| [2026-04-25 17:44:17,236][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 17:44:17] CUDA_VISIBLE_DEVICES: 0,1 |
| [2026-04-25 17:44:17] Number of processes: 2 |
| [2026-04-25 17:44:17] Process index: 0 |
| [2026-04-25 17:44:17] Mixed precision: bf16 |
| [2026-04-25 17:44:17] ============================================================ |
| [2026-04-25 17:44:17] HNet Training Pipeline (Hydra + Trackio + Accelerate) |
| [2026-04-25 17:44:17] ============================================================ |
| [2026-04-25 17:44:17] 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: 5.0e-05 |
| 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: 20000 |
| max_val_samples: 2000 |
| logging: |
| log_interval: 10 |
| save_interval: 3000 |
| eval_interval: 1000 |
| save_every_epoch: true |
| tracking: |
| enabled: true |
| backend: wandb |
| project: code-completion_lr-sweep |
| run_name: hnet_xl_code_lr_5e-5 |
| entity: null |
| base_url: https://wandb.platun0v.ru |
| local_dir: /workspace/byte-llms-code/outputs/lr_sweep/hnet_xl_code_lr_5e-5 |
| paths: |
| output_dir: /workspace/byte-llms-code/outputs/lr_sweep/hnet_xl_code_lr_5e-5 |
| seed: 42 |
| device: cuda |
|
|
| [2026-04-25 17:44:19] Initializing tokenizer... |
| [2026-04-25 17:44:19] Loading model... |
| [2026-04-25 17:44:24] Loaded pretrained: /workspace/byte-llms-code/hnet_project/checkpoints/hnet_2stage_XL_code.pt |
| [2026-04-25 17:44:24] Applied LR multipliers: [2.0, 1.5, 1.0] |
| [2026-04-25 17:44:24] Warming up model... |
| [2026-04-25 17:47:41] Total params: 1,654,090,112 |
| [2026-04-25 17:47:41] Trainable params: 1,654,090,112 |
| [2026-04-25 17:47:41] Creating dataloaders... |
| [2026-04-25 17:47:41] Train dataset size: 20000 |
| [2026-04-25 17:47:41] Train batches per epoch (before DDP split): 5000 |
| [2026-04-25 17:47:41] Validation dataset size: 2000 |
| [2026-04-25 17:47:41] Validation batches: 84 |
| [2026-04-25 17:47:41] Creating optimizer... |
| [2026-04-25 17:47:41] Total steps: 625, Steps per epoch: 2500 |
| [2026-04-25 17:47:41] Preparing model, optimizer, and dataloaders with Accelerate... |
| [2026-04-25 17:47:42] Train batches per epoch (after DDP split): 2500 |
| [2026-04-25 17:47:42] Starting training... |
| [2026-04-25 17:47:42] |
| ============================================================ |
| [2026-04-25 17:47:42] EPOCH 1/1 |
| [2026-04-25 17:47:42] ============================================================ |
| [2026-04-25 17:50:46] Epoch 1 | Step 10 | Loss: 0.6596 | LM: 0.6184 | LB: 1.1668 | CL0: 2.7 | CL1: 2.1 | HR0: 0.371/SR0: 0.367 | HR1: 0.472/SR1: 0.455 | LR: 1.95e-05 |
| [2026-04-25 17:50:54] Epoch 1 | Step 20 | Loss: 0.6101 | LM: 0.6312 | LB: 1.1650 | CL0: 2.8 | CL1: 2.1 | HR0: 0.364/SR0: 0.361 | HR1: 0.476/SR1: 0.459 | LR: 3.40e-05 |
| [2026-04-25 17:51:01] Epoch 1 | Step 30 | Loss: 0.5549 | LM: 0.5675 | LB: 1.1666 | CL0: 2.8 | CL1: 2.1 | HR0: 0.363/SR0: 0.360 | HR1: 0.478/SR1: 0.460 | LR: 4.85e-05 |
| [2026-04-25 17:51:09] Epoch 1 | Step 40 | Loss: 0.5140 | LM: 0.5316 | LB: 1.1688 | CL0: 2.7 | CL1: 2.1 | HR0: 0.367/SR0: 0.364 | HR1: 0.478/SR1: 0.459 | LR: 5.00e-05 |
| [2026-04-25 17:51:16] Epoch 1 | Step 50 | Loss: 0.4827 | LM: 0.4866 | LB: 1.1683 | CL0: 2.8 | CL1: 2.1 | HR0: 0.365/SR0: 0.362 | HR1: 0.479/SR1: 0.460 | LR: 5.00e-05 |
| [2026-04-25 17:51:23] Epoch 1 | Step 60 | Loss: 0.4620 | LM: 0.4543 | LB: 1.1683 | CL0: 2.8 | CL1: 2.1 | HR0: 0.362/SR0: 0.360 | HR1: 0.481/SR1: 0.461 | LR: 5.00e-05 |
| [2026-04-25 17:51:31] Epoch 1 | Step 70 | Loss: 0.4428 | LM: 0.4376 | LB: 1.1672 | CL0: 2.8 | CL1: 2.1 | HR0: 0.362/SR0: 0.359 | HR1: 0.480/SR1: 0.461 | LR: 5.00e-05 |
| [2026-04-25 17:51:38] Epoch 1 | Step 80 | Loss: 0.4263 | LM: 0.4253 | LB: 1.1680 | CL0: 2.8 | CL1: 2.1 | HR0: 0.361/SR0: 0.359 | HR1: 0.481/SR1: 0.462 | LR: 5.00e-05 |
| [2026-04-25 17:51:45] Epoch 1 | Step 90 | Loss: 0.4136 | LM: 0.4185 | LB: 1.1681 | CL0: 2.8 | CL1: 2.1 | HR0: 0.362/SR0: 0.360 | HR1: 0.481/SR1: 0.461 | LR: 5.00e-05 |
| [2026-04-25 17:51:52] Epoch 1 | Step 100 | Loss: 0.4098 | LM: 0.4064 | LB: 1.1692 | CL0: 2.8 | CL1: 2.1 | HR0: 0.363/SR0: 0.360 | HR1: 0.482/SR1: 0.462 | LR: 5.00e-05 |
| [2026-04-25 17:52:00] Epoch 1 | Step 110 | Loss: 0.4052 | LM: 0.4049 | LB: 1.1687 | CL0: 2.8 | CL1: 2.1 | HR0: 0.363/SR0: 0.361 | HR1: 0.481/SR1: 0.461 | LR: 5.00e-05 |
| [2026-04-25 17:52:07] Epoch 1 | Step 120 | Loss: 0.4008 | LM: 0.3999 | LB: 1.1679 | CL0: 2.8 | CL1: 2.1 | HR0: 0.363/SR0: 0.361 | HR1: 0.481/SR1: 0.461 | LR: 5.00e-05 |
| [2026-04-25 17:52:14] Epoch 1 | Step 130 | Loss: 0.3894 | LM: 0.3850 | LB: 1.1673 | CL0: 2.8 | CL1: 2.1 | HR0: 0.363/SR0: 0.360 | HR1: 0.481/SR1: 0.460 | LR: 5.00e-05 |
| [2026-04-25 17:52:21] Epoch 1 | Step 140 | Loss: 0.3838 | LM: 0.3834 | LB: 1.1663 | CL0: 2.8 | CL1: 2.1 | HR0: 0.363/SR0: 0.360 | HR1: 0.480/SR1: 0.460 | LR: 5.00e-05 |
| [2026-04-25 17:52:29] Epoch 1 | Step 150 | Loss: 0.3826 | LM: 0.3778 | LB: 1.1671 | CL0: 2.8 | CL1: 2.1 | HR0: 0.363/SR0: 0.361 | HR1: 0.480/SR1: 0.460 | LR: 5.00e-05 |
| [2026-04-25 17:52:36] Epoch 1 | Step 160 | Loss: 0.3760 | LM: 0.3788 | LB: 1.1665 | CL0: 2.8 | CL1: 2.1 | HR0: 0.363/SR0: 0.361 | HR1: 0.480/SR1: 0.459 | LR: 5.00e-05 |
| [2026-04-25 17:52:46] Epoch 1 | Step 170 | Loss: 0.3717 | LM: 0.3687 | LB: 1.1659 | CL0: 2.8 | CL1: 2.1 | HR0: 0.363/SR0: 0.361 | HR1: 0.480/SR1: 0.459 | LR: 5.00e-05 |
| [2026-04-25 17:52:53] Epoch 1 | Step 180 | Loss: 0.3693 | LM: 0.3638 | LB: 1.1666 | CL0: 2.8 | CL1: 2.1 | HR0: 0.363/SR0: 0.360 | HR1: 0.480/SR1: 0.460 | LR: 5.00e-05 |
| [2026-04-25 17:53:01] Epoch 1 | Step 190 | Loss: 0.3656 | LM: 0.3626 | LB: 1.1659 | CL0: 2.8 | CL1: 2.1 | HR0: 0.361/SR0: 0.359 | HR1: 0.480/SR1: 0.460 | LR: 5.00e-05 |
| [2026-04-25 17:53:08] Epoch 1 | Step 200 | Loss: 0.3625 | LM: 0.3600 | LB: 1.1654 | CL0: 2.8 | CL1: 2.1 | HR0: 0.361/SR0: 0.359 | HR1: 0.480/SR1: 0.460 | LR: 5.00e-05 |
| [2026-04-25 17:53:15] Epoch 1 | Step 210 | Loss: 0.3592 | LM: 0.3533 | LB: 1.1643 | CL0: 2.8 | CL1: 2.1 | HR0: 0.360/SR0: 0.358 | HR1: 0.479/SR1: 0.459 | LR: 5.00e-05 |
| [2026-04-25 17:53:23] Epoch 1 | Step 220 | Loss: 0.3587 | LM: 0.3455 | LB: 1.1640 | CL0: 2.8 | CL1: 2.1 | HR0: 0.360/SR0: 0.358 | HR1: 0.479/SR1: 0.459 | LR: 5.00e-05 |
| [2026-04-25 17:53:30] Epoch 1 | Step 230 | Loss: 0.3579 | LM: 0.3475 | LB: 1.1646 | CL0: 2.8 | CL1: 2.1 | HR0: 0.360/SR0: 0.358 | HR1: 0.480/SR1: 0.459 | LR: 5.00e-05 |
| [2026-04-25 17:53:37] Epoch 1 | Step 240 | Loss: 0.3575 | LM: 0.3465 | LB: 1.1638 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.480/SR1: 0.459 | LR: 5.00e-05 |
| [2026-04-25 17:53:44] Epoch 1 | Step 250 | Loss: 0.3542 | LM: 0.3427 | LB: 1.1638 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.479/SR1: 0.459 | LR: 5.00e-05 |
| [2026-04-25 17:53:52] Epoch 1 | Step 260 | Loss: 0.3546 | LM: 0.3436 | LB: 1.1633 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.479/SR1: 0.459 | LR: 4.72e-05 |
| [2026-04-25 17:53:59] Epoch 1 | Step 270 | Loss: 0.3533 | LM: 0.3435 | LB: 1.1625 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.357 | HR1: 0.478/SR1: 0.458 | LR: 3.96e-05 |
| [2026-04-25 17:54:06] Epoch 1 | Step 280 | Loss: 0.3517 | LM: 0.3432 | LB: 1.1627 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.357 | HR1: 0.479/SR1: 0.458 | LR: 2.89e-05 |
| [2026-04-25 17:54:14] Epoch 1 | Step 290 | Loss: 0.3502 | LM: 0.3400 | LB: 1.1621 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.357 | HR1: 0.478/SR1: 0.458 | LR: 1.79e-05 |
| [2026-04-25 17:54:21] Epoch 1 | Step 300 | Loss: 0.3480 | LM: 0.3369 | LB: 1.1615 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.357 | HR1: 0.478/SR1: 0.457 | LR: 9.30e-06 |
| [2026-04-25 17:54:28] Epoch 1 | Step 310 | Loss: 0.3471 | LM: 0.3338 | LB: 1.1607 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.357 | HR1: 0.477/SR1: 0.457 | LR: 5.18e-06 |
| [2026-04-25 17:54:36] Epoch 1 | Step 320 | Loss: 0.3462 | LM: 0.3325 | LB: 1.1606 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.477/SR1: 0.457 | LR: 5.00e-06 |
| [2026-04-25 17:54:43] Epoch 1 | Step 330 | Loss: 0.3450 | LM: 0.3310 | LB: 1.1607 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.477/SR1: 0.457 | LR: 5.00e-06 |
| [2026-04-25 17:54:51] Epoch 1 | Step 340 | Loss: 0.3444 | LM: 0.3292 | LB: 1.1610 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.357 | HR1: 0.477/SR1: 0.457 | LR: 5.00e-06 |
| [2026-04-25 17:54:58] Epoch 1 | Step 350 | Loss: 0.3419 | LM: 0.3263 | LB: 1.1613 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.478/SR1: 0.457 | LR: 5.00e-06 |
| [2026-04-25 17:55:05] Epoch 1 | Step 360 | Loss: 0.3400 | LM: 0.3260 | LB: 1.1614 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.477/SR1: 0.457 | LR: 5.00e-06 |
| [2026-04-25 17:55:13] Epoch 1 | Step 370 | Loss: 0.3383 | LM: 0.3238 | LB: 1.1614 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.477/SR1: 0.457 | LR: 5.00e-06 |
| [2026-04-25 17:55:20] Epoch 1 | Step 380 | Loss: 0.3383 | LM: 0.3261 | LB: 1.1614 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.477/SR1: 0.457 | LR: 5.00e-06 |
| [2026-04-25 17:55:27] Epoch 1 | Step 390 | Loss: 0.3374 | LM: 0.3237 | LB: 1.1612 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.477/SR1: 0.457 | LR: 5.00e-06 |
| [2026-04-25 17:55:35] Epoch 1 | Step 400 | Loss: 0.3361 | LM: 0.3226 | LB: 1.1613 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.477/SR1: 0.457 | LR: 5.00e-06 |
| [2026-04-25 17:55:42] Epoch 1 | Step 410 | Loss: 0.3359 | LM: 0.3221 | LB: 1.1613 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.477/SR1: 0.457 | LR: 5.00e-06 |
| [2026-04-25 17:55:49] Epoch 1 | Step 420 | Loss: 0.3345 | LM: 0.3206 | LB: 1.1611 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.477/SR1: 0.456 | LR: 5.00e-06 |
| [2026-04-25 17:55:56] Epoch 1 | Step 430 | Loss: 0.3337 | LM: 0.3198 | LB: 1.1606 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.357 | HR1: 0.477/SR1: 0.456 | LR: 5.00e-06 |
| [2026-04-25 17:56:03] Epoch 1 | Step 440 | Loss: 0.3332 | LM: 0.3203 | LB: 1.1609 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.477/SR1: 0.456 | LR: 5.00e-06 |
| [2026-04-25 17:56:11] Epoch 1 | Step 450 | Loss: 0.3327 | LM: 0.3191 | LB: 1.1610 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.477/SR1: 0.456 | LR: 5.00e-06 |
| [2026-04-25 17:56:18] Epoch 1 | Step 460 | Loss: 0.3328 | LM: 0.3204 | LB: 1.1609 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.477/SR1: 0.456 | LR: 5.00e-06 |
| [2026-04-25 17:56:25] Epoch 1 | Step 470 | Loss: 0.3332 | LM: 0.3214 | LB: 1.1614 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.478/SR1: 0.457 | LR: 5.00e-06 |
| [2026-04-25 17:56:33] Epoch 1 | Step 480 | Loss: 0.3328 | LM: 0.3211 | LB: 1.1616 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.478/SR1: 0.457 | LR: 5.00e-06 |
| [2026-04-25 17:56:40] Epoch 1 | Step 490 | Loss: 0.3328 | LM: 0.3213 | LB: 1.1619 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.358 | HR1: 0.478/SR1: 0.457 | LR: 5.00e-06 |
| [2026-04-25 17:56:47] Epoch 1 | Step 500 | Loss: 0.3315 | LM: 0.3215 | LB: 1.1621 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.358 | HR1: 0.478/SR1: 0.457 | LR: 5.00e-06 |
| [2026-04-25 17:56:54] Epoch 1 | Step 510 | Loss: 0.3310 | LM: 0.3211 | LB: 1.1620 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.358 | HR1: 0.478/SR1: 0.457 | LR: 5.00e-06 |
| [2026-04-25 17:57:01] Epoch 1 | Step 520 | Loss: 0.3307 | LM: 0.3198 | LB: 1.1616 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.478/SR1: 0.457 | LR: 5.00e-06 |
| [2026-04-25 17:57:09] Epoch 1 | Step 530 | Loss: 0.3303 | LM: 0.3196 | LB: 1.1611 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.357 | HR1: 0.478/SR1: 0.456 | LR: 5.00e-06 |
| [2026-04-25 17:57:16] Epoch 1 | Step 540 | Loss: 0.3312 | LM: 0.3209 | LB: 1.1610 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.357 | HR1: 0.478/SR1: 0.456 | LR: 5.00e-06 |
| [2026-04-25 17:57:23] Epoch 1 | Step 550 | Loss: 0.3309 | LM: 0.3201 | LB: 1.1611 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.357 | HR1: 0.478/SR1: 0.456 | LR: 5.00e-06 |
| [2026-04-25 17:57:31] Epoch 1 | Step 560 | Loss: 0.3304 | LM: 0.3206 | LB: 1.1615 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.478/SR1: 0.456 | LR: 5.00e-06 |
| [2026-04-25 17:57:38] Epoch 1 | Step 570 | Loss: 0.3304 | LM: 0.3197 | LB: 1.1612 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.478/SR1: 0.456 | LR: 5.00e-06 |
| [2026-04-25 17:57:45] Epoch 1 | Step 580 | Loss: 0.3298 | LM: 0.3189 | LB: 1.1612 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.478/SR1: 0.456 | LR: 5.00e-06 |
| [2026-04-25 17:57:53] Epoch 1 | Step 590 | Loss: 0.3302 | LM: 0.3205 | LB: 1.1613 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.478/SR1: 0.456 | LR: 5.00e-06 |
| [2026-04-25 17:58:00] Epoch 1 | Step 600 | Loss: 0.3302 | LM: 0.3214 | LB: 1.1614 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.478/SR1: 0.456 | LR: 5.00e-06 |
| [2026-04-25 17:58:08] Epoch 1 | Step 610 | Loss: 0.3300 | LM: 0.3205 | LB: 1.1610 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.477/SR1: 0.456 | LR: 5.00e-06 |
| [2026-04-25 17:58:16] Epoch 1 | Step 620 | Loss: 0.3296 | LM: 0.3199 | LB: 1.1609 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.477/SR1: 0.456 | LR: 5.00e-06 |
| [2026-04-25 17:58:17] Training interrupted by user |
| [2026-04-25 18:06:01,662][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 18:06:01] CUDA_VISIBLE_DEVICES: 0,1 |
| [2026-04-25 18:06:01] Number of processes: 2 |
| [2026-04-25 18:06:01] Process index: 0 |
| [2026-04-25 18:06:01] Mixed precision: bf16 |
| [2026-04-25 18:06:01] ============================================================ |
| [2026-04-25 18:06:01] HNet Training Pipeline (Hydra + Trackio + Accelerate) |
| [2026-04-25 18:06:01] ============================================================ |
| [2026-04-25 18:06:01] 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: 5.0e-05 |
| 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_5e-5 |
| entity: null |
| base_url: https://wandb.platun0v.ru |
| local_dir: /workspace/byte-llms-code/outputs/lr_sweep/hnet_xl_code_lr_5e-5 |
| paths: |
| output_dir: /workspace/byte-llms-code/outputs/lr_sweep/hnet_xl_code_lr_5e-5 |
| seed: 42 |
| device: cuda |
|
|
| [2026-04-25 18:06:04] Initializing tokenizer... |
| [2026-04-25 18:06:04] Loading model... |
| [2026-04-25 18:06:08] Loaded pretrained: /workspace/byte-llms-code/hnet_project/checkpoints/hnet_2stage_XL_code.pt |
| [2026-04-25 18:06:08] Applied LR multipliers: [2.0, 1.5, 1.0] |
| [2026-04-25 18:06:08] Warming up model... |
| [2026-04-25 18:06:52] Total params: 1,654,090,112 |
| [2026-04-25 18:06:52] Trainable params: 1,654,090,112 |
| [2026-04-25 18:06:52] Creating dataloaders... |
| [2026-04-25 18:06:52] Train dataset size: 316397 |
| [2026-04-25 18:06:52] Train batches per epoch (before DDP split): 79100 |
| [2026-04-25 18:06:52] Validation dataset size: 2000 |
| [2026-04-25 18:06:52] Validation batches: 84 |
| [2026-04-25 18:06:52] Creating optimizer... |
| [2026-04-25 18:06:52] Total steps: 9887, Steps per epoch: 39550 |
| [2026-04-25 18:06:52] Preparing model, optimizer, and dataloaders with Accelerate... |
| [2026-04-25 18:06:53] Train batches per epoch (after DDP split): 39550 |
| [2026-04-25 18:06:53] Starting training... |
| [2026-04-25 18:06:53] |
| ============================================================ |
| [2026-04-25 18:06:53] EPOCH 1/1 |
| [2026-04-25 18:06:53] ============================================================ |
| [2026-04-25 18:07:36] Epoch 1 | Step 10 | Loss: 0.6588 | LM: 0.6195 | LB: 1.1576 | CL0: 2.9 | CL1: 2.1 | HR0: 0.351/SR0: 0.351 | HR1: 0.476/SR1: 0.455 | LR: 5.91e-06 |
| [2026-04-25 18:07:44] Epoch 1 | Step 20 | Loss: 0.6660 | LM: 0.6516 | LB: 1.1551 | CL0: 2.9 | CL1: 2.1 | HR0: 0.352/SR0: 0.351 | HR1: 0.475/SR1: 0.455 | LR: 6.82e-06 |
| [2026-04-25 18:07:51] Epoch 1 | Step 30 | Loss: 0.6517 | LM: 0.6294 | LB: 1.1523 | CL0: 2.9 | CL1: 2.1 | HR0: 0.352/SR0: 0.350 | HR1: 0.473/SR1: 0.452 | LR: 7.73e-06 |
| [2026-04-25 18:07:59] Epoch 1 | Step 40 | Loss: 0.6486 | LM: 0.6151 | LB: 1.1604 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.478/SR1: 0.456 | LR: 8.64e-06 |
| [2026-04-25 18:08:07] Epoch 1 | Step 50 | Loss: 0.6291 | LM: 0.5822 | LB: 1.1592 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.355 | HR1: 0.476/SR1: 0.455 | LR: 9.55e-06 |
| [2026-04-25 18:08:14] Epoch 1 | Step 60 | Loss: 0.6094 | LM: 0.5674 | LB: 1.1615 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.478/SR1: 0.458 | LR: 1.05e-05 |
| [2026-04-25 18:08:21] Epoch 1 | Step 70 | Loss: 0.5959 | LM: 0.5623 | LB: 1.1611 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.478/SR1: 0.457 | LR: 1.14e-05 |
| [2026-04-25 18:08:29] Epoch 1 | Step 80 | Loss: 0.5881 | LM: 0.5592 | LB: 1.1624 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.479/SR1: 0.458 | LR: 1.23e-05 |
| [2026-04-25 18:08:36] Epoch 1 | Step 90 | Loss: 0.5763 | LM: 0.5506 | LB: 1.1630 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.479/SR1: 0.458 | LR: 1.32e-05 |
| [2026-04-25 18:08:43] Epoch 1 | Step 100 | Loss: 0.5632 | LM: 0.5514 | LB: 1.1628 | CL0: 2.8 | CL1: 2.1 | HR0: 0.360/SR0: 0.357 | HR1: 0.478/SR1: 0.457 | LR: 1.41e-05 |
| [2026-04-25 18:08:50] Epoch 1 | Step 110 | Loss: 0.5584 | LM: 0.5523 | LB: 1.1637 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.356 | HR1: 0.479/SR1: 0.458 | LR: 1.50e-05 |
| [2026-04-25 18:08:57] Epoch 1 | Step 120 | Loss: 0.5497 | LM: 0.5390 | LB: 1.1632 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.356 | HR1: 0.479/SR1: 0.458 | LR: 1.59e-05 |
| [2026-04-25 18:09:05] Epoch 1 | Step 130 | Loss: 0.5407 | LM: 0.5295 | LB: 1.1633 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.480/SR1: 0.459 | LR: 1.68e-05 |
| [2026-04-25 18:09:12] Epoch 1 | Step 140 | Loss: 0.5305 | LM: 0.5254 | LB: 1.1642 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.480/SR1: 0.459 | LR: 1.78e-05 |
| [2026-04-25 18:09:19] Epoch 1 | Step 150 | Loss: 0.5184 | LM: 0.5067 | LB: 1.1641 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.480/SR1: 0.459 | LR: 1.87e-05 |
| [2026-04-25 18:09:26] Epoch 1 | Step 160 | Loss: 0.5079 | LM: 0.4963 | LB: 1.1651 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.480/SR1: 0.459 | LR: 1.96e-05 |
| [2026-04-25 18:09:34] Epoch 1 | Step 170 | Loss: 0.5029 | LM: 0.4983 | LB: 1.1631 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.479/SR1: 0.458 | LR: 2.05e-05 |
| [2026-04-25 18:09:41] Epoch 1 | Step 180 | Loss: 0.4930 | LM: 0.4891 | LB: 1.1625 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.479/SR1: 0.458 | LR: 2.14e-05 |
| [2026-04-25 18:09:48] Epoch 1 | Step 190 | Loss: 0.4871 | LM: 0.4825 | LB: 1.1616 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.478/SR1: 0.457 | LR: 2.23e-05 |
| [2026-04-25 18:09:55] Epoch 1 | Step 200 | Loss: 0.4810 | LM: 0.4812 | LB: 1.1611 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.478/SR1: 0.457 | LR: 2.32e-05 |
| [2026-04-25 18:10:02] Epoch 1 | Step 210 | Loss: 0.4769 | LM: 0.4803 | LB: 1.1613 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.479/SR1: 0.457 | LR: 2.41e-05 |
| [2026-04-25 18:10:10] Epoch 1 | Step 220 | Loss: 0.4711 | LM: 0.4777 | LB: 1.1621 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.479/SR1: 0.458 | LR: 2.50e-05 |
| [2026-04-25 18:10:17] Epoch 1 | Step 230 | Loss: 0.4640 | LM: 0.4681 | LB: 1.1627 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.480/SR1: 0.458 | LR: 2.60e-05 |
| [2026-04-25 18:10:24] Epoch 1 | Step 240 | Loss: 0.4590 | LM: 0.4602 | LB: 1.1625 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.480/SR1: 0.458 | LR: 2.69e-05 |
| [2026-04-25 18:10:31] Epoch 1 | Step 250 | Loss: 0.4543 | LM: 0.4522 | LB: 1.1627 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.354 | HR1: 0.480/SR1: 0.459 | LR: 2.78e-05 |
| [2026-04-25 18:10:39] Epoch 1 | Step 260 | Loss: 0.4515 | LM: 0.4526 | LB: 1.1630 | CL0: 2.8 | CL1: 2.1 | HR0: 0.355/SR0: 0.354 | HR1: 0.481/SR1: 0.459 | LR: 2.87e-05 |
| [2026-04-25 18:10:46] Epoch 1 | Step 270 | Loss: 0.4463 | LM: 0.4500 | LB: 1.1623 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.354 | HR1: 0.480/SR1: 0.458 | LR: 2.96e-05 |
| [2026-04-25 18:10:53] Epoch 1 | Step 280 | Loss: 0.4410 | LM: 0.4488 | LB: 1.1626 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.354 | HR1: 0.480/SR1: 0.458 | LR: 3.05e-05 |
| [2026-04-25 18:11:01] Epoch 1 | Step 290 | Loss: 0.4370 | LM: 0.4461 | LB: 1.1629 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.480/SR1: 0.458 | LR: 3.14e-05 |
| [2026-04-25 18:11:08] Epoch 1 | Step 300 | Loss: 0.4343 | LM: 0.4438 | LB: 1.1635 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.480/SR1: 0.459 | LR: 3.23e-05 |
| [2026-04-25 18:11:15] Epoch 1 | Step 310 | Loss: 0.4308 | LM: 0.4395 | LB: 1.1630 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.480/SR1: 0.458 | LR: 3.32e-05 |
| [2026-04-25 18:11:22] Epoch 1 | Step 320 | Loss: 0.4263 | LM: 0.4346 | LB: 1.1633 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.480/SR1: 0.458 | LR: 3.41e-05 |
| [2026-04-25 18:11:29] Epoch 1 | Step 330 | Loss: 0.4228 | LM: 0.4312 | LB: 1.1635 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.481/SR1: 0.458 | LR: 3.51e-05 |
| [2026-04-25 18:11:37] Epoch 1 | Step 340 | Loss: 0.4191 | LM: 0.4276 | LB: 1.1637 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.481/SR1: 0.459 | LR: 3.60e-05 |
| [2026-04-25 18:11:44] Epoch 1 | Step 350 | Loss: 0.4165 | LM: 0.4250 | LB: 1.1639 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.481/SR1: 0.459 | LR: 3.69e-05 |
| [2026-04-25 18:11:51] Epoch 1 | Step 360 | Loss: 0.4123 | LM: 0.4205 | LB: 1.1636 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.481/SR1: 0.459 | LR: 3.78e-05 |
| [2026-04-25 18:11:58] Epoch 1 | Step 370 | Loss: 0.4087 | LM: 0.4176 | LB: 1.1631 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.480/SR1: 0.458 | LR: 3.87e-05 |
| [2026-04-25 18:12:06] Epoch 1 | Step 380 | Loss: 0.4055 | LM: 0.4156 | LB: 1.1632 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.480/SR1: 0.458 | LR: 3.96e-05 |
| [2026-04-25 18:12:13] Epoch 1 | Step 390 | Loss: 0.4031 | LM: 0.4125 | LB: 1.1636 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.481/SR1: 0.458 | LR: 4.05e-05 |
| [2026-04-25 18:12:20] Epoch 1 | Step 400 | Loss: 0.4011 | LM: 0.4106 | LB: 1.1630 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.480/SR1: 0.458 | LR: 4.14e-05 |
| [2026-04-25 18:12:27] Epoch 1 | Step 410 | Loss: 0.3987 | LM: 0.4091 | LB: 1.1629 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.480/SR1: 0.458 | LR: 4.23e-05 |
| [2026-04-25 18:12:34] Epoch 1 | Step 420 | Loss: 0.3962 | LM: 0.4071 | LB: 1.1631 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.480/SR1: 0.458 | LR: 4.33e-05 |
| [2026-04-25 18:12:42] Epoch 1 | Step 430 | Loss: 0.3949 | LM: 0.4044 | LB: 1.1629 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.480/SR1: 0.458 | LR: 4.42e-05 |
| [2026-04-25 18:12:49] Epoch 1 | Step 440 | Loss: 0.3919 | LM: 0.4015 | LB: 1.1628 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.480/SR1: 0.458 | LR: 4.51e-05 |
| [2026-04-25 18:12:56] Epoch 1 | Step 450 | Loss: 0.3903 | LM: 0.4001 | LB: 1.1626 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.480/SR1: 0.458 | LR: 4.60e-05 |
| [2026-04-25 18:13:03] Epoch 1 | Step 460 | Loss: 0.3885 | LM: 0.3979 | LB: 1.1627 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.480/SR1: 0.458 | LR: 4.69e-05 |
| [2026-04-25 18:13:10] Epoch 1 | Step 470 | Loss: 0.3861 | LM: 0.3953 | LB: 1.1625 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.480/SR1: 0.458 | LR: 4.78e-05 |
| [2026-04-25 18:13:18] Epoch 1 | Step 480 | Loss: 0.3843 | LM: 0.3928 | LB: 1.1627 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.480/SR1: 0.458 | LR: 4.87e-05 |
| [2026-04-25 18:13:25] Epoch 1 | Step 490 | Loss: 0.3822 | LM: 0.3901 | LB: 1.1628 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.480/SR1: 0.458 | LR: 4.96e-05 |
| [2026-04-25 18:13:32] Epoch 1 | Step 500 | Loss: 0.3804 | LM: 0.3867 | LB: 1.1626 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.480/SR1: 0.458 | LR: 5.00e-05 |
| [2026-04-25 18:13:39] Epoch 1 | Step 510 | Loss: 0.3782 | LM: 0.3831 | LB: 1.1626 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.480/SR1: 0.458 | LR: 5.00e-05 |
| [2026-04-25 18:13:47] Epoch 1 | Step 520 | Loss: 0.3773 | LM: 0.3825 | LB: 1.1622 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.480/SR1: 0.458 | LR: 5.00e-05 |
| [2026-04-25 18:13:54] Epoch 1 | Step 530 | Loss: 0.3758 | LM: 0.3813 | LB: 1.1620 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.479/SR1: 0.458 | LR: 5.00e-05 |
| [2026-04-25 18:14:01] Epoch 1 | Step 540 | Loss: 0.3738 | LM: 0.3799 | LB: 1.1619 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.479/SR1: 0.458 | LR: 5.00e-05 |
| [2026-04-25 18:14:08] Epoch 1 | Step 550 | Loss: 0.3717 | LM: 0.3775 | LB: 1.1617 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.479/SR1: 0.457 | LR: 5.00e-05 |
| [2026-04-25 18:14:15] Epoch 1 | Step 560 | Loss: 0.3705 | LM: 0.3747 | LB: 1.1615 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.479/SR1: 0.457 | LR: 5.00e-05 |
| [2026-04-25 18:14:22] Epoch 1 | Step 570 | Loss: 0.3693 | LM: 0.3735 | LB: 1.1616 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.479/SR1: 0.457 | LR: 5.00e-05 |
| [2026-04-25 18:14:30] Epoch 1 | Step 580 | Loss: 0.3679 | LM: 0.3720 | LB: 1.1614 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.479/SR1: 0.457 | LR: 5.00e-05 |
| [2026-04-25 18:14:37] Epoch 1 | Step 590 | Loss: 0.3670 | LM: 0.3710 | LB: 1.1611 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.479/SR1: 0.457 | LR: 5.00e-05 |
| [2026-04-25 18:14:44] Epoch 1 | Step 600 | Loss: 0.3655 | LM: 0.3686 | LB: 1.1607 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.478/SR1: 0.457 | LR: 5.00e-05 |
| [2026-04-25 18:14:51] Epoch 1 | Step 610 | Loss: 0.3649 | LM: 0.3669 | LB: 1.1607 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.478/SR1: 0.457 | LR: 5.00e-05 |
| [2026-04-25 18:14:59] Epoch 1 | Step 620 | Loss: 0.3641 | LM: 0.3658 | LB: 1.1607 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.478/SR1: 0.457 | LR: 5.00e-05 |
| [2026-04-25 18:15:07] Epoch 1 | Step 630 | Loss: 0.3630 | LM: 0.3656 | LB: 1.1606 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.478/SR1: 0.457 | LR: 5.00e-05 |
| [2026-04-25 18:15:15] Epoch 1 | Step 640 | Loss: 0.3623 | LM: 0.3640 | LB: 1.1605 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.478/SR1: 0.457 | LR: 5.00e-05 |
| [2026-04-25 18:15:22] Epoch 1 | Step 650 | Loss: 0.3612 | LM: 0.3626 | LB: 1.1602 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.478/SR1: 0.456 | LR: 5.00e-05 |
| [2026-04-25 18:15:29] Epoch 1 | Step 660 | Loss: 0.3608 | LM: 0.3614 | LB: 1.1600 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.478/SR1: 0.456 | LR: 5.00e-05 |
| [2026-04-25 18:15:37] Epoch 1 | Step 670 | Loss: 0.3597 | LM: 0.3601 | LB: 1.1600 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.478/SR1: 0.456 | LR: 5.00e-05 |
| [2026-04-25 18:15:44] Epoch 1 | Step 680 | Loss: 0.3589 | LM: 0.3598 | LB: 1.1603 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.478/SR1: 0.456 | LR: 5.00e-05 |
| [2026-04-25 18:15:51] Epoch 1 | Step 690 | Loss: 0.3581 | LM: 0.3599 | LB: 1.1599 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.478/SR1: 0.456 | LR: 5.00e-05 |
| [2026-04-25 18:15:58] Epoch 1 | Step 700 | Loss: 0.3577 | LM: 0.3610 | LB: 1.1598 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.478/SR1: 0.456 | LR: 5.00e-05 |
| [2026-04-25 18:16:05] Epoch 1 | Step 710 | Loss: 0.3566 | LM: 0.3608 | LB: 1.1596 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.478/SR1: 0.456 | LR: 5.00e-05 |
| [2026-04-25 18:16:12] Epoch 1 | Step 720 | Loss: 0.3557 | LM: 0.3601 | LB: 1.1594 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.477/SR1: 0.456 | LR: 5.00e-05 |
| [2026-04-25 18:16:20] Epoch 1 | Step 730 | Loss: 0.3551 | LM: 0.3592 | LB: 1.1594 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.477/SR1: 0.456 | LR: 5.00e-05 |
| [2026-04-25 18:16:27] Epoch 1 | Step 740 | Loss: 0.3541 | LM: 0.3581 | LB: 1.1592 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.477/SR1: 0.455 | LR: 5.00e-05 |
| [2026-04-25 18:16:34] Epoch 1 | Step 750 | Loss: 0.3531 | LM: 0.3569 | LB: 1.1588 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.477/SR1: 0.455 | LR: 5.00e-05 |
| [2026-04-25 18:16:41] Epoch 1 | Step 760 | Loss: 0.3529 | LM: 0.3558 | LB: 1.1586 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.477/SR1: 0.455 | LR: 5.00e-05 |
| [2026-04-25 18:16:48] Epoch 1 | Step 770 | Loss: 0.3528 | LM: 0.3553 | LB: 1.1585 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.477/SR1: 0.455 | LR: 5.00e-05 |
| [2026-04-25 18:16:56] Epoch 1 | Step 780 | Loss: 0.3519 | LM: 0.3542 | LB: 1.1583 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.477/SR1: 0.455 | LR: 5.00e-05 |
| [2026-04-25 18:17:03] Epoch 1 | Step 790 | Loss: 0.3510 | LM: 0.3533 | LB: 1.1583 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.477/SR1: 0.455 | LR: 5.00e-05 |
| [2026-04-25 18:17:10] Epoch 1 | Step 800 | Loss: 0.3499 | LM: 0.3515 | LB: 1.1582 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.477/SR1: 0.455 | LR: 5.00e-05 |
| [2026-04-25 18:17:17] Epoch 1 | Step 810 | Loss: 0.3493 | LM: 0.3513 | LB: 1.1583 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.477/SR1: 0.455 | LR: 5.00e-05 |
| [2026-04-25 18:17:25] Epoch 1 | Step 820 | Loss: 0.3486 | LM: 0.3504 | LB: 1.1582 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.477/SR1: 0.455 | LR: 5.00e-05 |
| [2026-04-25 18:17:32] Epoch 1 | Step 830 | Loss: 0.3483 | LM: 0.3504 | LB: 1.1581 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.477/SR1: 0.455 | LR: 5.00e-05 |
| [2026-04-25 18:17:39] Epoch 1 | Step 840 | Loss: 0.3478 | LM: 0.3492 | LB: 1.1582 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.477/SR1: 0.455 | LR: 5.00e-05 |
| [2026-04-25 18:17:48] Epoch 1 | Step 850 | Loss: 0.3468 | LM: 0.3485 | LB: 1.1581 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.477/SR1: 0.455 | LR: 5.00e-05 |
| [2026-04-25 18:17:56] Epoch 1 | Step 860 | Loss: 0.3463 | LM: 0.3471 | LB: 1.1581 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.477/SR1: 0.455 | LR: 5.00e-05 |
| [2026-04-25 18:18:03] Epoch 1 | Step 870 | Loss: 0.3462 | LM: 0.3466 | LB: 1.1580 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.476/SR1: 0.455 | LR: 5.00e-05 |
| [2026-04-25 18:18:10] Epoch 1 | Step 880 | Loss: 0.3457 | LM: 0.3465 | LB: 1.1580 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.476/SR1: 0.454 | LR: 5.00e-05 |
| [2026-04-25 18:18:17] Epoch 1 | Step 890 | Loss: 0.3452 | LM: 0.3456 | LB: 1.1579 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.476/SR1: 0.454 | LR: 5.00e-05 |
| [2026-04-25 18:18:24] Epoch 1 | Step 900 | Loss: 0.3449 | LM: 0.3447 | LB: 1.1582 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.477/SR1: 0.455 | LR: 5.00e-05 |
| [2026-04-25 18:18:32] Epoch 1 | Step 910 | Loss: 0.3447 | LM: 0.3439 | LB: 1.1580 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.476/SR1: 0.454 | LR: 5.00e-05 |
| [2026-04-25 18:18:39] Epoch 1 | Step 920 | Loss: 0.3446 | LM: 0.3437 | LB: 1.1579 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.476/SR1: 0.454 | LR: 5.00e-05 |
| [2026-04-25 18:18:46] Epoch 1 | Step 930 | Loss: 0.3441 | LM: 0.3427 | LB: 1.1578 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.476/SR1: 0.454 | LR: 5.00e-05 |
| [2026-04-25 18:18:53] Epoch 1 | Step 940 | Loss: 0.3439 | LM: 0.3420 | LB: 1.1577 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.476/SR1: 0.454 | LR: 5.00e-05 |
| [2026-04-25 18:19:00] Epoch 1 | Step 950 | Loss: 0.3431 | LM: 0.3415 | LB: 1.1577 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.476/SR1: 0.454 | LR: 5.00e-05 |
| [2026-04-25 18:19:08] Epoch 1 | Step 960 | Loss: 0.3423 | LM: 0.3415 | LB: 1.1576 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.476/SR1: 0.454 | LR: 5.00e-05 |
| [2026-04-25 18:19:15] Epoch 1 | Step 970 | Loss: 0.3418 | LM: 0.3417 | LB: 1.1574 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.476/SR1: 0.454 | LR: 5.00e-05 |
| [2026-04-25 18:19:22] Epoch 1 | Step 980 | Loss: 0.3411 | LM: 0.3403 | LB: 1.1574 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.476/SR1: 0.454 | LR: 5.00e-05 |
| [2026-04-25 18:19:30] Epoch 1 | Step 990 | Loss: 0.3403 | LM: 0.3398 | LB: 1.1573 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.476/SR1: 0.454 | LR: 5.00e-05 |
| [2026-04-25 18:19:37] Epoch 1 | Step 1000 | Loss: 0.3397 | LM: 0.3388 | LB: 1.1570 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.476/SR1: 0.453 | LR: 5.00e-05 |
| [2026-04-25 18:19:44] Epoch 1 | Step 1010 | Loss: 0.3396 | LM: 0.3388 | LB: 1.1569 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.453 | LR: 5.00e-05 |
| [2026-04-25 18:19:51] Epoch 1 | Step 1020 | Loss: 0.3393 | LM: 0.3388 | LB: 1.1568 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.453 | LR: 5.00e-05 |
| [2026-04-25 18:19:58] Epoch 1 | Step 1030 | Loss: 0.3391 | LM: 0.3386 | LB: 1.1566 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.453 | LR: 5.00e-05 |
| [2026-04-25 18:20:06] Epoch 1 | Step 1040 | Loss: 0.3383 | LM: 0.3378 | LB: 1.1565 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.453 | LR: 5.00e-05 |
| [2026-04-25 18:20:13] Epoch 1 | Step 1050 | Loss: 0.3377 | LM: 0.3371 | LB: 1.1564 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.453 | LR: 5.00e-05 |
| [2026-04-25 18:20:20] Epoch 1 | Step 1060 | Loss: 0.3368 | LM: 0.3360 | LB: 1.1564 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.453 | LR: 5.00e-05 |
| [2026-04-25 18:20:27] Epoch 1 | Step 1070 | Loss: 0.3364 | LM: 0.3351 | LB: 1.1563 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.453 | LR: 5.00e-05 |
| [2026-04-25 18:20:34] Epoch 1 | Step 1080 | Loss: 0.3364 | LM: 0.3339 | LB: 1.1565 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.453 | LR: 5.00e-05 |
| [2026-04-25 18:20:41] Epoch 1 | Step 1090 | Loss: 0.3366 | LM: 0.3341 | LB: 1.1565 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.453 | LR: 5.00e-05 |
| [2026-04-25 18:20:49] Epoch 1 | Step 1100 | Loss: 0.3362 | LM: 0.3341 | LB: 1.1565 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.453 | LR: 5.00e-05 |
| [2026-04-25 18:20:56] Epoch 1 | Step 1110 | Loss: 0.3360 | LM: 0.3332 | LB: 1.1565 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.453 | LR: 5.00e-05 |
| [2026-04-25 18:21:03] Epoch 1 | Step 1120 | Loss: 0.3360 | LM: 0.3327 | LB: 1.1565 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.453 | LR: 5.00e-05 |
| [2026-04-25 18:21:10] Epoch 1 | Step 1130 | Loss: 0.3360 | LM: 0.3319 | LB: 1.1564 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.453 | LR: 5.00e-05 |
| [2026-04-25 18:21:18] Epoch 1 | Step 1140 | Loss: 0.3357 | LM: 0.3314 | LB: 1.1561 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.452 | LR: 5.00e-05 |
| [2026-04-25 18:21:25] Epoch 1 | Step 1150 | Loss: 0.3350 | LM: 0.3306 | LB: 1.1561 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.452 | LR: 5.00e-05 |
| [2026-04-25 18:21:32] Epoch 1 | Step 1160 | Loss: 0.3350 | LM: 0.3308 | LB: 1.1559 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.452 | LR: 5.00e-05 |
| [2026-04-25 18:21:39] Epoch 1 | Step 1170 | Loss: 0.3350 | LM: 0.3302 | LB: 1.1558 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.475/SR1: 0.452 | LR: 5.00e-05 |
| [2026-04-25 18:21:46] Epoch 1 | Step 1180 | Loss: 0.3346 | LM: 0.3301 | LB: 1.1555 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.452 | LR: 5.00e-05 |
| [2026-04-25 18:21:54] Epoch 1 | Step 1190 | Loss: 0.3344 | LM: 0.3298 | LB: 1.1555 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.452 | LR: 5.00e-05 |
| [2026-04-25 18:22:01] Epoch 1 | Step 1200 | Loss: 0.3339 | LM: 0.3289 | LB: 1.1554 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.452 | LR: 5.00e-05 |
| [2026-04-25 18:22:08] Epoch 1 | Step 1210 | Loss: 0.3334 | LM: 0.3285 | LB: 1.1554 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.452 | LR: 5.00e-05 |
| [2026-04-25 18:22:15] Epoch 1 | Step 1220 | Loss: 0.3327 | LM: 0.3275 | LB: 1.1555 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.452 | LR: 5.00e-05 |
| [2026-04-25 18:22:22] Epoch 1 | Step 1230 | Loss: 0.3326 | LM: 0.3277 | LB: 1.1554 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.452 | LR: 5.00e-05 |
| [2026-04-25 18:22:30] Epoch 1 | Step 1240 | Loss: 0.3325 | LM: 0.3278 | LB: 1.1553 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.452 | LR: 5.00e-05 |
| [2026-04-25 18:22:37] Epoch 1 | Step 1250 | Loss: 0.3321 | LM: 0.3278 | LB: 1.1552 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.452 | LR: 5.00e-05 |
| [2026-04-25 18:22:44] Epoch 1 | Step 1260 | Loss: 0.3316 | LM: 0.3275 | LB: 1.1552 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.452 | LR: 5.00e-05 |
| [2026-04-25 18:22:51] Epoch 1 | Step 1270 | Loss: 0.3310 | LM: 0.3269 | LB: 1.1553 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.452 | LR: 5.00e-05 |
| [2026-04-25 18:22:59] Epoch 1 | Step 1280 | Loss: 0.3308 | LM: 0.3265 | LB: 1.1551 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.452 | LR: 5.00e-05 |
| [2026-04-25 18:23:06] Epoch 1 | Step 1290 | Loss: 0.3306 | LM: 0.3266 | LB: 1.1551 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.452 | LR: 5.00e-05 |
| [2026-04-25 18:23:13] Epoch 1 | Step 1300 | Loss: 0.3301 | LM: 0.3263 | LB: 1.1552 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.452 | LR: 5.00e-05 |
| [2026-04-25 18:23:20] Epoch 1 | Step 1310 | Loss: 0.3298 | LM: 0.3255 | LB: 1.1550 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.452 | LR: 5.00e-05 |
| [2026-04-25 18:23:27] Epoch 1 | Step 1320 | Loss: 0.3296 | LM: 0.3250 | LB: 1.1549 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.451 | LR: 5.00e-05 |
| [2026-04-25 18:23:35] Epoch 1 | Step 1330 | Loss: 0.3293 | LM: 0.3245 | LB: 1.1548 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.451 | LR: 5.00e-05 |
| [2026-04-25 18:23:42] Epoch 1 | Step 1340 | Loss: 0.3292 | LM: 0.3245 | LB: 1.1547 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.451 | LR: 5.00e-05 |
| [2026-04-25 18:23:49] Epoch 1 | Step 1350 | Loss: 0.3291 | LM: 0.3247 | LB: 1.1550 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.451 | LR: 5.00e-05 |
| [2026-04-25 18:23:56] Epoch 1 | Step 1360 | Loss: 0.3288 | LM: 0.3238 | LB: 1.1550 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.451 | LR: 5.00e-05 |
| [2026-04-25 18:24:03] Epoch 1 | Step 1370 | Loss: 0.3286 | LM: 0.3234 | LB: 1.1549 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.451 | LR: 5.00e-05 |
| [2026-04-25 18:24:11] Epoch 1 | Step 1380 | Loss: 0.3287 | LM: 0.3231 | LB: 1.1548 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.451 | LR: 5.00e-05 |
| [2026-04-25 18:24:18] Epoch 1 | Step 1390 | Loss: 0.3290 | LM: 0.3233 | LB: 1.1545 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.474/SR1: 0.451 | LR: 5.00e-05 |
| [2026-04-25 18:24:25] Epoch 1 | Step 1400 | Loss: 0.3288 | LM: 0.3229 | LB: 1.1543 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.473/SR1: 0.451 | LR: 5.00e-05 |
| [2026-04-25 18:24:32] Epoch 1 | Step 1410 | Loss: 0.3282 | LM: 0.3217 | LB: 1.1542 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.473/SR1: 0.451 | LR: 5.00e-05 |
| [2026-04-25 18:24:40] Epoch 1 | Step 1420 | Loss: 0.3280 | LM: 0.3214 | LB: 1.1543 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.473/SR1: 0.451 | LR: 5.00e-05 |
| [2026-04-25 18:24:47] Epoch 1 | Step 1430 | Loss: 0.3277 | LM: 0.3213 | LB: 1.1543 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.473/SR1: 0.451 | LR: 5.00e-05 |
| [2026-04-25 18:24:54] Epoch 1 | Step 1440 | Loss: 0.3273 | LM: 0.3209 | LB: 1.1542 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.473/SR1: 0.451 | LR: 5.00e-05 |
| [2026-04-25 18:25:01] Epoch 1 | Step 1450 | Loss: 0.3271 | LM: 0.3204 | LB: 1.1542 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.473/SR1: 0.451 | LR: 5.00e-05 |
| [2026-04-25 18:25:08] Epoch 1 | Step 1460 | Loss: 0.3266 | LM: 0.3198 | LB: 1.1540 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.473/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:25:16] Epoch 1 | Step 1470 | Loss: 0.3266 | LM: 0.3200 | LB: 1.1541 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.473/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:25:23] Epoch 1 | Step 1480 | Loss: 0.3263 | LM: 0.3197 | LB: 1.1540 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.473/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:25:30] Epoch 1 | Step 1490 | Loss: 0.3262 | LM: 0.3196 | LB: 1.1541 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.473/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:25:37] Epoch 1 | Step 1500 | Loss: 0.3259 | LM: 0.3192 | LB: 1.1540 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.473/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:25:44] Epoch 1 | Step 1510 | Loss: 0.3258 | LM: 0.3192 | LB: 1.1540 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.473/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:25:52] Epoch 1 | Step 1520 | Loss: 0.3256 | LM: 0.3188 | LB: 1.1541 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.473/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:25:59] Epoch 1 | Step 1530 | Loss: 0.3253 | LM: 0.3185 | LB: 1.1540 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.473/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:26:06] Epoch 1 | Step 1540 | Loss: 0.3253 | LM: 0.3187 | LB: 1.1540 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.473/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:26:13] Epoch 1 | Step 1550 | Loss: 0.3251 | LM: 0.3184 | LB: 1.1540 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.473/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:26:20] Epoch 1 | Step 1560 | Loss: 0.3249 | LM: 0.3181 | LB: 1.1539 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.473/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:26:28] Epoch 1 | Step 1570 | Loss: 0.3249 | LM: 0.3181 | LB: 1.1538 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.473/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:26:35] Epoch 1 | Step 1580 | Loss: 0.3248 | LM: 0.3184 | LB: 1.1539 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.473/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:26:42] Epoch 1 | Step 1590 | Loss: 0.3247 | LM: 0.3189 | LB: 1.1539 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.473/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:26:49] Epoch 1 | Step 1600 | Loss: 0.3245 | LM: 0.3186 | LB: 1.1539 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.473/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:26:56] Epoch 1 | Step 1610 | Loss: 0.3240 | LM: 0.3180 | LB: 1.1539 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.473/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:27:04] Epoch 1 | Step 1620 | Loss: 0.3236 | LM: 0.3176 | LB: 1.1539 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.473/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:27:11] Epoch 1 | Step 1630 | Loss: 0.3236 | LM: 0.3174 | LB: 1.1537 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.473/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:27:18] Epoch 1 | Step 1640 | Loss: 0.3233 | LM: 0.3174 | LB: 1.1535 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.472/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:27:25] Epoch 1 | Step 1650 | Loss: 0.3229 | LM: 0.3174 | LB: 1.1535 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.472/SR1: 0.450 | LR: 5.00e-05 |
| [2026-04-25 18:27:32] Epoch 1 | Step 1660 | Loss: 0.3226 | LM: 0.3166 | LB: 1.1534 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.472/SR1: 0.449 | LR: 5.00e-05 |
| [2026-04-25 18:27:40] Epoch 1 | Step 1670 | Loss: 0.3227 | LM: 0.3165 | LB: 1.1534 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.472/SR1: 0.449 | LR: 5.00e-05 |
| [2026-04-25 18:27:47] Epoch 1 | Step 1680 | Loss: 0.3226 | LM: 0.3161 | LB: 1.1534 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.472/SR1: 0.449 | LR: 5.00e-05 |
| [2026-04-25 18:27:54] Epoch 1 | Step 1690 | Loss: 0.3224 | LM: 0.3159 | LB: 1.1533 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.472/SR1: 0.449 | LR: 5.00e-05 |
| [2026-04-25 18:28:01] Epoch 1 | Step 1700 | Loss: 0.3219 | LM: 0.3153 | LB: 1.1533 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.472/SR1: 0.449 | LR: 5.00e-05 |
| [2026-04-25 18:28:09] Epoch 1 | Step 1710 | Loss: 0.3218 | LM: 0.3145 | LB: 1.1532 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.472/SR1: 0.449 | LR: 5.00e-05 |
| [2026-04-25 18:28:16] Epoch 1 | Step 1720 | Loss: 0.3216 | LM: 0.3145 | LB: 1.1530 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.472/SR1: 0.449 | LR: 5.00e-05 |
| [2026-04-25 18:28:23] Epoch 1 | Step 1730 | Loss: 0.3214 | LM: 0.3144 | LB: 1.1530 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.472/SR1: 0.449 | LR: 5.00e-05 |
| [2026-04-25 18:28:30] Epoch 1 | Step 1740 | Loss: 0.3213 | LM: 0.3146 | LB: 1.1530 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.472/SR1: 0.449 | LR: 5.00e-05 |
| [2026-04-25 18:28:37] Epoch 1 | Step 1750 | Loss: 0.3215 | LM: 0.3147 | LB: 1.1529 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.472/SR1: 0.449 | LR: 5.00e-05 |
| [2026-04-25 18:28:45] Epoch 1 | Step 1760 | Loss: 0.3213 | LM: 0.3146 | LB: 1.1527 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.472/SR1: 0.449 | LR: 5.00e-05 |
| [2026-04-25 18:28:52] Epoch 1 | Step 1770 | Loss: 0.3212 | LM: 0.3145 | LB: 1.1526 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.472/SR1: 0.449 | LR: 5.00e-05 |
| [2026-04-25 18:28:59] Epoch 1 | Step 1780 | Loss: 0.3211 | LM: 0.3143 | LB: 1.1526 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.472/SR1: 0.449 | LR: 5.00e-05 |
| [2026-04-25 18:29:06] Epoch 1 | Step 1790 | Loss: 0.3211 | LM: 0.3139 | LB: 1.1525 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.472/SR1: 0.449 | LR: 5.00e-05 |
| [2026-04-25 18:29:13] Epoch 1 | Step 1800 | Loss: 0.3210 | LM: 0.3138 | LB: 1.1524 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.471/SR1: 0.449 | LR: 5.00e-05 |
| [2026-04-25 18:29:21] Epoch 1 | Step 1810 | Loss: 0.3208 | LM: 0.3137 | LB: 1.1524 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.471/SR1: 0.449 | LR: 5.00e-05 |
| [2026-04-25 18:29:28] Epoch 1 | Step 1820 | Loss: 0.3209 | LM: 0.3136 | LB: 1.1523 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.471/SR1: 0.449 | LR: 5.00e-05 |
| [2026-04-25 18:29:35] Epoch 1 | Step 1830 | Loss: 0.3208 | LM: 0.3142 | LB: 1.1524 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.471/SR1: 0.448 | LR: 5.00e-05 |
| [2026-04-25 18:29:42] Epoch 1 | Step 1840 | Loss: 0.3207 | LM: 0.3143 | LB: 1.1523 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.471/SR1: 0.448 | LR: 5.00e-05 |
| [2026-04-25 18:29:49] Epoch 1 | Step 1850 | Loss: 0.3205 | LM: 0.3140 | LB: 1.1522 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.471/SR1: 0.448 | LR: 5.00e-05 |
| [2026-04-25 18:29:57] Epoch 1 | Step 1860 | Loss: 0.3204 | LM: 0.3136 | LB: 1.1522 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.471/SR1: 0.448 | LR: 5.00e-05 |
| [2026-04-25 18:30:04] Epoch 1 | Step 1870 | Loss: 0.3202 | LM: 0.3131 | LB: 1.1522 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.471/SR1: 0.448 | LR: 5.00e-05 |
| [2026-04-25 18:30:11] Epoch 1 | Step 1880 | Loss: 0.3201 | LM: 0.3131 | LB: 1.1520 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.471/SR1: 0.448 | LR: 5.00e-05 |
| [2026-04-25 18:30:18] Epoch 1 | Step 1890 | Loss: 0.3200 | LM: 0.3128 | LB: 1.1519 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.471/SR1: 0.448 | LR: 5.00e-05 |
| [2026-04-25 18:30:26] Epoch 1 | Step 1900 | Loss: 0.3199 | LM: 0.3128 | LB: 1.1517 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.471/SR1: 0.448 | LR: 5.00e-05 |
| [2026-04-25 18:30:33] Epoch 1 | Step 1910 | Loss: 0.3198 | LM: 0.3128 | LB: 1.1517 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.471/SR1: 0.448 | LR: 5.00e-05 |
| [2026-04-25 18:30:40] Epoch 1 | Step 1920 | Loss: 0.3198 | LM: 0.3124 | LB: 1.1517 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.471/SR1: 0.448 | LR: 5.00e-05 |
| [2026-04-25 18:30:47] Epoch 1 | Step 1930 | Loss: 0.3196 | LM: 0.3122 | LB: 1.1517 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.471/SR1: 0.448 | LR: 5.00e-05 |
| [2026-04-25 18:30:55] Epoch 1 | Step 1940 | Loss: 0.3194 | LM: 0.3122 | LB: 1.1517 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.471/SR1: 0.448 | LR: 5.00e-05 |
| [2026-04-25 18:31:02] Epoch 1 | Step 1950 | Loss: 0.3193 | LM: 0.3122 | LB: 1.1516 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.471/SR1: 0.448 | LR: 5.00e-05 |
| [2026-04-25 18:31:09] Epoch 1 | Step 1960 | Loss: 0.3193 | LM: 0.3123 | LB: 1.1515 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.471/SR1: 0.448 | LR: 5.00e-05 |
| [2026-04-25 18:31:16] Epoch 1 | Step 1970 | Loss: 0.3192 | LM: 0.3126 | LB: 1.1514 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.471/SR1: 0.448 | LR: 5.00e-05 |
| [2026-04-25 18:31:23] Epoch 1 | Step 1980 | Loss: 0.3192 | LM: 0.3125 | LB: 1.1514 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.471/SR1: 0.448 | LR: 5.00e-05 |
| [2026-04-25 18:31:31] Epoch 1 | Step 1990 | Loss: 0.3192 | LM: 0.3125 | LB: 1.1514 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.471/SR1: 0.448 | LR: 5.00e-05 |
| [2026-04-25 18:31:38] Epoch 1 | Step 2000 | Loss: 0.3190 | LM: 0.3122 | LB: 1.1514 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.471/SR1: 0.448 | LR: 5.00e-05 |
| [2026-04-25 18:31:39] Validation | Batch 10/42 | Loss: 0.2830 | LM_LOSS: 0.2717 | LB_LOSS: 1.1332 |
| [2026-04-25 18:31:40] Validation | Batch 20/42 | Loss: 0.3045 | LM_LOSS: 0.2931 | LB_LOSS: 1.1352 |
| [2026-04-25 18:31:41] Validation | Batch 30/42 | Loss: 0.2957 | LM_LOSS: 0.2844 | LB_LOSS: 1.1313 |
| [2026-04-25 18:31:43] Validation | Batch 40/42 | Loss: 0.3000 | LM_LOSS: 0.2887 | LB_LOSS: 1.1300 |
| [2026-04-25 18:31:43] Validation | Batch 42/42 | Loss: 0.2993 | LM_LOSS: 0.2880 | LB_LOSS: 1.1303 |
| [2026-04-25 18:31:43] Validation | Loss: 0.2993 | LM_LOSS: 0.2880 | LB_LOSS: 1.1303 | PPL: 1.33 | Time: 4.87s |
| [2026-04-25 18:31:45] New best model saved! Val loss: 0.2993 |
| [2026-04-25 18:31:53] Epoch 1 | Step 2010 | Loss: 0.3191 | LM: 0.3124 | LB: 1.1513 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.470/SR1: 0.447 | LR: 5.00e-05 |
| [2026-04-25 18:32:00] Epoch 1 | Step 2020 | Loss: 0.3189 | LM: 0.3124 | LB: 1.1512 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.470/SR1: 0.447 | LR: 5.00e-05 |
| [2026-04-25 18:32:07] Epoch 1 | Step 2030 | Loss: 0.3188 | LM: 0.3121 | LB: 1.1512 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.470/SR1: 0.447 | LR: 5.00e-05 |
| [2026-04-25 18:32:14] Epoch 1 | Step 2040 | Loss: 0.3186 | LM: 0.3117 | LB: 1.1511 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.470/SR1: 0.447 | LR: 5.00e-05 |
| [2026-04-25 18:32:21] Epoch 1 | Step 2050 | Loss: 0.3186 | LM: 0.3115 | LB: 1.1510 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.470/SR1: 0.447 | LR: 5.00e-05 |
| [2026-04-25 18:32:29] Epoch 1 | Step 2060 | Loss: 0.3185 | LM: 0.3116 | LB: 1.1510 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.470/SR1: 0.447 | LR: 5.00e-05 |
| [2026-04-25 18:32:36] Epoch 1 | Step 2070 | Loss: 0.3181 | LM: 0.3111 | LB: 1.1509 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.470/SR1: 0.447 | LR: 5.00e-05 |
| [2026-04-25 18:32:43] Epoch 1 | Step 2080 | Loss: 0.3178 | LM: 0.3108 | LB: 1.1508 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.470/SR1: 0.447 | LR: 5.00e-05 |
| [2026-04-25 18:32:51] Epoch 1 | Step 2090 | Loss: 0.3178 | LM: 0.3109 | LB: 1.1507 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.470/SR1: 0.447 | LR: 5.00e-05 |
| [2026-04-25 18:32:58] Epoch 1 | Step 2100 | Loss: 0.3176 | LM: 0.3105 | LB: 1.1506 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.470/SR1: 0.447 | LR: 5.00e-05 |
| [2026-04-25 18:33:05] Epoch 1 | Step 2110 | Loss: 0.3176 | LM: 0.3103 | LB: 1.1504 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.470/SR1: 0.447 | LR: 5.00e-05 |
| [2026-04-25 18:33:12] Epoch 1 | Step 2120 | Loss: 0.3174 | LM: 0.3106 | LB: 1.1504 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.470/SR1: 0.447 | LR: 5.00e-05 |
| [2026-04-25 18:33:19] Epoch 1 | Step 2130 | Loss: 0.3173 | LM: 0.3107 | LB: 1.1504 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.470/SR1: 0.447 | LR: 5.00e-05 |
| [2026-04-25 18:33:26] Epoch 1 | Step 2140 | Loss: 0.3170 | LM: 0.3109 | LB: 1.1504 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.470/SR1: 0.447 | LR: 5.00e-05 |
| [2026-04-25 18:33:34] Epoch 1 | Step 2150 | Loss: 0.3169 | LM: 0.3107 | LB: 1.1503 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.470/SR1: 0.447 | LR: 5.00e-05 |
| [2026-04-25 18:33:41] Epoch 1 | Step 2160 | Loss: 0.3169 | LM: 0.3106 | LB: 1.1503 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.470/SR1: 0.447 | LR: 5.00e-05 |
| [2026-04-25 18:33:48] Epoch 1 | Step 2170 | Loss: 0.3168 | LM: 0.3103 | LB: 1.1503 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.470/SR1: 0.447 | LR: 5.00e-05 |
| [2026-04-25 18:33:55] Epoch 1 | Step 2180 | Loss: 0.3166 | LM: 0.3102 | LB: 1.1503 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.470/SR1: 0.447 | LR: 5.00e-05 |
| [2026-04-25 18:34:03] Epoch 1 | Step 2190 | Loss: 0.3164 | LM: 0.3099 | LB: 1.1502 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.469/SR1: 0.447 | LR: 5.00e-05 |
| [2026-04-25 18:34:10] Epoch 1 | Step 2200 | Loss: 0.3163 | LM: 0.3099 | LB: 1.1501 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.469/SR1: 0.446 | LR: 5.00e-05 |
| [2026-04-25 18:34:17] Epoch 1 | Step 2210 | Loss: 0.3163 | LM: 0.3101 | LB: 1.1500 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.469/SR1: 0.446 | LR: 5.00e-05 |
| [2026-04-25 18:34:24] Epoch 1 | Step 2220 | Loss: 0.3164 | LM: 0.3101 | LB: 1.1500 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.469/SR1: 0.446 | LR: 5.00e-05 |
| [2026-04-25 18:34:32] Epoch 1 | Step 2230 | Loss: 0.3164 | LM: 0.3100 | LB: 1.1499 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.469/SR1: 0.446 | LR: 5.00e-05 |
| [2026-04-25 18:34:39] Epoch 1 | Step 2240 | Loss: 0.3165 | LM: 0.3096 | LB: 1.1499 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.469/SR1: 0.446 | LR: 5.00e-05 |
| [2026-04-25 18:34:46] Epoch 1 | Step 2250 | Loss: 0.3166 | LM: 0.3097 | LB: 1.1498 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.469/SR1: 0.446 | LR: 5.00e-05 |
| [2026-04-25 18:34:53] Epoch 1 | Step 2260 | Loss: 0.3164 | LM: 0.3093 | LB: 1.1497 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.469/SR1: 0.446 | LR: 5.00e-05 |
| [2026-04-25 18:35:00] Epoch 1 | Step 2270 | Loss: 0.3164 | LM: 0.3096 | LB: 1.1498 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.469/SR1: 0.446 | LR: 5.00e-05 |
| [2026-04-25 18:35:07] Epoch 1 | Step 2280 | Loss: 0.3163 | LM: 0.3094 | LB: 1.1496 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.469/SR1: 0.446 | LR: 5.00e-05 |
| [2026-04-25 18:35:15] Epoch 1 | Step 2290 | Loss: 0.3165 | LM: 0.3096 | LB: 1.1495 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.469/SR1: 0.446 | LR: 5.00e-05 |
| [2026-04-25 18:35:22] Epoch 1 | Step 2300 | Loss: 0.3165 | LM: 0.3092 | LB: 1.1494 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.469/SR1: 0.446 | LR: 5.00e-05 |
| [2026-04-25 18:35:29] Epoch 1 | Step 2310 | Loss: 0.3163 | LM: 0.3090 | LB: 1.1493 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.469/SR1: 0.446 | LR: 5.00e-05 |
| [2026-04-25 18:35:37] Epoch 1 | Step 2320 | Loss: 0.3164 | LM: 0.3091 | LB: 1.1493 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.469/SR1: 0.446 | LR: 5.00e-05 |
| [2026-04-25 18:35:44] Epoch 1 | Step 2330 | Loss: 0.3163 | LM: 0.3092 | LB: 1.1493 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.469/SR1: 0.446 | LR: 5.00e-05 |
| [2026-04-25 18:35:51] Epoch 1 | Step 2340 | Loss: 0.3162 | LM: 0.3093 | LB: 1.1493 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.469/SR1: 0.446 | LR: 5.00e-05 |
| [2026-04-25 18:35:58] Epoch 1 | Step 2350 | Loss: 0.3160 | LM: 0.3094 | LB: 1.1492 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.469/SR1: 0.446 | LR: 5.00e-05 |
| [2026-04-25 18:36:05] Epoch 1 | Step 2360 | Loss: 0.3160 | LM: 0.3094 | LB: 1.1492 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.469/SR1: 0.446 | LR: 5.00e-05 |
| [2026-04-25 18:36:13] Epoch 1 | Step 2370 | Loss: 0.3159 | LM: 0.3093 | LB: 1.1491 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.469/SR1: 0.446 | LR: 5.00e-05 |
| [2026-04-25 18:36:20] Epoch 1 | Step 2380 | Loss: 0.3157 | LM: 0.3091 | LB: 1.1490 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:36:27] Epoch 1 | Step 2390 | Loss: 0.3157 | LM: 0.3089 | LB: 1.1490 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:36:34] Epoch 1 | Step 2400 | Loss: 0.3156 | LM: 0.3091 | LB: 1.1490 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:36:41] Epoch 1 | Step 2410 | Loss: 0.3156 | LM: 0.3092 | LB: 1.1489 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:36:49] Epoch 1 | Step 2420 | Loss: 0.3157 | LM: 0.3090 | LB: 1.1488 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:36:56] Epoch 1 | Step 2430 | Loss: 0.3157 | LM: 0.3090 | LB: 1.1488 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:37:03] Epoch 1 | Step 2440 | Loss: 0.3155 | LM: 0.3090 | LB: 1.1487 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:37:10] Epoch 1 | Step 2450 | Loss: 0.3155 | LM: 0.3089 | LB: 1.1486 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:37:18] Epoch 1 | Step 2460 | Loss: 0.3154 | LM: 0.3087 | LB: 1.1486 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:37:25] Epoch 1 | Step 2470 | Loss: 0.3153 | LM: 0.3086 | LB: 1.1485 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:37:32] Epoch 1 | Step 2480 | Loss: 0.3152 | LM: 0.3084 | LB: 1.1484 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:37:39] Epoch 1 | Step 2490 | Loss: 0.3151 | LM: 0.3085 | LB: 1.1483 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:37:47] Epoch 1 | Step 2500 | Loss: 0.3150 | LM: 0.3085 | LB: 1.1482 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:37:54] Epoch 1 | Step 2510 | Loss: 0.3149 | LM: 0.3087 | LB: 1.1483 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:38:01] Epoch 1 | Step 2520 | Loss: 0.3146 | LM: 0.3082 | LB: 1.1482 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:38:08] Epoch 1 | Step 2530 | Loss: 0.3145 | LM: 0.3082 | LB: 1.1482 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:38:16] Epoch 1 | Step 2540 | Loss: 0.3143 | LM: 0.3080 | LB: 1.1482 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:38:23] Epoch 1 | Step 2550 | Loss: 0.3141 | LM: 0.3073 | LB: 1.1482 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:38:31] Epoch 1 | Step 2560 | Loss: 0.3140 | LM: 0.3076 | LB: 1.1482 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:38:38] Epoch 1 | Step 2570 | Loss: 0.3141 | LM: 0.3077 | LB: 1.1483 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:38:46] Epoch 1 | Step 2580 | Loss: 0.3141 | LM: 0.3077 | LB: 1.1481 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:38:53] Epoch 1 | Step 2590 | Loss: 0.3141 | LM: 0.3075 | LB: 1.1481 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.445 | LR: 5.00e-05 |
| [2026-04-25 18:39:00] Epoch 1 | Step 2600 | Loss: 0.3141 | LM: 0.3076 | LB: 1.1480 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.468/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:39:07] Epoch 1 | Step 2610 | Loss: 0.3140 | LM: 0.3072 | LB: 1.1480 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:39:14] Epoch 1 | Step 2620 | Loss: 0.3139 | LM: 0.3071 | LB: 1.1480 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:39:22] Epoch 1 | Step 2630 | Loss: 0.3138 | LM: 0.3070 | LB: 1.1479 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:39:29] Epoch 1 | Step 2640 | Loss: 0.3138 | LM: 0.3067 | LB: 1.1479 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:39:36] Epoch 1 | Step 2650 | Loss: 0.3135 | LM: 0.3065 | LB: 1.1479 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:39:43] Epoch 1 | Step 2660 | Loss: 0.3135 | LM: 0.3066 | LB: 1.1478 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:39:50] Epoch 1 | Step 2670 | Loss: 0.3134 | LM: 0.3068 | LB: 1.1478 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:39:58] Epoch 1 | Step 2680 | Loss: 0.3133 | LM: 0.3068 | LB: 1.1478 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:40:05] Epoch 1 | Step 2690 | Loss: 0.3132 | LM: 0.3069 | LB: 1.1478 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:40:12] Epoch 1 | Step 2700 | Loss: 0.3131 | LM: 0.3069 | LB: 1.1477 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:40:19] Epoch 1 | Step 2710 | Loss: 0.3128 | LM: 0.3066 | LB: 1.1476 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:40:27] Epoch 1 | Step 2720 | Loss: 0.3128 | LM: 0.3064 | LB: 1.1475 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:40:34] Epoch 1 | Step 2730 | Loss: 0.3127 | LM: 0.3064 | LB: 1.1475 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:40:41] Epoch 1 | Step 2740 | Loss: 0.3127 | LM: 0.3063 | LB: 1.1475 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:40:48] Epoch 1 | Step 2750 | Loss: 0.3127 | LM: 0.3063 | LB: 1.1474 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:40:55] Epoch 1 | Step 2760 | Loss: 0.3126 | LM: 0.3058 | LB: 1.1473 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:41:03] Epoch 1 | Step 2770 | Loss: 0.3125 | LM: 0.3058 | LB: 1.1472 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:41:10] Epoch 1 | Step 2780 | Loss: 0.3125 | LM: 0.3056 | LB: 1.1471 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:41:17] Epoch 1 | Step 2790 | Loss: 0.3124 | LM: 0.3057 | LB: 1.1471 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:41:25] Epoch 1 | Step 2800 | Loss: 0.3123 | LM: 0.3056 | LB: 1.1471 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.444 | LR: 5.00e-05 |
| [2026-04-25 18:41:32] Epoch 1 | Step 2810 | Loss: 0.3123 | LM: 0.3055 | LB: 1.1471 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:41:39] Epoch 1 | Step 2820 | Loss: 0.3123 | LM: 0.3055 | LB: 1.1470 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:41:46] Epoch 1 | Step 2830 | Loss: 0.3122 | LM: 0.3055 | LB: 1.1469 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:41:54] Epoch 1 | Step 2840 | Loss: 0.3122 | LM: 0.3056 | LB: 1.1470 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:42:01] Epoch 1 | Step 2850 | Loss: 0.3123 | LM: 0.3060 | LB: 1.1470 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:42:08] Epoch 1 | Step 2860 | Loss: 0.3122 | LM: 0.3059 | LB: 1.1470 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:42:15] Epoch 1 | Step 2870 | Loss: 0.3121 | LM: 0.3059 | LB: 1.1470 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.467/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:42:22] Epoch 1 | Step 2880 | Loss: 0.3120 | LM: 0.3057 | LB: 1.1469 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:42:30] Epoch 1 | Step 2890 | Loss: 0.3120 | LM: 0.3055 | LB: 1.1468 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:42:37] Epoch 1 | Step 2900 | Loss: 0.3118 | LM: 0.3052 | LB: 1.1467 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:42:44] Epoch 1 | Step 2910 | Loss: 0.3118 | LM: 0.3052 | LB: 1.1466 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:42:51] Epoch 1 | Step 2920 | Loss: 0.3118 | LM: 0.3054 | LB: 1.1466 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:42:59] Epoch 1 | Step 2930 | Loss: 0.3117 | LM: 0.3051 | LB: 1.1465 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:43:06] Epoch 1 | Step 2940 | Loss: 0.3115 | LM: 0.3049 | LB: 1.1464 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:43:13] Epoch 1 | Step 2950 | Loss: 0.3115 | LM: 0.3049 | LB: 1.1464 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:43:20] Epoch 1 | Step 2960 | Loss: 0.3115 | LM: 0.3050 | LB: 1.1463 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:43:27] Epoch 1 | Step 2970 | Loss: 0.3115 | LM: 0.3052 | LB: 1.1463 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:43:35] Epoch 1 | Step 2980 | Loss: 0.3113 | LM: 0.3051 | LB: 1.1462 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:43:42] Epoch 1 | Step 2990 | Loss: 0.3114 | LM: 0.3050 | LB: 1.1461 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:43:49] Epoch 1 | Step 3000 | Loss: 0.3114 | LM: 0.3050 | LB: 1.1461 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:43:56] Epoch 1 | Step 3010 | Loss: 0.3113 | LM: 0.3049 | LB: 1.1461 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:44:04] Epoch 1 | Step 3020 | Loss: 0.3111 | LM: 0.3048 | LB: 1.1460 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:44:11] Epoch 1 | Step 3030 | Loss: 0.3111 | LM: 0.3047 | LB: 1.1460 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.443 | LR: 5.00e-05 |
| [2026-04-25 18:44:18] Epoch 1 | Step 3040 | Loss: 0.3109 | LM: 0.3045 | LB: 1.1460 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:44:25] Epoch 1 | Step 3050 | Loss: 0.3107 | LM: 0.3042 | LB: 1.1459 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:44:33] Epoch 1 | Step 3060 | Loss: 0.3107 | LM: 0.3045 | LB: 1.1458 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:44:40] Epoch 1 | Step 3070 | Loss: 0.3105 | LM: 0.3044 | LB: 1.1458 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:44:47] Epoch 1 | Step 3080 | Loss: 0.3105 | LM: 0.3041 | LB: 1.1457 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.466/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:44:54] Epoch 1 | Step 3090 | Loss: 0.3103 | LM: 0.3038 | LB: 1.1456 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:45:01] Epoch 1 | Step 3100 | Loss: 0.3102 | LM: 0.3037 | LB: 1.1456 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:45:09] Epoch 1 | Step 3110 | Loss: 0.3101 | LM: 0.3035 | LB: 1.1455 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:45:16] Epoch 1 | Step 3120 | Loss: 0.3103 | LM: 0.3036 | LB: 1.1455 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:45:23] Epoch 1 | Step 3130 | Loss: 0.3102 | LM: 0.3035 | LB: 1.1455 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:45:31] Epoch 1 | Step 3140 | Loss: 0.3102 | LM: 0.3033 | LB: 1.1455 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:45:38] Epoch 1 | Step 3150 | Loss: 0.3103 | LM: 0.3035 | LB: 1.1454 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:45:45] Epoch 1 | Step 3160 | Loss: 0.3102 | LM: 0.3033 | LB: 1.1454 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:45:52] Epoch 1 | Step 3170 | Loss: 0.3102 | LM: 0.3035 | LB: 1.1453 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:45:59] Epoch 1 | Step 3180 | Loss: 0.3102 | LM: 0.3035 | LB: 1.1453 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:46:07] Epoch 1 | Step 3190 | Loss: 0.3100 | LM: 0.3033 | LB: 1.1452 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:46:14] Epoch 1 | Step 3200 | Loss: 0.3099 | LM: 0.3030 | LB: 1.1451 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:46:21] Epoch 1 | Step 3210 | Loss: 0.3099 | LM: 0.3027 | LB: 1.1451 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:46:28] Epoch 1 | Step 3220 | Loss: 0.3097 | LM: 0.3025 | LB: 1.1451 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:46:36] Epoch 1 | Step 3230 | Loss: 0.3097 | LM: 0.3025 | LB: 1.1450 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:46:43] Epoch 1 | Step 3240 | Loss: 0.3095 | LM: 0.3023 | LB: 1.1450 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:46:50] Epoch 1 | Step 3250 | Loss: 0.3095 | LM: 0.3023 | LB: 1.1449 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.442 | LR: 5.00e-05 |
| [2026-04-25 18:46:57] Epoch 1 | Step 3260 | Loss: 0.3095 | LM: 0.3020 | LB: 1.1449 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:47:05] Epoch 1 | Step 3270 | Loss: 0.3095 | LM: 0.3021 | LB: 1.1449 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:47:12] Epoch 1 | Step 3280 | Loss: 0.3092 | LM: 0.3018 | LB: 1.1449 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:47:19] Epoch 1 | Step 3290 | Loss: 0.3092 | LM: 0.3017 | LB: 1.1449 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:47:27] Epoch 1 | Step 3300 | Loss: 0.3091 | LM: 0.3019 | LB: 1.1449 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:47:34] Epoch 1 | Step 3310 | Loss: 0.3090 | LM: 0.3018 | LB: 1.1448 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:47:41] Epoch 1 | Step 3320 | Loss: 0.3090 | LM: 0.3016 | LB: 1.1448 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:47:48] Epoch 1 | Step 3330 | Loss: 0.3090 | LM: 0.3017 | LB: 1.1447 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:47:55] Epoch 1 | Step 3340 | Loss: 0.3090 | LM: 0.3019 | LB: 1.1447 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:48:03] Epoch 1 | Step 3350 | Loss: 0.3088 | LM: 0.3018 | LB: 1.1447 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.465/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:48:10] Epoch 1 | Step 3360 | Loss: 0.3087 | LM: 0.3015 | LB: 1.1446 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:48:17] Epoch 1 | Step 3370 | Loss: 0.3087 | LM: 0.3015 | LB: 1.1446 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:48:25] Epoch 1 | Step 3380 | Loss: 0.3086 | LM: 0.3014 | LB: 1.1446 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:48:32] Epoch 1 | Step 3390 | Loss: 0.3086 | LM: 0.3013 | LB: 1.1446 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:48:39] Epoch 1 | Step 3400 | Loss: 0.3088 | LM: 0.3014 | LB: 1.1445 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:48:46] Epoch 1 | Step 3410 | Loss: 0.3088 | LM: 0.3015 | LB: 1.1444 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:48:53] Epoch 1 | Step 3420 | Loss: 0.3086 | LM: 0.3016 | LB: 1.1444 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:49:01] Epoch 1 | Step 3430 | Loss: 0.3086 | LM: 0.3017 | LB: 1.1443 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:49:08] Epoch 1 | Step 3440 | Loss: 0.3086 | LM: 0.3018 | LB: 1.1443 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:49:15] Epoch 1 | Step 3450 | Loss: 0.3085 | LM: 0.3018 | LB: 1.1442 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:49:22] Epoch 1 | Step 3460 | Loss: 0.3085 | LM: 0.3015 | LB: 1.1442 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:49:30] Epoch 1 | Step 3470 | Loss: 0.3084 | LM: 0.3013 | LB: 1.1441 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:49:37] Epoch 1 | Step 3480 | Loss: 0.3085 | LM: 0.3015 | LB: 1.1441 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:49:44] Epoch 1 | Step 3490 | Loss: 0.3083 | LM: 0.3014 | LB: 1.1441 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:49:51] Epoch 1 | Step 3500 | Loss: 0.3082 | LM: 0.3012 | LB: 1.1440 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.441 | LR: 5.00e-05 |
| [2026-04-25 18:49:58] Epoch 1 | Step 3510 | Loss: 0.3082 | LM: 0.3012 | LB: 1.1440 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:50:06] Epoch 1 | Step 3520 | Loss: 0.3081 | LM: 0.3013 | LB: 1.1439 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:50:13] Epoch 1 | Step 3530 | Loss: 0.3081 | LM: 0.3011 | LB: 1.1438 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:50:20] Epoch 1 | Step 3540 | Loss: 0.3080 | LM: 0.3009 | LB: 1.1438 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:50:27] Epoch 1 | Step 3550 | Loss: 0.3080 | LM: 0.3009 | LB: 1.1438 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:50:34] Epoch 1 | Step 3560 | Loss: 0.3080 | LM: 0.3009 | LB: 1.1437 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:50:41] Epoch 1 | Step 3570 | Loss: 0.3080 | LM: 0.3008 | LB: 1.1437 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:50:49] Epoch 1 | Step 3580 | Loss: 0.3079 | LM: 0.3008 | LB: 1.1436 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:50:56] Epoch 1 | Step 3590 | Loss: 0.3079 | LM: 0.3008 | LB: 1.1436 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.464/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:51:03] Epoch 1 | Step 3600 | Loss: 0.3078 | LM: 0.3008 | LB: 1.1435 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:51:10] Epoch 1 | Step 3610 | Loss: 0.3077 | LM: 0.3005 | LB: 1.1434 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:51:18] Epoch 1 | Step 3620 | Loss: 0.3076 | LM: 0.3002 | LB: 1.1433 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:51:25] Epoch 1 | Step 3630 | Loss: 0.3076 | LM: 0.3004 | LB: 1.1433 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:51:32] Epoch 1 | Step 3640 | Loss: 0.3077 | LM: 0.3005 | LB: 1.1432 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:51:39] Epoch 1 | Step 3650 | Loss: 0.3077 | LM: 0.3007 | LB: 1.1432 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:51:46] Epoch 1 | Step 3660 | Loss: 0.3076 | LM: 0.3007 | LB: 1.1432 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:51:53] Epoch 1 | Step 3670 | Loss: 0.3076 | LM: 0.3003 | LB: 1.1431 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:52:01] Epoch 1 | Step 3680 | Loss: 0.3075 | LM: 0.3004 | LB: 1.1431 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:52:08] Epoch 1 | Step 3690 | Loss: 0.3076 | LM: 0.3005 | LB: 1.1430 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:52:15] Epoch 1 | Step 3700 | Loss: 0.3074 | LM: 0.3005 | LB: 1.1430 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:52:22] Epoch 1 | Step 3710 | Loss: 0.3073 | LM: 0.3003 | LB: 1.1429 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.440 | LR: 5.00e-05 |
| [2026-04-25 18:52:29] Epoch 1 | Step 3720 | Loss: 0.3074 | LM: 0.3005 | LB: 1.1429 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:52:37] Epoch 1 | Step 3730 | Loss: 0.3073 | LM: 0.3004 | LB: 1.1429 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:52:44] Epoch 1 | Step 3740 | Loss: 0.3073 | LM: 0.3002 | LB: 1.1428 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:52:51] Epoch 1 | Step 3750 | Loss: 0.3072 | LM: 0.3000 | LB: 1.1427 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:52:58] Epoch 1 | Step 3760 | Loss: 0.3073 | LM: 0.3001 | LB: 1.1427 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:53:06] Epoch 1 | Step 3770 | Loss: 0.3073 | LM: 0.3002 | LB: 1.1426 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:53:13] Epoch 1 | Step 3780 | Loss: 0.3072 | LM: 0.3001 | LB: 1.1426 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:53:20] Epoch 1 | Step 3790 | Loss: 0.3072 | LM: 0.3001 | LB: 1.1425 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:53:27] Epoch 1 | Step 3800 | Loss: 0.3073 | LM: 0.3001 | LB: 1.1425 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:53:34] Epoch 1 | Step 3810 | Loss: 0.3070 | LM: 0.2999 | LB: 1.1424 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.463/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:53:42] Epoch 1 | Step 3820 | Loss: 0.3070 | LM: 0.2997 | LB: 1.1424 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:53:49] Epoch 1 | Step 3830 | Loss: 0.3070 | LM: 0.2998 | LB: 1.1424 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:53:56] Epoch 1 | Step 3840 | Loss: 0.3070 | LM: 0.3000 | LB: 1.1423 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:54:03] Epoch 1 | Step 3850 | Loss: 0.3069 | LM: 0.2999 | LB: 1.1423 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:54:10] Epoch 1 | Step 3860 | Loss: 0.3068 | LM: 0.2998 | LB: 1.1422 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:54:17] Epoch 1 | Step 3870 | Loss: 0.3068 | LM: 0.2996 | LB: 1.1422 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:54:25] Epoch 1 | Step 3880 | Loss: 0.3066 | LM: 0.2993 | LB: 1.1421 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:54:32] Epoch 1 | Step 3890 | Loss: 0.3065 | LM: 0.2994 | LB: 1.1421 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:54:39] Epoch 1 | Step 3900 | Loss: 0.3065 | LM: 0.2993 | LB: 1.1421 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:54:46] Epoch 1 | Step 3910 | Loss: 0.3065 | LM: 0.2993 | LB: 1.1421 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:54:54] Epoch 1 | Step 3920 | Loss: 0.3065 | LM: 0.2992 | LB: 1.1420 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:55:01] Epoch 1 | Step 3930 | Loss: 0.3064 | LM: 0.2992 | LB: 1.1420 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.439 | LR: 5.00e-05 |
| [2026-04-25 18:55:08] Epoch 1 | Step 3940 | Loss: 0.3064 | LM: 0.2991 | LB: 1.1419 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.438 | LR: 5.00e-05 |
| [2026-04-25 18:55:15] Epoch 1 | Step 3950 | Loss: 0.3063 | LM: 0.2987 | LB: 1.1418 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.438 | LR: 5.00e-05 |
| [2026-04-25 18:55:22] Epoch 1 | Step 3960 | Loss: 0.3063 | LM: 0.2988 | LB: 1.1418 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.438 | LR: 5.00e-05 |
| [2026-04-25 18:55:30] Epoch 1 | Step 3970 | Loss: 0.3062 | LM: 0.2988 | LB: 1.1418 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.438 | LR: 5.00e-05 |
| [2026-04-25 18:55:37] Epoch 1 | Step 3980 | Loss: 0.3062 | LM: 0.2987 | LB: 1.1417 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.438 | LR: 4.99e-05 |
| [2026-04-25 18:55:44] Epoch 1 | Step 3990 | Loss: 0.3062 | LM: 0.2990 | LB: 1.1416 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.438 | LR: 4.99e-05 |
| [2026-04-25 18:55:51] Epoch 1 | Step 4000 | Loss: 0.3061 | LM: 0.2989 | LB: 1.1416 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.438 | LR: 4.98e-05 |
| [2026-04-25 18:55:52] Validation | Batch 10/42 | Loss: 0.2827 | LM_LOSS: 0.2715 | LB_LOSS: 1.1182 |
| [2026-04-25 18:55:53] Validation | Batch 20/42 | Loss: 0.3023 | LM_LOSS: 0.2911 | LB_LOSS: 1.1206 |
| [2026-04-25 18:55:55] Validation | Batch 30/42 | Loss: 0.2928 | LM_LOSS: 0.2816 | LB_LOSS: 1.1170 |
| [2026-04-25 18:55:56] Validation | Batch 40/42 | Loss: 0.2971 | LM_LOSS: 0.2859 | LB_LOSS: 1.1159 |
| [2026-04-25 18:55:56] Validation | Batch 42/42 | Loss: 0.2964 | LM_LOSS: 0.2853 | LB_LOSS: 1.1161 |
| [2026-04-25 18:55:56] Validation | Loss: 0.2964 | LM_LOSS: 0.2853 | LB_LOSS: 1.1161 | PPL: 1.33 | Time: 4.82s |
| [2026-04-25 18:55:59] New best model saved! Val loss: 0.2964 |
| [2026-04-25 18:56:07] Epoch 1 | Step 4010 | Loss: 0.3061 | LM: 0.2989 | LB: 1.1415 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.438 | LR: 4.97e-05 |
| [2026-04-25 18:56:14] Epoch 1 | Step 4020 | Loss: 0.3061 | LM: 0.2989 | LB: 1.1415 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.438 | LR: 4.95e-05 |
| [2026-04-25 18:56:21] Epoch 1 | Step 4030 | Loss: 0.3059 | LM: 0.2988 | LB: 1.1414 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.438 | LR: 4.94e-05 |
| [2026-04-25 18:56:28] Epoch 1 | Step 4040 | Loss: 0.3058 | LM: 0.2986 | LB: 1.1414 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.462/SR1: 0.438 | LR: 4.92e-05 |
| [2026-04-25 18:56:36] Epoch 1 | Step 4050 | Loss: 0.3057 | LM: 0.2986 | LB: 1.1413 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.438 | LR: 4.90e-05 |
| [2026-04-25 18:56:43] Epoch 1 | Step 4060 | Loss: 0.3055 | LM: 0.2983 | LB: 1.1412 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.438 | LR: 4.88e-05 |
| [2026-04-25 18:56:50] Epoch 1 | Step 4070 | Loss: 0.3055 | LM: 0.2984 | LB: 1.1412 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.438 | LR: 4.85e-05 |
| [2026-04-25 18:56:57] Epoch 1 | Step 4080 | Loss: 0.3055 | LM: 0.2985 | LB: 1.1412 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.438 | LR: 4.82e-05 |
| [2026-04-25 18:57:05] Epoch 1 | Step 4090 | Loss: 0.3055 | LM: 0.2984 | LB: 1.1411 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.438 | LR: 4.80e-05 |
| [2026-04-25 18:57:12] Epoch 1 | Step 4100 | Loss: 0.3055 | LM: 0.2984 | LB: 1.1411 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.438 | LR: 4.77e-05 |
| [2026-04-25 18:57:19] Epoch 1 | Step 4110 | Loss: 0.3054 | LM: 0.2984 | LB: 1.1410 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.438 | LR: 4.73e-05 |
| [2026-04-25 18:57:26] Epoch 1 | Step 4120 | Loss: 0.3055 | LM: 0.2984 | LB: 1.1410 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.438 | LR: 4.70e-05 |
| [2026-04-25 18:57:33] Epoch 1 | Step 4130 | Loss: 0.3054 | LM: 0.2982 | LB: 1.1409 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.438 | LR: 4.66e-05 |
| [2026-04-25 18:57:41] Epoch 1 | Step 4140 | Loss: 0.3054 | LM: 0.2983 | LB: 1.1409 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.438 | LR: 4.62e-05 |
| [2026-04-25 18:57:48] Epoch 1 | Step 4150 | Loss: 0.3056 | LM: 0.2985 | LB: 1.1408 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.438 | LR: 4.58e-05 |
| [2026-04-25 18:57:55] Epoch 1 | Step 4160 | Loss: 0.3056 | LM: 0.2987 | LB: 1.1408 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.438 | LR: 4.54e-05 |
| [2026-04-25 18:58:02] Epoch 1 | Step 4170 | Loss: 0.3055 | LM: 0.2988 | LB: 1.1408 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.438 | LR: 4.49e-05 |
| [2026-04-25 18:58:10] Epoch 1 | Step 4180 | Loss: 0.3055 | LM: 0.2989 | LB: 1.1408 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.437 | LR: 4.45e-05 |
| [2026-04-25 18:58:17] Epoch 1 | Step 4190 | Loss: 0.3055 | LM: 0.2989 | LB: 1.1407 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.437 | LR: 4.40e-05 |
| [2026-04-25 18:58:24] Epoch 1 | Step 4200 | Loss: 0.3056 | LM: 0.2991 | LB: 1.1407 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.437 | LR: 4.35e-05 |
| [2026-04-25 18:58:31] Epoch 1 | Step 4210 | Loss: 0.3055 | LM: 0.2990 | LB: 1.1406 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.437 | LR: 4.30e-05 |
| [2026-04-25 18:58:38] Epoch 1 | Step 4220 | Loss: 0.3057 | LM: 0.2992 | LB: 1.1406 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.437 | LR: 4.25e-05 |
| [2026-04-25 18:58:46] Epoch 1 | Step 4230 | Loss: 0.3057 | LM: 0.2992 | LB: 1.1406 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.437 | LR: 4.19e-05 |
| [2026-04-25 18:58:53] Epoch 1 | Step 4240 | Loss: 0.3058 | LM: 0.2994 | LB: 1.1405 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.437 | LR: 4.14e-05 |
| [2026-04-25 18:59:00] Epoch 1 | Step 4250 | Loss: 0.3058 | LM: 0.2994 | LB: 1.1405 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.437 | LR: 4.08e-05 |
| [2026-04-25 18:59:07] Epoch 1 | Step 4260 | Loss: 0.3057 | LM: 0.2991 | LB: 1.1405 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.437 | LR: 4.02e-05 |
| [2026-04-25 18:59:14] Epoch 1 | Step 4270 | Loss: 0.3058 | LM: 0.2990 | LB: 1.1405 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.437 | LR: 3.96e-05 |
| [2026-04-25 18:59:22] Epoch 1 | Step 4280 | Loss: 0.3057 | LM: 0.2989 | LB: 1.1404 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.437 | LR: 3.90e-05 |
| [2026-04-25 18:59:29] Epoch 1 | Step 4290 | Loss: 0.3057 | LM: 0.2988 | LB: 1.1404 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.437 | LR: 3.84e-05 |
| [2026-04-25 18:59:36] Epoch 1 | Step 4300 | Loss: 0.3056 | LM: 0.2987 | LB: 1.1404 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.437 | LR: 3.78e-05 |
| [2026-04-25 18:59:43] Epoch 1 | Step 4310 | Loss: 0.3057 | LM: 0.2986 | LB: 1.1403 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.437 | LR: 3.71e-05 |
| [2026-04-25 18:59:50] Epoch 1 | Step 4320 | Loss: 0.3057 | LM: 0.2985 | LB: 1.1403 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.437 | LR: 3.65e-05 |
| [2026-04-25 18:59:58] Epoch 1 | Step 4330 | Loss: 0.3056 | LM: 0.2986 | LB: 1.1402 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.437 | LR: 3.58e-05 |
| [2026-04-25 19:00:05] Epoch 1 | Step 4340 | Loss: 0.3056 | LM: 0.2987 | LB: 1.1402 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.437 | LR: 3.52e-05 |
| [2026-04-25 19:00:12] Epoch 1 | Step 4350 | Loss: 0.3055 | LM: 0.2986 | LB: 1.1401 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.437 | LR: 3.45e-05 |
| [2026-04-25 19:00:19] Epoch 1 | Step 4360 | Loss: 0.3055 | LM: 0.2985 | LB: 1.1401 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.437 | LR: 3.38e-05 |
| [2026-04-25 19:00:26] Epoch 1 | Step 4370 | Loss: 0.3055 | LM: 0.2987 | LB: 1.1401 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.437 | LR: 3.31e-05 |
| [2026-04-25 19:00:33] Epoch 1 | Step 4380 | Loss: 0.3054 | LM: 0.2987 | LB: 1.1400 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.437 | LR: 3.24e-05 |
| [2026-04-25 19:00:41] Epoch 1 | Step 4390 | Loss: 0.3054 | LM: 0.2986 | LB: 1.1399 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.437 | LR: 3.17e-05 |
| [2026-04-25 19:00:48] Epoch 1 | Step 4400 | Loss: 0.3054 | LM: 0.2984 | LB: 1.1399 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.437 | LR: 3.10e-05 |
| [2026-04-25 19:00:55] Epoch 1 | Step 4410 | Loss: 0.3052 | LM: 0.2983 | LB: 1.1399 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.437 | LR: 3.03e-05 |
| [2026-04-25 19:01:02] Epoch 1 | Step 4420 | Loss: 0.3053 | LM: 0.2984 | LB: 1.1398 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.437 | LR: 2.96e-05 |
| [2026-04-25 19:01:10] Epoch 1 | Step 4430 | Loss: 0.3052 | LM: 0.2983 | LB: 1.1398 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.437 | LR: 2.89e-05 |
| [2026-04-25 19:01:17] Epoch 1 | Step 4440 | Loss: 0.3053 | LM: 0.2983 | LB: 1.1398 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.436 | LR: 2.82e-05 |
| [2026-04-25 19:01:24] Epoch 1 | Step 4450 | Loss: 0.3052 | LM: 0.2981 | LB: 1.1397 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.436 | LR: 2.74e-05 |
| [2026-04-25 19:01:31] Epoch 1 | Step 4460 | Loss: 0.3053 | LM: 0.2981 | LB: 1.1396 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.436 | LR: 2.67e-05 |
| [2026-04-25 19:01:38] Epoch 1 | Step 4470 | Loss: 0.3052 | LM: 0.2980 | LB: 1.1396 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.436 | LR: 2.60e-05 |
| [2026-04-25 19:01:45] Epoch 1 | Step 4480 | Loss: 0.3050 | LM: 0.2979 | LB: 1.1395 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.436 | LR: 2.53e-05 |
| [2026-04-25 19:01:53] Epoch 1 | Step 4490 | Loss: 0.3049 | LM: 0.2979 | LB: 1.1395 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.436 | LR: 2.46e-05 |
| [2026-04-25 19:02:00] Epoch 1 | Step 4500 | Loss: 0.3049 | LM: 0.2978 | LB: 1.1394 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.436 | LR: 2.39e-05 |
| [2026-04-25 19:02:07] Epoch 1 | Step 4510 | Loss: 0.3048 | LM: 0.2977 | LB: 1.1394 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.436 | LR: 2.32e-05 |
| [2026-04-25 19:02:14] Epoch 1 | Step 4520 | Loss: 0.3047 | LM: 0.2976 | LB: 1.1394 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.436 | LR: 2.25e-05 |
| [2026-04-25 19:02:22] Epoch 1 | Step 4530 | Loss: 0.3046 | LM: 0.2974 | LB: 1.1393 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.436 | LR: 2.18e-05 |
| [2026-04-25 19:02:29] Epoch 1 | Step 4540 | Loss: 0.3046 | LM: 0.2975 | LB: 1.1393 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.436 | LR: 2.11e-05 |
| [2026-04-25 19:02:36] Epoch 1 | Step 4550 | Loss: 0.3045 | LM: 0.2974 | LB: 1.1392 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.436 | LR: 2.04e-05 |
| [2026-04-25 19:02:43] Epoch 1 | Step 4560 | Loss: 0.3045 | LM: 0.2974 | LB: 1.1392 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.436 | LR: 1.97e-05 |
| [2026-04-25 19:02:51] Epoch 1 | Step 4570 | Loss: 0.3045 | LM: 0.2973 | LB: 1.1392 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.436 | LR: 1.91e-05 |
| [2026-04-25 19:02:58] Epoch 1 | Step 4580 | Loss: 0.3045 | LM: 0.2973 | LB: 1.1392 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.436 | LR: 1.84e-05 |
| [2026-04-25 19:03:05] Epoch 1 | Step 4590 | Loss: 0.3044 | LM: 0.2974 | LB: 1.1392 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.436 | LR: 1.78e-05 |
| [2026-04-25 19:03:12] Epoch 1 | Step 4600 | Loss: 0.3044 | LM: 0.2972 | LB: 1.1391 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.436 | LR: 1.71e-05 |
| [2026-04-25 19:03:19] Epoch 1 | Step 4610 | Loss: 0.3043 | LM: 0.2971 | LB: 1.1391 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.460/SR1: 0.436 | LR: 1.65e-05 |
| [2026-04-25 19:03:26] Epoch 1 | Step 4620 | Loss: 0.3043 | LM: 0.2970 | LB: 1.1391 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.436 | LR: 1.59e-05 |
| [2026-04-25 19:03:34] Epoch 1 | Step 4630 | Loss: 0.3043 | LM: 0.2970 | LB: 1.1390 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.436 | LR: 1.53e-05 |
| [2026-04-25 19:03:41] Epoch 1 | Step 4640 | Loss: 0.3043 | LM: 0.2970 | LB: 1.1390 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.436 | LR: 1.47e-05 |
| [2026-04-25 19:03:48] Epoch 1 | Step 4650 | Loss: 0.3043 | LM: 0.2970 | LB: 1.1390 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.436 | LR: 1.41e-05 |
| [2026-04-25 19:03:55] Epoch 1 | Step 4660 | Loss: 0.3042 | LM: 0.2969 | LB: 1.1390 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.436 | LR: 1.35e-05 |
| [2026-04-25 19:04:03] Epoch 1 | Step 4670 | Loss: 0.3042 | LM: 0.2970 | LB: 1.1389 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.436 | LR: 1.30e-05 |
| [2026-04-25 19:04:10] Epoch 1 | Step 4680 | Loss: 0.3043 | LM: 0.2970 | LB: 1.1388 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.436 | LR: 1.24e-05 |
| [2026-04-25 19:04:17] Epoch 1 | Step 4690 | Loss: 0.3042 | LM: 0.2969 | LB: 1.1388 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.436 | LR: 1.19e-05 |
| [2026-04-25 19:04:24] Epoch 1 | Step 4700 | Loss: 0.3042 | LM: 0.2969 | LB: 1.1388 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 1.14e-05 |
| [2026-04-25 19:04:31] Epoch 1 | Step 4710 | Loss: 0.3042 | LM: 0.2969 | LB: 1.1387 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 1.09e-05 |
| [2026-04-25 19:04:39] Epoch 1 | Step 4720 | Loss: 0.3042 | LM: 0.2969 | LB: 1.1387 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 1.04e-05 |
| [2026-04-25 19:04:46] Epoch 1 | Step 4730 | Loss: 0.3042 | LM: 0.2969 | LB: 1.1387 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 9.98e-06 |
| [2026-04-25 19:04:53] Epoch 1 | Step 4740 | Loss: 0.3041 | LM: 0.2968 | LB: 1.1386 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 9.54e-06 |
| [2026-04-25 19:05:00] Epoch 1 | Step 4750 | Loss: 0.3041 | LM: 0.2967 | LB: 1.1386 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 9.12e-06 |
| [2026-04-25 19:05:07] Epoch 1 | Step 4760 | Loss: 0.3041 | LM: 0.2967 | LB: 1.1385 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 8.72e-06 |
| [2026-04-25 19:05:14] Epoch 1 | Step 4770 | Loss: 0.3040 | LM: 0.2964 | LB: 1.1385 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 8.33e-06 |
| [2026-04-25 19:05:22] Epoch 1 | Step 4780 | Loss: 0.3040 | LM: 0.2965 | LB: 1.1385 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 7.97e-06 |
| [2026-04-25 19:05:29] Epoch 1 | Step 4790 | Loss: 0.3040 | LM: 0.2964 | LB: 1.1385 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 7.62e-06 |
| [2026-04-25 19:05:36] Epoch 1 | Step 4800 | Loss: 0.3039 | LM: 0.2964 | LB: 1.1385 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 7.30e-06 |
| [2026-04-25 19:05:43] Epoch 1 | Step 4810 | Loss: 0.3038 | LM: 0.2963 | LB: 1.1384 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 6.99e-06 |
| [2026-04-25 19:05:50] Epoch 1 | Step 4820 | Loss: 0.3038 | LM: 0.2961 | LB: 1.1384 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 6.71e-06 |
| [2026-04-25 19:05:58] Epoch 1 | Step 4830 | Loss: 0.3036 | LM: 0.2960 | LB: 1.1383 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 6.45e-06 |
| [2026-04-25 19:06:05] Epoch 1 | Step 4840 | Loss: 0.3036 | LM: 0.2959 | LB: 1.1383 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 6.21e-06 |
| [2026-04-25 19:06:12] Epoch 1 | Step 4850 | Loss: 0.3036 | LM: 0.2960 | LB: 1.1383 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 5.99e-06 |
| [2026-04-25 19:06:19] Epoch 1 | Step 4860 | Loss: 0.3037 | LM: 0.2960 | LB: 1.1382 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 5.79e-06 |
| [2026-04-25 19:06:26] Epoch 1 | Step 4870 | Loss: 0.3037 | LM: 0.2960 | LB: 1.1382 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 5.61e-06 |
| [2026-04-25 19:06:33] Epoch 1 | Step 4880 | Loss: 0.3038 | LM: 0.2960 | LB: 1.1382 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 5.46e-06 |
| [2026-04-25 19:06:41] Epoch 1 | Step 4890 | Loss: 0.3037 | LM: 0.2961 | LB: 1.1382 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 5.32e-06 |
| [2026-04-25 19:06:48] Epoch 1 | Step 4900 | Loss: 0.3036 | LM: 0.2959 | LB: 1.1381 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 5.21e-06 |
| [2026-04-25 19:06:55] Epoch 1 | Step 4910 | Loss: 0.3036 | LM: 0.2958 | LB: 1.1381 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 5.13e-06 |
| [2026-04-25 19:07:02] Epoch 1 | Step 4920 | Loss: 0.3036 | LM: 0.2958 | LB: 1.1380 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 5.06e-06 |
| [2026-04-25 19:07:09] Epoch 1 | Step 4930 | Loss: 0.3036 | LM: 0.2958 | LB: 1.1380 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 5.02e-06 |
| [2026-04-25 19:07:17] Epoch 1 | Step 4940 | Loss: 0.3035 | LM: 0.2958 | LB: 1.1380 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 5.00e-06 |
| [2026-04-25 19:07:24] Epoch 1 | Step 4950 | Loss: 0.3035 | LM: 0.2958 | LB: 1.1379 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 5.00e-06 |
| [2026-04-25 19:07:31] Epoch 1 | Step 4960 | Loss: 0.3035 | LM: 0.2958 | LB: 1.1379 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.459/SR1: 0.435 | LR: 5.00e-06 |
| [2026-04-25 19:07:38] Epoch 1 | Step 4970 | Loss: 0.3034 | LM: 0.2958 | LB: 1.1379 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.435 | LR: 5.00e-06 |
| [2026-04-25 19:07:45] Epoch 1 | Step 4980 | Loss: 0.3034 | LM: 0.2958 | LB: 1.1379 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.435 | LR: 5.00e-06 |
| [2026-04-25 19:07:53] Epoch 1 | Step 4990 | Loss: 0.3033 | LM: 0.2957 | LB: 1.1378 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.435 | LR: 5.00e-06 |
| [2026-04-25 19:08:00] Epoch 1 | Step 5000 | Loss: 0.3034 | LM: 0.2958 | LB: 1.1378 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:08:07] Epoch 1 | Step 5010 | Loss: 0.3034 | LM: 0.2958 | LB: 1.1378 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:08:14] Epoch 1 | Step 5020 | Loss: 0.3033 | LM: 0.2956 | LB: 1.1378 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:08:21] Epoch 1 | Step 5030 | Loss: 0.3033 | LM: 0.2956 | LB: 1.1377 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:08:28] Epoch 1 | Step 5040 | Loss: 0.3033 | LM: 0.2954 | LB: 1.1377 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:08:35] Epoch 1 | Step 5050 | Loss: 0.3032 | LM: 0.2954 | LB: 1.1377 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:08:43] Epoch 1 | Step 5060 | Loss: 0.3032 | LM: 0.2953 | LB: 1.1376 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:08:50] Epoch 1 | Step 5070 | Loss: 0.3032 | LM: 0.2953 | LB: 1.1376 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:08:57] Epoch 1 | Step 5080 | Loss: 0.3033 | LM: 0.2953 | LB: 1.1376 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:09:04] Epoch 1 | Step 5090 | Loss: 0.3032 | LM: 0.2953 | LB: 1.1375 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:09:11] Epoch 1 | Step 5100 | Loss: 0.3032 | LM: 0.2952 | LB: 1.1375 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:09:19] Epoch 1 | Step 5110 | Loss: 0.3031 | LM: 0.2953 | LB: 1.1375 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:09:26] Epoch 1 | Step 5120 | Loss: 0.3032 | LM: 0.2953 | LB: 1.1374 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:09:33] Epoch 1 | Step 5130 | Loss: 0.3031 | LM: 0.2952 | LB: 1.1374 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:09:40] Epoch 1 | Step 5140 | Loss: 0.3030 | LM: 0.2952 | LB: 1.1374 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:09:47] Epoch 1 | Step 5150 | Loss: 0.3030 | LM: 0.2951 | LB: 1.1373 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:09:55] Epoch 1 | Step 5160 | Loss: 0.3029 | LM: 0.2951 | LB: 1.1373 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:10:02] Epoch 1 | Step 5170 | Loss: 0.3028 | LM: 0.2951 | LB: 1.1373 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:10:10] Epoch 1 | Step 5180 | Loss: 0.3028 | LM: 0.2950 | LB: 1.1372 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:10:17] Epoch 1 | Step 5190 | Loss: 0.3028 | LM: 0.2950 | LB: 1.1372 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:10:24] Epoch 1 | Step 5200 | Loss: 0.3028 | LM: 0.2950 | LB: 1.1372 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:10:31] Epoch 1 | Step 5210 | Loss: 0.3028 | LM: 0.2949 | LB: 1.1371 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:10:38] Epoch 1 | Step 5220 | Loss: 0.3027 | LM: 0.2948 | LB: 1.1371 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:10:45] Epoch 1 | Step 5230 | Loss: 0.3027 | LM: 0.2947 | LB: 1.1371 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:10:53] Epoch 1 | Step 5240 | Loss: 0.3027 | LM: 0.2946 | LB: 1.1370 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:11:00] Epoch 1 | Step 5250 | Loss: 0.3027 | LM: 0.2947 | LB: 1.1370 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:11:07] Epoch 1 | Step 5260 | Loss: 0.3027 | LM: 0.2946 | LB: 1.1370 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:11:14] Epoch 1 | Step 5270 | Loss: 0.3027 | LM: 0.2945 | LB: 1.1370 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:11:21] Epoch 1 | Step 5280 | Loss: 0.3026 | LM: 0.2944 | LB: 1.1369 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:11:28] Epoch 1 | Step 5290 | Loss: 0.3025 | LM: 0.2943 | LB: 1.1369 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:11:36] Epoch 1 | Step 5300 | Loss: 0.3025 | LM: 0.2942 | LB: 1.1369 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:11:43] Epoch 1 | Step 5310 | Loss: 0.3026 | LM: 0.2943 | LB: 1.1369 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:11:50] Epoch 1 | Step 5320 | Loss: 0.3025 | LM: 0.2942 | LB: 1.1369 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:11:57] Epoch 1 | Step 5330 | Loss: 0.3025 | LM: 0.2942 | LB: 1.1368 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.434 | LR: 5.00e-06 |
| [2026-04-25 19:12:04] Epoch 1 | Step 5340 | Loss: 0.3025 | LM: 0.2942 | LB: 1.1368 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:12:12] Epoch 1 | Step 5350 | Loss: 0.3024 | LM: 0.2941 | LB: 1.1367 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:12:19] Epoch 1 | Step 5360 | Loss: 0.3024 | LM: 0.2940 | LB: 1.1367 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:12:26] Epoch 1 | Step 5370 | Loss: 0.3024 | LM: 0.2939 | LB: 1.1366 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:12:33] Epoch 1 | Step 5380 | Loss: 0.3023 | LM: 0.2938 | LB: 1.1366 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:12:40] Epoch 1 | Step 5390 | Loss: 0.3022 | LM: 0.2937 | LB: 1.1365 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:12:48] Epoch 1 | Step 5400 | Loss: 0.3022 | LM: 0.2937 | LB: 1.1365 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:12:55] Epoch 1 | Step 5410 | Loss: 0.3022 | LM: 0.2937 | LB: 1.1365 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:13:02] Epoch 1 | Step 5420 | Loss: 0.3021 | LM: 0.2936 | LB: 1.1365 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:13:09] Epoch 1 | Step 5430 | Loss: 0.3021 | LM: 0.2935 | LB: 1.1365 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:13:16] Epoch 1 | Step 5440 | Loss: 0.3021 | LM: 0.2935 | LB: 1.1364 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:13:23] Epoch 1 | Step 5450 | Loss: 0.3022 | LM: 0.2934 | LB: 1.1364 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:13:31] Epoch 1 | Step 5460 | Loss: 0.3021 | LM: 0.2934 | LB: 1.1364 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:13:38] Epoch 1 | Step 5470 | Loss: 0.3021 | LM: 0.2933 | LB: 1.1363 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:13:45] Epoch 1 | Step 5480 | Loss: 0.3021 | LM: 0.2932 | LB: 1.1363 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:13:52] Epoch 1 | Step 5490 | Loss: 0.3021 | LM: 0.2932 | LB: 1.1362 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:13:59] Epoch 1 | Step 5500 | Loss: 0.3021 | LM: 0.2933 | LB: 1.1362 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:14:07] Epoch 1 | Step 5510 | Loss: 0.3021 | LM: 0.2935 | LB: 1.1362 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:14:14] Epoch 1 | Step 5520 | Loss: 0.3020 | LM: 0.2934 | LB: 1.1361 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:14:21] Epoch 1 | Step 5530 | Loss: 0.3020 | LM: 0.2933 | LB: 1.1361 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:14:28] Epoch 1 | Step 5540 | Loss: 0.3019 | LM: 0.2932 | LB: 1.1361 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:14:35] Epoch 1 | Step 5550 | Loss: 0.3019 | LM: 0.2931 | LB: 1.1360 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:14:43] Epoch 1 | Step 5560 | Loss: 0.3019 | LM: 0.2932 | LB: 1.1360 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:14:50] Epoch 1 | Step 5570 | Loss: 0.3020 | LM: 0.2932 | LB: 1.1360 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:14:57] Epoch 1 | Step 5580 | Loss: 0.3019 | LM: 0.2931 | LB: 1.1360 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:15:04] Epoch 1 | Step 5590 | Loss: 0.3019 | LM: 0.2932 | LB: 1.1359 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:15:11] Epoch 1 | Step 5600 | Loss: 0.3019 | LM: 0.2931 | LB: 1.1359 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:15:19] Epoch 1 | Step 5610 | Loss: 0.3019 | LM: 0.2932 | LB: 1.1359 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:15:26] Epoch 1 | Step 5620 | Loss: 0.3018 | LM: 0.2931 | LB: 1.1359 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:15:33] Epoch 1 | Step 5630 | Loss: 0.3019 | LM: 0.2931 | LB: 1.1359 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:15:40] Epoch 1 | Step 5640 | Loss: 0.3018 | LM: 0.2932 | LB: 1.1358 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:15:47] Epoch 1 | Step 5650 | Loss: 0.3019 | LM: 0.2933 | LB: 1.1358 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:15:55] Epoch 1 | Step 5660 | Loss: 0.3018 | LM: 0.2932 | LB: 1.1358 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:16:02] Epoch 1 | Step 5670 | Loss: 0.3018 | LM: 0.2931 | LB: 1.1358 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:16:09] Epoch 1 | Step 5680 | Loss: 0.3017 | LM: 0.2931 | LB: 1.1357 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.433 | LR: 5.00e-06 |
| [2026-04-25 19:16:17] Epoch 1 | Step 5690 | Loss: 0.3017 | LM: 0.2931 | LB: 1.1357 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:16:24] Epoch 1 | Step 5700 | Loss: 0.3017 | LM: 0.2931 | LB: 1.1357 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:16:31] Epoch 1 | Step 5710 | Loss: 0.3017 | LM: 0.2931 | LB: 1.1357 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:16:38] Epoch 1 | Step 5720 | Loss: 0.3017 | LM: 0.2931 | LB: 1.1356 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:16:45] Epoch 1 | Step 5730 | Loss: 0.3017 | LM: 0.2933 | LB: 1.1356 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:16:52] Epoch 1 | Step 5740 | Loss: 0.3017 | LM: 0.2932 | LB: 1.1356 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:17:00] Epoch 1 | Step 5750 | Loss: 0.3017 | LM: 0.2932 | LB: 1.1356 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:17:07] Epoch 1 | Step 5760 | Loss: 0.3017 | LM: 0.2932 | LB: 1.1356 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:17:14] Epoch 1 | Step 5770 | Loss: 0.3017 | LM: 0.2932 | LB: 1.1355 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:17:21] Epoch 1 | Step 5780 | Loss: 0.3017 | LM: 0.2932 | LB: 1.1355 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:17:28] Epoch 1 | Step 5790 | Loss: 0.3017 | LM: 0.2930 | LB: 1.1355 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:17:36] Epoch 1 | Step 5800 | Loss: 0.3018 | LM: 0.2932 | LB: 1.1354 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:17:43] Epoch 1 | Step 5810 | Loss: 0.3017 | LM: 0.2932 | LB: 1.1354 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:17:50] Epoch 1 | Step 5820 | Loss: 0.3017 | LM: 0.2930 | LB: 1.1354 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:17:57] Epoch 1 | Step 5830 | Loss: 0.3016 | LM: 0.2930 | LB: 1.1354 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:18:05] Epoch 1 | Step 5840 | Loss: 0.3016 | LM: 0.2930 | LB: 1.1354 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:18:12] Epoch 1 | Step 5850 | Loss: 0.3016 | LM: 0.2931 | LB: 1.1354 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:18:19] Epoch 1 | Step 5860 | Loss: 0.3016 | LM: 0.2930 | LB: 1.1353 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:18:26] Epoch 1 | Step 5870 | Loss: 0.3016 | LM: 0.2929 | LB: 1.1353 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:18:33] Epoch 1 | Step 5880 | Loss: 0.3016 | LM: 0.2931 | LB: 1.1353 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:18:41] Epoch 1 | Step 5890 | Loss: 0.3016 | LM: 0.2929 | LB: 1.1353 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:18:48] Epoch 1 | Step 5900 | Loss: 0.3015 | LM: 0.2929 | LB: 1.1353 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:18:55] Epoch 1 | Step 5910 | Loss: 0.3015 | LM: 0.2930 | LB: 1.1353 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:19:02] Epoch 1 | Step 5920 | Loss: 0.3015 | LM: 0.2929 | LB: 1.1352 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:19:09] Epoch 1 | Step 5930 | Loss: 0.3015 | LM: 0.2929 | LB: 1.1352 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:19:17] Epoch 1 | Step 5940 | Loss: 0.3015 | LM: 0.2929 | LB: 1.1352 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:19:24] Epoch 1 | Step 5950 | Loss: 0.3015 | LM: 0.2929 | LB: 1.1352 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:19:31] Epoch 1 | Step 5960 | Loss: 0.3015 | LM: 0.2929 | LB: 1.1352 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:19:38] Epoch 1 | Step 5970 | Loss: 0.3016 | LM: 0.2929 | LB: 1.1351 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:19:46] Epoch 1 | Step 5980 | Loss: 0.3016 | LM: 0.2929 | LB: 1.1351 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:19:53] Epoch 1 | Step 5990 | Loss: 0.3016 | LM: 0.2930 | LB: 1.1351 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:20:00] Epoch 1 | Step 6000 | Loss: 0.3015 | LM: 0.2930 | LB: 1.1351 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:20:01] Validation | Batch 10/42 | Loss: 0.2798 | LM_LOSS: 0.2687 | LB_LOSS: 1.1157 |
| [2026-04-25 19:20:02] Validation | Batch 20/42 | Loss: 0.3004 | LM_LOSS: 0.2892 | LB_LOSS: 1.1182 |
| [2026-04-25 19:20:03] Validation | Batch 30/42 | Loss: 0.2917 | LM_LOSS: 0.2805 | LB_LOSS: 1.1147 |
| [2026-04-25 19:20:05] Validation | Batch 40/42 | Loss: 0.2957 | LM_LOSS: 0.2845 | LB_LOSS: 1.1135 |
| [2026-04-25 19:20:05] Validation | Batch 42/42 | Loss: 0.2951 | LM_LOSS: 0.2840 | LB_LOSS: 1.1137 |
| [2026-04-25 19:20:05] Validation | Loss: 0.2951 | LM_LOSS: 0.2840 | LB_LOSS: 1.1137 | PPL: 1.33 | Time: 4.82s |
| [2026-04-25 19:20:08] New best model saved! Val loss: 0.2951 |
| [2026-04-25 19:20:15] Epoch 1 | Step 6010 | Loss: 0.3015 | LM: 0.2929 | LB: 1.1351 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:20:22] Epoch 1 | Step 6020 | Loss: 0.3015 | LM: 0.2928 | LB: 1.1350 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:20:30] Epoch 1 | Step 6030 | Loss: 0.3016 | LM: 0.2928 | LB: 1.1350 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:20:37] Epoch 1 | Step 6040 | Loss: 0.3016 | LM: 0.2928 | LB: 1.1350 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:20:44] Epoch 1 | Step 6050 | Loss: 0.3016 | LM: 0.2929 | LB: 1.1350 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:20:51] Epoch 1 | Step 6060 | Loss: 0.3016 | LM: 0.2929 | LB: 1.1350 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:20:58] Epoch 1 | Step 6070 | Loss: 0.3016 | LM: 0.2928 | LB: 1.1349 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:21:05] Epoch 1 | Step 6080 | Loss: 0.3015 | LM: 0.2927 | LB: 1.1349 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:21:13] Epoch 1 | Step 6090 | Loss: 0.3016 | LM: 0.2927 | LB: 1.1349 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:21:20] Epoch 1 | Step 6100 | Loss: 0.3016 | LM: 0.2928 | LB: 1.1348 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:21:27] Epoch 1 | Step 6110 | Loss: 0.3016 | LM: 0.2928 | LB: 1.1348 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:21:34] Epoch 1 | Step 6120 | Loss: 0.3016 | LM: 0.2928 | LB: 1.1347 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:21:42] Epoch 1 | Step 6130 | Loss: 0.3016 | LM: 0.2928 | LB: 1.1347 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:21:49] Epoch 1 | Step 6140 | Loss: 0.3014 | LM: 0.2926 | LB: 1.1347 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.432 | LR: 5.00e-06 |
| [2026-04-25 19:21:56] Epoch 1 | Step 6150 | Loss: 0.3014 | LM: 0.2926 | LB: 1.1347 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:22:03] Epoch 1 | Step 6160 | Loss: 0.3014 | LM: 0.2925 | LB: 1.1347 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:22:11] Epoch 1 | Step 6170 | Loss: 0.3014 | LM: 0.2925 | LB: 1.1347 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:22:18] Epoch 1 | Step 6180 | Loss: 0.3013 | LM: 0.2926 | LB: 1.1347 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:22:25] Epoch 1 | Step 6190 | Loss: 0.3013 | LM: 0.2925 | LB: 1.1347 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:22:32] Epoch 1 | Step 6200 | Loss: 0.3012 | LM: 0.2925 | LB: 1.1347 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:22:40] Epoch 1 | Step 6210 | Loss: 0.3013 | LM: 0.2924 | LB: 1.1347 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:22:47] Epoch 1 | Step 6220 | Loss: 0.3013 | LM: 0.2924 | LB: 1.1346 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:22:54] Epoch 1 | Step 6230 | Loss: 0.3013 | LM: 0.2925 | LB: 1.1346 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:23:01] Epoch 1 | Step 6240 | Loss: 0.3013 | LM: 0.2925 | LB: 1.1346 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:23:09] Epoch 1 | Step 6250 | Loss: 0.3012 | LM: 0.2925 | LB: 1.1346 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:23:16] Epoch 1 | Step 6260 | Loss: 0.3011 | LM: 0.2926 | LB: 1.1345 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:23:23] Epoch 1 | Step 6270 | Loss: 0.3011 | LM: 0.2925 | LB: 1.1345 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.456/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:23:30] Epoch 1 | Step 6280 | Loss: 0.3010 | LM: 0.2923 | LB: 1.1345 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:23:38] Epoch 1 | Step 6290 | Loss: 0.3010 | LM: 0.2924 | LB: 1.1345 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:23:45] Epoch 1 | Step 6300 | Loss: 0.3010 | LM: 0.2924 | LB: 1.1345 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:23:52] Epoch 1 | Step 6310 | Loss: 0.3010 | LM: 0.2924 | LB: 1.1344 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:23:59] Epoch 1 | Step 6320 | Loss: 0.3010 | LM: 0.2924 | LB: 1.1344 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:24:07] Epoch 1 | Step 6330 | Loss: 0.3011 | LM: 0.2925 | LB: 1.1344 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:24:14] Epoch 1 | Step 6340 | Loss: 0.3011 | LM: 0.2925 | LB: 1.1343 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:24:21] Epoch 1 | Step 6350 | Loss: 0.3011 | LM: 0.2926 | LB: 1.1343 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:24:28] Epoch 1 | Step 6360 | Loss: 0.3011 | LM: 0.2927 | LB: 1.1343 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:24:36] Epoch 1 | Step 6370 | Loss: 0.3011 | LM: 0.2927 | LB: 1.1343 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:24:43] Epoch 1 | Step 6380 | Loss: 0.3011 | LM: 0.2926 | LB: 1.1342 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:24:50] Epoch 1 | Step 6390 | Loss: 0.3010 | LM: 0.2925 | LB: 1.1342 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:24:57] Epoch 1 | Step 6400 | Loss: 0.3011 | LM: 0.2925 | LB: 1.1342 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:25:05] Epoch 1 | Step 6410 | Loss: 0.3010 | LM: 0.2924 | LB: 1.1342 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:25:12] Epoch 1 | Step 6420 | Loss: 0.3010 | LM: 0.2924 | LB: 1.1342 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:25:19] Epoch 1 | Step 6430 | Loss: 0.3010 | LM: 0.2924 | LB: 1.1342 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:25:26] Epoch 1 | Step 6440 | Loss: 0.3010 | LM: 0.2923 | LB: 1.1341 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:25:34] Epoch 1 | Step 6450 | Loss: 0.3010 | LM: 0.2922 | LB: 1.1341 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:25:41] Epoch 1 | Step 6460 | Loss: 0.3009 | LM: 0.2922 | LB: 1.1341 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:25:48] Epoch 1 | Step 6470 | Loss: 0.3009 | LM: 0.2921 | LB: 1.1340 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:25:55] Epoch 1 | Step 6480 | Loss: 0.3009 | LM: 0.2921 | LB: 1.1340 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:26:03] Epoch 1 | Step 6490 | Loss: 0.3009 | LM: 0.2922 | LB: 1.1340 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:26:10] Epoch 1 | Step 6500 | Loss: 0.3009 | LM: 0.2922 | LB: 1.1340 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:26:17] Epoch 1 | Step 6510 | Loss: 0.3008 | LM: 0.2922 | LB: 1.1340 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:26:25] Epoch 1 | Step 6520 | Loss: 0.3008 | LM: 0.2922 | LB: 1.1339 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:26:32] Epoch 1 | Step 6530 | Loss: 0.3007 | LM: 0.2920 | LB: 1.1339 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:26:39] Epoch 1 | Step 6540 | Loss: 0.3007 | LM: 0.2921 | LB: 1.1339 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:26:46] Epoch 1 | Step 6550 | Loss: 0.3006 | LM: 0.2919 | LB: 1.1339 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:26:53] Epoch 1 | Step 6560 | Loss: 0.3006 | LM: 0.2918 | LB: 1.1338 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:27:01] Epoch 1 | Step 6570 | Loss: 0.3006 | LM: 0.2918 | LB: 1.1338 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:27:08] Epoch 1 | Step 6580 | Loss: 0.3006 | LM: 0.2919 | LB: 1.1338 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:27:15] Epoch 1 | Step 6590 | Loss: 0.3006 | LM: 0.2919 | LB: 1.1338 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:27:23] Epoch 1 | Step 6600 | Loss: 0.3006 | LM: 0.2919 | LB: 1.1338 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:27:30] Epoch 1 | Step 6610 | Loss: 0.3006 | LM: 0.2918 | LB: 1.1338 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:27:37] Epoch 1 | Step 6620 | Loss: 0.3005 | LM: 0.2916 | LB: 1.1337 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:27:44] Epoch 1 | Step 6630 | Loss: 0.3005 | LM: 0.2915 | LB: 1.1337 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:27:51] Epoch 1 | Step 6640 | Loss: 0.3005 | LM: 0.2917 | LB: 1.1337 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:27:59] Epoch 1 | Step 6650 | Loss: 0.3005 | LM: 0.2916 | LB: 1.1337 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.431 | LR: 5.00e-06 |
| [2026-04-25 19:28:06] Epoch 1 | Step 6660 | Loss: 0.3004 | LM: 0.2915 | LB: 1.1336 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:28:13] Epoch 1 | Step 6670 | Loss: 0.3004 | LM: 0.2914 | LB: 1.1336 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:28:21] Epoch 1 | Step 6680 | Loss: 0.3004 | LM: 0.2914 | LB: 1.1336 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.455/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:28:28] Epoch 1 | Step 6690 | Loss: 0.3004 | LM: 0.2913 | LB: 1.1336 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.455/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:28:35] Epoch 1 | Step 6700 | Loss: 0.3004 | LM: 0.2913 | LB: 1.1335 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.455/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:28:42] Epoch 1 | Step 6710 | Loss: 0.3004 | LM: 0.2913 | LB: 1.1335 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.455/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:28:49] Epoch 1 | Step 6720 | Loss: 0.3004 | LM: 0.2912 | LB: 1.1335 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.455/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:28:57] Epoch 1 | Step 6730 | Loss: 0.3004 | LM: 0.2913 | LB: 1.1335 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.455/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:29:04] Epoch 1 | Step 6740 | Loss: 0.3004 | LM: 0.2912 | LB: 1.1334 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.455/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:29:11] Epoch 1 | Step 6750 | Loss: 0.3003 | LM: 0.2913 | LB: 1.1334 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.455/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:29:18] Epoch 1 | Step 6760 | Loss: 0.3003 | LM: 0.2913 | LB: 1.1334 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.455/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:29:25] Epoch 1 | Step 6770 | Loss: 0.3003 | LM: 0.2913 | LB: 1.1334 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.455/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:29:33] Epoch 1 | Step 6780 | Loss: 0.3003 | LM: 0.2913 | LB: 1.1334 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.455/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:29:40] Epoch 1 | Step 6790 | Loss: 0.3004 | LM: 0.2913 | LB: 1.1333 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.455/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:29:47] Epoch 1 | Step 6800 | Loss: 0.3004 | LM: 0.2912 | LB: 1.1333 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:29:54] Epoch 1 | Step 6810 | Loss: 0.3005 | LM: 0.2912 | LB: 1.1333 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:30:01] Epoch 1 | Step 6820 | Loss: 0.3005 | LM: 0.2912 | LB: 1.1333 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:30:09] Epoch 1 | Step 6830 | Loss: 0.3006 | LM: 0.2912 | LB: 1.1333 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:30:16] Epoch 1 | Step 6840 | Loss: 0.3006 | LM: 0.2913 | LB: 1.1333 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:30:23] Epoch 1 | Step 6850 | Loss: 0.3007 | LM: 0.2912 | LB: 1.1332 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:30:30] Epoch 1 | Step 6860 | Loss: 0.3006 | LM: 0.2912 | LB: 1.1332 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:30:38] Epoch 1 | Step 6870 | Loss: 0.3006 | LM: 0.2912 | LB: 1.1332 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:30:45] Epoch 1 | Step 6880 | Loss: 0.3006 | LM: 0.2912 | LB: 1.1332 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:30:52] Epoch 1 | Step 6890 | Loss: 0.3006 | LM: 0.2911 | LB: 1.1332 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:30:59] Epoch 1 | Step 6900 | Loss: 0.3006 | LM: 0.2912 | LB: 1.1331 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:31:07] Epoch 1 | Step 6910 | Loss: 0.3005 | LM: 0.2910 | LB: 1.1331 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:31:14] Epoch 1 | Step 6920 | Loss: 0.3005 | LM: 0.2910 | LB: 1.1331 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:31:21] Epoch 1 | Step 6930 | Loss: 0.3005 | LM: 0.2910 | LB: 1.1331 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:31:28] Epoch 1 | Step 6940 | Loss: 0.3005 | LM: 0.2910 | LB: 1.1330 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:31:36] Epoch 1 | Step 6950 | Loss: 0.3004 | LM: 0.2909 | LB: 1.1330 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:31:43] Epoch 1 | Step 6960 | Loss: 0.3005 | LM: 0.2910 | LB: 1.1330 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:31:50] Epoch 1 | Step 6970 | Loss: 0.3004 | LM: 0.2909 | LB: 1.1330 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:31:57] Epoch 1 | Step 6980 | Loss: 0.3004 | LM: 0.2910 | LB: 1.1330 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:32:05] Epoch 1 | Step 6990 | Loss: 0.3003 | LM: 0.2909 | LB: 1.1330 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:32:12] Epoch 1 | Step 7000 | Loss: 0.3003 | LM: 0.2910 | LB: 1.1330 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:32:19] Epoch 1 | Step 7010 | Loss: 0.3002 | LM: 0.2909 | LB: 1.1330 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:32:27] Epoch 1 | Step 7020 | Loss: 0.3003 | LM: 0.2910 | LB: 1.1330 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:32:34] Epoch 1 | Step 7030 | Loss: 0.3002 | LM: 0.2909 | LB: 1.1330 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:32:42] Epoch 1 | Step 7040 | Loss: 0.3003 | LM: 0.2909 | LB: 1.1330 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:32:49] Epoch 1 | Step 7050 | Loss: 0.3002 | LM: 0.2910 | LB: 1.1330 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:32:56] Epoch 1 | Step 7060 | Loss: 0.3002 | LM: 0.2910 | LB: 1.1329 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:33:04] Epoch 1 | Step 7070 | Loss: 0.3002 | LM: 0.2910 | LB: 1.1330 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:33:11] Epoch 1 | Step 7080 | Loss: 0.3002 | LM: 0.2910 | LB: 1.1329 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:33:18] Epoch 1 | Step 7090 | Loss: 0.3002 | LM: 0.2912 | LB: 1.1329 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:33:25] Epoch 1 | Step 7100 | Loss: 0.3001 | LM: 0.2910 | LB: 1.1329 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:33:33] Epoch 1 | Step 7110 | Loss: 0.3001 | LM: 0.2910 | LB: 1.1329 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:33:40] Epoch 1 | Step 7120 | Loss: 0.3002 | LM: 0.2908 | LB: 1.1329 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:33:47] Epoch 1 | Step 7130 | Loss: 0.3001 | LM: 0.2908 | LB: 1.1329 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:33:54] Epoch 1 | Step 7140 | Loss: 0.3001 | LM: 0.2908 | LB: 1.1329 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:34:02] Epoch 1 | Step 7150 | Loss: 0.3001 | LM: 0.2907 | LB: 1.1329 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:34:09] Epoch 1 | Step 7160 | Loss: 0.3000 | LM: 0.2906 | LB: 1.1329 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:34:16] Epoch 1 | Step 7170 | Loss: 0.3001 | LM: 0.2906 | LB: 1.1328 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:34:23] Epoch 1 | Step 7180 | Loss: 0.3001 | LM: 0.2906 | LB: 1.1328 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:34:30] Epoch 1 | Step 7190 | Loss: 0.3001 | LM: 0.2907 | LB: 1.1328 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:34:38] Epoch 1 | Step 7200 | Loss: 0.3001 | LM: 0.2906 | LB: 1.1328 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:34:45] Epoch 1 | Step 7210 | Loss: 0.3000 | LM: 0.2905 | LB: 1.1328 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:34:52] Epoch 1 | Step 7220 | Loss: 0.3000 | LM: 0.2906 | LB: 1.1328 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:34:59] Epoch 1 | Step 7230 | Loss: 0.3000 | LM: 0.2906 | LB: 1.1328 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:35:07] Epoch 1 | Step 7240 | Loss: 0.3000 | LM: 0.2905 | LB: 1.1327 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:35:14] Epoch 1 | Step 7250 | Loss: 0.3000 | LM: 0.2905 | LB: 1.1327 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.430 | LR: 5.00e-06 |
| [2026-04-25 19:35:21] Epoch 1 | Step 7260 | Loss: 0.3000 | LM: 0.2904 | LB: 1.1327 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:35:28] Epoch 1 | Step 7270 | Loss: 0.3001 | LM: 0.2905 | LB: 1.1327 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:35:35] Epoch 1 | Step 7280 | Loss: 0.3001 | LM: 0.2905 | LB: 1.1327 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:35:43] Epoch 1 | Step 7290 | Loss: 0.3000 | LM: 0.2904 | LB: 1.1326 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:35:50] Epoch 1 | Step 7300 | Loss: 0.3000 | LM: 0.2905 | LB: 1.1326 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:35:57] Epoch 1 | Step 7310 | Loss: 0.3000 | LM: 0.2904 | LB: 1.1326 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:36:04] Epoch 1 | Step 7320 | Loss: 0.2999 | LM: 0.2905 | LB: 1.1326 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:36:12] Epoch 1 | Step 7330 | Loss: 0.2999 | LM: 0.2905 | LB: 1.1326 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:36:19] Epoch 1 | Step 7340 | Loss: 0.3000 | LM: 0.2906 | LB: 1.1326 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:36:26] Epoch 1 | Step 7350 | Loss: 0.3000 | LM: 0.2906 | LB: 1.1325 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:36:33] Epoch 1 | Step 7360 | Loss: 0.3000 | LM: 0.2906 | LB: 1.1325 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:36:41] Epoch 1 | Step 7370 | Loss: 0.2999 | LM: 0.2905 | LB: 1.1325 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:36:48] Epoch 1 | Step 7380 | Loss: 0.2999 | LM: 0.2904 | LB: 1.1325 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:36:55] Epoch 1 | Step 7390 | Loss: 0.2999 | LM: 0.2904 | LB: 1.1325 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:37:02] Epoch 1 | Step 7400 | Loss: 0.2998 | LM: 0.2903 | LB: 1.1325 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:37:10] Epoch 1 | Step 7410 | Loss: 0.2999 | LM: 0.2903 | LB: 1.1324 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:37:17] Epoch 1 | Step 7420 | Loss: 0.2999 | LM: 0.2903 | LB: 1.1324 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:37:24] Epoch 1 | Step 7430 | Loss: 0.2999 | LM: 0.2903 | LB: 1.1324 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:37:31] Epoch 1 | Step 7440 | Loss: 0.2999 | LM: 0.2903 | LB: 1.1324 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:37:39] Epoch 1 | Step 7450 | Loss: 0.2998 | LM: 0.2902 | LB: 1.1324 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:37:46] Epoch 1 | Step 7460 | Loss: 0.2998 | LM: 0.2901 | LB: 1.1324 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:37:53] Epoch 1 | Step 7470 | Loss: 0.2998 | LM: 0.2900 | LB: 1.1323 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:38:00] Epoch 1 | Step 7480 | Loss: 0.2998 | LM: 0.2900 | LB: 1.1323 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:38:08] Epoch 1 | Step 7490 | Loss: 0.2999 | LM: 0.2900 | LB: 1.1323 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:38:15] Epoch 1 | Step 7500 | Loss: 0.2999 | LM: 0.2901 | LB: 1.1323 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:38:22] Epoch 1 | Step 7510 | Loss: 0.2999 | LM: 0.2900 | LB: 1.1323 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.454/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:38:29] Epoch 1 | Step 7520 | Loss: 0.2999 | LM: 0.2900 | LB: 1.1323 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:38:37] Epoch 1 | Step 7530 | Loss: 0.2998 | LM: 0.2899 | LB: 1.1323 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:38:44] Epoch 1 | Step 7540 | Loss: 0.2998 | LM: 0.2899 | LB: 1.1322 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:38:51] Epoch 1 | Step 7550 | Loss: 0.2998 | LM: 0.2899 | LB: 1.1322 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:38:58] Epoch 1 | Step 7560 | Loss: 0.2998 | LM: 0.2898 | LB: 1.1322 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:39:06] Epoch 1 | Step 7570 | Loss: 0.2998 | LM: 0.2898 | LB: 1.1322 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:39:13] Epoch 1 | Step 7580 | Loss: 0.2997 | LM: 0.2898 | LB: 1.1322 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:39:20] Epoch 1 | Step 7590 | Loss: 0.2997 | LM: 0.2898 | LB: 1.1322 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:39:28] Epoch 1 | Step 7600 | Loss: 0.2996 | LM: 0.2898 | LB: 1.1322 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:39:35] Epoch 1 | Step 7610 | Loss: 0.2996 | LM: 0.2899 | LB: 1.1322 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:39:42] Epoch 1 | Step 7620 | Loss: 0.2996 | LM: 0.2899 | LB: 1.1321 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:39:49] Epoch 1 | Step 7630 | Loss: 0.2995 | LM: 0.2898 | LB: 1.1321 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:39:57] Epoch 1 | Step 7640 | Loss: 0.2995 | LM: 0.2897 | LB: 1.1321 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:40:04] Epoch 1 | Step 7650 | Loss: 0.2995 | LM: 0.2897 | LB: 1.1321 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:40:11] Epoch 1 | Step 7660 | Loss: 0.2995 | LM: 0.2896 | LB: 1.1321 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:40:18] Epoch 1 | Step 7670 | Loss: 0.2994 | LM: 0.2896 | LB: 1.1321 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:40:26] Epoch 1 | Step 7680 | Loss: 0.2994 | LM: 0.2896 | LB: 1.1320 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:40:33] Epoch 1 | Step 7690 | Loss: 0.2994 | LM: 0.2896 | LB: 1.1320 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:40:40] Epoch 1 | Step 7700 | Loss: 0.2994 | LM: 0.2895 | LB: 1.1320 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:40:48] Epoch 1 | Step 7710 | Loss: 0.2993 | LM: 0.2894 | LB: 1.1320 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:40:55] Epoch 1 | Step 7720 | Loss: 0.2994 | LM: 0.2894 | LB: 1.1320 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:41:02] Epoch 1 | Step 7730 | Loss: 0.2995 | LM: 0.2894 | LB: 1.1320 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:41:09] Epoch 1 | Step 7740 | Loss: 0.2995 | LM: 0.2895 | LB: 1.1320 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:41:17] Epoch 1 | Step 7750 | Loss: 0.2995 | LM: 0.2896 | LB: 1.1320 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:41:24] Epoch 1 | Step 7760 | Loss: 0.2994 | LM: 0.2895 | LB: 1.1319 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:41:31] Epoch 1 | Step 7770 | Loss: 0.2994 | LM: 0.2894 | LB: 1.1319 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:41:38] Epoch 1 | Step 7780 | Loss: 0.2994 | LM: 0.2894 | LB: 1.1319 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:41:46] Epoch 1 | Step 7790 | Loss: 0.2994 | LM: 0.2894 | LB: 1.1319 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:41:53] Epoch 1 | Step 7800 | Loss: 0.2994 | LM: 0.2893 | LB: 1.1319 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:42:00] Epoch 1 | Step 7810 | Loss: 0.2994 | LM: 0.2893 | LB: 1.1319 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:42:08] Epoch 1 | Step 7820 | Loss: 0.2994 | LM: 0.2894 | LB: 1.1318 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:42:15] Epoch 1 | Step 7830 | Loss: 0.2994 | LM: 0.2894 | LB: 1.1318 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:42:22] Epoch 1 | Step 7840 | Loss: 0.2993 | LM: 0.2892 | LB: 1.1318 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:42:30] Epoch 1 | Step 7850 | Loss: 0.2993 | LM: 0.2891 | LB: 1.1318 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:42:37] Epoch 1 | Step 7860 | Loss: 0.2992 | LM: 0.2891 | LB: 1.1318 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:42:44] Epoch 1 | Step 7870 | Loss: 0.2992 | LM: 0.2890 | LB: 1.1317 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:42:51] Epoch 1 | Step 7880 | Loss: 0.2992 | LM: 0.2890 | LB: 1.1317 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:42:59] Epoch 1 | Step 7890 | Loss: 0.2992 | LM: 0.2891 | LB: 1.1317 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:43:06] Epoch 1 | Step 7900 | Loss: 0.2993 | LM: 0.2890 | LB: 1.1317 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:43:13] Epoch 1 | Step 7910 | Loss: 0.2993 | LM: 0.2892 | LB: 1.1317 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:43:20] Epoch 1 | Step 7920 | Loss: 0.2993 | LM: 0.2892 | LB: 1.1317 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:43:28] Epoch 1 | Step 7930 | Loss: 0.2993 | LM: 0.2892 | LB: 1.1317 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.429 | LR: 5.00e-06 |
| [2026-04-25 19:43:35] Epoch 1 | Step 7940 | Loss: 0.2993 | LM: 0.2892 | LB: 1.1316 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:43:42] Epoch 1 | Step 7950 | Loss: 0.2994 | LM: 0.2893 | LB: 1.1316 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:43:50] Epoch 1 | Step 7960 | Loss: 0.2993 | LM: 0.2893 | LB: 1.1316 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:43:57] Epoch 1 | Step 7970 | Loss: 0.2993 | LM: 0.2892 | LB: 1.1316 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:44:04] Epoch 1 | Step 7980 | Loss: 0.2993 | LM: 0.2892 | LB: 1.1316 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:44:11] Epoch 1 | Step 7990 | Loss: 0.2993 | LM: 0.2892 | LB: 1.1316 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:44:19] Epoch 1 | Step 8000 | Loss: 0.2992 | LM: 0.2892 | LB: 1.1316 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:44:19] Validation | Batch 10/42 | Loss: 0.2795 | LM_LOSS: 0.2684 | LB_LOSS: 1.1157 |
| [2026-04-25 19:44:21] Validation | Batch 20/42 | Loss: 0.3002 | LM_LOSS: 0.2890 | LB_LOSS: 1.1182 |
| [2026-04-25 19:44:22] Validation | Batch 30/42 | Loss: 0.2914 | LM_LOSS: 0.2802 | LB_LOSS: 1.1147 |
| [2026-04-25 19:44:23] Validation | Batch 40/42 | Loss: 0.2954 | LM_LOSS: 0.2843 | LB_LOSS: 1.1135 |
| [2026-04-25 19:44:23] Validation | Batch 42/42 | Loss: 0.2949 | LM_LOSS: 0.2837 | LB_LOSS: 1.1137 |
| [2026-04-25 19:44:23] Validation | Loss: 0.2949 | LM_LOSS: 0.2837 | LB_LOSS: 1.1137 | PPL: 1.33 | Time: 4.82s |
| [2026-04-25 19:44:27] New best model saved! Val loss: 0.2949 |
| [2026-04-25 19:44:34] Epoch 1 | Step 8010 | Loss: 0.2992 | LM: 0.2891 | LB: 1.1316 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:44:41] Epoch 1 | Step 8020 | Loss: 0.2992 | LM: 0.2890 | LB: 1.1316 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:44:49] Epoch 1 | Step 8030 | Loss: 0.2992 | LM: 0.2889 | LB: 1.1316 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:44:56] Epoch 1 | Step 8040 | Loss: 0.2992 | LM: 0.2889 | LB: 1.1315 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:45:03] Epoch 1 | Step 8050 | Loss: 0.2991 | LM: 0.2887 | LB: 1.1315 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:45:10] Epoch 1 | Step 8060 | Loss: 0.2991 | LM: 0.2888 | LB: 1.1316 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:45:17] Epoch 1 | Step 8070 | Loss: 0.2991 | LM: 0.2887 | LB: 1.1316 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:45:25] Epoch 1 | Step 8080 | Loss: 0.2991 | LM: 0.2887 | LB: 1.1316 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:45:32] Epoch 1 | Step 8090 | Loss: 0.2991 | LM: 0.2887 | LB: 1.1315 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:45:39] Epoch 1 | Step 8100 | Loss: 0.2990 | LM: 0.2887 | LB: 1.1315 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:45:47] Epoch 1 | Step 8110 | Loss: 0.2991 | LM: 0.2887 | LB: 1.1315 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:45:54] Epoch 1 | Step 8120 | Loss: 0.2991 | LM: 0.2886 | LB: 1.1315 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:46:01] Epoch 1 | Step 8130 | Loss: 0.2991 | LM: 0.2887 | LB: 1.1315 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:46:08] Epoch 1 | Step 8140 | Loss: 0.2991 | LM: 0.2887 | LB: 1.1315 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:46:15] Epoch 1 | Step 8150 | Loss: 0.2991 | LM: 0.2886 | LB: 1.1315 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:46:23] Epoch 1 | Step 8160 | Loss: 0.2990 | LM: 0.2886 | LB: 1.1315 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:46:30] Epoch 1 | Step 8170 | Loss: 0.2990 | LM: 0.2885 | LB: 1.1315 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:46:37] Epoch 1 | Step 8180 | Loss: 0.2990 | LM: 0.2886 | LB: 1.1314 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:46:44] Epoch 1 | Step 8190 | Loss: 0.2990 | LM: 0.2887 | LB: 1.1314 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:46:52] Epoch 1 | Step 8200 | Loss: 0.2990 | LM: 0.2887 | LB: 1.1314 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:46:59] Epoch 1 | Step 8210 | Loss: 0.2990 | LM: 0.2887 | LB: 1.1314 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:47:06] Epoch 1 | Step 8220 | Loss: 0.2990 | LM: 0.2887 | LB: 1.1314 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:47:13] Epoch 1 | Step 8230 | Loss: 0.2990 | LM: 0.2887 | LB: 1.1313 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:47:21] Epoch 1 | Step 8240 | Loss: 0.2990 | LM: 0.2887 | LB: 1.1313 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:47:28] Epoch 1 | Step 8250 | Loss: 0.2990 | LM: 0.2887 | LB: 1.1313 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:47:35] Epoch 1 | Step 8260 | Loss: 0.2991 | LM: 0.2887 | LB: 1.1313 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:47:42] Epoch 1 | Step 8270 | Loss: 0.2991 | LM: 0.2888 | LB: 1.1313 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:47:49] Epoch 1 | Step 8280 | Loss: 0.2991 | LM: 0.2887 | LB: 1.1313 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:47:57] Epoch 1 | Step 8290 | Loss: 0.2991 | LM: 0.2887 | LB: 1.1313 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:48:04] Epoch 1 | Step 8300 | Loss: 0.2991 | LM: 0.2886 | LB: 1.1312 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:48:11] Epoch 1 | Step 8310 | Loss: 0.2991 | LM: 0.2886 | LB: 1.1312 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:48:18] Epoch 1 | Step 8320 | Loss: 0.2991 | LM: 0.2885 | LB: 1.1312 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:48:26] Epoch 1 | Step 8330 | Loss: 0.2991 | LM: 0.2887 | LB: 1.1312 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:48:33] Epoch 1 | Step 8340 | Loss: 0.2991 | LM: 0.2887 | LB: 1.1312 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:48:40] Epoch 1 | Step 8350 | Loss: 0.2991 | LM: 0.2887 | LB: 1.1312 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.453/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:48:47] Epoch 1 | Step 8360 | Loss: 0.2990 | LM: 0.2887 | LB: 1.1312 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:48:54] Epoch 1 | Step 8370 | Loss: 0.2990 | LM: 0.2887 | LB: 1.1312 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:49:01] Epoch 1 | Step 8380 | Loss: 0.2990 | LM: 0.2887 | LB: 1.1312 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:49:09] Epoch 1 | Step 8390 | Loss: 0.2991 | LM: 0.2888 | LB: 1.1312 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:49:16] Epoch 1 | Step 8400 | Loss: 0.2990 | LM: 0.2888 | LB: 1.1311 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:49:23] Epoch 1 | Step 8410 | Loss: 0.2991 | LM: 0.2888 | LB: 1.1311 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:49:30] Epoch 1 | Step 8420 | Loss: 0.2991 | LM: 0.2888 | LB: 1.1311 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:49:37] Epoch 1 | Step 8430 | Loss: 0.2990 | LM: 0.2887 | LB: 1.1311 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:49:44] Epoch 1 | Step 8440 | Loss: 0.2990 | LM: 0.2887 | LB: 1.1311 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:49:52] Epoch 1 | Step 8450 | Loss: 0.2990 | LM: 0.2886 | LB: 1.1311 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:49:59] Epoch 1 | Step 8460 | Loss: 0.2990 | LM: 0.2887 | LB: 1.1311 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:50:06] Epoch 1 | Step 8470 | Loss: 0.2990 | LM: 0.2887 | LB: 1.1310 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:50:13] Epoch 1 | Step 8480 | Loss: 0.2990 | LM: 0.2887 | LB: 1.1311 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:50:20] Epoch 1 | Step 8490 | Loss: 0.2989 | LM: 0.2887 | LB: 1.1311 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:50:27] Epoch 1 | Step 8500 | Loss: 0.2990 | LM: 0.2887 | LB: 1.1310 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:50:34] Epoch 1 | Step 8510 | Loss: 0.2989 | LM: 0.2886 | LB: 1.1310 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:50:42] Epoch 1 | Step 8520 | Loss: 0.2990 | LM: 0.2885 | LB: 1.1310 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:50:49] Epoch 1 | Step 8530 | Loss: 0.2989 | LM: 0.2885 | LB: 1.1310 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:50:56] Epoch 1 | Step 8540 | Loss: 0.2990 | LM: 0.2887 | LB: 1.1310 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:51:03] Epoch 1 | Step 8550 | Loss: 0.2990 | LM: 0.2886 | LB: 1.1310 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:51:11] Epoch 1 | Step 8560 | Loss: 0.2990 | LM: 0.2886 | LB: 1.1310 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:51:18] Epoch 1 | Step 8570 | Loss: 0.2990 | LM: 0.2885 | LB: 1.1309 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:51:25] Epoch 1 | Step 8580 | Loss: 0.2990 | LM: 0.2885 | LB: 1.1309 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:51:32] Epoch 1 | Step 8590 | Loss: 0.2989 | LM: 0.2884 | LB: 1.1309 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:51:39] Epoch 1 | Step 8600 | Loss: 0.2989 | LM: 0.2884 | LB: 1.1309 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:51:47] Epoch 1 | Step 8610 | Loss: 0.2989 | LM: 0.2884 | LB: 1.1309 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:51:54] Epoch 1 | Step 8620 | Loss: 0.2989 | LM: 0.2883 | LB: 1.1309 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:52:01] Epoch 1 | Step 8630 | Loss: 0.2988 | LM: 0.2882 | LB: 1.1309 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:52:08] Epoch 1 | Step 8640 | Loss: 0.2989 | LM: 0.2883 | LB: 1.1309 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:52:15] Epoch 1 | Step 8650 | Loss: 0.2989 | LM: 0.2883 | LB: 1.1308 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:52:23] Epoch 1 | Step 8660 | Loss: 0.2989 | LM: 0.2882 | LB: 1.1308 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:52:30] Epoch 1 | Step 8670 | Loss: 0.2989 | LM: 0.2882 | LB: 1.1308 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:52:37] Epoch 1 | Step 8680 | Loss: 0.2989 | LM: 0.2882 | LB: 1.1308 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:52:44] Epoch 1 | Step 8690 | Loss: 0.2989 | LM: 0.2882 | LB: 1.1308 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:52:52] Epoch 1 | Step 8700 | Loss: 0.2988 | LM: 0.2882 | LB: 1.1308 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:52:59] Epoch 1 | Step 8710 | Loss: 0.2988 | LM: 0.2881 | LB: 1.1308 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:53:06] Epoch 1 | Step 8720 | Loss: 0.2987 | LM: 0.2881 | LB: 1.1308 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:53:13] Epoch 1 | Step 8730 | Loss: 0.2987 | LM: 0.2881 | LB: 1.1307 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:53:20] Epoch 1 | Step 8740 | Loss: 0.2988 | LM: 0.2882 | LB: 1.1307 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:53:28] Epoch 1 | Step 8750 | Loss: 0.2987 | LM: 0.2881 | LB: 1.1307 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:53:35] Epoch 1 | Step 8760 | Loss: 0.2987 | LM: 0.2882 | LB: 1.1307 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:53:42] Epoch 1 | Step 8770 | Loss: 0.2987 | LM: 0.2882 | LB: 1.1307 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:53:49] Epoch 1 | Step 8780 | Loss: 0.2987 | LM: 0.2883 | LB: 1.1307 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:53:56] Epoch 1 | Step 8790 | Loss: 0.2987 | LM: 0.2883 | LB: 1.1307 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:54:04] Epoch 1 | Step 8800 | Loss: 0.2987 | LM: 0.2882 | LB: 1.1307 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.428 | LR: 5.00e-06 |
| [2026-04-25 19:54:11] Epoch 1 | Step 8810 | Loss: 0.2986 | LM: 0.2882 | LB: 1.1307 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:54:18] Epoch 1 | Step 8820 | Loss: 0.2986 | LM: 0.2883 | LB: 1.1307 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:54:25] Epoch 1 | Step 8830 | Loss: 0.2986 | LM: 0.2883 | LB: 1.1306 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:54:33] Epoch 1 | Step 8840 | Loss: 0.2986 | LM: 0.2883 | LB: 1.1306 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:54:40] Epoch 1 | Step 8850 | Loss: 0.2986 | LM: 0.2883 | LB: 1.1306 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:54:47] Epoch 1 | Step 8860 | Loss: 0.2986 | LM: 0.2883 | LB: 1.1306 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:54:54] Epoch 1 | Step 8870 | Loss: 0.2986 | LM: 0.2884 | LB: 1.1306 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:55:02] Epoch 1 | Step 8880 | Loss: 0.2985 | LM: 0.2883 | LB: 1.1306 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:55:09] Epoch 1 | Step 8890 | Loss: 0.2985 | LM: 0.2883 | LB: 1.1306 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:55:16] Epoch 1 | Step 8900 | Loss: 0.2984 | LM: 0.2883 | LB: 1.1306 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:55:23] Epoch 1 | Step 8910 | Loss: 0.2984 | LM: 0.2884 | LB: 1.1306 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:55:30] Epoch 1 | Step 8920 | Loss: 0.2984 | LM: 0.2882 | LB: 1.1306 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:55:38] Epoch 1 | Step 8930 | Loss: 0.2983 | LM: 0.2882 | LB: 1.1305 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:55:45] Epoch 1 | Step 8940 | Loss: 0.2984 | LM: 0.2882 | LB: 1.1306 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:55:52] Epoch 1 | Step 8950 | Loss: 0.2984 | LM: 0.2882 | LB: 1.1305 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.355 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:55:59] Epoch 1 | Step 8960 | Loss: 0.2984 | LM: 0.2882 | LB: 1.1305 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:56:06] Epoch 1 | Step 8970 | Loss: 0.2984 | LM: 0.2882 | LB: 1.1305 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:56:13] Epoch 1 | Step 8980 | Loss: 0.2983 | LM: 0.2882 | LB: 1.1305 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:56:21] Epoch 1 | Step 8990 | Loss: 0.2983 | LM: 0.2881 | LB: 1.1305 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:56:28] Epoch 1 | Step 9000 | Loss: 0.2983 | LM: 0.2881 | LB: 1.1305 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:56:35] Epoch 1 | Step 9010 | Loss: 0.2983 | LM: 0.2881 | LB: 1.1305 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:56:42] Epoch 1 | Step 9020 | Loss: 0.2983 | LM: 0.2881 | LB: 1.1305 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:56:50] Epoch 1 | Step 9030 | Loss: 0.2983 | LM: 0.2881 | LB: 1.1305 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:56:57] Epoch 1 | Step 9040 | Loss: 0.2983 | LM: 0.2881 | LB: 1.1305 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:57:04] Epoch 1 | Step 9050 | Loss: 0.2983 | LM: 0.2881 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:57:11] Epoch 1 | Step 9060 | Loss: 0.2983 | LM: 0.2880 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:57:19] Epoch 1 | Step 9070 | Loss: 0.2982 | LM: 0.2880 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:57:26] Epoch 1 | Step 9080 | Loss: 0.2983 | LM: 0.2879 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:57:33] Epoch 1 | Step 9090 | Loss: 0.2982 | LM: 0.2879 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:57:40] Epoch 1 | Step 9100 | Loss: 0.2982 | LM: 0.2879 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:57:47] Epoch 1 | Step 9110 | Loss: 0.2982 | LM: 0.2878 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:57:54] Epoch 1 | Step 9120 | Loss: 0.2982 | LM: 0.2879 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:58:02] Epoch 1 | Step 9130 | Loss: 0.2982 | LM: 0.2879 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:58:09] Epoch 1 | Step 9140 | Loss: 0.2982 | LM: 0.2879 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:58:16] Epoch 1 | Step 9150 | Loss: 0.2982 | LM: 0.2878 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:58:23] Epoch 1 | Step 9160 | Loss: 0.2982 | LM: 0.2878 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:58:30] Epoch 1 | Step 9170 | Loss: 0.2981 | LM: 0.2877 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:58:37] Epoch 1 | Step 9180 | Loss: 0.2981 | LM: 0.2877 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:58:45] Epoch 1 | Step 9190 | Loss: 0.2980 | LM: 0.2876 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:58:52] Epoch 1 | Step 9200 | Loss: 0.2980 | LM: 0.2876 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:58:59] Epoch 1 | Step 9210 | Loss: 0.2980 | LM: 0.2876 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:59:06] Epoch 1 | Step 9220 | Loss: 0.2980 | LM: 0.2875 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:59:14] Epoch 1 | Step 9230 | Loss: 0.2980 | LM: 0.2875 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:59:21] Epoch 1 | Step 9240 | Loss: 0.2979 | LM: 0.2875 | LB: 1.1304 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:59:28] Epoch 1 | Step 9250 | Loss: 0.2979 | LM: 0.2874 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:59:35] Epoch 1 | Step 9260 | Loss: 0.2979 | LM: 0.2874 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:59:42] Epoch 1 | Step 9270 | Loss: 0.2979 | LM: 0.2874 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:59:50] Epoch 1 | Step 9280 | Loss: 0.2979 | LM: 0.2873 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 19:59:57] Epoch 1 | Step 9290 | Loss: 0.2979 | LM: 0.2874 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:00:04] Epoch 1 | Step 9300 | Loss: 0.2978 | LM: 0.2873 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:00:11] Epoch 1 | Step 9310 | Loss: 0.2978 | LM: 0.2873 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:00:18] Epoch 1 | Step 9320 | Loss: 0.2978 | LM: 0.2873 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:00:25] Epoch 1 | Step 9330 | Loss: 0.2978 | LM: 0.2873 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:00:32] Epoch 1 | Step 9340 | Loss: 0.2977 | LM: 0.2873 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:00:40] Epoch 1 | Step 9350 | Loss: 0.2977 | LM: 0.2873 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:00:47] Epoch 1 | Step 9360 | Loss: 0.2977 | LM: 0.2872 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:00:54] Epoch 1 | Step 9370 | Loss: 0.2977 | LM: 0.2871 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:01:01] Epoch 1 | Step 9380 | Loss: 0.2977 | LM: 0.2871 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:01:08] Epoch 1 | Step 9390 | Loss: 0.2976 | LM: 0.2870 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:01:16] Epoch 1 | Step 9400 | Loss: 0.2977 | LM: 0.2871 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:01:23] Epoch 1 | Step 9410 | Loss: 0.2976 | LM: 0.2871 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:01:30] Epoch 1 | Step 9420 | Loss: 0.2977 | LM: 0.2871 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:01:37] Epoch 1 | Step 9430 | Loss: 0.2977 | LM: 0.2871 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:01:44] Epoch 1 | Step 9440 | Loss: 0.2977 | LM: 0.2871 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:01:52] Epoch 1 | Step 9450 | Loss: 0.2977 | LM: 0.2871 | LB: 1.1303 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:01:59] Epoch 1 | Step 9460 | Loss: 0.2977 | LM: 0.2870 | LB: 1.1302 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:02:06] Epoch 1 | Step 9470 | Loss: 0.2976 | LM: 0.2870 | LB: 1.1302 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:02:13] Epoch 1 | Step 9480 | Loss: 0.2976 | LM: 0.2869 | LB: 1.1302 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:02:20] Epoch 1 | Step 9490 | Loss: 0.2976 | LM: 0.2869 | LB: 1.1302 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:02:27] Epoch 1 | Step 9500 | Loss: 0.2976 | LM: 0.2871 | LB: 1.1302 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:02:35] Epoch 1 | Step 9510 | Loss: 0.2976 | LM: 0.2870 | LB: 1.1302 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:02:42] Epoch 1 | Step 9520 | Loss: 0.2976 | LM: 0.2871 | LB: 1.1302 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:02:49] Epoch 1 | Step 9530 | Loss: 0.2976 | LM: 0.2871 | LB: 1.1302 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:02:56] Epoch 1 | Step 9540 | Loss: 0.2976 | LM: 0.2871 | LB: 1.1302 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:03:03] Epoch 1 | Step 9550 | Loss: 0.2976 | LM: 0.2871 | LB: 1.1302 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:03:11] Epoch 1 | Step 9560 | Loss: 0.2976 | LM: 0.2871 | LB: 1.1302 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:03:18] Epoch 1 | Step 9570 | Loss: 0.2976 | LM: 0.2871 | LB: 1.1302 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:03:25] Epoch 1 | Step 9580 | Loss: 0.2976 | LM: 0.2871 | LB: 1.1302 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:03:32] Epoch 1 | Step 9590 | Loss: 0.2976 | LM: 0.2871 | LB: 1.1302 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:03:39] Epoch 1 | Step 9600 | Loss: 0.2976 | LM: 0.2871 | LB: 1.1302 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:03:46] Epoch 1 | Step 9610 | Loss: 0.2976 | LM: 0.2870 | LB: 1.1302 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:03:54] Epoch 1 | Step 9620 | Loss: 0.2976 | LM: 0.2869 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:04:01] Epoch 1 | Step 9630 | Loss: 0.2976 | LM: 0.2870 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:04:08] Epoch 1 | Step 9640 | Loss: 0.2976 | LM: 0.2869 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:04:15] Epoch 1 | Step 9650 | Loss: 0.2976 | LM: 0.2869 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:04:22] Epoch 1 | Step 9660 | Loss: 0.2976 | LM: 0.2868 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:04:30] Epoch 1 | Step 9670 | Loss: 0.2976 | LM: 0.2869 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:04:37] Epoch 1 | Step 9680 | Loss: 0.2976 | LM: 0.2868 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:04:44] Epoch 1 | Step 9690 | Loss: 0.2976 | LM: 0.2868 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:04:51] Epoch 1 | Step 9700 | Loss: 0.2976 | LM: 0.2868 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:04:59] Epoch 1 | Step 9710 | Loss: 0.2975 | LM: 0.2868 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:05:06] Epoch 1 | Step 9720 | Loss: 0.2975 | LM: 0.2867 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:05:13] Epoch 1 | Step 9730 | Loss: 0.2975 | LM: 0.2867 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:05:20] Epoch 1 | Step 9740 | Loss: 0.2975 | LM: 0.2867 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:05:28] Epoch 1 | Step 9750 | Loss: 0.2975 | LM: 0.2867 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:05:35] Epoch 1 | Step 9760 | Loss: 0.2975 | LM: 0.2867 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:05:42] Epoch 1 | Step 9770 | Loss: 0.2975 | LM: 0.2867 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:05:49] Epoch 1 | Step 9780 | Loss: 0.2974 | LM: 0.2867 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:05:56] Epoch 1 | Step 9790 | Loss: 0.2974 | LM: 0.2867 | LB: 1.1301 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:06:04] Epoch 1 | Step 9800 | Loss: 0.2974 | LM: 0.2867 | LB: 1.1300 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:06:11] Epoch 1 | Step 9810 | Loss: 0.2974 | LM: 0.2867 | LB: 1.1300 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:06:18] Epoch 1 | Step 9820 | Loss: 0.2974 | LM: 0.2867 | LB: 1.1300 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:06:26] Epoch 1 | Step 9830 | Loss: 0.2974 | LM: 0.2866 | LB: 1.1300 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:06:33] Epoch 1 | Step 9840 | Loss: 0.2974 | LM: 0.2866 | LB: 1.1300 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:06:40] Epoch 1 | Step 9850 | Loss: 0.2974 | LM: 0.2866 | LB: 1.1300 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:06:47] Epoch 1 | Step 9860 | Loss: 0.2974 | LM: 0.2867 | LB: 1.1300 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:06:54] Epoch 1 | Step 9870 | Loss: 0.2974 | LM: 0.2867 | LB: 1.1300 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:07:02] Epoch 1 | Step 9880 | Loss: 0.2974 | LM: 0.2868 | LB: 1.1300 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.427 | LR: 5.00e-06 |
| [2026-04-25 20:07:07] Epoch 1 completed in 7214.25s | Loss: 0.2974 | CL0: 2.8 | CL1: 2.2 |
| [2026-04-25 20:07:07] |
| Training completed! |
| [2026-04-25 20:07:10] Final model: /workspace/byte-llms-code/outputs/lr_sweep/hnet_xl_code_lr_5e-5/model_final.pt |
|
|