0.304 | HR1: 0.243/SR1: 0.215 | LR: 1.00e-04 |
| [2026-05-24 07:14:15] Epoch 1 | Step 3540 | Loss: 0.9012 | LM: 0.3447 | LB: 1.1178 | CL0: 3.1 | CL1: 4.5 | HR0: 0.322/SR0: 0.304 | HR1: 0.243/SR1: 0.215 | LR: 1.00e-04 |
| [2026-05-24 07:14:26] Epoch 1 | Step 3550 | Loss: 0.9011 | LM: 0.3447 | LB: 1.1176 | CL0: 3.1 | CL1: 4.5 | HR0: 0.322/SR0: 0.304 | HR1: 0.243/SR1: 0.215 | LR: 1.00e-04 |
| [2026-05-24 07:14:37] Epoch 1 | Step 3560 | Loss: 0.9010 | LM: 0.3447 | LB: 1.1173 | CL0: 3.1 | CL1: 4.5 | HR0: 0.322/SR0: 0.303 | HR1: 0.243/SR1: 0.215 | LR: 1.00e-04 |
| [2026-05-24 07:14:49] Epoch 1 | Step 3570 | Loss: 0.9009 | LM: 0.3447 | LB: 1.1171 | CL0: 3.1 | CL1: 4.5 | HR0: 0.322/SR0: 0.303 | HR1: 0.243/SR1: 0.214 | LR: 1.00e-04 |
| [2026-05-24 07:15:00] Epoch 1 | Step 3580 | Loss: 0.9007 | LM: 0.3446 | LB: 1.1169 | CL0: 3.1 | CL1: 4.5 | HR0: 0.322/SR0: 0.303 | HR1: 0.243/SR1: 0.214 | LR: 1.00e-04 |
| [2026-05-24 07:15:11] Epoch 1 | Step 3590 | Loss: 0.9005 | LM: 0.3448 | LB: 1.1167 | CL0: 3.1 | CL1: 4.5 | HR0: 0.321/SR0: 0.303 | HR1: 0.242/SR1: 0.214 | LR: 1.00e-04 |
| [2026-05-24 07:15:22] Epoch 1 | Step 3600 | Loss: 0.9004 | LM: 0.3446 | LB: 1.1165 | CL0: 3.1 | CL1: 4.5 | HR0: 0.321/SR0: 0.303 | HR1: 0.242/SR1: 0.214 | LR: 1.00e-04 |
| [2026-05-24 07:15:33] Epoch 1 | Step 3610 | Loss: 0.9003 | LM: 0.3445 | LB: 1.1163 | CL0: 3.1 | CL1: 4.5 | HR0: 0.321/SR0: 0.303 | HR1: 0.242/SR1: 0.214 | LR: 1.00e-04 |
| [2026-05-24 07:15:45] Epoch 1 | Step 3620 | Loss: 0.9002 | LM: 0.3446 | LB: 1.1161 | CL0: 3.1 | CL1: 4.5 | HR0: 0.321/SR0: 0.303 | HR1: 0.242/SR1: 0.214 | LR: 1.00e-04 |
| [2026-05-24 07:15:56] Epoch 1 | Step 3630 | Loss: 0.9000 | LM: 0.3446 | LB: 1.1159 | CL0: 3.1 | CL1: 4.5 | HR0: 0.321/SR0: 0.303 | HR1: 0.242/SR1: 0.214 | LR: 1.00e-04 |
| [2026-05-24 07:16:07] Epoch 1 | Step 3640 | Loss: 0.9000 | LM: 0.3448 | LB: 1.1157 | CL0: 3.1 | CL1: 4.5 | HR0: 0.321/SR0: 0.302 | HR1: 0.242/SR1: 0.214 | LR: 1.00e-04 |
| [2026-05-24 07:16:18] Epoch 1 | Step 3650 | Loss: 0.8999 | LM: 0.3449 | LB: 1.1155 | CL0: 3.1 | CL1: 4.5 | HR0: 0.321/SR0: 0.302 | HR1: 0.242/SR1: 0.213 | LR: 1.00e-04 |
| [2026-05-24 07:16:29] Epoch 1 | Step 3660 | Loss: 0.8999 | LM: 0.3450 | LB: 1.1153 | CL0: 3.1 | CL1: 4.5 | HR0: 0.321/SR0: 0.302 | HR1: 0.242/SR1: 0.213 | LR: 1.00e-04 |
| [2026-05-24 07:16:41] Epoch 1 | Step 3670 | Loss: 0.8998 | LM: 0.3450 | LB: 1.1151 | CL0: 3.1 | CL1: 4.5 | HR0: 0.321/SR0: 0.302 | HR1: 0.241/SR1: 0.213 | LR: 1.00e-04 |
| [2026-05-24 07:16:52] Epoch 1 | Step 3680 | Loss: 0.8996 | LM: 0.3449 | LB: 1.1149 | CL0: 3.2 | CL1: 4.5 | HR0: 0.321/SR0: 0.302 | HR1: 0.241/SR1: 0.213 | LR: 1.00e-04 |
| [2026-05-24 07:17:03] Epoch 1 | Step 3690 | Loss: 0.8995 | LM: 0.3450 | LB: 1.1147 | CL0: 3.2 | CL1: 4.5 | HR0: 0.321/SR0: 0.302 | HR1: 0.241/SR1: 0.213 | LR: 1.00e-04 |
| [2026-05-24 07:17:14] Epoch 1 | Step 3700 | Loss: 0.8993 | LM: 0.3450 | LB: 1.1145 | CL0: 3.2 | CL1: 4.5 | HR0: 0.320/SR0: 0.302 | HR1: 0.241/SR1: 0.213 | LR: 1.00e-04 |
| [2026-05-24 07:17:26] Epoch 1 | Step 3710 | Loss: 0.8992 | LM: 0.3450 | LB: 1.1143 | CL0: 3.2 | CL1: 4.5 | HR0: 0.320/SR0: 0.301 | HR1: 0.241/SR1: 0.213 | LR: 1.00e-04 |
| [2026-05-24 07:17:37] Epoch 1 | Step 3720 | Loss: 0.8992 | LM: 0.3451 | LB: 1.1141 | CL0: 3.2 | CL1: 4.5 | HR0: 0.320/SR0: 0.301 | HR1: 0.241/SR1: 0.213 | LR: 1.00e-04 |
| [2026-05-24 07:17:48] Epoch 1 | Step 3730 | Loss: 0.8992 | LM: 0.3449 | LB: 1.1139 | CL0: 3.2 | CL1: 4.5 | HR0: 0.320/SR0: 0.301 | HR1: 0.241/SR1: 0.213 | LR: 1.00e-04 |
| [2026-05-24 07:17:59] Epoch 1 | Step 3740 | Loss: 0.8991 | LM: 0.3449 | LB: 1.1137 | CL0: 3.2 | CL1: 4.5 | HR0: 0.320/SR0: 0.301 | HR1: 0.241/SR1: 0.212 | LR: 1.00e-04 |
| [2026-05-24 07:18:11] Epoch 1 | Step 3750 | Loss: 0.8990 | LM: 0.3449 | LB: 1.1135 | CL0: 3.2 | CL1: 4.5 | HR0: 0.320/SR0: 0.301 | HR1: 0.241/SR1: 0.212 | LR: 1.00e-04 |
| [2026-05-24 07:18:22] Epoch 1 | Step 3760 | Loss: 0.8989 | LM: 0.3449 | LB: 1.1134 | CL0: 3.2 | CL1: 4.5 | HR0: 0.320/SR0: 0.301 | HR1: 0.240/SR1: 0.212 | LR: 1.00e-04 |
| [2026-05-24 07:18:34] Epoch 1 | Step 3770 | Loss: 0.8987 | LM: 0.3450 | LB: 1.1132 | CL0: 3.2 | CL1: 4.5 | HR0: 0.320/SR0: 0.301 | HR1: 0.240/SR1: 0.212 | LR: 1.00e-04 |
| [2026-05-24 07:18:45] Epoch 1 | Step 3780 | Loss: 0.8986 | LM: 0.3449 | LB: 1.1130 | CL0: 3.2 | CL1: 4.5 | HR0: 0.320/SR0: 0.301 | HR1: 0.240/SR1: 0.212 | LR: 1.00e-04 |
| [2026-05-24 07:18:56] Epoch 1 | Step 3790 | Loss: 0.8986 | LM: 0.3451 | LB: 1.1128 | CL0: 3.2 | CL1: 4.5 | HR0: 0.320/SR0: 0.301 | HR1: 0.240/SR1: 0.212 | LR: 1.00e-04 |
| [2026-05-24 07:19:07] Epoch 1 | Step 3800 | Loss: 0.8985 | LM: 0.3451 | LB: 1.1126 | CL0: 3.2 | CL1: 4.5 | HR0: 0.320/SR0: 0.300 | HR1: 0.240/SR1: 0.212 | LR: 1.00e-04 |
| [2026-05-24 07:19:17] Epoch 1 | Step 3810 | Loss: 0.8984 | LM: 0.3450 | LB: 1.1124 | CL0: 3.2 | CL1: 4.5 | HR0: 0.320/SR0: 0.300 | HR1: 0.240/SR1: 0.212 | LR: 1.00e-04 |
| [2026-05-24 07:19:28] Epoch 1 | Step 3820 | Loss: 0.8982 | LM: 0.3450 | LB: 1.1123 | CL0: 3.2 | CL1: 4.5 | HR0: 0.319/SR0: 0.300 | HR1: 0.240/SR1: 0.212 | LR: 1.00e-04 |
| [2026-05-24 07:19:38] Epoch 1 | Step 3830 | Loss: 0.8981 | LM: 0.3449 | LB: 1.1121 | CL0: 3.2 | CL1: 4.5 | HR0: 0.319/SR0: 0.300 | HR1: 0.240/SR1: 0.211 | LR: 1.00e-04 |
| [2026-05-24 07:19:49] Epoch 1 | Step 3840 | Loss: 0.8979 | LM: 0.3448 | LB: 1.1119 | CL0: 3.2 | CL1: 4.5 | HR0: 0.319/SR0: 0.300 | HR1: 0.240/SR1: 0.211 | LR: 1.00e-04 |
| [2026-05-24 07:20:00] Epoch 1 | Step 3850 | Loss: 0.8979 | LM: 0.3447 | LB: 1.1117 | CL0: 3.2 | CL1: 4.5 | HR0: 0.319/SR0: 0.300 | HR1: 0.240/SR1: 0.211 | LR: 1.00e-04 |
| [2026-05-24 07:20:11] Epoch 1 | Step 3860 | Loss: 0.8978 | LM: 0.3449 | LB: 1.1115 | CL0: 3.2 | CL1: 4.5 | HR0: 0.319/SR0: 0.300 | HR1: 0.239/SR1: 0.211 | LR: 1.00e-04 |
| [2026-05-24 07:20:22] Epoch 1 | Step 3870 | Loss: 0.8977 | LM: 0.3447 | LB: 1.1113 | CL0: 3.2 | CL1: 4.5 | HR0: 0.319/SR0: 0.300 | HR1: 0.239/SR1: 0.211 | LR: 1.00e-04 |
| [2026-05-24 07:20:33] Epoch 1 | Step 3880 | Loss: 0.8977 | LM: 0.3448 | LB: 1.1112 | CL0: 3.2 | CL1: 4.5 | HR0: 0.319/SR0: 0.300 | HR1: 0.239/SR1: 0.211 | LR: 1.00e-04 |
| [2026-05-24 07:20:43] Epoch 1 | Step 3890 | Loss: 0.8977 | LM: 0.3448 | LB: 1.1110 | CL0: 3.2 | CL1: 4.5 | HR0: 0.319/SR0: 0.299 | HR1: 0.239/SR1: 0.211 | LR: 1.00e-04 |
| [2026-05-24 07:20:54] Epoch 1 | Step 3900 | Loss: 0.8976 | LM: 0.3448 | LB: 1.1108 | CL0: 3.2 | CL1: 4.5 | HR0: 0.319/SR0: 0.299 | HR1: 0.239/SR1: 0.211 | LR: 1.00e-04 |
| [2026-05-24 07:21:06] Epoch 1 | Step 3910 | Loss: 0.8975 | LM: 0.3445 | LB: 1.1106 | CL0: 3.2 | CL1: 4.5 | HR0: 0.319/SR0: 0.299 | HR1: 0.239/SR1: 0.211 | LR: 1.00e-04 |
| [2026-05-24 07:21:16] Epoch 1 | Step 3920 | Loss: 0.8974 | LM: 0.3444 | LB: 1.1104 | CL0: 3.2 | CL1: 4.5 | HR0: 0.319/SR0: 0.299 | HR1: 0.239/SR1: 0.211 | LR: 1.00e-04 |
| [2026-05-24 07:21:27] Epoch 1 | Step 3930 | Loss: 0.8973 | LM: 0.3445 | LB: 1.1102 | CL0: 3.2 | CL1: 4.5 | HR0: 0.319/SR0: 0.299 | HR1: 0.239/SR1: 0.210 | LR: 1.00e-04 |
| [2026-05-24 07:21:37] Epoch 1 | Step 3940 | Loss: 0.8972 | LM: 0.3443 | LB: 1.1101 | CL0: 3.2 | CL1: 4.5 | HR0: 0.318/SR0: 0.299 | HR1: 0.239/SR1: 0.210 | LR: 1.00e-04 |
| [2026-05-24 07:21:48] Epoch 1 | Step 3950 | Loss: 0.8971 | LM: 0.3442 | LB: 1.1099 | CL0: 3.2 | CL1: 4.5 | HR0: 0.318/SR0: 0.299 | HR1: 0.238/SR1: 0.210 | LR: 1.00e-04 |
| [2026-05-24 07:21:59] Epoch 1 | Step 3960 | Loss: 0.8971 | LM: 0.3443 | LB: 1.1097 | CL0: 3.2 | CL1: 4.5 | HR0: 0.318/SR0: 0.299 | HR1: 0.238/SR1: 0.210 | LR: 1.00e-04 |
| [2026-05-24 07:22:10] Epoch 1 | Step 3970 | Loss: 0.8970 | LM: 0.3443 | LB: 1.1095 | CL0: 3.2 | CL1: 4.5 | HR0: 0.318/SR0: 0.299 | HR1: 0.238/SR1: 0.210 | LR: 1.00e-04 |
| [2026-05-24 07:22:20] Epoch 1 | Step 3980 | Loss: 0.8969 | LM: 0.3443 | LB: 1.1094 | CL0: 3.2 | CL1: 4.5 | HR0: 0.318/SR0: 0.298 | HR1: 0.238/SR1: 0.210 | LR: 1.00e-04 |
| [2026-05-24 07:22:31] Epoch 1 | Step 3990 | Loss: 0.8968 | LM: 0.3444 | LB: 1.1092 | CL0: 3.2 | CL1: 4.5 | HR0: 0.318/SR0: 0.298 | HR1: 0.238/SR1: 0.210 | LR: 1.00e-04 |
| [2026-05-24 07:22:42] Epoch 1 | Step 4000 | Loss: 0.8968 | LM: 0.3443 | LB: 1.1090 | CL0: 3.2 | CL1: 4.5 | HR0: 0.318/SR0: 0.298 | HR1: 0.238/SR1: 0.210 | LR: 1.00e-04 |
| [2026-05-24 07:22:44] Validation | Batch 10/1463 | Loss: 0.8143 | LM_LOSS: 0.2984 | LB_LOSS: 1.0318 |
| [2026-05-24 07:22:46] Validation | Batch 20/1463 | Loss: 0.8311 | LM_LOSS: 0.3132 | LB_LOSS: 1.0357 |
| [2026-05-24 07:22:48] Validation | Batch 30/1463 | Loss: 0.8379 | LM_LOSS: 0.3195 | LB_LOSS: 1.0368 |
| [2026-05-24 07:22:50] Validation | Batch 40/1463 | Loss: 0.8480 | LM_LOSS: 0.3288 | LB_LOSS: 1.0383 |
| [2026-05-24 07:22:51] Validation | Batch 50/1463 | Loss: 0.8550 | LM_LOSS: 0.3363 | LB_LOSS: 1.0374 |
| [2026-05-24 07:22:54] Validation | Batch 60/1463 | Loss: 0.8553 | LM_LOSS: 0.3367 | LB_LOSS: 1.0374 |
| [2026-05-24 07:22:56] Validation | Batch 70/1463 | Loss: 0.8550 | LM_LOSS: 0.3362 | LB_LOSS: 1.0375 |
| [2026-05-24 07:22:58] Validation | Batch 80/1463 | Loss: 0.8576 | LM_LOSS: 0.3389 | LB_LOSS: 1.0375 |
| [2026-05-24 07:23:00] Validation | Batch 90/1463 | Loss: 0.8569 | LM_LOSS: 0.3382 | LB_LOSS: 1.0374 |
| [2026-05-24 07:23:02] Validation | Batch 100/1463 | Loss: 0.8570 | LM_LOSS: 0.3383 | LB_LOSS: 1.0374 |
| [2026-05-24 07:23:04] Validation | Batch 110/1463 | Loss: 0.8553 | LM_LOSS: 0.3364 | LB_LOSS: 1.0378 |
| [2026-05-24 07:23:06] Validation | Batch 120/1463 | Loss: 0.8567 | LM_LOSS: 0.3377 | LB_LOSS: 1.0380 |
| [2026-05-24 07:23:07] Validation | Batch 130/1463 | Loss: 0.8591 | LM_LOSS: 0.3400 | LB_LOSS: 1.0381 |
| [2026-05-24 07:23:09] Validation | Batch 140/1463 | Loss: 0.8601 | LM_LOSS: 0.3411 | LB_LOSS: 1.0379 |
| [2026-05-24 07:23:11] Validation | Batch 150/1463 | Loss: 0.8586 | LM_LOSS: 0.3395 | LB_LOSS: 1.0382 |
| [2026-05-24 07:23:13] Validation | Batch 160/1463 | Loss: 0.8594 | LM_LOSS: 0.3403 | LB_LOSS: 1.0380 |
| [2026-05-24 07:23:15] Validation | Batch 170/1463 | Loss: 0.8588 | LM_LOSS: 0.3398 | LB_LOSS: 1.0380 |
| [2026-05-24 07:23:17] Validation | Batch 180/1463 | Loss: 0.8597 | LM_LOSS: 0.3407 | LB_LOSS: 1.0381 |
| [2026-05-24 07:23:19] Validation | Batch 190/1463 | Loss: 0.8604 | LM_LOSS: 0.3413 | LB_LOSS: 1.0381 |
| [2026-05-24 07:23:21] Validation | Batch 200/1463 | Loss: 0.8604 | LM_LOSS: 0.3413 | LB_LOSS: 1.0381 |
| [2026-05-24 07:23:23] Validation | Batch 210/1463 | Loss: 0.8611 | LM_LOSS: 0.3420 | LB_LOSS: 1.0382 |
| [2026-05-24 07:23:25] Validation | Batch 220/1463 | Loss: 0.8601 | LM_LOSS: 0.3410 | LB_LOSS: 1.0382 |
| [2026-05-24 07:23:27] Validation | Batch 230/1463 | Loss: 0.8618 | LM_LOSS: 0.3428 | LB_LOSS: 1.0380 |
| [2026-05-24 07:23:29] Validation | Batch 240/1463 | Loss: 0.8631 | LM_LOSS: 0.3442 | LB_LOSS: 1.0379 |
| [2026-05-24 07:23:31] Validation | Batch 250/1463 | Loss: 0.8622 | LM_LOSS: 0.3432 | LB_LOSS: 1.0380 |
| [2026-05-24 07:23:33] Validation | Batch 260/1463 | Loss: 0.8638 | LM_LOSS: 0.3447 | LB_LOSS: 1.0382 |
| [2026-05-24 07:23:35] Validation | Batch 270/1463 | Loss: 0.8624 | LM_LOSS: 0.3433 | LB_LOSS: 1.0382 |
| [2026-05-24 07:23:37] Validation | Batch 280/1463 | Loss: 0.8633 | LM_LOSS: 0.3442 | LB_LOSS: 1.0383 |
| [2026-05-24 07:23:39] Validation | Batch 290/1463 | Loss: 0.8624 | LM_LOSS: 0.3433 | LB_LOSS: 1.0383 |
| [2026-05-24 07:23:41] Validation | Batch 300/1463 | Loss: 0.8628 | LM_LOSS: 0.3436 | LB_LOSS: 1.0384 |
| [2026-05-24 07:23:43] Validation | Batch 310/1463 | Loss: 0.8636 | LM_LOSS: 0.3444 | LB_LOSS: 1.0384 |
| [2026-05-24 07:23:45] Validation | Batch 320/1463 | Loss: 0.8622 | LM_LOSS: 0.3431 | LB_LOSS: 1.0382 |
| [2026-05-24 07:23:46] Validation | Batch 330/1463 | Loss: 0.8622 | LM_LOSS: 0.3431 | LB_LOSS: 1.0382 |
| [2026-05-24 07:23:48] Validation | Batch 340/1463 | Loss: 0.8618 | LM_LOSS: 0.3428 | LB_LOSS: 1.0382 |
| [2026-05-24 07:23:50] Validation | Batch 350/1463 | Loss: 0.8623 | LM_LOSS: 0.3433 | LB_LOSS: 1.0382 |
| [2026-05-24 07:23:52] Validation | Batch 360/1463 | Loss: 0.8621 | LM_LOSS: 0.3430 | LB_LOSS: 1.0382 |
| [2026-05-24 07:23:54] Validation | Batch 370/1463 | Loss: 0.8618 | LM_LOSS: 0.3427 | LB_LOSS: 1.0383 |
| [2026-05-24 07:23:56] Validation | Batch 380/1463 | Loss: 0.8619 | LM_LOSS: 0.3428 | LB_LOSS: 1.0382 |
| [2026-05-24 07:23:57] Validation | Batch 390/1463 | Loss: 0.8627 | LM_LOSS: 0.3436 | LB_LOSS: 1.0382 |
| [2026-05-24 07:23:59] Validation | Batch 400/1463 | Loss: 0.8625 | LM_LOSS: 0.3434 | LB_LOSS: 1.0383 |
| [2026-05-24 07:24:01] Validation | Batch 410/1463 | Loss: 0.8624 | LM_LOSS: 0.3432 | LB_LOSS: 1.0383 |
| [2026-05-24 07:24:03] Validation | Batch 420/1463 | Loss: 0.8626 | LM_LOSS: 0.3434 | LB_LOSS: 1.0384 |
| [2026-05-24 07:24:05] Validation | Batch 430/1463 | Loss: 0.8621 | LM_LOSS: 0.3429 | LB_LOSS: 1.0384 |
| [2026-05-24 07:24:07] Validation | Batch 440/1463 | Loss: 0.8623 | LM_LOSS: 0.3431 | LB_LOSS: 1.0385 |
| [2026-05-24 07:24:09] Validation | Batch 450/1463 | Loss: 0.8622 | LM_LOSS: 0.3429 | LB_LOSS: 1.0386 |
| [2026-05-24 07:24:11] Validation | Batch 460/1463 | Loss: 0.8622 | LM_LOSS: 0.3429 | LB_LOSS: 1.0386 |
| [2026-05-24 07:24:13] Validation | Batch 470/1463 | Loss: 0.8628 | LM_LOSS: 0.3436 | LB_LOSS: 1.0385 |
| [2026-05-24 07:24:15] Validation | Batch 480/1463 | Loss: 0.8627 | LM_LOSS: 0.3435 | LB_LOSS: 1.0384 |
| [2026-05-24 07:24:17] Validation | Batch 490/1463 | Loss: 0.8624 | LM_LOSS: 0.3432 | LB_LOSS: 1.0384 |
| [2026-05-24 07:24:19] Validation | Batch 500/1463 | Loss: 0.8623 | LM_LOSS: 0.3431 | LB_LOSS: 1.0384 |
| [2026-05-24 07:24:21] Validation | Batch 510/1463 | Loss: 0.8618 | LM_LOSS: 0.3426 | LB_LOSS: 1.0384 |
| [2026-05-24 07:24:23] Validation | Batch 520/1463 | Loss: 0.8614 | LM_LOSS: 0.3422 | LB_LOSS: 1.0384 |
| [2026-05-24 07:24:25] Validation | Batch 530/1463 | Loss: 0.8618 | LM_LOSS: 0.3426 | LB_LOSS: 1.0384 |
| [2026-05-24 07:24:26] Validation | Batch 540/1463 | Loss: 0.8621 | LM_LOSS: 0.3429 | LB_LOSS: 1.0385 |
| [2026-05-24 07:24:28] Validation | Batch 550/1463 | Loss: 0.8617 | LM_LOSS: 0.3424 | LB_LOSS: 1.0385 |
| [2026-05-24 07:24:30] Validation | Batch 560/1463 | Loss: 0.8620 | LM_LOSS: 0.3427 | LB_LOSS: 1.0386 |
| [2026-05-24 07:24:32] Validation | Batch 570/1463 | Loss: 0.8620 | LM_LOSS: 0.3427 | LB_LOSS: 1.0386 |
| [2026-05-24 07:24:34] Validation | Batch 580/1463 | Loss: 0.8617 | LM_LOSS: 0.3424 | LB_LOSS: 1.0386 |
| [2026-05-24 07:24:36] Validation | Batch 590/1463 | Loss: 0.8617 | LM_LOSS: 0.3423 | LB_LOSS: 1.0387 |
| [2026-05-24 07:24:38] Validation | Batch 600/1463 | Loss: 0.8621 | LM_LOSS: 0.3427 | LB_LOSS: 1.0387 |
| [2026-05-24 07:24:41] Validation | Batch 610/1463 | Loss: 0.8622 | LM_LOSS: 0.3428 | LB_LOSS: 1.0388 |
| [2026-05-24 07:24:42] Validation | Batch 620/1463 | Loss: 0.8616 | LM_LOSS: 0.3423 | LB_LOSS: 1.0387 |
| [2026-05-24 07:24:44] Validation | Batch 630/1463 | Loss: 0.8612 | LM_LOSS: 0.3418 | LB_LOSS: 1.0388 |
| [2026-05-24 07:24:46] Validation | Batch 640/1463 | Loss: 0.8611 | LM_LOSS: 0.3417 | LB_LOSS: 1.0388 |
| [2026-05-24 07:24:48] Validation | Batch 650/1463 | Loss: 0.8606 | LM_LOSS: 0.3412 | LB_LOSS: 1.0388 |
| [2026-05-24 07:24:50] Validation | Batch 660/1463 | Loss: 0.8601 | LM_LOSS: 0.3407 | LB_LOSS: 1.0388 |
| [2026-05-24 07:24:52] Validation | Batch 670/1463 | Loss: 0.8598 | LM_LOSS: 0.3404 | LB_LOSS: 1.0387 |
| [2026-05-24 07:24:53] Validation | Batch 680/1463 | Loss: 0.8597 | LM_LOSS: 0.3404 | LB_LOSS: 1.0387 |
| [2026-05-24 07:24:55] Validation | Batch 690/1463 | Loss: 0.8601 | LM_LOSS: 0.3408 | LB_LOSS: 1.0387 |
| [2026-05-24 07:24:57] Validation | Batch 700/1463 | Loss: 0.8600 | LM_LOSS: 0.3406 | LB_LOSS: 1.0387 |
| [2026-05-24 07:24:59] Validation | Batch 710/1463 | Loss: 0.8604 | LM_LOSS: 0.3410 | LB_LOSS: 1.0388 |
| [2026-05-24 07:25:01] Validation | Batch 720/1463 | Loss: 0.8611 | LM_LOSS: 0.3417 | LB_LOSS: 1.0388 |
| [2026-05-24 07:25:02] Validation | Batch 730/1463 | Loss: 0.8609 | LM_LOSS: 0.3415 | LB_LOSS: 1.0388 |
| [2026-05-24 07:25:04] Validation | Batch 740/1463 | Loss: 0.8606 | LM_LOSS: 0.3411 | LB_LOSS: 1.0389 |
| [2026-05-24 07:25:06] Validation | Batch 750/1463 | Loss: 0.8604 | LM_LOSS: 0.3410 | LB_LOSS: 1.0388 |
| [2026-05-24 07:25:07] Validation | Batch 760/1463 | Loss: 0.8601 | LM_LOSS: 0.3407 | LB_LOSS: 1.0388 |
| [2026-05-24 07:25:09] Validation | Batch 770/1463 | Loss: 0.8599 | LM_LOSS: 0.3405 | LB_LOSS: 1.0389 |
| [2026-05-24 07:25:11] Validation | Batch 780/1463 | Loss: 0.8597 | LM_LOSS: 0.3402 | LB_LOSS: 1.0388 |
| [2026-05-24 07:25:12] Validation | Batch 790/1463 | Loss: 0.8598 | LM_LOSS: 0.3404 | LB_LOSS: 1.0388 |
| [2026-05-24 07:25:14] Validation | Batch 800/1463 | Loss: 0.8598 | LM_LOSS: 0.3404 | LB_LOSS: 1.0388 |
| [2026-05-24 07:25:16] Validation | Batch 810/1463 | Loss: 0.8593 | LM_LOSS: 0.3400 | LB_LOSS: 1.0387 |
| [2026-05-24 07:25:18] Validation | Batch 820/1463 | Loss: 0.8595 | LM_LOSS: 0.3402 | LB_LOSS: 1.0387 |
| [2026-05-24 07:25:20] Validation | Batch 830/1463 | Loss: 0.8598 | LM_LOSS: 0.3404 | LB_LOSS: 1.0387 |
| [2026-05-24 07:25:22] Validation | Batch 840/1463 | Loss: 0.8597 | LM_LOSS: 0.3404 | LB_LOSS: 1.0388 |
| [2026-05-24 07:25:24] Validation | Batch 850/1463 | Loss: 0.8600 | LM_LOSS: 0.3406 | LB_LOSS: 1.0388 |
| [2026-05-24 07:25:26] Validation | Batch 860/1463 | Loss: 0.8600 | LM_LOSS: 0.3406 | LB_LOSS: 1.0388 |
| [2026-05-24 07:25:28] Validation | Batch 870/1463 | Loss: 0.8601 | LM_LOSS: 0.3407 | LB_LOSS: 1.0388 |
| [2026-05-24 07:25:30] Validation | Batch 880/1463 | Loss: 0.8594 | LM_LOSS: 0.3400 | LB_LOSS: 1.0388 |
| [2026-05-24 07:25:31] Validation | Batch 890/1463 | Loss: 0.8594 | LM_LOSS: 0.3401 | LB_LOSS: 1.0387 |
| [2026-05-24 07:25:33] Validation | Batch 900/1463 | Loss: 0.8591 | LM_LOSS: 0.3398 | LB_LOSS: 1.0387 |
| [2026-05-24 07:25:35] Validation | Batch 910/1463 | Loss: 0.8590 | LM_LOSS: 0.3397 | LB_LOSS: 1.0388 |
| [2026-05-24 07:25:38] Validation | Batch 920/1463 | Loss: 0.8592 | LM_LOSS: 0.3399 | LB_LOSS: 1.0387 |
| [2026-05-24 07:25:39] Validation | Batch 930/1463 | Loss: 0.8590 | LM_LOSS: 0.3396 | LB_LOSS: 1.0387 |
| [2026-05-24 07:25:41] Validation | Batch 940/1463 | Loss: 0.8587 | LM_LOSS: 0.3393 | LB_LOSS: 1.0387 |
| [2026-05-24 07:25:43] Validation | Batch 950/1463 | Loss: 0.8590 | LM_LOSS: 0.3397 | LB_LOSS: 1.0387 |
| [2026-05-24 07:25:45] Validation | Batch 960/1463 | Loss: 0.8591 | LM_LOSS: 0.3397 | LB_LOSS: 1.0386 |
| [2026-05-24 07:25:47] Validation | Batch 970/1463 | Loss: 0.8591 | LM_LOSS: 0.3398 | LB_LOSS: 1.0386 |
| [2026-05-24 07:25:50] Validation | Batch 980/1463 | Loss: 0.8594 | LM_LOSS: 0.3401 | LB_LOSS: 1.0386 |
| [2026-05-24 07:25:51] Validation | Batch 990/1463 | Loss: 0.8596 | LM_LOSS: 0.3403 | LB_LOSS: 1.0386 |
| [2026-05-24 07:25:53] Validation | Batch 1000/1463 | Loss: 0.8602 | LM_LOSS: 0.3409 | LB_LOSS: 1.0386 |
| [2026-05-24 07:25:55] Validation | Batch 1010/1463 | Loss: 0.8602 | LM_LOSS: 0.3409 | LB_LOSS: 1.0387 |
| [2026-05-24 07:25:57] Validation | Batch 1020/1463 | Loss: 0.8604 | LM_LOSS: 0.3410 | LB_LOSS: 1.0387 |
| [2026-05-24 07:25:59] Validation | Batch 1030/1463 | Loss: 0.8609 | LM_LOSS: 0.3415 | LB_LOSS: 1.0387 |
| [2026-05-24 07:26:01] Validation | Batch 1040/1463 | Loss: 0.8604 | LM_LOSS: 0.3411 | LB_LOSS: 1.0387 |
| [2026-05-24 07:26:03] Validation | Batch 1050/1463 | Loss: 0.8603 | LM_LOSS: 0.3410 | LB_LOSS: 1.0386 |
| [2026-05-24 07:26:05] Validation | Batch 1060/1463 | Loss: 0.8602 | LM_LOSS: 0.3409 | LB_LOSS: 1.0386 |
| [2026-05-24 07:26:07] Validation | Batch 1070/1463 | Loss: 0.8603 | LM_LOSS: 0.3410 | LB_LOSS: 1.0387 |
| [2026-05-24 07:26:09] Validation | Batch 1080/1463 | Loss: 0.8601 | LM_LOSS: 0.3407 | LB_LOSS: 1.0387 |
| [2026-05-24 07:26:11] Validation | Batch 1090/1463 | Loss: 0.8601 | LM_LOSS: 0.3408 | LB_LOSS: 1.0387 |
| [2026-05-24 07:26:12] Validation | Batch 1100/1463 | Loss: 0.8600 | LM_LOSS: 0.3407 | LB_LOSS: 1.0386 |
| [2026-05-24 07:26:14] Validation | Batch 1110/1463 | Loss: 0.8600 | LM_LOSS: 0.3407 | LB_LOSS: 1.0386 |
| [2026-05-24 07:26:16] Validation | Batch 1120/1463 | Loss: 0.8598 | LM_LOSS: 0.3405 | LB_LOSS: 1.0387 |
| [2026-05-24 07:26:18] Validation | Batch 1130/1463 | Loss: 0.8596 | LM_LOSS: 0.3403 | LB_LOSS: 1.0386 |
| [2026-05-24 07:26:20] Validation | Batch 1140/1463 | Loss: 0.8598 | LM_LOSS: 0.3405 | LB_LOSS: 1.0386 |
| [2026-05-24 07:26:22] Validation | Batch 1150/1463 | Loss: 0.8598 | LM_LOSS: 0.3405 | LB_LOSS: 1.0386 |
| [2026-05-24 07:26:24] Validation | Batch 1160/1463 | Loss: 0.8597 | LM_LOSS: 0.3404 | LB_LOSS: 1.0386 |
| [2026-05-24 07:26:26] Validation | Batch 1170/1463 | Loss: 0.8597 | LM_LOSS: 0.3404 | LB_LOSS: 1.0386 |
| [2026-05-24 07:26:28] Validation | Batch 1180/1463 | Loss: 0.8598 | LM_LOSS: 0.3405 | LB_LOSS: 1.0386 |
| [2026-05-24 07:26:30] Validation | Batch 1190/1463 | Loss: 0.8599 | LM_LOSS: 0.3406 | LB_LOSS: 1.0386 |
| [2026-05-24 07:26:32] Validation | Batch 1200/1463 | Loss: 0.8600 | LM_LOSS: 0.3407 | LB_LOSS: 1.0386 |
| [2026-05-24 07:26:34] Validation | Batch 1210/1463 | Loss: 0.8602 | LM_LOSS: 0.3409 | LB_LOSS: 1.0387 |
| [2026-05-24 07:26:36] Validation | Batch 1220/1463 | Loss: 0.8606 | LM_LOSS: 0.3413 | LB_LOSS: 1.0387 |
| [2026-05-24 07:26:38] Validation | Batch 1230/1463 | Loss: 0.8606 | LM_LOSS: 0.3412 | LB_LOSS: 1.0387 |
| [2026-05-24 07:26:40] Validation | Batch 1240/1463 | Loss: 0.8609 | LM_LOSS: 0.3415 | LB_LOSS: 1.0387 |
| [2026-05-24 07:26:42] Validation | Batch 1250/1463 | Loss: 0.8610 | LM_LOSS: 0.3417 | LB_LOSS: 1.0387 |
| [2026-05-24 07:26:44] Validation | Batch 1260/1463 | Loss: 0.8609 | LM_LOSS: 0.3416 | LB_LOSS: 1.0387 |
| [2026-05-24 07:26:46] Validation | Batch 1270/1463 | Loss: 0.8608 | LM_LOSS: 0.3414 | LB_LOSS: 1.0387 |
| [2026-05-24 07:26:48] Validation | Batch 1280/1463 | Loss: 0.8605 | LM_LOSS: 0.3412 | LB_LOSS: 1.0387 |
| [2026-05-24 07:26:50] Validation | Batch 1290/1463 | Loss: 0.8605 | LM_LOSS: 0.3412 | LB_LOSS: 1.0386 |
| [2026-05-24 07:26:52] Validation | Batch 1300/1463 | Loss: 0.8603 | LM_LOSS: 0.3410 | LB_LOSS: 1.0386 |
| [2026-05-24 07:26:54] Validation | Batch 1310/1463 | Loss: 0.8603 | LM_LOSS: 0.3409 | LB_LOSS: 1.0386 |
| [2026-05-24 07:26:55] Validation | Batch 1320/1463 | Loss: 0.8603 | LM_LOSS: 0.3410 | LB_LOSS: 1.0386 |
| [2026-05-24 07:26:57] Validation | Batch 1330/1463 | Loss: 0.8604 | LM_LOSS: 0.3411 | LB_LOSS: 1.0386 |
| [2026-05-24 07:26:58] Validation | Batch 1340/1463 | Loss: 0.8607 | LM_LOSS: 0.3413 | LB_LOSS: 1.0386 |
| [2026-05-24 07:27:00] Validation | Batch 1350/1463 | Loss: 0.8607 | LM_LOSS: 0.3414 | LB_LOSS: 1.0386 |
| [2026-05-24 07:27:03] Validation | Batch 1360/1463 | Loss: 0.8610 | LM_LOSS: 0.3417 | LB_LOSS: 1.0386 |
| [2026-05-24 07:27:05] Validation | Batch 1370/1463 | Loss: 0.8613 | LM_LOSS: 0.3420 | LB_LOSS: 1.0386 |
| [2026-05-24 07:27:07] Validation | Batch 1380/1463 | Loss: 0.8611 | LM_LOSS: 0.3418 | LB_LOSS: 1.0386 |
| [2026-05-24 07:27:08] Validation | Batch 1390/1463 | Loss: 0.8610 | LM_LOSS: 0.3417 | LB_LOSS: 1.0386 |
| [2026-05-24 07:27:10] Validation | Batch 1400/1463 | Loss: 0.8613 | LM_LOSS: 0.3420 | LB_LOSS: 1.0386 |
| [2026-05-24 07:27:12] Validation | Batch 1410/1463 | Loss: 0.8615 | LM_LOSS: 0.3422 | LB_LOSS: 1.0386 |
| [2026-05-24 07:27:14] Validation | Batch 1420/1463 | Loss: 0.8615 | LM_LOSS: 0.3422 | LB_LOSS: 1.0386 |
| [2026-05-24 07:27:16] Validation | Batch 1430/1463 | Loss: 0.8615 | LM_LOSS: 0.3423 | LB_LOSS: 1.0386 |
| [2026-05-24 07:27:18] Validation | Batch 1440/1463 | Loss: 0.8620 | LM_LOSS: 0.3427 | LB_LOSS: 1.0386 |
| [2026-05-24 07:27:20] Validation | Batch 1450/1463 | Loss: 0.8617 | LM_LOSS: 0.3424 | LB_LOSS: 1.0386 |
| [2026-05-24 07:27:22] Validation | Batch 1460/1463 | Loss: 0.8620 | LM_LOSS: 0.3427 | LB_LOSS: 1.0386 |
| [2026-05-24 07:27:23] Validation | Batch 1463/1463 | Loss: 0.8619 | LM_LOSS: 0.3426 | LB_LOSS: 1.0385 |
| [2026-05-24 07:27:23] Validation | Loss: 0.8619 | LM_LOSS: 0.3426 | LB_LOSS: 1.0385 | PPL: 1.41 | Time: 280.04s |
| [2026-05-24 07:27:34] Epoch 1 | Step 4010 | Loss: 0.8966 | LM: 0.3442 | LB: 1.1088 | CL0: 3.2 | CL1: 4.5 | HR0: 0.318/SR0: 0.298 | HR1: 0.238/SR1: 0.210 | LR: 1.00e-04 |
| [2026-05-24 07:27:45] Epoch 1 | Step 4020 | Loss: 0.8965 | LM: 0.3443 | LB: 1.1087 | CL0: 3.2 | CL1: 4.5 | HR0: 0.318/SR0: 0.298 | HR1: 0.238/SR1: 0.210 | LR: 1.00e-04 |
| [2026-05-24 07:27:57] Epoch 1 | Step 4030 | Loss: 0.8965 | LM: 0.3442 | LB: 1.1085 | CL0: 3.2 | CL1: 4.5 | HR0: 0.318/SR0: 0.298 | HR1: 0.238/SR1: 0.209 | LR: 1.00e-04 |
| [2026-05-24 07:28:08] Epoch 1 | Step 4040 | Loss: 0.8965 | LM: 0.3441 | LB: 1.1083 | CL0: 3.2 | CL1: 4.5 | HR0: 0.318/SR0: 0.298 | HR1: 0.238/SR1: 0.209 | LR: 1.00e-04 |
| [2026-05-24 07:28:19] Epoch 1 | Step 4050 | Loss: 0.8964 | LM: 0.3440 | LB: 1.1081 | CL0: 3.2 | CL1: 4.5 | HR0: 0.318/SR0: 0.298 | HR1: 0.237/SR1: 0.209 | LR: 1.00e-04 |
| [2026-05-24 07:28:30] Epoch 1 | Step 4060 | Loss: 0.8963 | LM: 0.3441 | LB: 1.1080 | CL0: 3.2 | CL1: 4.5 | HR0: 0.317/SR0: 0.297 | HR1: 0.237/SR1: 0.209 | LR: 1.00e-04 |
| [2026-05-24 07:28:41] Epoch 1 | Step 4070 | Loss: 0.8963 | LM: 0.3441 | LB: 1.1078 | CL0: 3.2 | CL1: 4.5 | HR0: 0.317/SR0: 0.297 | HR1: 0.237/SR1: 0.209 | LR: 1.00e-04 |
| [2026-05-24 07:28:52] Epoch 1 | Step 4080 | Loss: 0.8962 | LM: 0.3442 | LB: 1.1076 | CL0: 3.2 | CL1: 4.5 | HR0: 0.317/SR0: 0.297 | HR1: 0.237/SR1: 0.209 | LR: 1.00e-04 |
| [2026-05-24 07:29:03] Epoch 1 | Step 4090 | Loss: 0.8961 | LM: 0.3442 | LB: 1.1075 | CL0: 3.2 | CL1: 4.5 | HR0: 0.317/SR0: 0.297 | HR1: 0.237/SR1: 0.209 | LR: 1.00e-04 |
| [2026-05-24 07:29:14] Epoch 1 | Step 4100 | Loss: 0.8961 | LM: 0.3442 | LB: 1.1073 | CL0: 3.2 | CL1: 4.5 | HR0: 0.317/SR0: 0.297 | HR1: 0.237/SR1: 0.209 | LR: 1.00e-04 |
| [2026-05-24 07:29:25] Epoch 1 | Step 4110 | Loss: 0.8960 | LM: 0.3444 | LB: 1.1071 | CL0: 3.2 | CL1: 4.5 | HR0: 0.317/SR0: 0.297 | HR1: 0.237/SR1: 0.209 | LR: 1.00e-04 |
| [2026-05-24 07:29:37] Epoch 1 | Step 4120 | Loss: 0.8960 | LM: 0.3444 | LB: 1.1070 | CL0: 3.2 | CL1: 4.5 | HR0: 0.317/SR0: 0.297 | HR1: 0.237/SR1: 0.209 | LR: 1.00e-04 |
| [2026-05-24 07:29:48] Epoch 1 | Step 4130 | Loss: 0.8958 | LM: 0.3444 | LB: 1.1068 | CL0: 3.2 | CL1: 4.5 | HR0: 0.317/SR0: 0.297 | HR1: 0.237/SR1: 0.208 | LR: 1.00e-04 |
| [2026-05-24 07:29:59] Epoch 1 | Step 4140 | Loss: 0.8957 | LM: 0.3442 | LB: 1.1066 | CL0: 3.2 | CL1: 4.5 | HR0: 0.317/SR0: 0.297 | HR1: 0.237/SR1: 0.208 | LR: 1.00e-04 |
| [2026-05-24 07:30:10] Epoch 1 | Step 4150 | Loss: 0.8956 | LM: 0.3443 | LB: 1.1065 | CL0: 3.2 | CL1: 4.5 | HR0: 0.317/SR0: 0.297 | HR1: 0.236/SR1: 0.208 | LR: 1.00e-04 |
| [2026-05-24 07:30:21] Epoch 1 | Step 4160 | Loss: 0.8955 | LM: 0.3444 | LB: 1.1063 | CL0: 3.2 | CL1: 4.6 | HR0: 0.317/SR0: 0.296 | HR1: 0.236/SR1: 0.208 | LR: 1.00e-04 |
| [2026-05-24 07:30:33] Epoch 1 | Step 4170 | Loss: 0.8955 | LM: 0.3443 | LB: 1.1061 | CL0: 3.2 | CL1: 4.6 | HR0: 0.317/SR0: 0.296 | HR1: 0.236/SR1: 0.208 | LR: 1.00e-04 |
| [2026-05-24 07:30:43] Epoch 1 | Step 4180 | Loss: 0.8954 | LM: 0.3444 | LB: 1.1060 | CL0: 3.2 | CL1: 4.6 | HR0: 0.317/SR0: 0.296 | HR1: 0.236/SR1: 0.208 | LR: 1.00e-04 |
| [2026-05-24 07:30:55] Epoch 1 | Step 4190 | Loss: 0.8953 | LM: 0.3443 | LB: 1.1058 | CL0: 3.2 | CL1: 4.6 | HR0: 0.316/SR0: 0.296 | HR1: 0.236/SR1: 0.208 | LR: 1.00e-04 |
| [2026-05-24 07:31:06] Epoch 1 | Step 4200 | Loss: 0.8952 | LM: 0.3444 | LB: 1.1057 | CL0: 3.2 | CL1: 4.6 | HR0: 0.316/SR0: 0.296 | HR1: 0.236/SR1: 0.208 | LR: 1.00e-04 |
| [2026-05-24 07:31:18] Epoch 1 | Step 4210 | Loss: 0.8951 | LM: 0.3445 | LB: 1.1055 | CL0: 3.2 | CL1: 4.6 | HR0: 0.316/SR0: 0.296 | HR1: 0.236/SR1: 0.208 | LR: 1.00e-04 |
| [2026-05-24 07:31:29] Epoch 1 | Step 4220 | Loss: 0.8950 | LM: 0.3443 | LB: 1.1053 | CL0: 3.2 | CL1: 4.6 | HR0: 0.316/SR0: 0.296 | HR1: 0.236/SR1: 0.208 | LR: 1.00e-04 |
| [2026-05-24 07:31:40] Epoch 1 | Step 4230 | Loss: 0.8950 | LM: 0.3442 | LB: 1.1052 | CL0: 3.2 | CL1: 4.6 | HR0: 0.316/SR0: 0.296 | HR1: 0.236/SR1: 0.207 | LR: 1.00e-04 |
| [2026-05-24 07:31:51] Epoch 1 | Step 4240 | Loss: 0.8949 | LM: 0.3442 | LB: 1.1051 | CL0: 3.2 | CL1: 4.6 | HR0: 0.316/SR0: 0.296 | HR1: 0.236/SR1: 0.207 | LR: 1.00e-04 |
| [2026-05-24 07:32:02] Epoch 1 | Step 4250 | Loss: 0.8948 | LM: 0.3441 | LB: 1.1049 | CL0: 3.2 | CL1: 4.6 | HR0: 0.316/SR0: 0.295 | HR1: 0.236/SR1: 0.207 | LR: 1.00e-04 |
| [2026-05-24 07:32:13] Epoch 1 | Step 4260 | Loss: 0.8947 | LM: 0.3439 | LB: 1.1047 | CL0: 3.2 | CL1: 4.6 | HR0: 0.316/SR0: 0.295 | HR1: 0.235/SR1: 0.207 | LR: 1.00e-04 |
| [2026-05-24 07:32:24] Epoch 1 | Step 4270 | Loss: 0.8946 | LM: 0.3437 | LB: 1.1046 | CL0: 3.2 | CL1: 4.6 | HR0: 0.316/SR0: 0.295 | HR1: 0.235/SR1: 0.207 | LR: 1.00e-04 |
| [2026-05-24 07:32:35] Epoch 1 | Step 4280 | Loss: 0.8945 | LM: 0.3436 | LB: 1.1044 | CL0: 3.2 | CL1: 4.6 | HR0: 0.316/SR0: 0.295 | HR1: 0.235/SR1: 0.207 | LR: 1.00e-04 |
| [2026-05-24 07:32:47] Epoch 1 | Step 4290 | Loss: 0.8945 | LM: 0.3437 | LB: 1.1043 | CL0: 3.2 | CL1: 4.6 | HR0: 0.316/SR0: 0.295 | HR1: 0.235/SR1: 0.207 | LR: 1.00e-04 |
| [2026-05-24 07:32:58] Epoch 1 | Step 4300 | Loss: 0.8945 | LM: 0.3438 | LB: 1.1041 | CL0: 3.2 | CL1: 4.6 | HR0: 0.316/SR0: 0.295 | HR1: 0.235/SR1: 0.207 | LR: 1.00e-04 |
| [2026-05-24 07:33:09] Epoch 1 | Step 4310 | Loss: 0.8944 | LM: 0.3439 | LB: 1.1040 | CL0: 3.2 | CL1: 4.6 | HR0: 0.316/SR0: 0.295 | HR1: 0.235/SR1: 0.207 | LR: 1.00e-04 |
| [2026-05-24 07:33:21] Epoch 1 | Step 4320 | Loss: 0.8944 | LM: 0.3439 | LB: 1.1038 | CL0: 3.2 | CL1: 4.6 | HR0: 0.316/SR0: 0.295 | HR1: 0.235/SR1: 0.207 | LR: 1.00e-04 |
| [2026-05-24 07:33:32] Epoch 1 | Step 4330 | Loss: 0.8943 | LM: 0.3439 | LB: 1.1037 | CL0: 3.2 | CL1: 4.6 | HR0: 0.315/SR0: 0.295 | HR1: 0.235/SR1: 0.207 | LR: 1.00e-04 |
| [2026-05-24 07:33:43] Epoch 1 | Step 4340 | Loss: 0.8942 | LM: 0.3441 | LB: 1.1035 | CL0: 3.2 | CL1: 4.6 | HR0: 0.315/SR0: 0.295 | HR1: 0.235/SR1: 0.207 | LR: 1.00e-04 |
| [2026-05-24 07:33:55] Epoch 1 | Step 4350 | Loss: 0.8942 | LM: 0.3441 | LB: 1.1034 | CL0: 3.2 | CL1: 4.6 | HR0: 0.315/SR0: 0.294 | HR1: 0.235/SR1: 0.207 | LR: 1.00e-04 |
| [2026-05-24 07:34:06] Epoch 1 | Step 4360 | Loss: 0.8941 | LM: 0.3440 | LB: 1.1032 | CL0: 3.2 | CL1: 4.6 | HR0: 0.315/SR0: 0.294 | HR1: 0.235/SR1: 0.206 | LR: 1.00e-04 |
| [2026-05-24 07:34:17] Epoch 1 | Step 4370 | Loss: 0.8940 | LM: 0.3440 | LB: 1.1031 | CL0: 3.2 | CL1: 4.6 | HR0: 0.315/SR0: 0.294 | HR1: 0.235/SR1: 0.206 | LR: 1.00e-04 |
| [2026-05-24 07:34:28] Epoch 1 | Step 4380 | Loss: 0.8939 | LM: 0.3439 | LB: 1.1029 | CL0: 3.2 | CL1: 4.6 | HR0: 0.315/SR0: 0.294 | HR1: 0.234/SR1: 0.206 | LR: 1.00e-04 |
| [2026-05-24 07:34:39] Epoch 1 | Step 4390 | Loss: 0.8938 | LM: 0.3437 | LB: 1.1028 | CL0: 3.2 | CL1: 4.6 | HR0: 0.315/SR0: 0.294 | HR1: 0.234/SR1: 0.206 | LR: 1.00e-04 |
| [2026-05-24 07:34:50] Epoch 1 | Step 4400 | Loss: 0.8938 | LM: 0.3438 | LB: 1.1026 | CL0: 3.2 | CL1: 4.6 | HR0: 0.315/SR0: 0.294 | HR1: 0.234/SR1: 0.206 | LR: 1.00e-04 |
| [2026-05-24 07:35:02] Epoch 1 | Step 4410 | Loss: 0.8936 | LM: 0.3435 | LB: 1.1025 | CL0: 3.2 | CL1: 4.6 | HR0: 0.315/SR0: 0.294 | HR1: 0.234/SR1: 0.206 | LR: 1.00e-04 |
| [2026-05-24 07:35:13] Epoch 1 | Step 4420 | Loss: 0.8935 | LM: 0.3435 | LB: 1.1023 | CL0: 3.2 | CL1: 4.6 | HR0: 0.315/SR0: 0.294 | HR1: 0.234/SR1: 0.206 | LR: 1.00e-04 |
| [2026-05-24 07:35:24] Epoch 1 | Step 4430 | Loss: 0.8934 | LM: 0.3434 | LB: 1.1022 | CL0: 3.2 | CL1: 4.6 | HR0: 0.315/SR0: 0.294 | HR1: 0.234/SR1: 0.206 | LR: 1.00e-04 |
| [2026-05-24 07:35:35] Epoch 1 | Step 4440 | Loss: 0.8934 | LM: 0.3433 | LB: 1.1020 | CL0: 3.2 | CL1: 4.6 | HR0: 0.315/SR0: 0.294 | HR1: 0.234/SR1: 0.206 | LR: 1.00e-04 |
| [2026-05-24 07:35:46] Epoch 1 | Step 4450 | Loss: 0.8933 | LM: 0.3433 | LB: 1.1019 | CL0: 3.2 | CL1: 4.6 | HR0: 0.315/SR0: 0.293 | HR1: 0.234/SR1: 0.206 | LR: 1.00e-04 |
| [2026-05-24 07:35:57] Epoch 1 | Step 4460 | Loss: 0.8931 | LM: 0.3432 | LB: 1.1017 | CL0: 3.2 | CL1: 4.6 | HR0: 0.314/SR0: 0.293 | HR1: 0.234/SR1: 0.206 | LR: 1.00e-04 |
| [2026-05-24 07:36:08] Epoch 1 | Step 4470 | Loss: 0.8931 | LM: 0.3433 | LB: 1.1016 | CL0: 3.2 | CL1: 4.6 | HR0: 0.314/SR0: 0.293 | HR1: 0.234/SR1: 0.205 | LR: 1.00e-04 |
| [2026-05-24 07:36:20] Epoch 1 | Step 4480 | Loss: 0.8930 | LM: 0.3434 | LB: 1.1014 | CL0: 3.2 | CL1: 4.6 | HR0: 0.314/SR0: 0.293 | HR1: 0.234/SR1: 0.205 | LR: 1.00e-04 |
| [2026-05-24 07:36:31] Epoch 1 | Step 4490 | Loss: 0.8930 | LM: 0.3434 | LB: 1.1013 | CL0: 3.2 | CL1: 4.6 | HR0: 0.314/SR0: 0.293 | HR1: 0.233/SR1: 0.205 | LR: 1.00e-04 |
| [2026-05-24 07:36:42] Epoch 1 | Step 4500 | Loss: 0.8929 | LM: 0.3432 | LB: 1.1011 | CL0: 3.2 | CL1: 4.6 | HR0: 0.314/SR0: 0.293 | HR1: 0.233/SR1: 0.205 | LR: 1.00e-04 |
| [2026-05-24 07:36:53] Epoch 1 | Step 4510 | Loss: 0.8928 | LM: 0.3432 | LB: 1.1010 | CL0: 3.2 | CL1: 4.6 | HR0: 0.314/SR0: 0.293 | HR1: 0.233/SR1: 0.205 | LR: 1.00e-04 |
| [2026-05-24 07:37:04] Epoch 1 | Step 4520 | Loss: 0.8928 | LM: 0.3432 | LB: 1.1008 | CL0: 3.2 | CL1: 4.6 | HR0: 0.314/SR0: 0.293 | HR1: 0.233/SR1: 0.205 | LR: 1.00e-04 |
| [2026-05-24 07:37:15] Epoch 1 | Step 4530 | Loss: 0.8927 | LM: 0.3432 | LB: 1.1007 | CL0: 3.2 | CL1: 4.6 | HR0: 0.314/SR0: 0.293 | HR1: 0.233/SR1: 0.205 | LR: 1.00e-04 |
| [2026-05-24 07:37:26] Epoch 1 | Step 4540 | Loss: 0.8926 | LM: 0.3432 | LB: 1.1005 | CL0: 3.2 | CL1: 4.6 | HR0: 0.314/SR0: 0.292 | HR1: 0.233/SR1: 0.205 | LR: 1.00e-04 |
| [2026-05-24 07:37:37] Epoch 1 | Step 4550 | Loss: 0.8925 | LM: 0.3432 | LB: 1.1004 | CL0: 3.2 | CL1: 4.6 | HR0: 0.314/SR0: 0.292 | HR1: 0.233/SR1: 0.205 | LR: 1.00e-04 |
| [2026-05-24 07:37:49] Epoch 1 | Step 4560 | Loss: 0.8924 | LM: 0.3430 | LB: 1.1002 | CL0: 3.2 | CL1: 4.6 | HR0: 0.314/SR0: 0.292 | HR1: 0.233/SR1: 0.205 | LR: 1.00e-04 |
| [2026-05-24 07:38:00] Epoch 1 | Step 4570 | Loss: 0.8923 | LM: 0.3432 | LB: 1.1001 | CL0: 3.2 | CL1: 4.6 | HR0: 0.314/SR0: 0.292 | HR1: 0.233/SR1: 0.205 | LR: 1.00e-04 |
| [2026-05-24 07:38:11] Epoch 1 | Step 4580 | Loss: 0.8923 | LM: 0.3432 | LB: 1.0999 | CL0: 3.2 | CL1: 4.6 | HR0: 0.314/SR0: 0.292 | HR1: 0.233/SR1: 0.204 | LR: 1.00e-04 |
| [2026-05-24 07:38:22] Epoch 1 | Step 4590 | Loss: 0.8922 | LM: 0.3432 | LB: 1.0998 | CL0: 3.2 | CL1: 4.6 | HR0: 0.313/SR0: 0.292 | HR1: 0.233/SR1: 0.204 | LR: 1.00e-04 |
| [2026-05-24 07:38:33] Epoch 1 | Step 4600 | Loss: 0.8922 | LM: 0.3431 | LB: 1.0996 | CL0: 3.2 | CL1: 4.6 | HR0: 0.313/SR0: 0.292 | HR1: 0.232/SR1: 0.204 | LR: 1.00e-04 |
| [2026-05-24 07:38:44] Epoch 1 | Step 4610 | Loss: 0.8921 | LM: 0.3431 | LB: 1.0995 | CL0: 3.2 | CL1: 4.6 | HR0: 0.313/SR0: 0.292 | HR1: 0.232/SR1: 0.204 | LR: 1.00e-04 |
| [2026-05-24 07:38:55] Epoch 1 | Step 4620 | Loss: 0.8921 | LM: 0.3432 | LB: 1.0994 | CL0: 3.2 | CL1: 4.6 | HR0: 0.313/SR0: 0.292 | HR1: 0.232/SR1: 0.204 | LR: 1.00e-04 |
| [2026-05-24 07:39:06] Epoch 1 | Step 4630 | Loss: 0.8919 | LM: 0.3431 | LB: 1.0992 | CL0: 3.2 | CL1: 4.6 | HR0: 0.313/SR0: 0.292 | HR1: 0.232/SR1: 0.204 | LR: 1.00e-04 |
| [2026-05-24 07:39:17] Epoch 1 | Step 4640 | Loss: 0.8919 | LM: 0.3431 | LB: 1.0991 | CL0: 3.2 | CL1: 4.6 | HR0: 0.313/SR0: 0.291 | HR1: 0.232/SR1: 0.204 | LR: 1.00e-04 |
| [2026-05-24 07:39:29] Epoch 1 | Step 4650 | Loss: 0.8918 | LM: 0.3431 | LB: 1.0990 | CL0: 3.2 | CL1: 4.6 | HR0: 0.313/SR0: 0.291 | HR1: 0.232/SR1: 0.204 | LR: 1.00e-04 |
| [2026-05-24 07:39:40] Epoch 1 | Step 4660 | Loss: 0.8917 | LM: 0.3430 | LB: 1.0988 | CL0: 3.2 | CL1: 4.6 | HR0: 0.313/SR0: 0.291 | HR1: 0.232/SR1: 0.204 | LR: 1.00e-04 |
| [2026-05-24 07:39:51] Epoch 1 | Step 4670 | Loss: 0.8916 | LM: 0.3429 | LB: 1.0987 | CL0: 3.2 | CL1: 4.6 | HR0: 0.313/SR0: 0.291 | HR1: 0.232/SR1: 0.204 | LR: 1.00e-04 |
| [2026-05-24 07:40:02] Epoch 1 | Step 4680 | Loss: 0.8915 | LM: 0.3429 | LB: 1.0985 | CL0: 3.2 | CL1: 4.6 | HR0: 0.313/SR0: 0.291 | HR1: 0.232/SR1: 0.204 | LR: 1.00e-04 |
| [2026-05-24 07:40:10] Epoch 1 completed in 6414.01s | Loss: 0.8915 | CL0: 3.2 | CL1: 4.6 |
| [2026-05-24 07:40:10] |
| ============================================================ |
| [2026-05-24 07:40:10] EPOCH 2/3 (step 4687) |
| [2026-05-24 07:40:10] ============================================================ |
| [2026-05-24 07:40:14] Epoch 2 | Step 4690 | Loss: 0.8212 | LM: 0.2697 | LB: 1.0307 | CL0: 3.6 | CL1: 5.1 | HR0: 0.277/SR0: 0.244 | HR1: 0.195/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:40:24] Epoch 2 | Step 4700 | Loss: 0.8282 | LM: 0.3348 | LB: 1.0353 | CL0: 3.5 | CL1: 5.6 | HR0: 0.283/SR0: 0.248 | HR1: 0.179/SR1: 0.154 | LR: 1.00e-04 |
| [2026-05-24 07:40:35] Epoch 2 | Step 4710 | Loss: 0.8324 | LM: 0.3403 | LB: 1.0396 | CL0: 3.5 | CL1: 5.6 | HR0: 0.289/SR0: 0.253 | HR1: 0.180/SR1: 0.154 | LR: 1.00e-04 |
| [2026-05-24 07:40:45] Epoch 2 | Step 4720 | Loss: 0.8267 | LM: 0.3304 | LB: 1.0400 | CL0: 3.5 | CL1: 5.4 | HR0: 0.289/SR0: 0.253 | HR1: 0.187/SR1: 0.160 | LR: 1.00e-04 |
| [2026-05-24 07:40:57] Epoch 2 | Step 4730 | Loss: 0.8250 | LM: 0.3260 | LB: 1.0378 | CL0: 3.5 | CL1: 5.4 | HR0: 0.285/SR0: 0.250 | HR1: 0.188/SR1: 0.161 | LR: 1.00e-04 |
| [2026-05-24 07:41:07] Epoch 2 | Step 4740 | Loss: 0.8202 | LM: 0.3158 | LB: 1.0379 | CL0: 3.5 | CL1: 5.5 | HR0: 0.286/SR0: 0.250 | HR1: 0.184/SR1: 0.158 | LR: 1.00e-04 |
| [2026-05-24 07:41:18] Epoch 2 | Step 4750 | Loss: 0.8169 | LM: 0.3166 | LB: 1.0386 | CL0: 3.5 | CL1: 5.4 | HR0: 0.287/SR0: 0.251 | HR1: 0.187/SR1: 0.160 | LR: 1.00e-04 |
| [2026-05-24 07:41:29] Epoch 2 | Step 4760 | Loss: 0.8167 | LM: 0.3174 | LB: 1.0383 | CL0: 3.5 | CL1: 5.3 | HR0: 0.286/SR0: 0.250 | HR1: 0.191/SR1: 0.163 | LR: 1.00e-04 |
| [2026-05-24 07:41:40] Epoch 2 | Step 4770 | Loss: 0.8152 | LM: 0.3197 | LB: 1.0381 | CL0: 3.5 | CL1: 5.3 | HR0: 0.285/SR0: 0.250 | HR1: 0.191/SR1: 0.164 | LR: 1.00e-04 |
| [2026-05-24 07:41:51] Epoch 2 | Step 4780 | Loss: 0.8138 | LM: 0.3210 | LB: 1.0387 | CL0: 3.5 | CL1: 5.3 | HR0: 0.286/SR0: 0.250 | HR1: 0.192/SR1: 0.164 | LR: 1.00e-04 |
| [2026-05-24 07:42:01] Epoch 2 | Step 4790 | Loss: 0.8151 | LM: 0.3190 | LB: 1.0382 | CL0: 3.5 | CL1: 5.3 | HR0: 0.285/SR0: 0.250 | HR1: 0.193/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:42:12] Epoch 2 | Step 4800 | Loss: 0.8149 | LM: 0.3199 | LB: 1.0375 | CL0: 3.5 | CL1: 5.2 | HR0: 0.284/SR0: 0.249 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 07:42:23] Epoch 2 | Step 4810 | Loss: 0.8173 | LM: 0.3196 | LB: 1.0380 | CL0: 3.5 | CL1: 5.2 | HR0: 0.285/SR0: 0.249 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 07:42:34] Epoch 2 | Step 4820 | Loss: 0.8164 | LM: 0.3172 | LB: 1.0380 | CL0: 3.5 | CL1: 5.3 | HR0: 0.285/SR0: 0.249 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:42:44] Epoch 2 | Step 4830 | Loss: 0.8174 | LM: 0.3139 | LB: 1.0373 | CL0: 3.5 | CL1: 5.3 | HR0: 0.284/SR0: 0.249 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:42:55] Epoch 2 | Step 4840 | Loss: 0.8176 | LM: 0.3148 | LB: 1.0379 | CL0: 3.5 | CL1: 5.3 | HR0: 0.285/SR0: 0.249 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 07:43:06] Epoch 2 | Step 4850 | Loss: 0.8164 | LM: 0.3134 | LB: 1.0379 | CL0: 3.5 | CL1: 5.2 | HR0: 0.285/SR0: 0.249 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 07:43:17] Epoch 2 | Step 4860 | Loss: 0.8177 | LM: 0.3131 | LB: 1.0375 | CL0: 3.5 | CL1: 5.3 | HR0: 0.285/SR0: 0.249 | HR1: 0.193/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:43:27] Epoch 2 | Step 4870 | Loss: 0.8191 | LM: 0.3129 | LB: 1.0374 | CL0: 3.5 | CL1: 5.3 | HR0: 0.285/SR0: 0.249 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:43:38] Epoch 2 | Step 4880 | Loss: 0.8207 | LM: 0.3139 | LB: 1.0371 | CL0: 3.5 | CL1: 5.3 | HR0: 0.284/SR0: 0.249 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:43:49] Epoch 2 | Step 4890 | Loss: 0.8201 | LM: 0.3133 | LB: 1.0369 | CL0: 3.5 | CL1: 5.3 | HR0: 0.284/SR0: 0.249 | HR1: 0.191/SR1: 0.164 | LR: 1.00e-04 |
| [2026-05-24 07:44:00] Epoch 2 | Step 4900 | Loss: 0.8207 | LM: 0.3143 | LB: 1.0365 | CL0: 3.5 | CL1: 5.3 | HR0: 0.284/SR0: 0.248 | HR1: 0.191/SR1: 0.164 | LR: 1.00e-04 |
| [2026-05-24 07:44:11] Epoch 2 | Step 4910 | Loss: 0.8211 | LM: 0.3142 | LB: 1.0364 | CL0: 3.5 | CL1: 5.3 | HR0: 0.283/SR0: 0.248 | HR1: 0.191/SR1: 0.164 | LR: 1.00e-04 |
| [2026-05-24 07:44:21] Epoch 2 | Step 4920 | Loss: 0.8208 | LM: 0.3140 | LB: 1.0362 | CL0: 3.5 | CL1: 5.3 | HR0: 0.283/SR0: 0.248 | HR1: 0.191/SR1: 0.164 | LR: 1.00e-04 |
| [2026-05-24 07:44:32] Epoch 2 | Step 4930 | Loss: 0.8203 | LM: 0.3127 | LB: 1.0362 | CL0: 3.5 | CL1: 5.3 | HR0: 0.283/SR0: 0.248 | HR1: 0.191/SR1: 0.164 | LR: 1.00e-04 |
| [2026-05-24 07:44:43] Epoch 2 | Step 4940 | Loss: 0.8210 | LM: 0.3125 | LB: 1.0360 | CL0: 3.6 | CL1: 5.3 | HR0: 0.283/SR0: 0.248 | HR1: 0.191/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:44:54] Epoch 2 | Step 4950 | Loss: 0.8199 | LM: 0.3122 | LB: 1.0359 | CL0: 3.6 | CL1: 5.3 | HR0: 0.283/SR0: 0.247 | HR1: 0.191/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:45:04] Epoch 2 | Step 4960 | Loss: 0.8209 | LM: 0.3147 | LB: 1.0356 | CL0: 3.6 | CL1: 5.3 | HR0: 0.283/SR0: 0.247 | HR1: 0.191/SR1: 0.164 | LR: 1.00e-04 |
| [2026-05-24 07:45:15] Epoch 2 | Step 4970 | Loss: 0.8208 | LM: 0.3135 | LB: 1.0355 | CL0: 3.6 | CL1: 5.3 | HR0: 0.282/SR0: 0.247 | HR1: 0.191/SR1: 0.164 | LR: 1.00e-04 |
| [2026-05-24 07:45:26] Epoch 2 | Step 4980 | Loss: 0.8202 | LM: 0.3125 | LB: 1.0355 | CL0: 3.6 | CL1: 5.3 | HR0: 0.282/SR0: 0.247 | HR1: 0.190/SR1: 0.164 | LR: 1.00e-04 |
| [2026-05-24 07:45:37] Epoch 2 | Step 4990 | Loss: 0.8199 | LM: 0.3122 | LB: 1.0354 | CL0: 3.6 | CL1: 5.3 | HR0: 0.282/SR0: 0.247 | HR1: 0.190/SR1: 0.164 | LR: 1.00e-04 |
| [2026-05-24 07:45:48] Epoch 2 | Step 5000 | Loss: 0.8199 | LM: 0.3113 | LB: 1.0352 | CL0: 3.6 | CL1: 5.3 | HR0: 0.282/SR0: 0.247 | HR1: 0.191/SR1: 0.164 | LR: 1.00e-04 |
| [2026-05-24 07:45:49] Validation | Batch 10/1463 | Loss: 0.8222 | LM_LOSS: 0.3084 | LB_LOSS: 1.0277 |
| [2026-05-24 07:45:51] Validation | Batch 20/1463 | Loss: 0.8387 | LM_LOSS: 0.3230 | LB_LOSS: 1.0313 |
| [2026-05-24 07:45:53] Validation | Batch 30/1463 | Loss: 0.8440 | LM_LOSS: 0.3278 | LB_LOSS: 1.0323 |
| [2026-05-24 07:45:55] Validation | Batch 40/1463 | Loss: 0.8525 | LM_LOSS: 0.3356 | LB_LOSS: 1.0338 |
| [2026-05-24 07:45:57] Validation | Batch 50/1463 | Loss: 0.8600 | LM_LOSS: 0.3434 | LB_LOSS: 1.0330 |
| [2026-05-24 07:45:59] Validation | Batch 60/1463 | Loss: 0.8606 | LM_LOSS: 0.3441 | LB_LOSS: 1.0330 |
| [2026-05-24 07:46:01] Validation | Batch 70/1463 | Loss: 0.8618 | LM_LOSS: 0.3452 | LB_LOSS: 1.0331 |
| [2026-05-24 07:46:03] Validation | Batch 80/1463 | Loss: 0.8642 | LM_LOSS: 0.3476 | LB_LOSS: 1.0331 |
| [2026-05-24 07:46:05] Validation | Batch 90/1463 | Loss: 0.8634 | LM_LOSS: 0.3469 | LB_LOSS: 1.0331 |
| [2026-05-24 07:46:07] Validation | Batch 100/1463 | Loss: 0.8632 | LM_LOSS: 0.3466 | LB_LOSS: 1.0331 |
| [2026-05-24 07:46:09] Validation | Batch 110/1463 | Loss: 0.8610 | LM_LOSS: 0.3443 | LB_LOSS: 1.0335 |
| [2026-05-24 07:46:10] Validation | Batch 120/1463 | Loss: 0.8620 | LM_LOSS: 0.3452 | LB_LOSS: 1.0336 |
| [2026-05-24 07:46:12] Validation | Batch 130/1463 | Loss: 0.8647 | LM_LOSS: 0.3479 | LB_LOSS: 1.0336 |
| [2026-05-24 07:46:14] Validation | Batch 140/1463 | Loss: 0.8661 | LM_LOSS: 0.3493 | LB_LOSS: 1.0336 |
| [2026-05-24 07:46:16] Validation | Batch 150/1463 | Loss: 0.8644 | LM_LOSS: 0.3475 | LB_LOSS: 1.0338 |
| [2026-05-24 07:46:18] Validation | Batch 160/1463 | Loss: 0.8648 | LM_LOSS: 0.3480 | LB_LOSS: 1.0336 |
| [2026-05-24 07:46:20] Validation | Batch 170/1463 | Loss: 0.8642 | LM_LOSS: 0.3474 | LB_LOSS: 1.0336 |
| [2026-05-24 07:46:22] Validation | Batch 180/1463 | Loss: 0.8649 | LM_LOSS: 0.3481 | LB_LOSS: 1.0336 |
| [2026-05-24 07:46:24] Validation | Batch 190/1463 | Loss: 0.8658 | LM_LOSS: 0.3489 | LB_LOSS: 1.0337 |
| [2026-05-24 07:46:26] Validation | Batch 200/1463 | Loss: 0.8656 | LM_LOSS: 0.3488 | LB_LOSS: 1.0337 |
| [2026-05-24 07:46:28] Validation | Batch 210/1463 | Loss: 0.8662 | LM_LOSS: 0.3493 | LB_LOSS: 1.0337 |
| [2026-05-24 07:46:30] Validation | Batch 220/1463 | Loss: 0.8653 | LM_LOSS: 0.3484 | LB_LOSS: 1.0338 |
| [2026-05-24 07:46:32] Validation | Batch 230/1463 | Loss: 0.8670 | LM_LOSS: 0.3502 | LB_LOSS: 1.0336 |
| [2026-05-24 07:46:34] Validation | Batch 240/1463 | Loss: 0.8682 | LM_LOSS: 0.3514 | LB_LOSS: 1.0336 |
| [2026-05-24 07:46:36] Validation | Batch 250/1463 | Loss: 0.8672 | LM_LOSS: 0.3504 | LB_LOSS: 1.0336 |
| [2026-05-24 07:46:38] Validation | Batch 260/1463 | Loss: 0.8688 | LM_LOSS: 0.3519 | LB_LOSS: 1.0338 |
| [2026-05-24 07:46:40] Validation | Batch 270/1463 | Loss: 0.8673 | LM_LOSS: 0.3504 | LB_LOSS: 1.0338 |
| [2026-05-24 07:46:41] Validation | Batch 280/1463 | Loss: 0.8680 | LM_LOSS: 0.3511 | LB_LOSS: 1.0339 |
| [2026-05-24 07:46:43] Validation | Batch 290/1463 | Loss: 0.8672 | LM_LOSS: 0.3502 | LB_LOSS: 1.0338 |
| [2026-05-24 07:46:45] Validation | Batch 300/1463 | Loss: 0.8678 | LM_LOSS: 0.3508 | LB_LOSS: 1.0340 |
| [2026-05-24 07:46:47] Validation | Batch 310/1463 | Loss: 0.8684 | LM_LOSS: 0.3514 | LB_LOSS: 1.0340 |
| [2026-05-24 07:46:49] Validation | Batch 320/1463 | Loss: 0.8670 | LM_LOSS: 0.3501 | LB_LOSS: 1.0337 |
| [2026-05-24 07:46:51] Validation | Batch 330/1463 | Loss: 0.8669 | LM_LOSS: 0.3501 | LB_LOSS: 1.0338 |
| [2026-05-24 07:46:52] Validation | Batch 340/1463 | Loss: 0.8664 | LM_LOSS: 0.3495 | LB_LOSS: 1.0338 |
| [2026-05-24 07:46:54] Validation | Batch 350/1463 | Loss: 0.8670 | LM_LOSS: 0.3502 | LB_LOSS: 1.0338 |
| [2026-05-24 07:46:56] Validation | Batch 360/1463 | Loss: 0.8668 | LM_LOSS: 0.3499 | LB_LOSS: 1.0338 |
| [2026-05-24 07:46:58] Validation | Batch 370/1463 | Loss: 0.8664 | LM_LOSS: 0.3495 | LB_LOSS: 1.0339 |
| [2026-05-24 07:47:00] Validation | Batch 380/1463 | Loss: 0.8665 | LM_LOSS: 0.3496 | LB_LOSS: 1.0338 |
| [2026-05-24 07:47:01] Validation | Batch 390/1463 | Loss: 0.8671 | LM_LOSS: 0.3502 | LB_LOSS: 1.0338 |
| [2026-05-24 07:47:03] Validation | Batch 400/1463 | Loss: 0.8669 | LM_LOSS: 0.3500 | LB_LOSS: 1.0339 |
| [2026-05-24 07:47:05] Validation | Batch 410/1463 | Loss: 0.8668 | LM_LOSS: 0.3499 | LB_LOSS: 1.0339 |
| [2026-05-24 07:47:07] Validation | Batch 420/1463 | Loss: 0.8670 | LM_LOSS: 0.3500 | LB_LOSS: 1.0340 |
| [2026-05-24 07:47:09] Validation | Batch 430/1463 | Loss: 0.8666 | LM_LOSS: 0.3495 | LB_LOSS: 1.0340 |
| [2026-05-24 07:47:11] Validation | Batch 440/1463 | Loss: 0.8667 | LM_LOSS: 0.3497 | LB_LOSS: 1.0341 |
| [2026-05-24 07:47:12] Validation | Batch 450/1463 | Loss: 0.8664 | LM_LOSS: 0.3493 | LB_LOSS: 1.0342 |
| [2026-05-24 07:47:15] Validation | Batch 460/1463 | Loss: 0.8664 | LM_LOSS: 0.3494 | LB_LOSS: 1.0341 |
| [2026-05-24 07:47:17] Validation | Batch 470/1463 | Loss: 0.8670 | LM_LOSS: 0.3500 | LB_LOSS: 1.0341 |
| [2026-05-24 07:47:19] Validation | Batch 480/1463 | Loss: 0.8668 | LM_LOSS: 0.3498 | LB_LOSS: 1.0340 |
| [2026-05-24 07:47:21] Validation | Batch 490/1463 | Loss: 0.8667 | LM_LOSS: 0.3497 | LB_LOSS: 1.0340 |
| [2026-05-24 07:47:23] Validation | Batch 500/1463 | Loss: 0.8665 | LM_LOSS: 0.3495 | LB_LOSS: 1.0340 |
| [2026-05-24 07:47:25] Validation | Batch 510/1463 | Loss: 0.8660 | LM_LOSS: 0.3490 | LB_LOSS: 1.0340 |
| [2026-05-24 07:47:27] Validation | Batch 520/1463 | Loss: 0.8656 | LM_LOSS: 0.3486 | LB_LOSS: 1.0341 |
| [2026-05-24 07:47:28] Validation | Batch 530/1463 | Loss: 0.8662 | LM_LOSS: 0.3492 | LB_LOSS: 1.0340 |
| [2026-05-24 07:47:30] Validation | Batch 540/1463 | Loss: 0.8664 | LM_LOSS: 0.3494 | LB_LOSS: 1.0341 |
| [2026-05-24 07:47:31] Validation | Batch 550/1463 | Loss: 0.8661 | LM_LOSS: 0.3491 | LB_LOSS: 1.0341 |
| [2026-05-24 07:47:33] Validation | Batch 560/1463 | Loss: 0.8664 | LM_LOSS: 0.3493 | LB_LOSS: 1.0342 |
| [2026-05-24 07:47:35] Validation | Batch 570/1463 | Loss: 0.8665 | LM_LOSS: 0.3494 | LB_LOSS: 1.0342 |
| [2026-05-24 07:47:37] Validation | Batch 580/1463 | Loss: 0.8661 | LM_LOSS: 0.3490 | LB_LOSS: 1.0342 |
| [2026-05-24 07:47:40] Validation | Batch 590/1463 | Loss: 0.8660 | LM_LOSS: 0.3488 | LB_LOSS: 1.0343 |
| [2026-05-24 07:47:42] Validation | Batch 600/1463 | Loss: 0.8663 | LM_LOSS: 0.3491 | LB_LOSS: 1.0343 |
| [2026-05-24 07:47:44] Validation | Batch 610/1463 | Loss: 0.8664 | LM_LOSS: 0.3493 | LB_LOSS: 1.0343 |
| [2026-05-24 07:47:46] Validation | Batch 620/1463 | Loss: 0.8657 | LM_LOSS: 0.3486 | LB_LOSS: 1.0343 |
| [2026-05-24 07:47:48] Validation | Batch 630/1463 | Loss: 0.8652 | LM_LOSS: 0.3481 | LB_LOSS: 1.0344 |
| [2026-05-24 07:47:49] Validation | Batch 640/1463 | Loss: 0.8651 | LM_LOSS: 0.3479 | LB_LOSS: 1.0344 |
| [2026-05-24 07:47:51] Validation | Batch 650/1463 | Loss: 0.8647 | LM_LOSS: 0.3474 | LB_LOSS: 1.0344 |
| [2026-05-24 07:47:53] Validation | Batch 660/1463 | Loss: 0.8641 | LM_LOSS: 0.3469 | LB_LOSS: 1.0344 |
| [2026-05-24 07:47:55] Validation | Batch 670/1463 | Loss: 0.8637 | LM_LOSS: 0.3465 | LB_LOSS: 1.0343 |
| [2026-05-24 07:47:56] Validation | Batch 680/1463 | Loss: 0.8637 | LM_LOSS: 0.3465 | LB_LOSS: 1.0343 |
| [2026-05-24 07:47:58] Validation | Batch 690/1463 | Loss: 0.8640 | LM_LOSS: 0.3469 | LB_LOSS: 1.0343 |
| [2026-05-24 07:48:00] Validation | Batch 700/1463 | Loss: 0.8639 | LM_LOSS: 0.3468 | LB_LOSS: 1.0343 |
| [2026-05-24 07:48:02] Validation | Batch 710/1463 | Loss: 0.8642 | LM_LOSS: 0.3471 | LB_LOSS: 1.0344 |
| [2026-05-24 07:48:04] Validation | Batch 720/1463 | Loss: 0.8650 | LM_LOSS: 0.3478 | LB_LOSS: 1.0344 |
| [2026-05-24 07:48:05] Validation | Batch 730/1463 | Loss: 0.8649 | LM_LOSS: 0.3476 | LB_LOSS: 1.0344 |
| [2026-05-24 07:48:07] Validation | Batch 740/1463 | Loss: 0.8645 | LM_LOSS: 0.3473 | LB_LOSS: 1.0344 |
| [2026-05-24 07:48:08] Validation | Batch 750/1463 | Loss: 0.8643 | LM_LOSS: 0.3471 | LB_LOSS: 1.0344 |
| [2026-05-24 07:48:10] Validation | Batch 760/1463 | Loss: 0.8641 | LM_LOSS: 0.3469 | LB_LOSS: 1.0344 |
| [2026-05-24 07:48:12] Validation | Batch 770/1463 | Loss: 0.8639 | LM_LOSS: 0.3467 | LB_LOSS: 1.0344 |
| [2026-05-24 07:48:13] Validation | Batch 780/1463 | Loss: 0.8636 | LM_LOSS: 0.3464 | LB_LOSS: 1.0344 |
| [2026-05-24 07:48:15] Validation | Batch 790/1463 | Loss: 0.8638 | LM_LOSS: 0.3466 | LB_LOSS: 1.0343 |
| [2026-05-24 07:48:17] Validation | Batch 800/1463 | Loss: 0.8637 | LM_LOSS: 0.3466 | LB_LOSS: 1.0344 |
| [2026-05-24 07:48:18] Validation | Batch 810/1463 | Loss: 0.8634 | LM_LOSS: 0.3462 | LB_LOSS: 1.0343 |
| [2026-05-24 07:48:20] Validation | Batch 820/1463 | Loss: 0.8636 | LM_LOSS: 0.3464 | LB_LOSS: 1.0343 |
| [2026-05-24 07:48:22] Validation | Batch 830/1463 | Loss: 0.8637 | LM_LOSS: 0.3465 | LB_LOSS: 1.0343 |
| [2026-05-24 07:48:24] Validation | Batch 840/1463 | Loss: 0.8637 | LM_LOSS: 0.3466 | LB_LOSS: 1.0343 |
| [2026-05-24 07:48:26] Validation | Batch 850/1463 | Loss: 0.8640 | LM_LOSS: 0.3468 | LB_LOSS: 1.0343 |
| [2026-05-24 07:48:28] Validation | Batch 860/1463 | Loss: 0.8641 | LM_LOSS: 0.3469 | LB_LOSS: 1.0344 |
| [2026-05-24 07:48:30] Validation | Batch 870/1463 | Loss: 0.8642 | LM_LOSS: 0.3470 | LB_LOSS: 1.0344 |
| [2026-05-24 07:48:32] Validation | Batch 880/1463 | Loss: 0.8634 | LM_LOSS: 0.3462 | LB_LOSS: 1.0344 |
| [2026-05-24 07:48:34] Validation | Batch 890/1463 | Loss: 0.8634 | LM_LOSS: 0.3463 | LB_LOSS: 1.0343 |
| [2026-05-24 07:48:35] Validation | Batch 900/1463 | Loss: 0.8631 | LM_LOSS: 0.3459 | LB_LOSS: 1.0343 |
| [2026-05-24 07:48:37] Validation | Batch 910/1463 | Loss: 0.8630 | LM_LOSS: 0.3459 | LB_LOSS: 1.0343 |
| [2026-05-24 07:48:40] Validation | Batch 920/1463 | Loss: 0.8632 | LM_LOSS: 0.3461 | LB_LOSS: 1.0343 |
| [2026-05-24 07:48:41] Validation | Batch 930/1463 | Loss: 0.8630 | LM_LOSS: 0.3458 | LB_LOSS: 1.0343 |
| [2026-05-24 07:48:43] Validation | Batch 940/1463 | Loss: 0.8627 | LM_LOSS: 0.3456 | LB_LOSS: 1.0343 |
| [2026-05-24 07:48:45] Validation | Batch 950/1463 | Loss: 0.8631 | LM_LOSS: 0.3459 | LB_LOSS: 1.0343 |
| [2026-05-24 07:48:47] Validation | Batch 960/1463 | Loss: 0.8631 | LM_LOSS: 0.3460 | LB_LOSS: 1.0342 |
| [2026-05-24 07:48:49] Validation | Batch 970/1463 | Loss: 0.8632 | LM_LOSS: 0.3461 | LB_LOSS: 1.0342 |
| [2026-05-24 07:48:51] Validation | Batch 980/1463 | Loss: 0.8635 | LM_LOSS: 0.3465 | LB_LOSS: 1.0342 |
| [2026-05-24 07:48:53] Validation | Batch 990/1463 | Loss: 0.8638 | LM_LOSS: 0.3467 | LB_LOSS: 1.0342 |
| [2026-05-24 07:48:55] Validation | Batch 1000/1463 | Loss: 0.8644 | LM_LOSS: 0.3473 | LB_LOSS: 1.0342 |
| [2026-05-24 07:48:57] Validation | Batch 1010/1463 | Loss: 0.8644 | LM_LOSS: 0.3473 | LB_LOSS: 1.0343 |
| [2026-05-24 07:48:59] Validation | Batch 1020/1463 | Loss: 0.8645 | LM_LOSS: 0.3474 | LB_LOSS: 1.0343 |
| [2026-05-24 07:49:01] Validation | Batch 1030/1463 | Loss: 0.8650 | LM_LOSS: 0.3478 | LB_LOSS: 1.0343 |
| [2026-05-24 07:49:03] Validation | Batch 1040/1463 | Loss: 0.8645 | LM_LOSS: 0.3474 | LB_LOSS: 1.0343 |
| [2026-05-24 07:49:05] Validation | Batch 1050/1463 | Loss: 0.8644 | LM_LOSS: 0.3473 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:07] Validation | Batch 1060/1463 | Loss: 0.8643 | LM_LOSS: 0.3472 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:09] Validation | Batch 1070/1463 | Loss: 0.8644 | LM_LOSS: 0.3472 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:10] Validation | Batch 1080/1463 | Loss: 0.8641 | LM_LOSS: 0.3470 | LB_LOSS: 1.0343 |
| [2026-05-24 07:49:12] Validation | Batch 1090/1463 | Loss: 0.8641 | LM_LOSS: 0.3470 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:14] Validation | Batch 1100/1463 | Loss: 0.8640 | LM_LOSS: 0.3469 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:16] Validation | Batch 1110/1463 | Loss: 0.8640 | LM_LOSS: 0.3469 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:17] Validation | Batch 1120/1463 | Loss: 0.8638 | LM_LOSS: 0.3467 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:20] Validation | Batch 1130/1463 | Loss: 0.8636 | LM_LOSS: 0.3465 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:21] Validation | Batch 1140/1463 | Loss: 0.8638 | LM_LOSS: 0.3467 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:24] Validation | Batch 1150/1463 | Loss: 0.8637 | LM_LOSS: 0.3466 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:25] Validation | Batch 1160/1463 | Loss: 0.8637 | LM_LOSS: 0.3466 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:27] Validation | Batch 1170/1463 | Loss: 0.8636 | LM_LOSS: 0.3465 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:29] Validation | Batch 1180/1463 | Loss: 0.8637 | LM_LOSS: 0.3466 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:31] Validation | Batch 1190/1463 | Loss: 0.8638 | LM_LOSS: 0.3468 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:33] Validation | Batch 1200/1463 | Loss: 0.8639 | LM_LOSS: 0.3468 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:35] Validation | Batch 1210/1463 | Loss: 0.8641 | LM_LOSS: 0.3470 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:37] Validation | Batch 1220/1463 | Loss: 0.8645 | LM_LOSS: 0.3474 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:39] Validation | Batch 1230/1463 | Loss: 0.8645 | LM_LOSS: 0.3473 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:40] Validation | Batch 1240/1463 | Loss: 0.8647 | LM_LOSS: 0.3476 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:42] Validation | Batch 1250/1463 | Loss: 0.8649 | LM_LOSS: 0.3478 | LB_LOSS: 1.0343 |
| [2026-05-24 07:49:45] Validation | Batch 1260/1463 | Loss: 0.8648 | LM_LOSS: 0.3477 | LB_LOSS: 1.0343 |
| [2026-05-24 07:49:46] Validation | Batch 1270/1463 | Loss: 0.8646 | LM_LOSS: 0.3475 | LB_LOSS: 1.0343 |
| [2026-05-24 07:49:49] Validation | Batch 1280/1463 | Loss: 0.8643 | LM_LOSS: 0.3472 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:50] Validation | Batch 1290/1463 | Loss: 0.8644 | LM_LOSS: 0.3473 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:52] Validation | Batch 1300/1463 | Loss: 0.8642 | LM_LOSS: 0.3471 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:54] Validation | Batch 1310/1463 | Loss: 0.8641 | LM_LOSS: 0.3470 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:56] Validation | Batch 1320/1463 | Loss: 0.8641 | LM_LOSS: 0.3470 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:57] Validation | Batch 1330/1463 | Loss: 0.8642 | LM_LOSS: 0.3471 | LB_LOSS: 1.0342 |
| [2026-05-24 07:49:59] Validation | Batch 1340/1463 | Loss: 0.8645 | LM_LOSS: 0.3474 | LB_LOSS: 1.0342 |
| [2026-05-24 07:50:01] Validation | Batch 1350/1463 | Loss: 0.8645 | LM_LOSS: 0.3474 | LB_LOSS: 1.0342 |
| [2026-05-24 07:50:03] Validation | Batch 1360/1463 | Loss: 0.8648 | LM_LOSS: 0.3477 | LB_LOSS: 1.0342 |
| [2026-05-24 07:50:05] Validation | Batch 1370/1463 | Loss: 0.8651 | LM_LOSS: 0.3480 | LB_LOSS: 1.0342 |
| [2026-05-24 07:50:07] Validation | Batch 1380/1463 | Loss: 0.8649 | LM_LOSS: 0.3478 | LB_LOSS: 1.0342 |
| [2026-05-24 07:50:09] Validation | Batch 1390/1463 | Loss: 0.8648 | LM_LOSS: 0.3477 | LB_LOSS: 1.0342 |
| [2026-05-24 07:50:11] Validation | Batch 1400/1463 | Loss: 0.8651 | LM_LOSS: 0.3480 | LB_LOSS: 1.0342 |
| [2026-05-24 07:50:12] Validation | Batch 1410/1463 | Loss: 0.8653 | LM_LOSS: 0.3482 | LB_LOSS: 1.0342 |
| [2026-05-24 07:50:14] Validation | Batch 1420/1463 | Loss: 0.8653 | LM_LOSS: 0.3482 | LB_LOSS: 1.0342 |
| [2026-05-24 07:50:16] Validation | Batch 1430/1463 | Loss: 0.8654 | LM_LOSS: 0.3483 | LB_LOSS: 1.0342 |
| [2026-05-24 07:50:18] Validation | Batch 1440/1463 | Loss: 0.8658 | LM_LOSS: 0.3487 | LB_LOSS: 1.0342 |
| [2026-05-24 07:50:20] Validation | Batch 1450/1463 | Loss: 0.8656 | LM_LOSS: 0.3485 | LB_LOSS: 1.0342 |
| [2026-05-24 07:50:22] Validation | Batch 1460/1463 | Loss: 0.8659 | LM_LOSS: 0.3488 | LB_LOSS: 1.0341 |
| [2026-05-24 07:50:23] Validation | Batch 1463/1463 | Loss: 0.8657 | LM_LOSS: 0.3487 | LB_LOSS: 1.0341 |
| [2026-05-24 07:50:23] Validation | Loss: 0.8657 | LM_LOSS: 0.3487 | LB_LOSS: 1.0341 | PPL: 1.42 | Time: 274.85s |
| [2026-05-24 07:50:34] Epoch 2 | Step 5010 | Loss: 0.8191 | LM: 0.3097 | LB: 1.0354 | CL0: 3.6 | CL1: 5.3 | HR0: 0.282/SR0: 0.247 | HR1: 0.191/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:50:44] Epoch 2 | Step 5020 | Loss: 0.8193 | LM: 0.3086 | LB: 1.0353 | CL0: 3.6 | CL1: 5.3 | HR0: 0.282/SR0: 0.246 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:50:55] Epoch 2 | Step 5030 | Loss: 0.8196 | LM: 0.3091 | LB: 1.0351 | CL0: 3.6 | CL1: 5.3 | HR0: 0.282/SR0: 0.246 | HR1: 0.191/SR1: 0.164 | LR: 1.00e-04 |
| [2026-05-24 07:51:06] Epoch 2 | Step 5040 | Loss: 0.8190 | LM: 0.3086 | LB: 1.0351 | CL0: 3.6 | CL1: 5.3 | HR0: 0.282/SR0: 0.246 | HR1: 0.191/SR1: 0.164 | LR: 1.00e-04 |
| [2026-05-24 07:51:16] Epoch 2 | Step 5050 | Loss: 0.8184 | LM: 0.3081 | LB: 1.0351 | CL0: 3.6 | CL1: 5.3 | HR0: 0.282/SR0: 0.246 | HR1: 0.191/SR1: 0.164 | LR: 1.00e-04 |
| [2026-05-24 07:51:27] Epoch 2 | Step 5060 | Loss: 0.8183 | LM: 0.3088 | LB: 1.0349 | CL0: 3.6 | CL1: 5.3 | HR0: 0.281/SR0: 0.246 | HR1: 0.191/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:51:38] Epoch 2 | Step 5070 | Loss: 0.8176 | LM: 0.3087 | LB: 1.0349 | CL0: 3.6 | CL1: 5.3 | HR0: 0.281/SR0: 0.246 | HR1: 0.191/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:51:49] Epoch 2 | Step 5080 | Loss: 0.8173 | LM: 0.3100 | LB: 1.0349 | CL0: 3.6 | CL1: 5.3 | HR0: 0.281/SR0: 0.246 | HR1: 0.191/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:52:01] Epoch 2 | Step 5090 | Loss: 0.8172 | LM: 0.3103 | LB: 1.0349 | CL0: 3.6 | CL1: 5.3 | HR0: 0.281/SR0: 0.246 | HR1: 0.191/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:52:12] Epoch 2 | Step 5100 | Loss: 0.8175 | LM: 0.3106 | LB: 1.0348 | CL0: 3.6 | CL1: 5.3 | HR0: 0.281/SR0: 0.246 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:52:23] Epoch 2 | Step 5110 | Loss: 0.8177 | LM: 0.3087 | LB: 1.0346 | CL0: 3.6 | CL1: 5.3 | HR0: 0.281/SR0: 0.246 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:52:34] Epoch 2 | Step 5120 | Loss: 0.8180 | LM: 0.3108 | LB: 1.0346 | CL0: 3.6 | CL1: 5.3 | HR0: 0.281/SR0: 0.246 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:52:45] Epoch 2 | Step 5130 | Loss: 0.8180 | LM: 0.3120 | LB: 1.0347 | CL0: 3.6 | CL1: 5.3 | HR0: 0.281/SR0: 0.246 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:52:56] Epoch 2 | Step 5140 | Loss: 0.8179 | LM: 0.3124 | LB: 1.0346 | CL0: 3.6 | CL1: 5.3 | HR0: 0.281/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:53:08] Epoch 2 | Step 5150 | Loss: 0.8174 | LM: 0.3118 | LB: 1.0346 | CL0: 3.6 | CL1: 5.3 | HR0: 0.281/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:53:20] Epoch 2 | Step 5160 | Loss: 0.8171 | LM: 0.3119 | LB: 1.0345 | CL0: 3.6 | CL1: 5.3 | HR0: 0.281/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:53:31] Epoch 2 | Step 5170 | Loss: 0.8169 | LM: 0.3112 | LB: 1.0346 | CL0: 3.6 | CL1: 5.3 | HR0: 0.281/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:53:43] Epoch 2 | Step 5180 | Loss: 0.8173 | LM: 0.3108 | LB: 1.0345 | CL0: 3.6 | CL1: 5.3 | HR0: 0.281/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:53:54] Epoch 2 | Step 5190 | Loss: 0.8171 | LM: 0.3104 | LB: 1.0344 | CL0: 3.6 | CL1: 5.3 | HR0: 0.280/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:54:05] Epoch 2 | Step 5200 | Loss: 0.8176 | LM: 0.3109 | LB: 1.0343 | CL0: 3.6 | CL1: 5.3 | HR0: 0.280/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:54:16] Epoch 2 | Step 5210 | Loss: 0.8179 | LM: 0.3098 | LB: 1.0343 | CL0: 3.6 | CL1: 5.3 | HR0: 0.280/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:54:28] Epoch 2 | Step 5220 | Loss: 0.8183 | LM: 0.3106 | LB: 1.0343 | CL0: 3.6 | CL1: 5.3 | HR0: 0.280/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:54:39] Epoch 2 | Step 5230 | Loss: 0.8186 | LM: 0.3110 | LB: 1.0343 | CL0: 3.6 | CL1: 5.3 | HR0: 0.280/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:54:50] Epoch 2 | Step 5240 | Loss: 0.8185 | LM: 0.3113 | LB: 1.0343 | CL0: 3.6 | CL1: 5.3 | HR0: 0.280/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:55:01] Epoch 2 | Step 5250 | Loss: 0.8184 | LM: 0.3113 | LB: 1.0342 | CL0: 3.6 | CL1: 5.3 | HR0: 0.280/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:55:13] Epoch 2 | Step 5260 | Loss: 0.8187 | LM: 0.3120 | LB: 1.0342 | CL0: 3.6 | CL1: 5.3 | HR0: 0.280/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:55:24] Epoch 2 | Step 5270 | Loss: 0.8188 | LM: 0.3119 | LB: 1.0342 | CL0: 3.6 | CL1: 5.3 | HR0: 0.280/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:55:35] Epoch 2 | Step 5280 | Loss: 0.8191 | LM: 0.3130 | LB: 1.0342 | CL0: 3.6 | CL1: 5.3 | HR0: 0.280/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:55:46] Epoch 2 | Step 5290 | Loss: 0.8194 | LM: 0.3122 | LB: 1.0342 | CL0: 3.6 | CL1: 5.3 | HR0: 0.280/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:55:57] Epoch 2 | Step 5300 | Loss: 0.8196 | LM: 0.3125 | LB: 1.0341 | CL0: 3.6 | CL1: 5.3 | HR0: 0.280/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:56:08] Epoch 2 | Step 5310 | Loss: 0.8198 | LM: 0.3128 | LB: 1.0340 | CL0: 3.6 | CL1: 5.3 | HR0: 0.280/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:56:20] Epoch 2 | Step 5320 | Loss: 0.8199 | LM: 0.3124 | LB: 1.0339 | CL0: 3.6 | CL1: 5.3 | HR0: 0.280/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:56:31] Epoch 2 | Step 5330 | Loss: 0.8197 | LM: 0.3125 | LB: 1.0340 | CL0: 3.6 | CL1: 5.3 | HR0: 0.280/SR0: 0.245 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:56:41] Epoch 2 | Step 5340 | Loss: 0.8195 | LM: 0.3125 | LB: 1.0338 | CL0: 3.6 | CL1: 5.3 | HR0: 0.280/SR0: 0.244 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:56:52] Epoch 2 | Step 5350 | Loss: 0.8193 | LM: 0.3118 | LB: 1.0337 | CL0: 3.6 | CL1: 5.3 | HR0: 0.280/SR0: 0.244 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:57:03] Epoch 2 | Step 5360 | Loss: 0.8194 | LM: 0.3112 | LB: 1.0336 | CL0: 3.6 | CL1: 5.3 | HR0: 0.279/SR0: 0.244 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:57:13] Epoch 2 | Step 5370 | Loss: 0.8198 | LM: 0.3112 | LB: 1.0335 | CL0: 3.6 | CL1: 5.3 | HR0: 0.279/SR0: 0.244 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:57:24] Epoch 2 | Step 5380 | Loss: 0.8194 | LM: 0.3112 | LB: 1.0334 | CL0: 3.6 | CL1: 5.3 | HR0: 0.279/SR0: 0.244 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:57:35] Epoch 2 | Step 5390 | Loss: 0.8193 | LM: 0.3112 | LB: 1.0335 | CL0: 3.6 | CL1: 5.3 | HR0: 0.279/SR0: 0.244 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:57:45] Epoch 2 | Step 5400 | Loss: 0.8193 | LM: 0.3102 | LB: 1.0333 | CL0: 3.6 | CL1: 5.3 | HR0: 0.279/SR0: 0.244 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:57:56] Epoch 2 | Step 5410 | Loss: 0.8195 | LM: 0.3101 | LB: 1.0333 | CL0: 3.6 | CL1: 5.3 | HR0: 0.279/SR0: 0.244 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:58:08] Epoch 2 | Step 5420 | Loss: 0.8195 | LM: 0.3101 | LB: 1.0332 | CL0: 3.6 | CL1: 5.3 | HR0: 0.279/SR0: 0.244 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:58:19] Epoch 2 | Step 5430 | Loss: 0.8197 | LM: 0.3102 | LB: 1.0331 | CL0: 3.6 | CL1: 5.3 | HR0: 0.279/SR0: 0.244 | HR1: 0.191/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:58:29] Epoch 2 | Step 5440 | Loss: 0.8195 | LM: 0.3098 | LB: 1.0331 | CL0: 3.6 | CL1: 5.3 | HR0: 0.279/SR0: 0.243 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:58:40] Epoch 2 | Step 5450 | Loss: 0.8193 | LM: 0.3098 | LB: 1.0330 | CL0: 3.6 | CL1: 5.3 | HR0: 0.279/SR0: 0.243 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:58:51] Epoch 2 | Step 5460 | Loss: 0.8194 | LM: 0.3100 | LB: 1.0331 | CL0: 3.6 | CL1: 5.3 | HR0: 0.279/SR0: 0.243 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:59:01] Epoch 2 | Step 5470 | Loss: 0.8192 | LM: 0.3095 | LB: 1.0330 | CL0: 3.6 | CL1: 5.3 | HR0: 0.278/SR0: 0.243 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:59:12] Epoch 2 | Step 5480 | Loss: 0.8191 | LM: 0.3094 | LB: 1.0330 | CL0: 3.6 | CL1: 5.3 | HR0: 0.278/SR0: 0.243 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:59:23] Epoch 2 | Step 5490 | Loss: 0.8189 | LM: 0.3096 | LB: 1.0330 | CL0: 3.6 | CL1: 5.3 | HR0: 0.279/SR0: 0.243 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:59:34] Epoch 2 | Step 5500 | Loss: 0.8192 | LM: 0.3099 | LB: 1.0330 | CL0: 3.6 | CL1: 5.3 | HR0: 0.279/SR0: 0.243 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:59:45] Epoch 2 | Step 5510 | Loss: 0.8192 | LM: 0.3099 | LB: 1.0330 | CL0: 3.6 | CL1: 5.3 | HR0: 0.278/SR0: 0.243 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 07:59:57] Epoch 2 | Step 5520 | Loss: 0.8195 | LM: 0.3095 | LB: 1.0329 | CL0: 3.6 | CL1: 5.3 | HR0: 0.278/SR0: 0.243 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 08:00:08] Epoch 2 | Step 5530 | Loss: 0.8193 | LM: 0.3092 | LB: 1.0330 | CL0: 3.6 | CL1: 5.3 | HR0: 0.278/SR0: 0.243 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 08:00:20] Epoch 2 | Step 5540 | Loss: 0.8190 | LM: 0.3093 | LB: 1.0331 | CL0: 3.6 | CL1: 5.3 | HR0: 0.278/SR0: 0.243 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:00:32] Epoch 2 | Step 5550 | Loss: 0.8190 | LM: 0.3098 | LB: 1.0331 | CL0: 3.6 | CL1: 5.3 | HR0: 0.279/SR0: 0.243 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:00:44] Epoch 2 | Step 5560 | Loss: 0.8190 | LM: 0.3090 | LB: 1.0330 | CL0: 3.6 | CL1: 5.3 | HR0: 0.278/SR0: 0.243 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:00:55] Epoch 2 | Step 5570 | Loss: 0.8189 | LM: 0.3086 | LB: 1.0329 | CL0: 3.6 | CL1: 5.3 | HR0: 0.278/SR0: 0.243 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:01:07] Epoch 2 | Step 5580 | Loss: 0.8189 | LM: 0.3086 | LB: 1.0329 | CL0: 3.6 | CL1: 5.3 | HR0: 0.278/SR0: 0.243 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:01:19] Epoch 2 | Step 5590 | Loss: 0.8190 | LM: 0.3088 | LB: 1.0328 | CL0: 3.6 | CL1: 5.3 | HR0: 0.278/SR0: 0.243 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:01:30] Epoch 2 | Step 5600 | Loss: 0.8191 | LM: 0.3089 | LB: 1.0327 | CL0: 3.6 | CL1: 5.3 | HR0: 0.278/SR0: 0.243 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:01:42] Epoch 2 | Step 5610 | Loss: 0.8194 | LM: 0.3093 | LB: 1.0328 | CL0: 3.6 | CL1: 5.3 | HR0: 0.278/SR0: 0.243 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:01:53] Epoch 2 | Step 5620 | Loss: 0.8193 | LM: 0.3093 | LB: 1.0328 | CL0: 3.6 | CL1: 5.2 | HR0: 0.278/SR0: 0.243 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:02:05] Epoch 2 | Step 5630 | Loss: 0.8193 | LM: 0.3093 | LB: 1.0327 | CL0: 3.6 | CL1: 5.2 | HR0: 0.278/SR0: 0.243 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:02:16] Epoch 2 | Step 5640 | Loss: 0.8195 | LM: 0.3093 | LB: 1.0328 | CL0: 3.6 | CL1: 5.3 | HR0: 0.278/SR0: 0.243 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:02:28] Epoch 2 | Step 5650 | Loss: 0.8195 | LM: 0.3092 | LB: 1.0327 | CL0: 3.6 | CL1: 5.3 | HR0: 0.278/SR0: 0.243 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:02:40] Epoch 2 | Step 5660 | Loss: 0.8194 | LM: 0.3085 | LB: 1.0327 | CL0: 3.6 | CL1: 5.3 | HR0: 0.278/SR0: 0.243 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:02:51] Epoch 2 | Step 5670 | Loss: 0.8191 | LM: 0.3082 | LB: 1.0325 | CL0: 3.6 | CL1: 5.3 | HR0: 0.278/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:03:03] Epoch 2 | Step 5680 | Loss: 0.8195 | LM: 0.3085 | LB: 1.0325 | CL0: 3.6 | CL1: 5.3 | HR0: 0.278/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:03:14] Epoch 2 | Step 5690 | Loss: 0.8195 | LM: 0.3078 | LB: 1.0325 | CL0: 3.6 | CL1: 5.3 | HR0: 0.278/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:03:26] Epoch 2 | Step 5700 | Loss: 0.8193 | LM: 0.3080 | LB: 1.0324 | CL0: 3.6 | CL1: 5.3 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:03:37] Epoch 2 | Step 5710 | Loss: 0.8195 | LM: 0.3081 | LB: 1.0324 | CL0: 3.6 | CL1: 5.3 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:03:49] Epoch 2 | Step 5720 | Loss: 0.8199 | LM: 0.3088 | LB: 1.0324 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:04:01] Epoch 2 | Step 5730 | Loss: 0.8200 | LM: 0.3089 | LB: 1.0323 | CL0: 3.6 | CL1: 5.3 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:04:13] Epoch 2 | Step 5740 | Loss: 0.8202 | LM: 0.3087 | LB: 1.0323 | CL0: 3.6 | CL1: 5.3 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:04:24] Epoch 2 | Step 5750 | Loss: 0.8204 | LM: 0.3086 | LB: 1.0322 | CL0: 3.6 | CL1: 5.3 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:04:35] Epoch 2 | Step 5760 | Loss: 0.8206 | LM: 0.3089 | LB: 1.0323 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:04:47] Epoch 2 | Step 5770 | Loss: 0.8205 | LM: 0.3089 | LB: 1.0322 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:04:59] Epoch 2 | Step 5780 | Loss: 0.8206 | LM: 0.3090 | LB: 1.0323 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:05:11] Epoch 2 | Step 5790 | Loss: 0.8209 | LM: 0.3092 | LB: 1.0323 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:05:22] Epoch 2 | Step 5800 | Loss: 0.8209 | LM: 0.3092 | LB: 1.0322 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:05:34] Epoch 2 | Step 5810 | Loss: 0.8209 | LM: 0.3092 | LB: 1.0322 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:05:45] Epoch 2 | Step 5820 | Loss: 0.8213 | LM: 0.3093 | LB: 1.0322 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:05:57] Epoch 2 | Step 5830 | Loss: 0.8214 | LM: 0.3090 | LB: 1.0321 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:06:09] Epoch 2 | Step 5840 | Loss: 0.8217 | LM: 0.3088 | LB: 1.0321 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:06:20] Epoch 2 | Step 5850 | Loss: 0.8218 | LM: 0.3085 | LB: 1.0321 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:06:31] Epoch 2 | Step 5860 | Loss: 0.8216 | LM: 0.3081 | LB: 1.0321 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:06:43] Epoch 2 | Step 5870 | Loss: 0.8216 | LM: 0.3083 | LB: 1.0321 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:06:55] Epoch 2 | Step 5880 | Loss: 0.8215 | LM: 0.3079 | LB: 1.0321 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:07:06] Epoch 2 | Step 5890 | Loss: 0.8216 | LM: 0.3075 | LB: 1.0321 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:07:18] Epoch 2 | Step 5900 | Loss: 0.8217 | LM: 0.3077 | LB: 1.0321 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:07:29] Epoch 2 | Step 5910 | Loss: 0.8216 | LM: 0.3073 | LB: 1.0321 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:07:41] Epoch 2 | Step 5920 | Loss: 0.8216 | LM: 0.3073 | LB: 1.0320 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:07:52] Epoch 2 | Step 5930 | Loss: 0.8218 | LM: 0.3077 | LB: 1.0320 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:08:04] Epoch 2 | Step 5940 | Loss: 0.8220 | LM: 0.3076 | LB: 1.0320 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.242 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:08:16] Epoch 2 | Step 5950 | Loss: 0.8221 | LM: 0.3077 | LB: 1.0319 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:08:27] Epoch 2 | Step 5960 | Loss: 0.8219 | LM: 0.3077 | LB: 1.0319 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:08:39] Epoch 2 | Step 5970 | Loss: 0.8218 | LM: 0.3074 | LB: 1.0318 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:08:50] Epoch 2 | Step 5980 | Loss: 0.8220 | LM: 0.3075 | LB: 1.0318 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:09:02] Epoch 2 | Step 5990 | Loss: 0.8220 | LM: 0.3075 | LB: 1.0318 | CL0: 3.6 | CL1: 5.2 | HR0: 0.277/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:09:13] Epoch 2 | Step 6000 | Loss: 0.8220 | LM: 0.3078 | LB: 1.0317 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:09:17] Checkpoint saved: outputs/2026-05-24/N_6.0/checkpoints/checkpoint_step_6000.pt |
| [2026-05-24 08:09:22] Validation | Batch 10/1463 | Loss: 0.8246 | LM_LOSS: 0.3139 | LB_LOSS: 1.0214 |
| [2026-05-24 08:09:24] Validation | Batch 20/1463 | Loss: 0.8413 | LM_LOSS: 0.3291 | LB_LOSS: 1.0244 |
| [2026-05-24 08:09:26] Validation | Batch 30/1463 | Loss: 0.8477 | LM_LOSS: 0.3350 | LB_LOSS: 1.0254 |
| [2026-05-24 08:09:27] Validation | Batch 40/1463 | Loss: 0.8553 | LM_LOSS: 0.3420 | LB_LOSS: 1.0266 |
| [2026-05-24 08:09:29] Validation | Batch 50/1463 | Loss: 0.8637 | LM_LOSS: 0.3508 | LB_LOSS: 1.0259 |
| [2026-05-24 08:09:31] Validation | Batch 60/1463 | Loss: 0.8654 | LM_LOSS: 0.3525 | LB_LOSS: 1.0259 |
| [2026-05-24 08:09:34] Validation | Batch 70/1463 | Loss: 0.8662 | LM_LOSS: 0.3532 | LB_LOSS: 1.0259 |
| [2026-05-24 08:09:36] Validation | Batch 80/1463 | Loss: 0.8687 | LM_LOSS: 0.3557 | LB_LOSS: 1.0260 |
| [2026-05-24 08:09:37] Validation | Batch 90/1463 | Loss: 0.8677 | LM_LOSS: 0.3548 | LB_LOSS: 1.0259 |
| [2026-05-24 08:09:39] Validation | Batch 100/1463 | Loss: 0.8669 | LM_LOSS: 0.3539 | LB_LOSS: 1.0259 |
| [2026-05-24 08:09:41] Validation | Batch 110/1463 | Loss: 0.8648 | LM_LOSS: 0.3516 | LB_LOSS: 1.0263 |
| [2026-05-24 08:09:43] Validation | Batch 120/1463 | Loss: 0.8661 | LM_LOSS: 0.3529 | LB_LOSS: 1.0264 |
| [2026-05-24 08:09:44] Validation | Batch 130/1463 | Loss: 0.8684 | LM_LOSS: 0.3552 | LB_LOSS: 1.0264 |
| [2026-05-24 08:09:46] Validation | Batch 140/1463 | Loss: 0.8697 | LM_LOSS: 0.3565 | LB_LOSS: 1.0264 |
| [2026-05-24 08:09:48] Validation | Batch 150/1463 | Loss: 0.8686 | LM_LOSS: 0.3553 | LB_LOSS: 1.0266 |
| [2026-05-24 08:09:50] Validation | Batch 160/1463 | Loss: 0.8694 | LM_LOSS: 0.3562 | LB_LOSS: 1.0264 |
| [2026-05-24 08:09:52] Validation | Batch 170/1463 | Loss: 0.8687 | LM_LOSS: 0.3555 | LB_LOSS: 1.0264 |
| [2026-05-24 08:09:54] Validation | Batch 180/1463 | Loss: 0.8697 | LM_LOSS: 0.3565 | LB_LOSS: 1.0265 |
| [2026-05-24 08:09:56] Validation | Batch 190/1463 | Loss: 0.8707 | LM_LOSS: 0.3574 | LB_LOSS: 1.0265 |
| [2026-05-24 08:09:58] Validation | Batch 200/1463 | Loss: 0.8705 | LM_LOSS: 0.3572 | LB_LOSS: 1.0265 |
| [2026-05-24 08:09:59] Validation | Batch 210/1463 | Loss: 0.8710 | LM_LOSS: 0.3577 | LB_LOSS: 1.0266 |
| [2026-05-24 08:10:02] Validation | Batch 220/1463 | Loss: 0.8700 | LM_LOSS: 0.3567 | LB_LOSS: 1.0266 |
| [2026-05-24 08:10:03] Validation | Batch 230/1463 | Loss: 0.8719 | LM_LOSS: 0.3587 | LB_LOSS: 1.0264 |
| [2026-05-24 08:10:05] Validation | Batch 240/1463 | Loss: 0.8733 | LM_LOSS: 0.3601 | LB_LOSS: 1.0264 |
| [2026-05-24 08:10:07] Validation | Batch 250/1463 | Loss: 0.8721 | LM_LOSS: 0.3589 | LB_LOSS: 1.0264 |
| [2026-05-24 08:10:09] Validation | Batch 260/1463 | Loss: 0.8738 | LM_LOSS: 0.3605 | LB_LOSS: 1.0266 |
| [2026-05-24 08:10:11] Validation | Batch 270/1463 | Loss: 0.8723 | LM_LOSS: 0.3590 | LB_LOSS: 1.0266 |
| [2026-05-24 08:10:13] Validation | Batch 280/1463 | Loss: 0.8733 | LM_LOSS: 0.3599 | LB_LOSS: 1.0266 |
| [2026-05-24 08:10:15] Validation | Batch 290/1463 | Loss: 0.8723 | LM_LOSS: 0.3590 | LB_LOSS: 1.0266 |
| [2026-05-24 08:10:16] Validation | Batch 300/1463 | Loss: 0.8730 | LM_LOSS: 0.3596 | LB_LOSS: 1.0268 |
| [2026-05-24 08:10:18] Validation | Batch 310/1463 | Loss: 0.8736 | LM_LOSS: 0.3602 | LB_LOSS: 1.0268 |
| [2026-05-24 08:10:20] Validation | Batch 320/1463 | Loss: 0.8723 | LM_LOSS: 0.3590 | LB_LOSS: 1.0266 |
| [2026-05-24 08:10:22] Validation | Batch 330/1463 | Loss: 0.8723 | LM_LOSS: 0.3590 | LB_LOSS: 1.0266 |
| [2026-05-24 08:10:23] Validation | Batch 340/1463 | Loss: 0.8718 | LM_LOSS: 0.3585 | LB_LOSS: 1.0266 |
| [2026-05-24 08:10:25] Validation | Batch 350/1463 | Loss: 0.8723 | LM_LOSS: 0.3590 | LB_LOSS: 1.0266 |
| [2026-05-24 08:10:27] Validation | Batch 360/1463 | Loss: 0.8722 | LM_LOSS: 0.3589 | LB_LOSS: 1.0266 |
| [2026-05-24 08:10:29] Validation | Batch 370/1463 | Loss: 0.8720 | LM_LOSS: 0.3587 | LB_LOSS: 1.0267 |
| [2026-05-24 08:10:30] Validation | Batch 380/1463 | Loss: 0.8720 | LM_LOSS: 0.3588 | LB_LOSS: 1.0266 |
| [2026-05-24 08:10:32] Validation | Batch 390/1463 | Loss: 0.8728 | LM_LOSS: 0.3595 | LB_LOSS: 1.0266 |
| [2026-05-24 08:10:34] Validation | Batch 400/1463 | Loss: 0.8726 | LM_LOSS: 0.3592 | LB_LOSS: 1.0266 |
| [2026-05-24 08:10:36] Validation | Batch 410/1463 | Loss: 0.8724 | LM_LOSS: 0.3590 | LB_LOSS: 1.0267 |
| [2026-05-24 08:10:38] Validation | Batch 420/1463 | Loss: 0.8724 | LM_LOSS: 0.3590 | LB_LOSS: 1.0268 |
| [2026-05-24 08:10:40] Validation | Batch 430/1463 | Loss: 0.8720 | LM_LOSS: 0.3585 | LB_LOSS: 1.0268 |
| [2026-05-24 08:10:42] Validation | Batch 440/1463 | Loss: 0.8723 | LM_LOSS: 0.3588 | LB_LOSS: 1.0269 |
| [2026-05-24 08:10:43] Validation | Batch 450/1463 | Loss: 0.8720 | LM_LOSS: 0.3586 | LB_LOSS: 1.0269 |
| [2026-05-24 08:10:45] Validation | Batch 460/1463 | Loss: 0.8720 | LM_LOSS: 0.3585 | LB_LOSS: 1.0269 |
| [2026-05-24 08:10:47] Validation | Batch 470/1463 | Loss: 0.8726 | LM_LOSS: 0.3591 | LB_LOSS: 1.0268 |
| [2026-05-24 08:10:49] Validation | Batch 480/1463 | Loss: 0.8725 | LM_LOSS: 0.3591 | LB_LOSS: 1.0268 |
| [2026-05-24 08:10:51] Validation | Batch 490/1463 | Loss: 0.8723 | LM_LOSS: 0.3589 | LB_LOSS: 1.0268 |
| [2026-05-24 08:10:54] Validation | Batch 500/1463 | Loss: 0.8721 | LM_LOSS: 0.3587 | LB_LOSS: 1.0268 |
| [2026-05-24 08:10:55] Validation | Batch 510/1463 | Loss: 0.8716 | LM_LOSS: 0.3582 | LB_LOSS: 1.0268 |
| [2026-05-24 08:10:57] Validation | Batch 520/1463 | Loss: 0.8712 | LM_LOSS: 0.3578 | LB_LOSS: 1.0268 |
| [2026-05-24 08:10:59] Validation | Batch 530/1463 | Loss: 0.8716 | LM_LOSS: 0.3581 | LB_LOSS: 1.0268 |
| [2026-05-24 08:11:00] Validation | Batch 540/1463 | Loss: 0.8719 | LM_LOSS: 0.3584 | LB_LOSS: 1.0269 |
| [2026-05-24 08:11:02] Validation | Batch 550/1463 | Loss: 0.8716 | LM_LOSS: 0.3581 | LB_LOSS: 1.0269 |
| [2026-05-24 08:11:04] Validation | Batch 560/1463 | Loss: 0.8720 | LM_LOSS: 0.3585 | LB_LOSS: 1.0270 |
| [2026-05-24 08:11:06] Validation | Batch 570/1463 | Loss: 0.8720 | LM_LOSS: 0.3586 | LB_LOSS: 1.0270 |
| [2026-05-24 08:11:08] Validation | Batch 580/1463 | Loss: 0.8717 | LM_LOSS: 0.3582 | LB_LOSS: 1.0270 |
| [2026-05-24 08:11:10] Validation | Batch 590/1463 | Loss: 0.8716 | LM_LOSS: 0.3580 | LB_LOSS: 1.0270 |
| [2026-05-24 08:11:12] Validation | Batch 600/1463 | Loss: 0.8719 | LM_LOSS: 0.3583 | LB_LOSS: 1.0271 |
| [2026-05-24 08:11:14] Validation | Batch 610/1463 | Loss: 0.8720 | LM_LOSS: 0.3584 | LB_LOSS: 1.0271 |
| [2026-05-24 08:11:16] Validation | Batch 620/1463 | Loss: 0.8713 | LM_LOSS: 0.3578 | LB_LOSS: 1.0271 |
| [2026-05-24 08:11:18] Validation | Batch 630/1463 | Loss: 0.8709 | LM_LOSS: 0.3573 | LB_LOSS: 1.0271 |
| [2026-05-24 08:11:20] Validation | Batch 640/1463 | Loss: 0.8708 | LM_LOSS: 0.3572 | LB_LOSS: 1.0271 |
| [2026-05-24 08:11:21] Validation | Batch 650/1463 | Loss: 0.8703 | LM_LOSS: 0.3568 | LB_LOSS: 1.0272 |
| [2026-05-24 08:11:23] Validation | Batch 660/1463 | Loss: 0.8698 | LM_LOSS: 0.3562 | LB_LOSS: 1.0271 |
| [2026-05-24 08:11:25] Validation | Batch 670/1463 | Loss: 0.8694 | LM_LOSS: 0.3558 | LB_LOSS: 1.0271 |
| [2026-05-24 08:11:26] Validation | Batch 680/1463 | Loss: 0.8692 | LM_LOSS: 0.3557 | LB_LOSS: 1.0270 |
| [2026-05-24 08:11:28] Validation | Batch 690/1463 | Loss: 0.8696 | LM_LOSS: 0.3561 | LB_LOSS: 1.0271 |
| [2026-05-24 08:11:30] Validation | Batch 700/1463 | Loss: 0.8695 | LM_LOSS: 0.3560 | LB_LOSS: 1.0270 |
| [2026-05-24 08:11:32] Validation | Batch 710/1463 | Loss: 0.8699 | LM_LOSS: 0.3563 | LB_LOSS: 1.0271 |
| [2026-05-24 08:11:34] Validation | Batch 720/1463 | Loss: 0.8706 | LM_LOSS: 0.3570 | LB_LOSS: 1.0272 |
| [2026-05-24 08:11:35] Validation | Batch 730/1463 | Loss: 0.8703 | LM_LOSS: 0.3567 | LB_LOSS: 1.0272 |
| [2026-05-24 08:11:37] Validation | Batch 740/1463 | Loss: 0.8699 | LM_LOSS: 0.3563 | LB_LOSS: 1.0272 |
| [2026-05-24 08:11:39] Validation | Batch 750/1463 | Loss: 0.8697 | LM_LOSS: 0.3562 | LB_LOSS: 1.0271 |
| [2026-05-24 08:11:40] Validation | Batch 760/1463 | Loss: 0.8694 | LM_LOSS: 0.3559 | LB_LOSS: 1.0271 |
| [2026-05-24 08:11:42] Validation | Batch 770/1463 | Loss: 0.8692 | LM_LOSS: 0.3556 | LB_LOSS: 1.0272 |
| [2026-05-24 08:11:44] Validation | Batch 780/1463 | Loss: 0.8690 | LM_LOSS: 0.3554 | LB_LOSS: 1.0271 |
| [2026-05-24 08:11:45] Validation | Batch 790/1463 | Loss: 0.8691 | LM_LOSS: 0.3556 | LB_LOSS: 1.0271 |
| [2026-05-24 08:11:47] Validation | Batch 800/1463 | Loss: 0.8691 | LM_LOSS: 0.3556 | LB_LOSS: 1.0271 |
| [2026-05-24 08:11:48] Validation | Batch 810/1463 | Loss: 0.8688 | LM_LOSS: 0.3553 | LB_LOSS: 1.0271 |
| [2026-05-24 08:11:50] Validation | Batch 820/1463 | Loss: 0.8690 | LM_LOSS: 0.3555 | LB_LOSS: 1.0270 |
| [2026-05-24 08:11:52] Validation | Batch 830/1463 | Loss: 0.8692 | LM_LOSS: 0.3557 | LB_LOSS: 1.0270 |
| [2026-05-24 08:11:54] Validation | Batch 840/1463 | Loss: 0.8693 | LM_LOSS: 0.3557 | LB_LOSS: 1.0271 |
| [2026-05-24 08:11:56] Validation | Batch 850/1463 | Loss: 0.8696 | LM_LOSS: 0.3560 | LB_LOSS: 1.0271 |
| [2026-05-24 08:11:58] Validation | Batch 860/1463 | Loss: 0.8696 | LM_LOSS: 0.3561 | LB_LOSS: 1.0271 |
| [2026-05-24 08:12:00] Validation | Batch 870/1463 | Loss: 0.8698 | LM_LOSS: 0.3562 | LB_LOSS: 1.0271 |
| [2026-05-24 08:12:02] Validation | Batch 880/1463 | Loss: 0.8691 | LM_LOSS: 0.3555 | LB_LOSS: 1.0271 |
| [2026-05-24 08:12:04] Validation | Batch 890/1463 | Loss: 0.8691 | LM_LOSS: 0.3556 | LB_LOSS: 1.0271 |
| [2026-05-24 08:12:05] Validation | Batch 900/1463 | Loss: 0.8689 | LM_LOSS: 0.3554 | LB_LOSS: 1.0271 |
| [2026-05-24 08:12:07] Validation | Batch 910/1463 | Loss: 0.8688 | LM_LOSS: 0.3553 | LB_LOSS: 1.0271 |
| [2026-05-24 08:12:10] Validation | Batch 920/1463 | Loss: 0.8690 | LM_LOSS: 0.3555 | LB_LOSS: 1.0271 |
| [2026-05-24 08:12:11] Validation | Batch 930/1463 | Loss: 0.8687 | LM_LOSS: 0.3552 | LB_LOSS: 1.0271 |
| [2026-05-24 08:12:13] Validation | Batch 940/1463 | Loss: 0.8685 | LM_LOSS: 0.3550 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:15] Validation | Batch 950/1463 | Loss: 0.8688 | LM_LOSS: 0.3553 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:17] Validation | Batch 960/1463 | Loss: 0.8689 | LM_LOSS: 0.3554 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:19] Validation | Batch 970/1463 | Loss: 0.8689 | LM_LOSS: 0.3554 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:21] Validation | Batch 980/1463 | Loss: 0.8692 | LM_LOSS: 0.3557 | LB_LOSS: 1.0269 |
| [2026-05-24 08:12:23] Validation | Batch 990/1463 | Loss: 0.8694 | LM_LOSS: 0.3560 | LB_LOSS: 1.0269 |
| [2026-05-24 08:12:25] Validation | Batch 1000/1463 | Loss: 0.8700 | LM_LOSS: 0.3565 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:27] Validation | Batch 1010/1463 | Loss: 0.8700 | LM_LOSS: 0.3565 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:29] Validation | Batch 1020/1463 | Loss: 0.8701 | LM_LOSS: 0.3566 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:31] Validation | Batch 1030/1463 | Loss: 0.8706 | LM_LOSS: 0.3571 | LB_LOSS: 1.0271 |
| [2026-05-24 08:12:33] Validation | Batch 1040/1463 | Loss: 0.8702 | LM_LOSS: 0.3567 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:35] Validation | Batch 1050/1463 | Loss: 0.8700 | LM_LOSS: 0.3565 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:37] Validation | Batch 1060/1463 | Loss: 0.8700 | LM_LOSS: 0.3565 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:39] Validation | Batch 1070/1463 | Loss: 0.8701 | LM_LOSS: 0.3566 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:40] Validation | Batch 1080/1463 | Loss: 0.8698 | LM_LOSS: 0.3563 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:42] Validation | Batch 1090/1463 | Loss: 0.8698 | LM_LOSS: 0.3563 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:44] Validation | Batch 1100/1463 | Loss: 0.8697 | LM_LOSS: 0.3562 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:45] Validation | Batch 1110/1463 | Loss: 0.8697 | LM_LOSS: 0.3562 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:47] Validation | Batch 1120/1463 | Loss: 0.8696 | LM_LOSS: 0.3561 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:49] Validation | Batch 1130/1463 | Loss: 0.8693 | LM_LOSS: 0.3558 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:51] Validation | Batch 1140/1463 | Loss: 0.8696 | LM_LOSS: 0.3561 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:53] Validation | Batch 1150/1463 | Loss: 0.8695 | LM_LOSS: 0.3560 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:55] Validation | Batch 1160/1463 | Loss: 0.8695 | LM_LOSS: 0.3560 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:57] Validation | Batch 1170/1463 | Loss: 0.8695 | LM_LOSS: 0.3560 | LB_LOSS: 1.0270 |
| [2026-05-24 08:12:59] Validation | Batch 1180/1463 | Loss: 0.8696 | LM_LOSS: 0.3561 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:01] Validation | Batch 1190/1463 | Loss: 0.8697 | LM_LOSS: 0.3562 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:03] Validation | Batch 1200/1463 | Loss: 0.8698 | LM_LOSS: 0.3563 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:05] Validation | Batch 1210/1463 | Loss: 0.8700 | LM_LOSS: 0.3565 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:06] Validation | Batch 1220/1463 | Loss: 0.8704 | LM_LOSS: 0.3569 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:08] Validation | Batch 1230/1463 | Loss: 0.8703 | LM_LOSS: 0.3568 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:10] Validation | Batch 1240/1463 | Loss: 0.8706 | LM_LOSS: 0.3571 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:12] Validation | Batch 1250/1463 | Loss: 0.8708 | LM_LOSS: 0.3573 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:14] Validation | Batch 1260/1463 | Loss: 0.8707 | LM_LOSS: 0.3572 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:16] Validation | Batch 1270/1463 | Loss: 0.8705 | LM_LOSS: 0.3570 | LB_LOSS: 1.0271 |
| [2026-05-24 08:13:18] Validation | Batch 1280/1463 | Loss: 0.8702 | LM_LOSS: 0.3567 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:20] Validation | Batch 1290/1463 | Loss: 0.8703 | LM_LOSS: 0.3568 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:22] Validation | Batch 1300/1463 | Loss: 0.8700 | LM_LOSS: 0.3565 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:24] Validation | Batch 1310/1463 | Loss: 0.8699 | LM_LOSS: 0.3564 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:25] Validation | Batch 1320/1463 | Loss: 0.8699 | LM_LOSS: 0.3564 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:26] Validation | Batch 1330/1463 | Loss: 0.8699 | LM_LOSS: 0.3564 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:28] Validation | Batch 1340/1463 | Loss: 0.8702 | LM_LOSS: 0.3567 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:30] Validation | Batch 1350/1463 | Loss: 0.8702 | LM_LOSS: 0.3567 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:33] Validation | Batch 1360/1463 | Loss: 0.8704 | LM_LOSS: 0.3569 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:34] Validation | Batch 1370/1463 | Loss: 0.8708 | LM_LOSS: 0.3573 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:36] Validation | Batch 1380/1463 | Loss: 0.8705 | LM_LOSS: 0.3571 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:38] Validation | Batch 1390/1463 | Loss: 0.8705 | LM_LOSS: 0.3570 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:40] Validation | Batch 1400/1463 | Loss: 0.8708 | LM_LOSS: 0.3573 | LB_LOSS: 1.0269 |
| [2026-05-24 08:13:41] Validation | Batch 1410/1463 | Loss: 0.8710 | LM_LOSS: 0.3575 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:43] Validation | Batch 1420/1463 | Loss: 0.8710 | LM_LOSS: 0.3575 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:45] Validation | Batch 1430/1463 | Loss: 0.8710 | LM_LOSS: 0.3576 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:47] Validation | Batch 1440/1463 | Loss: 0.8715 | LM_LOSS: 0.3580 | LB_LOSS: 1.0270 |
| [2026-05-24 08:13:49] Validation | Batch 1450/1463 | Loss: 0.8712 | LM_LOSS: 0.3577 | LB_LOSS: 1.0269 |
| [2026-05-24 08:13:51] Validation | Batch 1460/1463 | Loss: 0.8715 | LM_LOSS: 0.3580 | LB_LOSS: 1.0269 |
| [2026-05-24 08:13:52] Validation | Batch 1463/1463 | Loss: 0.8714 | LM_LOSS: 0.3579 | LB_LOSS: 1.0269 |
| [2026-05-24 08:13:52] Validation | Loss: 0.8714 | LM_LOSS: 0.3579 | LB_LOSS: 1.0269 | PPL: 1.43 | Time: 271.09s |
| [2026-05-24 08:14:03] Epoch 2 | Step 6010 | Loss: 0.8220 | LM: 0.3077 | LB: 1.0317 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:14:14] Epoch 2 | Step 6020 | Loss: 0.8218 | LM: 0.3075 | LB: 1.0316 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:14:25] Epoch 2 | Step 6030 | Loss: 0.8219 | LM: 0.3077 | LB: 1.0316 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:14:36] Epoch 2 | Step 6040 | Loss: 0.8221 | LM: 0.3075 | LB: 1.0316 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:14:47] Epoch 2 | Step 6050 | Loss: 0.8222 | LM: 0.3079 | LB: 1.0317 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:14:57] Epoch 2 | Step 6060 | Loss: 0.8222 | LM: 0.3080 | LB: 1.0316 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:15:08] Epoch 2 | Step 6070 | Loss: 0.8221 | LM: 0.3078 | LB: 1.0316 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:15:19] Epoch 2 | Step 6080 | Loss: 0.8225 | LM: 0.3081 | LB: 1.0316 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:15:29] Epoch 2 | Step 6090 | Loss: 0.8225 | LM: 0.3081 | LB: 1.0316 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:15:40] Epoch 2 | Step 6100 | Loss: 0.8226 | LM: 0.3082 | LB: 1.0315 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:15:50] Epoch 2 | Step 6110 | Loss: 0.8226 | LM: 0.3086 | LB: 1.0316 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:16:01] Epoch 2 | Step 6120 | Loss: 0.8226 | LM: 0.3086 | LB: 1.0316 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:16:12] Epoch 2 | Step 6130 | Loss: 0.8225 | LM: 0.3086 | LB: 1.0315 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:16:23] Epoch 2 | Step 6140 | Loss: 0.8224 | LM: 0.3085 | LB: 1.0315 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:16:34] Epoch 2 | Step 6150 | Loss: 0.8226 | LM: 0.3087 | LB: 1.0315 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:16:45] Epoch 2 | Step 6160 | Loss: 0.8225 | LM: 0.3086 | LB: 1.0314 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:16:55] Epoch 2 | Step 6170 | Loss: 0.8224 | LM: 0.3083 | LB: 1.0314 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:17:06] Epoch 2 | Step 6180 | Loss: 0.8226 | LM: 0.3083 | LB: 1.0314 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:17:16] Epoch 2 | Step 6190 | Loss: 0.8224 | LM: 0.3082 | LB: 1.0314 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:17:27] Epoch 2 | Step 6200 | Loss: 0.8225 | LM: 0.3083 | LB: 1.0314 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:17:38] Epoch 2 | Step 6210 | Loss: 0.8225 | LM: 0.3084 | LB: 1.0313 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:17:49] Epoch 2 | Step 6220 | Loss: 0.8226 | LM: 0.3087 | LB: 1.0313 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:18:00] Epoch 2 | Step 6230 | Loss: 0.8226 | LM: 0.3086 | LB: 1.0313 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.241 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:18:10] Epoch 2 | Step 6240 | Loss: 0.8228 | LM: 0.3088 | LB: 1.0312 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:18:21] Epoch 2 | Step 6250 | Loss: 0.8228 | LM: 0.3090 | LB: 1.0312 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:18:32] Epoch 2 | Step 6260 | Loss: 0.8228 | LM: 0.3092 | LB: 1.0312 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:18:43] Epoch 2 | Step 6270 | Loss: 0.8230 | LM: 0.3093 | LB: 1.0311 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:18:53] Epoch 2 | Step 6280 | Loss: 0.8229 | LM: 0.3089 | LB: 1.0311 | CL0: 3.6 | CL1: 5.2 | HR0: 0.276/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:19:04] Epoch 2 | Step 6290 | Loss: 0.8229 | LM: 0.3094 | LB: 1.0311 | CL0: 3.6 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:19:16] Epoch 2 | Step 6300 | Loss: 0.8229 | LM: 0.3091 | LB: 1.0310 | CL0: 3.6 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:19:27] Epoch 2 | Step 6310 | Loss: 0.8229 | LM: 0.3089 | LB: 1.0310 | CL0: 3.6 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:19:39] Epoch 2 | Step 6320 | Loss: 0.8229 | LM: 0.3086 | LB: 1.0310 | CL0: 3.6 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:19:51] Epoch 2 | Step 6330 | Loss: 0.8228 | LM: 0.3084 | LB: 1.0310 | CL0: 3.6 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:20:02] Epoch 2 | Step 6340 | Loss: 0.8229 | LM: 0.3083 | LB: 1.0309 | CL0: 3.6 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:20:14] Epoch 2 | Step 6350 | Loss: 0.8232 | LM: 0.3086 | LB: 1.0309 | CL0: 3.6 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:20:25] Epoch 2 | Step 6360 | Loss: 0.8231 | LM: 0.3086 | LB: 1.0309 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:20:37] Epoch 2 | Step 6370 | Loss: 0.8231 | LM: 0.3083 | LB: 1.0309 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:20:49] Epoch 2 | Step 6380 | Loss: 0.8232 | LM: 0.3083 | LB: 1.0309 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:21:00] Epoch 2 | Step 6390 | Loss: 0.8232 | LM: 0.3084 | LB: 1.0308 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:21:12] Epoch 2 | Step 6400 | Loss: 0.8234 | LM: 0.3087 | LB: 1.0309 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:21:24] Epoch 2 | Step 6410 | Loss: 0.8234 | LM: 0.3085 | LB: 1.0308 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:21:35] Epoch 2 | Step 6420 | Loss: 0.8234 | LM: 0.3086 | LB: 1.0308 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:21:47] Epoch 2 | Step 6430 | Loss: 0.8232 | LM: 0.3081 | LB: 1.0308 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:21:58] Epoch 2 | Step 6440 | Loss: 0.8233 | LM: 0.3081 | LB: 1.0308 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:22:10] Epoch 2 | Step 6450 | Loss: 0.8232 | LM: 0.3077 | LB: 1.0308 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:22:22] Epoch 2 | Step 6460 | Loss: 0.8233 | LM: 0.3075 | LB: 1.0308 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:22:33] Epoch 2 | Step 6470 | Loss: 0.8234 | LM: 0.3077 | LB: 1.0307 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:22:45] Epoch 2 | Step 6480 | Loss: 0.8235 | LM: 0.3077 | LB: 1.0307 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:22:56] Epoch 2 | Step 6490 | Loss: 0.8234 | LM: 0.3076 | LB: 1.0307 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:23:08] Epoch 2 | Step 6500 | Loss: 0.8235 | LM: 0.3075 | LB: 1.0307 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:23:20] Epoch 2 | Step 6510 | Loss: 0.8236 | LM: 0.3077 | LB: 1.0306 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.240 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:23:31] Epoch 2 | Step 6520 | Loss: 0.8235 | LM: 0.3076 | LB: 1.0306 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:23:43] Epoch 2 | Step 6530 | Loss: 0.8236 | LM: 0.3074 | LB: 1.0305 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:23:55] Epoch 2 | Step 6540 | Loss: 0.8235 | LM: 0.3075 | LB: 1.0305 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:24:06] Epoch 2 | Step 6550 | Loss: 0.8236 | LM: 0.3077 | LB: 1.0305 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:24:17] Epoch 2 | Step 6560 | Loss: 0.8235 | LM: 0.3075 | LB: 1.0305 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:24:29] Epoch 2 | Step 6570 | Loss: 0.8234 | LM: 0.3070 | LB: 1.0305 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:24:41] Epoch 2 | Step 6580 | Loss: 0.8233 | LM: 0.3074 | LB: 1.0305 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:24:52] Epoch 2 | Step 6590 | Loss: 0.8234 | LM: 0.3073 | LB: 1.0305 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:25:04] Epoch 2 | Step 6600 | Loss: 0.8234 | LM: 0.3071 | LB: 1.0304 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:25:15] Epoch 2 | Step 6610 | Loss: 0.8236 | LM: 0.3075 | LB: 1.0304 | CL0: 3.7 | CL1: 5.2 | HR0: 0.275/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:25:27] Epoch 2 | Step 6620 | Loss: 0.8236 | LM: 0.3075 | LB: 1.0304 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:25:39] Epoch 2 | Step 6630 | Loss: 0.8237 | LM: 0.3075 | LB: 1.0304 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:25:50] Epoch 2 | Step 6640 | Loss: 0.8238 | LM: 0.3076 | LB: 1.0304 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:26:02] Epoch 2 | Step 6650 | Loss: 0.8238 | LM: 0.3077 | LB: 1.0303 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:26:13] Epoch 2 | Step 6660 | Loss: 0.8237 | LM: 0.3075 | LB: 1.0303 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:26:25] Epoch 2 | Step 6670 | Loss: 0.8237 | LM: 0.3072 | LB: 1.0303 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:26:37] Epoch 2 | Step 6680 | Loss: 0.8239 | LM: 0.3076 | LB: 1.0303 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:26:48] Epoch 2 | Step 6690 | Loss: 0.8239 | LM: 0.3075 | LB: 1.0303 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:27:00] Epoch 2 | Step 6700 | Loss: 0.8241 | LM: 0.3078 | LB: 1.0303 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:27:12] Epoch 2 | Step 6710 | Loss: 0.8239 | LM: 0.3078 | LB: 1.0302 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:27:23] Epoch 2 | Step 6720 | Loss: 0.8239 | LM: 0.3075 | LB: 1.0302 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:27:35] Epoch 2 | Step 6730 | Loss: 0.8239 | LM: 0.3076 | LB: 1.0302 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:27:47] Epoch 2 | Step 6740 | Loss: 0.8238 | LM: 0.3076 | LB: 1.0302 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:27:58] Epoch 2 | Step 6750 | Loss: 0.8239 | LM: 0.3077 | LB: 1.0301 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:28:10] Epoch 2 | Step 6760 | Loss: 0.8238 | LM: 0.3077 | LB: 1.0301 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:28:21] Epoch 2 | Step 6770 | Loss: 0.8237 | LM: 0.3077 | LB: 1.0301 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:28:33] Epoch 2 | Step 6780 | Loss: 0.8236 | LM: 0.3074 | LB: 1.0300 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:28:45] Epoch 2 | Step 6790 | Loss: 0.8238 | LM: 0.3077 | LB: 1.0300 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.239 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:28:56] Epoch 2 | Step 6800 | Loss: 0.8239 | LM: 0.3080 | LB: 1.0300 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.238 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:29:08] Epoch 2 | Step 6810 | Loss: 0.8239 | LM: 0.3082 | LB: 1.0299 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.238 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:29:19] Epoch 2 | Step 6820 | Loss: 0.8238 | LM: 0.3081 | LB: 1.0299 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.238 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:29:31] Epoch 2 | Step 6830 | Loss: 0.8239 | LM: 0.3080 | LB: 1.0299 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.238 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:29:42] Epoch 2 | Step 6840 | Loss: 0.8238 | LM: 0.3079 | LB: 1.0298 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.238 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:29:54] Epoch 2 | Step 6850 | Loss: 0.8237 | LM: 0.3082 | LB: 1.0298 | CL0: 3.7 | CL1: 5.2 | HR0: 0.274/SR0: 0.238 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:30:06] Epoch 2 | Step 6860 | Loss: 0.8239 | LM: 0.3083 | LB: 1.0298 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:30:17] Epoch 2 | Step 6870 | Loss: 0.8240 | LM: 0.3083 | LB: 1.0298 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:30:29] Epoch 2 | Step 6880 | Loss: 0.8240 | LM: 0.3083 | LB: 1.0298 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:30:40] Epoch 2 | Step 6890 | Loss: 0.8238 | LM: 0.3083 | LB: 1.0298 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:30:52] Epoch 2 | Step 6900 | Loss: 0.8238 | LM: 0.3081 | LB: 1.0298 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:31:03] Epoch 2 | Step 6910 | Loss: 0.8237 | LM: 0.3080 | LB: 1.0298 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:31:15] Epoch 2 | Step 6920 | Loss: 0.8237 | LM: 0.3081 | LB: 1.0297 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:31:27] Epoch 2 | Step 6930 | Loss: 0.8240 | LM: 0.3082 | LB: 1.0297 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:31:38] Epoch 2 | Step 6940 | Loss: 0.8240 | LM: 0.3082 | LB: 1.0297 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:31:49] Epoch 2 | Step 6950 | Loss: 0.8240 | LM: 0.3082 | LB: 1.0296 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:32:00] Epoch 2 | Step 6960 | Loss: 0.8242 | LM: 0.3084 | LB: 1.0296 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:32:10] Epoch 2 | Step 6970 | Loss: 0.8242 | LM: 0.3085 | LB: 1.0296 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:32:21] Epoch 2 | Step 6980 | Loss: 0.8242 | LM: 0.3086 | LB: 1.0296 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:32:32] Epoch 2 | Step 6990 | Loss: 0.8242 | LM: 0.3084 | LB: 1.0296 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:32:43] Epoch 2 | Step 7000 | Loss: 0.8241 | LM: 0.3084 | LB: 1.0296 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:32:44] Validation | Batch 10/1463 | Loss: 0.8258 | LM_LOSS: 0.3161 | LB_LOSS: 1.0194 |
| [2026-05-24 08:32:46] Validation | Batch 20/1463 | Loss: 0.8435 | LM_LOSS: 0.3323 | LB_LOSS: 1.0224 |
| [2026-05-24 08:32:48] Validation | Batch 30/1463 | Loss: 0.8490 | LM_LOSS: 0.3373 | LB_LOSS: 1.0233 |
| [2026-05-24 08:32:49] Validation | Batch 40/1463 | Loss: 0.8569 | LM_LOSS: 0.3447 | LB_LOSS: 1.0244 |
| [2026-05-24 08:32:51] Validation | Batch 50/1463 | Loss: 0.8654 | LM_LOSS: 0.3535 | LB_LOSS: 1.0238 |
| [2026-05-24 08:32:53] Validation | Batch 60/1463 | Loss: 0.8664 | LM_LOSS: 0.3545 | LB_LOSS: 1.0239 |
| [2026-05-24 08:32:56] Validation | Batch 70/1463 | Loss: 0.8660 | LM_LOSS: 0.3541 | LB_LOSS: 1.0239 |
| [2026-05-24 08:32:58] Validation | Batch 80/1463 | Loss: 0.8686 | LM_LOSS: 0.3566 | LB_LOSS: 1.0239 |
| [2026-05-24 08:32:59] Validation | Batch 90/1463 | Loss: 0.8675 | LM_LOSS: 0.3555 | LB_LOSS: 1.0239 |
| [2026-05-24 08:33:01] Validation | Batch 100/1463 | Loss: 0.8672 | LM_LOSS: 0.3552 | LB_LOSS: 1.0240 |
| [2026-05-24 08:33:03] Validation | Batch 110/1463 | Loss: 0.8653 | LM_LOSS: 0.3532 | LB_LOSS: 1.0243 |
| [2026-05-24 08:33:05] Validation | Batch 120/1463 | Loss: 0.8668 | LM_LOSS: 0.3546 | LB_LOSS: 1.0243 |
| [2026-05-24 08:33:06] Validation | Batch 130/1463 | Loss: 0.8693 | LM_LOSS: 0.3572 | LB_LOSS: 1.0244 |
| [2026-05-24 08:33:08] Validation | Batch 140/1463 | Loss: 0.8707 | LM_LOSS: 0.3585 | LB_LOSS: 1.0243 |
| [2026-05-24 08:33:10] Validation | Batch 150/1463 | Loss: 0.8696 | LM_LOSS: 0.3574 | LB_LOSS: 1.0244 |
| [2026-05-24 08:33:12] Validation | Batch 160/1463 | Loss: 0.8705 | LM_LOSS: 0.3584 | LB_LOSS: 1.0243 |
| [2026-05-24 08:33:14] Validation | Batch 170/1463 | Loss: 0.8702 | LM_LOSS: 0.3580 | LB_LOSS: 1.0243 |
| [2026-05-24 08:33:16] Validation | Batch 180/1463 | Loss: 0.8709 | LM_LOSS: 0.3587 | LB_LOSS: 1.0244 |
| [2026-05-24 08:33:18] Validation | Batch 190/1463 | Loss: 0.8716 | LM_LOSS: 0.3594 | LB_LOSS: 1.0244 |
| [2026-05-24 08:33:20] Validation | Batch 200/1463 | Loss: 0.8712 | LM_LOSS: 0.3590 | LB_LOSS: 1.0244 |
| [2026-05-24 08:33:21] Validation | Batch 210/1463 | Loss: 0.8717 | LM_LOSS: 0.3595 | LB_LOSS: 1.0245 |
| [2026-05-24 08:33:24] Validation | Batch 220/1463 | Loss: 0.8707 | LM_LOSS: 0.3585 | LB_LOSS: 1.0245 |
| [2026-05-24 08:33:25] Validation | Batch 230/1463 | Loss: 0.8726 | LM_LOSS: 0.3605 | LB_LOSS: 1.0244 |
| [2026-05-24 08:33:27] Validation | Batch 240/1463 | Loss: 0.8738 | LM_LOSS: 0.3616 | LB_LOSS: 1.0243 |
| [2026-05-24 08:33:29] Validation | Batch 250/1463 | Loss: 0.8726 | LM_LOSS: 0.3605 | LB_LOSS: 1.0243 |
| [2026-05-24 08:33:31] Validation | Batch 260/1463 | Loss: 0.8743 | LM_LOSS: 0.3621 | LB_LOSS: 1.0245 |
| [2026-05-24 08:33:33] Validation | Batch 270/1463 | Loss: 0.8730 | LM_LOSS: 0.3608 | LB_LOSS: 1.0245 |
| [2026-05-24 08:33:35] Validation | Batch 280/1463 | Loss: 0.8739 | LM_LOSS: 0.3617 | LB_LOSS: 1.0245 |
| [2026-05-24 08:33:37] Validation | Batch 290/1463 | Loss: 0.8729 | LM_LOSS: 0.3606 | LB_LOSS: 1.0245 |
| [2026-05-24 08:33:38] Validation | Batch 300/1463 | Loss: 0.8738 | LM_LOSS: 0.3615 | LB_LOSS: 1.0246 |
| [2026-05-24 08:33:40] Validation | Batch 310/1463 | Loss: 0.8745 | LM_LOSS: 0.3622 | LB_LOSS: 1.0246 |
| [2026-05-24 08:33:42] Validation | Batch 320/1463 | Loss: 0.8730 | LM_LOSS: 0.3608 | LB_LOSS: 1.0244 |
| [2026-05-24 08:33:44] Validation | Batch 330/1463 | Loss: 0.8730 | LM_LOSS: 0.3608 | LB_LOSS: 1.0245 |
| [2026-05-24 08:33:45] Validation | Batch 340/1463 | Loss: 0.8725 | LM_LOSS: 0.3603 | LB_LOSS: 1.0245 |
| [2026-05-24 08:33:47] Validation | Batch 350/1463 | Loss: 0.8730 | LM_LOSS: 0.3608 | LB_LOSS: 1.0245 |
| [2026-05-24 08:33:49] Validation | Batch 360/1463 | Loss: 0.8729 | LM_LOSS: 0.3607 | LB_LOSS: 1.0245 |
| [2026-05-24 08:33:51] Validation | Batch 370/1463 | Loss: 0.8726 | LM_LOSS: 0.3603 | LB_LOSS: 1.0246 |
| [2026-05-24 08:33:52] Validation | Batch 380/1463 | Loss: 0.8725 | LM_LOSS: 0.3603 | LB_LOSS: 1.0245 |
| [2026-05-24 08:33:54] Validation | Batch 390/1463 | Loss: 0.8733 | LM_LOSS: 0.3610 | LB_LOSS: 1.0245 |
| [2026-05-24 08:33:56] Validation | Batch 400/1463 | Loss: 0.8732 | LM_LOSS: 0.3609 | LB_LOSS: 1.0245 |
| [2026-05-24 08:33:58] Validation | Batch 410/1463 | Loss: 0.8729 | LM_LOSS: 0.3606 | LB_LOSS: 1.0246 |
| [2026-05-24 08:34:00] Validation | Batch 420/1463 | Loss: 0.8728 | LM_LOSS: 0.3605 | LB_LOSS: 1.0246 |
| [2026-05-24 08:34:02] Validation | Batch 430/1463 | Loss: 0.8726 | LM_LOSS: 0.3602 | LB_LOSS: 1.0247 |
| [2026-05-24 08:34:03] Validation | Batch 440/1463 | Loss: 0.8727 | LM_LOSS: 0.3603 | LB_LOSS: 1.0248 |
| [2026-05-24 08:34:05] Validation | Batch 450/1463 | Loss: 0.8725 | LM_LOSS: 0.3601 | LB_LOSS: 1.0248 |
| [2026-05-24 08:34:07] Validation | Batch 460/1463 | Loss: 0.8725 | LM_LOSS: 0.3601 | LB_LOSS: 1.0248 |
| [2026-05-24 08:34:09] Validation | Batch 470/1463 | Loss: 0.8733 | LM_LOSS: 0.3609 | LB_LOSS: 1.0247 |
| [2026-05-24 08:34:11] Validation | Batch 480/1463 | Loss: 0.8732 | LM_LOSS: 0.3609 | LB_LOSS: 1.0247 |
| [2026-05-24 08:34:13] Validation | Batch 490/1463 | Loss: 0.8730 | LM_LOSS: 0.3607 | LB_LOSS: 1.0247 |
| [2026-05-24 08:34:15] Validation | Batch 500/1463 | Loss: 0.8728 | LM_LOSS: 0.3605 | LB_LOSS: 1.0247 |
| [2026-05-24 08:34:17] Validation | Batch 510/1463 | Loss: 0.8723 | LM_LOSS: 0.3600 | LB_LOSS: 1.0247 |
| [2026-05-24 08:34:19] Validation | Batch 520/1463 | Loss: 0.8720 | LM_LOSS: 0.3596 | LB_LOSS: 1.0247 |
| [2026-05-24 08:34:20] Validation | Batch 530/1463 | Loss: 0.8723 | LM_LOSS: 0.3600 | LB_LOSS: 1.0247 |
| [2026-05-24 08:34:22] Validation | Batch 540/1463 | Loss: 0.8727 | LM_LOSS: 0.3604 | LB_LOSS: 1.0247 |
| [2026-05-24 08:34:23] Validation | Batch 550/1463 | Loss: 0.8724 | LM_LOSS: 0.3600 | LB_LOSS: 1.0247 |
| [2026-05-24 08:34:25] Validation | Batch 560/1463 | Loss: 0.8729 | LM_LOSS: 0.3605 | LB_LOSS: 1.0248 |
| [2026-05-24 08:34:27] Validation | Batch 570/1463 | Loss: 0.8729 | LM_LOSS: 0.3605 | LB_LOSS: 1.0248 |
| [2026-05-24 08:34:29] Validation | Batch 580/1463 | Loss: 0.8725 | LM_LOSS: 0.3601 | LB_LOSS: 1.0248 |
| [2026-05-24 08:34:31] Validation | Batch 590/1463 | Loss: 0.8725 | LM_LOSS: 0.3601 | LB_LOSS: 1.0249 |
| [2026-05-24 08:34:33] Validation | Batch 600/1463 | Loss: 0.8729 | LM_LOSS: 0.3604 | LB_LOSS: 1.0249 |
| [2026-05-24 08:34:35] Validation | Batch 610/1463 | Loss: 0.8729 | LM_LOSS: 0.3605 | LB_LOSS: 1.0249 |
| [2026-05-24 08:34:37] Validation | Batch 620/1463 | Loss: 0.8722 | LM_LOSS: 0.3597 | LB_LOSS: 1.0249 |
| [2026-05-24 08:34:39] Validation | Batch 630/1463 | Loss: 0.8717 | LM_LOSS: 0.3592 | LB_LOSS: 1.0250 |
| [2026-05-24 08:34:41] Validation | Batch 640/1463 | Loss: 0.8716 | LM_LOSS: 0.3591 | LB_LOSS: 1.0250 |
| [2026-05-24 08:34:43] Validation | Batch 650/1463 | Loss: 0.8711 | LM_LOSS: 0.3586 | LB_LOSS: 1.0250 |
| [2026-05-24 08:34:44] Validation | Batch 660/1463 | Loss: 0.8706 | LM_LOSS: 0.3581 | LB_LOSS: 1.0250 |
| [2026-05-24 08:34:46] Validation | Batch 670/1463 | Loss: 0.8702 | LM_LOSS: 0.3577 | LB_LOSS: 1.0249 |
| [2026-05-24 08:34:47] Validation | Batch 680/1463 | Loss: 0.8701 | LM_LOSS: 0.3576 | LB_LOSS: 1.0249 |
| [2026-05-24 08:34:50] Validation | Batch 690/1463 | Loss: 0.8705 | LM_LOSS: 0.3580 | LB_LOSS: 1.0249 |
| [2026-05-24 08:34:51] Validation | Batch 700/1463 | Loss: 0.8704 | LM_LOSS: 0.3580 | LB_LOSS: 1.0249 |
| [2026-05-24 08:34:53] Validation | Batch 710/1463 | Loss: 0.8707 | LM_LOSS: 0.3582 | LB_LOSS: 1.0250 |
| [2026-05-24 08:34:55] Validation | Batch 720/1463 | Loss: 0.8714 | LM_LOSS: 0.3589 | LB_LOSS: 1.0250 |
| [2026-05-24 08:34:56] Validation | Batch 730/1463 | Loss: 0.8713 | LM_LOSS: 0.3588 | LB_LOSS: 1.0250 |
| [2026-05-24 08:34:58] Validation | Batch 740/1463 | Loss: 0.8708 | LM_LOSS: 0.3583 | LB_LOSS: 1.0250 |
| [2026-05-24 08:35:00] Validation | Batch 750/1463 | Loss: 0.8707 | LM_LOSS: 0.3582 | LB_LOSS: 1.0250 |
| [2026-05-24 08:35:01] Validation | Batch 760/1463 | Loss: 0.8704 | LM_LOSS: 0.3579 | LB_LOSS: 1.0250 |
| [2026-05-24 08:35:03] Validation | Batch 770/1463 | Loss: 0.8702 | LM_LOSS: 0.3577 | LB_LOSS: 1.0250 |
| [2026-05-24 08:35:04] Validation | Batch 780/1463 | Loss: 0.8700 | LM_LOSS: 0.3575 | LB_LOSS: 1.0250 |
| [2026-05-24 08:35:06] Validation | Batch 790/1463 | Loss: 0.8701 | LM_LOSS: 0.3577 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:07] Validation | Batch 800/1463 | Loss: 0.8701 | LM_LOSS: 0.3576 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:09] Validation | Batch 810/1463 | Loss: 0.8697 | LM_LOSS: 0.3573 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:11] Validation | Batch 820/1463 | Loss: 0.8700 | LM_LOSS: 0.3575 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:13] Validation | Batch 830/1463 | Loss: 0.8701 | LM_LOSS: 0.3576 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:15] Validation | Batch 840/1463 | Loss: 0.8701 | LM_LOSS: 0.3576 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:17] Validation | Batch 850/1463 | Loss: 0.8704 | LM_LOSS: 0.3579 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:19] Validation | Batch 860/1463 | Loss: 0.8705 | LM_LOSS: 0.3580 | LB_LOSS: 1.0250 |
| [2026-05-24 08:35:21] Validation | Batch 870/1463 | Loss: 0.8706 | LM_LOSS: 0.3581 | LB_LOSS: 1.0250 |
| [2026-05-24 08:35:22] Validation | Batch 880/1463 | Loss: 0.8699 | LM_LOSS: 0.3574 | LB_LOSS: 1.0250 |
| [2026-05-24 08:35:24] Validation | Batch 890/1463 | Loss: 0.8700 | LM_LOSS: 0.3575 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:26] Validation | Batch 900/1463 | Loss: 0.8697 | LM_LOSS: 0.3573 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:28] Validation | Batch 910/1463 | Loss: 0.8696 | LM_LOSS: 0.3571 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:30] Validation | Batch 920/1463 | Loss: 0.8699 | LM_LOSS: 0.3574 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:32] Validation | Batch 930/1463 | Loss: 0.8696 | LM_LOSS: 0.3571 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:33] Validation | Batch 940/1463 | Loss: 0.8693 | LM_LOSS: 0.3568 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:35] Validation | Batch 950/1463 | Loss: 0.8696 | LM_LOSS: 0.3572 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:37] Validation | Batch 960/1463 | Loss: 0.8697 | LM_LOSS: 0.3573 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:39] Validation | Batch 970/1463 | Loss: 0.8698 | LM_LOSS: 0.3574 | LB_LOSS: 1.0248 |
| [2026-05-24 08:35:41] Validation | Batch 980/1463 | Loss: 0.8701 | LM_LOSS: 0.3577 | LB_LOSS: 1.0248 |
| [2026-05-24 08:35:43] Validation | Batch 990/1463 | Loss: 0.8703 | LM_LOSS: 0.3579 | LB_LOSS: 1.0248 |
| [2026-05-24 08:35:45] Validation | Batch 1000/1463 | Loss: 0.8708 | LM_LOSS: 0.3584 | LB_LOSS: 1.0248 |
| [2026-05-24 08:35:47] Validation | Batch 1010/1463 | Loss: 0.8708 | LM_LOSS: 0.3584 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:49] Validation | Batch 1020/1463 | Loss: 0.8709 | LM_LOSS: 0.3584 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:51] Validation | Batch 1030/1463 | Loss: 0.8714 | LM_LOSS: 0.3590 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:52] Validation | Batch 1040/1463 | Loss: 0.8710 | LM_LOSS: 0.3585 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:54] Validation | Batch 1050/1463 | Loss: 0.8708 | LM_LOSS: 0.3584 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:56] Validation | Batch 1060/1463 | Loss: 0.8708 | LM_LOSS: 0.3584 | LB_LOSS: 1.0249 |
| [2026-05-24 08:35:58] Validation | Batch 1070/1463 | Loss: 0.8708 | LM_LOSS: 0.3584 | LB_LOSS: 1.0249 |
| [2026-05-24 08:36:00] Validation | Batch 1080/1463 | Loss: 0.8705 | LM_LOSS: 0.3581 | LB_LOSS: 1.0249 |
| [2026-05-24 08:36:02] Validation | Batch 1090/1463 | Loss: 0.8705 | LM_LOSS: 0.3581 | LB_LOSS: 1.0249 |
| [2026-05-24 08:36:03] Validation | Batch 1100/1463 | Loss: 0.8704 | LM_LOSS: 0.3580 | LB_LOSS: 1.0248 |
| [2026-05-24 08:36:05] Validation | Batch 1110/1463 | Loss: 0.8705 | LM_LOSS: 0.3580 | LB_LOSS: 1.0248 |
| [2026-05-24 08:36:07] Validation | Batch 1120/1463 | Loss: 0.8703 | LM_LOSS: 0.3578 | LB_LOSS: 1.0249 |
| [2026-05-24 08:36:09] Validation | Batch 1130/1463 | Loss: 0.8700 | LM_LOSS: 0.3576 | LB_LOSS: 1.0248 |
| [2026-05-24 08:36:11] Validation | Batch 1140/1463 | Loss: 0.8703 | LM_LOSS: 0.3578 | LB_LOSS: 1.0248 |
| [2026-05-24 08:36:13] Validation | Batch 1150/1463 | Loss: 0.8702 | LM_LOSS: 0.3578 | LB_LOSS: 1.0248 |
| [2026-05-24 08:36:14] Validation | Batch 1160/1463 | Loss: 0.8702 | LM_LOSS: 0.3578 | LB_LOSS: 1.0248 |
| [2026-05-24 08:36:16] Validation | Batch 1170/1463 | Loss: 0.8702 | LM_LOSS: 0.3578 | LB_LOSS: 1.0248 |
| [2026-05-24 08:36:18] Validation | Batch 1180/1463 | Loss: 0.8702 | LM_LOSS: 0.3578 | LB_LOSS: 1.0248 |
| [2026-05-24 08:36:20] Validation | Batch 1190/1463 | Loss: 0.8704 | LM_LOSS: 0.3580 | LB_LOSS: 1.0248 |
| [2026-05-24 08:36:22] Validation | Batch 1200/1463 | Loss: 0.8704 | LM_LOSS: 0.3580 | LB_LOSS: 1.0248 |
| [2026-05-24 08:36:24] Validation | Batch 1210/1463 | Loss: 0.8707 | LM_LOSS: 0.3582 | LB_LOSS: 1.0249 |
| [2026-05-24 08:36:26] Validation | Batch 1220/1463 | Loss: 0.8711 | LM_LOSS: 0.3587 | LB_LOSS: 1.0249 |
| [2026-05-24 08:36:27] Validation | Batch 1230/1463 | Loss: 0.8710 | LM_LOSS: 0.3586 | LB_LOSS: 1.0249 |
| [2026-05-24 08:36:29] Validation | Batch 1240/1463 | Loss: 0.8713 | LM_LOSS: 0.3589 | LB_LOSS: 1.0249 |
| [2026-05-24 08:36:31] Validation | Batch 1250/1463 | Loss: 0.8714 | LM_LOSS: 0.3590 | LB_LOSS: 1.0249 |
| [2026-05-24 08:36:33] Validation | Batch 1260/1463 | Loss: 0.8713 | LM_LOSS: 0.3589 | LB_LOSS: 1.0249 |
| [2026-05-24 08:36:35] Validation | Batch 1270/1463 | Loss: 0.8711 | LM_LOSS: 0.3586 | LB_LOSS: 1.0249 |
| [2026-05-24 08:36:37] Validation | Batch 1280/1463 | Loss: 0.8708 | LM_LOSS: 0.3584 | LB_LOSS: 1.0249 |
| [2026-05-24 08:36:39] Validation | Batch 1290/1463 | Loss: 0.8708 | LM_LOSS: 0.3584 | LB_LOSS: 1.0249 |
| [2026-05-24 08:36:41] Validation | Batch 1300/1463 | Loss: 0.8706 | LM_LOSS: 0.3581 | LB_LOSS: 1.0249 |
| [2026-05-24 08:36:43] Validation | Batch 1310/1463 | Loss: 0.8705 | LM_LOSS: 0.3581 | LB_LOSS: 1.0249 |
| [2026-05-24 08:36:44] Validation | Batch 1320/1463 | Loss: 0.8705 | LM_LOSS: 0.3581 | LB_LOSS: 1.0248 |
| [2026-05-24 08:36:45] Validation | Batch 1330/1463 | Loss: 0.8706 | LM_LOSS: 0.3582 | LB_LOSS: 1.0248 |
| [2026-05-24 08:36:47] Validation | Batch 1340/1463 | Loss: 0.8708 | LM_LOSS: 0.3584 | LB_LOSS: 1.0248 |
| [2026-05-24 08:36:49] Validation | Batch 1350/1463 | Loss: 0.8709 | LM_LOSS: 0.3584 | LB_LOSS: 1.0248 |
| [2026-05-24 08:36:51] Validation | Batch 1360/1463 | Loss: 0.8711 | LM_LOSS: 0.3587 | LB_LOSS: 1.0248 |
| [2026-05-24 08:36:53] Validation | Batch 1370/1463 | Loss: 0.8715 | LM_LOSS: 0.3591 | LB_LOSS: 1.0248 |
| [2026-05-24 08:36:55] Validation | Batch 1380/1463 | Loss: 0.8712 | LM_LOSS: 0.3588 | LB_LOSS: 1.0248 |
| [2026-05-24 08:36:57] Validation | Batch 1390/1463 | Loss: 0.8712 | LM_LOSS: 0.3587 | LB_LOSS: 1.0248 |
| [2026-05-24 08:36:59] Validation | Batch 1400/1463 | Loss: 0.8714 | LM_LOSS: 0.3590 | LB_LOSS: 1.0248 |
| [2026-05-24 08:37:00] Validation | Batch 1410/1463 | Loss: 0.8716 | LM_LOSS: 0.3592 | LB_LOSS: 1.0248 |
| [2026-05-24 08:37:02] Validation | Batch 1420/1463 | Loss: 0.8717 | LM_LOSS: 0.3593 | LB_LOSS: 1.0248 |
| [2026-05-24 08:37:04] Validation | Batch 1430/1463 | Loss: 0.8717 | LM_LOSS: 0.3593 | LB_LOSS: 1.0248 |
| [2026-05-24 08:37:06] Validation | Batch 1440/1463 | Loss: 0.8722 | LM_LOSS: 0.3598 | LB_LOSS: 1.0248 |
| [2026-05-24 08:37:08] Validation | Batch 1450/1463 | Loss: 0.8719 | LM_LOSS: 0.3595 | LB_LOSS: 1.0248 |
| [2026-05-24 08:37:10] Validation | Batch 1460/1463 | Loss: 0.8722 | LM_LOSS: 0.3598 | LB_LOSS: 1.0248 |
| [2026-05-24 08:37:10] Validation | Batch 1463/1463 | Loss: 0.8721 | LM_LOSS: 0.3597 | LB_LOSS: 1.0248 |
| [2026-05-24 08:37:10] Validation | Loss: 0.8721 | LM_LOSS: 0.3597 | LB_LOSS: 1.0248 | PPL: 1.43 | Time: 267.56s |
| [2026-05-24 08:37:21] Epoch 2 | Step 7010 | Loss: 0.8241 | LM: 0.3090 | LB: 1.0295 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:37:32] Epoch 2 | Step 7020 | Loss: 0.8242 | LM: 0.3091 | LB: 1.0295 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:37:43] Epoch 2 | Step 7030 | Loss: 0.8242 | LM: 0.3093 | LB: 1.0295 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:37:54] Epoch 2 | Step 7040 | Loss: 0.8242 | LM: 0.3094 | LB: 1.0295 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:38:04] Epoch 2 | Step 7050 | Loss: 0.8243 | LM: 0.3095 | LB: 1.0295 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:38:15] Epoch 2 | Step 7060 | Loss: 0.8243 | LM: 0.3095 | LB: 1.0295 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:38:26] Epoch 2 | Step 7070 | Loss: 0.8243 | LM: 0.3098 | LB: 1.0295 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:38:36] Epoch 2 | Step 7080 | Loss: 0.8244 | LM: 0.3098 | LB: 1.0294 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:38:47] Epoch 2 | Step 7090 | Loss: 0.8243 | LM: 0.3097 | LB: 1.0294 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:38:58] Epoch 2 | Step 7100 | Loss: 0.8244 | LM: 0.3097 | LB: 1.0294 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.238 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:39:08] Epoch 2 | Step 7110 | Loss: 0.8244 | LM: 0.3094 | LB: 1.0294 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.237 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:39:19] Epoch 2 | Step 7120 | Loss: 0.8243 | LM: 0.3093 | LB: 1.0293 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.237 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:39:30] Epoch 2 | Step 7130 | Loss: 0.8242 | LM: 0.3092 | LB: 1.0293 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.237 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:39:41] Epoch 2 | Step 7140 | Loss: 0.8243 | LM: 0.3092 | LB: 1.0293 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.237 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:39:51] Epoch 2 | Step 7150 | Loss: 0.8244 | LM: 0.3094 | LB: 1.0293 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.237 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:40:02] Epoch 2 | Step 7160 | Loss: 0.8245 | LM: 0.3093 | LB: 1.0293 | CL0: 3.7 | CL1: 5.2 | HR0: 0.273/SR0: 0.237 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:40:13] Epoch 2 | Step 7170 | Loss: 0.8244 | LM: 0.3092 | LB: 1.0293 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:40:23] Epoch 2 | Step 7180 | Loss: 0.8245 | LM: 0.3091 | LB: 1.0292 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:40:34] Epoch 2 | Step 7190 | Loss: 0.8244 | LM: 0.3090 | LB: 1.0292 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:40:45] Epoch 2 | Step 7200 | Loss: 0.8244 | LM: 0.3090 | LB: 1.0292 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:40:55] Epoch 2 | Step 7210 | Loss: 0.8244 | LM: 0.3090 | LB: 1.0292 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:41:06] Epoch 2 | Step 7220 | Loss: 0.8245 | LM: 0.3094 | LB: 1.0291 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:41:17] Epoch 2 | Step 7230 | Loss: 0.8244 | LM: 0.3092 | LB: 1.0291 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:41:28] Epoch 2 | Step 7240 | Loss: 0.8244 | LM: 0.3094 | LB: 1.0291 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:41:38] Epoch 2 | Step 7250 | Loss: 0.8245 | LM: 0.3095 | LB: 1.0291 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:41:49] Epoch 2 | Step 7260 | Loss: 0.8247 | LM: 0.3098 | LB: 1.0291 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:42:00] Epoch 2 | Step 7270 | Loss: 0.8246 | LM: 0.3097 | LB: 1.0290 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:42:10] Epoch 2 | Step 7280 | Loss: 0.8247 | LM: 0.3099 | LB: 1.0290 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:42:21] Epoch 2 | Step 7290 | Loss: 0.8247 | LM: 0.3099 | LB: 1.0290 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:42:32] Epoch 2 | Step 7300 | Loss: 0.8248 | LM: 0.3101 | LB: 1.0290 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:42:42] Epoch 2 | Step 7310 | Loss: 0.8248 | LM: 0.3099 | LB: 1.0290 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:42:53] Epoch 2 | Step 7320 | Loss: 0.8247 | LM: 0.3099 | LB: 1.0290 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:43:05] Epoch 2 | Step 7330 | Loss: 0.8247 | LM: 0.3098 | LB: 1.0289 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:43:16] Epoch 2 | Step 7340 | Loss: 0.8247 | LM: 0.3099 | LB: 1.0289 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:43:28] Epoch 2 | Step 7350 | Loss: 0.8247 | LM: 0.3100 | LB: 1.0289 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:43:40] Epoch 2 | Step 7360 | Loss: 0.8246 | LM: 0.3101 | LB: 1.0289 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:43:51] Epoch 2 | Step 7370 | Loss: 0.8247 | LM: 0.3100 | LB: 1.0289 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:44:03] Epoch 2 | Step 7380 | Loss: 0.8247 | LM: 0.3100 | LB: 1.0289 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:44:14] Epoch 2 | Step 7390 | Loss: 0.8248 | LM: 0.3104 | LB: 1.0288 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:44:26] Epoch 2 | Step 7400 | Loss: 0.8249 | LM: 0.3104 | LB: 1.0288 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:44:38] Epoch 2 | Step 7410 | Loss: 0.8249 | LM: 0.3104 | LB: 1.0288 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:44:49] Epoch 2 | Step 7420 | Loss: 0.8249 | LM: 0.3103 | LB: 1.0288 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:45:01] Epoch 2 | Step 7430 | Loss: 0.8250 | LM: 0.3106 | LB: 1.0288 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:45:12] Epoch 2 | Step 7440 | Loss: 0.8250 | LM: 0.3104 | LB: 1.0287 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.237 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:45:24] Epoch 2 | Step 7450 | Loss: 0.8249 | LM: 0.3103 | LB: 1.0287 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.236 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:45:36] Epoch 2 | Step 7460 | Loss: 0.8250 | LM: 0.3104 | LB: 1.0287 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.236 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:45:47] Epoch 2 | Step 7470 | Loss: 0.8250 | LM: 0.3106 | LB: 1.0287 | CL0: 3.7 | CL1: 5.2 | HR0: 0.272/SR0: 0.236 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 08:45:59] Epoch 2 | Step 7480 | Loss: 0.8250 | LM: 0.3106 | LB: 1.0286 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:46:10] Epoch 2 | Step 7490 | Loss: 0.8250 | LM: 0.3106 | LB: 1.0286 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:46:21] Epoch 2 | Step 7500 | Loss: 0.8251 | LM: 0.3108 | LB: 1.0286 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:46:32] Epoch 2 | Step 7510 | Loss: 0.8251 | LM: 0.3105 | LB: 1.0286 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:46:43] Epoch 2 | Step 7520 | Loss: 0.8251 | LM: 0.3105 | LB: 1.0286 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:46:53] Epoch 2 | Step 7530 | Loss: 0.8251 | LM: 0.3105 | LB: 1.0286 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:47:04] Epoch 2 | Step 7540 | Loss: 0.8251 | LM: 0.3107 | LB: 1.0286 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:47:15] Epoch 2 | Step 7550 | Loss: 0.8252 | LM: 0.3108 | LB: 1.0285 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:47:26] Epoch 2 | Step 7560 | Loss: 0.8252 | LM: 0.3109 | LB: 1.0285 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:47:37] Epoch 2 | Step 7570 | Loss: 0.8252 | LM: 0.3108 | LB: 1.0285 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:47:47] Epoch 2 | Step 7580 | Loss: 0.8252 | LM: 0.3109 | LB: 1.0285 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:47:58] Epoch 2 | Step 7590 | Loss: 0.8253 | LM: 0.3113 | LB: 1.0284 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:48:09] Epoch 2 | Step 7600 | Loss: 0.8253 | LM: 0.3112 | LB: 1.0284 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:48:19] Epoch 2 | Step 7610 | Loss: 0.8253 | LM: 0.3113 | LB: 1.0284 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:48:30] Epoch 2 | Step 7620 | Loss: 0.8252 | LM: 0.3113 | LB: 1.0284 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:48:41] Epoch 2 | Step 7630 | Loss: 0.8253 | LM: 0.3112 | LB: 1.0284 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:48:51] Epoch 2 | Step 7640 | Loss: 0.8253 | LM: 0.3113 | LB: 1.0284 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:49:02] Epoch 2 | Step 7650 | Loss: 0.8254 | LM: 0.3115 | LB: 1.0284 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:49:13] Epoch 2 | Step 7660 | Loss: 0.8254 | LM: 0.3114 | LB: 1.0284 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:49:24] Epoch 2 | Step 7670 | Loss: 0.8253 | LM: 0.3112 | LB: 1.0283 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:49:35] Epoch 2 | Step 7680 | Loss: 0.8253 | LM: 0.3112 | LB: 1.0283 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:49:45] Epoch 2 | Step 7690 | Loss: 0.8254 | LM: 0.3113 | LB: 1.0283 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:49:56] Epoch 2 | Step 7700 | Loss: 0.8254 | LM: 0.3112 | LB: 1.0283 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:50:07] Epoch 2 | Step 7710 | Loss: 0.8254 | LM: 0.3113 | LB: 1.0283 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:50:17] Epoch 2 | Step 7720 | Loss: 0.8255 | LM: 0.3115 | LB: 1.0283 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:50:29] Epoch 2 | Step 7730 | Loss: 0.8255 | LM: 0.3114 | LB: 1.0283 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:50:39] Epoch 2 | Step 7740 | Loss: 0.8256 | LM: 0.3116 | LB: 1.0283 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:50:50] Epoch 2 | Step 7750 | Loss: 0.8258 | LM: 0.3118 | LB: 1.0283 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:51:01] Epoch 2 | Step 7760 | Loss: 0.8258 | LM: 0.3119 | LB: 1.0283 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:51:11] Epoch 2 | Step 7770 | Loss: 0.8258 | LM: 0.3120 | LB: 1.0283 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:51:22] Epoch 2 | Step 7780 | Loss: 0.8258 | LM: 0.3121 | LB: 1.0283 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:51:32] Epoch 2 | Step 7790 | Loss: 0.8259 | LM: 0.3122 | LB: 1.0282 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:51:43] Epoch 2 | Step 7800 | Loss: 0.8259 | LM: 0.3121 | LB: 1.0282 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:51:53] Epoch 2 | Step 7810 | Loss: 0.8260 | LM: 0.3123 | LB: 1.0282 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:52:04] Epoch 2 | Step 7820 | Loss: 0.8261 | LM: 0.3123 | LB: 1.0282 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:52:15] Epoch 2 | Step 7830 | Loss: 0.8262 | LM: 0.3125 | LB: 1.0282 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:52:26] Epoch 2 | Step 7840 | Loss: 0.8262 | LM: 0.3126 | LB: 1.0282 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:52:36] Epoch 2 | Step 7850 | Loss: 0.8263 | LM: 0.3127 | LB: 1.0282 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:52:47] Epoch 2 | Step 7860 | Loss: 0.8261 | LM: 0.3124 | LB: 1.0281 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:52:58] Epoch 2 | Step 7870 | Loss: 0.8262 | LM: 0.3125 | LB: 1.0281 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.236 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:53:09] Epoch 2 | Step 7880 | Loss: 0.8261 | LM: 0.3127 | LB: 1.0281 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:53:19] Epoch 2 | Step 7890 | Loss: 0.8261 | LM: 0.3124 | LB: 1.0281 | CL0: 3.7 | CL1: 5.2 | HR0: 0.271/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:53:30] Epoch 2 | Step 7900 | Loss: 0.8261 | LM: 0.3125 | LB: 1.0280 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:53:40] Epoch 2 | Step 7910 | Loss: 0.8261 | LM: 0.3125 | LB: 1.0280 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:53:51] Epoch 2 | Step 7920 | Loss: 0.8260 | LM: 0.3126 | LB: 1.0280 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:54:01] Epoch 2 | Step 7930 | Loss: 0.8260 | LM: 0.3125 | LB: 1.0280 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:54:12] Epoch 2 | Step 7940 | Loss: 0.8259 | LM: 0.3124 | LB: 1.0280 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:54:23] Epoch 2 | Step 7950 | Loss: 0.8260 | LM: 0.3125 | LB: 1.0280 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:54:34] Epoch 2 | Step 7960 | Loss: 0.8261 | LM: 0.3128 | LB: 1.0280 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:54:44] Epoch 2 | Step 7970 | Loss: 0.8262 | LM: 0.3128 | LB: 1.0280 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:54:55] Epoch 2 | Step 7980 | Loss: 0.8262 | LM: 0.3129 | LB: 1.0280 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:55:05] Epoch 2 | Step 7990 | Loss: 0.8261 | LM: 0.3126 | LB: 1.0279 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:55:16] Epoch 2 | Step 8000 | Loss: 0.8262 | LM: 0.3127 | LB: 1.0279 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 08:55:17] Validation | Batch 10/1463 | Loss: 0.8307 | LM_LOSS: 0.3227 | LB_LOSS: 1.0161 |
| [2026-05-24 08:55:19] Validation | Batch 20/1463 | Loss: 0.8440 | LM_LOSS: 0.3346 | LB_LOSS: 1.0187 |
| [2026-05-24 08:55:21] Validation | Batch 30/1463 | Loss: 0.8490 | LM_LOSS: 0.3392 | LB_LOSS: 1.0196 |
| [2026-05-24 08:55:23] Validation | Batch 40/1463 | Loss: 0.8582 | LM_LOSS: 0.3479 | LB_LOSS: 1.0206 |
| [2026-05-24 08:55:24] Validation | Batch 50/1463 | Loss: 0.8653 | LM_LOSS: 0.3553 | LB_LOSS: 1.0201 |
| [2026-05-24 08:55:27] Validation | Batch 60/1463 | Loss: 0.8663 | LM_LOSS: 0.3563 | LB_LOSS: 1.0201 |
| [2026-05-24 08:55:29] Validation | Batch 70/1463 | Loss: 0.8662 | LM_LOSS: 0.3562 | LB_LOSS: 1.0201 |
| [2026-05-24 08:55:31] Validation | Batch 80/1463 | Loss: 0.8683 | LM_LOSS: 0.3582 | LB_LOSS: 1.0202 |
| [2026-05-24 08:55:32] Validation | Batch 90/1463 | Loss: 0.8676 | LM_LOSS: 0.3575 | LB_LOSS: 1.0201 |
| [2026-05-24 08:55:34] Validation | Batch 100/1463 | Loss: 0.8675 | LM_LOSS: 0.3574 | LB_LOSS: 1.0202 |
| [2026-05-24 08:55:36] Validation | Batch 110/1463 | Loss: 0.8659 | LM_LOSS: 0.3557 | LB_LOSS: 1.0204 |
| [2026-05-24 08:55:38] Validation | Batch 120/1463 | Loss: 0.8677 | LM_LOSS: 0.3574 | LB_LOSS: 1.0205 |
| [2026-05-24 08:55:39] Validation | Batch 130/1463 | Loss: 0.8710 | LM_LOSS: 0.3608 | LB_LOSS: 1.0205 |
| [2026-05-24 08:55:41] Validation | Batch 140/1463 | Loss: 0.8724 | LM_LOSS: 0.3622 | LB_LOSS: 1.0205 |
| [2026-05-24 08:55:43] Validation | Batch 150/1463 | Loss: 0.8712 | LM_LOSS: 0.3609 | LB_LOSS: 1.0206 |
| [2026-05-24 08:55:45] Validation | Batch 160/1463 | Loss: 0.8720 | LM_LOSS: 0.3618 | LB_LOSS: 1.0205 |
| [2026-05-24 08:55:47] Validation | Batch 170/1463 | Loss: 0.8714 | LM_LOSS: 0.3612 | LB_LOSS: 1.0205 |
| [2026-05-24 08:55:49] Validation | Batch 180/1463 | Loss: 0.8720 | LM_LOSS: 0.3617 | LB_LOSS: 1.0206 |
| [2026-05-24 08:55:51] Validation | Batch 190/1463 | Loss: 0.8727 | LM_LOSS: 0.3624 | LB_LOSS: 1.0206 |
| [2026-05-24 08:55:53] Validation | Batch 200/1463 | Loss: 0.8723 | LM_LOSS: 0.3620 | LB_LOSS: 1.0206 |
| [2026-05-24 08:55:54] Validation | Batch 210/1463 | Loss: 0.8729 | LM_LOSS: 0.3626 | LB_LOSS: 1.0206 |
| [2026-05-24 08:55:56] Validation | Batch 220/1463 | Loss: 0.8722 | LM_LOSS: 0.3619 | LB_LOSS: 1.0207 |
| [2026-05-24 08:55:58] Validation | Batch 230/1463 | Loss: 0.8741 | LM_LOSS: 0.3639 | LB_LOSS: 1.0205 |
| [2026-05-24 08:56:00] Validation | Batch 240/1463 | Loss: 0.8752 | LM_LOSS: 0.3649 | LB_LOSS: 1.0205 |
| [2026-05-24 08:56:02] Validation | Batch 250/1463 | Loss: 0.8740 | LM_LOSS: 0.3637 | LB_LOSS: 1.0205 |
| [2026-05-24 08:56:04] Validation | Batch 260/1463 | Loss: 0.8758 | LM_LOSS: 0.3655 | LB_LOSS: 1.0207 |
| [2026-05-24 08:56:06] Validation | Batch 270/1463 | Loss: 0.8747 | LM_LOSS: 0.3643 | LB_LOSS: 1.0207 |
| [2026-05-24 08:56:07] Validation | Batch 280/1463 | Loss: 0.8757 | LM_LOSS: 0.3654 | LB_LOSS: 1.0207 |
| [2026-05-24 08:56:09] Validation | Batch 290/1463 | Loss: 0.8747 | LM_LOSS: 0.3644 | LB_LOSS: 1.0207 |
| [2026-05-24 08:56:11] Validation | Batch 300/1463 | Loss: 0.8756 | LM_LOSS: 0.3652 | LB_LOSS: 1.0208 |
| [2026-05-24 08:56:13] Validation | Batch 310/1463 | Loss: 0.8764 | LM_LOSS: 0.3660 | LB_LOSS: 1.0208 |
| [2026-05-24 08:56:14] Validation | Batch 320/1463 | Loss: 0.8752 | LM_LOSS: 0.3648 | LB_LOSS: 1.0206 |
| [2026-05-24 08:56:16] Validation | Batch 330/1463 | Loss: 0.8753 | LM_LOSS: 0.3650 | LB_LOSS: 1.0206 |
| [2026-05-24 08:56:18] Validation | Batch 340/1463 | Loss: 0.8748 | LM_LOSS: 0.3644 | LB_LOSS: 1.0207 |
| [2026-05-24 08:56:20] Validation | Batch 350/1463 | Loss: 0.8754 | LM_LOSS: 0.3651 | LB_LOSS: 1.0206 |
| [2026-05-24 08:56:22] Validation | Batch 360/1463 | Loss: 0.8755 | LM_LOSS: 0.3651 | LB_LOSS: 1.0207 |
| [2026-05-24 08:56:23] Validation | Batch 370/1463 | Loss: 0.8753 | LM_LOSS: 0.3649 | LB_LOSS: 1.0207 |
| [2026-05-24 08:56:25] Validation | Batch 380/1463 | Loss: 0.8752 | LM_LOSS: 0.3649 | LB_LOSS: 1.0206 |
| [2026-05-24 08:56:27] Validation | Batch 390/1463 | Loss: 0.8759 | LM_LOSS: 0.3656 | LB_LOSS: 1.0206 |
| [2026-05-24 08:56:28] Validation | Batch 400/1463 | Loss: 0.8757 | LM_LOSS: 0.3653 | LB_LOSS: 1.0207 |
| [2026-05-24 08:56:30] Validation | Batch 410/1463 | Loss: 0.8753 | LM_LOSS: 0.3650 | LB_LOSS: 1.0208 |
| [2026-05-24 08:56:32] Validation | Batch 420/1463 | Loss: 0.8753 | LM_LOSS: 0.3650 | LB_LOSS: 1.0208 |
| [2026-05-24 08:56:34] Validation | Batch 430/1463 | Loss: 0.8750 | LM_LOSS: 0.3646 | LB_LOSS: 1.0208 |
| [2026-05-24 08:56:36] Validation | Batch 440/1463 | Loss: 0.8752 | LM_LOSS: 0.3647 | LB_LOSS: 1.0209 |
| [2026-05-24 08:56:37] Validation | Batch 450/1463 | Loss: 0.8750 | LM_LOSS: 0.3646 | LB_LOSS: 1.0209 |
| [2026-05-24 08:56:39] Validation | Batch 460/1463 | Loss: 0.8749 | LM_LOSS: 0.3645 | LB_LOSS: 1.0209 |
| [2026-05-24 08:56:41] Validation | Batch 470/1463 | Loss: 0.8756 | LM_LOSS: 0.3652 | LB_LOSS: 1.0209 |
| [2026-05-24 08:56:43] Validation | Batch 480/1463 | Loss: 0.8757 | LM_LOSS: 0.3653 | LB_LOSS: 1.0208 |
| [2026-05-24 08:56:45] Validation | Batch 490/1463 | Loss: 0.8755 | LM_LOSS: 0.3651 | LB_LOSS: 1.0208 |
| [2026-05-24 08:56:47] Validation | Batch 500/1463 | Loss: 0.8753 | LM_LOSS: 0.3649 | LB_LOSS: 1.0208 |
| [2026-05-24 08:56:49] Validation | Batch 510/1463 | Loss: 0.8748 | LM_LOSS: 0.3644 | LB_LOSS: 1.0208 |
| [2026-05-24 08:56:51] Validation | Batch 520/1463 | Loss: 0.8744 | LM_LOSS: 0.3640 | LB_LOSS: 1.0209 |
| [2026-05-24 08:56:52] Validation | Batch 530/1463 | Loss: 0.8747 | LM_LOSS: 0.3643 | LB_LOSS: 1.0208 |
| [2026-05-24 08:56:54] Validation | Batch 540/1463 | Loss: 0.8751 | LM_LOSS: 0.3647 | LB_LOSS: 1.0209 |
| [2026-05-24 08:56:55] Validation | Batch 550/1463 | Loss: 0.8747 | LM_LOSS: 0.3643 | LB_LOSS: 1.0209 |
| [2026-05-24 08:56:57] Validation | Batch 560/1463 | Loss: 0.8751 | LM_LOSS: 0.3646 | LB_LOSS: 1.0210 |
| [2026-05-24 08:56:59] Validation | Batch 570/1463 | Loss: 0.8751 | LM_LOSS: 0.3647 | LB_LOSS: 1.0209 |
| [2026-05-24 08:57:01] Validation | Batch 580/1463 | Loss: 0.8747 | LM_LOSS: 0.3643 | LB_LOSS: 1.0209 |
| [2026-05-24 08:57:03] Validation | Batch 590/1463 | Loss: 0.8747 | LM_LOSS: 0.3642 | LB_LOSS: 1.0210 |
| [2026-05-24 08:57:05] Validation | Batch 600/1463 | Loss: 0.8750 | LM_LOSS: 0.3644 | LB_LOSS: 1.0210 |
| [2026-05-24 08:57:07] Validation | Batch 610/1463 | Loss: 0.8751 | LM_LOSS: 0.3645 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:09] Validation | Batch 620/1463 | Loss: 0.8743 | LM_LOSS: 0.3638 | LB_LOSS: 1.0210 |
| [2026-05-24 08:57:11] Validation | Batch 630/1463 | Loss: 0.8738 | LM_LOSS: 0.3632 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:13] Validation | Batch 640/1463 | Loss: 0.8736 | LM_LOSS: 0.3631 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:14] Validation | Batch 650/1463 | Loss: 0.8732 | LM_LOSS: 0.3626 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:16] Validation | Batch 660/1463 | Loss: 0.8726 | LM_LOSS: 0.3621 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:18] Validation | Batch 670/1463 | Loss: 0.8722 | LM_LOSS: 0.3617 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:19] Validation | Batch 680/1463 | Loss: 0.8722 | LM_LOSS: 0.3617 | LB_LOSS: 1.0210 |
| [2026-05-24 08:57:21] Validation | Batch 690/1463 | Loss: 0.8726 | LM_LOSS: 0.3621 | LB_LOSS: 1.0210 |
| [2026-05-24 08:57:23] Validation | Batch 700/1463 | Loss: 0.8725 | LM_LOSS: 0.3620 | LB_LOSS: 1.0210 |
| [2026-05-24 08:57:24] Validation | Batch 710/1463 | Loss: 0.8728 | LM_LOSS: 0.3623 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:26] Validation | Batch 720/1463 | Loss: 0.8736 | LM_LOSS: 0.3630 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:28] Validation | Batch 730/1463 | Loss: 0.8734 | LM_LOSS: 0.3629 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:29] Validation | Batch 740/1463 | Loss: 0.8730 | LM_LOSS: 0.3624 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:31] Validation | Batch 750/1463 | Loss: 0.8729 | LM_LOSS: 0.3623 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:33] Validation | Batch 760/1463 | Loss: 0.8726 | LM_LOSS: 0.3621 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:34] Validation | Batch 770/1463 | Loss: 0.8725 | LM_LOSS: 0.3619 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:36] Validation | Batch 780/1463 | Loss: 0.8722 | LM_LOSS: 0.3616 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:37] Validation | Batch 790/1463 | Loss: 0.8724 | LM_LOSS: 0.3618 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:39] Validation | Batch 800/1463 | Loss: 0.8723 | LM_LOSS: 0.3618 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:40] Validation | Batch 810/1463 | Loss: 0.8719 | LM_LOSS: 0.3614 | LB_LOSS: 1.0210 |
| [2026-05-24 08:57:42] Validation | Batch 820/1463 | Loss: 0.8721 | LM_LOSS: 0.3616 | LB_LOSS: 1.0210 |
| [2026-05-24 08:57:44] Validation | Batch 830/1463 | Loss: 0.8722 | LM_LOSS: 0.3617 | LB_LOSS: 1.0210 |
| [2026-05-24 08:57:46] Validation | Batch 840/1463 | Loss: 0.8722 | LM_LOSS: 0.3616 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:48] Validation | Batch 850/1463 | Loss: 0.8725 | LM_LOSS: 0.3620 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:50] Validation | Batch 860/1463 | Loss: 0.8725 | LM_LOSS: 0.3620 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:52] Validation | Batch 870/1463 | Loss: 0.8727 | LM_LOSS: 0.3622 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:53] Validation | Batch 880/1463 | Loss: 0.8721 | LM_LOSS: 0.3615 | LB_LOSS: 1.0211 |
| [2026-05-24 08:57:55] Validation | Batch 890/1463 | Loss: 0.8721 | LM_LOSS: 0.3616 | LB_LOSS: 1.0210 |
| [2026-05-24 08:57:57] Validation | Batch 900/1463 | Loss: 0.8719 | LM_LOSS: 0.3613 | LB_LOSS: 1.0210 |
| [2026-05-24 08:57:59] Validation | Batch 910/1463 | Loss: 0.8718 | LM_LOSS: 0.3612 | LB_LOSS: 1.0211 |
| [2026-05-24 08:58:01] Validation | Batch 920/1463 | Loss: 0.8720 | LM_LOSS: 0.3614 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:03] Validation | Batch 930/1463 | Loss: 0.8717 | LM_LOSS: 0.3611 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:04] Validation | Batch 940/1463 | Loss: 0.8714 | LM_LOSS: 0.3609 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:06] Validation | Batch 950/1463 | Loss: 0.8717 | LM_LOSS: 0.3612 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:08] Validation | Batch 960/1463 | Loss: 0.8718 | LM_LOSS: 0.3613 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:10] Validation | Batch 970/1463 | Loss: 0.8720 | LM_LOSS: 0.3615 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:12] Validation | Batch 980/1463 | Loss: 0.8723 | LM_LOSS: 0.3618 | LB_LOSS: 1.0209 |
| [2026-05-24 08:58:14] Validation | Batch 990/1463 | Loss: 0.8726 | LM_LOSS: 0.3621 | LB_LOSS: 1.0209 |
| [2026-05-24 08:58:16] Validation | Batch 1000/1463 | Loss: 0.8732 | LM_LOSS: 0.3627 | LB_LOSS: 1.0209 |
| [2026-05-24 08:58:18] Validation | Batch 1010/1463 | Loss: 0.8732 | LM_LOSS: 0.3627 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:19] Validation | Batch 1020/1463 | Loss: 0.8733 | LM_LOSS: 0.3627 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:22] Validation | Batch 1030/1463 | Loss: 0.8738 | LM_LOSS: 0.3632 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:23] Validation | Batch 1040/1463 | Loss: 0.8733 | LM_LOSS: 0.3628 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:25] Validation | Batch 1050/1463 | Loss: 0.8731 | LM_LOSS: 0.3626 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:27] Validation | Batch 1060/1463 | Loss: 0.8731 | LM_LOSS: 0.3626 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:29] Validation | Batch 1070/1463 | Loss: 0.8731 | LM_LOSS: 0.3626 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:31] Validation | Batch 1080/1463 | Loss: 0.8729 | LM_LOSS: 0.3624 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:32] Validation | Batch 1090/1463 | Loss: 0.8729 | LM_LOSS: 0.3624 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:34] Validation | Batch 1100/1463 | Loss: 0.8728 | LM_LOSS: 0.3624 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:36] Validation | Batch 1110/1463 | Loss: 0.8729 | LM_LOSS: 0.3624 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:37] Validation | Batch 1120/1463 | Loss: 0.8727 | LM_LOSS: 0.3622 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:40] Validation | Batch 1130/1463 | Loss: 0.8724 | LM_LOSS: 0.3619 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:41] Validation | Batch 1140/1463 | Loss: 0.8726 | LM_LOSS: 0.3621 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:43] Validation | Batch 1150/1463 | Loss: 0.8726 | LM_LOSS: 0.3622 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:45] Validation | Batch 1160/1463 | Loss: 0.8726 | LM_LOSS: 0.3622 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:47] Validation | Batch 1170/1463 | Loss: 0.8726 | LM_LOSS: 0.3621 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:49] Validation | Batch 1180/1463 | Loss: 0.8726 | LM_LOSS: 0.3621 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:51] Validation | Batch 1190/1463 | Loss: 0.8728 | LM_LOSS: 0.3624 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:53] Validation | Batch 1200/1463 | Loss: 0.8729 | LM_LOSS: 0.3624 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:54] Validation | Batch 1210/1463 | Loss: 0.8732 | LM_LOSS: 0.3627 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:56] Validation | Batch 1220/1463 | Loss: 0.8736 | LM_LOSS: 0.3631 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:58] Validation | Batch 1230/1463 | Loss: 0.8736 | LM_LOSS: 0.3631 | LB_LOSS: 1.0210 |
| [2026-05-24 08:58:59] Validation | Batch 1240/1463 | Loss: 0.8739 | LM_LOSS: 0.3634 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:01] Validation | Batch 1250/1463 | Loss: 0.8740 | LM_LOSS: 0.3635 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:03] Validation | Batch 1260/1463 | Loss: 0.8739 | LM_LOSS: 0.3634 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:05] Validation | Batch 1270/1463 | Loss: 0.8737 | LM_LOSS: 0.3632 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:07] Validation | Batch 1280/1463 | Loss: 0.8735 | LM_LOSS: 0.3630 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:09] Validation | Batch 1290/1463 | Loss: 0.8735 | LM_LOSS: 0.3630 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:11] Validation | Batch 1300/1463 | Loss: 0.8732 | LM_LOSS: 0.3627 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:13] Validation | Batch 1310/1463 | Loss: 0.8731 | LM_LOSS: 0.3626 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:14] Validation | Batch 1320/1463 | Loss: 0.8732 | LM_LOSS: 0.3627 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:16] Validation | Batch 1330/1463 | Loss: 0.8731 | LM_LOSS: 0.3627 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:17] Validation | Batch 1340/1463 | Loss: 0.8734 | LM_LOSS: 0.3629 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:19] Validation | Batch 1350/1463 | Loss: 0.8734 | LM_LOSS: 0.3629 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:22] Validation | Batch 1360/1463 | Loss: 0.8737 | LM_LOSS: 0.3632 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:23] Validation | Batch 1370/1463 | Loss: 0.8741 | LM_LOSS: 0.3636 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:25] Validation | Batch 1380/1463 | Loss: 0.8738 | LM_LOSS: 0.3633 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:27] Validation | Batch 1390/1463 | Loss: 0.8737 | LM_LOSS: 0.3633 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:29] Validation | Batch 1400/1463 | Loss: 0.8740 | LM_LOSS: 0.3636 | LB_LOSS: 1.0209 |
| [2026-05-24 08:59:30] Validation | Batch 1410/1463 | Loss: 0.8742 | LM_LOSS: 0.3637 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:32] Validation | Batch 1420/1463 | Loss: 0.8743 | LM_LOSS: 0.3638 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:34] Validation | Batch 1430/1463 | Loss: 0.8744 | LM_LOSS: 0.3639 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:36] Validation | Batch 1440/1463 | Loss: 0.8748 | LM_LOSS: 0.3643 | LB_LOSS: 1.0210 |
| [2026-05-24 08:59:38] Validation | Batch 1450/1463 | Loss: 0.8745 | LM_LOSS: 0.3641 | LB_LOSS: 1.0209 |
| [2026-05-24 08:59:40] Validation | Batch 1460/1463 | Loss: 0.8748 | LM_LOSS: 0.3644 | LB_LOSS: 1.0209 |
| [2026-05-24 08:59:40] Validation | Batch 1463/1463 | Loss: 0.8747 | LM_LOSS: 0.3642 | LB_LOSS: 1.0209 |
| [2026-05-24 08:59:40] Validation | Loss: 0.8747 | LM_LOSS: 0.3642 | LB_LOSS: 1.0209 | PPL: 1.44 | Time: 264.30s |
| [2026-05-24 08:59:51] Epoch 2 | Step 8010 | Loss: 0.8262 | LM: 0.3127 | LB: 1.0279 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:00:02] Epoch 2 | Step 8020 | Loss: 0.8263 | LM: 0.3128 | LB: 1.0279 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:00:12] Epoch 2 | Step 8030 | Loss: 0.8263 | LM: 0.3128 | LB: 1.0279 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:00:23] Epoch 2 | Step 8040 | Loss: 0.8264 | LM: 0.3129 | LB: 1.0279 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:00:34] Epoch 2 | Step 8050 | Loss: 0.8263 | LM: 0.3128 | LB: 1.0278 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:00:44] Epoch 2 | Step 8060 | Loss: 0.8263 | LM: 0.3127 | LB: 1.0278 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:00:55] Epoch 2 | Step 8070 | Loss: 0.8264 | LM: 0.3127 | LB: 1.0278 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:01:06] Epoch 2 | Step 8080 | Loss: 0.8264 | LM: 0.3127 | LB: 1.0278 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:01:16] Epoch 2 | Step 8090 | Loss: 0.8264 | LM: 0.3127 | LB: 1.0278 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:01:27] Epoch 2 | Step 8100 | Loss: 0.8264 | LM: 0.3127 | LB: 1.0277 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:01:38] Epoch 2 | Step 8110 | Loss: 0.8264 | LM: 0.3128 | LB: 1.0277 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:01:48] Epoch 2 | Step 8120 | Loss: 0.8264 | LM: 0.3128 | LB: 1.0277 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:01:59] Epoch 2 | Step 8130 | Loss: 0.8265 | LM: 0.3128 | LB: 1.0277 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:02:10] Epoch 2 | Step 8140 | Loss: 0.8266 | LM: 0.3129 | LB: 1.0277 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:02:21] Epoch 2 | Step 8150 | Loss: 0.8266 | LM: 0.3129 | LB: 1.0276 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:02:31] Epoch 2 | Step 8160 | Loss: 0.8266 | LM: 0.3129 | LB: 1.0276 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:02:42] Epoch 2 | Step 8170 | Loss: 0.8267 | LM: 0.3132 | LB: 1.0276 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:02:53] Epoch 2 | Step 8180 | Loss: 0.8267 | LM: 0.3134 | LB: 1.0276 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:03:04] Epoch 2 | Step 8190 | Loss: 0.8268 | LM: 0.3135 | LB: 1.0276 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:03:15] Epoch 2 | Step 8200 | Loss: 0.8269 | LM: 0.3135 | LB: 1.0276 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:03:26] Epoch 2 | Step 8210 | Loss: 0.8270 | LM: 0.3137 | LB: 1.0276 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:03:37] Epoch 2 | Step 8220 | Loss: 0.8269 | LM: 0.3136 | LB: 1.0275 | CL0: 3.7 | CL1: 5.2 | HR0: 0.270/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:03:47] Epoch 2 | Step 8230 | Loss: 0.8270 | LM: 0.3136 | LB: 1.0275 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:03:58] Epoch 2 | Step 8240 | Loss: 0.8270 | LM: 0.3136 | LB: 1.0275 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:04:09] Epoch 2 | Step 8250 | Loss: 0.8270 | LM: 0.3138 | LB: 1.0275 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.235 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:04:20] Epoch 2 | Step 8260 | Loss: 0.8271 | LM: 0.3139 | LB: 1.0275 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:04:31] Epoch 2 | Step 8270 | Loss: 0.8272 | LM: 0.3139 | LB: 1.0275 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:04:42] Epoch 2 | Step 8280 | Loss: 0.8272 | LM: 0.3139 | LB: 1.0275 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:04:53] Epoch 2 | Step 8290 | Loss: 0.8273 | LM: 0.3140 | LB: 1.0275 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:05:04] Epoch 2 | Step 8300 | Loss: 0.8273 | LM: 0.3140 | LB: 1.0274 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:05:15] Epoch 2 | Step 8310 | Loss: 0.8273 | LM: 0.3142 | LB: 1.0274 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:05:26] Epoch 2 | Step 8320 | Loss: 0.8273 | LM: 0.3143 | LB: 1.0274 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:05:37] Epoch 2 | Step 8330 | Loss: 0.8274 | LM: 0.3143 | LB: 1.0274 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:05:48] Epoch 2 | Step 8340 | Loss: 0.8273 | LM: 0.3142 | LB: 1.0273 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:05:59] Epoch 2 | Step 8350 | Loss: 0.8274 | LM: 0.3142 | LB: 1.0273 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:06:11] Epoch 2 | Step 8360 | Loss: 0.8275 | LM: 0.3145 | LB: 1.0273 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:06:22] Epoch 2 | Step 8370 | Loss: 0.8276 | LM: 0.3144 | LB: 1.0273 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:06:33] Epoch 2 | Step 8380 | Loss: 0.8275 | LM: 0.3143 | LB: 1.0273 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:06:44] Epoch 2 | Step 8390 | Loss: 0.8276 | LM: 0.3143 | LB: 1.0272 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:06:55] Epoch 2 | Step 8400 | Loss: 0.8276 | LM: 0.3144 | LB: 1.0272 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:07:06] Epoch 2 | Step 8410 | Loss: 0.8276 | LM: 0.3142 | LB: 1.0272 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:07:18] Epoch 2 | Step 8420 | Loss: 0.8276 | LM: 0.3143 | LB: 1.0272 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:07:29] Epoch 2 | Step 8430 | Loss: 0.8277 | LM: 0.3144 | LB: 1.0272 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:07:40] Epoch 2 | Step 8440 | Loss: 0.8278 | LM: 0.3146 | LB: 1.0272 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:07:51] Epoch 2 | Step 8450 | Loss: 0.8278 | LM: 0.3147 | LB: 1.0271 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:08:02] Epoch 2 | Step 8460 | Loss: 0.8278 | LM: 0.3146 | LB: 1.0271 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:08:13] Epoch 2 | Step 8470 | Loss: 0.8277 | LM: 0.3145 | LB: 1.0271 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:08:24] Epoch 2 | Step 8480 | Loss: 0.8277 | LM: 0.3143 | LB: 1.0271 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:08:35] Epoch 2 | Step 8490 | Loss: 0.8278 | LM: 0.3145 | LB: 1.0271 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:08:46] Epoch 2 | Step 8500 | Loss: 0.8278 | LM: 0.3145 | LB: 1.0270 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:08:57] Epoch 2 | Step 8510 | Loss: 0.8279 | LM: 0.3147 | LB: 1.0270 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:09:07] Epoch 2 | Step 8520 | Loss: 0.8280 | LM: 0.3148 | LB: 1.0270 | CL0: 3.7 | CL1: 5.2 | HR0: 0.269/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:09:18] Epoch 2 | Step 8530 | Loss: 0.8280 | LM: 0.3150 | LB: 1.0270 | CL0: 3.7 | CL1: 5.2 | HR0: 0.268/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:09:29] Epoch 2 | Step 8540 | Loss: 0.8280 | LM: 0.3148 | LB: 1.0270 | CL0: 3.7 | CL1: 5.2 | HR0: 0.268/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:09:40] Epoch 2 | Step 8550 | Loss: 0.8281 | LM: 0.3148 | LB: 1.0269 | CL0: 3.7 | CL1: 5.2 | HR0: 0.268/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:09:51] Epoch 2 | Step 8560 | Loss: 0.8280 | LM: 0.3148 | LB: 1.0269 | CL0: 3.7 | CL1: 5.2 | HR0: 0.268/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:10:01] Epoch 2 | Step 8570 | Loss: 0.8280 | LM: 0.3147 | LB: 1.0270 | CL0: 3.7 | CL1: 5.2 | HR0: 0.268/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:10:12] Epoch 2 | Step 8580 | Loss: 0.8280 | LM: 0.3147 | LB: 1.0269 | CL0: 3.7 | CL1: 5.2 | HR0: 0.268/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:10:22] Epoch 2 | Step 8590 | Loss: 0.8281 | LM: 0.3149 | LB: 1.0269 | CL0: 3.7 | CL1: 5.2 | HR0: 0.268/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:10:33] Epoch 2 | Step 8600 | Loss: 0.8281 | LM: 0.3149 | LB: 1.0269 | CL0: 3.7 | CL1: 5.2 | HR0: 0.268/SR0: 0.234 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:10:44] Epoch 2 | Step 8610 | Loss: 0.8281 | LM: 0.3149 | LB: 1.0269 | CL0: 3.7 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:10:55] Epoch 2 | Step 8620 | Loss: 0.8282 | LM: 0.3151 | LB: 1.0269 | CL0: 3.7 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:11:06] Epoch 2 | Step 8630 | Loss: 0.8282 | LM: 0.3151 | LB: 1.0268 | CL0: 3.7 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:11:17] Epoch 2 | Step 8640 | Loss: 0.8282 | LM: 0.3150 | LB: 1.0268 | CL0: 3.7 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:11:28] Epoch 2 | Step 8650 | Loss: 0.8283 | LM: 0.3150 | LB: 1.0268 | CL0: 3.7 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:11:39] Epoch 2 | Step 8660 | Loss: 0.8282 | LM: 0.3150 | LB: 1.0268 | CL0: 3.8 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:11:51] Epoch 2 | Step 8670 | Loss: 0.8282 | LM: 0.3149 | LB: 1.0268 | CL0: 3.8 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:12:02] Epoch 2 | Step 8680 | Loss: 0.8283 | LM: 0.3149 | LB: 1.0268 | CL0: 3.8 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:12:13] Epoch 2 | Step 8690 | Loss: 0.8283 | LM: 0.3149 | LB: 1.0267 | CL0: 3.8 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:12:24] Epoch 2 | Step 8700 | Loss: 0.8283 | LM: 0.3152 | LB: 1.0267 | CL0: 3.8 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:12:35] Epoch 2 | Step 8710 | Loss: 0.8283 | LM: 0.3152 | LB: 1.0267 | CL0: 3.8 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:12:47] Epoch 2 | Step 8720 | Loss: 0.8284 | LM: 0.3153 | LB: 1.0267 | CL0: 3.8 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:12:58] Epoch 2 | Step 8730 | Loss: 0.8284 | LM: 0.3155 | LB: 1.0267 | CL0: 3.8 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:13:09] Epoch 2 | Step 8740 | Loss: 0.8285 | LM: 0.3156 | LB: 1.0267 | CL0: 3.8 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:13:20] Epoch 2 | Step 8750 | Loss: 0.8285 | LM: 0.3155 | LB: 1.0267 | CL0: 3.8 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:13:32] Epoch 2 | Step 8760 | Loss: 0.8286 | LM: 0.3156 | LB: 1.0267 | CL0: 3.8 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:13:43] Epoch 2 | Step 8770 | Loss: 0.8287 | LM: 0.3157 | LB: 1.0266 | CL0: 3.8 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:13:54] Epoch 2 | Step 8780 | Loss: 0.8287 | LM: 0.3156 | LB: 1.0266 | CL0: 3.8 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:14:05] Epoch 2 | Step 8790 | Loss: 0.8288 | LM: 0.3157 | LB: 1.0266 | CL0: 3.8 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:14:16] Epoch 2 | Step 8800 | Loss: 0.8289 | LM: 0.3158 | LB: 1.0266 | CL0: 3.8 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:14:27] Epoch 2 | Step 8810 | Loss: 0.8288 | LM: 0.3159 | LB: 1.0266 | CL0: 3.8 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:14:38] Epoch 2 | Step 8820 | Loss: 0.8289 | LM: 0.3161 | LB: 1.0266 | CL0: 3.8 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:14:49] Epoch 2 | Step 8830 | Loss: 0.8289 | LM: 0.3163 | LB: 1.0266 | CL0: 3.8 | CL1: 5.2 | HR0: 0.268/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:15:01] Epoch 2 | Step 8840 | Loss: 0.8289 | LM: 0.3164 | LB: 1.0265 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:15:12] Epoch 2 | Step 8850 | Loss: 0.8290 | LM: 0.3164 | LB: 1.0265 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:15:23] Epoch 2 | Step 8860 | Loss: 0.8290 | LM: 0.3165 | LB: 1.0265 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:15:34] Epoch 2 | Step 8870 | Loss: 0.8290 | LM: 0.3165 | LB: 1.0265 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:15:46] Epoch 2 | Step 8880 | Loss: 0.8291 | LM: 0.3166 | LB: 1.0265 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:15:57] Epoch 2 | Step 8890 | Loss: 0.8290 | LM: 0.3167 | LB: 1.0265 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:16:09] Epoch 2 | Step 8900 | Loss: 0.8291 | LM: 0.3166 | LB: 1.0264 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:16:21] Epoch 2 | Step 8910 | Loss: 0.8291 | LM: 0.3169 | LB: 1.0264 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:16:33] Epoch 2 | Step 8920 | Loss: 0.8291 | LM: 0.3169 | LB: 1.0264 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:16:44] Epoch 2 | Step 8930 | Loss: 0.8290 | LM: 0.3169 | LB: 1.0264 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:16:56] Epoch 2 | Step 8940 | Loss: 0.8290 | LM: 0.3168 | LB: 1.0264 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:17:07] Epoch 2 | Step 8950 | Loss: 0.8290 | LM: 0.3168 | LB: 1.0263 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:17:19] Epoch 2 | Step 8960 | Loss: 0.8290 | LM: 0.3168 | LB: 1.0263 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:17:31] Epoch 2 | Step 8970 | Loss: 0.8291 | LM: 0.3170 | LB: 1.0263 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:17:42] Epoch 2 | Step 8980 | Loss: 0.8292 | LM: 0.3171 | LB: 1.0263 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:17:54] Epoch 2 | Step 8990 | Loss: 0.8292 | LM: 0.3171 | LB: 1.0263 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.233 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:18:06] Epoch 2 | Step 9000 | Loss: 0.8292 | LM: 0.3170 | LB: 1.0263 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:18:10] Checkpoint saved: outputs/2026-05-24/N_6.0/checkpoints/checkpoint_step_9000.pt |
| [2026-05-24 09:18:18] Validation | Batch 10/1463 | Loss: 0.8312 | LM_LOSS: 0.3241 | LB_LOSS: 1.0143 |
| [2026-05-24 09:18:19] Validation | Batch 20/1463 | Loss: 0.8427 | LM_LOSS: 0.3344 | LB_LOSS: 1.0167 |
| [2026-05-24 09:18:21] Validation | Batch 30/1463 | Loss: 0.8470 | LM_LOSS: 0.3383 | LB_LOSS: 1.0175 |
| [2026-05-24 09:18:23] Validation | Batch 40/1463 | Loss: 0.8581 | LM_LOSS: 0.3488 | LB_LOSS: 1.0185 |
| [2026-05-24 09:18:24] Validation | Batch 50/1463 | Loss: 0.8655 | LM_LOSS: 0.3566 | LB_LOSS: 1.0179 |
| [2026-05-24 09:18:27] Validation | Batch 60/1463 | Loss: 0.8669 | LM_LOSS: 0.3579 | LB_LOSS: 1.0180 |
| [2026-05-24 09:18:29] Validation | Batch 70/1463 | Loss: 0.8669 | LM_LOSS: 0.3579 | LB_LOSS: 1.0180 |
| [2026-05-24 09:18:31] Validation | Batch 80/1463 | Loss: 0.8690 | LM_LOSS: 0.3600 | LB_LOSS: 1.0181 |
| [2026-05-24 09:18:33] Validation | Batch 90/1463 | Loss: 0.8685 | LM_LOSS: 0.3595 | LB_LOSS: 1.0180 |
| [2026-05-24 09:18:34] Validation | Batch 100/1463 | Loss: 0.8685 | LM_LOSS: 0.3595 | LB_LOSS: 1.0180 |
| [2026-05-24 09:18:36] Validation | Batch 110/1463 | Loss: 0.8663 | LM_LOSS: 0.3572 | LB_LOSS: 1.0183 |
| [2026-05-24 09:18:38] Validation | Batch 120/1463 | Loss: 0.8680 | LM_LOSS: 0.3588 | LB_LOSS: 1.0183 |
| [2026-05-24 09:18:39] Validation | Batch 130/1463 | Loss: 0.8712 | LM_LOSS: 0.3620 | LB_LOSS: 1.0183 |
| [2026-05-24 09:18:41] Validation | Batch 140/1463 | Loss: 0.8725 | LM_LOSS: 0.3634 | LB_LOSS: 1.0183 |
| [2026-05-24 09:18:43] Validation | Batch 150/1463 | Loss: 0.8713 | LM_LOSS: 0.3621 | LB_LOSS: 1.0184 |
| [2026-05-24 09:18:45] Validation | Batch 160/1463 | Loss: 0.8724 | LM_LOSS: 0.3632 | LB_LOSS: 1.0183 |
| [2026-05-24 09:18:47] Validation | Batch 170/1463 | Loss: 0.8719 | LM_LOSS: 0.3627 | LB_LOSS: 1.0183 |
| [2026-05-24 09:18:49] Validation | Batch 180/1463 | Loss: 0.8724 | LM_LOSS: 0.3632 | LB_LOSS: 1.0184 |
| [2026-05-24 09:18:51] Validation | Batch 190/1463 | Loss: 0.8732 | LM_LOSS: 0.3639 | LB_LOSS: 1.0184 |
| [2026-05-24 09:18:53] Validation | Batch 200/1463 | Loss: 0.8727 | LM_LOSS: 0.3634 | LB_LOSS: 1.0185 |
| [2026-05-24 09:18:54] Validation | Batch 210/1463 | Loss: 0.8732 | LM_LOSS: 0.3640 | LB_LOSS: 1.0185 |
| [2026-05-24 09:18:56] Validation | Batch 220/1463 | Loss: 0.8727 | LM_LOSS: 0.3634 | LB_LOSS: 1.0185 |
| [2026-05-24 09:18:58] Validation | Batch 230/1463 | Loss: 0.8745 | LM_LOSS: 0.3653 | LB_LOSS: 1.0184 |
| [2026-05-24 09:19:00] Validation | Batch 240/1463 | Loss: 0.8756 | LM_LOSS: 0.3664 | LB_LOSS: 1.0183 |
| [2026-05-24 09:19:02] Validation | Batch 250/1463 | Loss: 0.8744 | LM_LOSS: 0.3653 | LB_LOSS: 1.0184 |
| [2026-05-24 09:19:04] Validation | Batch 260/1463 | Loss: 0.8763 | LM_LOSS: 0.3670 | LB_LOSS: 1.0185 |
| [2026-05-24 09:19:06] Validation | Batch 270/1463 | Loss: 0.8751 | LM_LOSS: 0.3658 | LB_LOSS: 1.0185 |
| [2026-05-24 09:19:07] Validation | Batch 280/1463 | Loss: 0.8762 | LM_LOSS: 0.3670 | LB_LOSS: 1.0185 |
| [2026-05-24 09:19:09] Validation | Batch 290/1463 | Loss: 0.8752 | LM_LOSS: 0.3660 | LB_LOSS: 1.0185 |
| [2026-05-24 09:19:11] Validation | Batch 300/1463 | Loss: 0.8761 | LM_LOSS: 0.3668 | LB_LOSS: 1.0186 |
| [2026-05-24 09:19:13] Validation | Batch 310/1463 | Loss: 0.8768 | LM_LOSS: 0.3675 | LB_LOSS: 1.0186 |
| [2026-05-24 09:19:14] Validation | Batch 320/1463 | Loss: 0.8756 | LM_LOSS: 0.3663 | LB_LOSS: 1.0185 |
| [2026-05-24 09:19:16] Validation | Batch 330/1463 | Loss: 0.8757 | LM_LOSS: 0.3664 | LB_LOSS: 1.0185 |
| [2026-05-24 09:19:18] Validation | Batch 340/1463 | Loss: 0.8752 | LM_LOSS: 0.3659 | LB_LOSS: 1.0185 |
| [2026-05-24 09:19:20] Validation | Batch 350/1463 | Loss: 0.8758 | LM_LOSS: 0.3665 | LB_LOSS: 1.0185 |
| [2026-05-24 09:19:22] Validation | Batch 360/1463 | Loss: 0.8758 | LM_LOSS: 0.3666 | LB_LOSS: 1.0185 |
| [2026-05-24 09:19:23] Validation | Batch 370/1463 | Loss: 0.8755 | LM_LOSS: 0.3663 | LB_LOSS: 1.0185 |
| [2026-05-24 09:19:25] Validation | Batch 380/1463 | Loss: 0.8753 | LM_LOSS: 0.3661 | LB_LOSS: 1.0185 |
| [2026-05-24 09:19:27] Validation | Batch 390/1463 | Loss: 0.8760 | LM_LOSS: 0.3668 | LB_LOSS: 1.0185 |
| [2026-05-24 09:19:28] Validation | Batch 400/1463 | Loss: 0.8759 | LM_LOSS: 0.3666 | LB_LOSS: 1.0185 |
| [2026-05-24 09:19:30] Validation | Batch 410/1463 | Loss: 0.8756 | LM_LOSS: 0.3663 | LB_LOSS: 1.0186 |
| [2026-05-24 09:19:32] Validation | Batch 420/1463 | Loss: 0.8756 | LM_LOSS: 0.3663 | LB_LOSS: 1.0186 |
| [2026-05-24 09:19:34] Validation | Batch 430/1463 | Loss: 0.8753 | LM_LOSS: 0.3660 | LB_LOSS: 1.0187 |
| [2026-05-24 09:19:36] Validation | Batch 440/1463 | Loss: 0.8755 | LM_LOSS: 0.3662 | LB_LOSS: 1.0187 |
| [2026-05-24 09:19:37] Validation | Batch 450/1463 | Loss: 0.8754 | LM_LOSS: 0.3660 | LB_LOSS: 1.0187 |
| [2026-05-24 09:19:39] Validation | Batch 460/1463 | Loss: 0.8752 | LM_LOSS: 0.3659 | LB_LOSS: 1.0187 |
| [2026-05-24 09:19:41] Validation | Batch 470/1463 | Loss: 0.8760 | LM_LOSS: 0.3667 | LB_LOSS: 1.0187 |
| [2026-05-24 09:19:43] Validation | Batch 480/1463 | Loss: 0.8759 | LM_LOSS: 0.3666 | LB_LOSS: 1.0186 |
| [2026-05-24 09:19:45] Validation | Batch 490/1463 | Loss: 0.8756 | LM_LOSS: 0.3663 | LB_LOSS: 1.0186 |
| [2026-05-24 09:19:47] Validation | Batch 500/1463 | Loss: 0.8754 | LM_LOSS: 0.3661 | LB_LOSS: 1.0186 |
| [2026-05-24 09:19:49] Validation | Batch 510/1463 | Loss: 0.8749 | LM_LOSS: 0.3656 | LB_LOSS: 1.0186 |
| [2026-05-24 09:19:51] Validation | Batch 520/1463 | Loss: 0.8745 | LM_LOSS: 0.3652 | LB_LOSS: 1.0187 |
| [2026-05-24 09:19:52] Validation | Batch 530/1463 | Loss: 0.8748 | LM_LOSS: 0.3655 | LB_LOSS: 1.0186 |
| [2026-05-24 09:19:54] Validation | Batch 540/1463 | Loss: 0.8751 | LM_LOSS: 0.3658 | LB_LOSS: 1.0187 |
| [2026-05-24 09:19:55] Validation | Batch 550/1463 | Loss: 0.8748 | LM_LOSS: 0.3655 | LB_LOSS: 1.0187 |
| [2026-05-24 09:19:57] Validation | Batch 560/1463 | Loss: 0.8752 | LM_LOSS: 0.3659 | LB_LOSS: 1.0188 |
| [2026-05-24 09:19:59] Validation | Batch 570/1463 | Loss: 0.8752 | LM_LOSS: 0.3658 | LB_LOSS: 1.0188 |
| [2026-05-24 09:20:01] Validation | Batch 580/1463 | Loss: 0.8748 | LM_LOSS: 0.3654 | LB_LOSS: 1.0187 |
| [2026-05-24 09:20:03] Validation | Batch 590/1463 | Loss: 0.8748 | LM_LOSS: 0.3654 | LB_LOSS: 1.0188 |
| [2026-05-24 09:20:05] Validation | Batch 600/1463 | Loss: 0.8751 | LM_LOSS: 0.3657 | LB_LOSS: 1.0188 |
| [2026-05-24 09:20:07] Validation | Batch 610/1463 | Loss: 0.8752 | LM_LOSS: 0.3658 | LB_LOSS: 1.0188 |
| [2026-05-24 09:20:09] Validation | Batch 620/1463 | Loss: 0.8744 | LM_LOSS: 0.3650 | LB_LOSS: 1.0188 |
| [2026-05-24 09:20:11] Validation | Batch 630/1463 | Loss: 0.8740 | LM_LOSS: 0.3646 | LB_LOSS: 1.0189 |
| [2026-05-24 09:20:12] Validation | Batch 640/1463 | Loss: 0.8738 | LM_LOSS: 0.3644 | LB_LOSS: 1.0189 |
| [2026-05-24 09:20:14] Validation | Batch 650/1463 | Loss: 0.8734 | LM_LOSS: 0.3639 | LB_LOSS: 1.0189 |
| [2026-05-24 09:20:16] Validation | Batch 660/1463 | Loss: 0.8728 | LM_LOSS: 0.3633 | LB_LOSS: 1.0189 |
| [2026-05-24 09:20:17] Validation | Batch 670/1463 | Loss: 0.8724 | LM_LOSS: 0.3629 | LB_LOSS: 1.0189 |
| [2026-05-24 09:20:19] Validation | Batch 680/1463 | Loss: 0.8724 | LM_LOSS: 0.3630 | LB_LOSS: 1.0188 |
| [2026-05-24 09:20:21] Validation | Batch 690/1463 | Loss: 0.8727 | LM_LOSS: 0.3633 | LB_LOSS: 1.0188 |
| [2026-05-24 09:20:23] Validation | Batch 700/1463 | Loss: 0.8726 | LM_LOSS: 0.3632 | LB_LOSS: 1.0188 |
| [2026-05-24 09:20:24] Validation | Batch 710/1463 | Loss: 0.8730 | LM_LOSS: 0.3635 | LB_LOSS: 1.0189 |
| [2026-05-24 09:20:26] Validation | Batch 720/1463 | Loss: 0.8736 | LM_LOSS: 0.3642 | LB_LOSS: 1.0189 |
| [2026-05-24 09:20:28] Validation | Batch 730/1463 | Loss: 0.8734 | LM_LOSS: 0.3639 | LB_LOSS: 1.0189 |
| [2026-05-24 09:20:29] Validation | Batch 740/1463 | Loss: 0.8730 | LM_LOSS: 0.3635 | LB_LOSS: 1.0189 |
| [2026-05-24 09:20:31] Validation | Batch 750/1463 | Loss: 0.8729 | LM_LOSS: 0.3634 | LB_LOSS: 1.0189 |
| [2026-05-24 09:20:32] Validation | Batch 760/1463 | Loss: 0.8726 | LM_LOSS: 0.3632 | LB_LOSS: 1.0189 |
| [2026-05-24 09:20:34] Validation | Batch 770/1463 | Loss: 0.8725 | LM_LOSS: 0.3631 | LB_LOSS: 1.0189 |
| [2026-05-24 09:20:36] Validation | Batch 780/1463 | Loss: 0.8723 | LM_LOSS: 0.3628 | LB_LOSS: 1.0189 |
| [2026-05-24 09:20:37] Validation | Batch 790/1463 | Loss: 0.8726 | LM_LOSS: 0.3631 | LB_LOSS: 1.0188 |
| [2026-05-24 09:20:39] Validation | Batch 800/1463 | Loss: 0.8725 | LM_LOSS: 0.3631 | LB_LOSS: 1.0188 |
| [2026-05-24 09:20:40] Validation | Batch 810/1463 | Loss: 0.8722 | LM_LOSS: 0.3628 | LB_LOSS: 1.0188 |
| [2026-05-24 09:20:42] Validation | Batch 820/1463 | Loss: 0.8724 | LM_LOSS: 0.3630 | LB_LOSS: 1.0188 |
| [2026-05-24 09:20:44] Validation | Batch 830/1463 | Loss: 0.8725 | LM_LOSS: 0.3631 | LB_LOSS: 1.0188 |
| [2026-05-24 09:20:46] Validation | Batch 840/1463 | Loss: 0.8724 | LM_LOSS: 0.3630 | LB_LOSS: 1.0188 |
| [2026-05-24 09:20:48] Validation | Batch 850/1463 | Loss: 0.8727 | LM_LOSS: 0.3633 | LB_LOSS: 1.0188 |
| [2026-05-24 09:20:50] Validation | Batch 860/1463 | Loss: 0.8727 | LM_LOSS: 0.3633 | LB_LOSS: 1.0189 |
| [2026-05-24 09:20:51] Validation | Batch 870/1463 | Loss: 0.8729 | LM_LOSS: 0.3634 | LB_LOSS: 1.0189 |
| [2026-05-24 09:20:53] Validation | Batch 880/1463 | Loss: 0.8722 | LM_LOSS: 0.3628 | LB_LOSS: 1.0189 |
| [2026-05-24 09:20:55] Validation | Batch 890/1463 | Loss: 0.8722 | LM_LOSS: 0.3628 | LB_LOSS: 1.0188 |
| [2026-05-24 09:20:57] Validation | Batch 900/1463 | Loss: 0.8719 | LM_LOSS: 0.3625 | LB_LOSS: 1.0188 |
| [2026-05-24 09:20:59] Validation | Batch 910/1463 | Loss: 0.8718 | LM_LOSS: 0.3624 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:01] Validation | Batch 920/1463 | Loss: 0.8720 | LM_LOSS: 0.3625 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:02] Validation | Batch 930/1463 | Loss: 0.8717 | LM_LOSS: 0.3623 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:04] Validation | Batch 940/1463 | Loss: 0.8714 | LM_LOSS: 0.3620 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:06] Validation | Batch 950/1463 | Loss: 0.8718 | LM_LOSS: 0.3624 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:08] Validation | Batch 960/1463 | Loss: 0.8719 | LM_LOSS: 0.3625 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:10] Validation | Batch 970/1463 | Loss: 0.8720 | LM_LOSS: 0.3626 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:12] Validation | Batch 980/1463 | Loss: 0.8723 | LM_LOSS: 0.3629 | LB_LOSS: 1.0187 |
| [2026-05-24 09:21:13] Validation | Batch 990/1463 | Loss: 0.8725 | LM_LOSS: 0.3631 | LB_LOSS: 1.0187 |
| [2026-05-24 09:21:15] Validation | Batch 1000/1463 | Loss: 0.8731 | LM_LOSS: 0.3637 | LB_LOSS: 1.0187 |
| [2026-05-24 09:21:17] Validation | Batch 1010/1463 | Loss: 0.8731 | LM_LOSS: 0.3637 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:19] Validation | Batch 1020/1463 | Loss: 0.8732 | LM_LOSS: 0.3638 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:21] Validation | Batch 1030/1463 | Loss: 0.8737 | LM_LOSS: 0.3643 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:23] Validation | Batch 1040/1463 | Loss: 0.8732 | LM_LOSS: 0.3638 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:25] Validation | Batch 1050/1463 | Loss: 0.8730 | LM_LOSS: 0.3636 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:27] Validation | Batch 1060/1463 | Loss: 0.8730 | LM_LOSS: 0.3636 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:29] Validation | Batch 1070/1463 | Loss: 0.8730 | LM_LOSS: 0.3636 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:30] Validation | Batch 1080/1463 | Loss: 0.8728 | LM_LOSS: 0.3634 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:32] Validation | Batch 1090/1463 | Loss: 0.8728 | LM_LOSS: 0.3634 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:34] Validation | Batch 1100/1463 | Loss: 0.8727 | LM_LOSS: 0.3634 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:35] Validation | Batch 1110/1463 | Loss: 0.8728 | LM_LOSS: 0.3634 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:37] Validation | Batch 1120/1463 | Loss: 0.8726 | LM_LOSS: 0.3632 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:39] Validation | Batch 1130/1463 | Loss: 0.8724 | LM_LOSS: 0.3630 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:41] Validation | Batch 1140/1463 | Loss: 0.8726 | LM_LOSS: 0.3632 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:43] Validation | Batch 1150/1463 | Loss: 0.8726 | LM_LOSS: 0.3632 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:45] Validation | Batch 1160/1463 | Loss: 0.8726 | LM_LOSS: 0.3632 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:46] Validation | Batch 1170/1463 | Loss: 0.8726 | LM_LOSS: 0.3632 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:48] Validation | Batch 1180/1463 | Loss: 0.8726 | LM_LOSS: 0.3632 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:50] Validation | Batch 1190/1463 | Loss: 0.8728 | LM_LOSS: 0.3634 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:52] Validation | Batch 1200/1463 | Loss: 0.8729 | LM_LOSS: 0.3635 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:54] Validation | Batch 1210/1463 | Loss: 0.8732 | LM_LOSS: 0.3638 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:56] Validation | Batch 1220/1463 | Loss: 0.8736 | LM_LOSS: 0.3642 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:57] Validation | Batch 1230/1463 | Loss: 0.8735 | LM_LOSS: 0.3641 | LB_LOSS: 1.0188 |
| [2026-05-24 09:21:59] Validation | Batch 1240/1463 | Loss: 0.8738 | LM_LOSS: 0.3644 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:01] Validation | Batch 1250/1463 | Loss: 0.8739 | LM_LOSS: 0.3645 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:03] Validation | Batch 1260/1463 | Loss: 0.8738 | LM_LOSS: 0.3644 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:05] Validation | Batch 1270/1463 | Loss: 0.8736 | LM_LOSS: 0.3642 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:07] Validation | Batch 1280/1463 | Loss: 0.8734 | LM_LOSS: 0.3640 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:09] Validation | Batch 1290/1463 | Loss: 0.8734 | LM_LOSS: 0.3640 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:10] Validation | Batch 1300/1463 | Loss: 0.8732 | LM_LOSS: 0.3638 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:12] Validation | Batch 1310/1463 | Loss: 0.8731 | LM_LOSS: 0.3637 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:13] Validation | Batch 1320/1463 | Loss: 0.8732 | LM_LOSS: 0.3638 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:15] Validation | Batch 1330/1463 | Loss: 0.8731 | LM_LOSS: 0.3638 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:17] Validation | Batch 1340/1463 | Loss: 0.8734 | LM_LOSS: 0.3640 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:19] Validation | Batch 1350/1463 | Loss: 0.8734 | LM_LOSS: 0.3640 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:21] Validation | Batch 1360/1463 | Loss: 0.8737 | LM_LOSS: 0.3643 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:23] Validation | Batch 1370/1463 | Loss: 0.8741 | LM_LOSS: 0.3647 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:24] Validation | Batch 1380/1463 | Loss: 0.8738 | LM_LOSS: 0.3644 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:26] Validation | Batch 1390/1463 | Loss: 0.8738 | LM_LOSS: 0.3644 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:28] Validation | Batch 1400/1463 | Loss: 0.8740 | LM_LOSS: 0.3646 | LB_LOSS: 1.0187 |
| [2026-05-24 09:22:29] Validation | Batch 1410/1463 | Loss: 0.8742 | LM_LOSS: 0.3648 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:31] Validation | Batch 1420/1463 | Loss: 0.8742 | LM_LOSS: 0.3648 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:33] Validation | Batch 1430/1463 | Loss: 0.8742 | LM_LOSS: 0.3649 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:35] Validation | Batch 1440/1463 | Loss: 0.8747 | LM_LOSS: 0.3653 | LB_LOSS: 1.0188 |
| [2026-05-24 09:22:37] Validation | Batch 1450/1463 | Loss: 0.8744 | LM_LOSS: 0.3650 | LB_LOSS: 1.0187 |
| [2026-05-24 09:22:39] Validation | Batch 1460/1463 | Loss: 0.8747 | LM_LOSS: 0.3653 | LB_LOSS: 1.0187 |
| [2026-05-24 09:22:39] Validation | Batch 1463/1463 | Loss: 0.8746 | LM_LOSS: 0.3652 | LB_LOSS: 1.0187 |
| [2026-05-24 09:22:39] Validation | Loss: 0.8746 | LM_LOSS: 0.3652 | LB_LOSS: 1.0187 | PPL: 1.44 | Time: 263.32s |
| [2026-05-24 09:22:51] Epoch 2 | Step 9010 | Loss: 0.8292 | LM: 0.3170 | LB: 1.0262 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:23:03] Epoch 2 | Step 9020 | Loss: 0.8291 | LM: 0.3169 | LB: 1.0262 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:23:14] Epoch 2 | Step 9030 | Loss: 0.8291 | LM: 0.3169 | LB: 1.0262 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:23:26] Epoch 2 | Step 9040 | Loss: 0.8291 | LM: 0.3169 | LB: 1.0262 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:23:38] Epoch 2 | Step 9050 | Loss: 0.8291 | LM: 0.3170 | LB: 1.0262 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:23:49] Epoch 2 | Step 9060 | Loss: 0.8291 | LM: 0.3171 | LB: 1.0262 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:24:01] Epoch 2 | Step 9070 | Loss: 0.8292 | LM: 0.3170 | LB: 1.0262 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:24:12] Epoch 2 | Step 9080 | Loss: 0.8292 | LM: 0.3170 | LB: 1.0261 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:24:22] Epoch 2 | Step 9090 | Loss: 0.8292 | LM: 0.3170 | LB: 1.0261 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:24:33] Epoch 2 | Step 9100 | Loss: 0.8293 | LM: 0.3171 | LB: 1.0261 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:24:43] Epoch 2 | Step 9110 | Loss: 0.8293 | LM: 0.3170 | LB: 1.0261 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:24:54] Epoch 2 | Step 9120 | Loss: 0.8293 | LM: 0.3171 | LB: 1.0261 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:25:05] Epoch 2 | Step 9130 | Loss: 0.8293 | LM: 0.3171 | LB: 1.0261 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:25:16] Epoch 2 | Step 9140 | Loss: 0.8294 | LM: 0.3173 | LB: 1.0261 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:25:27] Epoch 2 | Step 9150 | Loss: 0.8294 | LM: 0.3174 | LB: 1.0261 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:25:37] Epoch 2 | Step 9160 | Loss: 0.8294 | LM: 0.3173 | LB: 1.0260 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:25:48] Epoch 2 | Step 9170 | Loss: 0.8294 | LM: 0.3173 | LB: 1.0260 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:25:58] Epoch 2 | Step 9180 | Loss: 0.8294 | LM: 0.3173 | LB: 1.0260 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:26:10] Epoch 2 | Step 9190 | Loss: 0.8295 | LM: 0.3174 | LB: 1.0260 | CL0: 3.8 | CL1: 5.2 | HR0: 0.267/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:26:21] Epoch 2 | Step 9200 | Loss: 0.8294 | LM: 0.3174 | LB: 1.0260 | CL0: 3.8 | CL1: 5.2 | HR0: 0.266/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:26:33] Epoch 2 | Step 9210 | Loss: 0.8295 | LM: 0.3174 | LB: 1.0260 | CL0: 3.8 | CL1: 5.2 | HR0: 0.266/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:26:45] Epoch 2 | Step 9220 | Loss: 0.8295 | LM: 0.3174 | LB: 1.0260 | CL0: 3.8 | CL1: 5.2 | HR0: 0.266/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:26:56] Epoch 2 | Step 9230 | Loss: 0.8296 | LM: 0.3174 | LB: 1.0259 | CL0: 3.8 | CL1: 5.2 | HR0: 0.266/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:27:08] Epoch 2 | Step 9240 | Loss: 0.8296 | LM: 0.3174 | LB: 1.0259 | CL0: 3.8 | CL1: 5.2 | HR0: 0.266/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:27:18] Epoch 2 | Step 9250 | Loss: 0.8297 | LM: 0.3174 | LB: 1.0259 | CL0: 3.8 | CL1: 5.2 | HR0: 0.266/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:27:29] Epoch 2 | Step 9260 | Loss: 0.8297 | LM: 0.3175 | LB: 1.0259 | CL0: 3.8 | CL1: 5.2 | HR0: 0.266/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:27:41] Epoch 2 | Step 9270 | Loss: 0.8297 | LM: 0.3174 | LB: 1.0259 | CL0: 3.8 | CL1: 5.2 | HR0: 0.266/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:27:52] Epoch 2 | Step 9280 | Loss: 0.8297 | LM: 0.3176 | LB: 1.0259 | CL0: 3.8 | CL1: 5.2 | HR0: 0.266/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:28:04] Epoch 2 | Step 9290 | Loss: 0.8298 | LM: 0.3176 | LB: 1.0259 | CL0: 3.8 | CL1: 5.2 | HR0: 0.266/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:28:16] Epoch 2 | Step 9300 | Loss: 0.8299 | LM: 0.3177 | LB: 1.0259 | CL0: 3.8 | CL1: 5.2 | HR0: 0.266/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:28:28] Epoch 2 | Step 9310 | Loss: 0.8300 | LM: 0.3177 | LB: 1.0259 | CL0: 3.8 | CL1: 5.2 | HR0: 0.266/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:28:39] Epoch 2 | Step 9320 | Loss: 0.8301 | LM: 0.3179 | LB: 1.0259 | CL0: 3.8 | CL1: 5.2 | HR0: 0.266/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:28:50] Epoch 2 | Step 9330 | Loss: 0.8301 | LM: 0.3180 | LB: 1.0258 | CL0: 3.8 | CL1: 5.2 | HR0: 0.266/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:29:01] Epoch 2 | Step 9340 | Loss: 0.8301 | LM: 0.3179 | LB: 1.0258 | CL0: 3.8 | CL1: 5.2 | HR0: 0.266/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:29:11] Epoch 2 | Step 9350 | Loss: 0.8302 | LM: 0.3180 | LB: 1.0258 | CL0: 3.8 | CL1: 5.2 | HR0: 0.266/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:29:22] Epoch 2 | Step 9360 | Loss: 0.8302 | LM: 0.3180 | LB: 1.0258 | CL0: 3.8 | CL1: 5.2 | HR0: 0.266/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:29:33] Epoch 2 | Step 9370 | Loss: 0.8302 | LM: 0.3181 | LB: 1.0258 | CL0: 3.8 | CL1: 5.2 | HR0: 0.266/SR0: 0.232 | HR1: 0.195/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:29:38] Epoch 2 completed in 6567.30s | Loss: 0.8302 | CL0: 3.8 | CL1: 5.2 |
| [2026-05-24 09:29:38] |
| ============================================================ |
| [2026-05-24 09:29:38] EPOCH 3/3 (step 9374) |
| [2026-05-24 09:29:38] ============================================================ |
| [2026-05-24 09:29:44] Epoch 3 | Step 9380 | Loss: 0.7854 | LM: 0.2420 | LB: 1.0171 | CL0: 4.0 | CL1: 5.5 | HR0: 0.251/SR0: 0.220 | HR1: 0.184/SR1: 0.160 | LR: 1.00e-04 |
| [2026-05-24 09:29:55] Epoch 3 | Step 9390 | Loss: 0.7902 | LM: 0.2673 | LB: 1.0186 | CL0: 4.0 | CL1: 5.2 | HR0: 0.254/SR0: 0.221 | HR1: 0.195/SR1: 0.168 | LR: 1.00e-04 |
| [2026-05-24 09:30:05] Epoch 3 | Step 9400 | Loss: 0.7844 | LM: 0.2747 | LB: 1.0176 | CL0: 4.0 | CL1: 5.1 | HR0: 0.252/SR0: 0.220 | HR1: 0.196/SR1: 0.168 | LR: 1.00e-04 |
| [2026-05-24 09:30:16] Epoch 3 | Step 9410 | Loss: 0.7836 | LM: 0.2606 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:30:27] Epoch 3 | Step 9420 | Loss: 0.7733 | LM: 0.2452 | LB: 1.0167 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.218 | HR1: 0.190/SR1: 0.164 | LR: 1.00e-04 |
| [2026-05-24 09:30:38] Epoch 3 | Step 9430 | Loss: 0.7734 | LM: 0.2477 | LB: 1.0177 | CL0: 4.0 | CL1: 5.3 | HR0: 0.252/SR0: 0.220 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:30:49] Epoch 3 | Step 9440 | Loss: 0.7692 | LM: 0.2416 | LB: 1.0172 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.191/SR1: 0.164 | LR: 1.00e-04 |
| [2026-05-24 09:30:59] Epoch 3 | Step 9450 | Loss: 0.7749 | LM: 0.2497 | LB: 1.0181 | CL0: 4.0 | CL1: 5.3 | HR0: 0.252/SR0: 0.220 | HR1: 0.191/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:31:10] Epoch 3 | Step 9460 | Loss: 0.7719 | LM: 0.2482 | LB: 1.0177 | CL0: 4.0 | CL1: 5.3 | HR0: 0.252/SR0: 0.219 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:31:21] Epoch 3 | Step 9470 | Loss: 0.7696 | LM: 0.2505 | LB: 1.0179 | CL0: 4.0 | CL1: 5.3 | HR0: 0.252/SR0: 0.220 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:31:32] Epoch 3 | Step 9480 | Loss: 0.7689 | LM: 0.2560 | LB: 1.0179 | CL0: 4.0 | CL1: 5.3 | HR0: 0.252/SR0: 0.220 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:31:42] Epoch 3 | Step 9490 | Loss: 0.7679 | LM: 0.2518 | LB: 1.0178 | CL0: 4.0 | CL1: 5.3 | HR0: 0.252/SR0: 0.220 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:31:53] Epoch 3 | Step 9500 | Loss: 0.7679 | LM: 0.2537 | LB: 1.0180 | CL0: 4.0 | CL1: 5.3 | HR0: 0.252/SR0: 0.220 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:32:04] Epoch 3 | Step 9510 | Loss: 0.7663 | LM: 0.2496 | LB: 1.0191 | CL0: 4.0 | CL1: 5.3 | HR0: 0.254/SR0: 0.221 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:32:15] Epoch 3 | Step 9520 | Loss: 0.7671 | LM: 0.2511 | LB: 1.0193 | CL0: 4.0 | CL1: 5.3 | HR0: 0.254/SR0: 0.222 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:32:27] Epoch 3 | Step 9530 | Loss: 0.7681 | LM: 0.2545 | LB: 1.0196 | CL0: 4.0 | CL1: 5.3 | HR0: 0.255/SR0: 0.222 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:32:38] Epoch 3 | Step 9540 | Loss: 0.7671 | LM: 0.2519 | LB: 1.0194 | CL0: 4.0 | CL1: 5.2 | HR0: 0.254/SR0: 0.221 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:32:50] Epoch 3 | Step 9550 | Loss: 0.7674 | LM: 0.2510 | LB: 1.0195 | CL0: 4.0 | CL1: 5.2 | HR0: 0.254/SR0: 0.222 | HR1: 0.193/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:33:02] Epoch 3 | Step 9560 | Loss: 0.7652 | LM: 0.2493 | LB: 1.0193 | CL0: 4.0 | CL1: 5.2 | HR0: 0.253/SR0: 0.221 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:33:13] Epoch 3 | Step 9570 | Loss: 0.7663 | LM: 0.2545 | LB: 1.0196 | CL0: 4.0 | CL1: 5.2 | HR0: 0.254/SR0: 0.222 | HR1: 0.193/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:33:25] Epoch 3 | Step 9580 | Loss: 0.7666 | LM: 0.2559 | LB: 1.0196 | CL0: 4.0 | CL1: 5.2 | HR0: 0.254/SR0: 0.222 | HR1: 0.193/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:33:36] Epoch 3 | Step 9590 | Loss: 0.7663 | LM: 0.2563 | LB: 1.0193 | CL0: 4.0 | CL1: 5.2 | HR0: 0.254/SR0: 0.221 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:33:48] Epoch 3 | Step 9600 | Loss: 0.7672 | LM: 0.2560 | LB: 1.0192 | CL0: 4.0 | CL1: 5.2 | HR0: 0.253/SR0: 0.221 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:34:00] Epoch 3 | Step 9610 | Loss: 0.7666 | LM: 0.2547 | LB: 1.0192 | CL0: 4.0 | CL1: 5.2 | HR0: 0.253/SR0: 0.221 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:34:11] Epoch 3 | Step 9620 | Loss: 0.7656 | LM: 0.2567 | LB: 1.0191 | CL0: 4.0 | CL1: 5.2 | HR0: 0.253/SR0: 0.221 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:34:23] Epoch 3 | Step 9630 | Loss: 0.7660 | LM: 0.2569 | LB: 1.0191 | CL0: 4.0 | CL1: 5.2 | HR0: 0.253/SR0: 0.221 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:34:34] Epoch 3 | Step 9640 | Loss: 0.7659 | LM: 0.2574 | LB: 1.0190 | CL0: 4.0 | CL1: 5.2 | HR0: 0.253/SR0: 0.221 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:34:46] Epoch 3 | Step 9650 | Loss: 0.7654 | LM: 0.2561 | LB: 1.0189 | CL0: 4.0 | CL1: 5.2 | HR0: 0.253/SR0: 0.221 | HR1: 0.193/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:34:58] Epoch 3 | Step 9660 | Loss: 0.7653 | LM: 0.2562 | LB: 1.0188 | CL0: 4.0 | CL1: 5.2 | HR0: 0.253/SR0: 0.220 | HR1: 0.193/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 09:35:09] Epoch 3 | Step 9670 | Loss: 0.7653 | LM: 0.2562 | LB: 1.0188 | CL0: 4.0 | CL1: 5.2 | HR0: 0.253/SR0: 0.220 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:35:21] Epoch 3 | Step 9680 | Loss: 0.7652 | LM: 0.2565 | LB: 1.0186 | CL0: 4.0 | CL1: 5.2 | HR0: 0.252/SR0: 0.220 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:35:32] Epoch 3 | Step 9690 | Loss: 0.7656 | LM: 0.2560 | LB: 1.0185 | CL0: 4.0 | CL1: 5.3 | HR0: 0.252/SR0: 0.220 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:35:44] Epoch 3 | Step 9700 | Loss: 0.7674 | LM: 0.2571 | LB: 1.0185 | CL0: 4.0 | CL1: 5.3 | HR0: 0.252/SR0: 0.220 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:35:55] Epoch 3 | Step 9710 | Loss: 0.7674 | LM: 0.2567 | LB: 1.0184 | CL0: 4.0 | CL1: 5.3 | HR0: 0.252/SR0: 0.220 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:36:05] Epoch 3 | Step 9720 | Loss: 0.7674 | LM: 0.2556 | LB: 1.0182 | CL0: 4.0 | CL1: 5.3 | HR0: 0.252/SR0: 0.220 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:36:16] Epoch 3 | Step 9730 | Loss: 0.7674 | LM: 0.2567 | LB: 1.0182 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.220 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:36:27] Epoch 3 | Step 9740 | Loss: 0.7672 | LM: 0.2575 | LB: 1.0182 | CL0: 4.0 | CL1: 5.3 | HR0: 0.252/SR0: 0.220 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:36:38] Epoch 3 | Step 9750 | Loss: 0.7674 | LM: 0.2567 | LB: 1.0182 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.220 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:36:48] Epoch 3 | Step 9760 | Loss: 0.7675 | LM: 0.2569 | LB: 1.0182 | CL0: 4.0 | CL1: 5.3 | HR0: 0.252/SR0: 0.220 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:36:59] Epoch 3 | Step 9770 | Loss: 0.7678 | LM: 0.2580 | LB: 1.0182 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.220 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:37:10] Epoch 3 | Step 9780 | Loss: 0.7681 | LM: 0.2581 | LB: 1.0182 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.220 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:37:20] Epoch 3 | Step 9790 | Loss: 0.7676 | LM: 0.2591 | LB: 1.0181 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.220 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:37:31] Epoch 3 | Step 9800 | Loss: 0.7675 | LM: 0.2594 | LB: 1.0181 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.220 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:37:42] Epoch 3 | Step 9810 | Loss: 0.7675 | LM: 0.2597 | LB: 1.0181 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:37:53] Epoch 3 | Step 9820 | Loss: 0.7673 | LM: 0.2600 | LB: 1.0180 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:38:04] Epoch 3 | Step 9830 | Loss: 0.7675 | LM: 0.2607 | LB: 1.0180 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:38:14] Epoch 3 | Step 9840 | Loss: 0.7682 | LM: 0.2612 | LB: 1.0181 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:38:25] Epoch 3 | Step 9850 | Loss: 0.7681 | LM: 0.2599 | LB: 1.0179 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:38:35] Epoch 3 | Step 9860 | Loss: 0.7684 | LM: 0.2592 | LB: 1.0179 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:38:46] Epoch 3 | Step 9870 | Loss: 0.7685 | LM: 0.2585 | LB: 1.0179 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:38:57] Epoch 3 | Step 9880 | Loss: 0.7689 | LM: 0.2599 | LB: 1.0179 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:39:08] Epoch 3 | Step 9890 | Loss: 0.7687 | LM: 0.2596 | LB: 1.0179 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:39:19] Epoch 3 | Step 9900 | Loss: 0.7682 | LM: 0.2592 | LB: 1.0179 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:39:29] Epoch 3 | Step 9910 | Loss: 0.7686 | LM: 0.2601 | LB: 1.0179 | CL0: 4.0 | CL1: 5.2 | HR0: 0.251/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:39:40] Epoch 3 | Step 9920 | Loss: 0.7682 | LM: 0.2601 | LB: 1.0179 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:39:51] Epoch 3 | Step 9930 | Loss: 0.7676 | LM: 0.2587 | LB: 1.0178 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:40:01] Epoch 3 | Step 9940 | Loss: 0.7679 | LM: 0.2590 | LB: 1.0178 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:40:12] Epoch 3 | Step 9950 | Loss: 0.7685 | LM: 0.2601 | LB: 1.0178 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:40:23] Epoch 3 | Step 9960 | Loss: 0.7684 | LM: 0.2598 | LB: 1.0179 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:40:33] Epoch 3 | Step 9970 | Loss: 0.7682 | LM: 0.2589 | LB: 1.0179 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:40:44] Epoch 3 | Step 9980 | Loss: 0.7678 | LM: 0.2586 | LB: 1.0179 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:40:55] Epoch 3 | Step 9990 | Loss: 0.7681 | LM: 0.2592 | LB: 1.0179 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:41:05] Epoch 3 | Step 10000 | Loss: 0.7681 | LM: 0.2590 | LB: 1.0178 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:41:07] Validation | Batch 10/1463 | Loss: 0.8631 | LM_LOSS: 0.3572 | LB_LOSS: 1.0117 |
| [2026-05-24 09:41:08] Validation | Batch 20/1463 | Loss: 0.8765 | LM_LOSS: 0.3698 | LB_LOSS: 1.0135 |
| [2026-05-24 09:41:10] Validation | Batch 30/1463 | Loss: 0.8778 | LM_LOSS: 0.3707 | LB_LOSS: 1.0143 |
| [2026-05-24 09:41:12] Validation | Batch 40/1463 | Loss: 0.8893 | LM_LOSS: 0.3818 | LB_LOSS: 1.0151 |
| [2026-05-24 09:41:14] Validation | Batch 50/1463 | Loss: 0.8984 | LM_LOSS: 0.3910 | LB_LOSS: 1.0147 |
| [2026-05-24 09:41:16] Validation | Batch 60/1463 | Loss: 0.9009 | LM_LOSS: 0.3935 | LB_LOSS: 1.0147 |
| [2026-05-24 09:41:18] Validation | Batch 70/1463 | Loss: 0.8998 | LM_LOSS: 0.3925 | LB_LOSS: 1.0147 |
| [2026-05-24 09:41:20] Validation | Batch 80/1463 | Loss: 0.9015 | LM_LOSS: 0.3941 | LB_LOSS: 1.0147 |
| [2026-05-24 09:41:22] Validation | Batch 90/1463 | Loss: 0.9003 | LM_LOSS: 0.3930 | LB_LOSS: 1.0146 |
| [2026-05-24 09:41:23] Validation | Batch 100/1463 | Loss: 0.8999 | LM_LOSS: 0.3925 | LB_LOSS: 1.0147 |
| [2026-05-24 09:41:25] Validation | Batch 110/1463 | Loss: 0.8976 | LM_LOSS: 0.3901 | LB_LOSS: 1.0149 |
| [2026-05-24 09:41:27] Validation | Batch 120/1463 | Loss: 0.8996 | LM_LOSS: 0.3921 | LB_LOSS: 1.0150 |
| [2026-05-24 09:41:28] Validation | Batch 130/1463 | Loss: 0.9026 | LM_LOSS: 0.3951 | LB_LOSS: 1.0150 |
| [2026-05-24 09:41:30] Validation | Batch 140/1463 | Loss: 0.9041 | LM_LOSS: 0.3966 | LB_LOSS: 1.0150 |
| [2026-05-24 09:41:32] Validation | Batch 150/1463 | Loss: 0.9029 | LM_LOSS: 0.3953 | LB_LOSS: 1.0151 |
| [2026-05-24 09:41:34] Validation | Batch 160/1463 | Loss: 0.9043 | LM_LOSS: 0.3968 | LB_LOSS: 1.0151 |
| [2026-05-24 09:41:36] Validation | Batch 170/1463 | Loss: 0.9035 | LM_LOSS: 0.3959 | LB_LOSS: 1.0151 |
| [2026-05-24 09:41:37] Validation | Batch 180/1463 | Loss: 0.9039 | LM_LOSS: 0.3964 | LB_LOSS: 1.0151 |
| [2026-05-24 09:41:39] Validation | Batch 190/1463 | Loss: 0.9047 | LM_LOSS: 0.3971 | LB_LOSS: 1.0151 |
| [2026-05-24 09:41:41] Validation | Batch 200/1463 | Loss: 0.9042 | LM_LOSS: 0.3966 | LB_LOSS: 1.0151 |
| [2026-05-24 09:41:43] Validation | Batch 210/1463 | Loss: 0.9048 | LM_LOSS: 0.3972 | LB_LOSS: 1.0152 |
| [2026-05-24 09:41:45] Validation | Batch 220/1463 | Loss: 0.9042 | LM_LOSS: 0.3966 | LB_LOSS: 1.0152 |
| [2026-05-24 09:41:47] Validation | Batch 230/1463 | Loss: 0.9059 | LM_LOSS: 0.3984 | LB_LOSS: 1.0151 |
| [2026-05-24 09:41:48] Validation | Batch 240/1463 | Loss: 0.9072 | LM_LOSS: 0.3997 | LB_LOSS: 1.0150 |
| [2026-05-24 09:41:50] Validation | Batch 250/1463 | Loss: 0.9059 | LM_LOSS: 0.3984 | LB_LOSS: 1.0150 |
| [2026-05-24 09:41:52] Validation | Batch 260/1463 | Loss: 0.9079 | LM_LOSS: 0.4002 | LB_LOSS: 1.0152 |
| [2026-05-24 09:41:54] Validation | Batch 270/1463 | Loss: 0.9065 | LM_LOSS: 0.3989 | LB_LOSS: 1.0152 |
| [2026-05-24 09:41:55] Validation | Batch 280/1463 | Loss: 0.9075 | LM_LOSS: 0.3999 | LB_LOSS: 1.0152 |
| [2026-05-24 09:41:57] Validation | Batch 290/1463 | Loss: 0.9065 | LM_LOSS: 0.3989 | LB_LOSS: 1.0152 |
| [2026-05-24 09:41:59] Validation | Batch 300/1463 | Loss: 0.9073 | LM_LOSS: 0.3996 | LB_LOSS: 1.0153 |
| [2026-05-24 09:42:01] Validation | Batch 310/1463 | Loss: 0.9078 | LM_LOSS: 0.4002 | LB_LOSS: 1.0153 |
| [2026-05-24 09:42:02] Validation | Batch 320/1463 | Loss: 0.9066 | LM_LOSS: 0.3990 | LB_LOSS: 1.0152 |
| [2026-05-24 09:42:04] Validation | Batch 330/1463 | Loss: 0.9067 | LM_LOSS: 0.3992 | LB_LOSS: 1.0152 |
| [2026-05-24 09:42:06] Validation | Batch 340/1463 | Loss: 0.9061 | LM_LOSS: 0.3985 | LB_LOSS: 1.0152 |
| [2026-05-24 09:42:08] Validation | Batch 350/1463 | Loss: 0.9068 | LM_LOSS: 0.3992 | LB_LOSS: 1.0152 |
| [2026-05-24 09:42:09] Validation | Batch 360/1463 | Loss: 0.9069 | LM_LOSS: 0.3994 | LB_LOSS: 1.0152 |
| [2026-05-24 09:42:11] Validation | Batch 370/1463 | Loss: 0.9068 | LM_LOSS: 0.3992 | LB_LOSS: 1.0152 |
| [2026-05-24 09:42:12] Validation | Batch 380/1463 | Loss: 0.9066 | LM_LOSS: 0.3990 | LB_LOSS: 1.0151 |
| [2026-05-24 09:42:14] Validation | Batch 390/1463 | Loss: 0.9074 | LM_LOSS: 0.3998 | LB_LOSS: 1.0151 |
| [2026-05-24 09:42:16] Validation | Batch 400/1463 | Loss: 0.9071 | LM_LOSS: 0.3996 | LB_LOSS: 1.0152 |
| [2026-05-24 09:42:17] Validation | Batch 410/1463 | Loss: 0.9070 | LM_LOSS: 0.3994 | LB_LOSS: 1.0152 |
| [2026-05-24 09:42:19] Validation | Batch 420/1463 | Loss: 0.9070 | LM_LOSS: 0.3994 | LB_LOSS: 1.0152 |
| [2026-05-24 09:42:21] Validation | Batch 430/1463 | Loss: 0.9069 | LM_LOSS: 0.3993 | LB_LOSS: 1.0153 |
| [2026-05-24 09:42:23] Validation | Batch 440/1463 | Loss: 0.9072 | LM_LOSS: 0.3996 | LB_LOSS: 1.0153 |
| [2026-05-24 09:42:24] Validation | Batch 450/1463 | Loss: 0.9070 | LM_LOSS: 0.3993 | LB_LOSS: 1.0154 |
| [2026-05-24 09:42:26] Validation | Batch 460/1463 | Loss: 0.9069 | LM_LOSS: 0.3992 | LB_LOSS: 1.0154 |
| [2026-05-24 09:42:28] Validation | Batch 470/1463 | Loss: 0.9075 | LM_LOSS: 0.3998 | LB_LOSS: 1.0153 |
| [2026-05-24 09:42:30] Validation | Batch 480/1463 | Loss: 0.9073 | LM_LOSS: 0.3997 | LB_LOSS: 1.0153 |
| [2026-05-24 09:42:32] Validation | Batch 490/1463 | Loss: 0.9071 | LM_LOSS: 0.3995 | LB_LOSS: 1.0153 |
| [2026-05-24 09:42:34] Validation | Batch 500/1463 | Loss: 0.9068 | LM_LOSS: 0.3992 | LB_LOSS: 1.0153 |
| [2026-05-24 09:42:36] Validation | Batch 510/1463 | Loss: 0.9062 | LM_LOSS: 0.3986 | LB_LOSS: 1.0153 |
| [2026-05-24 09:42:37] Validation | Batch 520/1463 | Loss: 0.9059 | LM_LOSS: 0.3983 | LB_LOSS: 1.0153 |
| [2026-05-24 09:42:39] Validation | Batch 530/1463 | Loss: 0.9064 | LM_LOSS: 0.3988 | LB_LOSS: 1.0153 |
| [2026-05-24 09:42:41] Validation | Batch 540/1463 | Loss: 0.9068 | LM_LOSS: 0.3991 | LB_LOSS: 1.0153 |
| [2026-05-24 09:42:42] Validation | Batch 550/1463 | Loss: 0.9064 | LM_LOSS: 0.3987 | LB_LOSS: 1.0153 |
| [2026-05-24 09:42:44] Validation | Batch 560/1463 | Loss: 0.9068 | LM_LOSS: 0.3991 | LB_LOSS: 1.0154 |
| [2026-05-24 09:42:46] Validation | Batch 570/1463 | Loss: 0.9066 | LM_LOSS: 0.3989 | LB_LOSS: 1.0154 |
| [2026-05-24 09:42:48] Validation | Batch 580/1463 | Loss: 0.9062 | LM_LOSS: 0.3985 | LB_LOSS: 1.0154 |
| [2026-05-24 09:42:50] Validation | Batch 590/1463 | Loss: 0.9062 | LM_LOSS: 0.3985 | LB_LOSS: 1.0154 |
| [2026-05-24 09:42:52] Validation | Batch 600/1463 | Loss: 0.9065 | LM_LOSS: 0.3988 | LB_LOSS: 1.0155 |
| [2026-05-24 09:42:53] Validation | Batch 610/1463 | Loss: 0.9064 | LM_LOSS: 0.3987 | LB_LOSS: 1.0155 |
| [2026-05-24 09:42:55] Validation | Batch 620/1463 | Loss: 0.9055 | LM_LOSS: 0.3978 | LB_LOSS: 1.0155 |
| [2026-05-24 09:42:57] Validation | Batch 630/1463 | Loss: 0.9051 | LM_LOSS: 0.3974 | LB_LOSS: 1.0155 |
| [2026-05-24 09:42:59] Validation | Batch 640/1463 | Loss: 0.9048 | LM_LOSS: 0.3971 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:00] Validation | Batch 650/1463 | Loss: 0.9044 | LM_LOSS: 0.3966 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:02] Validation | Batch 660/1463 | Loss: 0.9038 | LM_LOSS: 0.3960 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:04] Validation | Batch 670/1463 | Loss: 0.9033 | LM_LOSS: 0.3955 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:05] Validation | Batch 680/1463 | Loss: 0.9033 | LM_LOSS: 0.3956 | LB_LOSS: 1.0154 |
| [2026-05-24 09:43:07] Validation | Batch 690/1463 | Loss: 0.9037 | LM_LOSS: 0.3959 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:09] Validation | Batch 700/1463 | Loss: 0.9035 | LM_LOSS: 0.3958 | LB_LOSS: 1.0154 |
| [2026-05-24 09:43:10] Validation | Batch 710/1463 | Loss: 0.9038 | LM_LOSS: 0.3961 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:12] Validation | Batch 720/1463 | Loss: 0.9045 | LM_LOSS: 0.3968 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:14] Validation | Batch 730/1463 | Loss: 0.9043 | LM_LOSS: 0.3965 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:15] Validation | Batch 740/1463 | Loss: 0.9039 | LM_LOSS: 0.3961 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:17] Validation | Batch 750/1463 | Loss: 0.9037 | LM_LOSS: 0.3960 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:18] Validation | Batch 760/1463 | Loss: 0.9033 | LM_LOSS: 0.3955 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:20] Validation | Batch 770/1463 | Loss: 0.9032 | LM_LOSS: 0.3954 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:21] Validation | Batch 780/1463 | Loss: 0.9030 | LM_LOSS: 0.3952 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:23] Validation | Batch 790/1463 | Loss: 0.9032 | LM_LOSS: 0.3954 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:24] Validation | Batch 800/1463 | Loss: 0.9031 | LM_LOSS: 0.3953 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:26] Validation | Batch 810/1463 | Loss: 0.9027 | LM_LOSS: 0.3950 | LB_LOSS: 1.0154 |
| [2026-05-24 09:43:27] Validation | Batch 820/1463 | Loss: 0.9029 | LM_LOSS: 0.3952 | LB_LOSS: 1.0154 |
| [2026-05-24 09:43:29] Validation | Batch 830/1463 | Loss: 0.9030 | LM_LOSS: 0.3953 | LB_LOSS: 1.0154 |
| [2026-05-24 09:43:31] Validation | Batch 840/1463 | Loss: 0.9029 | LM_LOSS: 0.3952 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:33] Validation | Batch 850/1463 | Loss: 0.9032 | LM_LOSS: 0.3955 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:35] Validation | Batch 860/1463 | Loss: 0.9032 | LM_LOSS: 0.3955 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:37] Validation | Batch 870/1463 | Loss: 0.9033 | LM_LOSS: 0.3956 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:38] Validation | Batch 880/1463 | Loss: 0.9027 | LM_LOSS: 0.3949 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:40] Validation | Batch 890/1463 | Loss: 0.9027 | LM_LOSS: 0.3950 | LB_LOSS: 1.0154 |
| [2026-05-24 09:43:42] Validation | Batch 900/1463 | Loss: 0.9024 | LM_LOSS: 0.3947 | LB_LOSS: 1.0154 |
| [2026-05-24 09:43:44] Validation | Batch 910/1463 | Loss: 0.9023 | LM_LOSS: 0.3946 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:46] Validation | Batch 920/1463 | Loss: 0.9026 | LM_LOSS: 0.3948 | LB_LOSS: 1.0155 |
| [2026-05-24 09:43:47] Validation | Batch 930/1463 | Loss: 0.9022 | LM_LOSS: 0.3944 | LB_LOSS: 1.0154 |
| [2026-05-24 09:43:49] Validation | Batch 940/1463 | Loss: 0.9018 | LM_LOSS: 0.3941 | LB_LOSS: 1.0154 |
| [2026-05-24 09:43:51] Validation | Batch 950/1463 | Loss: 0.9023 | LM_LOSS: 0.3945 | LB_LOSS: 1.0154 |
| [2026-05-24 09:43:53] Validation | Batch 960/1463 | Loss: 0.9024 | LM_LOSS: 0.3947 | LB_LOSS: 1.0154 |
| [2026-05-24 09:43:55] Validation | Batch 970/1463 | Loss: 0.9025 | LM_LOSS: 0.3948 | LB_LOSS: 1.0154 |
| [2026-05-24 09:43:57] Validation | Batch 980/1463 | Loss: 0.9028 | LM_LOSS: 0.3951 | LB_LOSS: 1.0154 |
| [2026-05-24 09:43:58] Validation | Batch 990/1463 | Loss: 0.9030 | LM_LOSS: 0.3953 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:00] Validation | Batch 1000/1463 | Loss: 0.9036 | LM_LOSS: 0.3959 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:02] Validation | Batch 1010/1463 | Loss: 0.9035 | LM_LOSS: 0.3958 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:04] Validation | Batch 1020/1463 | Loss: 0.9036 | LM_LOSS: 0.3959 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:06] Validation | Batch 1030/1463 | Loss: 0.9041 | LM_LOSS: 0.3963 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:07] Validation | Batch 1040/1463 | Loss: 0.9035 | LM_LOSS: 0.3958 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:09] Validation | Batch 1050/1463 | Loss: 0.9034 | LM_LOSS: 0.3957 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:11] Validation | Batch 1060/1463 | Loss: 0.9033 | LM_LOSS: 0.3956 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:13] Validation | Batch 1070/1463 | Loss: 0.9034 | LM_LOSS: 0.3957 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:14] Validation | Batch 1080/1463 | Loss: 0.9031 | LM_LOSS: 0.3954 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:16] Validation | Batch 1090/1463 | Loss: 0.9031 | LM_LOSS: 0.3954 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:18] Validation | Batch 1100/1463 | Loss: 0.9031 | LM_LOSS: 0.3954 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:19] Validation | Batch 1110/1463 | Loss: 0.9031 | LM_LOSS: 0.3954 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:21] Validation | Batch 1120/1463 | Loss: 0.9029 | LM_LOSS: 0.3951 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:23] Validation | Batch 1130/1463 | Loss: 0.9026 | LM_LOSS: 0.3948 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:25] Validation | Batch 1140/1463 | Loss: 0.9028 | LM_LOSS: 0.3951 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:27] Validation | Batch 1150/1463 | Loss: 0.9028 | LM_LOSS: 0.3951 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:29] Validation | Batch 1160/1463 | Loss: 0.9028 | LM_LOSS: 0.3951 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:30] Validation | Batch 1170/1463 | Loss: 0.9027 | LM_LOSS: 0.3950 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:32] Validation | Batch 1180/1463 | Loss: 0.9027 | LM_LOSS: 0.3950 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:34] Validation | Batch 1190/1463 | Loss: 0.9029 | LM_LOSS: 0.3952 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:36] Validation | Batch 1200/1463 | Loss: 0.9030 | LM_LOSS: 0.3953 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:38] Validation | Batch 1210/1463 | Loss: 0.9034 | LM_LOSS: 0.3957 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:39] Validation | Batch 1220/1463 | Loss: 0.9038 | LM_LOSS: 0.3961 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:41] Validation | Batch 1230/1463 | Loss: 0.9037 | LM_LOSS: 0.3960 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:43] Validation | Batch 1240/1463 | Loss: 0.9040 | LM_LOSS: 0.3963 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:44] Validation | Batch 1250/1463 | Loss: 0.9042 | LM_LOSS: 0.3965 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:47] Validation | Batch 1260/1463 | Loss: 0.9042 | LM_LOSS: 0.3965 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:48] Validation | Batch 1270/1463 | Loss: 0.9040 | LM_LOSS: 0.3962 | LB_LOSS: 1.0155 |
| [2026-05-24 09:44:50] Validation | Batch 1280/1463 | Loss: 0.9037 | LM_LOSS: 0.3960 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:52] Validation | Batch 1290/1463 | Loss: 0.9037 | LM_LOSS: 0.3960 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:54] Validation | Batch 1300/1463 | Loss: 0.9035 | LM_LOSS: 0.3958 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:55] Validation | Batch 1310/1463 | Loss: 0.9034 | LM_LOSS: 0.3957 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:57] Validation | Batch 1320/1463 | Loss: 0.9034 | LM_LOSS: 0.3957 | LB_LOSS: 1.0154 |
| [2026-05-24 09:44:58] Validation | Batch 1330/1463 | Loss: 0.9034 | LM_LOSS: 0.3957 | LB_LOSS: 1.0154 |
| [2026-05-24 09:45:00] Validation | Batch 1340/1463 | Loss: 0.9036 | LM_LOSS: 0.3959 | LB_LOSS: 1.0154 |
| [2026-05-24 09:45:02] Validation | Batch 1350/1463 | Loss: 0.9037 | LM_LOSS: 0.3960 | LB_LOSS: 1.0154 |
| [2026-05-24 09:45:04] Validation | Batch 1360/1463 | Loss: 0.9040 | LM_LOSS: 0.3963 | LB_LOSS: 1.0154 |
| [2026-05-24 09:45:06] Validation | Batch 1370/1463 | Loss: 0.9043 | LM_LOSS: 0.3966 | LB_LOSS: 1.0154 |
| [2026-05-24 09:45:07] Validation | Batch 1380/1463 | Loss: 0.9042 | LM_LOSS: 0.3965 | LB_LOSS: 1.0154 |
| [2026-05-24 09:45:09] Validation | Batch 1390/1463 | Loss: 0.9041 | LM_LOSS: 0.3964 | LB_LOSS: 1.0154 |
| [2026-05-24 09:45:11] Validation | Batch 1400/1463 | Loss: 0.9043 | LM_LOSS: 0.3966 | LB_LOSS: 1.0154 |
| [2026-05-24 09:45:12] Validation | Batch 1410/1463 | Loss: 0.9045 | LM_LOSS: 0.3969 | LB_LOSS: 1.0154 |
| [2026-05-24 09:45:14] Validation | Batch 1420/1463 | Loss: 0.9046 | LM_LOSS: 0.3969 | LB_LOSS: 1.0154 |
| [2026-05-24 09:45:16] Validation | Batch 1430/1463 | Loss: 0.9046 | LM_LOSS: 0.3969 | LB_LOSS: 1.0154 |
| [2026-05-24 09:45:18] Validation | Batch 1440/1463 | Loss: 0.9051 | LM_LOSS: 0.3974 | LB_LOSS: 1.0154 |
| [2026-05-24 09:45:19] Validation | Batch 1450/1463 | Loss: 0.9047 | LM_LOSS: 0.3971 | LB_LOSS: 1.0154 |
| [2026-05-24 09:45:21] Validation | Batch 1460/1463 | Loss: 0.9051 | LM_LOSS: 0.3974 | LB_LOSS: 1.0154 |
| [2026-05-24 09:45:22] Validation | Batch 1463/1463 | Loss: 0.9050 | LM_LOSS: 0.3973 | LB_LOSS: 1.0154 |
| [2026-05-24 09:45:22] Validation | Loss: 0.9050 | LM_LOSS: 0.3973 | LB_LOSS: 1.0154 | PPL: 1.49 | Time: 256.50s |
| [2026-05-24 09:45:33] Epoch 3 | Step 10010 | Loss: 0.7679 | LM: 0.2592 | LB: 1.0177 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:45:43] Epoch 3 | Step 10020 | Loss: 0.7676 | LM: 0.2593 | LB: 1.0178 | CL0: 4.0 | CL1: 5.3 | HR0: 0.251/SR0: 0.219 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:45:54] Epoch 3 | Step 10030 | Loss: 0.7674 | LM: 0.2591 | LB: 1.0177 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:46:05] Epoch 3 | Step 10040 | Loss: 0.7672 | LM: 0.2591 | LB: 1.0176 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:46:16] Epoch 3 | Step 10050 | Loss: 0.7670 | LM: 0.2588 | LB: 1.0176 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:46:27] Epoch 3 | Step 10060 | Loss: 0.7671 | LM: 0.2592 | LB: 1.0176 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:46:39] Epoch 3 | Step 10070 | Loss: 0.7673 | LM: 0.2596 | LB: 1.0176 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:46:51] Epoch 3 | Step 10080 | Loss: 0.7678 | LM: 0.2606 | LB: 1.0176 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.192/SR1: 0.165 | LR: 1.00e-04 |
| [2026-05-24 09:47:02] Epoch 3 | Step 10090 | Loss: 0.7680 | LM: 0.2606 | LB: 1.0176 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:47:14] Epoch 3 | Step 10100 | Loss: 0.7678 | LM: 0.2601 | LB: 1.0176 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:47:25] Epoch 3 | Step 10110 | Loss: 0.7680 | LM: 0.2600 | LB: 1.0176 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:47:37] Epoch 3 | Step 10120 | Loss: 0.7682 | LM: 0.2601 | LB: 1.0176 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:47:48] Epoch 3 | Step 10130 | Loss: 0.7684 | LM: 0.2602 | LB: 1.0176 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:47:59] Epoch 3 | Step 10140 | Loss: 0.7680 | LM: 0.2594 | LB: 1.0176 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:48:10] Epoch 3 | Step 10150 | Loss: 0.7683 | LM: 0.2596 | LB: 1.0175 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.192/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:48:21] Epoch 3 | Step 10160 | Loss: 0.7683 | LM: 0.2598 | LB: 1.0176 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:48:32] Epoch 3 | Step 10170 | Loss: 0.7684 | LM: 0.2594 | LB: 1.0176 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:48:43] Epoch 3 | Step 10180 | Loss: 0.7683 | LM: 0.2596 | LB: 1.0176 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:48:54] Epoch 3 | Step 10190 | Loss: 0.7682 | LM: 0.2591 | LB: 1.0176 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:49:05] Epoch 3 | Step 10200 | Loss: 0.7680 | LM: 0.2583 | LB: 1.0176 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:49:15] Epoch 3 | Step 10210 | Loss: 0.7683 | LM: 0.2581 | LB: 1.0175 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:49:27] Epoch 3 | Step 10220 | Loss: 0.7681 | LM: 0.2582 | LB: 1.0176 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:49:38] Epoch 3 | Step 10230 | Loss: 0.7683 | LM: 0.2584 | LB: 1.0176 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:49:50] Epoch 3 | Step 10240 | Loss: 0.7686 | LM: 0.2588 | LB: 1.0177 | CL0: 4.0 | CL1: 5.3 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:50:01] Epoch 3 | Step 10250 | Loss: 0.7686 | LM: 0.2586 | LB: 1.0177 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:50:12] Epoch 3 | Step 10260 | Loss: 0.7687 | LM: 0.2584 | LB: 1.0177 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:50:23] Epoch 3 | Step 10270 | Loss: 0.7684 | LM: 0.2585 | LB: 1.0176 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:50:35] Epoch 3 | Step 10280 | Loss: 0.7685 | LM: 0.2587 | LB: 1.0176 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:50:46] Epoch 3 | Step 10290 | Loss: 0.7687 | LM: 0.2591 | LB: 1.0176 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:50:57] Epoch 3 | Step 10300 | Loss: 0.7687 | LM: 0.2591 | LB: 1.0175 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:51:08] Epoch 3 | Step 10310 | Loss: 0.7683 | LM: 0.2588 | LB: 1.0175 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:51:20] Epoch 3 | Step 10320 | Loss: 0.7683 | LM: 0.2590 | LB: 1.0175 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:51:31] Epoch 3 | Step 10330 | Loss: 0.7685 | LM: 0.2593 | LB: 1.0175 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:51:42] Epoch 3 | Step 10340 | Loss: 0.7687 | LM: 0.2598 | LB: 1.0175 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:51:53] Epoch 3 | Step 10350 | Loss: 0.7687 | LM: 0.2600 | LB: 1.0175 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:52:03] Epoch 3 | Step 10360 | Loss: 0.7687 | LM: 0.2600 | LB: 1.0175 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:52:14] Epoch 3 | Step 10370 | Loss: 0.7690 | LM: 0.2600 | LB: 1.0175 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:52:25] Epoch 3 | Step 10380 | Loss: 0.7688 | LM: 0.2594 | LB: 1.0175 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:52:37] Epoch 3 | Step 10390 | Loss: 0.7689 | LM: 0.2595 | LB: 1.0175 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:52:49] Epoch 3 | Step 10400 | Loss: 0.7691 | LM: 0.2602 | LB: 1.0175 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.219 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:53:00] Epoch 3 | Step 10410 | Loss: 0.7689 | LM: 0.2604 | LB: 1.0175 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:53:12] Epoch 3 | Step 10420 | Loss: 0.7693 | LM: 0.2609 | LB: 1.0175 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:53:23] Epoch 3 | Step 10430 | Loss: 0.7691 | LM: 0.2608 | LB: 1.0174 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:53:35] Epoch 3 | Step 10440 | Loss: 0.7686 | LM: 0.2605 | LB: 1.0174 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:53:46] Epoch 3 | Step 10450 | Loss: 0.7686 | LM: 0.2605 | LB: 1.0174 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:53:58] Epoch 3 | Step 10460 | Loss: 0.7686 | LM: 0.2604 | LB: 1.0174 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:54:10] Epoch 3 | Step 10470 | Loss: 0.7688 | LM: 0.2605 | LB: 1.0174 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:54:21] Epoch 3 | Step 10480 | Loss: 0.7688 | LM: 0.2604 | LB: 1.0174 | CL0: 4.0 | CL1: 5.2 | HR0: 0.250/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:54:33] Epoch 3 | Step 10490 | Loss: 0.7690 | LM: 0.2606 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:54:44] Epoch 3 | Step 10500 | Loss: 0.7689 | LM: 0.2606 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:54:56] Epoch 3 | Step 10510 | Loss: 0.7689 | LM: 0.2605 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:55:07] Epoch 3 | Step 10520 | Loss: 0.7692 | LM: 0.2608 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:55:19] Epoch 3 | Step 10530 | Loss: 0.7693 | LM: 0.2613 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:55:31] Epoch 3 | Step 10540 | Loss: 0.7691 | LM: 0.2613 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:55:43] Epoch 3 | Step 10550 | Loss: 0.7693 | LM: 0.2615 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:55:54] Epoch 3 | Step 10560 | Loss: 0.7694 | LM: 0.2617 | LB: 1.0174 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:56:06] Epoch 3 | Step 10570 | Loss: 0.7695 | LM: 0.2620 | LB: 1.0174 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:56:18] Epoch 3 | Step 10580 | Loss: 0.7697 | LM: 0.2622 | LB: 1.0174 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:56:29] Epoch 3 | Step 10590 | Loss: 0.7697 | LM: 0.2626 | LB: 1.0174 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:56:40] Epoch 3 | Step 10600 | Loss: 0.7697 | LM: 0.2624 | LB: 1.0174 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:56:51] Epoch 3 | Step 10610 | Loss: 0.7697 | LM: 0.2625 | LB: 1.0174 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:57:02] Epoch 3 | Step 10620 | Loss: 0.7697 | LM: 0.2623 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:57:12] Epoch 3 | Step 10630 | Loss: 0.7698 | LM: 0.2627 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:57:23] Epoch 3 | Step 10640 | Loss: 0.7701 | LM: 0.2633 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:57:34] Epoch 3 | Step 10650 | Loss: 0.7703 | LM: 0.2633 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:57:45] Epoch 3 | Step 10660 | Loss: 0.7701 | LM: 0.2633 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:57:55] Epoch 3 | Step 10670 | Loss: 0.7702 | LM: 0.2634 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:58:06] Epoch 3 | Step 10680 | Loss: 0.7702 | LM: 0.2634 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:58:17] Epoch 3 | Step 10690 | Loss: 0.7702 | LM: 0.2640 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:58:28] Epoch 3 | Step 10700 | Loss: 0.7707 | LM: 0.2645 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:58:38] Epoch 3 | Step 10710 | Loss: 0.7707 | LM: 0.2648 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:58:49] Epoch 3 | Step 10720 | Loss: 0.7708 | LM: 0.2648 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:59:00] Epoch 3 | Step 10730 | Loss: 0.7709 | LM: 0.2649 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:59:12] Epoch 3 | Step 10740 | Loss: 0.7708 | LM: 0.2648 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:59:23] Epoch 3 | Step 10750 | Loss: 0.7708 | LM: 0.2646 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:59:35] Epoch 3 | Step 10760 | Loss: 0.7707 | LM: 0.2645 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:59:46] Epoch 3 | Step 10770 | Loss: 0.7710 | LM: 0.2654 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 09:59:58] Epoch 3 | Step 10780 | Loss: 0.7709 | LM: 0.2651 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:00:10] Epoch 3 | Step 10790 | Loss: 0.7707 | LM: 0.2652 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 10:00:21] Epoch 3 | Step 10800 | Loss: 0.7709 | LM: 0.2652 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 10:00:32] Epoch 3 | Step 10810 | Loss: 0.7709 | LM: 0.2651 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 10:00:42] Epoch 3 | Step 10820 | Loss: 0.7710 | LM: 0.2652 | LB: 1.0173 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:00:53] Epoch 3 | Step 10830 | Loss: 0.7710 | LM: 0.2650 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:01:04] Epoch 3 | Step 10840 | Loss: 0.7709 | LM: 0.2648 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:01:16] Epoch 3 | Step 10850 | Loss: 0.7709 | LM: 0.2649 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:01:27] Epoch 3 | Step 10860 | Loss: 0.7710 | LM: 0.2647 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:01:39] Epoch 3 | Step 10870 | Loss: 0.7711 | LM: 0.2646 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:01:51] Epoch 3 | Step 10880 | Loss: 0.7714 | LM: 0.2648 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:02:02] Epoch 3 | Step 10890 | Loss: 0.7713 | LM: 0.2647 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:02:14] Epoch 3 | Step 10900 | Loss: 0.7713 | LM: 0.2648 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:02:25] Epoch 3 | Step 10910 | Loss: 0.7714 | LM: 0.2648 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:02:37] Epoch 3 | Step 10920 | Loss: 0.7712 | LM: 0.2650 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 10:02:48] Epoch 3 | Step 10930 | Loss: 0.7712 | LM: 0.2649 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 10:03:00] Epoch 3 | Step 10940 | Loss: 0.7712 | LM: 0.2648 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 10:03:11] Epoch 3 | Step 10950 | Loss: 0.7714 | LM: 0.2649 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:03:23] Epoch 3 | Step 10960 | Loss: 0.7716 | LM: 0.2653 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:03:35] Epoch 3 | Step 10970 | Loss: 0.7717 | LM: 0.2652 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:03:46] Epoch 3 | Step 10980 | Loss: 0.7717 | LM: 0.2650 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:03:58] Epoch 3 | Step 10990 | Loss: 0.7717 | LM: 0.2650 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:04:09] Epoch 3 | Step 11000 | Loss: 0.7717 | LM: 0.2649 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:04:11] Validation | Batch 10/1463 | Loss: 0.8620 | LM_LOSS: 0.3567 | LB_LOSS: 1.0106 |
| [2026-05-24 10:04:12] Validation | Batch 20/1463 | Loss: 0.8788 | LM_LOSS: 0.3724 | LB_LOSS: 1.0127 |
| [2026-05-24 10:04:14] Validation | Batch 30/1463 | Loss: 0.8798 | LM_LOSS: 0.3730 | LB_LOSS: 1.0135 |
| [2026-05-24 10:04:16] Validation | Batch 40/1463 | Loss: 0.8901 | LM_LOSS: 0.3829 | LB_LOSS: 1.0143 |
| [2026-05-24 10:04:18] Validation | Batch 50/1463 | Loss: 0.8982 | LM_LOSS: 0.3913 | LB_LOSS: 1.0138 |
| [2026-05-24 10:04:20] Validation | Batch 60/1463 | Loss: 0.8998 | LM_LOSS: 0.3928 | LB_LOSS: 1.0139 |
| [2026-05-24 10:04:22] Validation | Batch 70/1463 | Loss: 0.8994 | LM_LOSS: 0.3924 | LB_LOSS: 1.0139 |
| [2026-05-24 10:04:24] Validation | Batch 80/1463 | Loss: 0.9016 | LM_LOSS: 0.3946 | LB_LOSS: 1.0139 |
| [2026-05-24 10:04:26] Validation | Batch 90/1463 | Loss: 0.9001 | LM_LOSS: 0.3931 | LB_LOSS: 1.0139 |
| [2026-05-24 10:04:27] Validation | Batch 100/1463 | Loss: 0.8998 | LM_LOSS: 0.3929 | LB_LOSS: 1.0139 |
| [2026-05-24 10:04:29] Validation | Batch 110/1463 | Loss: 0.8974 | LM_LOSS: 0.3904 | LB_LOSS: 1.0142 |
| [2026-05-24 10:04:31] Validation | Batch 120/1463 | Loss: 0.8993 | LM_LOSS: 0.3922 | LB_LOSS: 1.0142 |
| [2026-05-24 10:04:32] Validation | Batch 130/1463 | Loss: 0.9023 | LM_LOSS: 0.3952 | LB_LOSS: 1.0142 |
| [2026-05-24 10:04:34] Validation | Batch 140/1463 | Loss: 0.9039 | LM_LOSS: 0.3968 | LB_LOSS: 1.0142 |
| [2026-05-24 10:04:36] Validation | Batch 150/1463 | Loss: 0.9028 | LM_LOSS: 0.3956 | LB_LOSS: 1.0143 |
| [2026-05-24 10:04:38] Validation | Batch 160/1463 | Loss: 0.9041 | LM_LOSS: 0.3970 | LB_LOSS: 1.0142 |
| [2026-05-24 10:04:40] Validation | Batch 170/1463 | Loss: 0.9033 | LM_LOSS: 0.3962 | LB_LOSS: 1.0142 |
| [2026-05-24 10:04:42] Validation | Batch 180/1463 | Loss: 0.9034 | LM_LOSS: 0.3963 | LB_LOSS: 1.0143 |
| [2026-05-24 10:04:44] Validation | Batch 190/1463 | Loss: 0.9043 | LM_LOSS: 0.3972 | LB_LOSS: 1.0143 |
| [2026-05-24 10:04:45] Validation | Batch 200/1463 | Loss: 0.9040 | LM_LOSS: 0.3968 | LB_LOSS: 1.0143 |
| [2026-05-24 10:04:47] Validation | Batch 210/1463 | Loss: 0.9044 | LM_LOSS: 0.3973 | LB_LOSS: 1.0143 |
| [2026-05-24 10:04:49] Validation | Batch 220/1463 | Loss: 0.9035 | LM_LOSS: 0.3964 | LB_LOSS: 1.0144 |
| [2026-05-24 10:04:51] Validation | Batch 230/1463 | Loss: 0.9054 | LM_LOSS: 0.3983 | LB_LOSS: 1.0143 |
| [2026-05-24 10:04:53] Validation | Batch 240/1463 | Loss: 0.9064 | LM_LOSS: 0.3993 | LB_LOSS: 1.0142 |
| [2026-05-24 10:04:55] Validation | Batch 250/1463 | Loss: 0.9049 | LM_LOSS: 0.3978 | LB_LOSS: 1.0142 |
| [2026-05-24 10:04:56] Validation | Batch 260/1463 | Loss: 0.9067 | LM_LOSS: 0.3995 | LB_LOSS: 1.0144 |
| [2026-05-24 10:04:58] Validation | Batch 270/1463 | Loss: 0.9052 | LM_LOSS: 0.3981 | LB_LOSS: 1.0144 |
| [2026-05-24 10:05:00] Validation | Batch 280/1463 | Loss: 0.9064 | LM_LOSS: 0.3992 | LB_LOSS: 1.0144 |
| [2026-05-24 10:05:02] Validation | Batch 290/1463 | Loss: 0.9054 | LM_LOSS: 0.3982 | LB_LOSS: 1.0144 |
| [2026-05-24 10:05:03] Validation | Batch 300/1463 | Loss: 0.9060 | LM_LOSS: 0.3988 | LB_LOSS: 1.0145 |
| [2026-05-24 10:05:05] Validation | Batch 310/1463 | Loss: 0.9065 | LM_LOSS: 0.3992 | LB_LOSS: 1.0145 |
| [2026-05-24 10:05:07] Validation | Batch 320/1463 | Loss: 0.9052 | LM_LOSS: 0.3980 | LB_LOSS: 1.0143 |
| [2026-05-24 10:05:08] Validation | Batch 330/1463 | Loss: 0.9052 | LM_LOSS: 0.3980 | LB_LOSS: 1.0143 |
| [2026-05-24 10:05:10] Validation | Batch 340/1463 | Loss: 0.9046 | LM_LOSS: 0.3974 | LB_LOSS: 1.0144 |
| [2026-05-24 10:05:12] Validation | Batch 350/1463 | Loss: 0.9053 | LM_LOSS: 0.3981 | LB_LOSS: 1.0143 |
| [2026-05-24 10:05:14] Validation | Batch 360/1463 | Loss: 0.9055 | LM_LOSS: 0.3983 | LB_LOSS: 1.0144 |
| [2026-05-24 10:05:15] Validation | Batch 370/1463 | Loss: 0.9053 | LM_LOSS: 0.3981 | LB_LOSS: 1.0144 |
| [2026-05-24 10:05:17] Validation | Batch 380/1463 | Loss: 0.9050 | LM_LOSS: 0.3979 | LB_LOSS: 1.0143 |
| [2026-05-24 10:05:19] Validation | Batch 390/1463 | Loss: 0.9060 | LM_LOSS: 0.3988 | LB_LOSS: 1.0143 |
| [2026-05-24 10:05:20] Validation | Batch 400/1463 | Loss: 0.9059 | LM_LOSS: 0.3988 | LB_LOSS: 1.0144 |
| [2026-05-24 10:05:22] Validation | Batch 410/1463 | Loss: 0.9056 | LM_LOSS: 0.3984 | LB_LOSS: 1.0144 |
| [2026-05-24 10:05:24] Validation | Batch 420/1463 | Loss: 0.9057 | LM_LOSS: 0.3985 | LB_LOSS: 1.0144 |
| [2026-05-24 10:05:26] Validation | Batch 430/1463 | Loss: 0.9054 | LM_LOSS: 0.3982 | LB_LOSS: 1.0145 |
| [2026-05-24 10:05:27] Validation | Batch 440/1463 | Loss: 0.9058 | LM_LOSS: 0.3985 | LB_LOSS: 1.0145 |
| [2026-05-24 10:05:29] Validation | Batch 450/1463 | Loss: 0.9057 | LM_LOSS: 0.3984 | LB_LOSS: 1.0146 |
| [2026-05-24 10:05:31] Validation | Batch 460/1463 | Loss: 0.9058 | LM_LOSS: 0.3985 | LB_LOSS: 1.0146 |
| [2026-05-24 10:05:33] Validation | Batch 470/1463 | Loss: 0.9065 | LM_LOSS: 0.3993 | LB_LOSS: 1.0145 |
| [2026-05-24 10:05:35] Validation | Batch 480/1463 | Loss: 0.9064 | LM_LOSS: 0.3992 | LB_LOSS: 1.0145 |
| [2026-05-24 10:05:37] Validation | Batch 490/1463 | Loss: 0.9062 | LM_LOSS: 0.3989 | LB_LOSS: 1.0145 |
| [2026-05-24 10:05:39] Validation | Batch 500/1463 | Loss: 0.9059 | LM_LOSS: 0.3987 | LB_LOSS: 1.0145 |
| [2026-05-24 10:05:41] Validation | Batch 510/1463 | Loss: 0.9053 | LM_LOSS: 0.3981 | LB_LOSS: 1.0145 |
| [2026-05-24 10:05:42] Validation | Batch 520/1463 | Loss: 0.9050 | LM_LOSS: 0.3977 | LB_LOSS: 1.0145 |
| [2026-05-24 10:05:44] Validation | Batch 530/1463 | Loss: 0.9054 | LM_LOSS: 0.3982 | LB_LOSS: 1.0145 |
| [2026-05-24 10:05:45] Validation | Batch 540/1463 | Loss: 0.9057 | LM_LOSS: 0.3984 | LB_LOSS: 1.0145 |
| [2026-05-24 10:05:47] Validation | Batch 550/1463 | Loss: 0.9054 | LM_LOSS: 0.3981 | LB_LOSS: 1.0145 |
| [2026-05-24 10:05:49] Validation | Batch 560/1463 | Loss: 0.9059 | LM_LOSS: 0.3986 | LB_LOSS: 1.0146 |
| [2026-05-24 10:05:51] Validation | Batch 570/1463 | Loss: 0.9058 | LM_LOSS: 0.3986 | LB_LOSS: 1.0146 |
| [2026-05-24 10:05:52] Validation | Batch 580/1463 | Loss: 0.9054 | LM_LOSS: 0.3981 | LB_LOSS: 1.0146 |
| [2026-05-24 10:05:54] Validation | Batch 590/1463 | Loss: 0.9053 | LM_LOSS: 0.3980 | LB_LOSS: 1.0146 |
| [2026-05-24 10:05:56] Validation | Batch 600/1463 | Loss: 0.9055 | LM_LOSS: 0.3982 | LB_LOSS: 1.0147 |
| [2026-05-24 10:05:58] Validation | Batch 610/1463 | Loss: 0.9056 | LM_LOSS: 0.3983 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:00] Validation | Batch 620/1463 | Loss: 0.9048 | LM_LOSS: 0.3975 | LB_LOSS: 1.0146 |
| [2026-05-24 10:06:02] Validation | Batch 630/1463 | Loss: 0.9044 | LM_LOSS: 0.3971 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:03] Validation | Batch 640/1463 | Loss: 0.9042 | LM_LOSS: 0.3968 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:05] Validation | Batch 650/1463 | Loss: 0.9037 | LM_LOSS: 0.3964 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:07] Validation | Batch 660/1463 | Loss: 0.9032 | LM_LOSS: 0.3958 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:08] Validation | Batch 670/1463 | Loss: 0.9028 | LM_LOSS: 0.3954 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:10] Validation | Batch 680/1463 | Loss: 0.9028 | LM_LOSS: 0.3955 | LB_LOSS: 1.0146 |
| [2026-05-24 10:06:12] Validation | Batch 690/1463 | Loss: 0.9032 | LM_LOSS: 0.3958 | LB_LOSS: 1.0146 |
| [2026-05-24 10:06:14] Validation | Batch 700/1463 | Loss: 0.9030 | LM_LOSS: 0.3957 | LB_LOSS: 1.0146 |
| [2026-05-24 10:06:15] Validation | Batch 710/1463 | Loss: 0.9034 | LM_LOSS: 0.3961 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:17] Validation | Batch 720/1463 | Loss: 0.9041 | LM_LOSS: 0.3967 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:19] Validation | Batch 730/1463 | Loss: 0.9039 | LM_LOSS: 0.3965 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:20] Validation | Batch 740/1463 | Loss: 0.9035 | LM_LOSS: 0.3961 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:21] Validation | Batch 750/1463 | Loss: 0.9033 | LM_LOSS: 0.3960 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:23] Validation | Batch 760/1463 | Loss: 0.9029 | LM_LOSS: 0.3956 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:25] Validation | Batch 770/1463 | Loss: 0.9027 | LM_LOSS: 0.3954 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:26] Validation | Batch 780/1463 | Loss: 0.9025 | LM_LOSS: 0.3952 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:28] Validation | Batch 790/1463 | Loss: 0.9027 | LM_LOSS: 0.3954 | LB_LOSS: 1.0146 |
| [2026-05-24 10:06:29] Validation | Batch 800/1463 | Loss: 0.9027 | LM_LOSS: 0.3953 | LB_LOSS: 1.0146 |
| [2026-05-24 10:06:31] Validation | Batch 810/1463 | Loss: 0.9023 | LM_LOSS: 0.3949 | LB_LOSS: 1.0146 |
| [2026-05-24 10:06:33] Validation | Batch 820/1463 | Loss: 0.9025 | LM_LOSS: 0.3952 | LB_LOSS: 1.0146 |
| [2026-05-24 10:06:34] Validation | Batch 830/1463 | Loss: 0.9025 | LM_LOSS: 0.3952 | LB_LOSS: 1.0146 |
| [2026-05-24 10:06:36] Validation | Batch 840/1463 | Loss: 0.9024 | LM_LOSS: 0.3951 | LB_LOSS: 1.0146 |
| [2026-05-24 10:06:38] Validation | Batch 850/1463 | Loss: 0.9027 | LM_LOSS: 0.3953 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:40] Validation | Batch 860/1463 | Loss: 0.9027 | LM_LOSS: 0.3954 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:42] Validation | Batch 870/1463 | Loss: 0.9029 | LM_LOSS: 0.3955 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:43] Validation | Batch 880/1463 | Loss: 0.9022 | LM_LOSS: 0.3949 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:45] Validation | Batch 890/1463 | Loss: 0.9022 | LM_LOSS: 0.3949 | LB_LOSS: 1.0146 |
| [2026-05-24 10:06:47] Validation | Batch 900/1463 | Loss: 0.9020 | LM_LOSS: 0.3947 | LB_LOSS: 1.0146 |
| [2026-05-24 10:06:49] Validation | Batch 910/1463 | Loss: 0.9020 | LM_LOSS: 0.3947 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:51] Validation | Batch 920/1463 | Loss: 0.9023 | LM_LOSS: 0.3949 | LB_LOSS: 1.0147 |
| [2026-05-24 10:06:52] Validation | Batch 930/1463 | Loss: 0.9019 | LM_LOSS: 0.3945 | LB_LOSS: 1.0146 |
| [2026-05-24 10:06:54] Validation | Batch 940/1463 | Loss: 0.9015 | LM_LOSS: 0.3942 | LB_LOSS: 1.0146 |
| [2026-05-24 10:06:56] Validation | Batch 950/1463 | Loss: 0.9020 | LM_LOSS: 0.3946 | LB_LOSS: 1.0146 |
| [2026-05-24 10:06:58] Validation | Batch 960/1463 | Loss: 0.9021 | LM_LOSS: 0.3948 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:00] Validation | Batch 970/1463 | Loss: 0.9022 | LM_LOSS: 0.3949 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:02] Validation | Batch 980/1463 | Loss: 0.9025 | LM_LOSS: 0.3952 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:03] Validation | Batch 990/1463 | Loss: 0.9026 | LM_LOSS: 0.3953 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:05] Validation | Batch 1000/1463 | Loss: 0.9032 | LM_LOSS: 0.3960 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:07] Validation | Batch 1010/1463 | Loss: 0.9033 | LM_LOSS: 0.3959 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:09] Validation | Batch 1020/1463 | Loss: 0.9034 | LM_LOSS: 0.3961 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:11] Validation | Batch 1030/1463 | Loss: 0.9038 | LM_LOSS: 0.3965 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:12] Validation | Batch 1040/1463 | Loss: 0.9032 | LM_LOSS: 0.3959 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:14] Validation | Batch 1050/1463 | Loss: 0.9032 | LM_LOSS: 0.3959 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:16] Validation | Batch 1060/1463 | Loss: 0.9031 | LM_LOSS: 0.3958 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:18] Validation | Batch 1070/1463 | Loss: 0.9031 | LM_LOSS: 0.3958 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:20] Validation | Batch 1080/1463 | Loss: 0.9028 | LM_LOSS: 0.3955 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:21] Validation | Batch 1090/1463 | Loss: 0.9028 | LM_LOSS: 0.3955 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:23] Validation | Batch 1100/1463 | Loss: 0.9027 | LM_LOSS: 0.3955 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:25] Validation | Batch 1110/1463 | Loss: 0.9028 | LM_LOSS: 0.3955 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:26] Validation | Batch 1120/1463 | Loss: 0.9026 | LM_LOSS: 0.3953 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:28] Validation | Batch 1130/1463 | Loss: 0.9023 | LM_LOSS: 0.3950 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:30] Validation | Batch 1140/1463 | Loss: 0.9026 | LM_LOSS: 0.3953 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:32] Validation | Batch 1150/1463 | Loss: 0.9026 | LM_LOSS: 0.3953 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:34] Validation | Batch 1160/1463 | Loss: 0.9026 | LM_LOSS: 0.3953 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:36] Validation | Batch 1170/1463 | Loss: 0.9024 | LM_LOSS: 0.3951 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:37] Validation | Batch 1180/1463 | Loss: 0.9024 | LM_LOSS: 0.3951 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:39] Validation | Batch 1190/1463 | Loss: 0.9027 | LM_LOSS: 0.3954 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:41] Validation | Batch 1200/1463 | Loss: 0.9028 | LM_LOSS: 0.3955 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:43] Validation | Batch 1210/1463 | Loss: 0.9031 | LM_LOSS: 0.3958 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:45] Validation | Batch 1220/1463 | Loss: 0.9036 | LM_LOSS: 0.3963 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:46] Validation | Batch 1230/1463 | Loss: 0.9035 | LM_LOSS: 0.3962 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:48] Validation | Batch 1240/1463 | Loss: 0.9038 | LM_LOSS: 0.3965 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:50] Validation | Batch 1250/1463 | Loss: 0.9040 | LM_LOSS: 0.3967 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:52] Validation | Batch 1260/1463 | Loss: 0.9039 | LM_LOSS: 0.3966 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:54] Validation | Batch 1270/1463 | Loss: 0.9037 | LM_LOSS: 0.3964 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:56] Validation | Batch 1280/1463 | Loss: 0.9034 | LM_LOSS: 0.3961 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:57] Validation | Batch 1290/1463 | Loss: 0.9035 | LM_LOSS: 0.3962 | LB_LOSS: 1.0146 |
| [2026-05-24 10:07:59] Validation | Batch 1300/1463 | Loss: 0.9032 | LM_LOSS: 0.3959 | LB_LOSS: 1.0146 |
| [2026-05-24 10:08:01] Validation | Batch 1310/1463 | Loss: 0.9031 | LM_LOSS: 0.3958 | LB_LOSS: 1.0146 |
| [2026-05-24 10:08:02] Validation | Batch 1320/1463 | Loss: 0.9031 | LM_LOSS: 0.3958 | LB_LOSS: 1.0146 |
| [2026-05-24 10:08:04] Validation | Batch 1330/1463 | Loss: 0.9030 | LM_LOSS: 0.3957 | LB_LOSS: 1.0146 |
| [2026-05-24 10:08:05] Validation | Batch 1340/1463 | Loss: 0.9032 | LM_LOSS: 0.3959 | LB_LOSS: 1.0146 |
| [2026-05-24 10:08:07] Validation | Batch 1350/1463 | Loss: 0.9032 | LM_LOSS: 0.3959 | LB_LOSS: 1.0146 |
| [2026-05-24 10:08:09] Validation | Batch 1360/1463 | Loss: 0.9035 | LM_LOSS: 0.3962 | LB_LOSS: 1.0146 |
| [2026-05-24 10:08:11] Validation | Batch 1370/1463 | Loss: 0.9040 | LM_LOSS: 0.3967 | LB_LOSS: 1.0146 |
| [2026-05-24 10:08:13] Validation | Batch 1380/1463 | Loss: 0.9038 | LM_LOSS: 0.3965 | LB_LOSS: 1.0146 |
| [2026-05-24 10:08:14] Validation | Batch 1390/1463 | Loss: 0.9037 | LM_LOSS: 0.3964 | LB_LOSS: 1.0146 |
| [2026-05-24 10:08:16] Validation | Batch 1400/1463 | Loss: 0.9040 | LM_LOSS: 0.3967 | LB_LOSS: 1.0146 |
| [2026-05-24 10:08:18] Validation | Batch 1410/1463 | Loss: 0.9042 | LM_LOSS: 0.3969 | LB_LOSS: 1.0146 |
| [2026-05-24 10:08:20] Validation | Batch 1420/1463 | Loss: 0.9042 | LM_LOSS: 0.3969 | LB_LOSS: 1.0146 |
| [2026-05-24 10:08:21] Validation | Batch 1430/1463 | Loss: 0.9042 | LM_LOSS: 0.3969 | LB_LOSS: 1.0146 |
| [2026-05-24 10:08:23] Validation | Batch 1440/1463 | Loss: 0.9047 | LM_LOSS: 0.3974 | LB_LOSS: 1.0146 |
| [2026-05-24 10:08:25] Validation | Batch 1450/1463 | Loss: 0.9043 | LM_LOSS: 0.3970 | LB_LOSS: 1.0146 |
| [2026-05-24 10:08:27] Validation | Batch 1460/1463 | Loss: 0.9046 | LM_LOSS: 0.3973 | LB_LOSS: 1.0146 |
| [2026-05-24 10:08:27] Validation | Batch 1463/1463 | Loss: 0.9045 | LM_LOSS: 0.3972 | LB_LOSS: 1.0145 |
| [2026-05-24 10:08:27] Validation | Loss: 0.9045 | LM_LOSS: 0.3972 | LB_LOSS: 1.0145 | PPL: 1.49 | Time: 258.04s |
| [2026-05-24 10:08:39] Epoch 3 | Step 11010 | Loss: 0.7717 | LM: 0.2649 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.193/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:08:51] Epoch 3 | Step 11020 | Loss: 0.7718 | LM: 0.2651 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:09:02] Epoch 3 | Step 11030 | Loss: 0.7717 | LM: 0.2651 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:09:14] Epoch 3 | Step 11040 | Loss: 0.7718 | LM: 0.2655 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:09:26] Epoch 3 | Step 11050 | Loss: 0.7718 | LM: 0.2654 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:09:37] Epoch 3 | Step 11060 | Loss: 0.7719 | LM: 0.2656 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:09:48] Epoch 3 | Step 11070 | Loss: 0.7719 | LM: 0.2655 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:10:00] Epoch 3 | Step 11080 | Loss: 0.7721 | LM: 0.2658 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:10:11] Epoch 3 | Step 11090 | Loss: 0.7722 | LM: 0.2660 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 10:10:23] Epoch 3 | Step 11100 | Loss: 0.7723 | LM: 0.2665 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 10:10:33] Epoch 3 | Step 11110 | Loss: 0.7723 | LM: 0.2665 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 10:10:44] Epoch 3 | Step 11120 | Loss: 0.7724 | LM: 0.2667 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 10:10:55] Epoch 3 | Step 11130 | Loss: 0.7724 | LM: 0.2668 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:11:05] Epoch 3 | Step 11140 | Loss: 0.7724 | LM: 0.2670 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 10:11:16] Epoch 3 | Step 11150 | Loss: 0.7726 | LM: 0.2671 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 10:11:26] Epoch 3 | Step 11160 | Loss: 0.7726 | LM: 0.2670 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 10:11:37] Epoch 3 | Step 11170 | Loss: 0.7728 | LM: 0.2673 | LB: 1.0172 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-04 |
| [2026-05-24 10:11:49] Epoch 3 | Step 11180 | Loss: 0.7728 | LM: 0.2674 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:12:00] Epoch 3 | Step 11190 | Loss: 0.7728 | LM: 0.2675 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:12:11] Epoch 3 | Step 11200 | Loss: 0.7728 | LM: 0.2673 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:12:22] Epoch 3 | Step 11210 | Loss: 0.7729 | LM: 0.2672 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:12:33] Epoch 3 | Step 11220 | Loss: 0.7729 | LM: 0.2670 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:12:44] Epoch 3 | Step 11230 | Loss: 0.7728 | LM: 0.2666 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:12:56] Epoch 3 | Step 11240 | Loss: 0.7729 | LM: 0.2667 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:13:07] Epoch 3 | Step 11250 | Loss: 0.7730 | LM: 0.2668 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:13:18] Epoch 3 | Step 11260 | Loss: 0.7730 | LM: 0.2667 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:13:29] Epoch 3 | Step 11270 | Loss: 0.7729 | LM: 0.2667 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.249/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:13:40] Epoch 3 | Step 11280 | Loss: 0.7730 | LM: 0.2667 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:13:52] Epoch 3 | Step 11290 | Loss: 0.7731 | LM: 0.2670 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 1.00e-04 |
| [2026-05-24 10:14:02] Epoch 3 | Step 11300 | Loss: 0.7731 | LM: 0.2669 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 9.99e-05 |
| [2026-05-24 10:14:14] Epoch 3 | Step 11310 | Loss: 0.7731 | LM: 0.2668 | LB: 1.0170 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 9.99e-05 |
| [2026-05-24 10:14:25] Epoch 3 | Step 11320 | Loss: 0.7730 | LM: 0.2666 | LB: 1.0170 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 9.99e-05 |
| [2026-05-24 10:14:36] Epoch 3 | Step 11330 | Loss: 0.7731 | LM: 0.2670 | LB: 1.0170 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 9.98e-05 |
| [2026-05-24 10:14:47] Epoch 3 | Step 11340 | Loss: 0.7732 | LM: 0.2669 | LB: 1.0170 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 9.98e-05 |
| [2026-05-24 10:14:58] Epoch 3 | Step 11350 | Loss: 0.7730 | LM: 0.2668 | LB: 1.0171 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 9.97e-05 |
| [2026-05-24 10:15:09] Epoch 3 | Step 11360 | Loss: 0.7730 | LM: 0.2668 | LB: 1.0170 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 9.97e-05 |
| [2026-05-24 10:15:21] Epoch 3 | Step 11370 | Loss: 0.7729 | LM: 0.2664 | LB: 1.0170 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 9.96e-05 |
| [2026-05-24 10:15:32] Epoch 3 | Step 11380 | Loss: 0.7729 | LM: 0.2663 | LB: 1.0170 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.95e-05 |
| [2026-05-24 10:15:43] Epoch 3 | Step 11390 | Loss: 0.7731 | LM: 0.2666 | LB: 1.0170 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.95e-05 |
| [2026-05-24 10:15:54] Epoch 3 | Step 11400 | Loss: 0.7731 | LM: 0.2667 | LB: 1.0170 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.94e-05 |
| [2026-05-24 10:16:05] Epoch 3 | Step 11410 | Loss: 0.7733 | LM: 0.2667 | LB: 1.0170 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.218 | HR1: 0.194/SR1: 0.166 | LR: 9.93e-05 |
| [2026-05-24 10:16:15] Epoch 3 | Step 11420 | Loss: 0.7733 | LM: 0.2667 | LB: 1.0170 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.92e-05 |
| [2026-05-24 10:16:26] Epoch 3 | Step 11430 | Loss: 0.7733 | LM: 0.2668 | LB: 1.0170 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.91e-05 |
| [2026-05-24 10:16:37] Epoch 3 | Step 11440 | Loss: 0.7733 | LM: 0.2670 | LB: 1.0170 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.90e-05 |
| [2026-05-24 10:16:48] Epoch 3 | Step 11450 | Loss: 0.7734 | LM: 0.2668 | LB: 1.0170 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.89e-05 |
| [2026-05-24 10:16:58] Epoch 3 | Step 11460 | Loss: 0.7734 | LM: 0.2671 | LB: 1.0170 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.88e-05 |
| [2026-05-24 10:17:09] Epoch 3 | Step 11470 | Loss: 0.7735 | LM: 0.2671 | LB: 1.0170 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.86e-05 |
| [2026-05-24 10:17:19] Epoch 3 | Step 11480 | Loss: 0.7737 | LM: 0.2670 | LB: 1.0170 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.193/SR1: 0.166 | LR: 9.85e-05 |
| [2026-05-24 10:17:30] Epoch 3 | Step 11490 | Loss: 0.7737 | LM: 0.2672 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.193/SR1: 0.166 | LR: 9.84e-05 |
| [2026-05-24 10:17:40] Epoch 3 | Step 11500 | Loss: 0.7737 | LM: 0.2674 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.193/SR1: 0.166 | LR: 9.83e-05 |
| [2026-05-24 10:17:51] Epoch 3 | Step 11510 | Loss: 0.7737 | LM: 0.2675 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.193/SR1: 0.166 | LR: 9.81e-05 |
| [2026-05-24 10:18:02] Epoch 3 | Step 11520 | Loss: 0.7738 | LM: 0.2675 | LB: 1.0169 | CL0: 4.0 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.80e-05 |
| [2026-05-24 10:18:12] Epoch 3 | Step 11530 | Loss: 0.7741 | LM: 0.2679 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.78e-05 |
| [2026-05-24 10:18:23] Epoch 3 | Step 11540 | Loss: 0.7741 | LM: 0.2678 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.193/SR1: 0.166 | LR: 9.77e-05 |
| [2026-05-24 10:18:34] Epoch 3 | Step 11550 | Loss: 0.7742 | LM: 0.2679 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.193/SR1: 0.166 | LR: 9.75e-05 |
| [2026-05-24 10:18:45] Epoch 3 | Step 11560 | Loss: 0.7743 | LM: 0.2679 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.73e-05 |
| [2026-05-24 10:18:56] Epoch 3 | Step 11570 | Loss: 0.7744 | LM: 0.2682 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.72e-05 |
| [2026-05-24 10:19:06] Epoch 3 | Step 11580 | Loss: 0.7744 | LM: 0.2684 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.70e-05 |
| [2026-05-24 10:19:17] Epoch 3 | Step 11590 | Loss: 0.7746 | LM: 0.2687 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.68e-05 |
| [2026-05-24 10:19:28] Epoch 3 | Step 11600 | Loss: 0.7745 | LM: 0.2684 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.66e-05 |
| [2026-05-24 10:19:38] Epoch 3 | Step 11610 | Loss: 0.7745 | LM: 0.2684 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.64e-05 |
| [2026-05-24 10:19:49] Epoch 3 | Step 11620 | Loss: 0.7746 | LM: 0.2683 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.62e-05 |
| [2026-05-24 10:19:59] Epoch 3 | Step 11630 | Loss: 0.7747 | LM: 0.2684 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.60e-05 |
| [2026-05-24 10:20:10] Epoch 3 | Step 11640 | Loss: 0.7747 | LM: 0.2683 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.58e-05 |
| [2026-05-24 10:20:20] Epoch 3 | Step 11650 | Loss: 0.7747 | LM: 0.2682 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.193/SR1: 0.166 | LR: 9.56e-05 |
| [2026-05-24 10:20:31] Epoch 3 | Step 11660 | Loss: 0.7747 | LM: 0.2681 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.193/SR1: 0.166 | LR: 9.54e-05 |
| [2026-05-24 10:20:42] Epoch 3 | Step 11670 | Loss: 0.7747 | LM: 0.2682 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.51e-05 |
| [2026-05-24 10:20:53] Epoch 3 | Step 11680 | Loss: 0.7747 | LM: 0.2682 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.49e-05 |
| [2026-05-24 10:21:04] Epoch 3 | Step 11690 | Loss: 0.7748 | LM: 0.2682 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.47e-05 |
| [2026-05-24 10:21:14] Epoch 3 | Step 11700 | Loss: 0.7749 | LM: 0.2682 | LB: 1.0169 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.44e-05 |
| [2026-05-24 10:21:25] Epoch 3 | Step 11710 | Loss: 0.7749 | LM: 0.2680 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.42e-05 |
| [2026-05-24 10:21:35] Epoch 3 | Step 11720 | Loss: 0.7750 | LM: 0.2681 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.39e-05 |
| [2026-05-24 10:21:46] Epoch 3 | Step 11730 | Loss: 0.7751 | LM: 0.2680 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.37e-05 |
| [2026-05-24 10:21:57] Epoch 3 | Step 11740 | Loss: 0.7751 | LM: 0.2680 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.34e-05 |
| [2026-05-24 10:22:07] Epoch 3 | Step 11750 | Loss: 0.7751 | LM: 0.2681 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.32e-05 |
| [2026-05-24 10:22:18] Epoch 3 | Step 11760 | Loss: 0.7752 | LM: 0.2680 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.29e-05 |
| [2026-05-24 10:22:28] Epoch 3 | Step 11770 | Loss: 0.7753 | LM: 0.2682 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.26e-05 |
| [2026-05-24 10:22:39] Epoch 3 | Step 11780 | Loss: 0.7754 | LM: 0.2683 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.23e-05 |
| [2026-05-24 10:22:50] Epoch 3 | Step 11790 | Loss: 0.7754 | LM: 0.2683 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.21e-05 |
| [2026-05-24 10:23:00] Epoch 3 | Step 11800 | Loss: 0.7756 | LM: 0.2686 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.18e-05 |
| [2026-05-24 10:23:11] Epoch 3 | Step 11810 | Loss: 0.7756 | LM: 0.2685 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.15e-05 |
| [2026-05-24 10:23:22] Epoch 3 | Step 11820 | Loss: 0.7756 | LM: 0.2685 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.12e-05 |
| [2026-05-24 10:23:33] Epoch 3 | Step 11830 | Loss: 0.7756 | LM: 0.2685 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.09e-05 |
| [2026-05-24 10:23:44] Epoch 3 | Step 11840 | Loss: 0.7756 | LM: 0.2686 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.06e-05 |
| [2026-05-24 10:23:55] Epoch 3 | Step 11850 | Loss: 0.7757 | LM: 0.2686 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 9.03e-05 |
| [2026-05-24 10:24:06] Epoch 3 | Step 11860 | Loss: 0.7757 | LM: 0.2686 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 8.99e-05 |
| [2026-05-24 10:24:16] Epoch 3 | Step 11870 | Loss: 0.7758 | LM: 0.2687 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.248/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 8.96e-05 |
| [2026-05-24 10:24:27] Epoch 3 | Step 11880 | Loss: 0.7757 | LM: 0.2685 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 8.93e-05 |
| [2026-05-24 10:24:38] Epoch 3 | Step 11890 | Loss: 0.7758 | LM: 0.2686 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 8.90e-05 |
| [2026-05-24 10:24:49] Epoch 3 | Step 11900 | Loss: 0.7759 | LM: 0.2688 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 8.86e-05 |
| [2026-05-24 10:24:59] Epoch 3 | Step 11910 | Loss: 0.7759 | LM: 0.2690 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 8.83e-05 |
| [2026-05-24 10:25:10] Epoch 3 | Step 11920 | Loss: 0.7760 | LM: 0.2690 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 8.80e-05 |
| [2026-05-24 10:25:20] Epoch 3 | Step 11930 | Loss: 0.7760 | LM: 0.2690 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 8.76e-05 |
| [2026-05-24 10:25:31] Epoch 3 | Step 11940 | Loss: 0.7761 | LM: 0.2690 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 8.73e-05 |
| [2026-05-24 10:25:42] Epoch 3 | Step 11950 | Loss: 0.7761 | LM: 0.2690 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 8.69e-05 |
| [2026-05-24 10:25:53] Epoch 3 | Step 11960 | Loss: 0.7762 | LM: 0.2689 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 8.66e-05 |
| [2026-05-24 10:26:04] Epoch 3 | Step 11970 | Loss: 0.7762 | LM: 0.2690 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 8.62e-05 |
| [2026-05-24 10:26:14] Epoch 3 | Step 11980 | Loss: 0.7763 | LM: 0.2694 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 8.58e-05 |
| [2026-05-24 10:26:25] Epoch 3 | Step 11990 | Loss: 0.7764 | LM: 0.2694 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 8.55e-05 |
| [2026-05-24 10:26:35] Epoch 3 | Step 12000 | Loss: 0.7763 | LM: 0.2692 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 8.51e-05 |
| [2026-05-24 10:26:41] Checkpoint saved: outputs/2026-05-24/N_6.0/checkpoints/checkpoint_step_12000.pt |
| [2026-05-24 10:26:49] Validation | Batch 10/1463 | Loss: 0.8565 | LM_LOSS: 0.3508 | LB_LOSS: 1.0114 |
| [2026-05-24 10:26:51] Validation | Batch 20/1463 | Loss: 0.8759 | LM_LOSS: 0.3690 | LB_LOSS: 1.0138 |
| [2026-05-24 10:26:53] Validation | Batch 30/1463 | Loss: 0.8762 | LM_LOSS: 0.3690 | LB_LOSS: 1.0145 |
| [2026-05-24 10:26:54] Validation | Batch 40/1463 | Loss: 0.8851 | LM_LOSS: 0.3774 | LB_LOSS: 1.0153 |
| [2026-05-24 10:26:56] Validation | Batch 50/1463 | Loss: 0.8926 | LM_LOSS: 0.3852 | LB_LOSS: 1.0147 |
| [2026-05-24 10:26:58] Validation | Batch 60/1463 | Loss: 0.8944 | LM_LOSS: 0.3869 | LB_LOSS: 1.0148 |
| [2026-05-24 10:27:00] Validation | Batch 70/1463 | Loss: 0.8944 | LM_LOSS: 0.3870 | LB_LOSS: 1.0149 |
| [2026-05-24 10:27:02] Validation | Batch 80/1463 | Loss: 0.8971 | LM_LOSS: 0.3897 | LB_LOSS: 1.0149 |
| [2026-05-24 10:27:04] Validation | Batch 90/1463 | Loss: 0.8960 | LM_LOSS: 0.3885 | LB_LOSS: 1.0149 |
| [2026-05-24 10:27:06] Validation | Batch 100/1463 | Loss: 0.8960 | LM_LOSS: 0.3885 | LB_LOSS: 1.0149 |
| [2026-05-24 10:27:08] Validation | Batch 110/1463 | Loss: 0.8933 | LM_LOSS: 0.3858 | LB_LOSS: 1.0151 |
| [2026-05-24 10:27:09] Validation | Batch 120/1463 | Loss: 0.8953 | LM_LOSS: 0.3878 | LB_LOSS: 1.0151 |
| [2026-05-24 10:27:11] Validation | Batch 130/1463 | Loss: 0.8982 | LM_LOSS: 0.3906 | LB_LOSS: 1.0151 |
| [2026-05-24 10:27:13] Validation | Batch 140/1463 | Loss: 0.8997 | LM_LOSS: 0.3922 | LB_LOSS: 1.0151 |
| [2026-05-24 10:27:15] Validation | Batch 150/1463 | Loss: 0.8978 | LM_LOSS: 0.3902 | LB_LOSS: 1.0152 |
| [2026-05-24 10:27:16] Validation | Batch 160/1463 | Loss: 0.8987 | LM_LOSS: 0.3912 | LB_LOSS: 1.0151 |
| [2026-05-24 10:27:18] Validation | Batch 170/1463 | Loss: 0.8974 | LM_LOSS: 0.3899 | LB_LOSS: 1.0151 |
| [2026-05-24 10:27:20] Validation | Batch 180/1463 | Loss: 0.8981 | LM_LOSS: 0.3905 | LB_LOSS: 1.0152 |
| [2026-05-24 10:27:22] Validation | Batch 190/1463 | Loss: 0.8986 | LM_LOSS: 0.3910 | LB_LOSS: 1.0152 |
| [2026-05-24 10:27:24] Validation | Batch 200/1463 | Loss: 0.8981 | LM_LOSS: 0.3905 | LB_LOSS: 1.0152 |
| [2026-05-24 10:27:25] Validation | Batch 210/1463 | Loss: 0.8984 | LM_LOSS: 0.3908 | LB_LOSS: 1.0152 |
| [2026-05-24 10:27:27] Validation | Batch 220/1463 | Loss: 0.8974 | LM_LOSS: 0.3898 | LB_LOSS: 1.0153 |
| [2026-05-24 10:27:29] Validation | Batch 230/1463 | Loss: 0.8993 | LM_LOSS: 0.3917 | LB_LOSS: 1.0152 |
| [2026-05-24 10:27:31] Validation | Batch 240/1463 | Loss: 0.9002 | LM_LOSS: 0.3926 | LB_LOSS: 1.0151 |
| [2026-05-24 10:27:33] Validation | Batch 250/1463 | Loss: 0.8988 | LM_LOSS: 0.3913 | LB_LOSS: 1.0151 |
| [2026-05-24 10:27:35] Validation | Batch 260/1463 | Loss: 0.9006 | LM_LOSS: 0.3930 | LB_LOSS: 1.0153 |
| [2026-05-24 10:27:37] Validation | Batch 270/1463 | Loss: 0.8991 | LM_LOSS: 0.3915 | LB_LOSS: 1.0153 |
| [2026-05-24 10:27:38] Validation | Batch 280/1463 | Loss: 0.9002 | LM_LOSS: 0.3926 | LB_LOSS: 1.0153 |
| [2026-05-24 10:27:40] Validation | Batch 290/1463 | Loss: 0.8991 | LM_LOSS: 0.3915 | LB_LOSS: 1.0153 |
| [2026-05-24 10:27:42] Validation | Batch 300/1463 | Loss: 0.8999 | LM_LOSS: 0.3922 | LB_LOSS: 1.0154 |
| [2026-05-24 10:27:44] Validation | Batch 310/1463 | Loss: 0.9005 | LM_LOSS: 0.3928 | LB_LOSS: 1.0154 |
| [2026-05-24 10:27:45] Validation | Batch 320/1463 | Loss: 0.8991 | LM_LOSS: 0.3915 | LB_LOSS: 1.0152 |
| [2026-05-24 10:27:47] Validation | Batch 330/1463 | Loss: 0.8993 | LM_LOSS: 0.3917 | LB_LOSS: 1.0152 |
| [2026-05-24 10:27:49] Validation | Batch 340/1463 | Loss: 0.8988 | LM_LOSS: 0.3911 | LB_LOSS: 1.0152 |
| [2026-05-24 10:27:51] Validation | Batch 350/1463 | Loss: 0.8993 | LM_LOSS: 0.3917 | LB_LOSS: 1.0152 |
| [2026-05-24 10:27:52] Validation | Batch 360/1463 | Loss: 0.8993 | LM_LOSS: 0.3917 | LB_LOSS: 1.0153 |
| [2026-05-24 10:27:54] Validation | Batch 370/1463 | Loss: 0.8992 | LM_LOSS: 0.3915 | LB_LOSS: 1.0153 |
| [2026-05-24 10:27:55] Validation | Batch 380/1463 | Loss: 0.8989 | LM_LOSS: 0.3913 | LB_LOSS: 1.0152 |
| [2026-05-24 10:27:57] Validation | Batch 390/1463 | Loss: 0.8998 | LM_LOSS: 0.3922 | LB_LOSS: 1.0152 |
| [2026-05-24 10:27:59] Validation | Batch 400/1463 | Loss: 0.8997 | LM_LOSS: 0.3921 | LB_LOSS: 1.0153 |
| [2026-05-24 10:28:01] Validation | Batch 410/1463 | Loss: 0.8994 | LM_LOSS: 0.3917 | LB_LOSS: 1.0153 |
| [2026-05-24 10:28:03] Validation | Batch 420/1463 | Loss: 0.8995 | LM_LOSS: 0.3918 | LB_LOSS: 1.0154 |
| [2026-05-24 10:28:05] Validation | Batch 430/1463 | Loss: 0.8992 | LM_LOSS: 0.3915 | LB_LOSS: 1.0154 |
| [2026-05-24 10:28:06] Validation | Batch 440/1463 | Loss: 0.8996 | LM_LOSS: 0.3919 | LB_LOSS: 1.0155 |
| [2026-05-24 10:28:08] Validation | Batch 450/1463 | Loss: 0.8995 | LM_LOSS: 0.3917 | LB_LOSS: 1.0155 |
| [2026-05-24 10:28:10] Validation | Batch 460/1463 | Loss: 0.8993 | LM_LOSS: 0.3916 | LB_LOSS: 1.0155 |
| [2026-05-24 10:28:12] Validation | Batch 470/1463 | Loss: 0.9001 | LM_LOSS: 0.3923 | LB_LOSS: 1.0154 |
| [2026-05-24 10:28:14] Validation | Batch 480/1463 | Loss: 0.9000 | LM_LOSS: 0.3923 | LB_LOSS: 1.0154 |
| [2026-05-24 10:28:15] Validation | Batch 490/1463 | Loss: 0.8997 | LM_LOSS: 0.3920 | LB_LOSS: 1.0154 |
| [2026-05-24 10:28:18] Validation | Batch 500/1463 | Loss: 0.8994 | LM_LOSS: 0.3917 | LB_LOSS: 1.0154 |
| [2026-05-24 10:28:19] Validation | Batch 510/1463 | Loss: 0.8987 | LM_LOSS: 0.3910 | LB_LOSS: 1.0154 |
| [2026-05-24 10:28:21] Validation | Batch 520/1463 | Loss: 0.8984 | LM_LOSS: 0.3907 | LB_LOSS: 1.0154 |
| [2026-05-24 10:28:22] Validation | Batch 530/1463 | Loss: 0.8988 | LM_LOSS: 0.3912 | LB_LOSS: 1.0154 |
| [2026-05-24 10:28:24] Validation | Batch 540/1463 | Loss: 0.8991 | LM_LOSS: 0.3914 | LB_LOSS: 1.0154 |
| [2026-05-24 10:28:25] Validation | Batch 550/1463 | Loss: 0.8988 | LM_LOSS: 0.3911 | LB_LOSS: 1.0154 |
| [2026-05-24 10:28:27] Validation | Batch 560/1463 | Loss: 0.8993 | LM_LOSS: 0.3915 | LB_LOSS: 1.0155 |
| [2026-05-24 10:28:29] Validation | Batch 570/1463 | Loss: 0.8992 | LM_LOSS: 0.3915 | LB_LOSS: 1.0155 |
| [2026-05-24 10:28:31] Validation | Batch 580/1463 | Loss: 0.8988 | LM_LOSS: 0.3910 | LB_LOSS: 1.0155 |
| [2026-05-24 10:28:33] Validation | Batch 590/1463 | Loss: 0.8987 | LM_LOSS: 0.3909 | LB_LOSS: 1.0155 |
| [2026-05-24 10:28:35] Validation | Batch 600/1463 | Loss: 0.8990 | LM_LOSS: 0.3912 | LB_LOSS: 1.0156 |
| [2026-05-24 10:28:37] Validation | Batch 610/1463 | Loss: 0.8990 | LM_LOSS: 0.3913 | LB_LOSS: 1.0156 |
| [2026-05-24 10:28:39] Validation | Batch 620/1463 | Loss: 0.8983 | LM_LOSS: 0.3906 | LB_LOSS: 1.0155 |
| [2026-05-24 10:28:41] Validation | Batch 630/1463 | Loss: 0.8979 | LM_LOSS: 0.3901 | LB_LOSS: 1.0156 |
| [2026-05-24 10:28:42] Validation | Batch 640/1463 | Loss: 0.8977 | LM_LOSS: 0.3899 | LB_LOSS: 1.0156 |
| [2026-05-24 10:28:44] Validation | Batch 650/1463 | Loss: 0.8973 | LM_LOSS: 0.3895 | LB_LOSS: 1.0156 |
| [2026-05-24 10:28:45] Validation | Batch 660/1463 | Loss: 0.8967 | LM_LOSS: 0.3889 | LB_LOSS: 1.0156 |
| [2026-05-24 10:28:47] Validation | Batch 670/1463 | Loss: 0.8962 | LM_LOSS: 0.3885 | LB_LOSS: 1.0156 |
| [2026-05-24 10:28:49] Validation | Batch 680/1463 | Loss: 0.8963 | LM_LOSS: 0.3885 | LB_LOSS: 1.0155 |
| [2026-05-24 10:28:51] Validation | Batch 690/1463 | Loss: 0.8968 | LM_LOSS: 0.3890 | LB_LOSS: 1.0156 |
| [2026-05-24 10:28:52] Validation | Batch 700/1463 | Loss: 0.8967 | LM_LOSS: 0.3889 | LB_LOSS: 1.0155 |
| [2026-05-24 10:28:54] Validation | Batch 710/1463 | Loss: 0.8971 | LM_LOSS: 0.3893 | LB_LOSS: 1.0156 |
| [2026-05-24 10:28:56] Validation | Batch 720/1463 | Loss: 0.8978 | LM_LOSS: 0.3900 | LB_LOSS: 1.0156 |
| [2026-05-24 10:28:57] Validation | Batch 730/1463 | Loss: 0.8977 | LM_LOSS: 0.3899 | LB_LOSS: 1.0156 |
| [2026-05-24 10:28:59] Validation | Batch 740/1463 | Loss: 0.8972 | LM_LOSS: 0.3894 | LB_LOSS: 1.0156 |
| [2026-05-24 10:29:00] Validation | Batch 750/1463 | Loss: 0.8971 | LM_LOSS: 0.3893 | LB_LOSS: 1.0156 |
| [2026-05-24 10:29:02] Validation | Batch 760/1463 | Loss: 0.8967 | LM_LOSS: 0.3889 | LB_LOSS: 1.0156 |
| [2026-05-24 10:29:03] Validation | Batch 770/1463 | Loss: 0.8965 | LM_LOSS: 0.3887 | LB_LOSS: 1.0156 |
| [2026-05-24 10:29:05] Validation | Batch 780/1463 | Loss: 0.8963 | LM_LOSS: 0.3885 | LB_LOSS: 1.0156 |
| [2026-05-24 10:29:06] Validation | Batch 790/1463 | Loss: 0.8965 | LM_LOSS: 0.3887 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:08] Validation | Batch 800/1463 | Loss: 0.8964 | LM_LOSS: 0.3887 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:10] Validation | Batch 810/1463 | Loss: 0.8960 | LM_LOSS: 0.3883 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:11] Validation | Batch 820/1463 | Loss: 0.8962 | LM_LOSS: 0.3885 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:13] Validation | Batch 830/1463 | Loss: 0.8963 | LM_LOSS: 0.3886 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:15] Validation | Batch 840/1463 | Loss: 0.8962 | LM_LOSS: 0.3884 | LB_LOSS: 1.0156 |
| [2026-05-24 10:29:17] Validation | Batch 850/1463 | Loss: 0.8965 | LM_LOSS: 0.3887 | LB_LOSS: 1.0156 |
| [2026-05-24 10:29:19] Validation | Batch 860/1463 | Loss: 0.8966 | LM_LOSS: 0.3888 | LB_LOSS: 1.0156 |
| [2026-05-24 10:29:21] Validation | Batch 870/1463 | Loss: 0.8968 | LM_LOSS: 0.3890 | LB_LOSS: 1.0156 |
| [2026-05-24 10:29:22] Validation | Batch 880/1463 | Loss: 0.8961 | LM_LOSS: 0.3883 | LB_LOSS: 1.0156 |
| [2026-05-24 10:29:24] Validation | Batch 890/1463 | Loss: 0.8961 | LM_LOSS: 0.3883 | LB_LOSS: 1.0156 |
| [2026-05-24 10:29:26] Validation | Batch 900/1463 | Loss: 0.8958 | LM_LOSS: 0.3881 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:28] Validation | Batch 910/1463 | Loss: 0.8958 | LM_LOSS: 0.3880 | LB_LOSS: 1.0156 |
| [2026-05-24 10:29:30] Validation | Batch 920/1463 | Loss: 0.8961 | LM_LOSS: 0.3883 | LB_LOSS: 1.0156 |
| [2026-05-24 10:29:31] Validation | Batch 930/1463 | Loss: 0.8957 | LM_LOSS: 0.3879 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:33] Validation | Batch 940/1463 | Loss: 0.8953 | LM_LOSS: 0.3876 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:35] Validation | Batch 950/1463 | Loss: 0.8958 | LM_LOSS: 0.3880 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:37] Validation | Batch 960/1463 | Loss: 0.8959 | LM_LOSS: 0.3881 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:39] Validation | Batch 970/1463 | Loss: 0.8960 | LM_LOSS: 0.3883 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:41] Validation | Batch 980/1463 | Loss: 0.8963 | LM_LOSS: 0.3886 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:42] Validation | Batch 990/1463 | Loss: 0.8965 | LM_LOSS: 0.3887 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:44] Validation | Batch 1000/1463 | Loss: 0.8972 | LM_LOSS: 0.3894 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:46] Validation | Batch 1010/1463 | Loss: 0.8971 | LM_LOSS: 0.3894 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:48] Validation | Batch 1020/1463 | Loss: 0.8972 | LM_LOSS: 0.3895 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:50] Validation | Batch 1030/1463 | Loss: 0.8977 | LM_LOSS: 0.3899 | LB_LOSS: 1.0156 |
| [2026-05-24 10:29:52] Validation | Batch 1040/1463 | Loss: 0.8972 | LM_LOSS: 0.3894 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:54] Validation | Batch 1050/1463 | Loss: 0.8971 | LM_LOSS: 0.3894 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:55] Validation | Batch 1060/1463 | Loss: 0.8970 | LM_LOSS: 0.3893 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:57] Validation | Batch 1070/1463 | Loss: 0.8971 | LM_LOSS: 0.3893 | LB_LOSS: 1.0155 |
| [2026-05-24 10:29:59] Validation | Batch 1080/1463 | Loss: 0.8968 | LM_LOSS: 0.3891 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:01] Validation | Batch 1090/1463 | Loss: 0.8968 | LM_LOSS: 0.3891 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:02] Validation | Batch 1100/1463 | Loss: 0.8968 | LM_LOSS: 0.3890 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:04] Validation | Batch 1110/1463 | Loss: 0.8969 | LM_LOSS: 0.3891 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:06] Validation | Batch 1120/1463 | Loss: 0.8966 | LM_LOSS: 0.3889 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:08] Validation | Batch 1130/1463 | Loss: 0.8964 | LM_LOSS: 0.3887 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:09] Validation | Batch 1140/1463 | Loss: 0.8967 | LM_LOSS: 0.3889 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:11] Validation | Batch 1150/1463 | Loss: 0.8966 | LM_LOSS: 0.3889 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:13] Validation | Batch 1160/1463 | Loss: 0.8967 | LM_LOSS: 0.3889 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:15] Validation | Batch 1170/1463 | Loss: 0.8966 | LM_LOSS: 0.3888 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:17] Validation | Batch 1180/1463 | Loss: 0.8966 | LM_LOSS: 0.3889 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:18] Validation | Batch 1190/1463 | Loss: 0.8968 | LM_LOSS: 0.3891 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:20] Validation | Batch 1200/1463 | Loss: 0.8969 | LM_LOSS: 0.3892 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:22] Validation | Batch 1210/1463 | Loss: 0.8973 | LM_LOSS: 0.3895 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:24] Validation | Batch 1220/1463 | Loss: 0.8977 | LM_LOSS: 0.3899 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:25] Validation | Batch 1230/1463 | Loss: 0.8976 | LM_LOSS: 0.3898 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:27] Validation | Batch 1240/1463 | Loss: 0.8979 | LM_LOSS: 0.3901 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:29] Validation | Batch 1250/1463 | Loss: 0.8981 | LM_LOSS: 0.3903 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:31] Validation | Batch 1260/1463 | Loss: 0.8981 | LM_LOSS: 0.3903 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:33] Validation | Batch 1270/1463 | Loss: 0.8978 | LM_LOSS: 0.3901 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:35] Validation | Batch 1280/1463 | Loss: 0.8976 | LM_LOSS: 0.3898 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:37] Validation | Batch 1290/1463 | Loss: 0.8976 | LM_LOSS: 0.3899 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:38] Validation | Batch 1300/1463 | Loss: 0.8973 | LM_LOSS: 0.3896 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:40] Validation | Batch 1310/1463 | Loss: 0.8972 | LM_LOSS: 0.3895 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:42] Validation | Batch 1320/1463 | Loss: 0.8972 | LM_LOSS: 0.3895 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:43] Validation | Batch 1330/1463 | Loss: 0.8972 | LM_LOSS: 0.3895 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:45] Validation | Batch 1340/1463 | Loss: 0.8975 | LM_LOSS: 0.3897 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:46] Validation | Batch 1350/1463 | Loss: 0.8975 | LM_LOSS: 0.3898 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:49] Validation | Batch 1360/1463 | Loss: 0.8978 | LM_LOSS: 0.3901 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:51] Validation | Batch 1370/1463 | Loss: 0.8982 | LM_LOSS: 0.3905 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:52] Validation | Batch 1380/1463 | Loss: 0.8981 | LM_LOSS: 0.3903 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:54] Validation | Batch 1390/1463 | Loss: 0.8980 | LM_LOSS: 0.3902 | LB_LOSS: 1.0155 |
| [2026-05-24 10:30:56] Validation | Batch 1400/1463 | Loss: 0.8983 | LM_LOSS: 0.3906 | LB_LOSS: 1.0154 |
| [2026-05-24 10:30:57] Validation | Batch 1410/1463 | Loss: 0.8985 | LM_LOSS: 0.3908 | LB_LOSS: 1.0154 |
| [2026-05-24 10:30:59] Validation | Batch 1420/1463 | Loss: 0.8985 | LM_LOSS: 0.3908 | LB_LOSS: 1.0155 |
| [2026-05-24 10:31:01] Validation | Batch 1430/1463 | Loss: 0.8986 | LM_LOSS: 0.3909 | LB_LOSS: 1.0155 |
| [2026-05-24 10:31:03] Validation | Batch 1440/1463 | Loss: 0.8991 | LM_LOSS: 0.3914 | LB_LOSS: 1.0155 |
| [2026-05-24 10:31:05] Validation | Batch 1450/1463 | Loss: 0.8987 | LM_LOSS: 0.3910 | LB_LOSS: 1.0154 |
| [2026-05-24 10:31:06] Validation | Batch 1460/1463 | Loss: 0.8990 | LM_LOSS: 0.3913 | LB_LOSS: 1.0154 |
| [2026-05-24 10:31:07] Validation | Batch 1463/1463 | Loss: 0.8989 | LM_LOSS: 0.3912 | LB_LOSS: 1.0154 |
| [2026-05-24 10:31:07] Validation | Loss: 0.8989 | LM_LOSS: 0.3912 | LB_LOSS: 1.0154 | PPL: 1.48 | Time: 259.25s |
| [2026-05-24 10:31:18] Epoch 3 | Step 12010 | Loss: 0.7763 | LM: 0.2693 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 8.47e-05 |
| [2026-05-24 10:31:28] Epoch 3 | Step 12020 | Loss: 0.7763 | LM: 0.2694 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 8.44e-05 |
| [2026-05-24 10:31:39] Epoch 3 | Step 12030 | Loss: 0.7764 | LM: 0.2695 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 8.40e-05 |
| [2026-05-24 10:31:50] Epoch 3 | Step 12040 | Loss: 0.7766 | LM: 0.2697 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 8.36e-05 |
| [2026-05-24 10:32:00] Epoch 3 | Step 12050 | Loss: 0.7765 | LM: 0.2696 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 8.32e-05 |
| [2026-05-24 10:32:11] Epoch 3 | Step 12060 | Loss: 0.7765 | LM: 0.2697 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.166 | LR: 8.28e-05 |
| [2026-05-24 10:32:22] Epoch 3 | Step 12070 | Loss: 0.7765 | LM: 0.2697 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 8.24e-05 |
| [2026-05-24 10:32:33] Epoch 3 | Step 12080 | Loss: 0.7766 | LM: 0.2699 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 8.20e-05 |
| [2026-05-24 10:32:44] Epoch 3 | Step 12090 | Loss: 0.7765 | LM: 0.2698 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 8.16e-05 |
| [2026-05-24 10:32:55] Epoch 3 | Step 12100 | Loss: 0.7763 | LM: 0.2697 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 8.12e-05 |
| [2026-05-24 10:33:05] Epoch 3 | Step 12110 | Loss: 0.7763 | LM: 0.2696 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 8.08e-05 |
| [2026-05-24 10:33:16] Epoch 3 | Step 12120 | Loss: 0.7762 | LM: 0.2695 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 8.04e-05 |
| [2026-05-24 10:33:27] Epoch 3 | Step 12130 | Loss: 0.7763 | LM: 0.2694 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.99e-05 |
| [2026-05-24 10:33:37] Epoch 3 | Step 12140 | Loss: 0.7763 | LM: 0.2695 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.95e-05 |
| [2026-05-24 10:33:48] Epoch 3 | Step 12150 | Loss: 0.7763 | LM: 0.2695 | LB: 1.0168 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.91e-05 |
| [2026-05-24 10:33:59] Epoch 3 | Step 12160 | Loss: 0.7764 | LM: 0.2694 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.87e-05 |
| [2026-05-24 10:34:09] Epoch 3 | Step 12170 | Loss: 0.7764 | LM: 0.2696 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.83e-05 |
| [2026-05-24 10:34:20] Epoch 3 | Step 12180 | Loss: 0.7764 | LM: 0.2695 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.78e-05 |
| [2026-05-24 10:34:31] Epoch 3 | Step 12190 | Loss: 0.7764 | LM: 0.2695 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.74e-05 |
| [2026-05-24 10:34:41] Epoch 3 | Step 12200 | Loss: 0.7764 | LM: 0.2694 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.69e-05 |
| [2026-05-24 10:34:52] Epoch 3 | Step 12210 | Loss: 0.7765 | LM: 0.2695 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.65e-05 |
| [2026-05-24 10:35:03] Epoch 3 | Step 12220 | Loss: 0.7766 | LM: 0.2697 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.61e-05 |
| [2026-05-24 10:35:13] Epoch 3 | Step 12230 | Loss: 0.7766 | LM: 0.2696 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.56e-05 |
| [2026-05-24 10:35:24] Epoch 3 | Step 12240 | Loss: 0.7766 | LM: 0.2697 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.52e-05 |
| [2026-05-24 10:35:35] Epoch 3 | Step 12250 | Loss: 0.7767 | LM: 0.2699 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.47e-05 |
| [2026-05-24 10:35:46] Epoch 3 | Step 12260 | Loss: 0.7767 | LM: 0.2698 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.43e-05 |
| [2026-05-24 10:35:56] Epoch 3 | Step 12270 | Loss: 0.7767 | LM: 0.2698 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.38e-05 |
| [2026-05-24 10:36:07] Epoch 3 | Step 12280 | Loss: 0.7768 | LM: 0.2698 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.34e-05 |
| [2026-05-24 10:36:17] Epoch 3 | Step 12290 | Loss: 0.7767 | LM: 0.2697 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.29e-05 |
| [2026-05-24 10:36:28] Epoch 3 | Step 12300 | Loss: 0.7768 | LM: 0.2699 | LB: 1.0167 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.24e-05 |
| [2026-05-24 10:36:39] Epoch 3 | Step 12310 | Loss: 0.7769 | LM: 0.2702 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.20e-05 |
| [2026-05-24 10:36:49] Epoch 3 | Step 12320 | Loss: 0.7768 | LM: 0.2702 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.15e-05 |
| [2026-05-24 10:37:00] Epoch 3 | Step 12330 | Loss: 0.7769 | LM: 0.2704 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.10e-05 |
| [2026-05-24 10:37:11] Epoch 3 | Step 12340 | Loss: 0.7770 | LM: 0.2705 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.06e-05 |
| [2026-05-24 10:37:21] Epoch 3 | Step 12350 | Loss: 0.7770 | LM: 0.2707 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 7.01e-05 |
| [2026-05-24 10:37:32] Epoch 3 | Step 12360 | Loss: 0.7770 | LM: 0.2706 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.96e-05 |
| [2026-05-24 10:37:43] Epoch 3 | Step 12370 | Loss: 0.7770 | LM: 0.2705 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.91e-05 |
| [2026-05-24 10:37:54] Epoch 3 | Step 12380 | Loss: 0.7770 | LM: 0.2706 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.87e-05 |
| [2026-05-24 10:38:04] Epoch 3 | Step 12390 | Loss: 0.7771 | LM: 0.2706 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.82e-05 |
| [2026-05-24 10:38:15] Epoch 3 | Step 12400 | Loss: 0.7772 | LM: 0.2707 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.77e-05 |
| [2026-05-24 10:38:26] Epoch 3 | Step 12410 | Loss: 0.7772 | LM: 0.2707 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.72e-05 |
| [2026-05-24 10:38:36] Epoch 3 | Step 12420 | Loss: 0.7772 | LM: 0.2708 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.67e-05 |
| [2026-05-24 10:38:47] Epoch 3 | Step 12430 | Loss: 0.7773 | LM: 0.2708 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.62e-05 |
| [2026-05-24 10:38:58] Epoch 3 | Step 12440 | Loss: 0.7772 | LM: 0.2706 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.58e-05 |
| [2026-05-24 10:39:09] Epoch 3 | Step 12450 | Loss: 0.7772 | LM: 0.2706 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.53e-05 |
| [2026-05-24 10:39:19] Epoch 3 | Step 12460 | Loss: 0.7771 | LM: 0.2705 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.48e-05 |
| [2026-05-24 10:39:30] Epoch 3 | Step 12470 | Loss: 0.7773 | LM: 0.2707 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.43e-05 |
| [2026-05-24 10:39:41] Epoch 3 | Step 12480 | Loss: 0.7774 | LM: 0.2708 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.38e-05 |
| [2026-05-24 10:39:52] Epoch 3 | Step 12490 | Loss: 0.7773 | LM: 0.2707 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.33e-05 |
| [2026-05-24 10:40:03] Epoch 3 | Step 12500 | Loss: 0.7773 | LM: 0.2706 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.28e-05 |
| [2026-05-24 10:40:13] Epoch 3 | Step 12510 | Loss: 0.7774 | LM: 0.2707 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.23e-05 |
| [2026-05-24 10:40:24] Epoch 3 | Step 12520 | Loss: 0.7773 | LM: 0.2706 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.18e-05 |
| [2026-05-24 10:40:35] Epoch 3 | Step 12530 | Loss: 0.7773 | LM: 0.2705 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.13e-05 |
| [2026-05-24 10:40:45] Epoch 3 | Step 12540 | Loss: 0.7773 | LM: 0.2704 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.08e-05 |
| [2026-05-24 10:40:56] Epoch 3 | Step 12550 | Loss: 0.7773 | LM: 0.2704 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 6.03e-05 |
| [2026-05-24 10:41:07] Epoch 3 | Step 12560 | Loss: 0.7774 | LM: 0.2705 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 5.98e-05 |
| [2026-05-24 10:41:17] Epoch 3 | Step 12570 | Loss: 0.7774 | LM: 0.2705 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 5.93e-05 |
| [2026-05-24 10:41:28] Epoch 3 | Step 12580 | Loss: 0.7774 | LM: 0.2703 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 5.88e-05 |
| [2026-05-24 10:41:39] Epoch 3 | Step 12590 | Loss: 0.7774 | LM: 0.2704 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 5.83e-05 |
| [2026-05-24 10:41:49] Epoch 3 | Step 12600 | Loss: 0.7774 | LM: 0.2705 | LB: 1.0166 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 5.78e-05 |
| [2026-05-24 10:42:00] Epoch 3 | Step 12610 | Loss: 0.7775 | LM: 0.2706 | LB: 1.0165 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 5.73e-05 |
| [2026-05-24 10:42:11] Epoch 3 | Step 12620 | Loss: 0.7775 | LM: 0.2706 | LB: 1.0165 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 5.68e-05 |
| [2026-05-24 10:42:22] Epoch 3 | Step 12630 | Loss: 0.7775 | LM: 0.2705 | LB: 1.0165 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.217 | HR1: 0.194/SR1: 0.167 | LR: 5.63e-05 |
| [2026-05-24 10:42:32] Epoch 3 | Step 12640 | Loss: 0.7775 | LM: 0.2705 | LB: 1.0165 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 5.58e-05 |
| [2026-05-24 10:42:43] Epoch 3 | Step 12650 | Loss: 0.7775 | LM: 0.2706 | LB: 1.0165 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 5.53e-05 |
| [2026-05-24 10:42:53] Epoch 3 | Step 12660 | Loss: 0.7775 | LM: 0.2705 | LB: 1.0165 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 5.48e-05 |
| [2026-05-24 10:43:04] Epoch 3 | Step 12670 | Loss: 0.7775 | LM: 0.2705 | LB: 1.0165 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 5.43e-05 |
| [2026-05-24 10:43:15] Epoch 3 | Step 12680 | Loss: 0.7775 | LM: 0.2705 | LB: 1.0165 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 5.38e-05 |
| [2026-05-24 10:43:25] Epoch 3 | Step 12690 | Loss: 0.7775 | LM: 0.2704 | LB: 1.0165 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 5.33e-05 |
| [2026-05-24 10:43:36] Epoch 3 | Step 12700 | Loss: 0.7774 | LM: 0.2704 | LB: 1.0165 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 5.28e-05 |
| [2026-05-24 10:43:47] Epoch 3 | Step 12710 | Loss: 0.7774 | LM: 0.2704 | LB: 1.0165 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 5.23e-05 |
| [2026-05-24 10:43:58] Epoch 3 | Step 12720 | Loss: 0.7773 | LM: 0.2702 | LB: 1.0165 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 5.18e-05 |
| [2026-05-24 10:44:08] Epoch 3 | Step 12730 | Loss: 0.7774 | LM: 0.2703 | LB: 1.0165 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 5.13e-05 |
| [2026-05-24 10:44:19] Epoch 3 | Step 12740 | Loss: 0.7774 | LM: 0.2703 | LB: 1.0165 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 5.08e-05 |
| [2026-05-24 10:44:30] Epoch 3 | Step 12750 | Loss: 0.7774 | LM: 0.2703 | LB: 1.0165 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 5.03e-05 |
| [2026-05-24 10:44:42] Epoch 3 | Step 12760 | Loss: 0.7775 | LM: 0.2703 | LB: 1.0165 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.98e-05 |
| [2026-05-24 10:44:53] Epoch 3 | Step 12770 | Loss: 0.7775 | LM: 0.2703 | LB: 1.0165 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.93e-05 |
| [2026-05-24 10:45:04] Epoch 3 | Step 12780 | Loss: 0.7776 | LM: 0.2704 | LB: 1.0164 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.88e-05 |
| [2026-05-24 10:45:15] Epoch 3 | Step 12790 | Loss: 0.7776 | LM: 0.2705 | LB: 1.0164 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.83e-05 |
| [2026-05-24 10:45:27] Epoch 3 | Step 12800 | Loss: 0.7777 | LM: 0.2705 | LB: 1.0164 | CL0: 4.1 | CL1: 5.2 | HR0: 0.247/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.78e-05 |
| [2026-05-24 10:45:38] Epoch 3 | Step 12810 | Loss: 0.7777 | LM: 0.2705 | LB: 1.0164 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.73e-05 |
| [2026-05-24 10:45:49] Epoch 3 | Step 12820 | Loss: 0.7777 | LM: 0.2705 | LB: 1.0164 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.68e-05 |
| [2026-05-24 10:46:00] Epoch 3 | Step 12830 | Loss: 0.7777 | LM: 0.2705 | LB: 1.0164 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.63e-05 |
| [2026-05-24 10:46:11] Epoch 3 | Step 12840 | Loss: 0.7778 | LM: 0.2707 | LB: 1.0164 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.58e-05 |
| [2026-05-24 10:46:21] Epoch 3 | Step 12850 | Loss: 0.7778 | LM: 0.2708 | LB: 1.0164 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.53e-05 |
| [2026-05-24 10:46:32] Epoch 3 | Step 12860 | Loss: 0.7779 | LM: 0.2708 | LB: 1.0164 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.48e-05 |
| [2026-05-24 10:46:42] Epoch 3 | Step 12870 | Loss: 0.7778 | LM: 0.2706 | LB: 1.0164 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.43e-05 |
| [2026-05-24 10:46:53] Epoch 3 | Step 12880 | Loss: 0.7779 | LM: 0.2707 | LB: 1.0164 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.39e-05 |
| [2026-05-24 10:47:04] Epoch 3 | Step 12890 | Loss: 0.7780 | LM: 0.2708 | LB: 1.0164 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.34e-05 |
| [2026-05-24 10:47:14] Epoch 3 | Step 12900 | Loss: 0.7779 | LM: 0.2708 | LB: 1.0164 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.29e-05 |
| [2026-05-24 10:47:25] Epoch 3 | Step 12910 | Loss: 0.7779 | LM: 0.2708 | LB: 1.0164 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.24e-05 |
| [2026-05-24 10:47:36] Epoch 3 | Step 12920 | Loss: 0.7780 | LM: 0.2710 | LB: 1.0164 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.19e-05 |
| [2026-05-24 10:47:47] Epoch 3 | Step 12930 | Loss: 0.7781 | LM: 0.2710 | LB: 1.0164 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.14e-05 |
| [2026-05-24 10:47:57] Epoch 3 | Step 12940 | Loss: 0.7780 | LM: 0.2710 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.10e-05 |
| [2026-05-24 10:48:08] Epoch 3 | Step 12950 | Loss: 0.7781 | LM: 0.2712 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.05e-05 |
| [2026-05-24 10:48:19] Epoch 3 | Step 12960 | Loss: 0.7781 | LM: 0.2711 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 4.00e-05 |
| [2026-05-24 10:48:30] Epoch 3 | Step 12970 | Loss: 0.7781 | LM: 0.2711 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.95e-05 |
| [2026-05-24 10:48:41] Epoch 3 | Step 12980 | Loss: 0.7780 | LM: 0.2710 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.91e-05 |
| [2026-05-24 10:48:52] Epoch 3 | Step 12990 | Loss: 0.7780 | LM: 0.2710 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.86e-05 |
| [2026-05-24 10:49:03] Epoch 3 | Step 13000 | Loss: 0.7780 | LM: 0.2710 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.81e-05 |
| [2026-05-24 10:49:04] Validation | Batch 10/1463 | Loss: 0.8558 | LM_LOSS: 0.3508 | LB_LOSS: 1.0099 |
| [2026-05-24 10:49:06] Validation | Batch 20/1463 | Loss: 0.8730 | LM_LOSS: 0.3670 | LB_LOSS: 1.0120 |
| [2026-05-24 10:49:08] Validation | Batch 30/1463 | Loss: 0.8730 | LM_LOSS: 0.3666 | LB_LOSS: 1.0127 |
| [2026-05-24 10:49:10] Validation | Batch 40/1463 | Loss: 0.8820 | LM_LOSS: 0.3752 | LB_LOSS: 1.0135 |
| [2026-05-24 10:49:11] Validation | Batch 50/1463 | Loss: 0.8908 | LM_LOSS: 0.3843 | LB_LOSS: 1.0130 |
| [2026-05-24 10:49:14] Validation | Batch 60/1463 | Loss: 0.8930 | LM_LOSS: 0.3865 | LB_LOSS: 1.0131 |
| [2026-05-24 10:49:16] Validation | Batch 70/1463 | Loss: 0.8933 | LM_LOSS: 0.3867 | LB_LOSS: 1.0131 |
| [2026-05-24 10:49:18] Validation | Batch 80/1463 | Loss: 0.8966 | LM_LOSS: 0.3900 | LB_LOSS: 1.0132 |
| [2026-05-24 10:49:19] Validation | Batch 90/1463 | Loss: 0.8955 | LM_LOSS: 0.3889 | LB_LOSS: 1.0131 |
| [2026-05-24 10:49:21] Validation | Batch 100/1463 | Loss: 0.8953 | LM_LOSS: 0.3887 | LB_LOSS: 1.0132 |
| [2026-05-24 10:49:23] Validation | Batch 110/1463 | Loss: 0.8930 | LM_LOSS: 0.3863 | LB_LOSS: 1.0134 |
| [2026-05-24 10:49:24] Validation | Batch 120/1463 | Loss: 0.8949 | LM_LOSS: 0.3882 | LB_LOSS: 1.0134 |
| [2026-05-24 10:49:26] Validation | Batch 130/1463 | Loss: 0.8980 | LM_LOSS: 0.3913 | LB_LOSS: 1.0134 |
| [2026-05-24 10:49:28] Validation | Batch 140/1463 | Loss: 0.8996 | LM_LOSS: 0.3930 | LB_LOSS: 1.0134 |
| [2026-05-24 10:49:30] Validation | Batch 150/1463 | Loss: 0.8981 | LM_LOSS: 0.3914 | LB_LOSS: 1.0135 |
| [2026-05-24 10:49:32] Validation | Batch 160/1463 | Loss: 0.8989 | LM_LOSS: 0.3922 | LB_LOSS: 1.0134 |
| [2026-05-24 10:49:33] Validation | Batch 170/1463 | Loss: 0.8980 | LM_LOSS: 0.3913 | LB_LOSS: 1.0134 |
| [2026-05-24 10:49:35] Validation | Batch 180/1463 | Loss: 0.8984 | LM_LOSS: 0.3917 | LB_LOSS: 1.0135 |
| [2026-05-24 10:49:37] Validation | Batch 190/1463 | Loss: 0.8992 | LM_LOSS: 0.3924 | LB_LOSS: 1.0135 |
| [2026-05-24 10:49:39] Validation | Batch 200/1463 | Loss: 0.8985 | LM_LOSS: 0.3918 | LB_LOSS: 1.0135 |
| [2026-05-24 10:49:40] Validation | Batch 210/1463 | Loss: 0.8989 | LM_LOSS: 0.3921 | LB_LOSS: 1.0135 |
| [2026-05-24 10:49:43] Validation | Batch 220/1463 | Loss: 0.8980 | LM_LOSS: 0.3912 | LB_LOSS: 1.0135 |
| [2026-05-24 10:49:44] Validation | Batch 230/1463 | Loss: 0.8998 | LM_LOSS: 0.3931 | LB_LOSS: 1.0134 |
| [2026-05-24 10:49:46] Validation | Batch 240/1463 | Loss: 0.9007 | LM_LOSS: 0.3940 | LB_LOSS: 1.0134 |
| [2026-05-24 10:49:48] Validation | Batch 250/1463 | Loss: 0.8992 | LM_LOSS: 0.3925 | LB_LOSS: 1.0134 |
| [2026-05-24 10:49:50] Validation | Batch 260/1463 | Loss: 0.9010 | LM_LOSS: 0.3943 | LB_LOSS: 1.0136 |
| [2026-05-24 10:49:52] Validation | Batch 270/1463 | Loss: 0.8994 | LM_LOSS: 0.3926 | LB_LOSS: 1.0135 |
| [2026-05-24 10:49:53] Validation | Batch 280/1463 | Loss: 0.9005 | LM_LOSS: 0.3937 | LB_LOSS: 1.0136 |
| [2026-05-24 10:49:55] Validation | Batch 290/1463 | Loss: 0.8993 | LM_LOSS: 0.3925 | LB_LOSS: 1.0135 |
| [2026-05-24 10:49:57] Validation | Batch 300/1463 | Loss: 0.9000 | LM_LOSS: 0.3932 | LB_LOSS: 1.0137 |
| [2026-05-24 10:49:59] Validation | Batch 310/1463 | Loss: 0.9005 | LM_LOSS: 0.3937 | LB_LOSS: 1.0136 |
| [2026-05-24 10:50:00] Validation | Batch 320/1463 | Loss: 0.8992 | LM_LOSS: 0.3925 | LB_LOSS: 1.0135 |
| [2026-05-24 10:50:02] Validation | Batch 330/1463 | Loss: 0.8992 | LM_LOSS: 0.3924 | LB_LOSS: 1.0135 |
| [2026-05-24 10:50:03] Validation | Batch 340/1463 | Loss: 0.8986 | LM_LOSS: 0.3918 | LB_LOSS: 1.0135 |
| [2026-05-24 10:50:05] Validation | Batch 350/1463 | Loss: 0.8993 | LM_LOSS: 0.3925 | LB_LOSS: 1.0135 |
| [2026-05-24 10:50:07] Validation | Batch 360/1463 | Loss: 0.8994 | LM_LOSS: 0.3926 | LB_LOSS: 1.0135 |
| [2026-05-24 10:50:09] Validation | Batch 370/1463 | Loss: 0.8992 | LM_LOSS: 0.3924 | LB_LOSS: 1.0136 |
| [2026-05-24 10:50:10] Validation | Batch 380/1463 | Loss: 0.8990 | LM_LOSS: 0.3923 | LB_LOSS: 1.0135 |
| [2026-05-24 10:50:12] Validation | Batch 390/1463 | Loss: 0.8999 | LM_LOSS: 0.3932 | LB_LOSS: 1.0135 |
| [2026-05-24 10:50:14] Validation | Batch 400/1463 | Loss: 0.9000 | LM_LOSS: 0.3932 | LB_LOSS: 1.0135 |
| [2026-05-24 10:50:15] Validation | Batch 410/1463 | Loss: 0.8996 | LM_LOSS: 0.3928 | LB_LOSS: 1.0136 |
| [2026-05-24 10:50:17] Validation | Batch 420/1463 | Loss: 0.8997 | LM_LOSS: 0.3929 | LB_LOSS: 1.0136 |
| [2026-05-24 10:50:19] Validation | Batch 430/1463 | Loss: 0.8995 | LM_LOSS: 0.3926 | LB_LOSS: 1.0137 |
| [2026-05-24 10:50:21] Validation | Batch 440/1463 | Loss: 0.8999 | LM_LOSS: 0.3931 | LB_LOSS: 1.0137 |
| [2026-05-24 10:50:22] Validation | Batch 450/1463 | Loss: 0.8999 | LM_LOSS: 0.3930 | LB_LOSS: 1.0137 |
| [2026-05-24 10:50:24] Validation | Batch 460/1463 | Loss: 0.8998 | LM_LOSS: 0.3929 | LB_LOSS: 1.0137 |
| [2026-05-24 10:50:26] Validation | Batch 470/1463 | Loss: 0.9005 | LM_LOSS: 0.3937 | LB_LOSS: 1.0137 |
| [2026-05-24 10:50:28] Validation | Batch 480/1463 | Loss: 0.9004 | LM_LOSS: 0.3936 | LB_LOSS: 1.0137 |
| [2026-05-24 10:50:30] Validation | Batch 490/1463 | Loss: 0.9001 | LM_LOSS: 0.3933 | LB_LOSS: 1.0136 |
| [2026-05-24 10:50:32] Validation | Batch 500/1463 | Loss: 0.8999 | LM_LOSS: 0.3931 | LB_LOSS: 1.0137 |
| [2026-05-24 10:50:34] Validation | Batch 510/1463 | Loss: 0.8993 | LM_LOSS: 0.3925 | LB_LOSS: 1.0137 |
| [2026-05-24 10:50:35] Validation | Batch 520/1463 | Loss: 0.8989 | LM_LOSS: 0.3921 | LB_LOSS: 1.0137 |
| [2026-05-24 10:50:37] Validation | Batch 530/1463 | Loss: 0.8994 | LM_LOSS: 0.3925 | LB_LOSS: 1.0137 |
| [2026-05-24 10:50:39] Validation | Batch 540/1463 | Loss: 0.8996 | LM_LOSS: 0.3928 | LB_LOSS: 1.0137 |
| [2026-05-24 10:50:40] Validation | Batch 550/1463 | Loss: 0.8993 | LM_LOSS: 0.3925 | LB_LOSS: 1.0137 |
| [2026-05-24 10:50:42] Validation | Batch 560/1463 | Loss: 0.8997 | LM_LOSS: 0.3928 | LB_LOSS: 1.0138 |
| [2026-05-24 10:50:44] Validation | Batch 570/1463 | Loss: 0.8996 | LM_LOSS: 0.3927 | LB_LOSS: 1.0137 |
| [2026-05-24 10:50:46] Validation | Batch 580/1463 | Loss: 0.8991 | LM_LOSS: 0.3922 | LB_LOSS: 1.0137 |
| [2026-05-24 10:50:48] Validation | Batch 590/1463 | Loss: 0.8991 | LM_LOSS: 0.3922 | LB_LOSS: 1.0138 |
| [2026-05-24 10:50:50] Validation | Batch 600/1463 | Loss: 0.8994 | LM_LOSS: 0.3925 | LB_LOSS: 1.0138 |
| [2026-05-24 10:50:52] Validation | Batch 610/1463 | Loss: 0.8993 | LM_LOSS: 0.3924 | LB_LOSS: 1.0138 |
| [2026-05-24 10:50:53] Validation | Batch 620/1463 | Loss: 0.8985 | LM_LOSS: 0.3916 | LB_LOSS: 1.0138 |
| [2026-05-24 10:50:55] Validation | Batch 630/1463 | Loss: 0.8982 | LM_LOSS: 0.3912 | LB_LOSS: 1.0138 |
| [2026-05-24 10:50:57] Validation | Batch 640/1463 | Loss: 0.8979 | LM_LOSS: 0.3910 | LB_LOSS: 1.0139 |
| [2026-05-24 10:50:58] Validation | Batch 650/1463 | Loss: 0.8975 | LM_LOSS: 0.3906 | LB_LOSS: 1.0139 |
| [2026-05-24 10:51:00] Validation | Batch 660/1463 | Loss: 0.8969 | LM_LOSS: 0.3900 | LB_LOSS: 1.0139 |
| [2026-05-24 10:51:02] Validation | Batch 670/1463 | Loss: 0.8964 | LM_LOSS: 0.3895 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:03] Validation | Batch 680/1463 | Loss: 0.8964 | LM_LOSS: 0.3895 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:05] Validation | Batch 690/1463 | Loss: 0.8970 | LM_LOSS: 0.3900 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:07] Validation | Batch 700/1463 | Loss: 0.8968 | LM_LOSS: 0.3899 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:08] Validation | Batch 710/1463 | Loss: 0.8972 | LM_LOSS: 0.3903 | LB_LOSS: 1.0139 |
| [2026-05-24 10:51:10] Validation | Batch 720/1463 | Loss: 0.8979 | LM_LOSS: 0.3910 | LB_LOSS: 1.0139 |
| [2026-05-24 10:51:12] Validation | Batch 730/1463 | Loss: 0.8978 | LM_LOSS: 0.3908 | LB_LOSS: 1.0139 |
| [2026-05-24 10:51:13] Validation | Batch 740/1463 | Loss: 0.8973 | LM_LOSS: 0.3904 | LB_LOSS: 1.0139 |
| [2026-05-24 10:51:15] Validation | Batch 750/1463 | Loss: 0.8971 | LM_LOSS: 0.3902 | LB_LOSS: 1.0139 |
| [2026-05-24 10:51:16] Validation | Batch 760/1463 | Loss: 0.8967 | LM_LOSS: 0.3898 | LB_LOSS: 1.0139 |
| [2026-05-24 10:51:18] Validation | Batch 770/1463 | Loss: 0.8966 | LM_LOSS: 0.3897 | LB_LOSS: 1.0139 |
| [2026-05-24 10:51:19] Validation | Batch 780/1463 | Loss: 0.8964 | LM_LOSS: 0.3895 | LB_LOSS: 1.0139 |
| [2026-05-24 10:51:21] Validation | Batch 790/1463 | Loss: 0.8966 | LM_LOSS: 0.3897 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:22] Validation | Batch 800/1463 | Loss: 0.8966 | LM_LOSS: 0.3897 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:24] Validation | Batch 810/1463 | Loss: 0.8961 | LM_LOSS: 0.3892 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:26] Validation | Batch 820/1463 | Loss: 0.8963 | LM_LOSS: 0.3894 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:28] Validation | Batch 830/1463 | Loss: 0.8964 | LM_LOSS: 0.3895 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:30] Validation | Batch 840/1463 | Loss: 0.8962 | LM_LOSS: 0.3893 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:31] Validation | Batch 850/1463 | Loss: 0.8965 | LM_LOSS: 0.3895 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:33] Validation | Batch 860/1463 | Loss: 0.8966 | LM_LOSS: 0.3896 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:35] Validation | Batch 870/1463 | Loss: 0.8967 | LM_LOSS: 0.3898 | LB_LOSS: 1.0139 |
| [2026-05-24 10:51:37] Validation | Batch 880/1463 | Loss: 0.8961 | LM_LOSS: 0.3891 | LB_LOSS: 1.0139 |
| [2026-05-24 10:51:38] Validation | Batch 890/1463 | Loss: 0.8961 | LM_LOSS: 0.3892 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:40] Validation | Batch 900/1463 | Loss: 0.8958 | LM_LOSS: 0.3889 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:42] Validation | Batch 910/1463 | Loss: 0.8958 | LM_LOSS: 0.3889 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:44] Validation | Batch 920/1463 | Loss: 0.8960 | LM_LOSS: 0.3891 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:46] Validation | Batch 930/1463 | Loss: 0.8956 | LM_LOSS: 0.3887 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:47] Validation | Batch 940/1463 | Loss: 0.8953 | LM_LOSS: 0.3884 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:49] Validation | Batch 950/1463 | Loss: 0.8958 | LM_LOSS: 0.3889 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:51] Validation | Batch 960/1463 | Loss: 0.8958 | LM_LOSS: 0.3889 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:53] Validation | Batch 970/1463 | Loss: 0.8959 | LM_LOSS: 0.3891 | LB_LOSS: 1.0138 |
| [2026-05-24 10:51:55] Validation | Batch 980/1463 | Loss: 0.8963 | LM_LOSS: 0.3894 | LB_LOSS: 1.0137 |
| [2026-05-24 10:51:56] Validation | Batch 990/1463 | Loss: 0.8964 | LM_LOSS: 0.3895 | LB_LOSS: 1.0137 |
| [2026-05-24 10:51:58] Validation | Batch 1000/1463 | Loss: 0.8971 | LM_LOSS: 0.3903 | LB_LOSS: 1.0137 |
| [2026-05-24 10:52:00] Validation | Batch 1010/1463 | Loss: 0.8971 | LM_LOSS: 0.3902 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:02] Validation | Batch 1020/1463 | Loss: 0.8973 | LM_LOSS: 0.3904 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:04] Validation | Batch 1030/1463 | Loss: 0.8977 | LM_LOSS: 0.3908 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:05] Validation | Batch 1040/1463 | Loss: 0.8972 | LM_LOSS: 0.3903 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:07] Validation | Batch 1050/1463 | Loss: 0.8970 | LM_LOSS: 0.3902 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:09] Validation | Batch 1060/1463 | Loss: 0.8969 | LM_LOSS: 0.3900 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:11] Validation | Batch 1070/1463 | Loss: 0.8969 | LM_LOSS: 0.3901 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:13] Validation | Batch 1080/1463 | Loss: 0.8967 | LM_LOSS: 0.3898 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:14] Validation | Batch 1090/1463 | Loss: 0.8966 | LM_LOSS: 0.3898 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:16] Validation | Batch 1100/1463 | Loss: 0.8966 | LM_LOSS: 0.3898 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:18] Validation | Batch 1110/1463 | Loss: 0.8967 | LM_LOSS: 0.3899 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:19] Validation | Batch 1120/1463 | Loss: 0.8965 | LM_LOSS: 0.3896 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:21] Validation | Batch 1130/1463 | Loss: 0.8962 | LM_LOSS: 0.3893 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:23] Validation | Batch 1140/1463 | Loss: 0.8965 | LM_LOSS: 0.3896 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:25] Validation | Batch 1150/1463 | Loss: 0.8964 | LM_LOSS: 0.3896 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:27] Validation | Batch 1160/1463 | Loss: 0.8964 | LM_LOSS: 0.3896 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:29] Validation | Batch 1170/1463 | Loss: 0.8963 | LM_LOSS: 0.3894 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:30] Validation | Batch 1180/1463 | Loss: 0.8963 | LM_LOSS: 0.3895 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:32] Validation | Batch 1190/1463 | Loss: 0.8966 | LM_LOSS: 0.3897 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:34] Validation | Batch 1200/1463 | Loss: 0.8967 | LM_LOSS: 0.3898 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:36] Validation | Batch 1210/1463 | Loss: 0.8971 | LM_LOSS: 0.3902 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:37] Validation | Batch 1220/1463 | Loss: 0.8975 | LM_LOSS: 0.3906 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:39] Validation | Batch 1230/1463 | Loss: 0.8973 | LM_LOSS: 0.3905 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:41] Validation | Batch 1240/1463 | Loss: 0.8977 | LM_LOSS: 0.3908 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:43] Validation | Batch 1250/1463 | Loss: 0.8979 | LM_LOSS: 0.3910 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:45] Validation | Batch 1260/1463 | Loss: 0.8978 | LM_LOSS: 0.3909 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:46] Validation | Batch 1270/1463 | Loss: 0.8976 | LM_LOSS: 0.3907 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:48] Validation | Batch 1280/1463 | Loss: 0.8973 | LM_LOSS: 0.3904 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:50] Validation | Batch 1290/1463 | Loss: 0.8974 | LM_LOSS: 0.3905 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:52] Validation | Batch 1300/1463 | Loss: 0.8971 | LM_LOSS: 0.3902 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:54] Validation | Batch 1310/1463 | Loss: 0.8970 | LM_LOSS: 0.3901 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:55] Validation | Batch 1320/1463 | Loss: 0.8970 | LM_LOSS: 0.3901 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:56] Validation | Batch 1330/1463 | Loss: 0.8969 | LM_LOSS: 0.3900 | LB_LOSS: 1.0138 |
| [2026-05-24 10:52:58] Validation | Batch 1340/1463 | Loss: 0.8972 | LM_LOSS: 0.3903 | LB_LOSS: 1.0138 |
| [2026-05-24 10:53:00] Validation | Batch 1350/1463 | Loss: 0.8972 | LM_LOSS: 0.3903 | LB_LOSS: 1.0138 |
| [2026-05-24 10:53:02] Validation | Batch 1360/1463 | Loss: 0.8975 | LM_LOSS: 0.3906 | LB_LOSS: 1.0137 |
| [2026-05-24 10:53:04] Validation | Batch 1370/1463 | Loss: 0.8980 | LM_LOSS: 0.3911 | LB_LOSS: 1.0138 |
| [2026-05-24 10:53:06] Validation | Batch 1380/1463 | Loss: 0.8978 | LM_LOSS: 0.3909 | LB_LOSS: 1.0137 |
| [2026-05-24 10:53:07] Validation | Batch 1390/1463 | Loss: 0.8977 | LM_LOSS: 0.3908 | LB_LOSS: 1.0138 |
| [2026-05-24 10:53:09] Validation | Batch 1400/1463 | Loss: 0.8980 | LM_LOSS: 0.3911 | LB_LOSS: 1.0137 |
| [2026-05-24 10:53:10] Validation | Batch 1410/1463 | Loss: 0.8982 | LM_LOSS: 0.3913 | LB_LOSS: 1.0137 |
| [2026-05-24 10:53:12] Validation | Batch 1420/1463 | Loss: 0.8982 | LM_LOSS: 0.3913 | LB_LOSS: 1.0137 |
| [2026-05-24 10:53:14] Validation | Batch 1430/1463 | Loss: 0.8982 | LM_LOSS: 0.3914 | LB_LOSS: 1.0137 |
| [2026-05-24 10:53:16] Validation | Batch 1440/1463 | Loss: 0.8987 | LM_LOSS: 0.3919 | LB_LOSS: 1.0137 |
| [2026-05-24 10:53:18] Validation | Batch 1450/1463 | Loss: 0.8984 | LM_LOSS: 0.3915 | LB_LOSS: 1.0137 |
| [2026-05-24 10:53:20] Validation | Batch 1460/1463 | Loss: 0.8987 | LM_LOSS: 0.3918 | LB_LOSS: 1.0137 |
| [2026-05-24 10:53:20] Validation | Batch 1463/1463 | Loss: 0.8986 | LM_LOSS: 0.3917 | LB_LOSS: 1.0137 |
| [2026-05-24 10:53:20] Validation | Loss: 0.8986 | LM_LOSS: 0.3917 | LB_LOSS: 1.0137 | PPL: 1.48 | Time: 257.36s |
| [2026-05-24 10:53:31] Epoch 3 | Step 13010 | Loss: 0.7780 | LM: 0.2712 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.77e-05 |
| [2026-05-24 10:53:42] Epoch 3 | Step 13020 | Loss: 0.7780 | LM: 0.2711 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.72e-05 |
| [2026-05-24 10:53:53] Epoch 3 | Step 13030 | Loss: 0.7780 | LM: 0.2712 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.67e-05 |
| [2026-05-24 10:54:04] Epoch 3 | Step 13040 | Loss: 0.7780 | LM: 0.2713 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.63e-05 |
| [2026-05-24 10:54:14] Epoch 3 | Step 13050 | Loss: 0.7779 | LM: 0.2713 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.58e-05 |
| [2026-05-24 10:54:25] Epoch 3 | Step 13060 | Loss: 0.7779 | LM: 0.2714 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.54e-05 |
| [2026-05-24 10:54:35] Epoch 3 | Step 13070 | Loss: 0.7779 | LM: 0.2714 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.49e-05 |
| [2026-05-24 10:54:46] Epoch 3 | Step 13080 | Loss: 0.7779 | LM: 0.2712 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.45e-05 |
| [2026-05-24 10:54:57] Epoch 3 | Step 13090 | Loss: 0.7780 | LM: 0.2714 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.40e-05 |
| [2026-05-24 10:55:07] Epoch 3 | Step 13100 | Loss: 0.7780 | LM: 0.2715 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.36e-05 |
| [2026-05-24 10:55:18] Epoch 3 | Step 13110 | Loss: 0.7780 | LM: 0.2716 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.31e-05 |
| [2026-05-24 10:55:29] Epoch 3 | Step 13120 | Loss: 0.7779 | LM: 0.2715 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.27e-05 |
| [2026-05-24 10:55:40] Epoch 3 | Step 13130 | Loss: 0.7779 | LM: 0.2715 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.23e-05 |
| [2026-05-24 10:55:51] Epoch 3 | Step 13140 | Loss: 0.7779 | LM: 0.2715 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.18e-05 |
| [2026-05-24 10:56:01] Epoch 3 | Step 13150 | Loss: 0.7779 | LM: 0.2714 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.14e-05 |
| [2026-05-24 10:56:12] Epoch 3 | Step 13160 | Loss: 0.7779 | LM: 0.2713 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.10e-05 |
| [2026-05-24 10:56:24] Epoch 3 | Step 13170 | Loss: 0.7779 | LM: 0.2714 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.06e-05 |
| [2026-05-24 10:56:35] Epoch 3 | Step 13180 | Loss: 0.7779 | LM: 0.2715 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 3.01e-05 |
| [2026-05-24 10:56:47] Epoch 3 | Step 13190 | Loss: 0.7778 | LM: 0.2714 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.97e-05 |
| [2026-05-24 10:56:59] Epoch 3 | Step 13200 | Loss: 0.7778 | LM: 0.2713 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.93e-05 |
| [2026-05-24 10:57:10] Epoch 3 | Step 13210 | Loss: 0.7779 | LM: 0.2714 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.89e-05 |
| [2026-05-24 10:57:22] Epoch 3 | Step 13220 | Loss: 0.7779 | LM: 0.2715 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.85e-05 |
| [2026-05-24 10:57:33] Epoch 3 | Step 13230 | Loss: 0.7780 | LM: 0.2715 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.81e-05 |
| [2026-05-24 10:57:45] Epoch 3 | Step 13240 | Loss: 0.7779 | LM: 0.2715 | LB: 1.0163 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.77e-05 |
| [2026-05-24 10:57:57] Epoch 3 | Step 13250 | Loss: 0.7779 | LM: 0.2714 | LB: 1.0162 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.73e-05 |
| [2026-05-24 10:58:08] Epoch 3 | Step 13260 | Loss: 0.7779 | LM: 0.2715 | LB: 1.0162 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.69e-05 |
| [2026-05-24 10:58:20] Epoch 3 | Step 13270 | Loss: 0.7779 | LM: 0.2715 | LB: 1.0162 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.65e-05 |
| [2026-05-24 10:58:31] Epoch 3 | Step 13280 | Loss: 0.7779 | LM: 0.2714 | LB: 1.0162 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.61e-05 |
| [2026-05-24 10:58:43] Epoch 3 | Step 13290 | Loss: 0.7779 | LM: 0.2714 | LB: 1.0162 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.57e-05 |
| [2026-05-24 10:58:54] Epoch 3 | Step 13300 | Loss: 0.7780 | LM: 0.2714 | LB: 1.0162 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.53e-05 |
| [2026-05-24 10:59:06] Epoch 3 | Step 13310 | Loss: 0.7780 | LM: 0.2714 | LB: 1.0162 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.50e-05 |
| [2026-05-24 10:59:17] Epoch 3 | Step 13320 | Loss: 0.7780 | LM: 0.2714 | LB: 1.0162 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.46e-05 |
| [2026-05-24 10:59:27] Epoch 3 | Step 13330 | Loss: 0.7780 | LM: 0.2713 | LB: 1.0162 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.42e-05 |
| [2026-05-24 10:59:38] Epoch 3 | Step 13340 | Loss: 0.7780 | LM: 0.2714 | LB: 1.0162 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.39e-05 |
| [2026-05-24 10:59:49] Epoch 3 | Step 13350 | Loss: 0.7780 | LM: 0.2715 | LB: 1.0162 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.35e-05 |
| [2026-05-24 11:00:00] Epoch 3 | Step 13360 | Loss: 0.7780 | LM: 0.2715 | LB: 1.0162 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.31e-05 |
| [2026-05-24 11:00:10] Epoch 3 | Step 13370 | Loss: 0.7780 | LM: 0.2715 | LB: 1.0162 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.28e-05 |
| [2026-05-24 11:00:21] Epoch 3 | Step 13380 | Loss: 0.7781 | LM: 0.2716 | LB: 1.0162 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.24e-05 |
| [2026-05-24 11:00:31] Epoch 3 | Step 13390 | Loss: 0.7781 | LM: 0.2716 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.21e-05 |
| [2026-05-24 11:00:42] Epoch 3 | Step 13400 | Loss: 0.7782 | LM: 0.2716 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.18e-05 |
| [2026-05-24 11:00:53] Epoch 3 | Step 13410 | Loss: 0.7783 | LM: 0.2719 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.14e-05 |
| [2026-05-24 11:01:04] Epoch 3 | Step 13420 | Loss: 0.7782 | LM: 0.2717 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.11e-05 |
| [2026-05-24 11:01:15] Epoch 3 | Step 13430 | Loss: 0.7782 | LM: 0.2717 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.08e-05 |
| [2026-05-24 11:01:25] Epoch 3 | Step 13440 | Loss: 0.7782 | LM: 0.2716 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.04e-05 |
| [2026-05-24 11:01:36] Epoch 3 | Step 13450 | Loss: 0.7782 | LM: 0.2716 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 2.01e-05 |
| [2026-05-24 11:01:47] Epoch 3 | Step 13460 | Loss: 0.7781 | LM: 0.2716 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.98e-05 |
| [2026-05-24 11:01:57] Epoch 3 | Step 13470 | Loss: 0.7781 | LM: 0.2716 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.95e-05 |
| [2026-05-24 11:02:08] Epoch 3 | Step 13480 | Loss: 0.7781 | LM: 0.2715 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.92e-05 |
| [2026-05-24 11:02:19] Epoch 3 | Step 13490 | Loss: 0.7782 | LM: 0.2716 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.89e-05 |
| [2026-05-24 11:02:30] Epoch 3 | Step 13500 | Loss: 0.7782 | LM: 0.2715 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.86e-05 |
| [2026-05-24 11:02:40] Epoch 3 | Step 13510 | Loss: 0.7782 | LM: 0.2716 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.83e-05 |
| [2026-05-24 11:02:51] Epoch 3 | Step 13520 | Loss: 0.7783 | LM: 0.2716 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.80e-05 |
| [2026-05-24 11:03:01] Epoch 3 | Step 13530 | Loss: 0.7783 | LM: 0.2715 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.77e-05 |
| [2026-05-24 11:03:12] Epoch 3 | Step 13540 | Loss: 0.7783 | LM: 0.2716 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.74e-05 |
| [2026-05-24 11:03:23] Epoch 3 | Step 13550 | Loss: 0.7784 | LM: 0.2717 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.72e-05 |
| [2026-05-24 11:03:33] Epoch 3 | Step 13560 | Loss: 0.7784 | LM: 0.2717 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.69e-05 |
| [2026-05-24 11:03:44] Epoch 3 | Step 13570 | Loss: 0.7784 | LM: 0.2716 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.66e-05 |
| [2026-05-24 11:03:55] Epoch 3 | Step 13580 | Loss: 0.7784 | LM: 0.2716 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.64e-05 |
| [2026-05-24 11:04:05] Epoch 3 | Step 13590 | Loss: 0.7785 | LM: 0.2717 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.61e-05 |
| [2026-05-24 11:04:16] Epoch 3 | Step 13600 | Loss: 0.7785 | LM: 0.2718 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.59e-05 |
| [2026-05-24 11:04:26] Epoch 3 | Step 13610 | Loss: 0.7785 | LM: 0.2717 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.56e-05 |
| [2026-05-24 11:04:37] Epoch 3 | Step 13620 | Loss: 0.7785 | LM: 0.2717 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.54e-05 |
| [2026-05-24 11:04:48] Epoch 3 | Step 13630 | Loss: 0.7785 | LM: 0.2717 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.51e-05 |
| [2026-05-24 11:04:58] Epoch 3 | Step 13640 | Loss: 0.7785 | LM: 0.2717 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.49e-05 |
| [2026-05-24 11:05:09] Epoch 3 | Step 13650 | Loss: 0.7785 | LM: 0.2716 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.47e-05 |
| [2026-05-24 11:05:19] Epoch 3 | Step 13660 | Loss: 0.7785 | LM: 0.2716 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.45e-05 |
| [2026-05-24 11:05:30] Epoch 3 | Step 13670 | Loss: 0.7785 | LM: 0.2715 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.42e-05 |
| [2026-05-24 11:05:41] Epoch 3 | Step 13680 | Loss: 0.7785 | LM: 0.2716 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.40e-05 |
| [2026-05-24 11:05:51] Epoch 3 | Step 13690 | Loss: 0.7785 | LM: 0.2716 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.38e-05 |
| [2026-05-24 11:06:02] Epoch 3 | Step 13700 | Loss: 0.7785 | LM: 0.2717 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.36e-05 |
| [2026-05-24 11:06:13] Epoch 3 | Step 13710 | Loss: 0.7785 | LM: 0.2717 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.34e-05 |
| [2026-05-24 11:06:24] Epoch 3 | Step 13720 | Loss: 0.7785 | LM: 0.2718 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.32e-05 |
| [2026-05-24 11:06:34] Epoch 3 | Step 13730 | Loss: 0.7785 | LM: 0.2718 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.31e-05 |
| [2026-05-24 11:06:45] Epoch 3 | Step 13740 | Loss: 0.7785 | LM: 0.2718 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.29e-05 |
| [2026-05-24 11:06:55] Epoch 3 | Step 13750 | Loss: 0.7785 | LM: 0.2718 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.27e-05 |
| [2026-05-24 11:07:06] Epoch 3 | Step 13760 | Loss: 0.7785 | LM: 0.2718 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.25e-05 |
| [2026-05-24 11:07:17] Epoch 3 | Step 13770 | Loss: 0.7786 | LM: 0.2720 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.24e-05 |
| [2026-05-24 11:07:27] Epoch 3 | Step 13780 | Loss: 0.7785 | LM: 0.2720 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.22e-05 |
| [2026-05-24 11:07:38] Epoch 3 | Step 13790 | Loss: 0.7786 | LM: 0.2720 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.21e-05 |
| [2026-05-24 11:07:48] Epoch 3 | Step 13800 | Loss: 0.7785 | LM: 0.2719 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.19e-05 |
| [2026-05-24 11:07:59] Epoch 3 | Step 13810 | Loss: 0.7786 | LM: 0.2720 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.18e-05 |
| [2026-05-24 11:08:10] Epoch 3 | Step 13820 | Loss: 0.7786 | LM: 0.2720 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.16e-05 |
| [2026-05-24 11:08:21] Epoch 3 | Step 13830 | Loss: 0.7787 | LM: 0.2720 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.15e-05 |
| [2026-05-24 11:08:31] Epoch 3 | Step 13840 | Loss: 0.7786 | LM: 0.2721 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.14e-05 |
| [2026-05-24 11:08:42] Epoch 3 | Step 13850 | Loss: 0.7786 | LM: 0.2721 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.13e-05 |
| [2026-05-24 11:08:53] Epoch 3 | Step 13860 | Loss: 0.7786 | LM: 0.2720 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.11e-05 |
| [2026-05-24 11:09:03] Epoch 3 | Step 13870 | Loss: 0.7786 | LM: 0.2720 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.10e-05 |
| [2026-05-24 11:09:14] Epoch 3 | Step 13880 | Loss: 0.7785 | LM: 0.2719 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.09e-05 |
| [2026-05-24 11:09:25] Epoch 3 | Step 13890 | Loss: 0.7785 | LM: 0.2720 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.08e-05 |
| [2026-05-24 11:09:36] Epoch 3 | Step 13900 | Loss: 0.7785 | LM: 0.2720 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.07e-05 |
| [2026-05-24 11:09:46] Epoch 3 | Step 13910 | Loss: 0.7785 | LM: 0.2720 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.06e-05 |
| [2026-05-24 11:09:57] Epoch 3 | Step 13920 | Loss: 0.7785 | LM: 0.2721 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.06e-05 |
| [2026-05-24 11:10:08] Epoch 3 | Step 13930 | Loss: 0.7785 | LM: 0.2721 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.05e-05 |
| [2026-05-24 11:10:19] Epoch 3 | Step 13940 | Loss: 0.7785 | LM: 0.2721 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.04e-05 |
| [2026-05-24 11:10:29] Epoch 3 | Step 13950 | Loss: 0.7785 | LM: 0.2721 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.04e-05 |
| [2026-05-24 11:10:40] Epoch 3 | Step 13960 | Loss: 0.7786 | LM: 0.2722 | LB: 1.0161 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.03e-05 |
| [2026-05-24 11:10:51] Epoch 3 | Step 13970 | Loss: 0.7786 | LM: 0.2721 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.02e-05 |
| [2026-05-24 11:11:01] Epoch 3 | Step 13980 | Loss: 0.7785 | LM: 0.2720 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.02e-05 |
| [2026-05-24 11:11:12] Epoch 3 | Step 13990 | Loss: 0.7786 | LM: 0.2719 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.01e-05 |
| [2026-05-24 11:11:23] Epoch 3 | Step 14000 | Loss: 0.7786 | LM: 0.2719 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.166 | LR: 1.01e-05 |
| [2026-05-24 11:11:24] Validation | Batch 10/1463 | Loss: 0.8591 | LM_LOSS: 0.3542 | LB_LOSS: 1.0097 |
| [2026-05-24 11:11:26] Validation | Batch 20/1463 | Loss: 0.8729 | LM_LOSS: 0.3671 | LB_LOSS: 1.0116 |
| [2026-05-24 11:11:28] Validation | Batch 30/1463 | Loss: 0.8720 | LM_LOSS: 0.3659 | LB_LOSS: 1.0123 |
| [2026-05-24 11:11:29] Validation | Batch 40/1463 | Loss: 0.8816 | LM_LOSS: 0.3751 | LB_LOSS: 1.0131 |
| [2026-05-24 11:11:31] Validation | Batch 50/1463 | Loss: 0.8903 | LM_LOSS: 0.3840 | LB_LOSS: 1.0126 |
| [2026-05-24 11:11:33] Validation | Batch 60/1463 | Loss: 0.8922 | LM_LOSS: 0.3858 | LB_LOSS: 1.0127 |
| [2026-05-24 11:11:35] Validation | Batch 70/1463 | Loss: 0.8924 | LM_LOSS: 0.3861 | LB_LOSS: 1.0127 |
| [2026-05-24 11:11:37] Validation | Batch 80/1463 | Loss: 0.8957 | LM_LOSS: 0.3893 | LB_LOSS: 1.0127 |
| [2026-05-24 11:11:39] Validation | Batch 90/1463 | Loss: 0.8946 | LM_LOSS: 0.3883 | LB_LOSS: 1.0127 |
| [2026-05-24 11:11:40] Validation | Batch 100/1463 | Loss: 0.8945 | LM_LOSS: 0.3881 | LB_LOSS: 1.0127 |
| [2026-05-24 11:11:42] Validation | Batch 110/1463 | Loss: 0.8922 | LM_LOSS: 0.3857 | LB_LOSS: 1.0129 |
| [2026-05-24 11:11:44] Validation | Batch 120/1463 | Loss: 0.8940 | LM_LOSS: 0.3876 | LB_LOSS: 1.0129 |
| [2026-05-24 11:11:45] Validation | Batch 130/1463 | Loss: 0.8974 | LM_LOSS: 0.3909 | LB_LOSS: 1.0130 |
| [2026-05-24 11:11:47] Validation | Batch 140/1463 | Loss: 0.8991 | LM_LOSS: 0.3926 | LB_LOSS: 1.0129 |
| [2026-05-24 11:11:49] Validation | Batch 150/1463 | Loss: 0.8977 | LM_LOSS: 0.3912 | LB_LOSS: 1.0131 |
| [2026-05-24 11:11:51] Validation | Batch 160/1463 | Loss: 0.8985 | LM_LOSS: 0.3920 | LB_LOSS: 1.0130 |
| [2026-05-24 11:11:53] Validation | Batch 170/1463 | Loss: 0.8978 | LM_LOSS: 0.3913 | LB_LOSS: 1.0130 |
| [2026-05-24 11:11:55] Validation | Batch 180/1463 | Loss: 0.8983 | LM_LOSS: 0.3918 | LB_LOSS: 1.0131 |
| [2026-05-24 11:11:56] Validation | Batch 190/1463 | Loss: 0.8989 | LM_LOSS: 0.3924 | LB_LOSS: 1.0131 |
| [2026-05-24 11:11:58] Validation | Batch 200/1463 | Loss: 0.8982 | LM_LOSS: 0.3916 | LB_LOSS: 1.0131 |
| [2026-05-24 11:12:00] Validation | Batch 210/1463 | Loss: 0.8986 | LM_LOSS: 0.3920 | LB_LOSS: 1.0131 |
| [2026-05-24 11:12:02] Validation | Batch 220/1463 | Loss: 0.8978 | LM_LOSS: 0.3912 | LB_LOSS: 1.0131 |
| [2026-05-24 11:12:04] Validation | Batch 230/1463 | Loss: 0.8996 | LM_LOSS: 0.3931 | LB_LOSS: 1.0130 |
| [2026-05-24 11:12:05] Validation | Batch 240/1463 | Loss: 0.9005 | LM_LOSS: 0.3940 | LB_LOSS: 1.0130 |
| [2026-05-24 11:12:07] Validation | Batch 250/1463 | Loss: 0.8989 | LM_LOSS: 0.3924 | LB_LOSS: 1.0130 |
| [2026-05-24 11:12:09] Validation | Batch 260/1463 | Loss: 0.9007 | LM_LOSS: 0.3941 | LB_LOSS: 1.0132 |
| [2026-05-24 11:12:11] Validation | Batch 270/1463 | Loss: 0.8991 | LM_LOSS: 0.3925 | LB_LOSS: 1.0131 |
| [2026-05-24 11:12:13] Validation | Batch 280/1463 | Loss: 0.9003 | LM_LOSS: 0.3937 | LB_LOSS: 1.0131 |
| [2026-05-24 11:12:15] Validation | Batch 290/1463 | Loss: 0.8992 | LM_LOSS: 0.3926 | LB_LOSS: 1.0131 |
| [2026-05-24 11:12:16] Validation | Batch 300/1463 | Loss: 0.8998 | LM_LOSS: 0.3932 | LB_LOSS: 1.0132 |
| [2026-05-24 11:12:18] Validation | Batch 310/1463 | Loss: 0.9004 | LM_LOSS: 0.3938 | LB_LOSS: 1.0132 |
| [2026-05-24 11:12:20] Validation | Batch 320/1463 | Loss: 0.8991 | LM_LOSS: 0.3925 | LB_LOSS: 1.0131 |
| [2026-05-24 11:12:21] Validation | Batch 330/1463 | Loss: 0.8990 | LM_LOSS: 0.3924 | LB_LOSS: 1.0131 |
| [2026-05-24 11:12:23] Validation | Batch 340/1463 | Loss: 0.8984 | LM_LOSS: 0.3918 | LB_LOSS: 1.0131 |
| [2026-05-24 11:12:25] Validation | Batch 350/1463 | Loss: 0.8991 | LM_LOSS: 0.3926 | LB_LOSS: 1.0131 |
| [2026-05-24 11:12:27] Validation | Batch 360/1463 | Loss: 0.8992 | LM_LOSS: 0.3927 | LB_LOSS: 1.0131 |
| [2026-05-24 11:12:28] Validation | Batch 370/1463 | Loss: 0.8990 | LM_LOSS: 0.3924 | LB_LOSS: 1.0132 |
| [2026-05-24 11:12:30] Validation | Batch 380/1463 | Loss: 0.8988 | LM_LOSS: 0.3923 | LB_LOSS: 1.0131 |
| [2026-05-24 11:12:32] Validation | Batch 390/1463 | Loss: 0.8997 | LM_LOSS: 0.3932 | LB_LOSS: 1.0131 |
| [2026-05-24 11:12:33] Validation | Batch 400/1463 | Loss: 0.8998 | LM_LOSS: 0.3932 | LB_LOSS: 1.0131 |
| [2026-05-24 11:12:35] Validation | Batch 410/1463 | Loss: 0.8995 | LM_LOSS: 0.3929 | LB_LOSS: 1.0132 |
| [2026-05-24 11:12:37] Validation | Batch 420/1463 | Loss: 0.8997 | LM_LOSS: 0.3931 | LB_LOSS: 1.0132 |
| [2026-05-24 11:12:39] Validation | Batch 430/1463 | Loss: 0.8994 | LM_LOSS: 0.3928 | LB_LOSS: 1.0133 |
| [2026-05-24 11:12:40] Validation | Batch 440/1463 | Loss: 0.8999 | LM_LOSS: 0.3933 | LB_LOSS: 1.0133 |
| [2026-05-24 11:12:42] Validation | Batch 450/1463 | Loss: 0.8998 | LM_LOSS: 0.3932 | LB_LOSS: 1.0133 |
| [2026-05-24 11:12:44] Validation | Batch 460/1463 | Loss: 0.8998 | LM_LOSS: 0.3931 | LB_LOSS: 1.0133 |
| [2026-05-24 11:12:46] Validation | Batch 470/1463 | Loss: 0.9005 | LM_LOSS: 0.3939 | LB_LOSS: 1.0133 |
| [2026-05-24 11:12:48] Validation | Batch 480/1463 | Loss: 0.9003 | LM_LOSS: 0.3937 | LB_LOSS: 1.0132 |
| [2026-05-24 11:12:49] Validation | Batch 490/1463 | Loss: 0.9001 | LM_LOSS: 0.3935 | LB_LOSS: 1.0132 |
| [2026-05-24 11:12:52] Validation | Batch 500/1463 | Loss: 0.8999 | LM_LOSS: 0.3933 | LB_LOSS: 1.0133 |
| [2026-05-24 11:12:53] Validation | Batch 510/1463 | Loss: 0.8992 | LM_LOSS: 0.3926 | LB_LOSS: 1.0133 |
| [2026-05-24 11:12:55] Validation | Batch 520/1463 | Loss: 0.8988 | LM_LOSS: 0.3921 | LB_LOSS: 1.0133 |
| [2026-05-24 11:12:56] Validation | Batch 530/1463 | Loss: 0.8992 | LM_LOSS: 0.3926 | LB_LOSS: 1.0133 |
| [2026-05-24 11:12:58] Validation | Batch 540/1463 | Loss: 0.8995 | LM_LOSS: 0.3928 | LB_LOSS: 1.0133 |
| [2026-05-24 11:12:59] Validation | Batch 550/1463 | Loss: 0.8991 | LM_LOSS: 0.3925 | LB_LOSS: 1.0133 |
| [2026-05-24 11:13:01] Validation | Batch 560/1463 | Loss: 0.8996 | LM_LOSS: 0.3929 | LB_LOSS: 1.0133 |
| [2026-05-24 11:13:03] Validation | Batch 570/1463 | Loss: 0.8995 | LM_LOSS: 0.3928 | LB_LOSS: 1.0133 |
| [2026-05-24 11:13:05] Validation | Batch 580/1463 | Loss: 0.8989 | LM_LOSS: 0.3923 | LB_LOSS: 1.0133 |
| [2026-05-24 11:13:07] Validation | Batch 590/1463 | Loss: 0.8989 | LM_LOSS: 0.3922 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:09] Validation | Batch 600/1463 | Loss: 0.8992 | LM_LOSS: 0.3925 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:11] Validation | Batch 610/1463 | Loss: 0.8992 | LM_LOSS: 0.3925 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:13] Validation | Batch 620/1463 | Loss: 0.8983 | LM_LOSS: 0.3916 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:14] Validation | Batch 630/1463 | Loss: 0.8980 | LM_LOSS: 0.3912 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:16] Validation | Batch 640/1463 | Loss: 0.8977 | LM_LOSS: 0.3910 | LB_LOSS: 1.0135 |
| [2026-05-24 11:13:18] Validation | Batch 650/1463 | Loss: 0.8973 | LM_LOSS: 0.3906 | LB_LOSS: 1.0135 |
| [2026-05-24 11:13:19] Validation | Batch 660/1463 | Loss: 0.8967 | LM_LOSS: 0.3900 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:21] Validation | Batch 670/1463 | Loss: 0.8963 | LM_LOSS: 0.3895 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:23] Validation | Batch 680/1463 | Loss: 0.8963 | LM_LOSS: 0.3896 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:25] Validation | Batch 690/1463 | Loss: 0.8967 | LM_LOSS: 0.3900 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:26] Validation | Batch 700/1463 | Loss: 0.8966 | LM_LOSS: 0.3899 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:28] Validation | Batch 710/1463 | Loss: 0.8970 | LM_LOSS: 0.3903 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:30] Validation | Batch 720/1463 | Loss: 0.8977 | LM_LOSS: 0.3910 | LB_LOSS: 1.0135 |
| [2026-05-24 11:13:31] Validation | Batch 730/1463 | Loss: 0.8976 | LM_LOSS: 0.3908 | LB_LOSS: 1.0135 |
| [2026-05-24 11:13:33] Validation | Batch 740/1463 | Loss: 0.8971 | LM_LOSS: 0.3904 | LB_LOSS: 1.0135 |
| [2026-05-24 11:13:34] Validation | Batch 750/1463 | Loss: 0.8969 | LM_LOSS: 0.3902 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:36] Validation | Batch 760/1463 | Loss: 0.8966 | LM_LOSS: 0.3898 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:38] Validation | Batch 770/1463 | Loss: 0.8964 | LM_LOSS: 0.3897 | LB_LOSS: 1.0135 |
| [2026-05-24 11:13:39] Validation | Batch 780/1463 | Loss: 0.8963 | LM_LOSS: 0.3896 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:41] Validation | Batch 790/1463 | Loss: 0.8965 | LM_LOSS: 0.3898 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:42] Validation | Batch 800/1463 | Loss: 0.8965 | LM_LOSS: 0.3898 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:44] Validation | Batch 810/1463 | Loss: 0.8960 | LM_LOSS: 0.3894 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:46] Validation | Batch 820/1463 | Loss: 0.8962 | LM_LOSS: 0.3895 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:48] Validation | Batch 830/1463 | Loss: 0.8963 | LM_LOSS: 0.3896 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:50] Validation | Batch 840/1463 | Loss: 0.8962 | LM_LOSS: 0.3895 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:52] Validation | Batch 850/1463 | Loss: 0.8964 | LM_LOSS: 0.3897 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:53] Validation | Batch 860/1463 | Loss: 0.8965 | LM_LOSS: 0.3898 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:55] Validation | Batch 870/1463 | Loss: 0.8967 | LM_LOSS: 0.3899 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:57] Validation | Batch 880/1463 | Loss: 0.8960 | LM_LOSS: 0.3893 | LB_LOSS: 1.0134 |
| [2026-05-24 11:13:59] Validation | Batch 890/1463 | Loss: 0.8960 | LM_LOSS: 0.3893 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:00] Validation | Batch 900/1463 | Loss: 0.8958 | LM_LOSS: 0.3891 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:02] Validation | Batch 910/1463 | Loss: 0.8958 | LM_LOSS: 0.3891 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:04] Validation | Batch 920/1463 | Loss: 0.8960 | LM_LOSS: 0.3893 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:06] Validation | Batch 930/1463 | Loss: 0.8956 | LM_LOSS: 0.3889 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:08] Validation | Batch 940/1463 | Loss: 0.8953 | LM_LOSS: 0.3886 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:10] Validation | Batch 950/1463 | Loss: 0.8958 | LM_LOSS: 0.3891 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:11] Validation | Batch 960/1463 | Loss: 0.8958 | LM_LOSS: 0.3891 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:14] Validation | Batch 970/1463 | Loss: 0.8959 | LM_LOSS: 0.3893 | LB_LOSS: 1.0133 |
| [2026-05-24 11:14:15] Validation | Batch 980/1463 | Loss: 0.8962 | LM_LOSS: 0.3896 | LB_LOSS: 1.0133 |
| [2026-05-24 11:14:17] Validation | Batch 990/1463 | Loss: 0.8964 | LM_LOSS: 0.3897 | LB_LOSS: 1.0133 |
| [2026-05-24 11:14:19] Validation | Batch 1000/1463 | Loss: 0.8971 | LM_LOSS: 0.3905 | LB_LOSS: 1.0133 |
| [2026-05-24 11:14:21] Validation | Batch 1010/1463 | Loss: 0.8971 | LM_LOSS: 0.3904 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:23] Validation | Batch 1020/1463 | Loss: 0.8973 | LM_LOSS: 0.3906 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:25] Validation | Batch 1030/1463 | Loss: 0.8977 | LM_LOSS: 0.3910 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:26] Validation | Batch 1040/1463 | Loss: 0.8972 | LM_LOSS: 0.3905 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:28] Validation | Batch 1050/1463 | Loss: 0.8971 | LM_LOSS: 0.3904 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:30] Validation | Batch 1060/1463 | Loss: 0.8970 | LM_LOSS: 0.3903 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:32] Validation | Batch 1070/1463 | Loss: 0.8970 | LM_LOSS: 0.3903 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:34] Validation | Batch 1080/1463 | Loss: 0.8967 | LM_LOSS: 0.3900 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:35] Validation | Batch 1090/1463 | Loss: 0.8967 | LM_LOSS: 0.3900 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:37] Validation | Batch 1100/1463 | Loss: 0.8967 | LM_LOSS: 0.3900 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:39] Validation | Batch 1110/1463 | Loss: 0.8968 | LM_LOSS: 0.3901 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:40] Validation | Batch 1120/1463 | Loss: 0.8966 | LM_LOSS: 0.3899 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:43] Validation | Batch 1130/1463 | Loss: 0.8963 | LM_LOSS: 0.3896 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:44] Validation | Batch 1140/1463 | Loss: 0.8966 | LM_LOSS: 0.3899 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:46] Validation | Batch 1150/1463 | Loss: 0.8965 | LM_LOSS: 0.3899 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:48] Validation | Batch 1160/1463 | Loss: 0.8965 | LM_LOSS: 0.3898 | LB_LOSS: 1.0133 |
| [2026-05-24 11:14:50] Validation | Batch 1170/1463 | Loss: 0.8964 | LM_LOSS: 0.3897 | LB_LOSS: 1.0133 |
| [2026-05-24 11:14:52] Validation | Batch 1180/1463 | Loss: 0.8964 | LM_LOSS: 0.3898 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:53] Validation | Batch 1190/1463 | Loss: 0.8967 | LM_LOSS: 0.3900 | LB_LOSS: 1.0133 |
| [2026-05-24 11:14:55] Validation | Batch 1200/1463 | Loss: 0.8968 | LM_LOSS: 0.3901 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:57] Validation | Batch 1210/1463 | Loss: 0.8972 | LM_LOSS: 0.3905 | LB_LOSS: 1.0134 |
| [2026-05-24 11:14:59] Validation | Batch 1220/1463 | Loss: 0.8976 | LM_LOSS: 0.3909 | LB_LOSS: 1.0134 |
| [2026-05-24 11:15:00] Validation | Batch 1230/1463 | Loss: 0.8975 | LM_LOSS: 0.3908 | LB_LOSS: 1.0134 |
| [2026-05-24 11:15:02] Validation | Batch 1240/1463 | Loss: 0.8977 | LM_LOSS: 0.3911 | LB_LOSS: 1.0134 |
| [2026-05-24 11:15:04] Validation | Batch 1250/1463 | Loss: 0.8979 | LM_LOSS: 0.3913 | LB_LOSS: 1.0134 |
| [2026-05-24 11:15:06] Validation | Batch 1260/1463 | Loss: 0.8979 | LM_LOSS: 0.3912 | LB_LOSS: 1.0134 |
| [2026-05-24 11:15:08] Validation | Batch 1270/1463 | Loss: 0.8977 | LM_LOSS: 0.3910 | LB_LOSS: 1.0134 |
| [2026-05-24 11:15:10] Validation | Batch 1280/1463 | Loss: 0.8974 | LM_LOSS: 0.3907 | LB_LOSS: 1.0134 |
| [2026-05-24 11:15:12] Validation | Batch 1290/1463 | Loss: 0.8975 | LM_LOSS: 0.3908 | LB_LOSS: 1.0134 |
| [2026-05-24 11:15:13] Validation | Batch 1300/1463 | Loss: 0.8972 | LM_LOSS: 0.3905 | LB_LOSS: 1.0134 |
| [2026-05-24 11:15:15] Validation | Batch 1310/1463 | Loss: 0.8971 | LM_LOSS: 0.3904 | LB_LOSS: 1.0134 |
| [2026-05-24 11:15:17] Validation | Batch 1320/1463 | Loss: 0.8971 | LM_LOSS: 0.3904 | LB_LOSS: 1.0134 |
| [2026-05-24 11:15:18] Validation | Batch 1330/1463 | Loss: 0.8970 | LM_LOSS: 0.3904 | LB_LOSS: 1.0133 |
| [2026-05-24 11:15:20] Validation | Batch 1340/1463 | Loss: 0.8973 | LM_LOSS: 0.3906 | LB_LOSS: 1.0133 |
| [2026-05-24 11:15:22] Validation | Batch 1350/1463 | Loss: 0.8973 | LM_LOSS: 0.3906 | LB_LOSS: 1.0133 |
| [2026-05-24 11:15:24] Validation | Batch 1360/1463 | Loss: 0.8976 | LM_LOSS: 0.3910 | LB_LOSS: 1.0133 |
| [2026-05-24 11:15:26] Validation | Batch 1370/1463 | Loss: 0.8981 | LM_LOSS: 0.3914 | LB_LOSS: 1.0133 |
| [2026-05-24 11:15:27] Validation | Batch 1380/1463 | Loss: 0.8979 | LM_LOSS: 0.3912 | LB_LOSS: 1.0133 |
| [2026-05-24 11:15:29] Validation | Batch 1390/1463 | Loss: 0.8978 | LM_LOSS: 0.3911 | LB_LOSS: 1.0133 |
| [2026-05-24 11:15:31] Validation | Batch 1400/1463 | Loss: 0.8981 | LM_LOSS: 0.3914 | LB_LOSS: 1.0133 |
| [2026-05-24 11:15:32] Validation | Batch 1410/1463 | Loss: 0.8983 | LM_LOSS: 0.3916 | LB_LOSS: 1.0133 |
| [2026-05-24 11:15:34] Validation | Batch 1420/1463 | Loss: 0.8983 | LM_LOSS: 0.3917 | LB_LOSS: 1.0133 |
| [2026-05-24 11:15:36] Validation | Batch 1430/1463 | Loss: 0.8984 | LM_LOSS: 0.3917 | LB_LOSS: 1.0133 |
| [2026-05-24 11:15:38] Validation | Batch 1440/1463 | Loss: 0.8989 | LM_LOSS: 0.3922 | LB_LOSS: 1.0133 |
| [2026-05-24 11:15:40] Validation | Batch 1450/1463 | Loss: 0.8985 | LM_LOSS: 0.3918 | LB_LOSS: 1.0133 |
| [2026-05-24 11:15:42] Validation | Batch 1460/1463 | Loss: 0.8988 | LM_LOSS: 0.3921 | LB_LOSS: 1.0133 |
| [2026-05-24 11:15:42] Validation | Batch 1463/1463 | Loss: 0.8987 | LM_LOSS: 0.3920 | LB_LOSS: 1.0133 |
| [2026-05-24 11:15:42] Validation | Loss: 0.8987 | LM_LOSS: 0.3920 | LB_LOSS: 1.0133 | PPL: 1.48 | Time: 259.70s |
| [2026-05-24 11:15:53] Epoch 3 | Step 14010 | Loss: 0.7786 | LM: 0.2720 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.01e-05 |
| [2026-05-24 11:16:04] Epoch 3 | Step 14020 | Loss: 0.7786 | LM: 0.2718 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-05 |
| [2026-05-24 11:16:16] Epoch 3 | Step 14030 | Loss: 0.7787 | LM: 0.2719 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-05 |
| [2026-05-24 11:16:27] Epoch 3 | Step 14040 | Loss: 0.7787 | LM: 0.2719 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-05 |
| [2026-05-24 11:16:38] Epoch 3 | Step 14050 | Loss: 0.7787 | LM: 0.2719 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-05 |
| [2026-05-24 11:16:50] Epoch 3 | Step 14060 | Loss: 0.7787 | LM: 0.2720 | LB: 1.0160 | CL0: 4.1 | CL1: 5.2 | HR0: 0.246/SR0: 0.216 | HR1: 0.194/SR1: 0.167 | LR: 1.00e-05 |
| [2026-05-24 11:16:52] Epoch 3 completed in 6433.85s | Loss: 0.7787 | CL0: 4.1 | CL1: 5.2 |
| [2026-05-24 11:16:52] |
| Training completed! |
| [2026-05-24 11:16:56] Final model: outputs/2026-05-24/N_6.0/model_final.pt |
|
|