| [2026-04-25 20:07:20,895][accelerate.utils.other][WARNING] - Detected kernel version 5.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher. |
| [2026-04-25 20:07:20] CUDA_VISIBLE_DEVICES: 0,1 |
| [2026-04-25 20:07:20] Number of processes: 2 |
| [2026-04-25 20:07:20] Process index: 0 |
| [2026-04-25 20:07:20] Mixed precision: bf16 |
| [2026-04-25 20:07:20] ============================================================ |
| [2026-04-25 20:07:20] HNet Training Pipeline (Hydra + Trackio + Accelerate) |
| [2026-04-25 20:07:20] ============================================================ |
| [2026-04-25 20:07:20] 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: 1 |
| batch_size: 4 |
| 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: 0.01 |
| load_balancing_N: 4.0 |
| max_grad_norm: 1.0 |
| use_amp: true |
| resume: false |
| resume_checkpoint: null |
| warmup_model: true |
| data: |
| path: /workspace/byte-llms-code/code_completion_exp/datasets/data_V4_full |
| max_context_len: 4096 |
| max_target_len: 256 |
| num_workers: 0 |
| pin_memory: true |
| max_train_samples: null |
| max_val_samples: 2000 |
| logging: |
| log_interval: 10 |
| save_interval: 0 |
| eval_interval: 2000 |
| save_every_epoch: false |
| tracking: |
| enabled: true |
| backend: wandb |
| project: code-completion_lr-sweep |
| run_name: hnet_xl_code_lr_1e-4 |
| entity: null |
| base_url: https://wandb.platun0v.ru |
| local_dir: /workspace/byte-llms-code/outputs/lr_sweep/hnet_xl_code_lr_1e-4 |
| paths: |
| output_dir: /workspace/byte-llms-code/outputs/lr_sweep/hnet_xl_code_lr_1e-4 |
| seed: 42 |
| device: cuda |
|
|
| [2026-04-25 20:07:23] Initializing tokenizer... |
| [2026-04-25 20:07:23] Loading model... |
| [2026-04-25 20:07:28] Loaded pretrained: /workspace/byte-llms-code/hnet_project/checkpoints/hnet_2stage_XL_code.pt |
| [2026-04-25 20:07:28] Applied LR multipliers: [2.0, 1.5, 1.0] |
| [2026-04-25 20:07:28] Warming up model... |
| [2026-04-25 20:08:11] Total params: 1,654,090,112 |
| [2026-04-25 20:08:11] Trainable params: 1,654,090,112 |
| [2026-04-25 20:08:11] Creating dataloaders... |
| [2026-04-25 20:08:11] Train dataset size: 316397 |
| [2026-04-25 20:08:11] Train batches per epoch (before DDP split): 79100 |
| [2026-04-25 20:08:11] Validation dataset size: 2000 |
| [2026-04-25 20:08:11] Validation batches: 84 |
| [2026-04-25 20:08:11] Creating optimizer... |
| [2026-04-25 20:08:11] Total steps: 9887, Steps per epoch: 39550 |
| [2026-04-25 20:08:11] Preparing model, optimizer, and dataloaders with Accelerate... |
| [2026-04-25 20:08:12] Train batches per epoch (after DDP split): 39550 |
| [2026-04-25 20:08:12] Starting training... |
| [2026-04-25 20:08:12] |
| ============================================================ |
| [2026-04-25 20:08:12] EPOCH 1/1 |
| [2026-04-25 20:08:12] ============================================================ |
| [2026-04-25 20:09:07] Epoch 1 | Step 10 | Loss: 0.6473 | LM: 0.6116 | LB: 1.1577 | CL0: 2.9 | CL1: 2.1 | HR0: 0.351/SR0: 0.351 | HR1: 0.476/SR1: 0.455 | LR: 1.18e-05 |
| [2026-04-25 20:09:15] Epoch 1 | Step 20 | Loss: 0.6433 | LM: 0.6306 | LB: 1.1554 | CL0: 2.9 | CL1: 2.1 | HR0: 0.352/SR0: 0.351 | HR1: 0.475/SR1: 0.455 | LR: 1.36e-05 |
| [2026-04-25 20:09:22] Epoch 1 | Step 30 | Loss: 0.6173 | LM: 0.5970 | LB: 1.1526 | CL0: 2.9 | CL1: 2.1 | HR0: 0.352/SR0: 0.351 | HR1: 0.473/SR1: 0.452 | LR: 1.55e-05 |
| [2026-04-25 20:09:29] Epoch 1 | Step 40 | Loss: 0.6019 | LM: 0.5722 | LB: 1.1608 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.478/SR1: 0.456 | LR: 1.73e-05 |
| [2026-04-25 20:09:36] Epoch 1 | Step 50 | Loss: 0.5685 | LM: 0.5288 | LB: 1.1597 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.476/SR1: 0.456 | LR: 1.91e-05 |
| [2026-04-25 20:09:43] Epoch 1 | Step 60 | Loss: 0.5394 | LM: 0.5020 | LB: 1.1622 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.479/SR1: 0.458 | LR: 2.09e-05 |
| [2026-04-25 20:09:50] Epoch 1 | Step 70 | Loss: 0.5170 | LM: 0.4868 | LB: 1.1621 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.479/SR1: 0.458 | LR: 2.28e-05 |
| [2026-04-25 20:09:57] Epoch 1 | Step 80 | Loss: 0.5018 | LM: 0.4809 | LB: 1.1636 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.480/SR1: 0.459 | LR: 2.46e-05 |
| [2026-04-25 20:10:05] Epoch 1 | Step 90 | Loss: 0.4886 | LM: 0.4675 | LB: 1.1645 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.481/SR1: 0.459 | LR: 2.64e-05 |
| [2026-04-25 20:10:12] Epoch 1 | Step 100 | Loss: 0.4758 | LM: 0.4668 | LB: 1.1644 | CL0: 2.8 | CL1: 2.1 | HR0: 0.360/SR0: 0.357 | HR1: 0.479/SR1: 0.458 | LR: 2.82e-05 |
| [2026-04-25 20:10:19] Epoch 1 | Step 110 | Loss: 0.4698 | LM: 0.4682 | LB: 1.1654 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.356 | HR1: 0.481/SR1: 0.459 | LR: 3.00e-05 |
| [2026-04-25 20:10:26] Epoch 1 | Step 120 | Loss: 0.4621 | LM: 0.4535 | LB: 1.1648 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.481/SR1: 0.459 | LR: 3.19e-05 |
| [2026-04-25 20:10:33] Epoch 1 | Step 130 | Loss: 0.4549 | LM: 0.4460 | LB: 1.1648 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.481/SR1: 0.460 | LR: 3.37e-05 |
| [2026-04-25 20:10:40] Epoch 1 | Step 140 | Loss: 0.4481 | LM: 0.4439 | LB: 1.1656 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.481/SR1: 0.460 | LR: 3.55e-05 |
| [2026-04-25 20:10:48] Epoch 1 | Step 150 | Loss: 0.4388 | LM: 0.4282 | LB: 1.1653 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.481/SR1: 0.460 | LR: 3.73e-05 |
| [2026-04-25 20:10:55] Epoch 1 | Step 160 | Loss: 0.4315 | LM: 0.4208 | LB: 1.1661 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.481/SR1: 0.460 | LR: 3.91e-05 |
| [2026-04-25 20:11:02] Epoch 1 | Step 170 | Loss: 0.4291 | LM: 0.4253 | LB: 1.1639 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.480/SR1: 0.459 | LR: 4.10e-05 |
| [2026-04-25 20:11:09] Epoch 1 | Step 180 | Loss: 0.4218 | LM: 0.4186 | LB: 1.1631 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.479/SR1: 0.458 | LR: 4.28e-05 |
| [2026-04-25 20:11:16] Epoch 1 | Step 190 | Loss: 0.4183 | LM: 0.4144 | LB: 1.1621 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.478/SR1: 0.457 | LR: 4.46e-05 |
| [2026-04-25 20:11:23] Epoch 1 | Step 200 | Loss: 0.4145 | LM: 0.4155 | LB: 1.1614 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.478/SR1: 0.457 | LR: 4.64e-05 |
| [2026-04-25 20:11:30] Epoch 1 | Step 210 | Loss: 0.4124 | LM: 0.4163 | LB: 1.1614 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.479/SR1: 0.457 | LR: 4.83e-05 |
| [2026-04-25 20:11:37] Epoch 1 | Step 220 | Loss: 0.4084 | LM: 0.4153 | LB: 1.1621 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.479/SR1: 0.458 | LR: 5.01e-05 |
| [2026-04-25 20:11:45] Epoch 1 | Step 230 | Loss: 0.4030 | LM: 0.4072 | LB: 1.1625 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.480/SR1: 0.458 | LR: 5.19e-05 |
| [2026-04-25 20:11:52] Epoch 1 | Step 240 | Loss: 0.3996 | LM: 0.4011 | LB: 1.1622 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.480/SR1: 0.458 | LR: 5.37e-05 |
| [2026-04-25 20:11:59] Epoch 1 | Step 250 | Loss: 0.3963 | LM: 0.3946 | LB: 1.1623 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.480/SR1: 0.458 | LR: 5.55e-05 |
| [2026-04-25 20:12:06] Epoch 1 | Step 260 | Loss: 0.3946 | LM: 0.3958 | LB: 1.1625 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.354 | HR1: 0.481/SR1: 0.459 | LR: 5.74e-05 |
| [2026-04-25 20:12:13] Epoch 1 | Step 270 | Loss: 0.3909 | LM: 0.3947 | LB: 1.1617 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.354 | HR1: 0.480/SR1: 0.458 | LR: 5.92e-05 |
| [2026-04-25 20:12:20] Epoch 1 | Step 280 | Loss: 0.3871 | LM: 0.3950 | LB: 1.1619 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.354 | HR1: 0.480/SR1: 0.458 | LR: 6.10e-05 |
| [2026-04-25 20:12:27] Epoch 1 | Step 290 | Loss: 0.3842 | LM: 0.3933 | LB: 1.1620 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.480/SR1: 0.458 | LR: 6.28e-05 |
| [2026-04-25 20:12:35] Epoch 1 | Step 300 | Loss: 0.3825 | LM: 0.3919 | LB: 1.1625 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.480/SR1: 0.458 | LR: 6.47e-05 |
| [2026-04-25 20:12:42] Epoch 1 | Step 310 | Loss: 0.3802 | LM: 0.3890 | LB: 1.1620 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.479/SR1: 0.457 | LR: 6.65e-05 |
| [2026-04-25 20:12:49] Epoch 1 | Step 320 | Loss: 0.3769 | LM: 0.3854 | LB: 1.1622 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.479/SR1: 0.457 | LR: 6.83e-05 |
| [2026-04-25 20:12:56] Epoch 1 | Step 330 | Loss: 0.3743 | LM: 0.3833 | LB: 1.1622 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.479/SR1: 0.457 | LR: 7.01e-05 |
| [2026-04-25 20:13:03] Epoch 1 | Step 340 | Loss: 0.3716 | LM: 0.3805 | LB: 1.1623 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.479/SR1: 0.457 | LR: 7.19e-05 |
| [2026-04-25 20:13:10] Epoch 1 | Step 350 | Loss: 0.3699 | LM: 0.3788 | LB: 1.1624 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.480/SR1: 0.457 | LR: 7.38e-05 |
| [2026-04-25 20:13:17] Epoch 1 | Step 360 | Loss: 0.3668 | LM: 0.3751 | LB: 1.1620 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.479/SR1: 0.457 | LR: 7.56e-05 |
| [2026-04-25 20:13:25] Epoch 1 | Step 370 | Loss: 0.3640 | LM: 0.3730 | LB: 1.1615 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.479/SR1: 0.457 | LR: 7.74e-05 |
| [2026-04-25 20:13:32] Epoch 1 | Step 380 | Loss: 0.3615 | LM: 0.3715 | LB: 1.1614 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.479/SR1: 0.457 | LR: 7.92e-05 |
| [2026-04-25 20:13:39] Epoch 1 | Step 390 | Loss: 0.3600 | LM: 0.3693 | LB: 1.1617 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.479/SR1: 0.457 | LR: 8.11e-05 |
| [2026-04-25 20:13:46] Epoch 1 | Step 400 | Loss: 0.3588 | LM: 0.3682 | LB: 1.1610 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.479/SR1: 0.456 | LR: 8.29e-05 |
| [2026-04-25 20:13:53] Epoch 1 | Step 410 | Loss: 0.3572 | LM: 0.3675 | LB: 1.1608 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.478/SR1: 0.456 | LR: 8.47e-05 |
| [2026-04-25 20:14:00] Epoch 1 | Step 420 | Loss: 0.3553 | LM: 0.3662 | LB: 1.1609 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.479/SR1: 0.456 | LR: 8.65e-05 |
| [2026-04-25 20:14:08] Epoch 1 | Step 430 | Loss: 0.3547 | LM: 0.3639 | LB: 1.1606 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.478/SR1: 0.456 | LR: 8.83e-05 |
| [2026-04-25 20:14:15] Epoch 1 | Step 440 | Loss: 0.3523 | LM: 0.3617 | LB: 1.1603 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.478/SR1: 0.456 | LR: 9.02e-05 |
| [2026-04-25 20:14:22] Epoch 1 | Step 450 | Loss: 0.3513 | LM: 0.3607 | LB: 1.1599 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.478/SR1: 0.455 | LR: 9.20e-05 |
| [2026-04-25 20:14:29] Epoch 1 | Step 460 | Loss: 0.3502 | LM: 0.3589 | LB: 1.1599 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.478/SR1: 0.455 | LR: 9.38e-05 |
| [2026-04-25 20:14:36] Epoch 1 | Step 470 | Loss: 0.3484 | LM: 0.3569 | LB: 1.1596 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.477/SR1: 0.455 | LR: 9.56e-05 |
| [2026-04-25 20:14:43] Epoch 1 | Step 480 | Loss: 0.3471 | LM: 0.3548 | LB: 1.1596 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.477/SR1: 0.455 | LR: 9.74e-05 |
| [2026-04-25 20:14:50] Epoch 1 | Step 490 | Loss: 0.3457 | LM: 0.3528 | LB: 1.1595 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.477/SR1: 0.455 | LR: 9.93e-05 |
| [2026-04-25 20:14:57] Epoch 1 | Step 500 | Loss: 0.3445 | LM: 0.3500 | LB: 1.1592 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.477/SR1: 0.455 | LR: 1.00e-04 |
| [2026-04-25 20:15:05] Epoch 1 | Step 510 | Loss: 0.3429 | LM: 0.3469 | LB: 1.1590 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.477/SR1: 0.454 | LR: 1.00e-04 |
| [2026-04-25 20:15:12] Epoch 1 | Step 520 | Loss: 0.3425 | LM: 0.3470 | LB: 1.1585 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.476/SR1: 0.454 | LR: 1.00e-04 |
| [2026-04-25 20:15:19] Epoch 1 | Step 530 | Loss: 0.3415 | LM: 0.3463 | LB: 1.1581 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.476/SR1: 0.454 | LR: 1.00e-04 |
| [2026-04-25 20:15:26] Epoch 1 | Step 540 | Loss: 0.3401 | LM: 0.3454 | LB: 1.1577 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.476/SR1: 0.454 | LR: 1.00e-04 |
| [2026-04-25 20:15:33] Epoch 1 | Step 550 | Loss: 0.3386 | LM: 0.3437 | LB: 1.1574 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.476/SR1: 0.453 | LR: 1.00e-04 |
| [2026-04-25 20:15:40] Epoch 1 | Step 560 | Loss: 0.3378 | LM: 0.3413 | LB: 1.1570 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.453 | LR: 1.00e-04 |
| [2026-04-25 20:15:47] Epoch 1 | Step 570 | Loss: 0.3370 | LM: 0.3405 | LB: 1.1570 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.453 | LR: 1.00e-04 |
| [2026-04-25 20:15:55] Epoch 1 | Step 580 | Loss: 0.3362 | LM: 0.3395 | LB: 1.1566 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.453 | LR: 1.00e-04 |
| [2026-04-25 20:16:02] Epoch 1 | Step 590 | Loss: 0.3357 | LM: 0.3389 | LB: 1.1562 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.452 | LR: 1.00e-04 |
| [2026-04-25 20:16:09] Epoch 1 | Step 600 | Loss: 0.3346 | LM: 0.3370 | LB: 1.1556 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.452 | LR: 1.00e-04 |
| [2026-04-25 20:16:16] Epoch 1 | Step 610 | Loss: 0.3346 | LM: 0.3358 | LB: 1.1554 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.452 | LR: 1.00e-04 |
| [2026-04-25 20:16:23] Epoch 1 | Step 620 | Loss: 0.3342 | LM: 0.3353 | LB: 1.1552 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.452 | LR: 1.00e-04 |
| [2026-04-25 20:16:30] Epoch 1 | Step 630 | Loss: 0.3335 | LM: 0.3354 | LB: 1.1550 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.451 | LR: 1.00e-04 |
| [2026-04-25 20:16:38] Epoch 1 | Step 640 | Loss: 0.3332 | LM: 0.3342 | LB: 1.1547 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.473/SR1: 0.451 | LR: 1.00e-04 |
| [2026-04-25 20:16:45] Epoch 1 | Step 650 | Loss: 0.3324 | LM: 0.3333 | LB: 1.1543 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.473/SR1: 0.451 | LR: 1.00e-04 |
| [2026-04-25 20:16:52] Epoch 1 | Step 660 | Loss: 0.3323 | LM: 0.3324 | LB: 1.1540 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.473/SR1: 0.450 | LR: 1.00e-04 |
| [2026-04-25 20:16:59] Epoch 1 | Step 670 | Loss: 0.3316 | LM: 0.3314 | LB: 1.1538 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.472/SR1: 0.450 | LR: 1.00e-04 |
| [2026-04-25 20:17:06] Epoch 1 | Step 680 | Loss: 0.3311 | LM: 0.3315 | LB: 1.1539 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.473/SR1: 0.450 | LR: 1.00e-04 |
| [2026-04-25 20:17:13] Epoch 1 | Step 690 | Loss: 0.3306 | LM: 0.3318 | LB: 1.1534 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.472/SR1: 0.450 | LR: 1.00e-04 |
| [2026-04-25 20:17:20] Epoch 1 | Step 700 | Loss: 0.3306 | LM: 0.3333 | LB: 1.1531 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.472/SR1: 0.450 | LR: 1.00e-04 |
| [2026-04-25 20:17:28] Epoch 1 | Step 710 | Loss: 0.3297 | LM: 0.3334 | LB: 1.1529 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.472/SR1: 0.449 | LR: 1.00e-04 |
| [2026-04-25 20:17:35] Epoch 1 | Step 720 | Loss: 0.3292 | LM: 0.3331 | LB: 1.1525 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.471/SR1: 0.449 | LR: 1.00e-04 |
| [2026-04-25 20:17:42] Epoch 1 | Step 730 | Loss: 0.3288 | LM: 0.3325 | LB: 1.1523 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.471/SR1: 0.449 | LR: 1.00e-04 |
| [2026-04-25 20:17:49] Epoch 1 | Step 740 | Loss: 0.3282 | LM: 0.3319 | LB: 1.1520 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.471/SR1: 0.449 | LR: 1.00e-04 |
| [2026-04-25 20:17:56] Epoch 1 | Step 750 | Loss: 0.3275 | LM: 0.3309 | LB: 1.1514 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.470/SR1: 0.448 | LR: 1.00e-04 |
| [2026-04-25 20:18:03] Epoch 1 | Step 760 | Loss: 0.3277 | LM: 0.3302 | LB: 1.1511 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.470/SR1: 0.448 | LR: 1.00e-04 |
| [2026-04-25 20:18:10] Epoch 1 | Step 770 | Loss: 0.3278 | LM: 0.3300 | LB: 1.1509 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.470/SR1: 0.448 | LR: 1.00e-04 |
| [2026-04-25 20:18:18] Epoch 1 | Step 780 | Loss: 0.3272 | LM: 0.3291 | LB: 1.1505 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.470/SR1: 0.447 | LR: 1.00e-04 |
| [2026-04-25 20:18:25] Epoch 1 | Step 790 | Loss: 0.3266 | LM: 0.3285 | LB: 1.1503 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.470/SR1: 0.447 | LR: 1.00e-04 |
| [2026-04-25 20:18:32] Epoch 1 | Step 800 | Loss: 0.3257 | LM: 0.3270 | LB: 1.1500 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.470/SR1: 0.447 | LR: 1.00e-04 |
| [2026-04-25 20:18:39] Epoch 1 | Step 810 | Loss: 0.3254 | LM: 0.3271 | LB: 1.1499 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.469/SR1: 0.447 | LR: 1.00e-04 |
| [2026-04-25 20:18:46] Epoch 1 | Step 820 | Loss: 0.3250 | LM: 0.3265 | LB: 1.1497 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.469/SR1: 0.447 | LR: 1.00e-04 |
| [2026-04-25 20:18:53] Epoch 1 | Step 830 | Loss: 0.3249 | LM: 0.3268 | LB: 1.1494 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.469/SR1: 0.447 | LR: 1.00e-04 |
| [2026-04-25 20:19:00] Epoch 1 | Step 840 | Loss: 0.3246 | LM: 0.3259 | LB: 1.1493 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.469/SR1: 0.446 | LR: 1.00e-04 |
| [2026-04-25 20:19:08] Epoch 1 | Step 850 | Loss: 0.3239 | LM: 0.3254 | LB: 1.1491 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.469/SR1: 0.446 | LR: 1.00e-04 |
| [2026-04-25 20:19:15] Epoch 1 | Step 860 | Loss: 0.3236 | LM: 0.3242 | LB: 1.1489 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.469/SR1: 0.446 | LR: 1.00e-04 |
| [2026-04-25 20:19:22] Epoch 1 | Step 870 | Loss: 0.3237 | LM: 0.3239 | LB: 1.1487 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.468/SR1: 0.446 | LR: 1.00e-04 |
| [2026-04-25 20:19:29] Epoch 1 | Step 880 | Loss: 0.3235 | LM: 0.3239 | LB: 1.1486 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.468/SR1: 0.446 | LR: 1.00e-04 |
| [2026-04-25 20:19:36] Epoch 1 | Step 890 | Loss: 0.3232 | LM: 0.3233 | LB: 1.1484 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.468/SR1: 0.445 | LR: 1.00e-04 |
| [2026-04-25 20:19:43] Epoch 1 | Step 900 | Loss: 0.3230 | LM: 0.3227 | LB: 1.1485 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.468/SR1: 0.445 | LR: 1.00e-04 |
| [2026-04-25 20:19:50] Epoch 1 | Step 910 | Loss: 0.3230 | LM: 0.3221 | LB: 1.1481 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.468/SR1: 0.445 | LR: 1.00e-04 |
| [2026-04-25 20:19:58] Epoch 1 | Step 920 | Loss: 0.3232 | LM: 0.3221 | LB: 1.1480 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.468/SR1: 0.445 | LR: 1.00e-04 |
| [2026-04-25 20:20:05] Epoch 1 | Step 930 | Loss: 0.3229 | LM: 0.3213 | LB: 1.1477 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.467/SR1: 0.445 | LR: 1.00e-04 |
| [2026-04-25 20:20:12] Epoch 1 | Step 940 | Loss: 0.3229 | LM: 0.3209 | LB: 1.1475 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.467/SR1: 0.444 | LR: 1.00e-04 |
| [2026-04-25 20:20:19] Epoch 1 | Step 950 | Loss: 0.3222 | LM: 0.3206 | LB: 1.1474 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.467/SR1: 0.444 | LR: 1.00e-04 |
| [2026-04-25 20:20:26] Epoch 1 | Step 960 | Loss: 0.3216 | LM: 0.3208 | LB: 1.1472 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.467/SR1: 0.444 | LR: 1.00e-04 |
| [2026-04-25 20:20:33] Epoch 1 | Step 970 | Loss: 0.3213 | LM: 0.3211 | LB: 1.1469 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.467/SR1: 0.444 | LR: 1.00e-04 |
| [2026-04-25 20:20:41] Epoch 1 | Step 980 | Loss: 0.3207 | LM: 0.3198 | LB: 1.1468 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.466/SR1: 0.444 | LR: 1.00e-04 |
| [2026-04-25 20:20:48] Epoch 1 | Step 990 | Loss: 0.3201 | LM: 0.3195 | LB: 1.1466 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.466/SR1: 0.443 | LR: 1.00e-04 |
| [2026-04-25 20:20:55] Epoch 1 | Step 1000 | Loss: 0.3197 | LM: 0.3186 | LB: 1.1462 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.466/SR1: 0.443 | LR: 1.00e-04 |
| [2026-04-25 20:21:02] Epoch 1 | Step 1010 | Loss: 0.3198 | LM: 0.3188 | LB: 1.1460 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.466/SR1: 0.443 | LR: 1.00e-04 |
| [2026-04-25 20:21:09] Epoch 1 | Step 1020 | Loss: 0.3197 | LM: 0.3190 | LB: 1.1458 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.466/SR1: 0.443 | LR: 1.00e-04 |
| [2026-04-25 20:21:16] Epoch 1 | Step 1030 | Loss: 0.3196 | LM: 0.3189 | LB: 1.1455 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.465/SR1: 0.443 | LR: 1.00e-04 |
| [2026-04-25 20:21:23] Epoch 1 | Step 1040 | Loss: 0.3190 | LM: 0.3182 | LB: 1.1453 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.465/SR1: 0.442 | LR: 1.00e-04 |
| [2026-04-25 20:21:30] Epoch 1 | Step 1050 | Loss: 0.3186 | LM: 0.3178 | LB: 1.1451 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.465/SR1: 0.442 | LR: 1.00e-04 |
| [2026-04-25 20:21:37] Epoch 1 | Step 1060 | Loss: 0.3178 | LM: 0.3168 | LB: 1.1450 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.465/SR1: 0.442 | LR: 1.00e-04 |
| [2026-04-25 20:21:45] Epoch 1 | Step 1070 | Loss: 0.3175 | LM: 0.3160 | LB: 1.1448 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.465/SR1: 0.442 | LR: 1.00e-04 |
| [2026-04-25 20:21:52] Epoch 1 | Step 1080 | Loss: 0.3177 | LM: 0.3150 | LB: 1.1448 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.465/SR1: 0.442 | LR: 1.00e-04 |
| [2026-04-25 20:21:59] Epoch 1 | Step 1090 | Loss: 0.3181 | LM: 0.3155 | LB: 1.1447 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.465/SR1: 0.442 | LR: 1.00e-04 |
| [2026-04-25 20:22:06] Epoch 1 | Step 1100 | Loss: 0.3178 | LM: 0.3155 | LB: 1.1446 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.465/SR1: 0.442 | LR: 1.00e-04 |
| [2026-04-25 20:22:13] Epoch 1 | Step 1110 | Loss: 0.3178 | LM: 0.3148 | LB: 1.1445 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.464/SR1: 0.441 | LR: 1.00e-04 |
| [2026-04-25 20:22:20] Epoch 1 | Step 1120 | Loss: 0.3179 | LM: 0.3146 | LB: 1.1444 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.464/SR1: 0.441 | LR: 1.00e-04 |
| [2026-04-25 20:22:27] Epoch 1 | Step 1130 | Loss: 0.3180 | LM: 0.3139 | LB: 1.1441 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.464/SR1: 0.441 | LR: 1.00e-04 |
| [2026-04-25 20:22:34] Epoch 1 | Step 1140 | Loss: 0.3178 | LM: 0.3136 | LB: 1.1438 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.464/SR1: 0.441 | LR: 1.00e-04 |
| [2026-04-25 20:22:42] Epoch 1 | Step 1150 | Loss: 0.3173 | LM: 0.3129 | LB: 1.1437 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.464/SR1: 0.441 | LR: 1.00e-04 |
| [2026-04-25 20:22:49] Epoch 1 | Step 1160 | Loss: 0.3173 | LM: 0.3131 | LB: 1.1434 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.463/SR1: 0.440 | LR: 1.00e-04 |
| [2026-04-25 20:22:56] Epoch 1 | Step 1170 | Loss: 0.3174 | LM: 0.3127 | LB: 1.1432 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.463/SR1: 0.440 | LR: 1.00e-04 |
| [2026-04-25 20:23:03] Epoch 1 | Step 1180 | Loss: 0.3173 | LM: 0.3127 | LB: 1.1429 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.463/SR1: 0.440 | LR: 1.00e-04 |
| [2026-04-25 20:23:10] Epoch 1 | Step 1190 | Loss: 0.3172 | LM: 0.3126 | LB: 1.1428 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.463/SR1: 0.440 | LR: 1.00e-04 |
| [2026-04-25 20:23:17] Epoch 1 | Step 1200 | Loss: 0.3168 | LM: 0.3117 | LB: 1.1426 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.463/SR1: 0.440 | LR: 1.00e-04 |
| [2026-04-25 20:23:24] Epoch 1 | Step 1210 | Loss: 0.3165 | LM: 0.3116 | LB: 1.1425 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.463/SR1: 0.439 | LR: 1.00e-04 |
| [2026-04-25 20:23:32] Epoch 1 | Step 1220 | Loss: 0.3159 | LM: 0.3107 | LB: 1.1424 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.463/SR1: 0.439 | LR: 1.00e-04 |
| [2026-04-25 20:23:39] Epoch 1 | Step 1230 | Loss: 0.3159 | LM: 0.3110 | LB: 1.1423 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.463/SR1: 0.439 | LR: 1.00e-04 |
| [2026-04-25 20:23:46] Epoch 1 | Step 1240 | Loss: 0.3159 | LM: 0.3111 | LB: 1.1421 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.462/SR1: 0.439 | LR: 1.00e-04 |
| [2026-04-25 20:23:53] Epoch 1 | Step 1250 | Loss: 0.3156 | LM: 0.3112 | LB: 1.1420 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.462/SR1: 0.439 | LR: 1.00e-04 |
| [2026-04-25 20:24:00] Epoch 1 | Step 1260 | Loss: 0.3152 | LM: 0.3111 | LB: 1.1418 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.462/SR1: 0.439 | LR: 1.00e-04 |
| [2026-04-25 20:24:07] Epoch 1 | Step 1270 | Loss: 0.3148 | LM: 0.3107 | LB: 1.1418 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.462/SR1: 0.439 | LR: 1.00e-04 |
| [2026-04-25 20:24:14] Epoch 1 | Step 1280 | Loss: 0.3147 | LM: 0.3103 | LB: 1.1416 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.462/SR1: 0.439 | LR: 1.00e-04 |
| [2026-04-25 20:24:22] Epoch 1 | Step 1290 | Loss: 0.3145 | LM: 0.3105 | LB: 1.1415 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.462/SR1: 0.438 | LR: 1.00e-04 |
| [2026-04-25 20:24:29] Epoch 1 | Step 1300 | Loss: 0.3142 | LM: 0.3103 | LB: 1.1415 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.462/SR1: 0.438 | LR: 1.00e-04 |
| [2026-04-25 20:24:36] Epoch 1 | Step 1310 | Loss: 0.3139 | LM: 0.3097 | LB: 1.1412 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.462/SR1: 0.438 | LR: 1.00e-04 |
| [2026-04-25 20:24:43] Epoch 1 | Step 1320 | Loss: 0.3139 | LM: 0.3092 | LB: 1.1410 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.462/SR1: 0.438 | LR: 1.00e-04 |
| [2026-04-25 20:24:50] Epoch 1 | Step 1330 | Loss: 0.3136 | LM: 0.3089 | LB: 1.1408 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.461/SR1: 0.438 | LR: 1.00e-04 |
| [2026-04-25 20:24:57] Epoch 1 | Step 1340 | Loss: 0.3136 | LM: 0.3090 | LB: 1.1406 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.461/SR1: 0.438 | LR: 1.00e-04 |
| [2026-04-25 20:25:04] Epoch 1 | Step 1350 | Loss: 0.3136 | LM: 0.3093 | LB: 1.1408 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.461/SR1: 0.438 | LR: 1.00e-04 |
| [2026-04-25 20:25:11] Epoch 1 | Step 1360 | Loss: 0.3135 | LM: 0.3085 | LB: 1.1408 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.461/SR1: 0.438 | LR: 1.00e-04 |
| [2026-04-25 20:25:18] Epoch 1 | Step 1370 | Loss: 0.3133 | LM: 0.3082 | LB: 1.1406 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.461/SR1: 0.438 | LR: 1.00e-04 |
| [2026-04-25 20:25:26] Epoch 1 | Step 1380 | Loss: 0.3135 | LM: 0.3080 | LB: 1.1404 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.461/SR1: 0.437 | LR: 1.00e-04 |
| [2026-04-25 20:25:33] Epoch 1 | Step 1390 | Loss: 0.3139 | LM: 0.3083 | LB: 1.1401 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.461/SR1: 0.437 | LR: 1.00e-04 |
| [2026-04-25 20:25:40] Epoch 1 | Step 1400 | Loss: 0.3138 | LM: 0.3080 | LB: 1.1398 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.460/SR1: 0.437 | LR: 1.00e-04 |
| [2026-04-25 20:25:47] Epoch 1 | Step 1410 | Loss: 0.3134 | LM: 0.3069 | LB: 1.1397 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.460/SR1: 0.437 | LR: 1.00e-04 |
| [2026-04-25 20:25:54] Epoch 1 | Step 1420 | Loss: 0.3132 | LM: 0.3068 | LB: 1.1397 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.460/SR1: 0.437 | LR: 1.00e-04 |
| [2026-04-25 20:26:02] Epoch 1 | Step 1430 | Loss: 0.3130 | LM: 0.3067 | LB: 1.1396 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.460/SR1: 0.437 | LR: 1.00e-04 |
| [2026-04-25 20:26:09] Epoch 1 | Step 1440 | Loss: 0.3127 | LM: 0.3064 | LB: 1.1395 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.460/SR1: 0.436 | LR: 1.00e-04 |
| [2026-04-25 20:26:16] Epoch 1 | Step 1450 | Loss: 0.3126 | LM: 0.3060 | LB: 1.1393 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.460/SR1: 0.436 | LR: 1.00e-04 |
| [2026-04-25 20:26:23] Epoch 1 | Step 1460 | Loss: 0.3122 | LM: 0.3055 | LB: 1.1392 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.460/SR1: 0.436 | LR: 1.00e-04 |
| [2026-04-25 20:26:30] Epoch 1 | Step 1470 | Loss: 0.3122 | LM: 0.3058 | LB: 1.1392 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.460/SR1: 0.436 | LR: 1.00e-04 |
| [2026-04-25 20:26:37] Epoch 1 | Step 1480 | Loss: 0.3120 | LM: 0.3054 | LB: 1.1390 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.460/SR1: 0.436 | LR: 1.00e-04 |
| [2026-04-25 20:26:44] Epoch 1 | Step 1490 | Loss: 0.3120 | LM: 0.3053 | LB: 1.1390 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.460/SR1: 0.436 | LR: 1.00e-04 |
| [2026-04-25 20:26:51] Epoch 1 | Step 1500 | Loss: 0.3118 | LM: 0.3050 | LB: 1.1388 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.459/SR1: 0.436 | LR: 1.00e-04 |
| [2026-04-25 20:26:59] Epoch 1 | Step 1510 | Loss: 0.3117 | LM: 0.3051 | LB: 1.1388 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.459/SR1: 0.436 | LR: 1.00e-04 |
| [2026-04-25 20:27:06] Epoch 1 | Step 1520 | Loss: 0.3116 | LM: 0.3048 | LB: 1.1388 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.459/SR1: 0.436 | LR: 1.00e-04 |
| [2026-04-25 20:27:13] Epoch 1 | Step 1530 | Loss: 0.3114 | LM: 0.3046 | LB: 1.1386 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.459/SR1: 0.435 | LR: 1.00e-04 |
| [2026-04-25 20:27:20] Epoch 1 | Step 1540 | Loss: 0.3115 | LM: 0.3049 | LB: 1.1386 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.459/SR1: 0.435 | LR: 1.00e-04 |
| [2026-04-25 20:27:27] Epoch 1 | Step 1550 | Loss: 0.3114 | LM: 0.3046 | LB: 1.1385 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.459/SR1: 0.435 | LR: 1.00e-04 |
| [2026-04-25 20:27:34] Epoch 1 | Step 1560 | Loss: 0.3112 | LM: 0.3045 | LB: 1.1384 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.459/SR1: 0.435 | LR: 1.00e-04 |
| [2026-04-25 20:27:41] Epoch 1 | Step 1570 | Loss: 0.3113 | LM: 0.3046 | LB: 1.1383 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.459/SR1: 0.435 | LR: 1.00e-04 |
| [2026-04-25 20:27:48] Epoch 1 | Step 1580 | Loss: 0.3112 | LM: 0.3049 | LB: 1.1382 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.459/SR1: 0.435 | LR: 1.00e-04 |
| [2026-04-25 20:27:55] Epoch 1 | Step 1590 | Loss: 0.3112 | LM: 0.3055 | LB: 1.1383 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.459/SR1: 0.435 | LR: 1.00e-04 |
| [2026-04-25 20:28:02] Epoch 1 | Step 1600 | Loss: 0.3111 | LM: 0.3052 | LB: 1.1382 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 1.00e-04 |
| [2026-04-25 20:28:10] Epoch 1 | Step 1610 | Loss: 0.3107 | LM: 0.3047 | LB: 1.1382 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.458/SR1: 0.435 | LR: 1.00e-04 |
| [2026-04-25 20:28:17] Epoch 1 | Step 1620 | Loss: 0.3104 | LM: 0.3044 | LB: 1.1380 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.458/SR1: 0.435 | LR: 1.00e-04 |
| [2026-04-25 20:28:24] Epoch 1 | Step 1630 | Loss: 0.3104 | LM: 0.3043 | LB: 1.1379 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 1.00e-04 |
| [2026-04-25 20:28:31] Epoch 1 | Step 1640 | Loss: 0.3102 | LM: 0.3043 | LB: 1.1376 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.458/SR1: 0.434 | LR: 1.00e-04 |
| [2026-04-25 20:28:38] Epoch 1 | Step 1650 | Loss: 0.3100 | LM: 0.3044 | LB: 1.1376 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 1.00e-04 |
| [2026-04-25 20:28:45] Epoch 1 | Step 1660 | Loss: 0.3097 | LM: 0.3036 | LB: 1.1375 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.458/SR1: 0.434 | LR: 1.00e-04 |
| [2026-04-25 20:28:52] Epoch 1 | Step 1670 | Loss: 0.3098 | LM: 0.3036 | LB: 1.1374 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.458/SR1: 0.434 | LR: 1.00e-04 |
| [2026-04-25 20:28:59] Epoch 1 | Step 1680 | Loss: 0.3099 | LM: 0.3033 | LB: 1.1374 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.458/SR1: 0.434 | LR: 1.00e-04 |
| [2026-04-25 20:29:06] Epoch 1 | Step 1690 | Loss: 0.3097 | LM: 0.3031 | LB: 1.1373 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 1.00e-04 |
| [2026-04-25 20:29:14] Epoch 1 | Step 1700 | Loss: 0.3093 | LM: 0.3025 | LB: 1.1372 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 1.00e-04 |
| [2026-04-25 20:29:21] Epoch 1 | Step 1710 | Loss: 0.3092 | LM: 0.3018 | LB: 1.1371 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.458/SR1: 0.434 | LR: 1.00e-04 |
| [2026-04-25 20:29:28] Epoch 1 | Step 1720 | Loss: 0.3091 | LM: 0.3019 | LB: 1.1369 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 1.00e-04 |
| [2026-04-25 20:29:35] Epoch 1 | Step 1730 | Loss: 0.3089 | LM: 0.3019 | LB: 1.1368 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 1.00e-04 |
| [2026-04-25 20:29:42] Epoch 1 | Step 1740 | Loss: 0.3089 | LM: 0.3021 | LB: 1.1367 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 1.00e-04 |
| [2026-04-25 20:29:49] Epoch 1 | Step 1750 | Loss: 0.3091 | LM: 0.3023 | LB: 1.1366 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 1.00e-04 |
| [2026-04-25 20:29:56] Epoch 1 | Step 1760 | Loss: 0.3090 | LM: 0.3022 | LB: 1.1364 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 1.00e-04 |
| [2026-04-25 20:30:03] Epoch 1 | Step 1770 | Loss: 0.3090 | LM: 0.3023 | LB: 1.1363 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 1.00e-04 |
| [2026-04-25 20:30:11] Epoch 1 | Step 1780 | Loss: 0.3089 | LM: 0.3021 | LB: 1.1362 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 1.00e-04 |
| [2026-04-25 20:30:18] Epoch 1 | Step 1790 | Loss: 0.3090 | LM: 0.3018 | LB: 1.1361 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 1.00e-04 |
| [2026-04-25 20:30:25] Epoch 1 | Step 1800 | Loss: 0.3089 | LM: 0.3017 | LB: 1.1360 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.457/SR1: 0.432 | LR: 1.00e-04 |
| [2026-04-25 20:30:32] Epoch 1 | Step 1810 | Loss: 0.3088 | LM: 0.3017 | LB: 1.1359 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 1.00e-04 |
| [2026-04-25 20:30:39] Epoch 1 | Step 1820 | Loss: 0.3089 | LM: 0.3016 | LB: 1.1358 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.456/SR1: 0.432 | LR: 1.00e-04 |
| [2026-04-25 20:30:46] Epoch 1 | Step 1830 | Loss: 0.3089 | LM: 0.3023 | LB: 1.1357 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 1.00e-04 |
| [2026-04-25 20:30:53] Epoch 1 | Step 1840 | Loss: 0.3088 | LM: 0.3024 | LB: 1.1356 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 1.00e-04 |
| [2026-04-25 20:31:00] Epoch 1 | Step 1850 | Loss: 0.3086 | LM: 0.3022 | LB: 1.1355 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 1.00e-04 |
| [2026-04-25 20:31:07] Epoch 1 | Step 1860 | Loss: 0.3087 | LM: 0.3018 | LB: 1.1354 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 1.00e-04 |
| [2026-04-25 20:31:14] Epoch 1 | Step 1870 | Loss: 0.3085 | LM: 0.3014 | LB: 1.1354 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 1.00e-04 |
| [2026-04-25 20:31:22] Epoch 1 | Step 1880 | Loss: 0.3084 | LM: 0.3015 | LB: 1.1352 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 1.00e-04 |
| [2026-04-25 20:31:29] Epoch 1 | Step 1890 | Loss: 0.3084 | LM: 0.3012 | LB: 1.1350 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 1.00e-04 |
| [2026-04-25 20:31:36] Epoch 1 | Step 1900 | Loss: 0.3083 | LM: 0.3013 | LB: 1.1348 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 1.00e-04 |
| [2026-04-25 20:31:43] Epoch 1 | Step 1910 | Loss: 0.3083 | LM: 0.3013 | LB: 1.1348 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 1.00e-04 |
| [2026-04-25 20:31:50] Epoch 1 | Step 1920 | Loss: 0.3083 | LM: 0.3010 | LB: 1.1347 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 1.00e-04 |
| [2026-04-25 20:31:57] Epoch 1 | Step 1930 | Loss: 0.3082 | LM: 0.3009 | LB: 1.1346 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.455/SR1: 0.431 | LR: 1.00e-04 |
| [2026-04-25 20:32:04] Epoch 1 | Step 1940 | Loss: 0.3081 | LM: 0.3010 | LB: 1.1346 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.455/SR1: 0.431 | LR: 1.00e-04 |
| [2026-04-25 20:32:11] Epoch 1 | Step 1950 | Loss: 0.3080 | LM: 0.3010 | LB: 1.1344 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.455/SR1: 0.431 | LR: 1.00e-04 |
| [2026-04-25 20:32:18] Epoch 1 | Step 1960 | Loss: 0.3080 | LM: 0.3012 | LB: 1.1343 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.455/SR1: 0.431 | LR: 1.00e-04 |
| [2026-04-25 20:32:25] Epoch 1 | Step 1970 | Loss: 0.3081 | LM: 0.3015 | LB: 1.1342 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.455/SR1: 0.431 | LR: 1.00e-04 |
| [2026-04-25 20:32:32] Epoch 1 | Step 1980 | Loss: 0.3080 | LM: 0.3014 | LB: 1.1342 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 1.00e-04 |
| [2026-04-25 20:32:39] Epoch 1 | Step 1990 | Loss: 0.3080 | LM: 0.3015 | LB: 1.1341 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 1.00e-04 |
| [2026-04-25 20:32:46] Epoch 1 | Step 2000 | Loss: 0.3080 | LM: 0.3013 | LB: 1.1340 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 1.00e-04 |
| [2026-04-25 20:32:47] Validation | Batch 10/42 | Loss: 0.2826 | LM_LOSS: 0.2715 | LB_LOSS: 1.1078 |
| [2026-04-25 20:32:49] Validation | Batch 20/42 | Loss: 0.3051 | LM_LOSS: 0.2940 | LB_LOSS: 1.1106 |
| [2026-04-25 20:32:50] Validation | Batch 30/42 | Loss: 0.2964 | LM_LOSS: 0.2853 | LB_LOSS: 1.1074 |
| [2026-04-25 20:32:51] Validation | Batch 40/42 | Loss: 0.3008 | LM_LOSS: 0.2898 | LB_LOSS: 1.1064 |
| [2026-04-25 20:32:51] Validation | Batch 42/42 | Loss: 0.3003 | LM_LOSS: 0.2892 | LB_LOSS: 1.1066 |
| [2026-04-25 20:32:51] Validation | Loss: 0.3003 | LM_LOSS: 0.2892 | LB_LOSS: 1.1066 | PPL: 1.33 | Time: 4.80s |
| [2026-04-25 20:32:54] New best model saved! Val loss: 0.3003 |
| [2026-04-25 20:33:01] Epoch 1 | Step 2010 | Loss: 0.3081 | LM: 0.3015 | LB: 1.1340 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.430 | LR: 1.00e-04 |
| [2026-04-25 20:33:08] Epoch 1 | Step 2020 | Loss: 0.3079 | LM: 0.3015 | LB: 1.1338 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 1.00e-04 |
| [2026-04-25 20:33:15] Epoch 1 | Step 2030 | Loss: 0.3079 | LM: 0.3012 | LB: 1.1337 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 1.00e-04 |
| [2026-04-25 20:33:22] Epoch 1 | Step 2040 | Loss: 0.3078 | LM: 0.3009 | LB: 1.1336 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 1.00e-04 |
| [2026-04-25 20:33:29] Epoch 1 | Step 2050 | Loss: 0.3077 | LM: 0.3008 | LB: 1.1334 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 1.00e-04 |
| [2026-04-25 20:33:36] Epoch 1 | Step 2060 | Loss: 0.3077 | LM: 0.3010 | LB: 1.1334 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 1.00e-04 |
| [2026-04-25 20:33:43] Epoch 1 | Step 2070 | Loss: 0.3073 | LM: 0.3005 | LB: 1.1332 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 1.00e-04 |
| [2026-04-25 20:33:51] Epoch 1 | Step 2080 | Loss: 0.3071 | LM: 0.3003 | LB: 1.1331 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 1.00e-04 |
| [2026-04-25 20:33:58] Epoch 1 | Step 2090 | Loss: 0.3071 | LM: 0.3005 | LB: 1.1329 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.429 | LR: 1.00e-04 |
| [2026-04-25 20:34:05] Epoch 1 | Step 2100 | Loss: 0.3070 | LM: 0.3001 | LB: 1.1328 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 1.00e-04 |
| [2026-04-25 20:34:12] Epoch 1 | Step 2110 | Loss: 0.3070 | LM: 0.3000 | LB: 1.1326 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.453/SR1: 0.429 | LR: 1.00e-04 |
| [2026-04-25 20:34:19] Epoch 1 | Step 2120 | Loss: 0.3069 | LM: 0.3002 | LB: 1.1326 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 1.00e-04 |
| [2026-04-25 20:34:26] Epoch 1 | Step 2130 | Loss: 0.3068 | LM: 0.3004 | LB: 1.1325 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 1.00e-04 |
| [2026-04-25 20:34:33] Epoch 1 | Step 2140 | Loss: 0.3066 | LM: 0.3007 | LB: 1.1324 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 1.00e-04 |
| [2026-04-25 20:34:40] Epoch 1 | Step 2150 | Loss: 0.3066 | LM: 0.3006 | LB: 1.1324 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 1.00e-04 |
| [2026-04-25 20:34:47] Epoch 1 | Step 2160 | Loss: 0.3065 | LM: 0.3005 | LB: 1.1323 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 1.00e-04 |
| [2026-04-25 20:34:54] Epoch 1 | Step 2170 | Loss: 0.3065 | LM: 0.3003 | LB: 1.1322 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 1.00e-04 |
| [2026-04-25 20:35:01] Epoch 1 | Step 2180 | Loss: 0.3063 | LM: 0.3002 | LB: 1.1321 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 1.00e-04 |
| [2026-04-25 20:35:08] Epoch 1 | Step 2190 | Loss: 0.3062 | LM: 0.2999 | LB: 1.1320 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.453/SR1: 0.429 | LR: 1.00e-04 |
| [2026-04-25 20:35:15] Epoch 1 | Step 2200 | Loss: 0.3062 | LM: 0.3000 | LB: 1.1319 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 1.00e-04 |
| [2026-04-25 20:35:22] Epoch 1 | Step 2210 | Loss: 0.3062 | LM: 0.3001 | LB: 1.1318 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.428 | LR: 1.00e-04 |
| [2026-04-25 20:35:30] Epoch 1 | Step 2220 | Loss: 0.3063 | LM: 0.3002 | LB: 1.1317 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.428 | LR: 1.00e-04 |
| [2026-04-25 20:35:37] Epoch 1 | Step 2230 | Loss: 0.3064 | LM: 0.3002 | LB: 1.1316 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.428 | LR: 1.00e-04 |
| [2026-04-25 20:35:44] Epoch 1 | Step 2240 | Loss: 0.3066 | LM: 0.2999 | LB: 1.1315 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.428 | LR: 1.00e-04 |
| [2026-04-25 20:35:51] Epoch 1 | Step 2250 | Loss: 0.3066 | LM: 0.3000 | LB: 1.1314 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.428 | LR: 1.00e-04 |
| [2026-04-25 20:35:58] Epoch 1 | Step 2260 | Loss: 0.3065 | LM: 0.2996 | LB: 1.1313 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.428 | LR: 1.00e-04 |
| [2026-04-25 20:36:05] Epoch 1 | Step 2270 | Loss: 0.3065 | LM: 0.3000 | LB: 1.1312 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.428 | LR: 1.00e-04 |
| [2026-04-25 20:36:12] Epoch 1 | Step 2280 | Loss: 0.3064 | LM: 0.2998 | LB: 1.1311 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.428 | LR: 1.00e-04 |
| [2026-04-25 20:36:19] Epoch 1 | Step 2290 | Loss: 0.3067 | LM: 0.3000 | LB: 1.1309 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 1.00e-04 |
| [2026-04-25 20:36:26] Epoch 1 | Step 2300 | Loss: 0.3066 | LM: 0.2996 | LB: 1.1308 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.451/SR1: 0.427 | LR: 1.00e-04 |
| [2026-04-25 20:36:33] Epoch 1 | Step 2310 | Loss: 0.3065 | LM: 0.2995 | LB: 1.1307 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 1.00e-04 |
| [2026-04-25 20:36:40] Epoch 1 | Step 2320 | Loss: 0.3065 | LM: 0.2997 | LB: 1.1306 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 1.00e-04 |
| [2026-04-25 20:36:47] Epoch 1 | Step 2330 | Loss: 0.3065 | LM: 0.2997 | LB: 1.1305 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 1.00e-04 |
| [2026-04-25 20:36:55] Epoch 1 | Step 2340 | Loss: 0.3064 | LM: 0.2999 | LB: 1.1305 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 1.00e-04 |
| [2026-04-25 20:37:02] Epoch 1 | Step 2350 | Loss: 0.3063 | LM: 0.3001 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 1.00e-04 |
| [2026-04-25 20:37:09] Epoch 1 | Step 2360 | Loss: 0.3064 | LM: 0.3002 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 1.00e-04 |
| [2026-04-25 20:37:16] Epoch 1 | Step 2370 | Loss: 0.3063 | LM: 0.3000 | LB: 1.1302 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 1.00e-04 |
| [2026-04-25 20:37:23] Epoch 1 | Step 2380 | Loss: 0.3062 | LM: 0.2998 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.451/SR1: 0.427 | LR: 1.00e-04 |
| [2026-04-25 20:37:30] Epoch 1 | Step 2390 | Loss: 0.3062 | LM: 0.2997 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 1.00e-04 |
| [2026-04-25 20:37:37] Epoch 1 | Step 2400 | Loss: 0.3061 | LM: 0.2999 | LB: 1.1300 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.450/SR1: 0.427 | LR: 1.00e-04 |
| [2026-04-25 20:37:44] Epoch 1 | Step 2410 | Loss: 0.3061 | LM: 0.3001 | LB: 1.1299 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.450/SR1: 0.427 | LR: 1.00e-04 |
| [2026-04-25 20:37:51] Epoch 1 | Step 2420 | Loss: 0.3062 | LM: 0.2999 | LB: 1.1297 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.450/SR1: 0.426 | LR: 1.00e-04 |
| [2026-04-25 20:37:58] Epoch 1 | Step 2430 | Loss: 0.3062 | LM: 0.3000 | LB: 1.1297 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.450/SR1: 0.426 | LR: 1.00e-04 |
| [2026-04-25 20:38:05] Epoch 1 | Step 2440 | Loss: 0.3061 | LM: 0.2999 | LB: 1.1296 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.450/SR1: 0.426 | LR: 1.00e-04 |
| [2026-04-25 20:38:12] Epoch 1 | Step 2450 | Loss: 0.3061 | LM: 0.2998 | LB: 1.1295 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.450/SR1: 0.426 | LR: 1.00e-04 |
| [2026-04-25 20:38:19] Epoch 1 | Step 2460 | Loss: 0.3061 | LM: 0.2998 | LB: 1.1294 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.450/SR1: 0.426 | LR: 1.00e-04 |
| [2026-04-25 20:38:26] Epoch 1 | Step 2470 | Loss: 0.3061 | LM: 0.2996 | LB: 1.1293 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.450/SR1: 0.426 | LR: 1.00e-04 |
| [2026-04-25 20:38:34] Epoch 1 | Step 2480 | Loss: 0.3060 | LM: 0.2995 | LB: 1.1292 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.450/SR1: 0.426 | LR: 1.00e-04 |
| [2026-04-25 20:38:41] Epoch 1 | Step 2490 | Loss: 0.3059 | LM: 0.2996 | LB: 1.1291 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.450/SR1: 0.426 | LR: 1.00e-04 |
| [2026-04-25 20:38:48] Epoch 1 | Step 2500 | Loss: 0.3058 | LM: 0.2997 | LB: 1.1290 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.450/SR1: 0.426 | LR: 1.00e-04 |
| [2026-04-25 20:38:55] Epoch 1 | Step 2510 | Loss: 0.3057 | LM: 0.2999 | LB: 1.1290 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.449/SR1: 0.426 | LR: 1.00e-04 |
| [2026-04-25 20:39:02] Epoch 1 | Step 2520 | Loss: 0.3055 | LM: 0.2995 | LB: 1.1289 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.449/SR1: 0.426 | LR: 1.00e-04 |
| [2026-04-25 20:39:09] Epoch 1 | Step 2530 | Loss: 0.3053 | LM: 0.2994 | LB: 1.1289 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.449/SR1: 0.426 | LR: 1.00e-04 |
| [2026-04-25 20:39:16] Epoch 1 | Step 2540 | Loss: 0.3053 | LM: 0.2993 | LB: 1.1288 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.449/SR1: 0.426 | LR: 1.00e-04 |
| [2026-04-25 20:39:23] Epoch 1 | Step 2550 | Loss: 0.3051 | LM: 0.2987 | LB: 1.1288 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.449/SR1: 0.425 | LR: 1.00e-04 |
| [2026-04-25 20:39:30] Epoch 1 | Step 2560 | Loss: 0.3050 | LM: 0.2989 | LB: 1.1288 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.449/SR1: 0.425 | LR: 1.00e-04 |
| [2026-04-25 20:39:38] Epoch 1 | Step 2570 | Loss: 0.3051 | LM: 0.2990 | LB: 1.1288 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.449/SR1: 0.425 | LR: 1.00e-04 |
| [2026-04-25 20:39:45] Epoch 1 | Step 2580 | Loss: 0.3051 | LM: 0.2991 | LB: 1.1287 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.449/SR1: 0.425 | LR: 1.00e-04 |
| [2026-04-25 20:39:52] Epoch 1 | Step 2590 | Loss: 0.3051 | LM: 0.2989 | LB: 1.1286 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.449/SR1: 0.425 | LR: 1.00e-04 |
| [2026-04-25 20:39:59] Epoch 1 | Step 2600 | Loss: 0.3052 | LM: 0.2991 | LB: 1.1285 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.449/SR1: 0.425 | LR: 1.00e-04 |
| [2026-04-25 20:40:06] Epoch 1 | Step 2610 | Loss: 0.3052 | LM: 0.2987 | LB: 1.1285 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.449/SR1: 0.425 | LR: 1.00e-04 |
| [2026-04-25 20:40:13] Epoch 1 | Step 2620 | Loss: 0.3051 | LM: 0.2986 | LB: 1.1284 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.449/SR1: 0.425 | LR: 1.00e-04 |
| [2026-04-25 20:40:20] Epoch 1 | Step 2630 | Loss: 0.3050 | LM: 0.2985 | LB: 1.1284 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.449/SR1: 0.425 | LR: 1.00e-04 |
| [2026-04-25 20:40:28] Epoch 1 | Step 2640 | Loss: 0.3050 | LM: 0.2983 | LB: 1.1283 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.449/SR1: 0.425 | LR: 1.00e-04 |
| [2026-04-25 20:40:35] Epoch 1 | Step 2650 | Loss: 0.3048 | LM: 0.2981 | LB: 1.1283 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.449/SR1: 0.425 | LR: 1.00e-04 |
| [2026-04-25 20:40:42] Epoch 1 | Step 2660 | Loss: 0.3048 | LM: 0.2982 | LB: 1.1282 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.449/SR1: 0.425 | LR: 1.00e-04 |
| [2026-04-25 20:40:49] Epoch 1 | Step 2670 | Loss: 0.3047 | LM: 0.2985 | LB: 1.1282 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.449/SR1: 0.425 | LR: 1.00e-04 |
| [2026-04-25 20:40:56] Epoch 1 | Step 2680 | Loss: 0.3046 | LM: 0.2985 | LB: 1.1281 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.449/SR1: 0.425 | LR: 1.00e-04 |
| [2026-04-25 20:41:03] Epoch 1 | Step 2690 | Loss: 0.3046 | LM: 0.2986 | LB: 1.1281 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.448/SR1: 0.425 | LR: 1.00e-04 |
| [2026-04-25 20:41:10] Epoch 1 | Step 2700 | Loss: 0.3045 | LM: 0.2986 | LB: 1.1280 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.448/SR1: 0.425 | LR: 1.00e-04 |
| [2026-04-25 20:41:18] Epoch 1 | Step 2710 | Loss: 0.3043 | LM: 0.2983 | LB: 1.1279 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.448/SR1: 0.424 | LR: 1.00e-04 |
| [2026-04-25 20:41:25] Epoch 1 | Step 2720 | Loss: 0.3043 | LM: 0.2982 | LB: 1.1278 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.448/SR1: 0.424 | LR: 1.00e-04 |
| [2026-04-25 20:41:32] Epoch 1 | Step 2730 | Loss: 0.3042 | LM: 0.2982 | LB: 1.1277 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.448/SR1: 0.424 | LR: 1.00e-04 |
| [2026-04-25 20:41:39] Epoch 1 | Step 2740 | Loss: 0.3043 | LM: 0.2982 | LB: 1.1276 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.448/SR1: 0.424 | LR: 1.00e-04 |
| [2026-04-25 20:41:46] Epoch 1 | Step 2750 | Loss: 0.3043 | LM: 0.2981 | LB: 1.1275 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.448/SR1: 0.424 | LR: 1.00e-04 |
| [2026-04-25 20:41:53] Epoch 1 | Step 2760 | Loss: 0.3041 | LM: 0.2977 | LB: 1.1274 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.448/SR1: 0.424 | LR: 1.00e-04 |
| [2026-04-25 20:42:00] Epoch 1 | Step 2770 | Loss: 0.3041 | LM: 0.2977 | LB: 1.1273 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.448/SR1: 0.424 | LR: 1.00e-04 |
| [2026-04-25 20:42:07] Epoch 1 | Step 2780 | Loss: 0.3041 | LM: 0.2975 | LB: 1.1272 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.448/SR1: 0.424 | LR: 1.00e-04 |
| [2026-04-25 20:42:14] Epoch 1 | Step 2790 | Loss: 0.3040 | LM: 0.2976 | LB: 1.1272 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.448/SR1: 0.424 | LR: 1.00e-04 |
| [2026-04-25 20:42:21] Epoch 1 | Step 2800 | Loss: 0.3039 | LM: 0.2976 | LB: 1.1271 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.448/SR1: 0.424 | LR: 1.00e-04 |
| [2026-04-25 20:42:29] Epoch 1 | Step 2810 | Loss: 0.3040 | LM: 0.2975 | LB: 1.1270 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.448/SR1: 0.424 | LR: 1.00e-04 |
| [2026-04-25 20:42:36] Epoch 1 | Step 2820 | Loss: 0.3040 | LM: 0.2976 | LB: 1.1269 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.447/SR1: 0.424 | LR: 1.00e-04 |
| [2026-04-25 20:42:43] Epoch 1 | Step 2830 | Loss: 0.3039 | LM: 0.2976 | LB: 1.1269 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.447/SR1: 0.423 | LR: 1.00e-04 |
| [2026-04-25 20:42:50] Epoch 1 | Step 2840 | Loss: 0.3040 | LM: 0.2977 | LB: 1.1269 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.447/SR1: 0.423 | LR: 1.00e-04 |
| [2026-04-25 20:42:57] Epoch 1 | Step 2850 | Loss: 0.3041 | LM: 0.2981 | LB: 1.1268 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.447/SR1: 0.423 | LR: 1.00e-04 |
| [2026-04-25 20:43:04] Epoch 1 | Step 2860 | Loss: 0.3040 | LM: 0.2981 | LB: 1.1268 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.447/SR1: 0.423 | LR: 1.00e-04 |
| [2026-04-25 20:43:12] Epoch 1 | Step 2870 | Loss: 0.3039 | LM: 0.2981 | LB: 1.1268 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.447/SR1: 0.423 | LR: 1.00e-04 |
| [2026-04-25 20:43:19] Epoch 1 | Step 2880 | Loss: 0.3039 | LM: 0.2979 | LB: 1.1267 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.447/SR1: 0.423 | LR: 1.00e-04 |
| [2026-04-25 20:43:26] Epoch 1 | Step 2890 | Loss: 0.3038 | LM: 0.2977 | LB: 1.1265 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.447/SR1: 0.423 | LR: 1.00e-04 |
| [2026-04-25 20:43:33] Epoch 1 | Step 2900 | Loss: 0.3037 | LM: 0.2975 | LB: 1.1264 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.447/SR1: 0.423 | LR: 1.00e-04 |
| [2026-04-25 20:43:40] Epoch 1 | Step 2910 | Loss: 0.3037 | LM: 0.2974 | LB: 1.1263 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.447/SR1: 0.423 | LR: 1.00e-04 |
| [2026-04-25 20:43:47] Epoch 1 | Step 2920 | Loss: 0.3038 | LM: 0.2977 | LB: 1.1262 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.447/SR1: 0.423 | LR: 1.00e-04 |
| [2026-04-25 20:43:54] Epoch 1 | Step 2930 | Loss: 0.3037 | LM: 0.2975 | LB: 1.1262 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.447/SR1: 0.423 | LR: 1.00e-04 |
| [2026-04-25 20:44:01] Epoch 1 | Step 2940 | Loss: 0.3035 | LM: 0.2973 | LB: 1.1260 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.446/SR1: 0.423 | LR: 1.00e-04 |
| [2026-04-25 20:44:08] Epoch 1 | Step 2950 | Loss: 0.3036 | LM: 0.2974 | LB: 1.1259 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.446/SR1: 0.422 | LR: 1.00e-04 |
| [2026-04-25 20:44:15] Epoch 1 | Step 2960 | Loss: 0.3036 | LM: 0.2975 | LB: 1.1259 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.446/SR1: 0.422 | LR: 1.00e-04 |
| [2026-04-25 20:44:23] Epoch 1 | Step 2970 | Loss: 0.3036 | LM: 0.2977 | LB: 1.1258 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.446/SR1: 0.422 | LR: 1.00e-04 |
| [2026-04-25 20:44:30] Epoch 1 | Step 2980 | Loss: 0.3035 | LM: 0.2976 | LB: 1.1257 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.446/SR1: 0.422 | LR: 1.00e-04 |
| [2026-04-25 20:44:37] Epoch 1 | Step 2990 | Loss: 0.3036 | LM: 0.2976 | LB: 1.1256 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.446/SR1: 0.422 | LR: 1.00e-04 |
| [2026-04-25 20:44:44] Epoch 1 | Step 3000 | Loss: 0.3035 | LM: 0.2976 | LB: 1.1256 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.446/SR1: 0.422 | LR: 1.00e-04 |
| [2026-04-25 20:44:51] Epoch 1 | Step 3010 | Loss: 0.3035 | LM: 0.2976 | LB: 1.1255 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.446/SR1: 0.422 | LR: 1.00e-04 |
| [2026-04-25 20:44:59] Epoch 1 | Step 3020 | Loss: 0.3033 | LM: 0.2974 | LB: 1.1254 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.446/SR1: 0.422 | LR: 1.00e-04 |
| [2026-04-25 20:45:06] Epoch 1 | Step 3030 | Loss: 0.3033 | LM: 0.2974 | LB: 1.1254 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.446/SR1: 0.422 | LR: 1.00e-04 |
| [2026-04-25 20:45:13] Epoch 1 | Step 3040 | Loss: 0.3031 | LM: 0.2972 | LB: 1.1253 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.446/SR1: 0.422 | LR: 1.00e-04 |
| [2026-04-25 20:45:20] Epoch 1 | Step 3050 | Loss: 0.3030 | LM: 0.2969 | LB: 1.1252 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.446/SR1: 0.422 | LR: 1.00e-04 |
| [2026-04-25 20:45:27] Epoch 1 | Step 3060 | Loss: 0.3030 | LM: 0.2973 | LB: 1.1252 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.446/SR1: 0.422 | LR: 1.00e-04 |
| [2026-04-25 20:45:34] Epoch 1 | Step 3070 | Loss: 0.3029 | LM: 0.2972 | LB: 1.1251 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.446/SR1: 0.422 | LR: 1.00e-04 |
| [2026-04-25 20:45:41] Epoch 1 | Step 3080 | Loss: 0.3028 | LM: 0.2969 | LB: 1.1250 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.446/SR1: 0.422 | LR: 1.00e-04 |
| [2026-04-25 20:45:48] Epoch 1 | Step 3090 | Loss: 0.3027 | LM: 0.2966 | LB: 1.1249 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.445/SR1: 0.421 | LR: 1.00e-04 |
| [2026-04-25 20:45:55] Epoch 1 | Step 3100 | Loss: 0.3026 | LM: 0.2966 | LB: 1.1248 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.445/SR1: 0.421 | LR: 1.00e-04 |
| [2026-04-25 20:46:02] Epoch 1 | Step 3110 | Loss: 0.3025 | LM: 0.2965 | LB: 1.1248 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.445/SR1: 0.421 | LR: 1.00e-04 |
| [2026-04-25 20:46:10] Epoch 1 | Step 3120 | Loss: 0.3027 | LM: 0.2965 | LB: 1.1247 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.445/SR1: 0.421 | LR: 1.00e-04 |
| [2026-04-25 20:46:17] Epoch 1 | Step 3130 | Loss: 0.3027 | LM: 0.2964 | LB: 1.1247 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.445/SR1: 0.421 | LR: 1.00e-04 |
| [2026-04-25 20:46:24] Epoch 1 | Step 3140 | Loss: 0.3027 | LM: 0.2963 | LB: 1.1247 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.445/SR1: 0.421 | LR: 1.00e-04 |
| [2026-04-25 20:46:31] Epoch 1 | Step 3150 | Loss: 0.3028 | LM: 0.2965 | LB: 1.1246 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.445/SR1: 0.421 | LR: 1.00e-04 |
| [2026-04-25 20:46:38] Epoch 1 | Step 3160 | Loss: 0.3028 | LM: 0.2964 | LB: 1.1245 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.445/SR1: 0.421 | LR: 1.00e-04 |
| [2026-04-25 20:46:45] Epoch 1 | Step 3170 | Loss: 0.3028 | LM: 0.2965 | LB: 1.1244 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.445/SR1: 0.421 | LR: 1.00e-04 |
| [2026-04-25 20:46:52] Epoch 1 | Step 3180 | Loss: 0.3028 | LM: 0.2966 | LB: 1.1244 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.445/SR1: 0.421 | LR: 1.00e-04 |
| [2026-04-25 20:46:59] Epoch 1 | Step 3190 | Loss: 0.3026 | LM: 0.2964 | LB: 1.1243 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.445/SR1: 0.421 | LR: 1.00e-04 |
| [2026-04-25 20:47:06] Epoch 1 | Step 3200 | Loss: 0.3025 | LM: 0.2961 | LB: 1.1242 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.445/SR1: 0.421 | LR: 1.00e-04 |
| [2026-04-25 20:47:13] Epoch 1 | Step 3210 | Loss: 0.3025 | LM: 0.2958 | LB: 1.1241 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.445/SR1: 0.421 | LR: 1.00e-04 |
| [2026-04-25 20:47:21] Epoch 1 | Step 3220 | Loss: 0.3023 | LM: 0.2957 | LB: 1.1241 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.445/SR1: 0.421 | LR: 1.00e-04 |
| [2026-04-25 20:47:28] Epoch 1 | Step 3230 | Loss: 0.3023 | LM: 0.2956 | LB: 1.1240 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.445/SR1: 0.421 | LR: 1.00e-04 |
| [2026-04-25 20:47:35] Epoch 1 | Step 3240 | Loss: 0.3022 | LM: 0.2954 | LB: 1.1240 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.445/SR1: 0.420 | LR: 1.00e-04 |
| [2026-04-25 20:47:42] Epoch 1 | Step 3250 | Loss: 0.3022 | LM: 0.2955 | LB: 1.1239 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.444/SR1: 0.420 | LR: 1.00e-04 |
| [2026-04-25 20:47:49] Epoch 1 | Step 3260 | Loss: 0.3022 | LM: 0.2952 | LB: 1.1238 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.444/SR1: 0.420 | LR: 1.00e-04 |
| [2026-04-25 20:47:56] Epoch 1 | Step 3270 | Loss: 0.3021 | LM: 0.2953 | LB: 1.1238 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.444/SR1: 0.420 | LR: 1.00e-04 |
| [2026-04-25 20:48:03] Epoch 1 | Step 3280 | Loss: 0.3020 | LM: 0.2950 | LB: 1.1238 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.444/SR1: 0.420 | LR: 1.00e-04 |
| [2026-04-25 20:48:10] Epoch 1 | Step 3290 | Loss: 0.3019 | LM: 0.2950 | LB: 1.1238 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.444/SR1: 0.420 | LR: 1.00e-04 |
| [2026-04-25 20:48:17] Epoch 1 | Step 3300 | Loss: 0.3019 | LM: 0.2952 | LB: 1.1238 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.444/SR1: 0.420 | LR: 1.00e-04 |
| [2026-04-25 20:48:25] Epoch 1 | Step 3310 | Loss: 0.3018 | LM: 0.2951 | LB: 1.1237 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.444/SR1: 0.420 | LR: 1.00e-04 |
| [2026-04-25 20:48:32] Epoch 1 | Step 3320 | Loss: 0.3018 | LM: 0.2950 | LB: 1.1236 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.444/SR1: 0.420 | LR: 1.00e-04 |
| [2026-04-25 20:48:39] Epoch 1 | Step 3330 | Loss: 0.3018 | LM: 0.2950 | LB: 1.1236 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.444/SR1: 0.420 | LR: 1.00e-04 |
| [2026-04-25 20:48:46] Epoch 1 | Step 3340 | Loss: 0.3018 | LM: 0.2952 | LB: 1.1235 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.444/SR1: 0.420 | LR: 1.00e-04 |
| [2026-04-25 20:48:53] Epoch 1 | Step 3350 | Loss: 0.3016 | LM: 0.2951 | LB: 1.1235 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.444/SR1: 0.420 | LR: 1.00e-04 |
| [2026-04-25 20:49:00] Epoch 1 | Step 3360 | Loss: 0.3015 | LM: 0.2949 | LB: 1.1234 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.444/SR1: 0.420 | LR: 1.00e-04 |
| [2026-04-25 20:49:07] Epoch 1 | Step 3370 | Loss: 0.3016 | LM: 0.2948 | LB: 1.1233 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.444/SR1: 0.420 | LR: 1.00e-04 |
| [2026-04-25 20:49:14] Epoch 1 | Step 3380 | Loss: 0.3014 | LM: 0.2947 | LB: 1.1233 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.444/SR1: 0.420 | LR: 1.00e-04 |
| [2026-04-25 20:49:21] Epoch 1 | Step 3390 | Loss: 0.3015 | LM: 0.2947 | LB: 1.1233 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.444/SR1: 0.420 | LR: 1.00e-04 |
| [2026-04-25 20:49:29] Epoch 1 | Step 3400 | Loss: 0.3017 | LM: 0.2948 | LB: 1.1232 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.444/SR1: 0.420 | LR: 1.00e-04 |
| [2026-04-25 20:49:36] Epoch 1 | Step 3410 | Loss: 0.3017 | LM: 0.2949 | LB: 1.1231 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.444/SR1: 0.419 | LR: 1.00e-04 |
| [2026-04-25 20:49:43] Epoch 1 | Step 3420 | Loss: 0.3016 | LM: 0.2950 | LB: 1.1231 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.443/SR1: 0.419 | LR: 1.00e-04 |
| [2026-04-25 20:49:50] Epoch 1 | Step 3430 | Loss: 0.3015 | LM: 0.2952 | LB: 1.1230 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.443/SR1: 0.419 | LR: 1.00e-04 |
| [2026-04-25 20:49:57] Epoch 1 | Step 3440 | Loss: 0.3015 | LM: 0.2953 | LB: 1.1229 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.443/SR1: 0.419 | LR: 1.00e-04 |
| [2026-04-25 20:50:04] Epoch 1 | Step 3450 | Loss: 0.3015 | LM: 0.2953 | LB: 1.1228 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.443/SR1: 0.419 | LR: 1.00e-04 |
| [2026-04-25 20:50:11] Epoch 1 | Step 3460 | Loss: 0.3014 | LM: 0.2950 | LB: 1.1227 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.443/SR1: 0.419 | LR: 1.00e-04 |
| [2026-04-25 20:50:19] Epoch 1 | Step 3470 | Loss: 0.3014 | LM: 0.2949 | LB: 1.1227 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.443/SR1: 0.419 | LR: 1.00e-04 |
| [2026-04-25 20:50:26] Epoch 1 | Step 3480 | Loss: 0.3014 | LM: 0.2950 | LB: 1.1226 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.443/SR1: 0.419 | LR: 1.00e-04 |
| [2026-04-25 20:50:33] Epoch 1 | Step 3490 | Loss: 0.3013 | LM: 0.2950 | LB: 1.1226 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.443/SR1: 0.419 | LR: 1.00e-04 |
| [2026-04-25 20:50:40] Epoch 1 | Step 3500 | Loss: 0.3012 | LM: 0.2948 | LB: 1.1225 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.443/SR1: 0.419 | LR: 1.00e-04 |
| [2026-04-25 20:50:47] Epoch 1 | Step 3510 | Loss: 0.3012 | LM: 0.2948 | LB: 1.1224 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.443/SR1: 0.419 | LR: 1.00e-04 |
| [2026-04-25 20:50:54] Epoch 1 | Step 3520 | Loss: 0.3011 | LM: 0.2949 | LB: 1.1224 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.443/SR1: 0.419 | LR: 1.00e-04 |
| [2026-04-25 20:51:01] Epoch 1 | Step 3530 | Loss: 0.3012 | LM: 0.2947 | LB: 1.1223 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.443/SR1: 0.419 | LR: 1.00e-04 |
| [2026-04-25 20:51:08] Epoch 1 | Step 3540 | Loss: 0.3011 | LM: 0.2945 | LB: 1.1222 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.443/SR1: 0.419 | LR: 1.00e-04 |
| [2026-04-25 20:51:15] Epoch 1 | Step 3550 | Loss: 0.3011 | LM: 0.2945 | LB: 1.1222 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.443/SR1: 0.418 | LR: 1.00e-04 |
| [2026-04-25 20:51:23] Epoch 1 | Step 3560 | Loss: 0.3011 | LM: 0.2946 | LB: 1.1221 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.443/SR1: 0.418 | LR: 1.00e-04 |
| [2026-04-25 20:51:30] Epoch 1 | Step 3570 | Loss: 0.3011 | LM: 0.2945 | LB: 1.1220 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.443/SR1: 0.418 | LR: 1.00e-04 |
| [2026-04-25 20:51:37] Epoch 1 | Step 3580 | Loss: 0.3010 | LM: 0.2945 | LB: 1.1219 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.442/SR1: 0.418 | LR: 1.00e-04 |
| [2026-04-25 20:51:44] Epoch 1 | Step 3590 | Loss: 0.3010 | LM: 0.2945 | LB: 1.1219 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.442/SR1: 0.418 | LR: 1.00e-04 |
| [2026-04-25 20:51:51] Epoch 1 | Step 3600 | Loss: 0.3009 | LM: 0.2945 | LB: 1.1218 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.442/SR1: 0.418 | LR: 1.00e-04 |
| [2026-04-25 20:51:58] Epoch 1 | Step 3610 | Loss: 0.3008 | LM: 0.2943 | LB: 1.1217 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.442/SR1: 0.418 | LR: 1.00e-04 |
| [2026-04-25 20:52:05] Epoch 1 | Step 3620 | Loss: 0.3007 | LM: 0.2940 | LB: 1.1217 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.442/SR1: 0.418 | LR: 1.00e-04 |
| [2026-04-25 20:52:12] Epoch 1 | Step 3630 | Loss: 0.3008 | LM: 0.2942 | LB: 1.1216 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.442/SR1: 0.418 | LR: 1.00e-04 |
| [2026-04-25 20:52:19] Epoch 1 | Step 3640 | Loss: 0.3009 | LM: 0.2943 | LB: 1.1215 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.442/SR1: 0.418 | LR: 1.00e-04 |
| [2026-04-25 20:52:26] Epoch 1 | Step 3650 | Loss: 0.3009 | LM: 0.2945 | LB: 1.1215 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.442/SR1: 0.418 | LR: 1.00e-04 |
| [2026-04-25 20:52:34] Epoch 1 | Step 3660 | Loss: 0.3008 | LM: 0.2945 | LB: 1.1215 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.442/SR1: 0.418 | LR: 1.00e-04 |
| [2026-04-25 20:52:41] Epoch 1 | Step 3670 | Loss: 0.3008 | LM: 0.2942 | LB: 1.1214 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.442/SR1: 0.418 | LR: 1.00e-04 |
| [2026-04-25 20:52:48] Epoch 1 | Step 3680 | Loss: 0.3007 | LM: 0.2943 | LB: 1.1213 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.442/SR1: 0.418 | LR: 1.00e-04 |
| [2026-04-25 20:52:55] Epoch 1 | Step 3690 | Loss: 0.3008 | LM: 0.2944 | LB: 1.1212 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.442/SR1: 0.417 | LR: 1.00e-04 |
| [2026-04-25 20:53:02] Epoch 1 | Step 3700 | Loss: 0.3007 | LM: 0.2943 | LB: 1.1211 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.442/SR1: 0.417 | LR: 1.00e-04 |
| [2026-04-25 20:53:09] Epoch 1 | Step 3710 | Loss: 0.3006 | LM: 0.2941 | LB: 1.1211 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.442/SR1: 0.417 | LR: 1.00e-04 |
| [2026-04-25 20:53:16] Epoch 1 | Step 3720 | Loss: 0.3006 | LM: 0.2943 | LB: 1.1211 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.442/SR1: 0.417 | LR: 1.00e-04 |
| [2026-04-25 20:53:23] Epoch 1 | Step 3730 | Loss: 0.3006 | LM: 0.2942 | LB: 1.1210 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.441/SR1: 0.417 | LR: 1.00e-04 |
| [2026-04-25 20:53:31] Epoch 1 | Step 3740 | Loss: 0.3006 | LM: 0.2941 | LB: 1.1209 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.441/SR1: 0.417 | LR: 1.00e-04 |
| [2026-04-25 20:53:38] Epoch 1 | Step 3750 | Loss: 0.3005 | LM: 0.2939 | LB: 1.1208 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.441/SR1: 0.417 | LR: 1.00e-04 |
| [2026-04-25 20:53:45] Epoch 1 | Step 3760 | Loss: 0.3006 | LM: 0.2940 | LB: 1.1208 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.441/SR1: 0.417 | LR: 1.00e-04 |
| [2026-04-25 20:53:52] Epoch 1 | Step 3770 | Loss: 0.3006 | LM: 0.2941 | LB: 1.1207 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.441/SR1: 0.417 | LR: 1.00e-04 |
| [2026-04-25 20:53:59] Epoch 1 | Step 3780 | Loss: 0.3006 | LM: 0.2940 | LB: 1.1207 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.441/SR1: 0.417 | LR: 1.00e-04 |
| [2026-04-25 20:54:06] Epoch 1 | Step 3790 | Loss: 0.3006 | LM: 0.2940 | LB: 1.1206 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.441/SR1: 0.417 | LR: 1.00e-04 |
| [2026-04-25 20:54:13] Epoch 1 | Step 3800 | Loss: 0.3006 | LM: 0.2941 | LB: 1.1206 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.441/SR1: 0.417 | LR: 1.00e-04 |
| [2026-04-25 20:54:20] Epoch 1 | Step 3810 | Loss: 0.3004 | LM: 0.2939 | LB: 1.1205 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.441/SR1: 0.417 | LR: 1.00e-04 |
| [2026-04-25 20:54:27] Epoch 1 | Step 3820 | Loss: 0.3004 | LM: 0.2937 | LB: 1.1204 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.441/SR1: 0.417 | LR: 1.00e-04 |
| [2026-04-25 20:54:34] Epoch 1 | Step 3830 | Loss: 0.3004 | LM: 0.2938 | LB: 1.1204 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.441/SR1: 0.417 | LR: 1.00e-04 |
| [2026-04-25 20:54:41] Epoch 1 | Step 3840 | Loss: 0.3004 | LM: 0.2939 | LB: 1.1203 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.441/SR1: 0.417 | LR: 1.00e-04 |
| [2026-04-25 20:54:48] Epoch 1 | Step 3850 | Loss: 0.3003 | LM: 0.2938 | LB: 1.1203 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.441/SR1: 0.416 | LR: 1.00e-04 |
| [2026-04-25 20:54:55] Epoch 1 | Step 3860 | Loss: 0.3003 | LM: 0.2938 | LB: 1.1202 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.441/SR1: 0.416 | LR: 1.00e-04 |
| [2026-04-25 20:55:02] Epoch 1 | Step 3870 | Loss: 0.3003 | LM: 0.2936 | LB: 1.1202 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.441/SR1: 0.416 | LR: 1.00e-04 |
| [2026-04-25 20:55:09] Epoch 1 | Step 3880 | Loss: 0.3001 | LM: 0.2933 | LB: 1.1201 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.441/SR1: 0.416 | LR: 1.00e-04 |
| [2026-04-25 20:55:17] Epoch 1 | Step 3890 | Loss: 0.3000 | LM: 0.2934 | LB: 1.1201 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.440/SR1: 0.416 | LR: 1.00e-04 |
| [2026-04-25 20:55:24] Epoch 1 | Step 3900 | Loss: 0.3000 | LM: 0.2933 | LB: 1.1200 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.440/SR1: 0.416 | LR: 1.00e-04 |
| [2026-04-25 20:55:31] Epoch 1 | Step 3910 | Loss: 0.3000 | LM: 0.2934 | LB: 1.1200 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.440/SR1: 0.416 | LR: 1.00e-04 |
| [2026-04-25 20:55:38] Epoch 1 | Step 3920 | Loss: 0.3001 | LM: 0.2933 | LB: 1.1200 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.440/SR1: 0.416 | LR: 1.00e-04 |
| [2026-04-25 20:55:45] Epoch 1 | Step 3930 | Loss: 0.3000 | LM: 0.2933 | LB: 1.1199 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.440/SR1: 0.416 | LR: 1.00e-04 |
| [2026-04-25 20:55:52] Epoch 1 | Step 3940 | Loss: 0.3000 | LM: 0.2932 | LB: 1.1198 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.440/SR1: 0.416 | LR: 1.00e-04 |
| [2026-04-25 20:55:59] Epoch 1 | Step 3950 | Loss: 0.2999 | LM: 0.2929 | LB: 1.1198 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.440/SR1: 0.416 | LR: 1.00e-04 |
| [2026-04-25 20:56:06] Epoch 1 | Step 3960 | Loss: 0.2999 | LM: 0.2929 | LB: 1.1197 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.440/SR1: 0.416 | LR: 1.00e-04 |
| [2026-04-25 20:56:13] Epoch 1 | Step 3970 | Loss: 0.2998 | LM: 0.2929 | LB: 1.1197 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.440/SR1: 0.416 | LR: 9.99e-05 |
| [2026-04-25 20:56:20] Epoch 1 | Step 3980 | Loss: 0.2998 | LM: 0.2929 | LB: 1.1196 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.440/SR1: 0.416 | LR: 9.99e-05 |
| [2026-04-25 20:56:27] Epoch 1 | Step 3990 | Loss: 0.2998 | LM: 0.2931 | LB: 1.1195 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.440/SR1: 0.416 | LR: 9.97e-05 |
| [2026-04-25 20:56:34] Epoch 1 | Step 4000 | Loss: 0.2998 | LM: 0.2931 | LB: 1.1195 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.440/SR1: 0.416 | LR: 9.95e-05 |
| [2026-04-25 20:56:35] Validation | Batch 10/42 | Loss: 0.2820 | LM_LOSS: 0.2711 | LB_LOSS: 1.0925 |
| [2026-04-25 20:56:36] Validation | Batch 20/42 | Loss: 0.3017 | LM_LOSS: 0.2907 | LB_LOSS: 1.0959 |
| [2026-04-25 20:56:38] Validation | Batch 30/42 | Loss: 0.2930 | LM_LOSS: 0.2820 | LB_LOSS: 1.0932 |
| [2026-04-25 20:56:39] Validation | Batch 40/42 | Loss: 0.2970 | LM_LOSS: 0.2861 | LB_LOSS: 1.0924 |
| [2026-04-25 20:56:39] Validation | Batch 42/42 | Loss: 0.2964 | LM_LOSS: 0.2855 | LB_LOSS: 1.0926 |
| [2026-04-25 20:56:39] Validation | Loss: 0.2964 | LM_LOSS: 0.2855 | LB_LOSS: 1.0926 | PPL: 1.33 | Time: 4.75s |
| [2026-04-25 20:56:42] New best model saved! Val loss: 0.2964 |
| [2026-04-25 20:56:49] Epoch 1 | Step 4010 | Loss: 0.2997 | LM: 0.2931 | LB: 1.1194 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.440/SR1: 0.416 | LR: 9.93e-05 |
| [2026-04-25 20:56:56] Epoch 1 | Step 4020 | Loss: 0.2997 | LM: 0.2931 | LB: 1.1193 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.440/SR1: 0.415 | LR: 9.90e-05 |
| [2026-04-25 20:57:03] Epoch 1 | Step 4030 | Loss: 0.2996 | LM: 0.2930 | LB: 1.1193 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.440/SR1: 0.415 | LR: 9.87e-05 |
| [2026-04-25 20:57:10] Epoch 1 | Step 4040 | Loss: 0.2995 | LM: 0.2928 | LB: 1.1192 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.440/SR1: 0.415 | LR: 9.84e-05 |
| [2026-04-25 20:57:18] Epoch 1 | Step 4050 | Loss: 0.2994 | LM: 0.2928 | LB: 1.1191 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.440/SR1: 0.415 | LR: 9.80e-05 |
| [2026-04-25 20:57:25] Epoch 1 | Step 4060 | Loss: 0.2992 | LM: 0.2926 | LB: 1.1191 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.440/SR1: 0.415 | LR: 9.75e-05 |
| [2026-04-25 20:57:32] Epoch 1 | Step 4070 | Loss: 0.2992 | LM: 0.2927 | LB: 1.1190 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.440/SR1: 0.415 | LR: 9.70e-05 |
| [2026-04-25 20:57:39] Epoch 1 | Step 4080 | Loss: 0.2992 | LM: 0.2928 | LB: 1.1190 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.415 | LR: 9.65e-05 |
| [2026-04-25 20:57:46] Epoch 1 | Step 4090 | Loss: 0.2992 | LM: 0.2927 | LB: 1.1189 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.415 | LR: 9.59e-05 |
| [2026-04-25 20:57:53] Epoch 1 | Step 4100 | Loss: 0.2993 | LM: 0.2927 | LB: 1.1188 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.415 | LR: 9.53e-05 |
| [2026-04-25 20:58:00] Epoch 1 | Step 4110 | Loss: 0.2992 | LM: 0.2928 | LB: 1.1188 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.415 | LR: 9.46e-05 |
| [2026-04-25 20:58:07] Epoch 1 | Step 4120 | Loss: 0.2993 | LM: 0.2928 | LB: 1.1187 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.415 | LR: 9.40e-05 |
| [2026-04-25 20:58:14] Epoch 1 | Step 4130 | Loss: 0.2992 | LM: 0.2926 | LB: 1.1187 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.415 | LR: 9.32e-05 |
| [2026-04-25 20:58:21] Epoch 1 | Step 4140 | Loss: 0.2992 | LM: 0.2927 | LB: 1.1186 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.415 | LR: 9.24e-05 |
| [2026-04-25 20:58:28] Epoch 1 | Step 4150 | Loss: 0.2994 | LM: 0.2929 | LB: 1.1186 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.415 | LR: 9.16e-05 |
| [2026-04-25 20:58:35] Epoch 1 | Step 4160 | Loss: 0.2994 | LM: 0.2930 | LB: 1.1185 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.415 | LR: 9.08e-05 |
| [2026-04-25 20:58:42] Epoch 1 | Step 4170 | Loss: 0.2994 | LM: 0.2932 | LB: 1.1186 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.415 | LR: 8.99e-05 |
| [2026-04-25 20:58:49] Epoch 1 | Step 4180 | Loss: 0.2994 | LM: 0.2933 | LB: 1.1185 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.415 | LR: 8.90e-05 |
| [2026-04-25 20:58:56] Epoch 1 | Step 4190 | Loss: 0.2993 | LM: 0.2933 | LB: 1.1184 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.415 | LR: 8.80e-05 |
| [2026-04-25 20:59:03] Epoch 1 | Step 4200 | Loss: 0.2994 | LM: 0.2934 | LB: 1.1184 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.414 | LR: 8.70e-05 |
| [2026-04-25 20:59:10] Epoch 1 | Step 4210 | Loss: 0.2994 | LM: 0.2933 | LB: 1.1183 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.414 | LR: 8.60e-05 |
| [2026-04-25 20:59:18] Epoch 1 | Step 4220 | Loss: 0.2996 | LM: 0.2935 | LB: 1.1183 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.414 | LR: 8.50e-05 |
| [2026-04-25 20:59:25] Epoch 1 | Step 4230 | Loss: 0.2996 | LM: 0.2935 | LB: 1.1183 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.414 | LR: 8.39e-05 |
| [2026-04-25 20:59:32] Epoch 1 | Step 4240 | Loss: 0.2997 | LM: 0.2937 | LB: 1.1182 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.414 | LR: 8.28e-05 |
| [2026-04-25 20:59:39] Epoch 1 | Step 4250 | Loss: 0.2997 | LM: 0.2937 | LB: 1.1182 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.414 | LR: 8.16e-05 |
| [2026-04-25 20:59:46] Epoch 1 | Step 4260 | Loss: 0.2996 | LM: 0.2934 | LB: 1.1182 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.414 | LR: 8.05e-05 |
| [2026-04-25 20:59:53] Epoch 1 | Step 4270 | Loss: 0.2997 | LM: 0.2934 | LB: 1.1181 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.414 | LR: 7.93e-05 |
| [2026-04-25 21:00:00] Epoch 1 | Step 4280 | Loss: 0.2996 | LM: 0.2933 | LB: 1.1181 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.414 | LR: 7.81e-05 |
| [2026-04-25 21:00:07] Epoch 1 | Step 4290 | Loss: 0.2995 | LM: 0.2931 | LB: 1.1181 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.414 | LR: 7.68e-05 |
| [2026-04-25 21:00:14] Epoch 1 | Step 4300 | Loss: 0.2995 | LM: 0.2931 | LB: 1.1180 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.414 | LR: 7.56e-05 |
| [2026-04-25 21:00:21] Epoch 1 | Step 4310 | Loss: 0.2996 | LM: 0.2930 | LB: 1.1180 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.414 | LR: 7.43e-05 |
| [2026-04-25 21:00:28] Epoch 1 | Step 4320 | Loss: 0.2996 | LM: 0.2929 | LB: 1.1179 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.439/SR1: 0.414 | LR: 7.30e-05 |
| [2026-04-25 21:00:35] Epoch 1 | Step 4330 | Loss: 0.2996 | LM: 0.2930 | LB: 1.1179 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.414 | LR: 7.16e-05 |
| [2026-04-25 21:00:42] Epoch 1 | Step 4340 | Loss: 0.2995 | LM: 0.2931 | LB: 1.1179 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.414 | LR: 7.03e-05 |
| [2026-04-25 21:00:50] Epoch 1 | Step 4350 | Loss: 0.2994 | LM: 0.2931 | LB: 1.1178 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.414 | LR: 6.90e-05 |
| [2026-04-25 21:00:57] Epoch 1 | Step 4360 | Loss: 0.2994 | LM: 0.2930 | LB: 1.1178 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.414 | LR: 6.76e-05 |
| [2026-04-25 21:01:04] Epoch 1 | Step 4370 | Loss: 0.2994 | LM: 0.2932 | LB: 1.1177 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.414 | LR: 6.62e-05 |
| [2026-04-25 21:01:11] Epoch 1 | Step 4380 | Loss: 0.2993 | LM: 0.2931 | LB: 1.1176 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.414 | LR: 6.48e-05 |
| [2026-04-25 21:01:18] Epoch 1 | Step 4390 | Loss: 0.2993 | LM: 0.2930 | LB: 1.1176 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.413 | LR: 6.34e-05 |
| [2026-04-25 21:01:25] Epoch 1 | Step 4400 | Loss: 0.2993 | LM: 0.2928 | LB: 1.1175 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.413 | LR: 6.20e-05 |
| [2026-04-25 21:01:32] Epoch 1 | Step 4410 | Loss: 0.2992 | LM: 0.2927 | LB: 1.1175 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.413 | LR: 6.06e-05 |
| [2026-04-25 21:01:39] Epoch 1 | Step 4420 | Loss: 0.2992 | LM: 0.2928 | LB: 1.1174 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.413 | LR: 5.92e-05 |
| [2026-04-25 21:01:46] Epoch 1 | Step 4430 | Loss: 0.2992 | LM: 0.2928 | LB: 1.1174 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.413 | LR: 5.78e-05 |
| [2026-04-25 21:01:53] Epoch 1 | Step 4440 | Loss: 0.2993 | LM: 0.2928 | LB: 1.1173 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.413 | LR: 5.63e-05 |
| [2026-04-25 21:02:00] Epoch 1 | Step 4450 | Loss: 0.2992 | LM: 0.2926 | LB: 1.1173 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.413 | LR: 5.49e-05 |
| [2026-04-25 21:02:07] Epoch 1 | Step 4460 | Loss: 0.2993 | LM: 0.2926 | LB: 1.1172 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.413 | LR: 5.35e-05 |
| [2026-04-25 21:02:14] Epoch 1 | Step 4470 | Loss: 0.2992 | LM: 0.2925 | LB: 1.1171 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.413 | LR: 5.20e-05 |
| [2026-04-25 21:02:21] Epoch 1 | Step 4480 | Loss: 0.2991 | LM: 0.2924 | LB: 1.1171 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.413 | LR: 5.06e-05 |
| [2026-04-25 21:02:29] Epoch 1 | Step 4490 | Loss: 0.2990 | LM: 0.2924 | LB: 1.1170 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.413 | LR: 4.92e-05 |
| [2026-04-25 21:02:36] Epoch 1 | Step 4500 | Loss: 0.2989 | LM: 0.2923 | LB: 1.1170 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.413 | LR: 4.78e-05 |
| [2026-04-25 21:02:43] Epoch 1 | Step 4510 | Loss: 0.2988 | LM: 0.2922 | LB: 1.1170 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.413 | LR: 4.64e-05 |
| [2026-04-25 21:02:50] Epoch 1 | Step 4520 | Loss: 0.2988 | LM: 0.2922 | LB: 1.1169 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.413 | LR: 4.50e-05 |
| [2026-04-25 21:02:57] Epoch 1 | Step 4530 | Loss: 0.2987 | LM: 0.2920 | LB: 1.1169 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.413 | LR: 4.36e-05 |
| [2026-04-25 21:03:04] Epoch 1 | Step 4540 | Loss: 0.2987 | LM: 0.2921 | LB: 1.1168 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.413 | LR: 4.22e-05 |
| [2026-04-25 21:03:11] Epoch 1 | Step 4550 | Loss: 0.2986 | LM: 0.2920 | LB: 1.1168 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.438/SR1: 0.413 | LR: 4.08e-05 |
| [2026-04-25 21:03:18] Epoch 1 | Step 4560 | Loss: 0.2986 | LM: 0.2920 | LB: 1.1168 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.413 | LR: 3.95e-05 |
| [2026-04-25 21:03:25] Epoch 1 | Step 4570 | Loss: 0.2986 | LM: 0.2919 | LB: 1.1167 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.413 | LR: 3.82e-05 |
| [2026-04-25 21:03:32] Epoch 1 | Step 4580 | Loss: 0.2986 | LM: 0.2919 | LB: 1.1167 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.413 | LR: 3.68e-05 |
| [2026-04-25 21:03:39] Epoch 1 | Step 4590 | Loss: 0.2985 | LM: 0.2919 | LB: 1.1167 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.413 | LR: 3.55e-05 |
| [2026-04-25 21:03:46] Epoch 1 | Step 4600 | Loss: 0.2985 | LM: 0.2918 | LB: 1.1167 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 3.43e-05 |
| [2026-04-25 21:03:54] Epoch 1 | Step 4610 | Loss: 0.2984 | LM: 0.2916 | LB: 1.1166 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 3.30e-05 |
| [2026-04-25 21:04:01] Epoch 1 | Step 4620 | Loss: 0.2984 | LM: 0.2916 | LB: 1.1166 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 3.18e-05 |
| [2026-04-25 21:04:08] Epoch 1 | Step 4630 | Loss: 0.2984 | LM: 0.2916 | LB: 1.1165 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 3.05e-05 |
| [2026-04-25 21:04:15] Epoch 1 | Step 4640 | Loss: 0.2984 | LM: 0.2916 | LB: 1.1165 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 2.94e-05 |
| [2026-04-25 21:04:22] Epoch 1 | Step 4650 | Loss: 0.2984 | LM: 0.2916 | LB: 1.1165 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 2.82e-05 |
| [2026-04-25 21:04:29] Epoch 1 | Step 4660 | Loss: 0.2984 | LM: 0.2915 | LB: 1.1164 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 2.71e-05 |
| [2026-04-25 21:04:36] Epoch 1 | Step 4670 | Loss: 0.2984 | LM: 0.2916 | LB: 1.1164 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 2.60e-05 |
| [2026-04-25 21:04:43] Epoch 1 | Step 4680 | Loss: 0.2984 | LM: 0.2916 | LB: 1.1163 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 2.49e-05 |
| [2026-04-25 21:04:50] Epoch 1 | Step 4690 | Loss: 0.2984 | LM: 0.2915 | LB: 1.1163 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 2.38e-05 |
| [2026-04-25 21:04:57] Epoch 1 | Step 4700 | Loss: 0.2984 | LM: 0.2916 | LB: 1.1162 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 2.28e-05 |
| [2026-04-25 21:05:04] Epoch 1 | Step 4710 | Loss: 0.2984 | LM: 0.2915 | LB: 1.1162 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 2.18e-05 |
| [2026-04-25 21:05:12] Epoch 1 | Step 4720 | Loss: 0.2983 | LM: 0.2915 | LB: 1.1162 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 2.09e-05 |
| [2026-04-25 21:05:19] Epoch 1 | Step 4730 | Loss: 0.2983 | LM: 0.2915 | LB: 1.1161 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 2.00e-05 |
| [2026-04-25 21:05:26] Epoch 1 | Step 4740 | Loss: 0.2983 | LM: 0.2915 | LB: 1.1161 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 1.91e-05 |
| [2026-04-25 21:05:33] Epoch 1 | Step 4750 | Loss: 0.2983 | LM: 0.2914 | LB: 1.1160 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 1.82e-05 |
| [2026-04-25 21:05:40] Epoch 1 | Step 4760 | Loss: 0.2983 | LM: 0.2913 | LB: 1.1160 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 1.74e-05 |
| [2026-04-25 21:05:47] Epoch 1 | Step 4770 | Loss: 0.2982 | LM: 0.2911 | LB: 1.1160 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 1.67e-05 |
| [2026-04-25 21:05:54] Epoch 1 | Step 4780 | Loss: 0.2982 | LM: 0.2912 | LB: 1.1160 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 1.59e-05 |
| [2026-04-25 21:06:01] Epoch 1 | Step 4790 | Loss: 0.2982 | LM: 0.2911 | LB: 1.1159 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 1.52e-05 |
| [2026-04-25 21:06:08] Epoch 1 | Step 4800 | Loss: 0.2981 | LM: 0.2910 | LB: 1.1159 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 1.46e-05 |
| [2026-04-25 21:06:16] Epoch 1 | Step 4810 | Loss: 0.2981 | LM: 0.2910 | LB: 1.1158 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 1.40e-05 |
| [2026-04-25 21:06:23] Epoch 1 | Step 4820 | Loss: 0.2980 | LM: 0.2908 | LB: 1.1158 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.412 | LR: 1.34e-05 |
| [2026-04-25 21:06:30] Epoch 1 | Step 4830 | Loss: 0.2979 | LM: 0.2906 | LB: 1.1158 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.437/SR1: 0.411 | LR: 1.29e-05 |
| [2026-04-25 21:06:37] Epoch 1 | Step 4840 | Loss: 0.2979 | LM: 0.2906 | LB: 1.1157 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.24e-05 |
| [2026-04-25 21:06:44] Epoch 1 | Step 4850 | Loss: 0.2979 | LM: 0.2907 | LB: 1.1157 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.20e-05 |
| [2026-04-25 21:06:51] Epoch 1 | Step 4860 | Loss: 0.2980 | LM: 0.2906 | LB: 1.1156 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.16e-05 |
| [2026-04-25 21:06:58] Epoch 1 | Step 4870 | Loss: 0.2980 | LM: 0.2906 | LB: 1.1156 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.12e-05 |
| [2026-04-25 21:07:05] Epoch 1 | Step 4880 | Loss: 0.2980 | LM: 0.2907 | LB: 1.1156 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.09e-05 |
| [2026-04-25 21:07:12] Epoch 1 | Step 4890 | Loss: 0.2979 | LM: 0.2907 | LB: 1.1155 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.06e-05 |
| [2026-04-25 21:07:19] Epoch 1 | Step 4900 | Loss: 0.2979 | LM: 0.2906 | LB: 1.1155 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.04e-05 |
| [2026-04-25 21:07:26] Epoch 1 | Step 4910 | Loss: 0.2979 | LM: 0.2905 | LB: 1.1155 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.03e-05 |
| [2026-04-25 21:07:34] Epoch 1 | Step 4920 | Loss: 0.2979 | LM: 0.2905 | LB: 1.1154 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.01e-05 |
| [2026-04-25 21:07:41] Epoch 1 | Step 4930 | Loss: 0.2978 | LM: 0.2904 | LB: 1.1154 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.00e-05 |
| [2026-04-25 21:07:48] Epoch 1 | Step 4940 | Loss: 0.2978 | LM: 0.2905 | LB: 1.1153 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.00e-05 |
| [2026-04-25 21:07:55] Epoch 1 | Step 4950 | Loss: 0.2978 | LM: 0.2905 | LB: 1.1153 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.00e-05 |
| [2026-04-25 21:08:02] Epoch 1 | Step 4960 | Loss: 0.2978 | LM: 0.2905 | LB: 1.1153 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.00e-05 |
| [2026-04-25 21:08:09] Epoch 1 | Step 4970 | Loss: 0.2978 | LM: 0.2904 | LB: 1.1152 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.00e-05 |
| [2026-04-25 21:08:16] Epoch 1 | Step 4980 | Loss: 0.2977 | LM: 0.2905 | LB: 1.1152 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.00e-05 |
| [2026-04-25 21:08:23] Epoch 1 | Step 4990 | Loss: 0.2977 | LM: 0.2904 | LB: 1.1151 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.00e-05 |
| [2026-04-25 21:08:31] Epoch 1 | Step 5000 | Loss: 0.2978 | LM: 0.2905 | LB: 1.1151 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.00e-05 |
| [2026-04-25 21:08:38] Epoch 1 | Step 5010 | Loss: 0.2977 | LM: 0.2905 | LB: 1.1151 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.00e-05 |
| [2026-04-25 21:08:45] Epoch 1 | Step 5020 | Loss: 0.2976 | LM: 0.2903 | LB: 1.1151 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.00e-05 |
| [2026-04-25 21:08:52] Epoch 1 | Step 5030 | Loss: 0.2976 | LM: 0.2903 | LB: 1.1150 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.00e-05 |
| [2026-04-25 21:08:59] Epoch 1 | Step 5040 | Loss: 0.2976 | LM: 0.2901 | LB: 1.1150 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.00e-05 |
| [2026-04-25 21:09:06] Epoch 1 | Step 5050 | Loss: 0.2976 | LM: 0.2902 | LB: 1.1150 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.00e-05 |
| [2026-04-25 21:09:13] Epoch 1 | Step 5060 | Loss: 0.2976 | LM: 0.2901 | LB: 1.1149 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.411 | LR: 1.00e-05 |
| [2026-04-25 21:09:20] Epoch 1 | Step 5070 | Loss: 0.2976 | LM: 0.2900 | LB: 1.1149 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:09:27] Epoch 1 | Step 5080 | Loss: 0.2976 | LM: 0.2900 | LB: 1.1149 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:09:35] Epoch 1 | Step 5090 | Loss: 0.2976 | LM: 0.2900 | LB: 1.1148 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:09:42] Epoch 1 | Step 5100 | Loss: 0.2975 | LM: 0.2899 | LB: 1.1148 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:09:49] Epoch 1 | Step 5110 | Loss: 0.2975 | LM: 0.2900 | LB: 1.1147 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:09:56] Epoch 1 | Step 5120 | Loss: 0.2975 | LM: 0.2900 | LB: 1.1147 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:10:03] Epoch 1 | Step 5130 | Loss: 0.2974 | LM: 0.2899 | LB: 1.1147 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.436/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:10:10] Epoch 1 | Step 5140 | Loss: 0.2974 | LM: 0.2899 | LB: 1.1146 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:10:17] Epoch 1 | Step 5150 | Loss: 0.2974 | LM: 0.2899 | LB: 1.1146 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:10:24] Epoch 1 | Step 5160 | Loss: 0.2973 | LM: 0.2898 | LB: 1.1145 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:10:31] Epoch 1 | Step 5170 | Loss: 0.2972 | LM: 0.2898 | LB: 1.1145 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:10:38] Epoch 1 | Step 5180 | Loss: 0.2972 | LM: 0.2898 | LB: 1.1145 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:10:45] Epoch 1 | Step 5190 | Loss: 0.2972 | LM: 0.2898 | LB: 1.1144 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:10:52] Epoch 1 | Step 5200 | Loss: 0.2972 | LM: 0.2898 | LB: 1.1144 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:10:59] Epoch 1 | Step 5210 | Loss: 0.2972 | LM: 0.2897 | LB: 1.1143 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:11:06] Epoch 1 | Step 5220 | Loss: 0.2972 | LM: 0.2896 | LB: 1.1143 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:11:13] Epoch 1 | Step 5230 | Loss: 0.2972 | LM: 0.2895 | LB: 1.1143 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:11:20] Epoch 1 | Step 5240 | Loss: 0.2972 | LM: 0.2894 | LB: 1.1142 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:11:28] Epoch 1 | Step 5250 | Loss: 0.2972 | LM: 0.2895 | LB: 1.1142 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:11:35] Epoch 1 | Step 5260 | Loss: 0.2971 | LM: 0.2895 | LB: 1.1142 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:11:42] Epoch 1 | Step 5270 | Loss: 0.2971 | LM: 0.2894 | LB: 1.1142 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:11:49] Epoch 1 | Step 5280 | Loss: 0.2970 | LM: 0.2893 | LB: 1.1141 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:11:56] Epoch 1 | Step 5290 | Loss: 0.2970 | LM: 0.2892 | LB: 1.1141 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:12:03] Epoch 1 | Step 5300 | Loss: 0.2970 | LM: 0.2891 | LB: 1.1141 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:12:10] Epoch 1 | Step 5310 | Loss: 0.2970 | LM: 0.2892 | LB: 1.1141 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:12:17] Epoch 1 | Step 5320 | Loss: 0.2970 | LM: 0.2891 | LB: 1.1140 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.410 | LR: 1.00e-05 |
| [2026-04-25 21:12:24] Epoch 1 | Step 5330 | Loss: 0.2970 | LM: 0.2891 | LB: 1.1140 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:12:31] Epoch 1 | Step 5340 | Loss: 0.2969 | LM: 0.2891 | LB: 1.1140 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:12:38] Epoch 1 | Step 5350 | Loss: 0.2969 | LM: 0.2890 | LB: 1.1139 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:12:45] Epoch 1 | Step 5360 | Loss: 0.2969 | LM: 0.2890 | LB: 1.1139 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:12:52] Epoch 1 | Step 5370 | Loss: 0.2969 | LM: 0.2889 | LB: 1.1138 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:12:59] Epoch 1 | Step 5380 | Loss: 0.2968 | LM: 0.2888 | LB: 1.1137 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:13:06] Epoch 1 | Step 5390 | Loss: 0.2967 | LM: 0.2887 | LB: 1.1137 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:13:14] Epoch 1 | Step 5400 | Loss: 0.2967 | LM: 0.2887 | LB: 1.1137 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:13:21] Epoch 1 | Step 5410 | Loss: 0.2967 | LM: 0.2886 | LB: 1.1137 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:13:28] Epoch 1 | Step 5420 | Loss: 0.2966 | LM: 0.2885 | LB: 1.1137 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.435/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:13:35] Epoch 1 | Step 5430 | Loss: 0.2966 | LM: 0.2885 | LB: 1.1136 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:13:42] Epoch 1 | Step 5440 | Loss: 0.2966 | LM: 0.2885 | LB: 1.1136 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:13:49] Epoch 1 | Step 5450 | Loss: 0.2967 | LM: 0.2884 | LB: 1.1135 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:13:56] Epoch 1 | Step 5460 | Loss: 0.2966 | LM: 0.2884 | LB: 1.1135 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:14:03] Epoch 1 | Step 5470 | Loss: 0.2966 | LM: 0.2884 | LB: 1.1135 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:14:10] Epoch 1 | Step 5480 | Loss: 0.2966 | LM: 0.2882 | LB: 1.1134 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:14:17] Epoch 1 | Step 5490 | Loss: 0.2966 | LM: 0.2882 | LB: 1.1134 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:14:24] Epoch 1 | Step 5500 | Loss: 0.2966 | LM: 0.2884 | LB: 1.1133 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:14:31] Epoch 1 | Step 5510 | Loss: 0.2966 | LM: 0.2885 | LB: 1.1133 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:14:38] Epoch 1 | Step 5520 | Loss: 0.2966 | LM: 0.2884 | LB: 1.1133 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:14:45] Epoch 1 | Step 5530 | Loss: 0.2965 | LM: 0.2884 | LB: 1.1132 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:14:52] Epoch 1 | Step 5540 | Loss: 0.2965 | LM: 0.2882 | LB: 1.1132 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:14:59] Epoch 1 | Step 5550 | Loss: 0.2964 | LM: 0.2882 | LB: 1.1131 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:15:07] Epoch 1 | Step 5560 | Loss: 0.2964 | LM: 0.2883 | LB: 1.1131 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:15:14] Epoch 1 | Step 5570 | Loss: 0.2965 | LM: 0.2883 | LB: 1.1131 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:15:21] Epoch 1 | Step 5580 | Loss: 0.2965 | LM: 0.2882 | LB: 1.1131 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.409 | LR: 1.00e-05 |
| [2026-04-25 21:15:28] Epoch 1 | Step 5590 | Loss: 0.2964 | LM: 0.2883 | LB: 1.1131 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:15:35] Epoch 1 | Step 5600 | Loss: 0.2965 | LM: 0.2882 | LB: 1.1130 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:15:42] Epoch 1 | Step 5610 | Loss: 0.2965 | LM: 0.2883 | LB: 1.1130 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:15:49] Epoch 1 | Step 5620 | Loss: 0.2964 | LM: 0.2882 | LB: 1.1130 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:15:56] Epoch 1 | Step 5630 | Loss: 0.2964 | LM: 0.2882 | LB: 1.1130 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:16:03] Epoch 1 | Step 5640 | Loss: 0.2964 | LM: 0.2884 | LB: 1.1129 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:16:10] Epoch 1 | Step 5650 | Loss: 0.2964 | LM: 0.2884 | LB: 1.1129 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:16:17] Epoch 1 | Step 5660 | Loss: 0.2964 | LM: 0.2883 | LB: 1.1129 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:16:24] Epoch 1 | Step 5670 | Loss: 0.2964 | LM: 0.2883 | LB: 1.1129 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:16:31] Epoch 1 | Step 5680 | Loss: 0.2963 | LM: 0.2882 | LB: 1.1128 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:16:38] Epoch 1 | Step 5690 | Loss: 0.2963 | LM: 0.2883 | LB: 1.1128 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:16:45] Epoch 1 | Step 5700 | Loss: 0.2963 | LM: 0.2883 | LB: 1.1127 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:16:52] Epoch 1 | Step 5710 | Loss: 0.2963 | LM: 0.2883 | LB: 1.1127 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:17:00] Epoch 1 | Step 5720 | Loss: 0.2963 | LM: 0.2883 | LB: 1.1127 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:17:07] Epoch 1 | Step 5730 | Loss: 0.2963 | LM: 0.2885 | LB: 1.1127 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:17:14] Epoch 1 | Step 5740 | Loss: 0.2963 | LM: 0.2884 | LB: 1.1127 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:17:21] Epoch 1 | Step 5750 | Loss: 0.2963 | LM: 0.2884 | LB: 1.1126 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:17:28] Epoch 1 | Step 5760 | Loss: 0.2963 | LM: 0.2883 | LB: 1.1126 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:17:35] Epoch 1 | Step 5770 | Loss: 0.2964 | LM: 0.2884 | LB: 1.1126 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.434/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:17:42] Epoch 1 | Step 5780 | Loss: 0.2963 | LM: 0.2884 | LB: 1.1125 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:17:49] Epoch 1 | Step 5790 | Loss: 0.2964 | LM: 0.2882 | LB: 1.1125 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.433/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:17:56] Epoch 1 | Step 5800 | Loss: 0.2964 | LM: 0.2883 | LB: 1.1125 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.433/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:18:03] Epoch 1 | Step 5810 | Loss: 0.2964 | LM: 0.2884 | LB: 1.1124 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.433/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:18:10] Epoch 1 | Step 5820 | Loss: 0.2963 | LM: 0.2882 | LB: 1.1124 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.433/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:18:17] Epoch 1 | Step 5830 | Loss: 0.2963 | LM: 0.2882 | LB: 1.1124 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:18:24] Epoch 1 | Step 5840 | Loss: 0.2962 | LM: 0.2882 | LB: 1.1124 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:18:31] Epoch 1 | Step 5850 | Loss: 0.2963 | LM: 0.2883 | LB: 1.1124 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:18:38] Epoch 1 | Step 5860 | Loss: 0.2962 | LM: 0.2882 | LB: 1.1123 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:18:45] Epoch 1 | Step 5870 | Loss: 0.2962 | LM: 0.2881 | LB: 1.1123 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:18:52] Epoch 1 | Step 5880 | Loss: 0.2963 | LM: 0.2883 | LB: 1.1123 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:18:59] Epoch 1 | Step 5890 | Loss: 0.2962 | LM: 0.2882 | LB: 1.1123 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:19:06] Epoch 1 | Step 5900 | Loss: 0.2962 | LM: 0.2881 | LB: 1.1122 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:19:13] Epoch 1 | Step 5910 | Loss: 0.2962 | LM: 0.2882 | LB: 1.1122 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:19:20] Epoch 1 | Step 5920 | Loss: 0.2961 | LM: 0.2881 | LB: 1.1122 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:19:27] Epoch 1 | Step 5930 | Loss: 0.2962 | LM: 0.2881 | LB: 1.1122 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:19:34] Epoch 1 | Step 5940 | Loss: 0.2961 | LM: 0.2882 | LB: 1.1122 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.408 | LR: 1.00e-05 |
| [2026-04-25 21:19:41] Epoch 1 | Step 5950 | Loss: 0.2961 | LM: 0.2881 | LB: 1.1121 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:19:48] Epoch 1 | Step 5960 | Loss: 0.2961 | LM: 0.2881 | LB: 1.1121 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:19:55] Epoch 1 | Step 5970 | Loss: 0.2962 | LM: 0.2881 | LB: 1.1121 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:20:02] Epoch 1 | Step 5980 | Loss: 0.2962 | LM: 0.2882 | LB: 1.1121 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:20:09] Epoch 1 | Step 5990 | Loss: 0.2962 | LM: 0.2883 | LB: 1.1121 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:20:17] Epoch 1 | Step 6000 | Loss: 0.2962 | LM: 0.2882 | LB: 1.1121 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:20:17] Validation | Batch 10/42 | Loss: 0.2761 | LM_LOSS: 0.2652 | LB_LOSS: 1.0908 |
| [2026-04-25 21:20:19] Validation | Batch 20/42 | Loss: 0.2970 | LM_LOSS: 0.2861 | LB_LOSS: 1.0943 |
| [2026-04-25 21:20:20] Validation | Batch 30/42 | Loss: 0.2894 | LM_LOSS: 0.2785 | LB_LOSS: 1.0916 |
| [2026-04-25 21:20:21] Validation | Batch 40/42 | Loss: 0.2931 | LM_LOSS: 0.2822 | LB_LOSS: 1.0908 |
| [2026-04-25 21:20:21] Validation | Batch 42/42 | Loss: 0.2926 | LM_LOSS: 0.2817 | LB_LOSS: 1.0911 |
| [2026-04-25 21:20:21] Validation | Loss: 0.2926 | LM_LOSS: 0.2817 | LB_LOSS: 1.0911 | PPL: 1.32 | Time: 4.74s |
| [2026-04-25 21:20:24] New best model saved! Val loss: 0.2926 |
| [2026-04-25 21:20:31] Epoch 1 | Step 6010 | Loss: 0.2962 | LM: 0.2881 | LB: 1.1120 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:20:38] Epoch 1 | Step 6020 | Loss: 0.2962 | LM: 0.2880 | LB: 1.1120 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:20:45] Epoch 1 | Step 6030 | Loss: 0.2962 | LM: 0.2880 | LB: 1.1119 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:20:52] Epoch 1 | Step 6040 | Loss: 0.2962 | LM: 0.2880 | LB: 1.1119 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:20:59] Epoch 1 | Step 6050 | Loss: 0.2963 | LM: 0.2881 | LB: 1.1119 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:21:06] Epoch 1 | Step 6060 | Loss: 0.2963 | LM: 0.2881 | LB: 1.1119 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:21:13] Epoch 1 | Step 6070 | Loss: 0.2962 | LM: 0.2880 | LB: 1.1119 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:21:20] Epoch 1 | Step 6080 | Loss: 0.2962 | LM: 0.2879 | LB: 1.1118 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:21:27] Epoch 1 | Step 6090 | Loss: 0.2962 | LM: 0.2879 | LB: 1.1118 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:21:34] Epoch 1 | Step 6100 | Loss: 0.2963 | LM: 0.2880 | LB: 1.1117 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:21:41] Epoch 1 | Step 6110 | Loss: 0.2963 | LM: 0.2880 | LB: 1.1117 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:21:48] Epoch 1 | Step 6120 | Loss: 0.2963 | LM: 0.2880 | LB: 1.1117 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:21:55] Epoch 1 | Step 6130 | Loss: 0.2962 | LM: 0.2879 | LB: 1.1116 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:22:02] Epoch 1 | Step 6140 | Loss: 0.2961 | LM: 0.2878 | LB: 1.1116 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:22:09] Epoch 1 | Step 6150 | Loss: 0.2961 | LM: 0.2878 | LB: 1.1116 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:22:17] Epoch 1 | Step 6160 | Loss: 0.2960 | LM: 0.2877 | LB: 1.1116 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:22:24] Epoch 1 | Step 6170 | Loss: 0.2961 | LM: 0.2877 | LB: 1.1116 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:22:31] Epoch 1 | Step 6180 | Loss: 0.2960 | LM: 0.2878 | LB: 1.1116 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:22:38] Epoch 1 | Step 6190 | Loss: 0.2959 | LM: 0.2878 | LB: 1.1116 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:22:45] Epoch 1 | Step 6200 | Loss: 0.2959 | LM: 0.2877 | LB: 1.1116 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:22:52] Epoch 1 | Step 6210 | Loss: 0.2959 | LM: 0.2876 | LB: 1.1115 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:22:59] Epoch 1 | Step 6220 | Loss: 0.2960 | LM: 0.2877 | LB: 1.1115 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:23:06] Epoch 1 | Step 6230 | Loss: 0.2959 | LM: 0.2877 | LB: 1.1115 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:23:13] Epoch 1 | Step 6240 | Loss: 0.2959 | LM: 0.2877 | LB: 1.1115 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.433/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:23:20] Epoch 1 | Step 6250 | Loss: 0.2959 | LM: 0.2878 | LB: 1.1114 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:23:27] Epoch 1 | Step 6260 | Loss: 0.2958 | LM: 0.2878 | LB: 1.1114 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:23:34] Epoch 1 | Step 6270 | Loss: 0.2958 | LM: 0.2877 | LB: 1.1114 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:23:41] Epoch 1 | Step 6280 | Loss: 0.2957 | LM: 0.2875 | LB: 1.1114 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:23:48] Epoch 1 | Step 6290 | Loss: 0.2957 | LM: 0.2876 | LB: 1.1113 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:23:55] Epoch 1 | Step 6300 | Loss: 0.2957 | LM: 0.2876 | LB: 1.1113 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:24:02] Epoch 1 | Step 6310 | Loss: 0.2957 | LM: 0.2876 | LB: 1.1113 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.407 | LR: 1.00e-05 |
| [2026-04-25 21:24:09] Epoch 1 | Step 6320 | Loss: 0.2957 | LM: 0.2876 | LB: 1.1112 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:24:16] Epoch 1 | Step 6330 | Loss: 0.2958 | LM: 0.2877 | LB: 1.1112 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:24:23] Epoch 1 | Step 6340 | Loss: 0.2958 | LM: 0.2877 | LB: 1.1112 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:24:30] Epoch 1 | Step 6350 | Loss: 0.2958 | LM: 0.2878 | LB: 1.1112 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:24:37] Epoch 1 | Step 6360 | Loss: 0.2958 | LM: 0.2879 | LB: 1.1111 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:24:44] Epoch 1 | Step 6370 | Loss: 0.2958 | LM: 0.2879 | LB: 1.1111 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:24:51] Epoch 1 | Step 6380 | Loss: 0.2958 | LM: 0.2878 | LB: 1.1111 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:24:59] Epoch 1 | Step 6390 | Loss: 0.2958 | LM: 0.2877 | LB: 1.1111 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:25:06] Epoch 1 | Step 6400 | Loss: 0.2958 | LM: 0.2877 | LB: 1.1110 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:25:13] Epoch 1 | Step 6410 | Loss: 0.2957 | LM: 0.2876 | LB: 1.1110 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:25:20] Epoch 1 | Step 6420 | Loss: 0.2957 | LM: 0.2876 | LB: 1.1110 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:25:27] Epoch 1 | Step 6430 | Loss: 0.2957 | LM: 0.2876 | LB: 1.1110 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:25:34] Epoch 1 | Step 6440 | Loss: 0.2957 | LM: 0.2875 | LB: 1.1110 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:25:41] Epoch 1 | Step 6450 | Loss: 0.2957 | LM: 0.2875 | LB: 1.1109 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:25:48] Epoch 1 | Step 6460 | Loss: 0.2956 | LM: 0.2874 | LB: 1.1109 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:25:55] Epoch 1 | Step 6470 | Loss: 0.2956 | LM: 0.2873 | LB: 1.1109 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:26:02] Epoch 1 | Step 6480 | Loss: 0.2956 | LM: 0.2873 | LB: 1.1108 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:26:09] Epoch 1 | Step 6490 | Loss: 0.2957 | LM: 0.2874 | LB: 1.1108 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:26:16] Epoch 1 | Step 6500 | Loss: 0.2956 | LM: 0.2873 | LB: 1.1108 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:26:24] Epoch 1 | Step 6510 | Loss: 0.2956 | LM: 0.2873 | LB: 1.1108 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:26:31] Epoch 1 | Step 6520 | Loss: 0.2955 | LM: 0.2874 | LB: 1.1107 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:26:38] Epoch 1 | Step 6530 | Loss: 0.2954 | LM: 0.2872 | LB: 1.1107 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:26:45] Epoch 1 | Step 6540 | Loss: 0.2954 | LM: 0.2873 | LB: 1.1107 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:26:52] Epoch 1 | Step 6550 | Loss: 0.2954 | LM: 0.2871 | LB: 1.1107 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:26:59] Epoch 1 | Step 6560 | Loss: 0.2953 | LM: 0.2870 | LB: 1.1107 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:27:06] Epoch 1 | Step 6570 | Loss: 0.2953 | LM: 0.2871 | LB: 1.1106 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:27:13] Epoch 1 | Step 6580 | Loss: 0.2954 | LM: 0.2872 | LB: 1.1106 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:27:20] Epoch 1 | Step 6590 | Loss: 0.2953 | LM: 0.2872 | LB: 1.1106 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:27:27] Epoch 1 | Step 6600 | Loss: 0.2953 | LM: 0.2871 | LB: 1.1106 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:27:34] Epoch 1 | Step 6610 | Loss: 0.2953 | LM: 0.2870 | LB: 1.1106 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:27:41] Epoch 1 | Step 6620 | Loss: 0.2953 | LM: 0.2869 | LB: 1.1105 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:27:48] Epoch 1 | Step 6630 | Loss: 0.2953 | LM: 0.2868 | LB: 1.1105 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:27:56] Epoch 1 | Step 6640 | Loss: 0.2953 | LM: 0.2869 | LB: 1.1105 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:28:03] Epoch 1 | Step 6650 | Loss: 0.2953 | LM: 0.2869 | LB: 1.1105 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:28:10] Epoch 1 | Step 6660 | Loss: 0.2952 | LM: 0.2868 | LB: 1.1104 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:28:17] Epoch 1 | Step 6670 | Loss: 0.2952 | LM: 0.2867 | LB: 1.1104 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.432/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:28:24] Epoch 1 | Step 6680 | Loss: 0.2952 | LM: 0.2866 | LB: 1.1104 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:28:31] Epoch 1 | Step 6690 | Loss: 0.2952 | LM: 0.2866 | LB: 1.1103 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:28:38] Epoch 1 | Step 6700 | Loss: 0.2952 | LM: 0.2865 | LB: 1.1103 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.406 | LR: 1.00e-05 |
| [2026-04-25 21:28:45] Epoch 1 | Step 6710 | Loss: 0.2952 | LM: 0.2865 | LB: 1.1103 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:28:52] Epoch 1 | Step 6720 | Loss: 0.2952 | LM: 0.2865 | LB: 1.1103 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:28:59] Epoch 1 | Step 6730 | Loss: 0.2952 | LM: 0.2865 | LB: 1.1102 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:29:07] Epoch 1 | Step 6740 | Loss: 0.2952 | LM: 0.2865 | LB: 1.1102 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:29:14] Epoch 1 | Step 6750 | Loss: 0.2951 | LM: 0.2865 | LB: 1.1102 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:29:21] Epoch 1 | Step 6760 | Loss: 0.2952 | LM: 0.2866 | LB: 1.1102 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:29:28] Epoch 1 | Step 6770 | Loss: 0.2951 | LM: 0.2865 | LB: 1.1102 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:29:35] Epoch 1 | Step 6780 | Loss: 0.2951 | LM: 0.2865 | LB: 1.1101 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:29:42] Epoch 1 | Step 6790 | Loss: 0.2952 | LM: 0.2865 | LB: 1.1101 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:29:49] Epoch 1 | Step 6800 | Loss: 0.2952 | LM: 0.2865 | LB: 1.1101 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:29:56] Epoch 1 | Step 6810 | Loss: 0.2953 | LM: 0.2864 | LB: 1.1101 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:30:03] Epoch 1 | Step 6820 | Loss: 0.2953 | LM: 0.2864 | LB: 1.1101 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:30:10] Epoch 1 | Step 6830 | Loss: 0.2954 | LM: 0.2865 | LB: 1.1101 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:30:18] Epoch 1 | Step 6840 | Loss: 0.2954 | LM: 0.2865 | LB: 1.1100 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:30:25] Epoch 1 | Step 6850 | Loss: 0.2954 | LM: 0.2865 | LB: 1.1100 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:30:32] Epoch 1 | Step 6860 | Loss: 0.2954 | LM: 0.2865 | LB: 1.1100 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:30:39] Epoch 1 | Step 6870 | Loss: 0.2954 | LM: 0.2865 | LB: 1.1100 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:30:46] Epoch 1 | Step 6880 | Loss: 0.2954 | LM: 0.2864 | LB: 1.1099 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:30:53] Epoch 1 | Step 6890 | Loss: 0.2954 | LM: 0.2864 | LB: 1.1099 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:31:00] Epoch 1 | Step 6900 | Loss: 0.2954 | LM: 0.2864 | LB: 1.1099 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:31:07] Epoch 1 | Step 6910 | Loss: 0.2954 | LM: 0.2863 | LB: 1.1099 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:31:14] Epoch 1 | Step 6920 | Loss: 0.2953 | LM: 0.2863 | LB: 1.1098 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:31:22] Epoch 1 | Step 6930 | Loss: 0.2953 | LM: 0.2863 | LB: 1.1098 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:31:29] Epoch 1 | Step 6940 | Loss: 0.2953 | LM: 0.2862 | LB: 1.1098 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:31:36] Epoch 1 | Step 6950 | Loss: 0.2952 | LM: 0.2862 | LB: 1.1098 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:31:43] Epoch 1 | Step 6960 | Loss: 0.2953 | LM: 0.2862 | LB: 1.1098 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:31:50] Epoch 1 | Step 6970 | Loss: 0.2952 | LM: 0.2862 | LB: 1.1098 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:31:57] Epoch 1 | Step 6980 | Loss: 0.2952 | LM: 0.2863 | LB: 1.1098 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:32:04] Epoch 1 | Step 6990 | Loss: 0.2951 | LM: 0.2862 | LB: 1.1097 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:32:11] Epoch 1 | Step 7000 | Loss: 0.2951 | LM: 0.2863 | LB: 1.1097 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:32:18] Epoch 1 | Step 7010 | Loss: 0.2951 | LM: 0.2862 | LB: 1.1097 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:32:25] Epoch 1 | Step 7020 | Loss: 0.2951 | LM: 0.2864 | LB: 1.1097 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:32:32] Epoch 1 | Step 7030 | Loss: 0.2951 | LM: 0.2863 | LB: 1.1097 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:32:39] Epoch 1 | Step 7040 | Loss: 0.2951 | LM: 0.2863 | LB: 1.1097 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:32:47] Epoch 1 | Step 7050 | Loss: 0.2950 | LM: 0.2863 | LB: 1.1097 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:32:54] Epoch 1 | Step 7060 | Loss: 0.2950 | LM: 0.2863 | LB: 1.1097 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:33:01] Epoch 1 | Step 7070 | Loss: 0.2950 | LM: 0.2863 | LB: 1.1097 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:33:08] Epoch 1 | Step 7080 | Loss: 0.2950 | LM: 0.2863 | LB: 1.1096 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:33:15] Epoch 1 | Step 7090 | Loss: 0.2950 | LM: 0.2865 | LB: 1.1096 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:33:22] Epoch 1 | Step 7100 | Loss: 0.2950 | LM: 0.2862 | LB: 1.1096 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:33:29] Epoch 1 | Step 7110 | Loss: 0.2949 | LM: 0.2862 | LB: 1.1096 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:33:36] Epoch 1 | Step 7120 | Loss: 0.2950 | LM: 0.2861 | LB: 1.1096 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:33:43] Epoch 1 | Step 7130 | Loss: 0.2950 | LM: 0.2861 | LB: 1.1096 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:33:51] Epoch 1 | Step 7140 | Loss: 0.2949 | LM: 0.2861 | LB: 1.1096 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:33:58] Epoch 1 | Step 7150 | Loss: 0.2950 | LM: 0.2860 | LB: 1.1096 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:34:05] Epoch 1 | Step 7160 | Loss: 0.2949 | LM: 0.2859 | LB: 1.1095 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:34:12] Epoch 1 | Step 7170 | Loss: 0.2949 | LM: 0.2859 | LB: 1.1095 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:34:19] Epoch 1 | Step 7180 | Loss: 0.2949 | LM: 0.2859 | LB: 1.1095 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.405 | LR: 1.00e-05 |
| [2026-04-25 21:34:26] Epoch 1 | Step 7190 | Loss: 0.2950 | LM: 0.2860 | LB: 1.1095 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:34:33] Epoch 1 | Step 7200 | Loss: 0.2949 | LM: 0.2859 | LB: 1.1095 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:34:40] Epoch 1 | Step 7210 | Loss: 0.2949 | LM: 0.2858 | LB: 1.1095 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:34:47] Epoch 1 | Step 7220 | Loss: 0.2949 | LM: 0.2859 | LB: 1.1095 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:34:54] Epoch 1 | Step 7230 | Loss: 0.2949 | LM: 0.2859 | LB: 1.1094 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:35:01] Epoch 1 | Step 7240 | Loss: 0.2949 | LM: 0.2858 | LB: 1.1094 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:35:09] Epoch 1 | Step 7250 | Loss: 0.2949 | LM: 0.2858 | LB: 1.1094 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.431/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:35:16] Epoch 1 | Step 7260 | Loss: 0.2949 | LM: 0.2857 | LB: 1.1094 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:35:23] Epoch 1 | Step 7270 | Loss: 0.2949 | LM: 0.2858 | LB: 1.1093 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:35:30] Epoch 1 | Step 7280 | Loss: 0.2950 | LM: 0.2858 | LB: 1.1093 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:35:37] Epoch 1 | Step 7290 | Loss: 0.2949 | LM: 0.2858 | LB: 1.1093 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:35:44] Epoch 1 | Step 7300 | Loss: 0.2949 | LM: 0.2858 | LB: 1.1093 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:35:52] Epoch 1 | Step 7310 | Loss: 0.2949 | LM: 0.2857 | LB: 1.1093 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:35:59] Epoch 1 | Step 7320 | Loss: 0.2948 | LM: 0.2858 | LB: 1.1093 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:36:06] Epoch 1 | Step 7330 | Loss: 0.2948 | LM: 0.2858 | LB: 1.1092 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:36:13] Epoch 1 | Step 7340 | Loss: 0.2949 | LM: 0.2859 | LB: 1.1092 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:36:20] Epoch 1 | Step 7350 | Loss: 0.2949 | LM: 0.2860 | LB: 1.1092 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:36:27] Epoch 1 | Step 7360 | Loss: 0.2949 | LM: 0.2859 | LB: 1.1092 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:36:34] Epoch 1 | Step 7370 | Loss: 0.2948 | LM: 0.2858 | LB: 1.1091 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:36:41] Epoch 1 | Step 7380 | Loss: 0.2948 | LM: 0.2858 | LB: 1.1091 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:36:48] Epoch 1 | Step 7390 | Loss: 0.2947 | LM: 0.2857 | LB: 1.1091 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:36:55] Epoch 1 | Step 7400 | Loss: 0.2947 | LM: 0.2857 | LB: 1.1091 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:37:03] Epoch 1 | Step 7410 | Loss: 0.2947 | LM: 0.2857 | LB: 1.1091 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:37:10] Epoch 1 | Step 7420 | Loss: 0.2948 | LM: 0.2857 | LB: 1.1091 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:37:17] Epoch 1 | Step 7430 | Loss: 0.2948 | LM: 0.2857 | LB: 1.1091 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:37:24] Epoch 1 | Step 7440 | Loss: 0.2948 | LM: 0.2857 | LB: 1.1090 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:37:31] Epoch 1 | Step 7450 | Loss: 0.2947 | LM: 0.2855 | LB: 1.1090 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:37:38] Epoch 1 | Step 7460 | Loss: 0.2947 | LM: 0.2855 | LB: 1.1090 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:37:45] Epoch 1 | Step 7470 | Loss: 0.2947 | LM: 0.2854 | LB: 1.1090 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:37:52] Epoch 1 | Step 7480 | Loss: 0.2947 | LM: 0.2853 | LB: 1.1090 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:37:59] Epoch 1 | Step 7490 | Loss: 0.2948 | LM: 0.2854 | LB: 1.1089 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:38:06] Epoch 1 | Step 7500 | Loss: 0.2948 | LM: 0.2854 | LB: 1.1089 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:38:13] Epoch 1 | Step 7510 | Loss: 0.2948 | LM: 0.2853 | LB: 1.1089 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:38:21] Epoch 1 | Step 7520 | Loss: 0.2948 | LM: 0.2853 | LB: 1.1089 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:38:28] Epoch 1 | Step 7530 | Loss: 0.2947 | LM: 0.2853 | LB: 1.1089 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:38:35] Epoch 1 | Step 7540 | Loss: 0.2947 | LM: 0.2852 | LB: 1.1089 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:38:42] Epoch 1 | Step 7550 | Loss: 0.2947 | LM: 0.2853 | LB: 1.1088 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:38:49] Epoch 1 | Step 7560 | Loss: 0.2947 | LM: 0.2852 | LB: 1.1088 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:38:56] Epoch 1 | Step 7570 | Loss: 0.2947 | LM: 0.2852 | LB: 1.1088 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:39:03] Epoch 1 | Step 7580 | Loss: 0.2947 | LM: 0.2852 | LB: 1.1088 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:39:10] Epoch 1 | Step 7590 | Loss: 0.2946 | LM: 0.2851 | LB: 1.1088 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:39:17] Epoch 1 | Step 7600 | Loss: 0.2946 | LM: 0.2852 | LB: 1.1088 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:39:24] Epoch 1 | Step 7610 | Loss: 0.2946 | LM: 0.2853 | LB: 1.1088 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:39:31] Epoch 1 | Step 7620 | Loss: 0.2945 | LM: 0.2852 | LB: 1.1087 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:39:38] Epoch 1 | Step 7630 | Loss: 0.2945 | LM: 0.2852 | LB: 1.1087 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:39:46] Epoch 1 | Step 7640 | Loss: 0.2945 | LM: 0.2851 | LB: 1.1087 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:39:53] Epoch 1 | Step 7650 | Loss: 0.2945 | LM: 0.2850 | LB: 1.1087 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:40:00] Epoch 1 | Step 7660 | Loss: 0.2944 | LM: 0.2850 | LB: 1.1087 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:40:07] Epoch 1 | Step 7670 | Loss: 0.2944 | LM: 0.2850 | LB: 1.1087 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:40:14] Epoch 1 | Step 7680 | Loss: 0.2943 | LM: 0.2850 | LB: 1.1086 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:40:21] Epoch 1 | Step 7690 | Loss: 0.2944 | LM: 0.2850 | LB: 1.1086 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:40:28] Epoch 1 | Step 7700 | Loss: 0.2943 | LM: 0.2849 | LB: 1.1086 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:40:35] Epoch 1 | Step 7710 | Loss: 0.2943 | LM: 0.2847 | LB: 1.1086 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:40:42] Epoch 1 | Step 7720 | Loss: 0.2944 | LM: 0.2848 | LB: 1.1086 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:40:49] Epoch 1 | Step 7730 | Loss: 0.2944 | LM: 0.2848 | LB: 1.1086 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.404 | LR: 1.00e-05 |
| [2026-04-25 21:40:56] Epoch 1 | Step 7740 | Loss: 0.2944 | LM: 0.2849 | LB: 1.1086 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:41:04] Epoch 1 | Step 7750 | Loss: 0.2944 | LM: 0.2850 | LB: 1.1086 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.430/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:41:11] Epoch 1 | Step 7760 | Loss: 0.2944 | LM: 0.2849 | LB: 1.1085 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:41:18] Epoch 1 | Step 7770 | Loss: 0.2944 | LM: 0.2848 | LB: 1.1085 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:41:25] Epoch 1 | Step 7780 | Loss: 0.2943 | LM: 0.2848 | LB: 1.1085 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:41:32] Epoch 1 | Step 7790 | Loss: 0.2943 | LM: 0.2848 | LB: 1.1085 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:41:39] Epoch 1 | Step 7800 | Loss: 0.2943 | LM: 0.2847 | LB: 1.1085 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.430/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:41:46] Epoch 1 | Step 7810 | Loss: 0.2944 | LM: 0.2847 | LB: 1.1084 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:41:53] Epoch 1 | Step 7820 | Loss: 0.2943 | LM: 0.2848 | LB: 1.1084 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:42:00] Epoch 1 | Step 7830 | Loss: 0.2943 | LM: 0.2848 | LB: 1.1084 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:42:07] Epoch 1 | Step 7840 | Loss: 0.2943 | LM: 0.2847 | LB: 1.1084 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:42:14] Epoch 1 | Step 7850 | Loss: 0.2942 | LM: 0.2845 | LB: 1.1084 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.430/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:42:21] Epoch 1 | Step 7860 | Loss: 0.2942 | LM: 0.2845 | LB: 1.1083 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:42:29] Epoch 1 | Step 7870 | Loss: 0.2941 | LM: 0.2844 | LB: 1.1083 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:42:36] Epoch 1 | Step 7880 | Loss: 0.2942 | LM: 0.2845 | LB: 1.1083 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:42:43] Epoch 1 | Step 7890 | Loss: 0.2942 | LM: 0.2845 | LB: 1.1083 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:42:50] Epoch 1 | Step 7900 | Loss: 0.2942 | LM: 0.2845 | LB: 1.1083 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:42:57] Epoch 1 | Step 7910 | Loss: 0.2942 | LM: 0.2846 | LB: 1.1082 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:43:04] Epoch 1 | Step 7920 | Loss: 0.2942 | LM: 0.2846 | LB: 1.1082 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:43:11] Epoch 1 | Step 7930 | Loss: 0.2942 | LM: 0.2846 | LB: 1.1082 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:43:18] Epoch 1 | Step 7940 | Loss: 0.2943 | LM: 0.2846 | LB: 1.1082 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:43:25] Epoch 1 | Step 7950 | Loss: 0.2943 | LM: 0.2847 | LB: 1.1082 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:43:33] Epoch 1 | Step 7960 | Loss: 0.2943 | LM: 0.2847 | LB: 1.1082 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:43:40] Epoch 1 | Step 7970 | Loss: 0.2943 | LM: 0.2847 | LB: 1.1082 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:43:47] Epoch 1 | Step 7980 | Loss: 0.2943 | LM: 0.2847 | LB: 1.1082 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:43:54] Epoch 1 | Step 7990 | Loss: 0.2942 | LM: 0.2847 | LB: 1.1082 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:44:01] Epoch 1 | Step 8000 | Loss: 0.2942 | LM: 0.2846 | LB: 1.1081 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:44:02] Validation | Batch 10/42 | Loss: 0.2754 | LM_LOSS: 0.2645 | LB_LOSS: 1.0908 |
| [2026-04-25 21:44:03] Validation | Batch 20/42 | Loss: 0.2965 | LM_LOSS: 0.2855 | LB_LOSS: 1.0943 |
| [2026-04-25 21:44:04] Validation | Batch 30/42 | Loss: 0.2888 | LM_LOSS: 0.2779 | LB_LOSS: 1.0916 |
| [2026-04-25 21:44:05] Validation | Batch 40/42 | Loss: 0.2926 | LM_LOSS: 0.2817 | LB_LOSS: 1.0908 |
| [2026-04-25 21:44:06] Validation | Batch 42/42 | Loss: 0.2922 | LM_LOSS: 0.2813 | LB_LOSS: 1.0911 |
| [2026-04-25 21:44:06] Validation | Loss: 0.2922 | LM_LOSS: 0.2813 | LB_LOSS: 1.0911 | PPL: 1.32 | Time: 4.74s |
| [2026-04-25 21:44:09] New best model saved! Val loss: 0.2922 |
| [2026-04-25 21:44:16] Epoch 1 | Step 8010 | Loss: 0.2942 | LM: 0.2845 | LB: 1.1081 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:44:23] Epoch 1 | Step 8020 | Loss: 0.2941 | LM: 0.2844 | LB: 1.1081 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:44:30] Epoch 1 | Step 8030 | Loss: 0.2941 | LM: 0.2844 | LB: 1.1081 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:44:38] Epoch 1 | Step 8040 | Loss: 0.2942 | LM: 0.2843 | LB: 1.1081 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:44:45] Epoch 1 | Step 8050 | Loss: 0.2941 | LM: 0.2842 | LB: 1.1081 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:44:52] Epoch 1 | Step 8060 | Loss: 0.2941 | LM: 0.2842 | LB: 1.1081 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:44:59] Epoch 1 | Step 8070 | Loss: 0.2941 | LM: 0.2841 | LB: 1.1081 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:45:06] Epoch 1 | Step 8080 | Loss: 0.2941 | LM: 0.2842 | LB: 1.1081 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:45:13] Epoch 1 | Step 8090 | Loss: 0.2941 | LM: 0.2841 | LB: 1.1081 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:45:20] Epoch 1 | Step 8100 | Loss: 0.2940 | LM: 0.2841 | LB: 1.1081 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:45:27] Epoch 1 | Step 8110 | Loss: 0.2941 | LM: 0.2841 | LB: 1.1080 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:45:34] Epoch 1 | Step 8120 | Loss: 0.2941 | LM: 0.2841 | LB: 1.1080 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:45:41] Epoch 1 | Step 8130 | Loss: 0.2941 | LM: 0.2842 | LB: 1.1080 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:45:48] Epoch 1 | Step 8140 | Loss: 0.2941 | LM: 0.2842 | LB: 1.1080 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:45:56] Epoch 1 | Step 8150 | Loss: 0.2941 | LM: 0.2841 | LB: 1.1080 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:46:03] Epoch 1 | Step 8160 | Loss: 0.2940 | LM: 0.2840 | LB: 1.1080 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:46:10] Epoch 1 | Step 8170 | Loss: 0.2940 | LM: 0.2840 | LB: 1.1080 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:46:17] Epoch 1 | Step 8180 | Loss: 0.2940 | LM: 0.2841 | LB: 1.1079 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:46:24] Epoch 1 | Step 8190 | Loss: 0.2940 | LM: 0.2841 | LB: 1.1079 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:46:31] Epoch 1 | Step 8200 | Loss: 0.2940 | LM: 0.2842 | LB: 1.1079 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:46:38] Epoch 1 | Step 8210 | Loss: 0.2940 | LM: 0.2841 | LB: 1.1079 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:46:45] Epoch 1 | Step 8220 | Loss: 0.2940 | LM: 0.2841 | LB: 1.1079 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:46:52] Epoch 1 | Step 8230 | Loss: 0.2940 | LM: 0.2842 | LB: 1.1079 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:47:00] Epoch 1 | Step 8240 | Loss: 0.2940 | LM: 0.2842 | LB: 1.1078 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:47:07] Epoch 1 | Step 8250 | Loss: 0.2940 | LM: 0.2842 | LB: 1.1078 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:47:14] Epoch 1 | Step 8260 | Loss: 0.2941 | LM: 0.2842 | LB: 1.1078 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:47:21] Epoch 1 | Step 8270 | Loss: 0.2941 | LM: 0.2842 | LB: 1.1078 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:47:28] Epoch 1 | Step 8280 | Loss: 0.2941 | LM: 0.2841 | LB: 1.1078 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:47:35] Epoch 1 | Step 8290 | Loss: 0.2942 | LM: 0.2841 | LB: 1.1078 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:47:42] Epoch 1 | Step 8300 | Loss: 0.2941 | LM: 0.2840 | LB: 1.1077 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:47:49] Epoch 1 | Step 8310 | Loss: 0.2941 | LM: 0.2841 | LB: 1.1077 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:47:56] Epoch 1 | Step 8320 | Loss: 0.2941 | LM: 0.2840 | LB: 1.1077 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:48:04] Epoch 1 | Step 8330 | Loss: 0.2941 | LM: 0.2841 | LB: 1.1077 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.403 | LR: 1.00e-05 |
| [2026-04-25 21:48:11] Epoch 1 | Step 8340 | Loss: 0.2941 | LM: 0.2842 | LB: 1.1077 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:48:18] Epoch 1 | Step 8350 | Loss: 0.2941 | LM: 0.2842 | LB: 1.1077 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:48:25] Epoch 1 | Step 8360 | Loss: 0.2941 | LM: 0.2842 | LB: 1.1077 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:48:32] Epoch 1 | Step 8370 | Loss: 0.2941 | LM: 0.2842 | LB: 1.1076 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:48:39] Epoch 1 | Step 8380 | Loss: 0.2941 | LM: 0.2842 | LB: 1.1076 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:48:46] Epoch 1 | Step 8390 | Loss: 0.2941 | LM: 0.2843 | LB: 1.1076 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:48:53] Epoch 1 | Step 8400 | Loss: 0.2941 | LM: 0.2843 | LB: 1.1076 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:49:00] Epoch 1 | Step 8410 | Loss: 0.2941 | LM: 0.2843 | LB: 1.1076 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:49:08] Epoch 1 | Step 8420 | Loss: 0.2941 | LM: 0.2843 | LB: 1.1076 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:49:15] Epoch 1 | Step 8430 | Loss: 0.2941 | LM: 0.2842 | LB: 1.1076 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:49:22] Epoch 1 | Step 8440 | Loss: 0.2941 | LM: 0.2842 | LB: 1.1076 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:49:29] Epoch 1 | Step 8450 | Loss: 0.2940 | LM: 0.2841 | LB: 1.1075 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:49:36] Epoch 1 | Step 8460 | Loss: 0.2940 | LM: 0.2842 | LB: 1.1075 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:49:43] Epoch 1 | Step 8470 | Loss: 0.2940 | LM: 0.2842 | LB: 1.1075 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:49:50] Epoch 1 | Step 8480 | Loss: 0.2940 | LM: 0.2842 | LB: 1.1075 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:49:57] Epoch 1 | Step 8490 | Loss: 0.2940 | LM: 0.2842 | LB: 1.1075 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:50:05] Epoch 1 | Step 8500 | Loss: 0.2940 | LM: 0.2842 | LB: 1.1075 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:50:12] Epoch 1 | Step 8510 | Loss: 0.2940 | LM: 0.2841 | LB: 1.1075 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:50:19] Epoch 1 | Step 8520 | Loss: 0.2940 | LM: 0.2840 | LB: 1.1075 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:50:26] Epoch 1 | Step 8530 | Loss: 0.2940 | LM: 0.2840 | LB: 1.1074 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:50:33] Epoch 1 | Step 8540 | Loss: 0.2940 | LM: 0.2842 | LB: 1.1074 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:50:40] Epoch 1 | Step 8550 | Loss: 0.2941 | LM: 0.2841 | LB: 1.1074 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:50:47] Epoch 1 | Step 8560 | Loss: 0.2940 | LM: 0.2841 | LB: 1.1074 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:50:54] Epoch 1 | Step 8570 | Loss: 0.2941 | LM: 0.2841 | LB: 1.1074 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:51:01] Epoch 1 | Step 8580 | Loss: 0.2940 | LM: 0.2840 | LB: 1.1073 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:51:08] Epoch 1 | Step 8590 | Loss: 0.2940 | LM: 0.2840 | LB: 1.1073 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:51:15] Epoch 1 | Step 8600 | Loss: 0.2940 | LM: 0.2839 | LB: 1.1073 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:51:22] Epoch 1 | Step 8610 | Loss: 0.2940 | LM: 0.2839 | LB: 1.1073 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:51:29] Epoch 1 | Step 8620 | Loss: 0.2939 | LM: 0.2838 | LB: 1.1073 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:51:36] Epoch 1 | Step 8630 | Loss: 0.2939 | LM: 0.2838 | LB: 1.1073 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:51:43] Epoch 1 | Step 8640 | Loss: 0.2939 | LM: 0.2839 | LB: 1.1073 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:51:51] Epoch 1 | Step 8650 | Loss: 0.2940 | LM: 0.2838 | LB: 1.1073 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.429/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:51:58] Epoch 1 | Step 8660 | Loss: 0.2939 | LM: 0.2837 | LB: 1.1073 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:52:05] Epoch 1 | Step 8670 | Loss: 0.2940 | LM: 0.2838 | LB: 1.1072 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:52:12] Epoch 1 | Step 8680 | Loss: 0.2940 | LM: 0.2837 | LB: 1.1072 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:52:19] Epoch 1 | Step 8690 | Loss: 0.2939 | LM: 0.2837 | LB: 1.1072 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:52:26] Epoch 1 | Step 8700 | Loss: 0.2939 | LM: 0.2837 | LB: 1.1072 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:52:33] Epoch 1 | Step 8710 | Loss: 0.2938 | LM: 0.2836 | LB: 1.1072 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:52:40] Epoch 1 | Step 8720 | Loss: 0.2938 | LM: 0.2836 | LB: 1.1072 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:52:47] Epoch 1 | Step 8730 | Loss: 0.2938 | LM: 0.2837 | LB: 1.1072 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:52:54] Epoch 1 | Step 8740 | Loss: 0.2938 | LM: 0.2837 | LB: 1.1071 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:53:01] Epoch 1 | Step 8750 | Loss: 0.2938 | LM: 0.2837 | LB: 1.1071 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:53:08] Epoch 1 | Step 8760 | Loss: 0.2938 | LM: 0.2837 | LB: 1.1071 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:53:15] Epoch 1 | Step 8770 | Loss: 0.2938 | LM: 0.2837 | LB: 1.1071 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:53:22] Epoch 1 | Step 8780 | Loss: 0.2938 | LM: 0.2838 | LB: 1.1071 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:53:30] Epoch 1 | Step 8790 | Loss: 0.2938 | LM: 0.2838 | LB: 1.1071 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:53:37] Epoch 1 | Step 8800 | Loss: 0.2937 | LM: 0.2838 | LB: 1.1071 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:53:44] Epoch 1 | Step 8810 | Loss: 0.2937 | LM: 0.2837 | LB: 1.1071 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:53:51] Epoch 1 | Step 8820 | Loss: 0.2937 | LM: 0.2838 | LB: 1.1071 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:53:58] Epoch 1 | Step 8830 | Loss: 0.2937 | LM: 0.2839 | LB: 1.1070 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:54:05] Epoch 1 | Step 8840 | Loss: 0.2937 | LM: 0.2838 | LB: 1.1070 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:54:12] Epoch 1 | Step 8850 | Loss: 0.2937 | LM: 0.2838 | LB: 1.1070 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:54:19] Epoch 1 | Step 8860 | Loss: 0.2937 | LM: 0.2838 | LB: 1.1070 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:54:26] Epoch 1 | Step 8870 | Loss: 0.2937 | LM: 0.2839 | LB: 1.1070 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:54:33] Epoch 1 | Step 8880 | Loss: 0.2936 | LM: 0.2839 | LB: 1.1070 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:54:40] Epoch 1 | Step 8890 | Loss: 0.2936 | LM: 0.2839 | LB: 1.1070 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:54:47] Epoch 1 | Step 8900 | Loss: 0.2935 | LM: 0.2838 | LB: 1.1070 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:54:54] Epoch 1 | Step 8910 | Loss: 0.2935 | LM: 0.2839 | LB: 1.1070 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:55:02] Epoch 1 | Step 8920 | Loss: 0.2935 | LM: 0.2838 | LB: 1.1069 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:55:09] Epoch 1 | Step 8930 | Loss: 0.2934 | LM: 0.2838 | LB: 1.1069 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:55:16] Epoch 1 | Step 8940 | Loss: 0.2935 | LM: 0.2838 | LB: 1.1069 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:55:23] Epoch 1 | Step 8950 | Loss: 0.2935 | LM: 0.2838 | LB: 1.1069 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:55:30] Epoch 1 | Step 8960 | Loss: 0.2935 | LM: 0.2838 | LB: 1.1069 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:55:37] Epoch 1 | Step 8970 | Loss: 0.2935 | LM: 0.2838 | LB: 1.1069 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:55:44] Epoch 1 | Step 8980 | Loss: 0.2934 | LM: 0.2837 | LB: 1.1069 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:55:51] Epoch 1 | Step 8990 | Loss: 0.2934 | LM: 0.2837 | LB: 1.1069 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:55:58] Epoch 1 | Step 9000 | Loss: 0.2934 | LM: 0.2837 | LB: 1.1069 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:56:06] Epoch 1 | Step 9010 | Loss: 0.2934 | LM: 0.2837 | LB: 1.1069 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:56:13] Epoch 1 | Step 9020 | Loss: 0.2934 | LM: 0.2836 | LB: 1.1069 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.428/SR1: 0.402 | LR: 1.00e-05 |
| [2026-04-25 21:56:20] Epoch 1 | Step 9030 | Loss: 0.2934 | LM: 0.2837 | LB: 1.1069 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:56:28] Epoch 1 | Step 9040 | Loss: 0.2934 | LM: 0.2836 | LB: 1.1068 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:56:36] Epoch 1 | Step 9050 | Loss: 0.2934 | LM: 0.2837 | LB: 1.1068 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:56:43] Epoch 1 | Step 9060 | Loss: 0.2934 | LM: 0.2836 | LB: 1.1068 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:56:50] Epoch 1 | Step 9070 | Loss: 0.2934 | LM: 0.2836 | LB: 1.1068 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.354 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:56:58] Epoch 1 | Step 9080 | Loss: 0.2934 | LM: 0.2835 | LB: 1.1068 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:57:05] Epoch 1 | Step 9090 | Loss: 0.2933 | LM: 0.2834 | LB: 1.1068 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:57:12] Epoch 1 | Step 9100 | Loss: 0.2934 | LM: 0.2835 | LB: 1.1068 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:57:20] Epoch 1 | Step 9110 | Loss: 0.2934 | LM: 0.2834 | LB: 1.1068 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:57:27] Epoch 1 | Step 9120 | Loss: 0.2934 | LM: 0.2835 | LB: 1.1068 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:57:34] Epoch 1 | Step 9130 | Loss: 0.2933 | LM: 0.2835 | LB: 1.1068 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:57:42] Epoch 1 | Step 9140 | Loss: 0.2933 | LM: 0.2835 | LB: 1.1068 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:57:49] Epoch 1 | Step 9150 | Loss: 0.2933 | LM: 0.2834 | LB: 1.1068 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:57:56] Epoch 1 | Step 9160 | Loss: 0.2933 | LM: 0.2834 | LB: 1.1068 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:58:04] Epoch 1 | Step 9170 | Loss: 0.2932 | LM: 0.2833 | LB: 1.1068 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:58:11] Epoch 1 | Step 9180 | Loss: 0.2932 | LM: 0.2833 | LB: 1.1068 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:58:18] Epoch 1 | Step 9190 | Loss: 0.2932 | LM: 0.2832 | LB: 1.1068 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:58:25] Epoch 1 | Step 9200 | Loss: 0.2932 | LM: 0.2832 | LB: 1.1068 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:58:32] Epoch 1 | Step 9210 | Loss: 0.2932 | LM: 0.2832 | LB: 1.1067 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:58:39] Epoch 1 | Step 9220 | Loss: 0.2932 | LM: 0.2832 | LB: 1.1067 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:58:47] Epoch 1 | Step 9230 | Loss: 0.2931 | LM: 0.2831 | LB: 1.1067 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:58:54] Epoch 1 | Step 9240 | Loss: 0.2931 | LM: 0.2831 | LB: 1.1067 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:59:01] Epoch 1 | Step 9250 | Loss: 0.2931 | LM: 0.2830 | LB: 1.1067 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:59:08] Epoch 1 | Step 9260 | Loss: 0.2930 | LM: 0.2831 | LB: 1.1067 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:59:15] Epoch 1 | Step 9270 | Loss: 0.2930 | LM: 0.2830 | LB: 1.1067 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:59:23] Epoch 1 | Step 9280 | Loss: 0.2930 | LM: 0.2830 | LB: 1.1067 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:59:30] Epoch 1 | Step 9290 | Loss: 0.2930 | LM: 0.2830 | LB: 1.1067 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:59:37] Epoch 1 | Step 9300 | Loss: 0.2930 | LM: 0.2829 | LB: 1.1067 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:59:44] Epoch 1 | Step 9310 | Loss: 0.2930 | LM: 0.2830 | LB: 1.1067 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:59:51] Epoch 1 | Step 9320 | Loss: 0.2930 | LM: 0.2830 | LB: 1.1067 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 21:59:58] Epoch 1 | Step 9330 | Loss: 0.2930 | LM: 0.2830 | LB: 1.1067 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:00:05] Epoch 1 | Step 9340 | Loss: 0.2929 | LM: 0.2829 | LB: 1.1066 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:00:13] Epoch 1 | Step 9350 | Loss: 0.2929 | LM: 0.2829 | LB: 1.1066 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:00:20] Epoch 1 | Step 9360 | Loss: 0.2929 | LM: 0.2828 | LB: 1.1066 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:00:27] Epoch 1 | Step 9370 | Loss: 0.2929 | LM: 0.2828 | LB: 1.1066 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:00:34] Epoch 1 | Step 9380 | Loss: 0.2929 | LM: 0.2827 | LB: 1.1066 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:00:41] Epoch 1 | Step 9390 | Loss: 0.2928 | LM: 0.2827 | LB: 1.1066 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:00:48] Epoch 1 | Step 9400 | Loss: 0.2928 | LM: 0.2827 | LB: 1.1066 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:00:56] Epoch 1 | Step 9410 | Loss: 0.2928 | LM: 0.2828 | LB: 1.1066 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:01:03] Epoch 1 | Step 9420 | Loss: 0.2929 | LM: 0.2828 | LB: 1.1066 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:01:10] Epoch 1 | Step 9430 | Loss: 0.2929 | LM: 0.2827 | LB: 1.1066 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:01:17] Epoch 1 | Step 9440 | Loss: 0.2929 | LM: 0.2827 | LB: 1.1066 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:01:24] Epoch 1 | Step 9450 | Loss: 0.2929 | LM: 0.2827 | LB: 1.1066 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:01:31] Epoch 1 | Step 9460 | Loss: 0.2928 | LM: 0.2827 | LB: 1.1065 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:01:39] Epoch 1 | Step 9470 | Loss: 0.2928 | LM: 0.2826 | LB: 1.1065 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:01:46] Epoch 1 | Step 9480 | Loss: 0.2927 | LM: 0.2825 | LB: 1.1065 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:01:53] Epoch 1 | Step 9490 | Loss: 0.2928 | LM: 0.2826 | LB: 1.1065 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:02:00] Epoch 1 | Step 9500 | Loss: 0.2928 | LM: 0.2827 | LB: 1.1065 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:02:07] Epoch 1 | Step 9510 | Loss: 0.2928 | LM: 0.2827 | LB: 1.1065 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:02:14] Epoch 1 | Step 9520 | Loss: 0.2928 | LM: 0.2827 | LB: 1.1065 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:02:22] Epoch 1 | Step 9530 | Loss: 0.2928 | LM: 0.2827 | LB: 1.1065 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:02:29] Epoch 1 | Step 9540 | Loss: 0.2928 | LM: 0.2827 | LB: 1.1065 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:02:36] Epoch 1 | Step 9550 | Loss: 0.2928 | LM: 0.2827 | LB: 1.1065 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:02:43] Epoch 1 | Step 9560 | Loss: 0.2928 | LM: 0.2827 | LB: 1.1065 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:02:50] Epoch 1 | Step 9570 | Loss: 0.2928 | LM: 0.2827 | LB: 1.1065 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:02:57] Epoch 1 | Step 9580 | Loss: 0.2928 | LM: 0.2827 | LB: 1.1065 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:03:04] Epoch 1 | Step 9590 | Loss: 0.2928 | LM: 0.2827 | LB: 1.1064 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:03:12] Epoch 1 | Step 9600 | Loss: 0.2928 | LM: 0.2827 | LB: 1.1064 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:03:19] Epoch 1 | Step 9610 | Loss: 0.2928 | LM: 0.2826 | LB: 1.1064 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:03:26] Epoch 1 | Step 9620 | Loss: 0.2928 | LM: 0.2826 | LB: 1.1064 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:03:33] Epoch 1 | Step 9630 | Loss: 0.2928 | LM: 0.2826 | LB: 1.1064 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:03:40] Epoch 1 | Step 9640 | Loss: 0.2928 | LM: 0.2825 | LB: 1.1064 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:03:47] Epoch 1 | Step 9650 | Loss: 0.2928 | LM: 0.2825 | LB: 1.1064 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:03:54] Epoch 1 | Step 9660 | Loss: 0.2928 | LM: 0.2825 | LB: 1.1064 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:04:02] Epoch 1 | Step 9670 | Loss: 0.2928 | LM: 0.2825 | LB: 1.1064 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:04:09] Epoch 1 | Step 9680 | Loss: 0.2928 | LM: 0.2825 | LB: 1.1064 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:04:16] Epoch 1 | Step 9690 | Loss: 0.2928 | LM: 0.2824 | LB: 1.1064 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:04:23] Epoch 1 | Step 9700 | Loss: 0.2928 | LM: 0.2824 | LB: 1.1064 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:04:31] Epoch 1 | Step 9710 | Loss: 0.2927 | LM: 0.2824 | LB: 1.1063 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:04:38] Epoch 1 | Step 9720 | Loss: 0.2927 | LM: 0.2824 | LB: 1.1064 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.355 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:04:45] Epoch 1 | Step 9730 | Loss: 0.2927 | LM: 0.2824 | LB: 1.1063 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:04:52] Epoch 1 | Step 9740 | Loss: 0.2927 | LM: 0.2824 | LB: 1.1063 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:04:59] Epoch 1 | Step 9750 | Loss: 0.2927 | LM: 0.2823 | LB: 1.1063 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:05:07] Epoch 1 | Step 9760 | Loss: 0.2927 | LM: 0.2824 | LB: 1.1063 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.428/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:05:14] Epoch 1 | Step 9770 | Loss: 0.2927 | LM: 0.2823 | LB: 1.1063 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.427/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:05:21] Epoch 1 | Step 9780 | Loss: 0.2926 | LM: 0.2823 | LB: 1.1063 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.427/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:05:28] Epoch 1 | Step 9790 | Loss: 0.2926 | LM: 0.2823 | LB: 1.1063 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.427/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:05:35] Epoch 1 | Step 9800 | Loss: 0.2926 | LM: 0.2823 | LB: 1.1063 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.427/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:05:42] Epoch 1 | Step 9810 | Loss: 0.2926 | LM: 0.2823 | LB: 1.1062 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.427/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:05:50] Epoch 1 | Step 9820 | Loss: 0.2926 | LM: 0.2823 | LB: 1.1062 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.427/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:05:57] Epoch 1 | Step 9830 | Loss: 0.2926 | LM: 0.2823 | LB: 1.1062 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.427/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:06:04] Epoch 1 | Step 9840 | Loss: 0.2926 | LM: 0.2823 | LB: 1.1062 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.427/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:06:11] Epoch 1 | Step 9850 | Loss: 0.2926 | LM: 0.2822 | LB: 1.1062 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.427/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:06:19] Epoch 1 | Step 9860 | Loss: 0.2926 | LM: 0.2823 | LB: 1.1062 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.427/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:06:26] Epoch 1 | Step 9870 | Loss: 0.2926 | LM: 0.2823 | LB: 1.1062 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.427/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:06:33] Epoch 1 | Step 9880 | Loss: 0.2926 | LM: 0.2824 | LB: 1.1062 | CL0: 2.8 | CL1: 2.4 | HR0: 0.358/SR0: 0.354 | HR1: 0.427/SR1: 0.401 | LR: 1.00e-05 |
| [2026-04-25 22:06:38] Epoch 1 completed in 7105.89s | Loss: 0.2926 | CL0: 2.8 | CL1: 2.4 |
| [2026-04-25 22:06:38] |
| Training completed! |
| [2026-04-25 22:06:41] Final model: /workspace/byte-llms-code/outputs/lr_sweep/hnet_xl_code_lr_1e-4/model_final.pt |
|
|
