| [2026-04-26 00:19:39,962][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. |
| [2026-04-26 00:19:39] CUDA_VISIBLE_DEVICES: 0,1 |
| [2026-04-26 00:19:39] Number of processes: 2 |
| [2026-04-26 00:19:39] Process index: 0 |
| [2026-04-26 00:19:39] Mixed precision: bf16 |
| [2026-04-26 00:19:39] ============================================================ |
| [2026-04-26 00:19:39] HNet Training Pipeline (Hydra + Trackio + Accelerate) |
| [2026-04-26 00:19:39] ============================================================ |
| [2026-04-26 00:19:39] Config: |
| model: |
| config_path: /workspace/byte-llms-code/hnet_project/configs/hnet_2stage_XL_code.json |
| checkpoint_path: /workspace/byte-llms-code/hnet_project/checkpoints/hnet_2stage_XL_code.pt |
| training: |
| epochs: 1 |
| batch_size: 4 |
| eval_batch_size: 24 |
| gradient_accumulation_steps: 4 |
| lr: 0.0005 |
| 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-4 |
| entity: null |
| base_url: https://wandb.platun0v.ru |
| local_dir: /workspace/byte-llms-code/outputs/lr_sweep/hnet_xl_code_lr_5e-4 |
| paths: |
| output_dir: /workspace/byte-llms-code/outputs/lr_sweep/hnet_xl_code_lr_5e-4 |
| seed: 42 |
| device: cuda |
|
|
| [2026-04-26 00:19:42] Initializing tokenizer... |
| [2026-04-26 00:19:42] Loading model... |
| [2026-04-26 00:19:46] Loaded pretrained: /workspace/byte-llms-code/hnet_project/checkpoints/hnet_2stage_XL_code.pt |
| [2026-04-26 00:19:46] Applied LR multipliers: [2.0, 1.5, 1.0] |
| [2026-04-26 00:19:46] Warming up model... |
| [2026-04-26 00:20:30] Total params: 1,654,090,112 |
| [2026-04-26 00:20:30] Trainable params: 1,654,090,112 |
| [2026-04-26 00:20:30] Creating dataloaders... |
| [2026-04-26 00:20:30] Train dataset size: 316397 |
| [2026-04-26 00:20:30] Train batches per epoch (before DDP split): 79100 |
| [2026-04-26 00:20:30] Validation dataset size: 2000 |
| [2026-04-26 00:20:30] Validation batches: 84 |
| [2026-04-26 00:20:30] Creating optimizer... |
| [2026-04-26 00:20:30] Total steps: 9887, Steps per epoch: 39550 |
| [2026-04-26 00:20:30] Preparing model, optimizer, and dataloaders with Accelerate... |
| [2026-04-26 00:20:31] Train batches per epoch (after DDP split): 39550 |
| [2026-04-26 00:20:31] Starting training... |
| [2026-04-26 00:20:31] |
| ============================================================ |
| [2026-04-26 00:20:31] EPOCH 1/1 |
| [2026-04-26 00:20:31] ============================================================ |
| [2026-04-26 00:21:00] Epoch 1 | Step 10 | Loss: 0.4872 | LM: 0.4905 | LB: 1.1588 | CL0: 2.9 | CL1: 2.1 | HR0: 0.352/SR0: 0.351 | HR1: 0.477/SR1: 0.456 | LR: 5.91e-05 |
| [2026-04-26 00:21:07] Epoch 1 | Step 20 | Loss: 0.4350 | LM: 0.4343 | LB: 1.1587 | CL0: 2.9 | CL1: 2.1 | HR0: 0.352/SR0: 0.351 | HR1: 0.478/SR1: 0.458 | LR: 6.82e-05 |
| [2026-04-26 00:21:14] Epoch 1 | Step 30 | Loss: 0.4059 | LM: 0.3807 | LB: 1.1566 | CL0: 2.9 | CL1: 2.1 | HR0: 0.352/SR0: 0.351 | HR1: 0.477/SR1: 0.455 | LR: 7.73e-05 |
| [2026-04-26 00:21:21] Epoch 1 | Step 40 | Loss: 0.3922 | LM: 0.3709 | LB: 1.1645 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.481/SR1: 0.459 | LR: 8.64e-05 |
| [2026-04-26 00:21:28] Epoch 1 | Step 50 | Loss: 0.3724 | LM: 0.3462 | LB: 1.1630 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.479/SR1: 0.458 | LR: 9.55e-05 |
| [2026-04-26 00:21:36] Epoch 1 | Step 60 | Loss: 0.3575 | LM: 0.3315 | LB: 1.1649 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.481/SR1: 0.461 | LR: 1.05e-04 |
| [2026-04-26 00:21:43] Epoch 1 | Step 70 | Loss: 0.3491 | LM: 0.3283 | LB: 1.1640 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.480/SR1: 0.459 | LR: 1.14e-04 |
| [2026-04-26 00:21:50] Epoch 1 | Step 80 | Loss: 0.3458 | LM: 0.3333 | LB: 1.1648 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.481/SR1: 0.459 | LR: 1.23e-04 |
| [2026-04-26 00:21:57] Epoch 1 | Step 90 | Loss: 0.3442 | LM: 0.3325 | LB: 1.1649 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.481/SR1: 0.459 | LR: 1.32e-04 |
| [2026-04-26 00:22:04] Epoch 1 | Step 100 | Loss: 0.3400 | LM: 0.3378 | LB: 1.1641 | CL0: 2.8 | CL1: 2.1 | HR0: 0.360/SR0: 0.357 | HR1: 0.479/SR1: 0.458 | LR: 1.41e-04 |
| [2026-04-26 00:22:11] Epoch 1 | Step 110 | Loss: 0.3399 | LM: 0.3444 | LB: 1.1644 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.480/SR1: 0.458 | LR: 1.50e-04 |
| [2026-04-26 00:22:18] Epoch 1 | Step 120 | Loss: 0.3394 | LM: 0.3361 | LB: 1.1629 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.479/SR1: 0.457 | LR: 1.59e-04 |
| [2026-04-26 00:22:25] Epoch 1 | Step 130 | Loss: 0.3381 | LM: 0.3329 | LB: 1.1621 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.479/SR1: 0.457 | LR: 1.68e-04 |
| [2026-04-26 00:22:33] Epoch 1 | Step 140 | Loss: 0.3372 | LM: 0.3354 | LB: 1.1621 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.478/SR1: 0.457 | LR: 1.78e-04 |
| [2026-04-26 00:22:40] Epoch 1 | Step 150 | Loss: 0.3331 | LM: 0.3255 | LB: 1.1612 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.477/SR1: 0.456 | LR: 1.87e-04 |
| [2026-04-26 00:22:47] Epoch 1 | Step 160 | Loss: 0.3306 | LM: 0.3237 | LB: 1.1614 | CL0: 2.8 | CL1: 2.1 | HR0: 0.359/SR0: 0.357 | HR1: 0.477/SR1: 0.456 | LR: 1.96e-04 |
| [2026-04-26 00:22:54] Epoch 1 | Step 170 | Loss: 0.3322 | LM: 0.3314 | LB: 1.1588 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.475/SR1: 0.454 | LR: 2.05e-04 |
| [2026-04-26 00:23:01] Epoch 1 | Step 180 | Loss: 0.3292 | LM: 0.3287 | LB: 1.1574 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.474/SR1: 0.453 | LR: 2.14e-04 |
| [2026-04-26 00:23:08] Epoch 1 | Step 190 | Loss: 0.3294 | LM: 0.3288 | LB: 1.1557 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.472/SR1: 0.451 | LR: 2.23e-04 |
| [2026-04-26 00:23:15] Epoch 1 | Step 200 | Loss: 0.3293 | LM: 0.3336 | LB: 1.1543 | CL0: 2.8 | CL1: 2.1 | HR0: 0.358/SR0: 0.356 | HR1: 0.471/SR1: 0.451 | LR: 2.32e-04 |
| [2026-04-26 00:23:23] Epoch 1 | Step 210 | Loss: 0.3305 | LM: 0.3372 | LB: 1.1534 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.471/SR1: 0.450 | LR: 2.41e-04 |
| [2026-04-26 00:23:30] Epoch 1 | Step 220 | Loss: 0.3301 | LM: 0.3393 | LB: 1.1528 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.355 | HR1: 0.470/SR1: 0.450 | LR: 2.50e-04 |
| [2026-04-26 00:23:37] Epoch 1 | Step 230 | Loss: 0.3279 | LM: 0.3343 | LB: 1.1522 | CL0: 2.8 | CL1: 2.1 | HR0: 0.357/SR0: 0.356 | HR1: 0.469/SR1: 0.449 | LR: 2.60e-04 |
| [2026-04-26 00:23:44] Epoch 1 | Step 240 | Loss: 0.3277 | LM: 0.3314 | LB: 1.1507 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.355 | HR1: 0.468/SR1: 0.448 | LR: 2.69e-04 |
| [2026-04-26 00:23:51] Epoch 1 | Step 250 | Loss: 0.3271 | LM: 0.3279 | LB: 1.1498 | CL0: 2.8 | CL1: 2.2 | HR0: 0.356/SR0: 0.355 | HR1: 0.468/SR1: 0.448 | LR: 2.78e-04 |
| [2026-04-26 00:23:58] Epoch 1 | Step 260 | Loss: 0.3278 | LM: 0.3311 | LB: 1.1485 | CL0: 2.8 | CL1: 2.2 | HR0: 0.356/SR0: 0.354 | HR1: 0.467/SR1: 0.447 | LR: 2.87e-04 |
| [2026-04-26 00:24:05] Epoch 1 | Step 270 | Loss: 0.3270 | LM: 0.3328 | LB: 1.1468 | CL0: 2.8 | CL1: 2.2 | HR0: 0.356/SR0: 0.354 | HR1: 0.465/SR1: 0.445 | LR: 2.96e-04 |
| [2026-04-26 00:24:12] Epoch 1 | Step 280 | Loss: 0.3258 | LM: 0.3361 | LB: 1.1461 | CL0: 2.8 | CL1: 2.2 | HR0: 0.356/SR0: 0.355 | HR1: 0.464/SR1: 0.445 | LR: 3.05e-04 |
| [2026-04-26 00:24:20] Epoch 1 | Step 290 | Loss: 0.3252 | LM: 0.3363 | LB: 1.1451 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.462/SR1: 0.443 | LR: 3.14e-04 |
| [2026-04-26 00:24:27] Epoch 1 | Step 300 | Loss: 0.3259 | LM: 0.3370 | LB: 1.1442 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.461/SR1: 0.442 | LR: 3.23e-04 |
| [2026-04-26 00:24:34] Epoch 1 | Step 310 | Loss: 0.3258 | LM: 0.3361 | LB: 1.1425 | CL0: 2.8 | CL1: 2.2 | HR0: 0.357/SR0: 0.355 | HR1: 0.459/SR1: 0.441 | LR: 3.32e-04 |
| [2026-04-26 00:24:41] Epoch 1 | Step 320 | Loss: 0.3250 | LM: 0.3355 | LB: 1.1414 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.458/SR1: 0.439 | LR: 3.41e-04 |
| [2026-04-26 00:24:48] Epoch 1 | Step 330 | Loss: 0.3249 | LM: 0.3361 | LB: 1.1402 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.457/SR1: 0.438 | LR: 3.51e-04 |
| [2026-04-26 00:24:55] Epoch 1 | Step 340 | Loss: 0.3247 | LM: 0.3357 | LB: 1.1389 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.455/SR1: 0.437 | LR: 3.60e-04 |
| [2026-04-26 00:25:02] Epoch 1 | Step 350 | Loss: 0.3248 | LM: 0.3359 | LB: 1.1379 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.454/SR1: 0.436 | LR: 3.69e-04 |
| [2026-04-26 00:25:09] Epoch 1 | Step 360 | Loss: 0.3242 | LM: 0.3341 | LB: 1.1368 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.452/SR1: 0.435 | LR: 3.78e-04 |
| [2026-04-26 00:25:17] Epoch 1 | Step 370 | Loss: 0.3235 | LM: 0.3337 | LB: 1.1354 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.451/SR1: 0.434 | LR: 3.87e-04 |
| [2026-04-26 00:25:24] Epoch 1 | Step 380 | Loss: 0.3229 | LM: 0.3339 | LB: 1.1345 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.450/SR1: 0.433 | LR: 3.96e-04 |
| [2026-04-26 00:25:31] Epoch 1 | Step 390 | Loss: 0.3233 | LM: 0.3340 | LB: 1.1340 | CL0: 2.8 | CL1: 2.2 | HR0: 0.358/SR0: 0.356 | HR1: 0.449/SR1: 0.432 | LR: 4.05e-04 |
| [2026-04-26 00:25:38] Epoch 1 | Step 400 | Loss: 0.3240 | LM: 0.3350 | LB: 1.1328 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.448/SR1: 0.431 | LR: 4.14e-04 |
| [2026-04-26 00:25:45] Epoch 1 | Step 410 | Loss: 0.3244 | LM: 0.3360 | LB: 1.1318 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.447/SR1: 0.430 | LR: 4.23e-04 |
| [2026-04-26 00:25:52] Epoch 1 | Step 420 | Loss: 0.3246 | LM: 0.3367 | LB: 1.1312 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.446/SR1: 0.430 | LR: 4.33e-04 |
| [2026-04-26 00:25:59] Epoch 1 | Step 430 | Loss: 0.3260 | LM: 0.3363 | LB: 1.1307 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.446/SR1: 0.430 | LR: 4.42e-04 |
| [2026-04-26 00:26:06] Epoch 1 | Step 440 | Loss: 0.3252 | LM: 0.3360 | LB: 1.1301 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.445/SR1: 0.429 | LR: 4.51e-04 |
| [2026-04-26 00:26:13] Epoch 1 | Step 450 | Loss: 0.3258 | LM: 0.3369 | LB: 1.1296 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.445/SR1: 0.429 | LR: 4.60e-04 |
| [2026-04-26 00:26:21] Epoch 1 | Step 460 | Loss: 0.3265 | LM: 0.3366 | LB: 1.1292 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.444/SR1: 0.429 | LR: 4.69e-04 |
| [2026-04-26 00:26:28] Epoch 1 | Step 470 | Loss: 0.3265 | LM: 0.3365 | LB: 1.1284 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.356 | HR1: 0.443/SR1: 0.428 | LR: 4.78e-04 |
| [2026-04-26 00:26:35] Epoch 1 | Step 480 | Loss: 0.3268 | LM: 0.3363 | LB: 1.1277 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.443/SR1: 0.427 | LR: 4.87e-04 |
| [2026-04-26 00:26:42] Epoch 1 | Step 490 | Loss: 0.3270 | LM: 0.3361 | LB: 1.1271 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.442/SR1: 0.427 | LR: 4.96e-04 |
| [2026-04-26 00:26:49] Epoch 1 | Step 500 | Loss: 0.3277 | LM: 0.3348 | LB: 1.1264 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.441/SR1: 0.426 | LR: 5.00e-04 |
| [2026-04-26 00:26:56] Epoch 1 | Step 510 | Loss: 0.3277 | LM: 0.3334 | LB: 1.1257 | CL0: 2.8 | CL1: 2.3 | HR0: 0.358/SR0: 0.355 | HR1: 0.440/SR1: 0.425 | LR: 5.00e-04 |
| [2026-04-26 00:27:03] Epoch 1 | Step 520 | Loss: 0.3288 | LM: 0.3349 | LB: 1.1248 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.440/SR1: 0.424 | LR: 5.00e-04 |
| [2026-04-26 00:27:10] Epoch 1 | Step 530 | Loss: 0.3292 | LM: 0.3355 | LB: 1.1240 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.439/SR1: 0.424 | LR: 5.00e-04 |
| [2026-04-26 00:27:17] Epoch 1 | Step 540 | Loss: 0.3291 | LM: 0.3360 | LB: 1.1234 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.438/SR1: 0.423 | LR: 5.00e-04 |
| [2026-04-26 00:27:24] Epoch 1 | Step 550 | Loss: 0.3291 | LM: 0.3356 | LB: 1.1229 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.438/SR1: 0.423 | LR: 5.00e-04 |
| [2026-04-26 00:27:31] Epoch 1 | Step 560 | Loss: 0.3296 | LM: 0.3344 | LB: 1.1226 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.437/SR1: 0.423 | LR: 5.00e-04 |
| [2026-04-26 00:27:39] Epoch 1 | Step 570 | Loss: 0.3303 | LM: 0.3355 | LB: 1.1226 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.355 | HR1: 0.437/SR1: 0.423 | LR: 5.00e-04 |
| [2026-04-26 00:27:46] Epoch 1 | Step 580 | Loss: 0.3310 | LM: 0.3361 | LB: 1.1224 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.437/SR1: 0.423 | LR: 5.00e-04 |
| [2026-04-26 00:27:53] Epoch 1 | Step 590 | Loss: 0.3319 | LM: 0.3367 | LB: 1.1221 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.437/SR1: 0.422 | LR: 5.00e-04 |
| [2026-04-26 00:28:00] Epoch 1 | Step 600 | Loss: 0.3322 | LM: 0.3359 | LB: 1.1217 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.437/SR1: 0.422 | LR: 5.00e-04 |
| [2026-04-26 00:28:07] Epoch 1 | Step 610 | Loss: 0.3332 | LM: 0.3360 | LB: 1.1215 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.437/SR1: 0.422 | LR: 5.00e-04 |
| [2026-04-26 00:28:14] Epoch 1 | Step 620 | Loss: 0.3341 | LM: 0.3366 | LB: 1.1213 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.436/SR1: 0.422 | LR: 5.00e-04 |
| [2026-04-26 00:28:22] Epoch 1 | Step 630 | Loss: 0.3346 | LM: 0.3385 | LB: 1.1210 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.436/SR1: 0.422 | LR: 5.00e-04 |
| [2026-04-26 00:28:29] Epoch 1 | Step 640 | Loss: 0.3356 | LM: 0.3384 | LB: 1.1206 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.354 | HR1: 0.436/SR1: 0.421 | LR: 5.00e-04 |
| [2026-04-26 00:28:36] Epoch 1 | Step 650 | Loss: 0.3358 | LM: 0.3386 | LB: 1.1201 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.353 | HR1: 0.435/SR1: 0.421 | LR: 5.00e-04 |
| [2026-04-26 00:28:43] Epoch 1 | Step 660 | Loss: 0.3366 | LM: 0.3389 | LB: 1.1195 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.353 | HR1: 0.435/SR1: 0.420 | LR: 5.00e-04 |
| [2026-04-26 00:28:50] Epoch 1 | Step 670 | Loss: 0.3370 | LM: 0.3395 | LB: 1.1190 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.353 | HR1: 0.434/SR1: 0.420 | LR: 5.00e-04 |
| [2026-04-26 00:28:57] Epoch 1 | Step 680 | Loss: 0.3377 | LM: 0.3406 | LB: 1.1189 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.353 | HR1: 0.434/SR1: 0.420 | LR: 5.00e-04 |
| [2026-04-26 00:29:04] Epoch 1 | Step 690 | Loss: 0.3381 | LM: 0.3418 | LB: 1.1184 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.353 | HR1: 0.434/SR1: 0.419 | LR: 5.00e-04 |
| [2026-04-26 00:29:11] Epoch 1 | Step 700 | Loss: 0.3390 | LM: 0.3443 | LB: 1.1181 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.353 | HR1: 0.433/SR1: 0.419 | LR: 5.00e-04 |
| [2026-04-26 00:29:19] Epoch 1 | Step 710 | Loss: 0.3392 | LM: 0.3454 | LB: 1.1177 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.353 | HR1: 0.433/SR1: 0.419 | LR: 5.00e-04 |
| [2026-04-26 00:29:26] Epoch 1 | Step 720 | Loss: 0.3398 | LM: 0.3464 | LB: 1.1172 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.353 | HR1: 0.432/SR1: 0.418 | LR: 5.00e-04 |
| [2026-04-26 00:29:33] Epoch 1 | Step 730 | Loss: 0.3403 | LM: 0.3466 | LB: 1.1169 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.353 | HR1: 0.432/SR1: 0.418 | LR: 5.00e-04 |
| [2026-04-26 00:29:40] Epoch 1 | Step 740 | Loss: 0.3406 | LM: 0.3469 | LB: 1.1164 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.353 | HR1: 0.431/SR1: 0.417 | LR: 5.00e-04 |
| [2026-04-26 00:29:47] Epoch 1 | Step 750 | Loss: 0.3409 | LM: 0.3468 | LB: 1.1158 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.353 | HR1: 0.431/SR1: 0.417 | LR: 5.00e-04 |
| [2026-04-26 00:29:54] Epoch 1 | Step 760 | Loss: 0.3418 | LM: 0.3468 | LB: 1.1153 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.353 | HR1: 0.430/SR1: 0.416 | LR: 5.00e-04 |
| [2026-04-26 00:30:01] Epoch 1 | Step 770 | Loss: 0.3429 | LM: 0.3477 | LB: 1.1149 | CL0: 2.8 | CL1: 2.3 | HR0: 0.357/SR0: 0.353 | HR1: 0.430/SR1: 0.416 | LR: 5.00e-04 |
| [2026-04-26 00:30:08] Epoch 1 | Step 780 | Loss: 0.3433 | LM: 0.3477 | LB: 1.1145 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.352 | HR1: 0.429/SR1: 0.416 | LR: 5.00e-04 |
| [2026-04-26 00:30:15] Epoch 1 | Step 790 | Loss: 0.3436 | LM: 0.3482 | LB: 1.1142 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.352 | HR1: 0.429/SR1: 0.415 | LR: 5.00e-04 |
| [2026-04-26 00:30:22] Epoch 1 | Step 800 | Loss: 0.3434 | LM: 0.3474 | LB: 1.1138 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.352 | HR1: 0.429/SR1: 0.415 | LR: 5.00e-04 |
| [2026-04-26 00:30:30] Epoch 1 | Step 810 | Loss: 0.3437 | LM: 0.3483 | LB: 1.1135 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.352 | HR1: 0.428/SR1: 0.415 | LR: 5.00e-04 |
| [2026-04-26 00:30:37] Epoch 1 | Step 820 | Loss: 0.3440 | LM: 0.3481 | LB: 1.1132 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.352 | HR1: 0.428/SR1: 0.415 | LR: 5.00e-04 |
| [2026-04-26 00:30:44] Epoch 1 | Step 830 | Loss: 0.3447 | LM: 0.3494 | LB: 1.1127 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.352 | HR1: 0.428/SR1: 0.414 | LR: 5.00e-04 |
| [2026-04-26 00:30:51] Epoch 1 | Step 840 | Loss: 0.3450 | LM: 0.3488 | LB: 1.1124 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.352 | HR1: 0.427/SR1: 0.414 | LR: 5.00e-04 |
| [2026-04-26 00:30:58] Epoch 1 | Step 850 | Loss: 0.3448 | LM: 0.3490 | LB: 1.1120 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.352 | HR1: 0.427/SR1: 0.413 | LR: 5.00e-04 |
| [2026-04-26 00:31:05] Epoch 1 | Step 860 | Loss: 0.3454 | LM: 0.3487 | LB: 1.1116 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.352 | HR1: 0.426/SR1: 0.413 | LR: 5.00e-04 |
| [2026-04-26 00:31:12] Epoch 1 | Step 870 | Loss: 0.3464 | LM: 0.3495 | LB: 1.1113 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.352 | HR1: 0.426/SR1: 0.412 | LR: 5.00e-04 |
| [2026-04-26 00:31:19] Epoch 1 | Step 880 | Loss: 0.3471 | LM: 0.3501 | LB: 1.1110 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.352 | HR1: 0.425/SR1: 0.412 | LR: 5.00e-04 |
| [2026-04-26 00:31:26] Epoch 1 | Step 890 | Loss: 0.3477 | LM: 0.3503 | LB: 1.1107 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.352 | HR1: 0.425/SR1: 0.412 | LR: 5.00e-04 |
| [2026-04-26 00:31:34] Epoch 1 | Step 900 | Loss: 0.3481 | LM: 0.3501 | LB: 1.1105 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.352 | HR1: 0.425/SR1: 0.411 | LR: 5.00e-04 |
| [2026-04-26 00:31:41] Epoch 1 | Step 910 | Loss: 0.3487 | LM: 0.3504 | LB: 1.1101 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.352 | HR1: 0.424/SR1: 0.411 | LR: 5.00e-04 |
| [2026-04-26 00:31:48] Epoch 1 | Step 920 | Loss: 0.3496 | LM: 0.3510 | LB: 1.1099 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.352 | HR1: 0.424/SR1: 0.411 | LR: 5.00e-04 |
| [2026-04-26 00:31:55] Epoch 1 | Step 930 | Loss: 0.3500 | LM: 0.3509 | LB: 1.1096 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.352 | HR1: 0.423/SR1: 0.410 | LR: 5.00e-04 |
| [2026-04-26 00:32:02] Epoch 1 | Step 940 | Loss: 0.3505 | LM: 0.3507 | LB: 1.1093 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.352 | HR1: 0.423/SR1: 0.410 | LR: 5.00e-04 |
| [2026-04-26 00:32:09] Epoch 1 | Step 950 | Loss: 0.3504 | LM: 0.3510 | LB: 1.1092 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.352 | HR1: 0.423/SR1: 0.410 | LR: 5.00e-04 |
| [2026-04-26 00:32:16] Epoch 1 | Step 960 | Loss: 0.3504 | LM: 0.3521 | LB: 1.1091 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.352 | HR1: 0.423/SR1: 0.410 | LR: 5.00e-04 |
| [2026-04-26 00:32:23] Epoch 1 | Step 970 | Loss: 0.3507 | LM: 0.3529 | LB: 1.1089 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.352 | HR1: 0.423/SR1: 0.410 | LR: 5.00e-04 |
| [2026-04-26 00:32:30] Epoch 1 | Step 980 | Loss: 0.3506 | LM: 0.3521 | LB: 1.1087 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.352 | HR1: 0.423/SR1: 0.410 | LR: 5.00e-04 |
| [2026-04-26 00:32:38] Epoch 1 | Step 990 | Loss: 0.3506 | LM: 0.3526 | LB: 1.1086 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.352 | HR1: 0.423/SR1: 0.410 | LR: 5.00e-04 |
| [2026-04-26 00:32:45] Epoch 1 | Step 1000 | Loss: 0.3507 | LM: 0.3520 | LB: 1.1084 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.352 | HR1: 0.422/SR1: 0.410 | LR: 5.00e-04 |
| [2026-04-26 00:32:52] Epoch 1 | Step 1010 | Loss: 0.3513 | LM: 0.3529 | LB: 1.1082 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.352 | HR1: 0.422/SR1: 0.409 | LR: 5.00e-04 |
| [2026-04-26 00:32:59] Epoch 1 | Step 1020 | Loss: 0.3515 | LM: 0.3534 | LB: 1.1080 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.422/SR1: 0.409 | LR: 5.00e-04 |
| [2026-04-26 00:33:06] Epoch 1 | Step 1030 | Loss: 0.3520 | LM: 0.3534 | LB: 1.1077 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.351 | HR1: 0.422/SR1: 0.409 | LR: 5.00e-04 |
| [2026-04-26 00:33:13] Epoch 1 | Step 1040 | Loss: 0.3518 | LM: 0.3531 | LB: 1.1075 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.351 | HR1: 0.422/SR1: 0.409 | LR: 5.00e-04 |
| [2026-04-26 00:33:20] Epoch 1 | Step 1050 | Loss: 0.3519 | LM: 0.3533 | LB: 1.1074 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.421/SR1: 0.409 | LR: 5.00e-04 |
| [2026-04-26 00:33:27] Epoch 1 | Step 1060 | Loss: 0.3517 | LM: 0.3531 | LB: 1.1072 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.421/SR1: 0.409 | LR: 5.00e-04 |
| [2026-04-26 00:33:34] Epoch 1 | Step 1070 | Loss: 0.3517 | LM: 0.3527 | LB: 1.1070 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.421/SR1: 0.408 | LR: 5.00e-04 |
| [2026-04-26 00:33:41] Epoch 1 | Step 1080 | Loss: 0.3524 | LM: 0.3523 | LB: 1.1070 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.421/SR1: 0.408 | LR: 5.00e-04 |
| [2026-04-26 00:33:48] Epoch 1 | Step 1090 | Loss: 0.3532 | LM: 0.3533 | LB: 1.1069 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.421/SR1: 0.408 | LR: 5.00e-04 |
| [2026-04-26 00:33:56] Epoch 1 | Step 1100 | Loss: 0.3534 | LM: 0.3538 | LB: 1.1069 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.421/SR1: 0.408 | LR: 5.00e-04 |
| [2026-04-26 00:34:03] Epoch 1 | Step 1110 | Loss: 0.3537 | LM: 0.3533 | LB: 1.1069 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.421/SR1: 0.408 | LR: 5.00e-04 |
| [2026-04-26 00:34:10] Epoch 1 | Step 1120 | Loss: 0.3542 | LM: 0.3534 | LB: 1.1070 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.421/SR1: 0.408 | LR: 5.00e-04 |
| [2026-04-26 00:34:17] Epoch 1 | Step 1130 | Loss: 0.3548 | LM: 0.3529 | LB: 1.1069 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.421/SR1: 0.408 | LR: 5.00e-04 |
| [2026-04-26 00:34:24] Epoch 1 | Step 1140 | Loss: 0.3551 | LM: 0.3531 | LB: 1.1067 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.421/SR1: 0.408 | LR: 5.00e-04 |
| [2026-04-26 00:34:31] Epoch 1 | Step 1150 | Loss: 0.3549 | LM: 0.3527 | LB: 1.1065 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.420/SR1: 0.408 | LR: 5.00e-04 |
| [2026-04-26 00:34:38] Epoch 1 | Step 1160 | Loss: 0.3555 | LM: 0.3532 | LB: 1.1064 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.420/SR1: 0.408 | LR: 5.00e-04 |
| [2026-04-26 00:34:46] Epoch 1 | Step 1170 | Loss: 0.3560 | LM: 0.3530 | LB: 1.1062 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.420/SR1: 0.408 | LR: 5.00e-04 |
| [2026-04-26 00:34:53] Epoch 1 | Step 1180 | Loss: 0.3562 | LM: 0.3534 | LB: 1.1059 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.420/SR1: 0.407 | LR: 5.00e-04 |
| [2026-04-26 00:35:00] Epoch 1 | Step 1190 | Loss: 0.3565 | LM: 0.3538 | LB: 1.1057 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.420/SR1: 0.407 | LR: 5.00e-04 |
| [2026-04-26 00:35:07] Epoch 1 | Step 1200 | Loss: 0.3566 | LM: 0.3535 | LB: 1.1055 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.419/SR1: 0.407 | LR: 5.00e-04 |
| [2026-04-26 00:35:14] Epoch 1 | Step 1210 | Loss: 0.3568 | LM: 0.3542 | LB: 1.1054 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.419/SR1: 0.407 | LR: 5.00e-04 |
| [2026-04-26 00:35:21] Epoch 1 | Step 1220 | Loss: 0.3566 | LM: 0.3534 | LB: 1.1052 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.419/SR1: 0.407 | LR: 5.00e-04 |
| [2026-04-26 00:35:28] Epoch 1 | Step 1230 | Loss: 0.3570 | LM: 0.3542 | LB: 1.1049 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.419/SR1: 0.406 | LR: 5.00e-04 |
| [2026-04-26 00:35:35] Epoch 1 | Step 1240 | Loss: 0.3574 | LM: 0.3545 | LB: 1.1047 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.418/SR1: 0.406 | LR: 5.00e-04 |
| [2026-04-26 00:35:43] Epoch 1 | Step 1250 | Loss: 0.3574 | LM: 0.3550 | LB: 1.1045 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.418/SR1: 0.406 | LR: 5.00e-04 |
| [2026-04-26 00:35:50] Epoch 1 | Step 1260 | Loss: 0.3574 | LM: 0.3551 | LB: 1.1043 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.418/SR1: 0.406 | LR: 5.00e-04 |
| [2026-04-26 00:35:57] Epoch 1 | Step 1270 | Loss: 0.3573 | LM: 0.3548 | LB: 1.1042 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.351 | HR1: 0.418/SR1: 0.406 | LR: 5.00e-04 |
| [2026-04-26 00:36:04] Epoch 1 | Step 1280 | Loss: 0.3575 | LM: 0.3547 | LB: 1.1041 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.350 | HR1: 0.418/SR1: 0.406 | LR: 5.00e-04 |
| [2026-04-26 00:36:11] Epoch 1 | Step 1290 | Loss: 0.3578 | LM: 0.3551 | LB: 1.1040 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.350 | HR1: 0.418/SR1: 0.406 | LR: 5.00e-04 |
| [2026-04-26 00:36:18] Epoch 1 | Step 1300 | Loss: 0.3578 | LM: 0.3553 | LB: 1.1040 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.350 | HR1: 0.418/SR1: 0.406 | LR: 5.00e-04 |
| [2026-04-26 00:36:25] Epoch 1 | Step 1310 | Loss: 0.3580 | LM: 0.3551 | LB: 1.1038 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.350 | HR1: 0.417/SR1: 0.405 | LR: 5.00e-04 |
| [2026-04-26 00:36:33] Epoch 1 | Step 1320 | Loss: 0.3584 | LM: 0.3553 | LB: 1.1036 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.350 | HR1: 0.417/SR1: 0.405 | LR: 5.00e-04 |
| [2026-04-26 00:36:40] Epoch 1 | Step 1330 | Loss: 0.3585 | LM: 0.3553 | LB: 1.1034 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.350 | HR1: 0.417/SR1: 0.405 | LR: 5.00e-04 |
| [2026-04-26 00:36:47] Epoch 1 | Step 1340 | Loss: 0.3587 | LM: 0.3555 | LB: 1.1032 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.350 | HR1: 0.417/SR1: 0.405 | LR: 5.00e-04 |
| [2026-04-26 00:36:54] Epoch 1 | Step 1350 | Loss: 0.3590 | LM: 0.3562 | LB: 1.1033 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.350 | HR1: 0.417/SR1: 0.405 | LR: 5.00e-04 |
| [2026-04-26 00:37:01] Epoch 1 | Step 1360 | Loss: 0.3592 | LM: 0.3559 | LB: 1.1031 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.350 | HR1: 0.417/SR1: 0.405 | LR: 5.00e-04 |
| [2026-04-26 00:37:08] Epoch 1 | Step 1370 | Loss: 0.3593 | LM: 0.3559 | LB: 1.1030 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.350 | HR1: 0.416/SR1: 0.405 | LR: 5.00e-04 |
| [2026-04-26 00:37:15] Epoch 1 | Step 1380 | Loss: 0.3598 | LM: 0.3559 | LB: 1.1028 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.350 | HR1: 0.416/SR1: 0.405 | LR: 5.00e-04 |
| [2026-04-26 00:37:22] Epoch 1 | Step 1390 | Loss: 0.3605 | LM: 0.3565 | LB: 1.1025 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.350 | HR1: 0.416/SR1: 0.404 | LR: 5.00e-04 |
| [2026-04-26 00:37:30] Epoch 1 | Step 1400 | Loss: 0.3606 | LM: 0.3563 | LB: 1.1023 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.350 | HR1: 0.416/SR1: 0.404 | LR: 5.00e-04 |
| [2026-04-26 00:37:37] Epoch 1 | Step 1410 | Loss: 0.3605 | LM: 0.3554 | LB: 1.1021 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.350 | HR1: 0.416/SR1: 0.404 | LR: 5.00e-04 |
| [2026-04-26 00:37:44] Epoch 1 | Step 1420 | Loss: 0.3607 | LM: 0.3556 | LB: 1.1020 | CL0: 2.8 | CL1: 2.4 | HR0: 0.357/SR0: 0.349 | HR1: 0.416/SR1: 0.404 | LR: 5.00e-04 |
| [2026-04-26 00:37:51] Epoch 1 | Step 1430 | Loss: 0.3608 | LM: 0.3559 | LB: 1.1019 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.349 | HR1: 0.415/SR1: 0.404 | LR: 5.00e-04 |
| [2026-04-26 00:37:58] Epoch 1 | Step 1440 | Loss: 0.3608 | LM: 0.3559 | LB: 1.1017 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.349 | HR1: 0.415/SR1: 0.404 | LR: 5.00e-04 |
| [2026-04-26 00:38:05] Epoch 1 | Step 1450 | Loss: 0.3609 | LM: 0.3557 | LB: 1.1016 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.349 | HR1: 0.415/SR1: 0.404 | LR: 5.00e-04 |
| [2026-04-26 00:38:12] Epoch 1 | Step 1460 | Loss: 0.3608 | LM: 0.3556 | LB: 1.1015 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.349 | HR1: 0.415/SR1: 0.404 | LR: 5.00e-04 |
| [2026-04-26 00:38:20] Epoch 1 | Step 1470 | Loss: 0.3612 | LM: 0.3561 | LB: 1.1015 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.349 | HR1: 0.415/SR1: 0.403 | LR: 5.00e-04 |
| [2026-04-26 00:38:27] Epoch 1 | Step 1480 | Loss: 0.3612 | LM: 0.3557 | LB: 1.1012 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.349 | HR1: 0.415/SR1: 0.403 | LR: 5.00e-04 |
| [2026-04-26 00:38:34] Epoch 1 | Step 1490 | Loss: 0.3614 | LM: 0.3560 | LB: 1.1012 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.349 | HR1: 0.415/SR1: 0.403 | LR: 5.00e-04 |
| [2026-04-26 00:38:41] Epoch 1 | Step 1500 | Loss: 0.3616 | LM: 0.3562 | LB: 1.1012 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.349 | HR1: 0.415/SR1: 0.403 | LR: 5.00e-04 |
| [2026-04-26 00:38:48] Epoch 1 | Step 1510 | Loss: 0.3618 | LM: 0.3566 | LB: 1.1014 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.349 | HR1: 0.415/SR1: 0.404 | LR: 5.00e-04 |
| [2026-04-26 00:38:55] Epoch 1 | Step 1520 | Loss: 0.3620 | LM: 0.3565 | LB: 1.1015 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.349 | HR1: 0.415/SR1: 0.404 | LR: 5.00e-04 |
| [2026-04-26 00:39:02] Epoch 1 | Step 1530 | Loss: 0.3621 | LM: 0.3564 | LB: 1.1015 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.349 | HR1: 0.415/SR1: 0.404 | LR: 5.00e-04 |
| [2026-04-26 00:39:09] Epoch 1 | Step 1540 | Loss: 0.3624 | LM: 0.3572 | LB: 1.1017 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.349 | HR1: 0.415/SR1: 0.404 | LR: 5.00e-04 |
| [2026-04-26 00:39:16] Epoch 1 | Step 1550 | Loss: 0.3626 | LM: 0.3572 | LB: 1.1016 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.349 | HR1: 0.415/SR1: 0.404 | LR: 5.00e-04 |
| [2026-04-26 00:39:23] Epoch 1 | Step 1560 | Loss: 0.3626 | LM: 0.3571 | LB: 1.1015 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.349 | HR1: 0.415/SR1: 0.404 | LR: 5.00e-04 |
| [2026-04-26 00:39:30] Epoch 1 | Step 1570 | Loss: 0.3629 | LM: 0.3575 | LB: 1.1014 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.349 | HR1: 0.415/SR1: 0.404 | LR: 5.00e-04 |
| [2026-04-26 00:39:37] Epoch 1 | Step 1580 | Loss: 0.3630 | LM: 0.3579 | LB: 1.1014 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.415/SR1: 0.404 | LR: 5.00e-04 |
| [2026-04-26 00:39:45] Epoch 1 | Step 1590 | Loss: 0.3632 | LM: 0.3588 | LB: 1.1014 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.415/SR1: 0.404 | LR: 5.00e-04 |
| [2026-04-26 00:39:52] Epoch 1 | Step 1600 | Loss: 0.3633 | LM: 0.3588 | LB: 1.1012 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.415/SR1: 0.403 | LR: 5.00e-04 |
| [2026-04-26 00:39:59] Epoch 1 | Step 1610 | Loss: 0.3632 | LM: 0.3585 | LB: 1.1012 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.415/SR1: 0.403 | LR: 5.00e-04 |
| [2026-04-26 00:40:06] Epoch 1 | Step 1620 | Loss: 0.3631 | LM: 0.3584 | LB: 1.1011 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.415/SR1: 0.403 | LR: 5.00e-04 |
| [2026-04-26 00:40:13] Epoch 1 | Step 1630 | Loss: 0.3634 | LM: 0.3585 | LB: 1.1009 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.414/SR1: 0.403 | LR: 5.00e-04 |
| [2026-04-26 00:40:20] Epoch 1 | Step 1640 | Loss: 0.3634 | LM: 0.3587 | LB: 1.1007 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.414/SR1: 0.403 | LR: 5.00e-04 |
| [2026-04-26 00:40:27] Epoch 1 | Step 1650 | Loss: 0.3633 | LM: 0.3589 | LB: 1.1007 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.414/SR1: 0.403 | LR: 5.00e-04 |
| [2026-04-26 00:40:34] Epoch 1 | Step 1660 | Loss: 0.3633 | LM: 0.3583 | LB: 1.1008 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.415/SR1: 0.403 | LR: 5.00e-04 |
| [2026-04-26 00:40:42] Epoch 1 | Step 1670 | Loss: 0.3636 | LM: 0.3586 | LB: 1.1009 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.415/SR1: 0.403 | LR: 5.00e-04 |
| [2026-04-26 00:40:49] Epoch 1 | Step 1680 | Loss: 0.3638 | LM: 0.3585 | LB: 1.1010 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.415/SR1: 0.403 | LR: 5.00e-04 |
| [2026-04-26 00:40:56] Epoch 1 | Step 1690 | Loss: 0.3638 | LM: 0.3582 | LB: 1.1010 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.415/SR1: 0.403 | LR: 5.00e-04 |
| [2026-04-26 00:41:03] Epoch 1 | Step 1700 | Loss: 0.3635 | LM: 0.3578 | LB: 1.1009 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.415/SR1: 0.403 | LR: 5.00e-04 |
| [2026-04-26 00:41:10] Epoch 1 | Step 1710 | Loss: 0.3637 | LM: 0.3573 | LB: 1.1007 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.415/SR1: 0.403 | LR: 5.00e-04 |
| [2026-04-26 00:41:17] Epoch 1 | Step 1720 | Loss: 0.3637 | LM: 0.3574 | LB: 1.1005 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.414/SR1: 0.403 | LR: 5.00e-04 |
| [2026-04-26 00:41:24] Epoch 1 | Step 1730 | Loss: 0.3637 | LM: 0.3576 | LB: 1.1004 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.414/SR1: 0.403 | LR: 5.00e-04 |
| [2026-04-26 00:41:31] Epoch 1 | Step 1740 | Loss: 0.3639 | LM: 0.3579 | LB: 1.1002 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.414/SR1: 0.402 | LR: 5.00e-04 |
| [2026-04-26 00:41:38] Epoch 1 | Step 1750 | Loss: 0.3642 | LM: 0.3583 | LB: 1.1001 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.414/SR1: 0.402 | LR: 5.00e-04 |
| [2026-04-26 00:41:46] Epoch 1 | Step 1760 | Loss: 0.3643 | LM: 0.3584 | LB: 1.0998 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.413/SR1: 0.402 | LR: 5.00e-04 |
| [2026-04-26 00:41:53] Epoch 1 | Step 1770 | Loss: 0.3645 | LM: 0.3586 | LB: 1.0996 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.413/SR1: 0.402 | LR: 5.00e-04 |
| [2026-04-26 00:42:00] Epoch 1 | Step 1780 | Loss: 0.3646 | LM: 0.3585 | LB: 1.0995 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.413/SR1: 0.402 | LR: 5.00e-04 |
| [2026-04-26 00:42:07] Epoch 1 | Step 1790 | Loss: 0.3649 | LM: 0.3586 | LB: 1.0993 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.413/SR1: 0.401 | LR: 5.00e-04 |
| [2026-04-26 00:42:14] Epoch 1 | Step 1800 | Loss: 0.3650 | LM: 0.3587 | LB: 1.0991 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.348 | HR1: 0.413/SR1: 0.401 | LR: 5.00e-04 |
| [2026-04-26 00:42:21] Epoch 1 | Step 1810 | Loss: 0.3651 | LM: 0.3589 | LB: 1.0989 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.347 | HR1: 0.412/SR1: 0.401 | LR: 5.00e-04 |
| [2026-04-26 00:42:28] Epoch 1 | Step 1820 | Loss: 0.3653 | LM: 0.3589 | LB: 1.0988 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.347 | HR1: 0.412/SR1: 0.401 | LR: 5.00e-04 |
| [2026-04-26 00:42:35] Epoch 1 | Step 1830 | Loss: 0.3655 | LM: 0.3599 | LB: 1.0986 | CL0: 2.8 | CL1: 2.4 | HR0: 0.356/SR0: 0.347 | HR1: 0.412/SR1: 0.401 | LR: 5.00e-04 |
| [2026-04-26 00:42:42] Epoch 1 | Step 1840 | Loss: 0.3657 | LM: 0.3602 | LB: 1.0984 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.412/SR1: 0.400 | LR: 5.00e-04 |
| [2026-04-26 00:42:49] Epoch 1 | Step 1850 | Loss: 0.3656 | LM: 0.3600 | LB: 1.0983 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.412/SR1: 0.400 | LR: 5.00e-04 |
| [2026-04-26 00:42:56] Epoch 1 | Step 1860 | Loss: 0.3659 | LM: 0.3600 | LB: 1.0982 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.411/SR1: 0.400 | LR: 5.00e-04 |
| [2026-04-26 00:43:04] Epoch 1 | Step 1870 | Loss: 0.3660 | LM: 0.3598 | LB: 1.0982 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.411/SR1: 0.400 | LR: 5.00e-04 |
| [2026-04-26 00:43:11] Epoch 1 | Step 1880 | Loss: 0.3660 | LM: 0.3599 | LB: 1.0980 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.411/SR1: 0.400 | LR: 5.00e-04 |
| [2026-04-26 00:43:18] Epoch 1 | Step 1890 | Loss: 0.3662 | LM: 0.3599 | LB: 1.0978 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.411/SR1: 0.400 | LR: 5.00e-04 |
| [2026-04-26 00:43:25] Epoch 1 | Step 1900 | Loss: 0.3662 | LM: 0.3600 | LB: 1.0976 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.411/SR1: 0.399 | LR: 5.00e-04 |
| [2026-04-26 00:43:32] Epoch 1 | Step 1910 | Loss: 0.3664 | LM: 0.3603 | LB: 1.0975 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.411/SR1: 0.399 | LR: 5.00e-04 |
| [2026-04-26 00:43:39] Epoch 1 | Step 1920 | Loss: 0.3666 | LM: 0.3601 | LB: 1.0973 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.411/SR1: 0.399 | LR: 5.00e-04 |
| [2026-04-26 00:43:46] Epoch 1 | Step 1930 | Loss: 0.3666 | LM: 0.3601 | LB: 1.0972 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.410/SR1: 0.399 | LR: 5.00e-04 |
| [2026-04-26 00:43:53] Epoch 1 | Step 1940 | Loss: 0.3665 | LM: 0.3603 | LB: 1.0971 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.410/SR1: 0.399 | LR: 5.00e-04 |
| [2026-04-26 00:44:01] Epoch 1 | Step 1950 | Loss: 0.3665 | LM: 0.3604 | LB: 1.0969 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.410/SR1: 0.399 | LR: 5.00e-04 |
| [2026-04-26 00:44:08] Epoch 1 | Step 1960 | Loss: 0.3667 | LM: 0.3608 | LB: 1.0968 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.410/SR1: 0.399 | LR: 5.00e-04 |
| [2026-04-26 00:44:15] Epoch 1 | Step 1970 | Loss: 0.3669 | LM: 0.3612 | LB: 1.0966 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.410/SR1: 0.398 | LR: 5.00e-04 |
| [2026-04-26 00:44:22] Epoch 1 | Step 1980 | Loss: 0.3671 | LM: 0.3613 | LB: 1.0965 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.410/SR1: 0.398 | LR: 5.00e-04 |
| [2026-04-26 00:44:29] Epoch 1 | Step 1990 | Loss: 0.3672 | LM: 0.3616 | LB: 1.0963 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.409/SR1: 0.398 | LR: 5.00e-04 |
| [2026-04-26 00:44:36] Epoch 1 | Step 2000 | Loss: 0.3673 | LM: 0.3616 | LB: 1.0962 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.409/SR1: 0.398 | LR: 5.00e-04 |
| [2026-04-26 00:44:37] Validation | Batch 10/42 | Loss: 0.3763 | LM_LOSS: 0.3657 | LB_LOSS: 1.0613 |
| [2026-04-26 00:44:38] Validation | Batch 20/42 | Loss: 0.3979 | LM_LOSS: 0.3872 | LB_LOSS: 1.0651 |
| [2026-04-26 00:44:39] Validation | Batch 30/42 | Loss: 0.3903 | LM_LOSS: 0.3797 | LB_LOSS: 1.0634 |
| [2026-04-26 00:44:40] Validation | Batch 40/42 | Loss: 0.3950 | LM_LOSS: 0.3843 | LB_LOSS: 1.0631 |
| [2026-04-26 00:44:41] Validation | Batch 42/42 | Loss: 0.3958 | LM_LOSS: 0.3852 | LB_LOSS: 1.0633 |
| [2026-04-26 00:44:41] Validation | Loss: 0.3958 | LM_LOSS: 0.3852 | LB_LOSS: 1.0633 | PPL: 1.46 | Time: 4.51s |
| [2026-04-26 00:44:43] New best model saved! Val loss: 0.3958 |
| [2026-04-26 00:44:50] Epoch 1 | Step 2010 | Loss: 0.3675 | LM: 0.3620 | LB: 1.0961 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.409/SR1: 0.398 | LR: 5.00e-04 |
| [2026-04-26 00:44:57] Epoch 1 | Step 2020 | Loss: 0.3676 | LM: 0.3621 | LB: 1.0960 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.409/SR1: 0.398 | LR: 5.00e-04 |
| [2026-04-26 00:45:05] Epoch 1 | Step 2030 | Loss: 0.3677 | LM: 0.3621 | LB: 1.0959 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.347 | HR1: 0.409/SR1: 0.398 | LR: 5.00e-04 |
| [2026-04-26 00:45:12] Epoch 1 | Step 2040 | Loss: 0.3678 | LM: 0.3620 | LB: 1.0958 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.346 | HR1: 0.409/SR1: 0.398 | LR: 5.00e-04 |
| [2026-04-26 00:45:19] Epoch 1 | Step 2050 | Loss: 0.3678 | LM: 0.3619 | LB: 1.0956 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.346 | HR1: 0.409/SR1: 0.397 | LR: 5.00e-04 |
| [2026-04-26 00:45:26] Epoch 1 | Step 2060 | Loss: 0.3679 | LM: 0.3623 | LB: 1.0955 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.346 | HR1: 0.409/SR1: 0.397 | LR: 5.00e-04 |
| [2026-04-26 00:45:33] Epoch 1 | Step 2070 | Loss: 0.3677 | LM: 0.3618 | LB: 1.0954 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.346 | HR1: 0.408/SR1: 0.397 | LR: 5.00e-04 |
| [2026-04-26 00:45:40] Epoch 1 | Step 2080 | Loss: 0.3676 | LM: 0.3618 | LB: 1.0953 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.346 | HR1: 0.408/SR1: 0.397 | LR: 5.00e-04 |
| [2026-04-26 00:45:47] Epoch 1 | Step 2090 | Loss: 0.3677 | LM: 0.3619 | LB: 1.0952 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.346 | HR1: 0.408/SR1: 0.397 | LR: 5.00e-04 |
| [2026-04-26 00:45:54] Epoch 1 | Step 2100 | Loss: 0.3678 | LM: 0.3617 | LB: 1.0950 | CL0: 2.8 | CL1: 2.5 | HR0: 0.356/SR0: 0.346 | HR1: 0.408/SR1: 0.397 | LR: 5.00e-04 |
| [2026-04-26 00:46:01] Epoch 1 | Step 2110 | Loss: 0.3680 | LM: 0.3617 | LB: 1.0949 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.346 | HR1: 0.408/SR1: 0.397 | LR: 5.00e-04 |
| [2026-04-26 00:46:08] Epoch 1 | Step 2120 | Loss: 0.3679 | LM: 0.3621 | LB: 1.0949 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.346 | HR1: 0.408/SR1: 0.397 | LR: 5.00e-04 |
| [2026-04-26 00:46:16] Epoch 1 | Step 2130 | Loss: 0.3680 | LM: 0.3626 | LB: 1.0949 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.346 | HR1: 0.408/SR1: 0.397 | LR: 5.00e-04 |
| [2026-04-26 00:46:23] Epoch 1 | Step 2140 | Loss: 0.3679 | LM: 0.3632 | LB: 1.0948 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.346 | HR1: 0.408/SR1: 0.397 | LR: 5.00e-04 |
| [2026-04-26 00:46:30] Epoch 1 | Step 2150 | Loss: 0.3680 | LM: 0.3631 | LB: 1.0947 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.346 | HR1: 0.408/SR1: 0.397 | LR: 5.00e-04 |
| [2026-04-26 00:46:37] Epoch 1 | Step 2160 | Loss: 0.3681 | LM: 0.3632 | LB: 1.0946 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.346 | HR1: 0.408/SR1: 0.396 | LR: 5.00e-04 |
| [2026-04-26 00:46:44] Epoch 1 | Step 2170 | Loss: 0.3681 | LM: 0.3630 | LB: 1.0945 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.346 | HR1: 0.408/SR1: 0.396 | LR: 5.00e-04 |
| [2026-04-26 00:46:51] Epoch 1 | Step 2180 | Loss: 0.3681 | LM: 0.3631 | LB: 1.0944 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.346 | HR1: 0.408/SR1: 0.396 | LR: 5.00e-04 |
| [2026-04-26 00:46:58] Epoch 1 | Step 2190 | Loss: 0.3681 | LM: 0.3629 | LB: 1.0944 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.346 | HR1: 0.408/SR1: 0.396 | LR: 5.00e-04 |
| [2026-04-26 00:47:05] Epoch 1 | Step 2200 | Loss: 0.3682 | LM: 0.3631 | LB: 1.0943 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.346 | HR1: 0.407/SR1: 0.396 | LR: 5.00e-04 |
| [2026-04-26 00:47:12] Epoch 1 | Step 2210 | Loss: 0.3684 | LM: 0.3635 | LB: 1.0942 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.346 | HR1: 0.407/SR1: 0.396 | LR: 5.00e-04 |
| [2026-04-26 00:47:19] Epoch 1 | Step 2220 | Loss: 0.3687 | LM: 0.3638 | LB: 1.0941 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.346 | HR1: 0.407/SR1: 0.396 | LR: 5.00e-04 |
| [2026-04-26 00:47:27] Epoch 1 | Step 2230 | Loss: 0.3689 | LM: 0.3638 | LB: 1.0940 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.346 | HR1: 0.407/SR1: 0.396 | LR: 5.00e-04 |
| [2026-04-26 00:47:34] Epoch 1 | Step 2240 | Loss: 0.3691 | LM: 0.3636 | LB: 1.0940 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.346 | HR1: 0.407/SR1: 0.396 | LR: 5.00e-04 |
| [2026-04-26 00:47:41] Epoch 1 | Step 2250 | Loss: 0.3693 | LM: 0.3638 | LB: 1.0939 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.407/SR1: 0.396 | LR: 5.00e-04 |
| [2026-04-26 00:47:48] Epoch 1 | Step 2260 | Loss: 0.3693 | LM: 0.3635 | LB: 1.0938 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.407/SR1: 0.396 | LR: 5.00e-04 |
| [2026-04-26 00:47:55] Epoch 1 | Step 2270 | Loss: 0.3694 | LM: 0.3640 | LB: 1.0938 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.407/SR1: 0.396 | LR: 5.00e-04 |
| [2026-04-26 00:48:02] Epoch 1 | Step 2280 | Loss: 0.3695 | LM: 0.3641 | LB: 1.0937 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.407/SR1: 0.396 | LR: 5.00e-04 |
| [2026-04-26 00:48:09] Epoch 1 | Step 2290 | Loss: 0.3699 | LM: 0.3644 | LB: 1.0935 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.407/SR1: 0.395 | LR: 5.00e-04 |
| [2026-04-26 00:48:16] Epoch 1 | Step 2300 | Loss: 0.3699 | LM: 0.3641 | LB: 1.0934 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.407/SR1: 0.395 | LR: 5.00e-04 |
| [2026-04-26 00:48:23] Epoch 1 | Step 2310 | Loss: 0.3699 | LM: 0.3642 | LB: 1.0933 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.407/SR1: 0.395 | LR: 5.00e-04 |
| [2026-04-26 00:48:30] Epoch 1 | Step 2320 | Loss: 0.3701 | LM: 0.3643 | LB: 1.0933 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.407/SR1: 0.395 | LR: 5.00e-04 |
| [2026-04-26 00:48:37] Epoch 1 | Step 2330 | Loss: 0.3701 | LM: 0.3645 | LB: 1.0932 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.406/SR1: 0.395 | LR: 5.00e-04 |
| [2026-04-26 00:48:45] Epoch 1 | Step 2340 | Loss: 0.3702 | LM: 0.3649 | LB: 1.0931 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.406/SR1: 0.395 | LR: 5.00e-04 |
| [2026-04-26 00:48:52] Epoch 1 | Step 2350 | Loss: 0.3702 | LM: 0.3651 | LB: 1.0930 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.406/SR1: 0.395 | LR: 5.00e-04 |
| [2026-04-26 00:48:59] Epoch 1 | Step 2360 | Loss: 0.3703 | LM: 0.3652 | LB: 1.0929 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.406/SR1: 0.395 | LR: 5.00e-04 |
| [2026-04-26 00:49:06] Epoch 1 | Step 2370 | Loss: 0.3704 | LM: 0.3652 | LB: 1.0928 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.406/SR1: 0.395 | LR: 5.00e-04 |
| [2026-04-26 00:49:13] Epoch 1 | Step 2380 | Loss: 0.3703 | LM: 0.3651 | LB: 1.0927 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.406/SR1: 0.395 | LR: 5.00e-04 |
| [2026-04-26 00:49:20] Epoch 1 | Step 2390 | Loss: 0.3705 | LM: 0.3652 | LB: 1.0926 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.406/SR1: 0.395 | LR: 5.00e-04 |
| [2026-04-26 00:49:27] Epoch 1 | Step 2400 | Loss: 0.3706 | LM: 0.3656 | LB: 1.0926 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.406/SR1: 0.394 | LR: 5.00e-04 |
| [2026-04-26 00:49:34] Epoch 1 | Step 2410 | Loss: 0.3708 | LM: 0.3662 | LB: 1.0925 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.406/SR1: 0.394 | LR: 5.00e-04 |
| [2026-04-26 00:49:41] Epoch 1 | Step 2420 | Loss: 0.3710 | LM: 0.3660 | LB: 1.0924 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.405/SR1: 0.394 | LR: 5.00e-04 |
| [2026-04-26 00:49:49] Epoch 1 | Step 2430 | Loss: 0.3710 | LM: 0.3661 | LB: 1.0923 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.405/SR1: 0.394 | LR: 5.00e-04 |
| [2026-04-26 00:49:56] Epoch 1 | Step 2440 | Loss: 0.3710 | LM: 0.3661 | LB: 1.0922 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.405/SR1: 0.394 | LR: 5.00e-04 |
| [2026-04-26 00:50:03] Epoch 1 | Step 2450 | Loss: 0.3710 | LM: 0.3661 | LB: 1.0921 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.405/SR1: 0.394 | LR: 5.00e-04 |
| [2026-04-26 00:50:10] Epoch 1 | Step 2460 | Loss: 0.3710 | LM: 0.3661 | LB: 1.0920 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.405/SR1: 0.394 | LR: 5.00e-04 |
| [2026-04-26 00:50:17] Epoch 1 | Step 2470 | Loss: 0.3711 | LM: 0.3660 | LB: 1.0919 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.405/SR1: 0.394 | LR: 5.00e-04 |
| [2026-04-26 00:50:24] Epoch 1 | Step 2480 | Loss: 0.3712 | LM: 0.3659 | LB: 1.0918 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.405/SR1: 0.394 | LR: 5.00e-04 |
| [2026-04-26 00:50:31] Epoch 1 | Step 2490 | Loss: 0.3711 | LM: 0.3662 | LB: 1.0917 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.405/SR1: 0.394 | LR: 5.00e-04 |
| [2026-04-26 00:50:39] Epoch 1 | Step 2500 | Loss: 0.3711 | LM: 0.3663 | LB: 1.0916 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.405/SR1: 0.393 | LR: 5.00e-04 |
| [2026-04-26 00:50:46] Epoch 1 | Step 2510 | Loss: 0.3712 | LM: 0.3666 | LB: 1.0916 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.405/SR1: 0.393 | LR: 5.00e-04 |
| [2026-04-26 00:50:53] Epoch 1 | Step 2520 | Loss: 0.3709 | LM: 0.3662 | LB: 1.0915 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.404/SR1: 0.393 | LR: 5.00e-04 |
| [2026-04-26 00:51:00] Epoch 1 | Step 2530 | Loss: 0.3709 | LM: 0.3663 | LB: 1.0915 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.404/SR1: 0.393 | LR: 5.00e-04 |
| [2026-04-26 00:51:07] Epoch 1 | Step 2540 | Loss: 0.3709 | LM: 0.3662 | LB: 1.0914 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.404/SR1: 0.393 | LR: 5.00e-04 |
| [2026-04-26 00:51:14] Epoch 1 | Step 2550 | Loss: 0.3707 | LM: 0.3656 | LB: 1.0913 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.404/SR1: 0.393 | LR: 5.00e-04 |
| [2026-04-26 00:51:21] Epoch 1 | Step 2560 | Loss: 0.3707 | LM: 0.3658 | LB: 1.0913 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.404/SR1: 0.393 | LR: 5.00e-04 |
| [2026-04-26 00:51:28] Epoch 1 | Step 2570 | Loss: 0.3708 | LM: 0.3661 | LB: 1.0912 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.404/SR1: 0.393 | LR: 5.00e-04 |
| [2026-04-26 00:51:35] Epoch 1 | Step 2580 | Loss: 0.3710 | LM: 0.3662 | LB: 1.0911 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.404/SR1: 0.393 | LR: 5.00e-04 |
| [2026-04-26 00:51:43] Epoch 1 | Step 2590 | Loss: 0.3711 | LM: 0.3660 | LB: 1.0910 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.404/SR1: 0.393 | LR: 5.00e-04 |
| [2026-04-26 00:51:50] Epoch 1 | Step 2600 | Loss: 0.3712 | LM: 0.3663 | LB: 1.0909 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.404/SR1: 0.392 | LR: 5.00e-04 |
| [2026-04-26 00:51:57] Epoch 1 | Step 2610 | Loss: 0.3713 | LM: 0.3659 | LB: 1.0909 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.404/SR1: 0.392 | LR: 5.00e-04 |
| [2026-04-26 00:52:04] Epoch 1 | Step 2620 | Loss: 0.3713 | LM: 0.3659 | LB: 1.0908 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.403/SR1: 0.392 | LR: 5.00e-04 |
| [2026-04-26 00:52:11] Epoch 1 | Step 2630 | Loss: 0.3713 | LM: 0.3660 | LB: 1.0907 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.403/SR1: 0.392 | LR: 5.00e-04 |
| [2026-04-26 00:52:18] Epoch 1 | Step 2640 | Loss: 0.3715 | LM: 0.3658 | LB: 1.0906 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.403/SR1: 0.392 | LR: 5.00e-04 |
| [2026-04-26 00:52:25] Epoch 1 | Step 2650 | Loss: 0.3713 | LM: 0.3657 | LB: 1.0906 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.403/SR1: 0.392 | LR: 5.00e-04 |
| [2026-04-26 00:52:32] Epoch 1 | Step 2660 | Loss: 0.3714 | LM: 0.3660 | LB: 1.0905 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.403/SR1: 0.392 | LR: 5.00e-04 |
| [2026-04-26 00:52:39] Epoch 1 | Step 2670 | Loss: 0.3714 | LM: 0.3663 | LB: 1.0904 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.403/SR1: 0.392 | LR: 5.00e-04 |
| [2026-04-26 00:52:46] Epoch 1 | Step 2680 | Loss: 0.3714 | LM: 0.3663 | LB: 1.0903 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.403/SR1: 0.392 | LR: 5.00e-04 |
| [2026-04-26 00:52:53] Epoch 1 | Step 2690 | Loss: 0.3714 | LM: 0.3666 | LB: 1.0902 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.403/SR1: 0.392 | LR: 5.00e-04 |
| [2026-04-26 00:53:01] Epoch 1 | Step 2700 | Loss: 0.3714 | LM: 0.3667 | LB: 1.0901 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.403/SR1: 0.392 | LR: 5.00e-04 |
| [2026-04-26 00:53:08] Epoch 1 | Step 2710 | Loss: 0.3713 | LM: 0.3665 | LB: 1.0900 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.402/SR1: 0.391 | LR: 5.00e-04 |
| [2026-04-26 00:53:15] Epoch 1 | Step 2720 | Loss: 0.3714 | LM: 0.3666 | LB: 1.0899 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.402/SR1: 0.391 | LR: 5.00e-04 |
| [2026-04-26 00:53:22] Epoch 1 | Step 2730 | Loss: 0.3714 | LM: 0.3666 | LB: 1.0898 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.402/SR1: 0.391 | LR: 5.00e-04 |
| [2026-04-26 00:53:29] Epoch 1 | Step 2740 | Loss: 0.3715 | LM: 0.3666 | LB: 1.0897 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.402/SR1: 0.391 | LR: 5.00e-04 |
| [2026-04-26 00:53:36] Epoch 1 | Step 2750 | Loss: 0.3716 | LM: 0.3666 | LB: 1.0895 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.402/SR1: 0.391 | LR: 5.00e-04 |
| [2026-04-26 00:53:43] Epoch 1 | Step 2760 | Loss: 0.3715 | LM: 0.3662 | LB: 1.0894 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.345 | HR1: 0.402/SR1: 0.391 | LR: 5.00e-04 |
| [2026-04-26 00:53:51] Epoch 1 | Step 2770 | Loss: 0.3715 | LM: 0.3663 | LB: 1.0893 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.402/SR1: 0.391 | LR: 5.00e-04 |
| [2026-04-26 00:53:58] Epoch 1 | Step 2780 | Loss: 0.3716 | LM: 0.3660 | LB: 1.0892 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.401/SR1: 0.391 | LR: 5.00e-04 |
| [2026-04-26 00:54:05] Epoch 1 | Step 2790 | Loss: 0.3716 | LM: 0.3662 | LB: 1.0892 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.401/SR1: 0.390 | LR: 5.00e-04 |
| [2026-04-26 00:54:12] Epoch 1 | Step 2800 | Loss: 0.3716 | LM: 0.3663 | LB: 1.0891 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.401/SR1: 0.390 | LR: 5.00e-04 |
| [2026-04-26 00:54:19] Epoch 1 | Step 2810 | Loss: 0.3717 | LM: 0.3663 | LB: 1.0890 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.401/SR1: 0.390 | LR: 5.00e-04 |
| [2026-04-26 00:54:26] Epoch 1 | Step 2820 | Loss: 0.3718 | LM: 0.3666 | LB: 1.0889 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.401/SR1: 0.390 | LR: 5.00e-04 |
| [2026-04-26 00:54:33] Epoch 1 | Step 2830 | Loss: 0.3718 | LM: 0.3666 | LB: 1.0888 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.401/SR1: 0.390 | LR: 5.00e-04 |
| [2026-04-26 00:54:41] Epoch 1 | Step 2840 | Loss: 0.3722 | LM: 0.3670 | LB: 1.0887 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.401/SR1: 0.390 | LR: 5.00e-04 |
| [2026-04-26 00:54:48] Epoch 1 | Step 2850 | Loss: 0.3723 | LM: 0.3675 | LB: 1.0887 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.401/SR1: 0.390 | LR: 5.00e-04 |
| [2026-04-26 00:54:55] Epoch 1 | Step 2860 | Loss: 0.3724 | LM: 0.3675 | LB: 1.0886 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.401/SR1: 0.390 | LR: 5.00e-04 |
| [2026-04-26 00:55:02] Epoch 1 | Step 2870 | Loss: 0.3724 | LM: 0.3676 | LB: 1.0886 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.401/SR1: 0.390 | LR: 5.00e-04 |
| [2026-04-26 00:55:09] Epoch 1 | Step 2880 | Loss: 0.3724 | LM: 0.3675 | LB: 1.0885 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.400/SR1: 0.390 | LR: 5.00e-04 |
| [2026-04-26 00:55:16] Epoch 1 | Step 2890 | Loss: 0.3724 | LM: 0.3673 | LB: 1.0884 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.400/SR1: 0.390 | LR: 5.00e-04 |
| [2026-04-26 00:55:23] Epoch 1 | Step 2900 | Loss: 0.3723 | LM: 0.3671 | LB: 1.0883 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.400/SR1: 0.389 | LR: 5.00e-04 |
| [2026-04-26 00:55:31] Epoch 1 | Step 2910 | Loss: 0.3724 | LM: 0.3672 | LB: 1.0882 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.400/SR1: 0.389 | LR: 5.00e-04 |
| [2026-04-26 00:55:38] Epoch 1 | Step 2920 | Loss: 0.3725 | LM: 0.3675 | LB: 1.0882 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.400/SR1: 0.389 | LR: 5.00e-04 |
| [2026-04-26 00:55:45] Epoch 1 | Step 2930 | Loss: 0.3724 | LM: 0.3673 | LB: 1.0881 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.400/SR1: 0.389 | LR: 5.00e-04 |
| [2026-04-26 00:55:52] Epoch 1 | Step 2940 | Loss: 0.3723 | LM: 0.3673 | LB: 1.0880 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.400/SR1: 0.389 | LR: 5.00e-04 |
| [2026-04-26 00:55:59] Epoch 1 | Step 2950 | Loss: 0.3725 | LM: 0.3675 | LB: 1.0879 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.400/SR1: 0.389 | LR: 5.00e-04 |
| [2026-04-26 00:56:06] Epoch 1 | Step 2960 | Loss: 0.3726 | LM: 0.3677 | LB: 1.0879 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.400/SR1: 0.389 | LR: 5.00e-04 |
| [2026-04-26 00:56:13] Epoch 1 | Step 2970 | Loss: 0.3727 | LM: 0.3678 | LB: 1.0878 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.400/SR1: 0.389 | LR: 5.00e-04 |
| [2026-04-26 00:56:21] Epoch 1 | Step 2980 | Loss: 0.3726 | LM: 0.3678 | LB: 1.0877 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.399/SR1: 0.389 | LR: 5.00e-04 |
| [2026-04-26 00:56:28] Epoch 1 | Step 2990 | Loss: 0.3728 | LM: 0.3679 | LB: 1.0876 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.399/SR1: 0.389 | LR: 5.00e-04 |
| [2026-04-26 00:56:35] Epoch 1 | Step 3000 | Loss: 0.3728 | LM: 0.3679 | LB: 1.0875 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.399/SR1: 0.389 | LR: 5.00e-04 |
| [2026-04-26 00:56:42] Epoch 1 | Step 3010 | Loss: 0.3728 | LM: 0.3679 | LB: 1.0875 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.399/SR1: 0.389 | LR: 5.00e-04 |
| [2026-04-26 00:56:49] Epoch 1 | Step 3020 | Loss: 0.3727 | LM: 0.3678 | LB: 1.0874 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.399/SR1: 0.389 | LR: 5.00e-04 |
| [2026-04-26 00:56:57] Epoch 1 | Step 3030 | Loss: 0.3727 | LM: 0.3679 | LB: 1.0874 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.399/SR1: 0.389 | LR: 5.00e-04 |
| [2026-04-26 00:57:04] Epoch 1 | Step 3040 | Loss: 0.3726 | LM: 0.3677 | LB: 1.0874 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.399/SR1: 0.389 | LR: 5.00e-04 |
| [2026-04-26 00:57:11] Epoch 1 | Step 3050 | Loss: 0.3726 | LM: 0.3674 | LB: 1.0873 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.399/SR1: 0.389 | LR: 5.00e-04 |
| [2026-04-26 00:57:18] Epoch 1 | Step 3060 | Loss: 0.3727 | LM: 0.3680 | LB: 1.0873 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.399/SR1: 0.389 | LR: 5.00e-04 |
| [2026-04-26 00:57:25] Epoch 1 | Step 3070 | Loss: 0.3726 | LM: 0.3680 | LB: 1.0873 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.399/SR1: 0.389 | LR: 5.00e-04 |
| [2026-04-26 00:57:32] Epoch 1 | Step 3080 | Loss: 0.3726 | LM: 0.3678 | LB: 1.0872 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.399/SR1: 0.389 | LR: 5.00e-04 |
| [2026-04-26 00:57:39] Epoch 1 | Step 3090 | Loss: 0.3725 | LM: 0.3675 | LB: 1.0871 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.399/SR1: 0.388 | LR: 5.00e-04 |
| [2026-04-26 00:57:46] Epoch 1 | Step 3100 | Loss: 0.3725 | LM: 0.3675 | LB: 1.0871 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.399/SR1: 0.388 | LR: 5.00e-04 |
| [2026-04-26 00:57:54] Epoch 1 | Step 3110 | Loss: 0.3724 | LM: 0.3674 | LB: 1.0871 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.399/SR1: 0.388 | LR: 5.00e-04 |
| [2026-04-26 00:58:01] Epoch 1 | Step 3120 | Loss: 0.3727 | LM: 0.3676 | LB: 1.0871 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.399/SR1: 0.388 | LR: 5.00e-04 |
| [2026-04-26 00:58:08] Epoch 1 | Step 3130 | Loss: 0.3727 | LM: 0.3677 | LB: 1.0870 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.399/SR1: 0.388 | LR: 5.00e-04 |
| [2026-04-26 00:58:15] Epoch 1 | Step 3140 | Loss: 0.3728 | LM: 0.3676 | LB: 1.0870 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.399/SR1: 0.388 | LR: 5.00e-04 |
| [2026-04-26 00:58:22] Epoch 1 | Step 3150 | Loss: 0.3730 | LM: 0.3679 | LB: 1.0869 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.399/SR1: 0.388 | LR: 5.00e-04 |
| [2026-04-26 00:58:29] Epoch 1 | Step 3160 | Loss: 0.3730 | LM: 0.3677 | LB: 1.0868 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.399/SR1: 0.388 | LR: 5.00e-04 |
| [2026-04-26 00:58:36] Epoch 1 | Step 3170 | Loss: 0.3731 | LM: 0.3679 | LB: 1.0868 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.398/SR1: 0.388 | LR: 5.00e-04 |
| [2026-04-26 00:58:43] Epoch 1 | Step 3180 | Loss: 0.3731 | LM: 0.3683 | LB: 1.0867 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.398/SR1: 0.388 | LR: 5.00e-04 |
| [2026-04-26 00:58:51] Epoch 1 | Step 3190 | Loss: 0.3730 | LM: 0.3680 | LB: 1.0866 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.398/SR1: 0.388 | LR: 5.00e-04 |
| [2026-04-26 00:58:58] Epoch 1 | Step 3200 | Loss: 0.3730 | LM: 0.3678 | LB: 1.0865 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.398/SR1: 0.388 | LR: 5.00e-04 |
| [2026-04-26 00:59:05] Epoch 1 | Step 3210 | Loss: 0.3730 | LM: 0.3675 | LB: 1.0864 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.398/SR1: 0.388 | LR: 5.00e-04 |
| [2026-04-26 00:59:12] Epoch 1 | Step 3220 | Loss: 0.3729 | LM: 0.3674 | LB: 1.0863 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.344 | HR1: 0.398/SR1: 0.388 | LR: 5.00e-04 |
| [2026-04-26 00:59:19] Epoch 1 | Step 3230 | Loss: 0.3730 | LM: 0.3674 | LB: 1.0862 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.398/SR1: 0.387 | LR: 5.00e-04 |
| [2026-04-26 00:59:26] Epoch 1 | Step 3240 | Loss: 0.3729 | LM: 0.3673 | LB: 1.0862 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.398/SR1: 0.387 | LR: 5.00e-04 |
| [2026-04-26 00:59:33] Epoch 1 | Step 3250 | Loss: 0.3730 | LM: 0.3673 | LB: 1.0861 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.398/SR1: 0.387 | LR: 5.00e-04 |
| [2026-04-26 00:59:40] Epoch 1 | Step 3260 | Loss: 0.3731 | LM: 0.3672 | LB: 1.0860 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.398/SR1: 0.387 | LR: 5.00e-04 |
| [2026-04-26 00:59:48] Epoch 1 | Step 3270 | Loss: 0.3731 | LM: 0.3674 | LB: 1.0860 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.398/SR1: 0.387 | LR: 5.00e-04 |
| [2026-04-26 00:59:55] Epoch 1 | Step 3280 | Loss: 0.3730 | LM: 0.3673 | LB: 1.0859 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.398/SR1: 0.387 | LR: 5.00e-04 |
| [2026-04-26 01:00:02] Epoch 1 | Step 3290 | Loss: 0.3730 | LM: 0.3673 | LB: 1.0859 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.397/SR1: 0.387 | LR: 5.00e-04 |
| [2026-04-26 01:00:09] Epoch 1 | Step 3300 | Loss: 0.3731 | LM: 0.3677 | LB: 1.0859 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.397/SR1: 0.387 | LR: 5.00e-04 |
| [2026-04-26 01:00:16] Epoch 1 | Step 3310 | Loss: 0.3731 | LM: 0.3676 | LB: 1.0858 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.397/SR1: 0.387 | LR: 5.00e-04 |
| [2026-04-26 01:00:23] Epoch 1 | Step 3320 | Loss: 0.3732 | LM: 0.3676 | LB: 1.0857 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.397/SR1: 0.387 | LR: 5.00e-04 |
| [2026-04-26 01:00:31] Epoch 1 | Step 3330 | Loss: 0.3732 | LM: 0.3677 | LB: 1.0856 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.397/SR1: 0.387 | LR: 5.00e-04 |
| [2026-04-26 01:00:38] Epoch 1 | Step 3340 | Loss: 0.3733 | LM: 0.3679 | LB: 1.0856 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.397/SR1: 0.387 | LR: 5.00e-04 |
| [2026-04-26 01:00:45] Epoch 1 | Step 3350 | Loss: 0.3732 | LM: 0.3679 | LB: 1.0856 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.397/SR1: 0.387 | LR: 5.00e-04 |
| [2026-04-26 01:00:52] Epoch 1 | Step 3360 | Loss: 0.3732 | LM: 0.3678 | LB: 1.0854 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.397/SR1: 0.386 | LR: 5.00e-04 |
| [2026-04-26 01:00:59] Epoch 1 | Step 3370 | Loss: 0.3733 | LM: 0.3677 | LB: 1.0854 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.397/SR1: 0.386 | LR: 5.00e-04 |
| [2026-04-26 01:01:06] Epoch 1 | Step 3380 | Loss: 0.3732 | LM: 0.3677 | LB: 1.0854 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.397/SR1: 0.386 | LR: 5.00e-04 |
| [2026-04-26 01:01:14] Epoch 1 | Step 3390 | Loss: 0.3733 | LM: 0.3678 | LB: 1.0853 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.397/SR1: 0.386 | LR: 5.00e-04 |
| [2026-04-26 01:01:21] Epoch 1 | Step 3400 | Loss: 0.3735 | LM: 0.3679 | LB: 1.0852 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.397/SR1: 0.386 | LR: 5.00e-04 |
| [2026-04-26 01:01:28] Epoch 1 | Step 3410 | Loss: 0.3735 | LM: 0.3680 | LB: 1.0852 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.396/SR1: 0.386 | LR: 5.00e-04 |
| [2026-04-26 01:01:35] Epoch 1 | Step 3420 | Loss: 0.3735 | LM: 0.3682 | LB: 1.0851 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.396/SR1: 0.386 | LR: 5.00e-04 |
| [2026-04-26 01:01:42] Epoch 1 | Step 3430 | Loss: 0.3735 | LM: 0.3684 | LB: 1.0850 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.396/SR1: 0.386 | LR: 5.00e-04 |
| [2026-04-26 01:01:49] Epoch 1 | Step 3440 | Loss: 0.3736 | LM: 0.3686 | LB: 1.0850 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.396/SR1: 0.386 | LR: 5.00e-04 |
| [2026-04-26 01:01:56] Epoch 1 | Step 3450 | Loss: 0.3736 | LM: 0.3687 | LB: 1.0849 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.396/SR1: 0.386 | LR: 5.00e-04 |
| [2026-04-26 01:02:03] Epoch 1 | Step 3460 | Loss: 0.3736 | LM: 0.3685 | LB: 1.0849 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.343 | HR1: 0.396/SR1: 0.386 | LR: 5.00e-04 |
| [2026-04-26 01:02:11] Epoch 1 | Step 3470 | Loss: 0.3736 | LM: 0.3684 | LB: 1.0848 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.343 | HR1: 0.396/SR1: 0.386 | LR: 5.00e-04 |
| [2026-04-26 01:02:18] Epoch 1 | Step 3480 | Loss: 0.3736 | LM: 0.3685 | LB: 1.0847 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.343 | HR1: 0.396/SR1: 0.386 | LR: 5.00e-04 |
| [2026-04-26 01:02:25] Epoch 1 | Step 3490 | Loss: 0.3736 | LM: 0.3685 | LB: 1.0846 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.343 | HR1: 0.396/SR1: 0.386 | LR: 5.00e-04 |
| [2026-04-26 01:02:32] Epoch 1 | Step 3500 | Loss: 0.3735 | LM: 0.3684 | LB: 1.0845 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.343 | HR1: 0.396/SR1: 0.386 | LR: 5.00e-04 |
| [2026-04-26 01:02:39] Epoch 1 | Step 3510 | Loss: 0.3736 | LM: 0.3685 | LB: 1.0845 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.343 | HR1: 0.396/SR1: 0.385 | LR: 5.00e-04 |
| [2026-04-26 01:02:46] Epoch 1 | Step 3520 | Loss: 0.3736 | LM: 0.3687 | LB: 1.0844 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.343 | HR1: 0.396/SR1: 0.385 | LR: 5.00e-04 |
| [2026-04-26 01:02:53] Epoch 1 | Step 3530 | Loss: 0.3737 | LM: 0.3686 | LB: 1.0843 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.343 | HR1: 0.396/SR1: 0.385 | LR: 5.00e-04 |
| [2026-04-26 01:03:01] Epoch 1 | Step 3540 | Loss: 0.3737 | LM: 0.3683 | LB: 1.0843 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.343 | HR1: 0.396/SR1: 0.385 | LR: 5.00e-04 |
| [2026-04-26 01:03:08] Epoch 1 | Step 3550 | Loss: 0.3737 | LM: 0.3684 | LB: 1.0842 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.343 | HR1: 0.395/SR1: 0.385 | LR: 5.00e-04 |
| [2026-04-26 01:03:15] Epoch 1 | Step 3560 | Loss: 0.3738 | LM: 0.3686 | LB: 1.0841 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.343 | HR1: 0.395/SR1: 0.385 | LR: 5.00e-04 |
| [2026-04-26 01:03:22] Epoch 1 | Step 3570 | Loss: 0.3738 | LM: 0.3686 | LB: 1.0840 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.343 | HR1: 0.395/SR1: 0.385 | LR: 5.00e-04 |
| [2026-04-26 01:03:29] Epoch 1 | Step 3580 | Loss: 0.3738 | LM: 0.3687 | LB: 1.0839 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.343 | HR1: 0.395/SR1: 0.385 | LR: 5.00e-04 |
| [2026-04-26 01:03:36] Epoch 1 | Step 3590 | Loss: 0.3738 | LM: 0.3687 | LB: 1.0839 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.343 | HR1: 0.395/SR1: 0.385 | LR: 5.00e-04 |
| [2026-04-26 01:03:43] Epoch 1 | Step 3600 | Loss: 0.3738 | LM: 0.3687 | LB: 1.0838 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.343 | HR1: 0.395/SR1: 0.385 | LR: 5.00e-04 |
| [2026-04-26 01:03:50] Epoch 1 | Step 3610 | Loss: 0.3737 | LM: 0.3686 | LB: 1.0837 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.343 | HR1: 0.395/SR1: 0.385 | LR: 5.00e-04 |
| [2026-04-26 01:03:57] Epoch 1 | Step 3620 | Loss: 0.3737 | LM: 0.3683 | LB: 1.0836 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.395/SR1: 0.384 | LR: 5.00e-04 |
| [2026-04-26 01:04:05] Epoch 1 | Step 3630 | Loss: 0.3738 | LM: 0.3685 | LB: 1.0835 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.395/SR1: 0.384 | LR: 5.00e-04 |
| [2026-04-26 01:04:12] Epoch 1 | Step 3640 | Loss: 0.3739 | LM: 0.3687 | LB: 1.0835 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.395/SR1: 0.384 | LR: 5.00e-04 |
| [2026-04-26 01:04:19] Epoch 1 | Step 3650 | Loss: 0.3740 | LM: 0.3690 | LB: 1.0834 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.394/SR1: 0.384 | LR: 5.00e-04 |
| [2026-04-26 01:04:26] Epoch 1 | Step 3660 | Loss: 0.3739 | LM: 0.3690 | LB: 1.0834 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.394/SR1: 0.384 | LR: 5.00e-04 |
| [2026-04-26 01:04:33] Epoch 1 | Step 3670 | Loss: 0.3739 | LM: 0.3687 | LB: 1.0833 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.394/SR1: 0.384 | LR: 5.00e-04 |
| [2026-04-26 01:04:40] Epoch 1 | Step 3680 | Loss: 0.3739 | LM: 0.3688 | LB: 1.0832 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.394/SR1: 0.384 | LR: 5.00e-04 |
| [2026-04-26 01:04:47] Epoch 1 | Step 3690 | Loss: 0.3740 | LM: 0.3690 | LB: 1.0832 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.394/SR1: 0.384 | LR: 5.00e-04 |
| [2026-04-26 01:04:54] Epoch 1 | Step 3700 | Loss: 0.3739 | LM: 0.3689 | LB: 1.0831 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.394/SR1: 0.384 | LR: 5.00e-04 |
| [2026-04-26 01:05:02] Epoch 1 | Step 3710 | Loss: 0.3739 | LM: 0.3689 | LB: 1.0831 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.394/SR1: 0.384 | LR: 5.00e-04 |
| [2026-04-26 01:05:09] Epoch 1 | Step 3720 | Loss: 0.3739 | LM: 0.3691 | LB: 1.0830 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.394/SR1: 0.384 | LR: 5.00e-04 |
| [2026-04-26 01:05:16] Epoch 1 | Step 3730 | Loss: 0.3740 | LM: 0.3690 | LB: 1.0829 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.394/SR1: 0.384 | LR: 5.00e-04 |
| [2026-04-26 01:05:23] Epoch 1 | Step 3740 | Loss: 0.3740 | LM: 0.3689 | LB: 1.0829 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.394/SR1: 0.384 | LR: 5.00e-04 |
| [2026-04-26 01:05:31] Epoch 1 | Step 3750 | Loss: 0.3739 | LM: 0.3687 | LB: 1.0828 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.394/SR1: 0.384 | LR: 5.00e-04 |
| [2026-04-26 01:05:38] Epoch 1 | Step 3760 | Loss: 0.3740 | LM: 0.3688 | LB: 1.0827 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.394/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:05:45] Epoch 1 | Step 3770 | Loss: 0.3740 | LM: 0.3689 | LB: 1.0827 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.394/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:05:52] Epoch 1 | Step 3780 | Loss: 0.3741 | LM: 0.3689 | LB: 1.0826 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.393/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:05:59] Epoch 1 | Step 3790 | Loss: 0.3742 | LM: 0.3690 | LB: 1.0826 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.393/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:06:07] Epoch 1 | Step 3800 | Loss: 0.3743 | LM: 0.3691 | LB: 1.0825 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.393/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:06:14] Epoch 1 | Step 3810 | Loss: 0.3741 | LM: 0.3688 | LB: 1.0825 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.393/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:06:21] Epoch 1 | Step 3820 | Loss: 0.3741 | LM: 0.3687 | LB: 1.0824 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.393/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:06:28] Epoch 1 | Step 3830 | Loss: 0.3741 | LM: 0.3687 | LB: 1.0823 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.393/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:06:35] Epoch 1 | Step 3840 | Loss: 0.3741 | LM: 0.3691 | LB: 1.0822 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.393/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:06:42] Epoch 1 | Step 3850 | Loss: 0.3741 | LM: 0.3690 | LB: 1.0822 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.393/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:06:49] Epoch 1 | Step 3860 | Loss: 0.3741 | LM: 0.3690 | LB: 1.0821 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.393/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:06:56] Epoch 1 | Step 3870 | Loss: 0.3741 | LM: 0.3687 | LB: 1.0820 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.393/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:07:03] Epoch 1 | Step 3880 | Loss: 0.3740 | LM: 0.3685 | LB: 1.0820 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.393/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:07:11] Epoch 1 | Step 3890 | Loss: 0.3740 | LM: 0.3687 | LB: 1.0819 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.393/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:07:18] Epoch 1 | Step 3900 | Loss: 0.3740 | LM: 0.3687 | LB: 1.0819 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.393/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:07:25] Epoch 1 | Step 3910 | Loss: 0.3741 | LM: 0.3687 | LB: 1.0819 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.393/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:07:32] Epoch 1 | Step 3920 | Loss: 0.3742 | LM: 0.3687 | LB: 1.0819 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.393/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:07:39] Epoch 1 | Step 3930 | Loss: 0.3742 | LM: 0.3688 | LB: 1.0818 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.393/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:07:46] Epoch 1 | Step 3940 | Loss: 0.3742 | LM: 0.3687 | LB: 1.0818 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.392/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:07:53] Epoch 1 | Step 3950 | Loss: 0.3741 | LM: 0.3684 | LB: 1.0818 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.392/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:08:00] Epoch 1 | Step 3960 | Loss: 0.3741 | LM: 0.3685 | LB: 1.0817 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.392/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:08:07] Epoch 1 | Step 3970 | Loss: 0.3741 | LM: 0.3684 | LB: 1.0817 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.392/SR1: 0.383 | LR: 5.00e-04 |
| [2026-04-26 01:08:15] Epoch 1 | Step 3980 | Loss: 0.3741 | LM: 0.3684 | LB: 1.0817 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.392/SR1: 0.383 | LR: 4.99e-04 |
| [2026-04-26 01:08:22] Epoch 1 | Step 3990 | Loss: 0.3741 | LM: 0.3687 | LB: 1.0816 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.392/SR1: 0.382 | LR: 4.99e-04 |
| [2026-04-26 01:08:29] Epoch 1 | Step 4000 | Loss: 0.3741 | LM: 0.3686 | LB: 1.0816 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.392/SR1: 0.382 | LR: 4.98e-04 |
| [2026-04-26 01:08:30] Validation | Batch 10/42 | Loss: 0.3711 | LM_LOSS: 0.3604 | LB_LOSS: 1.0699 |
| [2026-04-26 01:08:31] Validation | Batch 20/42 | Loss: 0.3913 | LM_LOSS: 0.3806 | LB_LOSS: 1.0735 |
| [2026-04-26 01:08:32] Validation | Batch 30/42 | Loss: 0.3810 | LM_LOSS: 0.3703 | LB_LOSS: 1.0721 |
| [2026-04-26 01:08:33] Validation | Batch 40/42 | Loss: 0.3872 | LM_LOSS: 0.3765 | LB_LOSS: 1.0715 |
| [2026-04-26 01:08:33] Validation | Batch 42/42 | Loss: 0.3869 | LM_LOSS: 0.3762 | LB_LOSS: 1.0719 |
| [2026-04-26 01:08:33] Validation | Loss: 0.3869 | LM_LOSS: 0.3762 | LB_LOSS: 1.0719 | PPL: 1.45 | Time: 4.60s |
| [2026-04-26 01:08:36] New best model saved! Val loss: 0.3869 |
| [2026-04-26 01:08:43] Epoch 1 | Step 4010 | Loss: 0.3741 | LM: 0.3687 | LB: 1.0816 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.392/SR1: 0.382 | LR: 4.97e-04 |
| [2026-04-26 01:08:51] Epoch 1 | Step 4020 | Loss: 0.3741 | LM: 0.3688 | LB: 1.0815 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.392/SR1: 0.382 | LR: 4.95e-04 |
| [2026-04-26 01:08:58] Epoch 1 | Step 4030 | Loss: 0.3740 | LM: 0.3686 | LB: 1.0815 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.342 | HR1: 0.392/SR1: 0.382 | LR: 4.94e-04 |
| [2026-04-26 01:09:05] Epoch 1 | Step 4040 | Loss: 0.3739 | LM: 0.3686 | LB: 1.0815 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.341 | HR1: 0.392/SR1: 0.382 | LR: 4.92e-04 |
| [2026-04-26 01:09:12] Epoch 1 | Step 4050 | Loss: 0.3739 | LM: 0.3686 | LB: 1.0815 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.341 | HR1: 0.392/SR1: 0.382 | LR: 4.90e-04 |
| [2026-04-26 01:09:19] Epoch 1 | Step 4060 | Loss: 0.3737 | LM: 0.3684 | LB: 1.0814 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.341 | HR1: 0.392/SR1: 0.382 | LR: 4.88e-04 |
| [2026-04-26 01:09:26] Epoch 1 | Step 4070 | Loss: 0.3738 | LM: 0.3685 | LB: 1.0814 | CL0: 2.8 | CL1: 2.6 | HR0: 0.354/SR0: 0.341 | HR1: 0.392/SR1: 0.382 | LR: 4.85e-04 |
| [2026-04-26 01:09:33] Epoch 1 | Step 4080 | Loss: 0.3738 | LM: 0.3686 | LB: 1.0813 | CL0: 2.9 | CL1: 2.6 | HR0: 0.354/SR0: 0.341 | HR1: 0.392/SR1: 0.382 | LR: 4.82e-04 |
| [2026-04-26 01:09:40] Epoch 1 | Step 4090 | Loss: 0.3739 | LM: 0.3686 | LB: 1.0813 | CL0: 2.9 | CL1: 2.6 | HR0: 0.354/SR0: 0.341 | HR1: 0.392/SR1: 0.382 | LR: 4.80e-04 |
| [2026-04-26 01:09:47] Epoch 1 | Step 4100 | Loss: 0.3739 | LM: 0.3687 | LB: 1.0812 | CL0: 2.9 | CL1: 2.6 | HR0: 0.354/SR0: 0.341 | HR1: 0.392/SR1: 0.382 | LR: 4.77e-04 |
| [2026-04-26 01:09:54] Epoch 1 | Step 4110 | Loss: 0.3739 | LM: 0.3687 | LB: 1.0812 | CL0: 2.9 | CL1: 2.6 | HR0: 0.354/SR0: 0.341 | HR1: 0.392/SR1: 0.382 | LR: 4.73e-04 |
| [2026-04-26 01:10:02] Epoch 1 | Step 4120 | Loss: 0.3740 | LM: 0.3689 | LB: 1.0811 | CL0: 2.9 | CL1: 2.6 | HR0: 0.354/SR0: 0.341 | HR1: 0.392/SR1: 0.382 | LR: 4.70e-04 |
| [2026-04-26 01:10:09] Epoch 1 | Step 4130 | Loss: 0.3740 | LM: 0.3686 | LB: 1.0811 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.392/SR1: 0.382 | LR: 4.66e-04 |
| [2026-04-26 01:10:16] Epoch 1 | Step 4140 | Loss: 0.3741 | LM: 0.3687 | LB: 1.0810 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.392/SR1: 0.382 | LR: 4.62e-04 |
| [2026-04-26 01:10:23] Epoch 1 | Step 4150 | Loss: 0.3742 | LM: 0.3689 | LB: 1.0810 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.392/SR1: 0.382 | LR: 4.58e-04 |
| [2026-04-26 01:10:30] Epoch 1 | Step 4160 | Loss: 0.3744 | LM: 0.3692 | LB: 1.0810 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.392/SR1: 0.382 | LR: 4.54e-04 |
| [2026-04-26 01:10:37] Epoch 1 | Step 4170 | Loss: 0.3744 | LM: 0.3693 | LB: 1.0809 | CL0: 2.9 | CL1: 2.6 | HR0: 0.354/SR0: 0.341 | HR1: 0.392/SR1: 0.382 | LR: 4.49e-04 |
| [2026-04-26 01:10:44] Epoch 1 | Step 4180 | Loss: 0.3744 | LM: 0.3694 | LB: 1.0809 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.391/SR1: 0.382 | LR: 4.45e-04 |
| [2026-04-26 01:10:51] Epoch 1 | Step 4190 | Loss: 0.3743 | LM: 0.3694 | LB: 1.0808 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.391/SR1: 0.382 | LR: 4.40e-04 |
| [2026-04-26 01:10:58] Epoch 1 | Step 4200 | Loss: 0.3745 | LM: 0.3696 | LB: 1.0808 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.391/SR1: 0.382 | LR: 4.35e-04 |
| [2026-04-26 01:11:05] Epoch 1 | Step 4210 | Loss: 0.3745 | LM: 0.3696 | LB: 1.0807 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.391/SR1: 0.382 | LR: 4.30e-04 |
| [2026-04-26 01:11:13] Epoch 1 | Step 4220 | Loss: 0.3747 | LM: 0.3698 | LB: 1.0807 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.391/SR1: 0.382 | LR: 4.25e-04 |
| [2026-04-26 01:11:20] Epoch 1 | Step 4230 | Loss: 0.3747 | LM: 0.3699 | LB: 1.0806 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.391/SR1: 0.382 | LR: 4.19e-04 |
| [2026-04-26 01:11:27] Epoch 1 | Step 4240 | Loss: 0.3748 | LM: 0.3701 | LB: 1.0806 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.391/SR1: 0.382 | LR: 4.14e-04 |
| [2026-04-26 01:11:34] Epoch 1 | Step 4250 | Loss: 0.3749 | LM: 0.3701 | LB: 1.0806 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.391/SR1: 0.382 | LR: 4.08e-04 |
| [2026-04-26 01:11:41] Epoch 1 | Step 4260 | Loss: 0.3748 | LM: 0.3699 | LB: 1.0805 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.391/SR1: 0.382 | LR: 4.02e-04 |
| [2026-04-26 01:11:48] Epoch 1 | Step 4270 | Loss: 0.3749 | LM: 0.3698 | LB: 1.0805 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.391/SR1: 0.381 | LR: 3.96e-04 |
| [2026-04-26 01:11:55] Epoch 1 | Step 4280 | Loss: 0.3749 | LM: 0.3697 | LB: 1.0804 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.391/SR1: 0.381 | LR: 3.90e-04 |
| [2026-04-26 01:12:02] Epoch 1 | Step 4290 | Loss: 0.3748 | LM: 0.3696 | LB: 1.0804 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.391/SR1: 0.381 | LR: 3.84e-04 |
| [2026-04-26 01:12:09] Epoch 1 | Step 4300 | Loss: 0.3748 | LM: 0.3696 | LB: 1.0803 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.391/SR1: 0.381 | LR: 3.78e-04 |
| [2026-04-26 01:12:16] Epoch 1 | Step 4310 | Loss: 0.3749 | LM: 0.3695 | LB: 1.0803 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.391/SR1: 0.381 | LR: 3.71e-04 |
| [2026-04-26 01:12:23] Epoch 1 | Step 4320 | Loss: 0.3749 | LM: 0.3694 | LB: 1.0802 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.391/SR1: 0.381 | LR: 3.65e-04 |
| [2026-04-26 01:12:31] Epoch 1 | Step 4330 | Loss: 0.3749 | LM: 0.3695 | LB: 1.0801 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.390/SR1: 0.381 | LR: 3.58e-04 |
| [2026-04-26 01:12:38] Epoch 1 | Step 4340 | Loss: 0.3748 | LM: 0.3697 | LB: 1.0801 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.390/SR1: 0.381 | LR: 3.52e-04 |
| [2026-04-26 01:12:45] Epoch 1 | Step 4350 | Loss: 0.3747 | LM: 0.3697 | LB: 1.0800 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.390/SR1: 0.381 | LR: 3.45e-04 |
| [2026-04-26 01:12:52] Epoch 1 | Step 4360 | Loss: 0.3747 | LM: 0.3696 | LB: 1.0800 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.390/SR1: 0.381 | LR: 3.38e-04 |
| [2026-04-26 01:12:59] Epoch 1 | Step 4370 | Loss: 0.3747 | LM: 0.3698 | LB: 1.0799 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.390/SR1: 0.381 | LR: 3.31e-04 |
| [2026-04-26 01:13:06] Epoch 1 | Step 4380 | Loss: 0.3746 | LM: 0.3698 | LB: 1.0799 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.390/SR1: 0.381 | LR: 3.24e-04 |
| [2026-04-26 01:13:13] Epoch 1 | Step 4390 | Loss: 0.3747 | LM: 0.3698 | LB: 1.0798 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.390/SR1: 0.381 | LR: 3.17e-04 |
| [2026-04-26 01:13:20] Epoch 1 | Step 4400 | Loss: 0.3747 | LM: 0.3696 | LB: 1.0798 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.390/SR1: 0.381 | LR: 3.10e-04 |
| [2026-04-26 01:13:27] Epoch 1 | Step 4410 | Loss: 0.3746 | LM: 0.3695 | LB: 1.0797 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.390/SR1: 0.381 | LR: 3.03e-04 |
| [2026-04-26 01:13:34] Epoch 1 | Step 4420 | Loss: 0.3746 | LM: 0.3696 | LB: 1.0797 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.390/SR1: 0.381 | LR: 2.96e-04 |
| [2026-04-26 01:13:41] Epoch 1 | Step 4430 | Loss: 0.3745 | LM: 0.3695 | LB: 1.0796 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.390/SR1: 0.380 | LR: 2.89e-04 |
| [2026-04-26 01:13:49] Epoch 1 | Step 4440 | Loss: 0.3746 | LM: 0.3695 | LB: 1.0796 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.390/SR1: 0.380 | LR: 2.82e-04 |
| [2026-04-26 01:13:56] Epoch 1 | Step 4450 | Loss: 0.3746 | LM: 0.3693 | LB: 1.0795 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.390/SR1: 0.380 | LR: 2.74e-04 |
| [2026-04-26 01:14:03] Epoch 1 | Step 4460 | Loss: 0.3747 | LM: 0.3693 | LB: 1.0795 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.390/SR1: 0.380 | LR: 2.67e-04 |
| [2026-04-26 01:14:10] Epoch 1 | Step 4470 | Loss: 0.3745 | LM: 0.3692 | LB: 1.0794 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.390/SR1: 0.380 | LR: 2.60e-04 |
| [2026-04-26 01:14:17] Epoch 1 | Step 4480 | Loss: 0.3745 | LM: 0.3692 | LB: 1.0794 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.390/SR1: 0.380 | LR: 2.53e-04 |
| [2026-04-26 01:14:24] Epoch 1 | Step 4490 | Loss: 0.3744 | LM: 0.3692 | LB: 1.0793 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.389/SR1: 0.380 | LR: 2.46e-04 |
| [2026-04-26 01:14:31] Epoch 1 | Step 4500 | Loss: 0.3743 | LM: 0.3691 | LB: 1.0792 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.389/SR1: 0.380 | LR: 2.39e-04 |
| [2026-04-26 01:14:39] Epoch 1 | Step 4510 | Loss: 0.3742 | LM: 0.3689 | LB: 1.0792 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.389/SR1: 0.380 | LR: 2.32e-04 |
| [2026-04-26 01:14:46] Epoch 1 | Step 4520 | Loss: 0.3741 | LM: 0.3690 | LB: 1.0792 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.389/SR1: 0.380 | LR: 2.25e-04 |
| [2026-04-26 01:14:53] Epoch 1 | Step 4530 | Loss: 0.3740 | LM: 0.3688 | LB: 1.0791 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.389/SR1: 0.380 | LR: 2.18e-04 |
| [2026-04-26 01:15:00] Epoch 1 | Step 4540 | Loss: 0.3740 | LM: 0.3689 | LB: 1.0791 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.389/SR1: 0.380 | LR: 2.11e-04 |
| [2026-04-26 01:15:08] Epoch 1 | Step 4550 | Loss: 0.3739 | LM: 0.3688 | LB: 1.0790 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.389/SR1: 0.380 | LR: 2.04e-04 |
| [2026-04-26 01:15:15] Epoch 1 | Step 4560 | Loss: 0.3739 | LM: 0.3687 | LB: 1.0790 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.389/SR1: 0.380 | LR: 1.97e-04 |
| [2026-04-26 01:15:22] Epoch 1 | Step 4570 | Loss: 0.3739 | LM: 0.3686 | LB: 1.0789 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.389/SR1: 0.380 | LR: 1.91e-04 |
| [2026-04-26 01:15:29] Epoch 1 | Step 4580 | Loss: 0.3738 | LM: 0.3686 | LB: 1.0789 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.389/SR1: 0.380 | LR: 1.84e-04 |
| [2026-04-26 01:15:36] Epoch 1 | Step 4590 | Loss: 0.3738 | LM: 0.3686 | LB: 1.0789 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.389/SR1: 0.380 | LR: 1.78e-04 |
| [2026-04-26 01:15:43] Epoch 1 | Step 4600 | Loss: 0.3737 | LM: 0.3684 | LB: 1.0788 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.389/SR1: 0.380 | LR: 1.71e-04 |
| [2026-04-26 01:15:51] Epoch 1 | Step 4610 | Loss: 0.3736 | LM: 0.3683 | LB: 1.0788 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.389/SR1: 0.380 | LR: 1.65e-04 |
| [2026-04-26 01:15:58] Epoch 1 | Step 4620 | Loss: 0.3736 | LM: 0.3682 | LB: 1.0788 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.341 | HR1: 0.389/SR1: 0.379 | LR: 1.59e-04 |
| [2026-04-26 01:16:05] Epoch 1 | Step 4630 | Loss: 0.3736 | LM: 0.3683 | LB: 1.0787 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.389/SR1: 0.379 | LR: 1.53e-04 |
| [2026-04-26 01:16:12] Epoch 1 | Step 4640 | Loss: 0.3736 | LM: 0.3683 | LB: 1.0787 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.389/SR1: 0.379 | LR: 1.47e-04 |
| [2026-04-26 01:16:19] Epoch 1 | Step 4650 | Loss: 0.3736 | LM: 0.3682 | LB: 1.0786 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.389/SR1: 0.379 | LR: 1.41e-04 |
| [2026-04-26 01:16:27] Epoch 1 | Step 4660 | Loss: 0.3736 | LM: 0.3681 | LB: 1.0786 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.388/SR1: 0.379 | LR: 1.35e-04 |
| [2026-04-26 01:16:34] Epoch 1 | Step 4670 | Loss: 0.3735 | LM: 0.3681 | LB: 1.0785 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.388/SR1: 0.379 | LR: 1.30e-04 |
| [2026-04-26 01:16:41] Epoch 1 | Step 4680 | Loss: 0.3735 | LM: 0.3681 | LB: 1.0784 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.388/SR1: 0.379 | LR: 1.24e-04 |
| [2026-04-26 01:16:48] Epoch 1 | Step 4690 | Loss: 0.3734 | LM: 0.3679 | LB: 1.0784 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.388/SR1: 0.379 | LR: 1.19e-04 |
| [2026-04-26 01:16:55] Epoch 1 | Step 4700 | Loss: 0.3734 | LM: 0.3680 | LB: 1.0784 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.388/SR1: 0.379 | LR: 1.14e-04 |
| [2026-04-26 01:17:02] Epoch 1 | Step 4710 | Loss: 0.3734 | LM: 0.3679 | LB: 1.0783 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.388/SR1: 0.379 | LR: 1.09e-04 |
| [2026-04-26 01:17:10] Epoch 1 | Step 4720 | Loss: 0.3734 | LM: 0.3680 | LB: 1.0783 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.388/SR1: 0.379 | LR: 1.04e-04 |
| [2026-04-26 01:17:17] Epoch 1 | Step 4730 | Loss: 0.3733 | LM: 0.3679 | LB: 1.0782 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.388/SR1: 0.379 | LR: 9.98e-05 |
| [2026-04-26 01:17:24] Epoch 1 | Step 4740 | Loss: 0.3733 | LM: 0.3678 | LB: 1.0782 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.388/SR1: 0.379 | LR: 9.54e-05 |
| [2026-04-26 01:17:31] Epoch 1 | Step 4750 | Loss: 0.3733 | LM: 0.3677 | LB: 1.0781 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.388/SR1: 0.379 | LR: 9.12e-05 |
| [2026-04-26 01:17:38] Epoch 1 | Step 4760 | Loss: 0.3732 | LM: 0.3677 | LB: 1.0781 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.388/SR1: 0.379 | LR: 8.72e-05 |
| [2026-04-26 01:17:45] Epoch 1 | Step 4770 | Loss: 0.3731 | LM: 0.3674 | LB: 1.0781 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.388/SR1: 0.379 | LR: 8.33e-05 |
| [2026-04-26 01:17:53] Epoch 1 | Step 4780 | Loss: 0.3731 | LM: 0.3674 | LB: 1.0781 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.388/SR1: 0.379 | LR: 7.97e-05 |
| [2026-04-26 01:18:00] Epoch 1 | Step 4790 | Loss: 0.3731 | LM: 0.3673 | LB: 1.0780 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.388/SR1: 0.379 | LR: 7.62e-05 |
| [2026-04-26 01:18:07] Epoch 1 | Step 4800 | Loss: 0.3730 | LM: 0.3672 | LB: 1.0780 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.388/SR1: 0.379 | LR: 7.30e-05 |
| [2026-04-26 01:18:14] Epoch 1 | Step 4810 | Loss: 0.3729 | LM: 0.3671 | LB: 1.0779 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.388/SR1: 0.379 | LR: 6.99e-05 |
| [2026-04-26 01:18:21] Epoch 1 | Step 4820 | Loss: 0.3728 | LM: 0.3669 | LB: 1.0779 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.388/SR1: 0.378 | LR: 6.71e-05 |
| [2026-04-26 01:18:28] Epoch 1 | Step 4830 | Loss: 0.3726 | LM: 0.3666 | LB: 1.0779 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.388/SR1: 0.378 | LR: 6.45e-05 |
| [2026-04-26 01:18:35] Epoch 1 | Step 4840 | Loss: 0.3726 | LM: 0.3665 | LB: 1.0778 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.388/SR1: 0.378 | LR: 6.21e-05 |
| [2026-04-26 01:18:42] Epoch 1 | Step 4850 | Loss: 0.3726 | LM: 0.3666 | LB: 1.0778 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.99e-05 |
| [2026-04-26 01:18:49] Epoch 1 | Step 4860 | Loss: 0.3727 | LM: 0.3666 | LB: 1.0777 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.79e-05 |
| [2026-04-26 01:18:56] Epoch 1 | Step 4870 | Loss: 0.3727 | LM: 0.3665 | LB: 1.0777 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.61e-05 |
| [2026-04-26 01:19:03] Epoch 1 | Step 4880 | Loss: 0.3727 | LM: 0.3665 | LB: 1.0776 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.46e-05 |
| [2026-04-26 01:19:10] Epoch 1 | Step 4890 | Loss: 0.3726 | LM: 0.3665 | LB: 1.0776 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.32e-05 |
| [2026-04-26 01:19:18] Epoch 1 | Step 4900 | Loss: 0.3725 | LM: 0.3663 | LB: 1.0776 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.21e-05 |
| [2026-04-26 01:19:25] Epoch 1 | Step 4910 | Loss: 0.3725 | LM: 0.3662 | LB: 1.0775 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.13e-05 |
| [2026-04-26 01:19:32] Epoch 1 | Step 4920 | Loss: 0.3724 | LM: 0.3661 | LB: 1.0775 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.06e-05 |
| [2026-04-26 01:19:39] Epoch 1 | Step 4930 | Loss: 0.3724 | LM: 0.3660 | LB: 1.0774 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.02e-05 |
| [2026-04-26 01:19:46] Epoch 1 | Step 4940 | Loss: 0.3723 | LM: 0.3660 | LB: 1.0774 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.00e-05 |
| [2026-04-26 01:19:53] Epoch 1 | Step 4950 | Loss: 0.3723 | LM: 0.3661 | LB: 1.0773 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.00e-05 |
| [2026-04-26 01:20:00] Epoch 1 | Step 4960 | Loss: 0.3723 | LM: 0.3660 | LB: 1.0773 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.00e-05 |
| [2026-04-26 01:20:07] Epoch 1 | Step 4970 | Loss: 0.3722 | LM: 0.3660 | LB: 1.0773 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.00e-05 |
| [2026-04-26 01:20:14] Epoch 1 | Step 4980 | Loss: 0.3722 | LM: 0.3659 | LB: 1.0772 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.00e-05 |
| [2026-04-26 01:20:22] Epoch 1 | Step 4990 | Loss: 0.3720 | LM: 0.3658 | LB: 1.0772 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.00e-05 |
| [2026-04-26 01:20:29] Epoch 1 | Step 5000 | Loss: 0.3721 | LM: 0.3659 | LB: 1.0771 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.00e-05 |
| [2026-04-26 01:20:36] Epoch 1 | Step 5010 | Loss: 0.3720 | LM: 0.3659 | LB: 1.0771 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.00e-05 |
| [2026-04-26 01:20:43] Epoch 1 | Step 5020 | Loss: 0.3719 | LM: 0.3657 | LB: 1.0771 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.00e-05 |
| [2026-04-26 01:20:50] Epoch 1 | Step 5030 | Loss: 0.3719 | LM: 0.3657 | LB: 1.0771 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.00e-05 |
| [2026-04-26 01:20:57] Epoch 1 | Step 5040 | Loss: 0.3718 | LM: 0.3655 | LB: 1.0770 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.00e-05 |
| [2026-04-26 01:21:04] Epoch 1 | Step 5050 | Loss: 0.3718 | LM: 0.3655 | LB: 1.0770 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.387/SR1: 0.378 | LR: 5.00e-05 |
| [2026-04-26 01:21:11] Epoch 1 | Step 5060 | Loss: 0.3718 | LM: 0.3653 | LB: 1.0770 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.386/SR1: 0.378 | LR: 5.00e-05 |
| [2026-04-26 01:21:19] Epoch 1 | Step 5070 | Loss: 0.3717 | LM: 0.3652 | LB: 1.0769 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:21:26] Epoch 1 | Step 5080 | Loss: 0.3717 | LM: 0.3652 | LB: 1.0769 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:21:33] Epoch 1 | Step 5090 | Loss: 0.3717 | LM: 0.3652 | LB: 1.0769 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:21:40] Epoch 1 | Step 5100 | Loss: 0.3716 | LM: 0.3651 | LB: 1.0768 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:21:47] Epoch 1 | Step 5110 | Loss: 0.3715 | LM: 0.3651 | LB: 1.0768 | CL0: 2.9 | CL1: 2.6 | HR0: 0.353/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:21:54] Epoch 1 | Step 5120 | Loss: 0.3716 | LM: 0.3652 | LB: 1.0767 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:22:01] Epoch 1 | Step 5130 | Loss: 0.3715 | LM: 0.3650 | LB: 1.0767 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:22:09] Epoch 1 | Step 5140 | Loss: 0.3714 | LM: 0.3650 | LB: 1.0767 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:22:16] Epoch 1 | Step 5150 | Loss: 0.3713 | LM: 0.3649 | LB: 1.0766 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:22:23] Epoch 1 | Step 5160 | Loss: 0.3711 | LM: 0.3648 | LB: 1.0766 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:22:30] Epoch 1 | Step 5170 | Loss: 0.3711 | LM: 0.3648 | LB: 1.0765 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:22:37] Epoch 1 | Step 5180 | Loss: 0.3710 | LM: 0.3647 | LB: 1.0765 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:22:44] Epoch 1 | Step 5190 | Loss: 0.3710 | LM: 0.3647 | LB: 1.0765 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:22:51] Epoch 1 | Step 5200 | Loss: 0.3709 | LM: 0.3646 | LB: 1.0764 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:22:58] Epoch 1 | Step 5210 | Loss: 0.3709 | LM: 0.3645 | LB: 1.0764 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:23:05] Epoch 1 | Step 5220 | Loss: 0.3709 | LM: 0.3644 | LB: 1.0764 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:23:13] Epoch 1 | Step 5230 | Loss: 0.3709 | LM: 0.3643 | LB: 1.0763 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:23:20] Epoch 1 | Step 5240 | Loss: 0.3708 | LM: 0.3641 | LB: 1.0763 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:23:27] Epoch 1 | Step 5250 | Loss: 0.3708 | LM: 0.3643 | LB: 1.0763 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:23:34] Epoch 1 | Step 5260 | Loss: 0.3707 | LM: 0.3642 | LB: 1.0762 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.386/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:23:41] Epoch 1 | Step 5270 | Loss: 0.3707 | LM: 0.3641 | LB: 1.0762 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.385/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:23:48] Epoch 1 | Step 5280 | Loss: 0.3706 | LM: 0.3639 | LB: 1.0762 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.385/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:23:55] Epoch 1 | Step 5290 | Loss: 0.3705 | LM: 0.3639 | LB: 1.0761 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.385/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:24:02] Epoch 1 | Step 5300 | Loss: 0.3705 | LM: 0.3638 | LB: 1.0761 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.385/SR1: 0.377 | LR: 5.00e-05 |
| [2026-04-26 01:24:09] Epoch 1 | Step 5310 | Loss: 0.3705 | LM: 0.3638 | LB: 1.0761 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.385/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:24:17] Epoch 1 | Step 5320 | Loss: 0.3704 | LM: 0.3636 | LB: 1.0761 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.385/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:24:24] Epoch 1 | Step 5330 | Loss: 0.3704 | LM: 0.3636 | LB: 1.0760 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.385/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:24:31] Epoch 1 | Step 5340 | Loss: 0.3704 | LM: 0.3636 | LB: 1.0760 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.385/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:24:38] Epoch 1 | Step 5350 | Loss: 0.3703 | LM: 0.3636 | LB: 1.0759 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.385/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:24:45] Epoch 1 | Step 5360 | Loss: 0.3703 | LM: 0.3634 | LB: 1.0759 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.340 | HR1: 0.385/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:24:52] Epoch 1 | Step 5370 | Loss: 0.3702 | LM: 0.3633 | LB: 1.0758 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.385/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:24:59] Epoch 1 | Step 5380 | Loss: 0.3701 | LM: 0.3632 | LB: 1.0758 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.385/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:25:06] Epoch 1 | Step 5390 | Loss: 0.3700 | LM: 0.3630 | LB: 1.0757 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.385/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:25:14] Epoch 1 | Step 5400 | Loss: 0.3700 | LM: 0.3630 | LB: 1.0757 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.385/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:25:21] Epoch 1 | Step 5410 | Loss: 0.3699 | LM: 0.3629 | LB: 1.0757 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.385/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:25:28] Epoch 1 | Step 5420 | Loss: 0.3699 | LM: 0.3629 | LB: 1.0757 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.385/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:25:35] Epoch 1 | Step 5430 | Loss: 0.3698 | LM: 0.3629 | LB: 1.0757 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.385/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:25:42] Epoch 1 | Step 5440 | Loss: 0.3698 | LM: 0.3628 | LB: 1.0756 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.385/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:25:49] Epoch 1 | Step 5450 | Loss: 0.3698 | LM: 0.3627 | LB: 1.0756 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.385/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:25:56] Epoch 1 | Step 5460 | Loss: 0.3698 | LM: 0.3626 | LB: 1.0755 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.385/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:26:03] Epoch 1 | Step 5470 | Loss: 0.3697 | LM: 0.3625 | LB: 1.0755 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.385/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:26:10] Epoch 1 | Step 5480 | Loss: 0.3697 | LM: 0.3623 | LB: 1.0755 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:26:17] Epoch 1 | Step 5490 | Loss: 0.3697 | LM: 0.3624 | LB: 1.0754 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:26:24] Epoch 1 | Step 5500 | Loss: 0.3697 | LM: 0.3625 | LB: 1.0754 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:26:32] Epoch 1 | Step 5510 | Loss: 0.3697 | LM: 0.3626 | LB: 1.0753 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:26:40] Epoch 1 | Step 5520 | Loss: 0.3696 | LM: 0.3625 | LB: 1.0753 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:26:47] Epoch 1 | Step 5530 | Loss: 0.3696 | LM: 0.3624 | LB: 1.0753 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:26:54] Epoch 1 | Step 5540 | Loss: 0.3694 | LM: 0.3622 | LB: 1.0752 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:27:01] Epoch 1 | Step 5550 | Loss: 0.3694 | LM: 0.3621 | LB: 1.0752 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.376 | LR: 5.00e-05 |
| [2026-04-26 01:27:08] Epoch 1 | Step 5560 | Loss: 0.3693 | LM: 0.3621 | LB: 1.0752 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:27:15] Epoch 1 | Step 5570 | Loss: 0.3694 | LM: 0.3621 | LB: 1.0751 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:27:22] Epoch 1 | Step 5580 | Loss: 0.3693 | LM: 0.3620 | LB: 1.0751 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:27:29] Epoch 1 | Step 5590 | Loss: 0.3692 | LM: 0.3621 | LB: 1.0751 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:27:37] Epoch 1 | Step 5600 | Loss: 0.3692 | LM: 0.3620 | LB: 1.0751 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:27:44] Epoch 1 | Step 5610 | Loss: 0.3692 | LM: 0.3621 | LB: 1.0750 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:27:51] Epoch 1 | Step 5620 | Loss: 0.3692 | LM: 0.3620 | LB: 1.0750 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:27:58] Epoch 1 | Step 5630 | Loss: 0.3691 | LM: 0.3620 | LB: 1.0750 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:28:05] Epoch 1 | Step 5640 | Loss: 0.3691 | LM: 0.3621 | LB: 1.0749 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:28:12] Epoch 1 | Step 5650 | Loss: 0.3691 | LM: 0.3621 | LB: 1.0749 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:28:19] Epoch 1 | Step 5660 | Loss: 0.3690 | LM: 0.3620 | LB: 1.0749 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:28:27] Epoch 1 | Step 5670 | Loss: 0.3690 | LM: 0.3620 | LB: 1.0749 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:28:34] Epoch 1 | Step 5680 | Loss: 0.3688 | LM: 0.3619 | LB: 1.0748 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:28:41] Epoch 1 | Step 5690 | Loss: 0.3689 | LM: 0.3619 | LB: 1.0748 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:28:48] Epoch 1 | Step 5700 | Loss: 0.3688 | LM: 0.3619 | LB: 1.0748 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:28:55] Epoch 1 | Step 5710 | Loss: 0.3688 | LM: 0.3618 | LB: 1.0747 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:29:02] Epoch 1 | Step 5720 | Loss: 0.3688 | LM: 0.3618 | LB: 1.0747 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:29:09] Epoch 1 | Step 5730 | Loss: 0.3687 | LM: 0.3619 | LB: 1.0747 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.384/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:29:16] Epoch 1 | Step 5740 | Loss: 0.3687 | LM: 0.3618 | LB: 1.0746 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:29:24] Epoch 1 | Step 5750 | Loss: 0.3687 | LM: 0.3618 | LB: 1.0746 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:29:31] Epoch 1 | Step 5760 | Loss: 0.3687 | LM: 0.3617 | LB: 1.0746 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:29:38] Epoch 1 | Step 5770 | Loss: 0.3687 | LM: 0.3617 | LB: 1.0746 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:29:45] Epoch 1 | Step 5780 | Loss: 0.3687 | LM: 0.3617 | LB: 1.0745 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:29:52] Epoch 1 | Step 5790 | Loss: 0.3687 | LM: 0.3615 | LB: 1.0745 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:29:59] Epoch 1 | Step 5800 | Loss: 0.3687 | LM: 0.3616 | LB: 1.0744 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:30:07] Epoch 1 | Step 5810 | Loss: 0.3687 | LM: 0.3617 | LB: 1.0744 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:30:14] Epoch 1 | Step 5820 | Loss: 0.3686 | LM: 0.3615 | LB: 1.0744 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:30:21] Epoch 1 | Step 5830 | Loss: 0.3685 | LM: 0.3614 | LB: 1.0744 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:30:28] Epoch 1 | Step 5840 | Loss: 0.3685 | LM: 0.3614 | LB: 1.0743 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:30:35] Epoch 1 | Step 5850 | Loss: 0.3685 | LM: 0.3616 | LB: 1.0743 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:30:42] Epoch 1 | Step 5860 | Loss: 0.3684 | LM: 0.3614 | LB: 1.0743 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:30:50] Epoch 1 | Step 5870 | Loss: 0.3684 | LM: 0.3614 | LB: 1.0743 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:30:57] Epoch 1 | Step 5880 | Loss: 0.3684 | LM: 0.3615 | LB: 1.0743 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.375 | LR: 5.00e-05 |
| [2026-04-26 01:31:04] Epoch 1 | Step 5890 | Loss: 0.3684 | LM: 0.3614 | LB: 1.0742 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:31:11] Epoch 1 | Step 5900 | Loss: 0.3683 | LM: 0.3614 | LB: 1.0742 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:31:18] Epoch 1 | Step 5910 | Loss: 0.3683 | LM: 0.3614 | LB: 1.0742 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:31:25] Epoch 1 | Step 5920 | Loss: 0.3682 | LM: 0.3614 | LB: 1.0742 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:31:33] Epoch 1 | Step 5930 | Loss: 0.3682 | LM: 0.3614 | LB: 1.0741 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:31:40] Epoch 1 | Step 5940 | Loss: 0.3682 | LM: 0.3614 | LB: 1.0741 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:31:47] Epoch 1 | Step 5950 | Loss: 0.3682 | LM: 0.3614 | LB: 1.0741 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:31:54] Epoch 1 | Step 5960 | Loss: 0.3682 | LM: 0.3614 | LB: 1.0741 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:32:01] Epoch 1 | Step 5970 | Loss: 0.3682 | LM: 0.3613 | LB: 1.0740 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:32:08] Epoch 1 | Step 5980 | Loss: 0.3682 | LM: 0.3613 | LB: 1.0740 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:32:15] Epoch 1 | Step 5990 | Loss: 0.3682 | LM: 0.3614 | LB: 1.0740 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:32:23] Epoch 1 | Step 6000 | Loss: 0.3681 | LM: 0.3613 | LB: 1.0740 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:32:23] Validation | Batch 10/42 | Loss: 0.3375 | LM_LOSS: 0.3270 | LB_LOSS: 1.0515 |
| [2026-04-26 01:32:24] Validation | Batch 20/42 | Loss: 0.3568 | LM_LOSS: 0.3462 | LB_LOSS: 1.0552 |
| [2026-04-26 01:32:26] Validation | Batch 30/42 | Loss: 0.3470 | LM_LOSS: 0.3365 | LB_LOSS: 1.0541 |
| [2026-04-26 01:32:27] Validation | Batch 40/42 | Loss: 0.3531 | LM_LOSS: 0.3426 | LB_LOSS: 1.0537 |
| [2026-04-26 01:32:27] Validation | Batch 42/42 | Loss: 0.3528 | LM_LOSS: 0.3423 | LB_LOSS: 1.0540 |
| [2026-04-26 01:32:27] Validation | Loss: 0.3528 | LM_LOSS: 0.3423 | LB_LOSS: 1.0540 | PPL: 1.40 | Time: 4.47s |
| [2026-04-26 01:32:30] New best model saved! Val loss: 0.3528 |
| [2026-04-26 01:32:37] Epoch 1 | Step 6010 | Loss: 0.3681 | LM: 0.3612 | LB: 1.0739 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:32:44] Epoch 1 | Step 6020 | Loss: 0.3681 | LM: 0.3611 | LB: 1.0739 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.383/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:32:51] Epoch 1 | Step 6030 | Loss: 0.3681 | LM: 0.3609 | LB: 1.0738 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:32:59] Epoch 1 | Step 6040 | Loss: 0.3681 | LM: 0.3609 | LB: 1.0738 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:33:06] Epoch 1 | Step 6050 | Loss: 0.3681 | LM: 0.3610 | LB: 1.0738 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:33:13] Epoch 1 | Step 6060 | Loss: 0.3681 | LM: 0.3610 | LB: 1.0738 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:33:20] Epoch 1 | Step 6070 | Loss: 0.3680 | LM: 0.3609 | LB: 1.0737 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:33:27] Epoch 1 | Step 6080 | Loss: 0.3680 | LM: 0.3608 | LB: 1.0737 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:33:34] Epoch 1 | Step 6090 | Loss: 0.3680 | LM: 0.3608 | LB: 1.0737 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:33:41] Epoch 1 | Step 6100 | Loss: 0.3680 | LM: 0.3608 | LB: 1.0736 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:33:48] Epoch 1 | Step 6110 | Loss: 0.3680 | LM: 0.3608 | LB: 1.0736 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:33:56] Epoch 1 | Step 6120 | Loss: 0.3679 | LM: 0.3608 | LB: 1.0736 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:34:03] Epoch 1 | Step 6130 | Loss: 0.3678 | LM: 0.3607 | LB: 1.0735 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:34:10] Epoch 1 | Step 6140 | Loss: 0.3677 | LM: 0.3605 | LB: 1.0735 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:34:17] Epoch 1 | Step 6150 | Loss: 0.3676 | LM: 0.3604 | LB: 1.0735 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:34:24] Epoch 1 | Step 6160 | Loss: 0.3676 | LM: 0.3604 | LB: 1.0734 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:34:31] Epoch 1 | Step 6170 | Loss: 0.3676 | LM: 0.3602 | LB: 1.0734 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:34:38] Epoch 1 | Step 6180 | Loss: 0.3675 | LM: 0.3603 | LB: 1.0734 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:34:45] Epoch 1 | Step 6190 | Loss: 0.3674 | LM: 0.3603 | LB: 1.0734 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:34:53] Epoch 1 | Step 6200 | Loss: 0.3674 | LM: 0.3602 | LB: 1.0734 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:35:00] Epoch 1 | Step 6210 | Loss: 0.3674 | LM: 0.3600 | LB: 1.0734 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:35:07] Epoch 1 | Step 6220 | Loss: 0.3674 | LM: 0.3601 | LB: 1.0734 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:35:14] Epoch 1 | Step 6230 | Loss: 0.3673 | LM: 0.3602 | LB: 1.0733 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.374 | LR: 5.00e-05 |
| [2026-04-26 01:35:21] Epoch 1 | Step 6240 | Loss: 0.3673 | LM: 0.3601 | LB: 1.0733 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:35:28] Epoch 1 | Step 6250 | Loss: 0.3672 | LM: 0.3601 | LB: 1.0733 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:35:35] Epoch 1 | Step 6260 | Loss: 0.3672 | LM: 0.3602 | LB: 1.0733 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:35:43] Epoch 1 | Step 6270 | Loss: 0.3671 | LM: 0.3601 | LB: 1.0732 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:35:50] Epoch 1 | Step 6280 | Loss: 0.3670 | LM: 0.3598 | LB: 1.0732 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:35:57] Epoch 1 | Step 6290 | Loss: 0.3670 | LM: 0.3598 | LB: 1.0732 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:36:04] Epoch 1 | Step 6300 | Loss: 0.3669 | LM: 0.3598 | LB: 1.0732 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:36:11] Epoch 1 | Step 6310 | Loss: 0.3669 | LM: 0.3598 | LB: 1.0731 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.382/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:36:18] Epoch 1 | Step 6320 | Loss: 0.3668 | LM: 0.3598 | LB: 1.0731 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:36:25] Epoch 1 | Step 6330 | Loss: 0.3669 | LM: 0.3599 | LB: 1.0731 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:36:33] Epoch 1 | Step 6340 | Loss: 0.3669 | LM: 0.3599 | LB: 1.0730 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:36:40] Epoch 1 | Step 6350 | Loss: 0.3669 | LM: 0.3599 | LB: 1.0730 | CL0: 2.9 | CL1: 2.6 | HR0: 0.352/SR0: 0.339 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:36:47] Epoch 1 | Step 6360 | Loss: 0.3669 | LM: 0.3600 | LB: 1.0730 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.339 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:36:54] Epoch 1 | Step 6370 | Loss: 0.3669 | LM: 0.3599 | LB: 1.0730 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.339 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:37:01] Epoch 1 | Step 6380 | Loss: 0.3668 | LM: 0.3598 | LB: 1.0729 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.339 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:37:08] Epoch 1 | Step 6390 | Loss: 0.3668 | LM: 0.3597 | LB: 1.0729 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.339 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:37:15] Epoch 1 | Step 6400 | Loss: 0.3668 | LM: 0.3596 | LB: 1.0729 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:37:22] Epoch 1 | Step 6410 | Loss: 0.3667 | LM: 0.3596 | LB: 1.0729 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:37:29] Epoch 1 | Step 6420 | Loss: 0.3667 | LM: 0.3595 | LB: 1.0729 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:37:37] Epoch 1 | Step 6430 | Loss: 0.3666 | LM: 0.3595 | LB: 1.0728 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:37:44] Epoch 1 | Step 6440 | Loss: 0.3666 | LM: 0.3594 | LB: 1.0728 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:37:51] Epoch 1 | Step 6450 | Loss: 0.3666 | LM: 0.3594 | LB: 1.0728 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:37:58] Epoch 1 | Step 6460 | Loss: 0.3665 | LM: 0.3592 | LB: 1.0727 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:38:05] Epoch 1 | Step 6470 | Loss: 0.3665 | LM: 0.3591 | LB: 1.0727 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:38:12] Epoch 1 | Step 6480 | Loss: 0.3665 | LM: 0.3592 | LB: 1.0727 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:38:19] Epoch 1 | Step 6490 | Loss: 0.3666 | LM: 0.3593 | LB: 1.0727 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:38:26] Epoch 1 | Step 6500 | Loss: 0.3665 | LM: 0.3591 | LB: 1.0726 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:38:34] Epoch 1 | Step 6510 | Loss: 0.3664 | LM: 0.3591 | LB: 1.0726 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:38:41] Epoch 1 | Step 6520 | Loss: 0.3664 | LM: 0.3591 | LB: 1.0726 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:38:48] Epoch 1 | Step 6530 | Loss: 0.3662 | LM: 0.3590 | LB: 1.0726 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:38:55] Epoch 1 | Step 6540 | Loss: 0.3662 | LM: 0.3590 | LB: 1.0725 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:39:02] Epoch 1 | Step 6550 | Loss: 0.3662 | LM: 0.3587 | LB: 1.0725 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:39:09] Epoch 1 | Step 6560 | Loss: 0.3661 | LM: 0.3586 | LB: 1.0725 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:39:16] Epoch 1 | Step 6570 | Loss: 0.3661 | LM: 0.3587 | LB: 1.0725 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:39:24] Epoch 1 | Step 6580 | Loss: 0.3661 | LM: 0.3587 | LB: 1.0725 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:39:31] Epoch 1 | Step 6590 | Loss: 0.3660 | LM: 0.3587 | LB: 1.0724 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:39:38] Epoch 1 | Step 6600 | Loss: 0.3660 | LM: 0.3586 | LB: 1.0724 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:39:45] Epoch 1 | Step 6610 | Loss: 0.3660 | LM: 0.3586 | LB: 1.0724 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.373 | LR: 5.00e-05 |
| [2026-04-26 01:39:52] Epoch 1 | Step 6620 | Loss: 0.3659 | LM: 0.3584 | LB: 1.0724 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:39:59] Epoch 1 | Step 6630 | Loss: 0.3659 | LM: 0.3583 | LB: 1.0724 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:40:06] Epoch 1 | Step 6640 | Loss: 0.3659 | LM: 0.3584 | LB: 1.0723 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:40:13] Epoch 1 | Step 6650 | Loss: 0.3659 | LM: 0.3583 | LB: 1.0723 | CL0: 2.9 | CL1: 2.7 | HR0: 0.352/SR0: 0.338 | HR1: 0.381/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:40:20] Epoch 1 | Step 6660 | Loss: 0.3657 | LM: 0.3582 | LB: 1.0723 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:40:27] Epoch 1 | Step 6670 | Loss: 0.3657 | LM: 0.3581 | LB: 1.0722 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:40:34] Epoch 1 | Step 6680 | Loss: 0.3657 | LM: 0.3579 | LB: 1.0722 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:40:41] Epoch 1 | Step 6690 | Loss: 0.3657 | LM: 0.3579 | LB: 1.0722 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:40:48] Epoch 1 | Step 6700 | Loss: 0.3656 | LM: 0.3578 | LB: 1.0722 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:40:56] Epoch 1 | Step 6710 | Loss: 0.3656 | LM: 0.3578 | LB: 1.0721 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:41:03] Epoch 1 | Step 6720 | Loss: 0.3656 | LM: 0.3577 | LB: 1.0721 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:41:10] Epoch 1 | Step 6730 | Loss: 0.3656 | LM: 0.3577 | LB: 1.0721 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:41:17] Epoch 1 | Step 6740 | Loss: 0.3656 | LM: 0.3577 | LB: 1.0721 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:41:24] Epoch 1 | Step 6750 | Loss: 0.3655 | LM: 0.3577 | LB: 1.0721 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:41:31] Epoch 1 | Step 6760 | Loss: 0.3655 | LM: 0.3578 | LB: 1.0720 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:41:38] Epoch 1 | Step 6770 | Loss: 0.3655 | LM: 0.3577 | LB: 1.0720 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:41:45] Epoch 1 | Step 6780 | Loss: 0.3655 | LM: 0.3577 | LB: 1.0720 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:41:52] Epoch 1 | Step 6790 | Loss: 0.3655 | LM: 0.3577 | LB: 1.0720 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:41:59] Epoch 1 | Step 6800 | Loss: 0.3656 | LM: 0.3576 | LB: 1.0720 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:42:06] Epoch 1 | Step 6810 | Loss: 0.3656 | LM: 0.3576 | LB: 1.0719 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:42:13] Epoch 1 | Step 6820 | Loss: 0.3656 | LM: 0.3575 | LB: 1.0719 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:42:20] Epoch 1 | Step 6830 | Loss: 0.3657 | LM: 0.3576 | LB: 1.0719 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:42:27] Epoch 1 | Step 6840 | Loss: 0.3657 | LM: 0.3575 | LB: 1.0719 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:42:35] Epoch 1 | Step 6850 | Loss: 0.3657 | LM: 0.3574 | LB: 1.0719 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:42:42] Epoch 1 | Step 6860 | Loss: 0.3657 | LM: 0.3575 | LB: 1.0718 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:42:49] Epoch 1 | Step 6870 | Loss: 0.3656 | LM: 0.3574 | LB: 1.0718 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:42:56] Epoch 1 | Step 6880 | Loss: 0.3656 | LM: 0.3574 | LB: 1.0718 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:43:03] Epoch 1 | Step 6890 | Loss: 0.3656 | LM: 0.3573 | LB: 1.0718 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:43:10] Epoch 1 | Step 6900 | Loss: 0.3656 | LM: 0.3574 | LB: 1.0717 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:43:17] Epoch 1 | Step 6910 | Loss: 0.3655 | LM: 0.3573 | LB: 1.0717 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:43:24] Epoch 1 | Step 6920 | Loss: 0.3655 | LM: 0.3573 | LB: 1.0717 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:43:31] Epoch 1 | Step 6930 | Loss: 0.3655 | LM: 0.3573 | LB: 1.0717 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:43:38] Epoch 1 | Step 6940 | Loss: 0.3654 | LM: 0.3572 | LB: 1.0716 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:43:45] Epoch 1 | Step 6950 | Loss: 0.3654 | LM: 0.3572 | LB: 1.0716 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:43:52] Epoch 1 | Step 6960 | Loss: 0.3654 | LM: 0.3572 | LB: 1.0716 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:43:59] Epoch 1 | Step 6970 | Loss: 0.3653 | LM: 0.3571 | LB: 1.0716 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:44:06] Epoch 1 | Step 6980 | Loss: 0.3653 | LM: 0.3571 | LB: 1.0716 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.380/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:44:14] Epoch 1 | Step 6990 | Loss: 0.3652 | LM: 0.3571 | LB: 1.0715 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:44:21] Epoch 1 | Step 7000 | Loss: 0.3652 | LM: 0.3572 | LB: 1.0715 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:44:28] Epoch 1 | Step 7010 | Loss: 0.3651 | LM: 0.3572 | LB: 1.0715 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.372 | LR: 5.00e-05 |
| [2026-04-26 01:44:35] Epoch 1 | Step 7020 | Loss: 0.3651 | LM: 0.3572 | LB: 1.0715 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:44:42] Epoch 1 | Step 7030 | Loss: 0.3651 | LM: 0.3571 | LB: 1.0715 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:44:49] Epoch 1 | Step 7040 | Loss: 0.3651 | LM: 0.3571 | LB: 1.0715 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:44:56] Epoch 1 | Step 7050 | Loss: 0.3650 | LM: 0.3572 | LB: 1.0714 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:45:04] Epoch 1 | Step 7060 | Loss: 0.3650 | LM: 0.3572 | LB: 1.0714 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:45:11] Epoch 1 | Step 7070 | Loss: 0.3650 | LM: 0.3572 | LB: 1.0714 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:45:18] Epoch 1 | Step 7080 | Loss: 0.3650 | LM: 0.3571 | LB: 1.0714 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:45:25] Epoch 1 | Step 7090 | Loss: 0.3650 | LM: 0.3573 | LB: 1.0714 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:45:32] Epoch 1 | Step 7100 | Loss: 0.3649 | LM: 0.3571 | LB: 1.0714 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:45:39] Epoch 1 | Step 7110 | Loss: 0.3648 | LM: 0.3570 | LB: 1.0714 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:45:46] Epoch 1 | Step 7120 | Loss: 0.3649 | LM: 0.3569 | LB: 1.0714 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:45:53] Epoch 1 | Step 7130 | Loss: 0.3648 | LM: 0.3569 | LB: 1.0714 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:46:00] Epoch 1 | Step 7140 | Loss: 0.3648 | LM: 0.3569 | LB: 1.0713 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:46:07] Epoch 1 | Step 7150 | Loss: 0.3648 | LM: 0.3568 | LB: 1.0713 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:46:14] Epoch 1 | Step 7160 | Loss: 0.3647 | LM: 0.3566 | LB: 1.0713 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:46:21] Epoch 1 | Step 7170 | Loss: 0.3647 | LM: 0.3567 | LB: 1.0713 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:46:28] Epoch 1 | Step 7180 | Loss: 0.3647 | LM: 0.3566 | LB: 1.0712 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:46:35] Epoch 1 | Step 7190 | Loss: 0.3648 | LM: 0.3567 | LB: 1.0712 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:46:43] Epoch 1 | Step 7200 | Loss: 0.3647 | LM: 0.3566 | LB: 1.0712 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:46:50] Epoch 1 | Step 7210 | Loss: 0.3646 | LM: 0.3565 | LB: 1.0712 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:46:57] Epoch 1 | Step 7220 | Loss: 0.3647 | LM: 0.3566 | LB: 1.0712 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:47:04] Epoch 1 | Step 7230 | Loss: 0.3646 | LM: 0.3566 | LB: 1.0712 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:47:11] Epoch 1 | Step 7240 | Loss: 0.3646 | LM: 0.3564 | LB: 1.0712 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:47:18] Epoch 1 | Step 7250 | Loss: 0.3646 | LM: 0.3564 | LB: 1.0712 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:47:25] Epoch 1 | Step 7260 | Loss: 0.3645 | LM: 0.3562 | LB: 1.0711 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:47:32] Epoch 1 | Step 7270 | Loss: 0.3645 | LM: 0.3563 | LB: 1.0711 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:47:39] Epoch 1 | Step 7280 | Loss: 0.3645 | LM: 0.3563 | LB: 1.0711 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:47:46] Epoch 1 | Step 7290 | Loss: 0.3645 | LM: 0.3562 | LB: 1.0711 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:47:53] Epoch 1 | Step 7300 | Loss: 0.3644 | LM: 0.3562 | LB: 1.0710 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:48:00] Epoch 1 | Step 7310 | Loss: 0.3644 | LM: 0.3561 | LB: 1.0710 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:48:07] Epoch 1 | Step 7320 | Loss: 0.3643 | LM: 0.3562 | LB: 1.0710 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:48:14] Epoch 1 | Step 7330 | Loss: 0.3643 | LM: 0.3561 | LB: 1.0710 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:48:22] Epoch 1 | Step 7340 | Loss: 0.3644 | LM: 0.3562 | LB: 1.0710 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:48:29] Epoch 1 | Step 7350 | Loss: 0.3644 | LM: 0.3563 | LB: 1.0710 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:48:36] Epoch 1 | Step 7360 | Loss: 0.3643 | LM: 0.3562 | LB: 1.0709 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:48:43] Epoch 1 | Step 7370 | Loss: 0.3642 | LM: 0.3561 | LB: 1.0709 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:48:50] Epoch 1 | Step 7380 | Loss: 0.3642 | LM: 0.3560 | LB: 1.0709 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:48:57] Epoch 1 | Step 7390 | Loss: 0.3641 | LM: 0.3560 | LB: 1.0709 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:49:04] Epoch 1 | Step 7400 | Loss: 0.3641 | LM: 0.3559 | LB: 1.0709 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:49:11] Epoch 1 | Step 7410 | Loss: 0.3641 | LM: 0.3558 | LB: 1.0708 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:49:18] Epoch 1 | Step 7420 | Loss: 0.3641 | LM: 0.3559 | LB: 1.0708 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:49:25] Epoch 1 | Step 7430 | Loss: 0.3641 | LM: 0.3558 | LB: 1.0708 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:49:32] Epoch 1 | Step 7440 | Loss: 0.3640 | LM: 0.3558 | LB: 1.0708 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:49:39] Epoch 1 | Step 7450 | Loss: 0.3640 | LM: 0.3556 | LB: 1.0708 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:49:46] Epoch 1 | Step 7460 | Loss: 0.3639 | LM: 0.3555 | LB: 1.0708 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.379/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:49:53] Epoch 1 | Step 7470 | Loss: 0.3639 | LM: 0.3554 | LB: 1.0707 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:50:01] Epoch 1 | Step 7480 | Loss: 0.3639 | LM: 0.3553 | LB: 1.0707 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:50:08] Epoch 1 | Step 7490 | Loss: 0.3639 | LM: 0.3553 | LB: 1.0707 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:50:15] Epoch 1 | Step 7500 | Loss: 0.3639 | LM: 0.3554 | LB: 1.0707 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:50:22] Epoch 1 | Step 7510 | Loss: 0.3640 | LM: 0.3553 | LB: 1.0707 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:50:29] Epoch 1 | Step 7520 | Loss: 0.3639 | LM: 0.3553 | LB: 1.0707 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:50:36] Epoch 1 | Step 7530 | Loss: 0.3638 | LM: 0.3552 | LB: 1.0707 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:50:43] Epoch 1 | Step 7540 | Loss: 0.3638 | LM: 0.3551 | LB: 1.0707 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:50:50] Epoch 1 | Step 7550 | Loss: 0.3638 | LM: 0.3552 | LB: 1.0706 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:50:57] Epoch 1 | Step 7560 | Loss: 0.3637 | LM: 0.3550 | LB: 1.0706 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:51:04] Epoch 1 | Step 7570 | Loss: 0.3637 | LM: 0.3551 | LB: 1.0706 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:51:12] Epoch 1 | Step 7580 | Loss: 0.3637 | LM: 0.3551 | LB: 1.0706 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.371 | LR: 5.00e-05 |
| [2026-04-26 01:51:19] Epoch 1 | Step 7590 | Loss: 0.3637 | LM: 0.3550 | LB: 1.0706 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:51:26] Epoch 1 | Step 7600 | Loss: 0.3636 | LM: 0.3551 | LB: 1.0706 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:51:33] Epoch 1 | Step 7610 | Loss: 0.3636 | LM: 0.3552 | LB: 1.0706 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:51:40] Epoch 1 | Step 7620 | Loss: 0.3635 | LM: 0.3551 | LB: 1.0705 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:51:47] Epoch 1 | Step 7630 | Loss: 0.3635 | LM: 0.3550 | LB: 1.0705 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:51:54] Epoch 1 | Step 7640 | Loss: 0.3634 | LM: 0.3549 | LB: 1.0705 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:52:01] Epoch 1 | Step 7650 | Loss: 0.3634 | LM: 0.3548 | LB: 1.0705 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:52:08] Epoch 1 | Step 7660 | Loss: 0.3633 | LM: 0.3548 | LB: 1.0705 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:52:15] Epoch 1 | Step 7670 | Loss: 0.3633 | LM: 0.3547 | LB: 1.0705 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:52:22] Epoch 1 | Step 7680 | Loss: 0.3632 | LM: 0.3547 | LB: 1.0704 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:52:30] Epoch 1 | Step 7690 | Loss: 0.3632 | LM: 0.3547 | LB: 1.0704 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:52:37] Epoch 1 | Step 7700 | Loss: 0.3632 | LM: 0.3547 | LB: 1.0704 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:52:44] Epoch 1 | Step 7710 | Loss: 0.3631 | LM: 0.3545 | LB: 1.0704 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:52:51] Epoch 1 | Step 7720 | Loss: 0.3632 | LM: 0.3545 | LB: 1.0704 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:52:58] Epoch 1 | Step 7730 | Loss: 0.3632 | LM: 0.3545 | LB: 1.0704 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:53:05] Epoch 1 | Step 7740 | Loss: 0.3632 | LM: 0.3546 | LB: 1.0704 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:53:12] Epoch 1 | Step 7750 | Loss: 0.3632 | LM: 0.3546 | LB: 1.0704 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:53:19] Epoch 1 | Step 7760 | Loss: 0.3631 | LM: 0.3546 | LB: 1.0703 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:53:26] Epoch 1 | Step 7770 | Loss: 0.3631 | LM: 0.3544 | LB: 1.0703 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:53:33] Epoch 1 | Step 7780 | Loss: 0.3630 | LM: 0.3543 | LB: 1.0703 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:53:40] Epoch 1 | Step 7790 | Loss: 0.3630 | LM: 0.3543 | LB: 1.0703 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:53:47] Epoch 1 | Step 7800 | Loss: 0.3630 | LM: 0.3543 | LB: 1.0703 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:53:54] Epoch 1 | Step 7810 | Loss: 0.3630 | LM: 0.3543 | LB: 1.0703 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:54:02] Epoch 1 | Step 7820 | Loss: 0.3630 | LM: 0.3543 | LB: 1.0702 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:54:09] Epoch 1 | Step 7830 | Loss: 0.3629 | LM: 0.3543 | LB: 1.0702 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:54:16] Epoch 1 | Step 7840 | Loss: 0.3629 | LM: 0.3541 | LB: 1.0702 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:54:23] Epoch 1 | Step 7850 | Loss: 0.3628 | LM: 0.3540 | LB: 1.0702 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:54:30] Epoch 1 | Step 7860 | Loss: 0.3628 | LM: 0.3539 | LB: 1.0702 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:54:37] Epoch 1 | Step 7870 | Loss: 0.3627 | LM: 0.3539 | LB: 1.0701 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:54:44] Epoch 1 | Step 7880 | Loss: 0.3627 | LM: 0.3539 | LB: 1.0701 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:54:51] Epoch 1 | Step 7890 | Loss: 0.3627 | LM: 0.3538 | LB: 1.0701 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:54:58] Epoch 1 | Step 7900 | Loss: 0.3627 | LM: 0.3538 | LB: 1.0701 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:55:05] Epoch 1 | Step 7910 | Loss: 0.3627 | LM: 0.3539 | LB: 1.0701 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:55:12] Epoch 1 | Step 7920 | Loss: 0.3627 | LM: 0.3540 | LB: 1.0701 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:55:19] Epoch 1 | Step 7930 | Loss: 0.3627 | LM: 0.3540 | LB: 1.0700 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:55:26] Epoch 1 | Step 7940 | Loss: 0.3627 | LM: 0.3539 | LB: 1.0700 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:55:33] Epoch 1 | Step 7950 | Loss: 0.3627 | LM: 0.3540 | LB: 1.0700 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.378/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:55:41] Epoch 1 | Step 7960 | Loss: 0.3627 | LM: 0.3540 | LB: 1.0700 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:55:48] Epoch 1 | Step 7970 | Loss: 0.3627 | LM: 0.3540 | LB: 1.0700 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:55:55] Epoch 1 | Step 7980 | Loss: 0.3626 | LM: 0.3539 | LB: 1.0700 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:56:02] Epoch 1 | Step 7990 | Loss: 0.3626 | LM: 0.3539 | LB: 1.0700 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:56:09] Epoch 1 | Step 8000 | Loss: 0.3626 | LM: 0.3538 | LB: 1.0699 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:56:10] Validation | Batch 10/42 | Loss: 0.3336 | LM_LOSS: 0.3230 | LB_LOSS: 1.0526 |
| [2026-04-26 01:56:11] Validation | Batch 20/42 | Loss: 0.3531 | LM_LOSS: 0.3426 | LB_LOSS: 1.0564 |
| [2026-04-26 01:56:12] Validation | Batch 30/42 | Loss: 0.3430 | LM_LOSS: 0.3325 | LB_LOSS: 1.0553 |
| [2026-04-26 01:56:13] Validation | Batch 40/42 | Loss: 0.3490 | LM_LOSS: 0.3385 | LB_LOSS: 1.0550 |
| [2026-04-26 01:56:13] Validation | Batch 42/42 | Loss: 0.3487 | LM_LOSS: 0.3382 | LB_LOSS: 1.0553 |
| [2026-04-26 01:56:13] Validation | Loss: 0.3487 | LM_LOSS: 0.3382 | LB_LOSS: 1.0553 | PPL: 1.40 | Time: 4.52s |
| [2026-04-26 01:56:16] New best model saved! Val loss: 0.3487 |
| [2026-04-26 01:56:23] Epoch 1 | Step 8010 | Loss: 0.3625 | LM: 0.3537 | LB: 1.0699 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:56:31] Epoch 1 | Step 8020 | Loss: 0.3624 | LM: 0.3536 | LB: 1.0699 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:56:38] Epoch 1 | Step 8030 | Loss: 0.3624 | LM: 0.3534 | LB: 1.0699 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:56:45] Epoch 1 | Step 8040 | Loss: 0.3624 | LM: 0.3534 | LB: 1.0699 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:56:52] Epoch 1 | Step 8050 | Loss: 0.3623 | LM: 0.3532 | LB: 1.0699 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:56:59] Epoch 1 | Step 8060 | Loss: 0.3623 | LM: 0.3532 | LB: 1.0699 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:57:06] Epoch 1 | Step 8070 | Loss: 0.3622 | LM: 0.3531 | LB: 1.0699 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:57:13] Epoch 1 | Step 8080 | Loss: 0.3623 | LM: 0.3532 | LB: 1.0699 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:57:20] Epoch 1 | Step 8090 | Loss: 0.3622 | LM: 0.3531 | LB: 1.0699 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:57:27] Epoch 1 | Step 8100 | Loss: 0.3621 | LM: 0.3531 | LB: 1.0699 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:57:34] Epoch 1 | Step 8110 | Loss: 0.3622 | LM: 0.3531 | LB: 1.0698 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:57:41] Epoch 1 | Step 8120 | Loss: 0.3622 | LM: 0.3531 | LB: 1.0698 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:57:49] Epoch 1 | Step 8130 | Loss: 0.3621 | LM: 0.3531 | LB: 1.0698 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:57:56] Epoch 1 | Step 8140 | Loss: 0.3622 | LM: 0.3531 | LB: 1.0698 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:58:03] Epoch 1 | Step 8150 | Loss: 0.3622 | LM: 0.3531 | LB: 1.0698 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:58:10] Epoch 1 | Step 8160 | Loss: 0.3621 | LM: 0.3530 | LB: 1.0698 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.338 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:58:17] Epoch 1 | Step 8170 | Loss: 0.3621 | LM: 0.3529 | LB: 1.0698 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:58:24] Epoch 1 | Step 8180 | Loss: 0.3620 | LM: 0.3530 | LB: 1.0697 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:58:31] Epoch 1 | Step 8190 | Loss: 0.3620 | LM: 0.3530 | LB: 1.0697 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:58:38] Epoch 1 | Step 8200 | Loss: 0.3620 | LM: 0.3531 | LB: 1.0697 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:58:45] Epoch 1 | Step 8210 | Loss: 0.3620 | LM: 0.3530 | LB: 1.0697 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:58:52] Epoch 1 | Step 8220 | Loss: 0.3619 | LM: 0.3530 | LB: 1.0697 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.370 | LR: 5.00e-05 |
| [2026-04-26 01:58:59] Epoch 1 | Step 8230 | Loss: 0.3620 | LM: 0.3530 | LB: 1.0697 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 01:59:06] Epoch 1 | Step 8240 | Loss: 0.3620 | LM: 0.3530 | LB: 1.0696 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 01:59:13] Epoch 1 | Step 8250 | Loss: 0.3620 | LM: 0.3530 | LB: 1.0696 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 01:59:21] Epoch 1 | Step 8260 | Loss: 0.3620 | LM: 0.3530 | LB: 1.0696 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 01:59:28] Epoch 1 | Step 8270 | Loss: 0.3620 | LM: 0.3530 | LB: 1.0696 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 01:59:35] Epoch 1 | Step 8280 | Loss: 0.3620 | LM: 0.3529 | LB: 1.0696 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 01:59:42] Epoch 1 | Step 8290 | Loss: 0.3620 | LM: 0.3529 | LB: 1.0696 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 01:59:49] Epoch 1 | Step 8300 | Loss: 0.3620 | LM: 0.3528 | LB: 1.0696 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 01:59:56] Epoch 1 | Step 8310 | Loss: 0.3620 | LM: 0.3528 | LB: 1.0696 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:00:03] Epoch 1 | Step 8320 | Loss: 0.3620 | LM: 0.3527 | LB: 1.0695 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:00:10] Epoch 1 | Step 8330 | Loss: 0.3620 | LM: 0.3528 | LB: 1.0695 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:00:17] Epoch 1 | Step 8340 | Loss: 0.3619 | LM: 0.3529 | LB: 1.0695 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:00:25] Epoch 1 | Step 8350 | Loss: 0.3619 | LM: 0.3529 | LB: 1.0695 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:00:32] Epoch 1 | Step 8360 | Loss: 0.3618 | LM: 0.3529 | LB: 1.0695 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:00:39] Epoch 1 | Step 8370 | Loss: 0.3618 | LM: 0.3529 | LB: 1.0695 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:00:46] Epoch 1 | Step 8380 | Loss: 0.3618 | LM: 0.3528 | LB: 1.0695 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:00:53] Epoch 1 | Step 8390 | Loss: 0.3618 | LM: 0.3529 | LB: 1.0695 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:01:00] Epoch 1 | Step 8400 | Loss: 0.3618 | LM: 0.3528 | LB: 1.0694 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:01:07] Epoch 1 | Step 8410 | Loss: 0.3618 | LM: 0.3528 | LB: 1.0694 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:01:14] Epoch 1 | Step 8420 | Loss: 0.3618 | LM: 0.3528 | LB: 1.0694 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:01:22] Epoch 1 | Step 8430 | Loss: 0.3617 | LM: 0.3527 | LB: 1.0694 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:01:29] Epoch 1 | Step 8440 | Loss: 0.3617 | LM: 0.3527 | LB: 1.0694 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:01:36] Epoch 1 | Step 8450 | Loss: 0.3617 | LM: 0.3526 | LB: 1.0694 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:01:43] Epoch 1 | Step 8460 | Loss: 0.3617 | LM: 0.3527 | LB: 1.0693 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:01:50] Epoch 1 | Step 8470 | Loss: 0.3616 | LM: 0.3526 | LB: 1.0693 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:01:57] Epoch 1 | Step 8480 | Loss: 0.3616 | LM: 0.3526 | LB: 1.0693 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:02:04] Epoch 1 | Step 8490 | Loss: 0.3616 | LM: 0.3526 | LB: 1.0693 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:02:11] Epoch 1 | Step 8500 | Loss: 0.3616 | LM: 0.3526 | LB: 1.0693 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:02:19] Epoch 1 | Step 8510 | Loss: 0.3615 | LM: 0.3525 | LB: 1.0693 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:02:26] Epoch 1 | Step 8520 | Loss: 0.3615 | LM: 0.3524 | LB: 1.0693 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:02:33] Epoch 1 | Step 8530 | Loss: 0.3615 | LM: 0.3524 | LB: 1.0693 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:02:40] Epoch 1 | Step 8540 | Loss: 0.3615 | LM: 0.3525 | LB: 1.0693 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:02:47] Epoch 1 | Step 8550 | Loss: 0.3615 | LM: 0.3525 | LB: 1.0692 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:02:54] Epoch 1 | Step 8560 | Loss: 0.3615 | LM: 0.3524 | LB: 1.0692 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:03:01] Epoch 1 | Step 8570 | Loss: 0.3615 | LM: 0.3524 | LB: 1.0692 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.377/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:03:08] Epoch 1 | Step 8580 | Loss: 0.3614 | LM: 0.3523 | LB: 1.0692 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:03:15] Epoch 1 | Step 8590 | Loss: 0.3614 | LM: 0.3522 | LB: 1.0692 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:03:22] Epoch 1 | Step 8600 | Loss: 0.3613 | LM: 0.3521 | LB: 1.0691 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:03:30] Epoch 1 | Step 8610 | Loss: 0.3613 | LM: 0.3521 | LB: 1.0691 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:03:37] Epoch 1 | Step 8620 | Loss: 0.3613 | LM: 0.3520 | LB: 1.0691 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:03:44] Epoch 1 | Step 8630 | Loss: 0.3612 | LM: 0.3519 | LB: 1.0691 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:03:51] Epoch 1 | Step 8640 | Loss: 0.3612 | LM: 0.3520 | LB: 1.0691 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:03:58] Epoch 1 | Step 8650 | Loss: 0.3612 | LM: 0.3519 | LB: 1.0691 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:04:05] Epoch 1 | Step 8660 | Loss: 0.3612 | LM: 0.3518 | LB: 1.0691 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:04:12] Epoch 1 | Step 8670 | Loss: 0.3612 | LM: 0.3518 | LB: 1.0691 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:04:19] Epoch 1 | Step 8680 | Loss: 0.3612 | LM: 0.3518 | LB: 1.0691 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:04:26] Epoch 1 | Step 8690 | Loss: 0.3611 | LM: 0.3517 | LB: 1.0691 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:04:33] Epoch 1 | Step 8700 | Loss: 0.3611 | LM: 0.3517 | LB: 1.0691 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:04:41] Epoch 1 | Step 8710 | Loss: 0.3610 | LM: 0.3516 | LB: 1.0690 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:04:48] Epoch 1 | Step 8720 | Loss: 0.3610 | LM: 0.3516 | LB: 1.0690 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:04:55] Epoch 1 | Step 8730 | Loss: 0.3610 | LM: 0.3516 | LB: 1.0690 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:05:02] Epoch 1 | Step 8740 | Loss: 0.3610 | LM: 0.3516 | LB: 1.0690 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:05:09] Epoch 1 | Step 8750 | Loss: 0.3610 | LM: 0.3516 | LB: 1.0690 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:05:16] Epoch 1 | Step 8760 | Loss: 0.3609 | LM: 0.3517 | LB: 1.0690 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:05:23] Epoch 1 | Step 8770 | Loss: 0.3609 | LM: 0.3517 | LB: 1.0690 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:05:30] Epoch 1 | Step 8780 | Loss: 0.3608 | LM: 0.3517 | LB: 1.0690 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:05:37] Epoch 1 | Step 8790 | Loss: 0.3608 | LM: 0.3518 | LB: 1.0690 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:05:44] Epoch 1 | Step 8800 | Loss: 0.3608 | LM: 0.3517 | LB: 1.0689 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:05:51] Epoch 1 | Step 8810 | Loss: 0.3607 | LM: 0.3517 | LB: 1.0690 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:05:58] Epoch 1 | Step 8820 | Loss: 0.3607 | LM: 0.3517 | LB: 1.0689 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:06:05] Epoch 1 | Step 8830 | Loss: 0.3607 | LM: 0.3518 | LB: 1.0689 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:06:12] Epoch 1 | Step 8840 | Loss: 0.3606 | LM: 0.3518 | LB: 1.0689 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:06:20] Epoch 1 | Step 8850 | Loss: 0.3606 | LM: 0.3517 | LB: 1.0689 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:06:27] Epoch 1 | Step 8860 | Loss: 0.3606 | LM: 0.3517 | LB: 1.0689 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:06:34] Epoch 1 | Step 8870 | Loss: 0.3606 | LM: 0.3518 | LB: 1.0689 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:06:41] Epoch 1 | Step 8880 | Loss: 0.3606 | LM: 0.3517 | LB: 1.0689 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:06:48] Epoch 1 | Step 8890 | Loss: 0.3605 | LM: 0.3517 | LB: 1.0688 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:06:55] Epoch 1 | Step 8900 | Loss: 0.3604 | LM: 0.3516 | LB: 1.0688 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:07:02] Epoch 1 | Step 8910 | Loss: 0.3605 | LM: 0.3518 | LB: 1.0688 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:07:09] Epoch 1 | Step 8920 | Loss: 0.3604 | LM: 0.3516 | LB: 1.0688 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:07:17] Epoch 1 | Step 8930 | Loss: 0.3603 | LM: 0.3516 | LB: 1.0688 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:07:24] Epoch 1 | Step 8940 | Loss: 0.3603 | LM: 0.3516 | LB: 1.0688 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:07:31] Epoch 1 | Step 8950 | Loss: 0.3603 | LM: 0.3516 | LB: 1.0688 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.369 | LR: 5.00e-05 |
| [2026-04-26 02:07:38] Epoch 1 | Step 8960 | Loss: 0.3603 | LM: 0.3516 | LB: 1.0688 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:07:45] Epoch 1 | Step 8970 | Loss: 0.3603 | LM: 0.3516 | LB: 1.0688 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:07:52] Epoch 1 | Step 8980 | Loss: 0.3603 | LM: 0.3515 | LB: 1.0688 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:07:59] Epoch 1 | Step 8990 | Loss: 0.3602 | LM: 0.3514 | LB: 1.0688 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:08:06] Epoch 1 | Step 9000 | Loss: 0.3602 | LM: 0.3515 | LB: 1.0688 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:08:13] Epoch 1 | Step 9010 | Loss: 0.3602 | LM: 0.3514 | LB: 1.0687 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:08:20] Epoch 1 | Step 9020 | Loss: 0.3602 | LM: 0.3514 | LB: 1.0687 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:08:27] Epoch 1 | Step 9030 | Loss: 0.3602 | LM: 0.3514 | LB: 1.0687 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:08:34] Epoch 1 | Step 9040 | Loss: 0.3602 | LM: 0.3513 | LB: 1.0687 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:08:42] Epoch 1 | Step 9050 | Loss: 0.3601 | LM: 0.3513 | LB: 1.0687 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:08:49] Epoch 1 | Step 9060 | Loss: 0.3601 | LM: 0.3512 | LB: 1.0687 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:08:56] Epoch 1 | Step 9070 | Loss: 0.3601 | LM: 0.3512 | LB: 1.0687 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:09:03] Epoch 1 | Step 9080 | Loss: 0.3601 | LM: 0.3512 | LB: 1.0687 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:09:10] Epoch 1 | Step 9090 | Loss: 0.3601 | LM: 0.3511 | LB: 1.0687 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:09:17] Epoch 1 | Step 9100 | Loss: 0.3601 | LM: 0.3511 | LB: 1.0687 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:09:24] Epoch 1 | Step 9110 | Loss: 0.3600 | LM: 0.3511 | LB: 1.0687 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:09:31] Epoch 1 | Step 9120 | Loss: 0.3600 | LM: 0.3511 | LB: 1.0687 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:09:38] Epoch 1 | Step 9130 | Loss: 0.3600 | LM: 0.3511 | LB: 1.0687 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:09:45] Epoch 1 | Step 9140 | Loss: 0.3600 | LM: 0.3511 | LB: 1.0687 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:09:52] Epoch 1 | Step 9150 | Loss: 0.3600 | LM: 0.3510 | LB: 1.0687 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:10:00] Epoch 1 | Step 9160 | Loss: 0.3599 | LM: 0.3510 | LB: 1.0687 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:10:07] Epoch 1 | Step 9170 | Loss: 0.3598 | LM: 0.3509 | LB: 1.0686 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:10:14] Epoch 1 | Step 9180 | Loss: 0.3598 | LM: 0.3509 | LB: 1.0686 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:10:21] Epoch 1 | Step 9190 | Loss: 0.3597 | LM: 0.3508 | LB: 1.0686 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:10:28] Epoch 1 | Step 9200 | Loss: 0.3597 | LM: 0.3507 | LB: 1.0686 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:10:35] Epoch 1 | Step 9210 | Loss: 0.3597 | LM: 0.3507 | LB: 1.0686 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:10:42] Epoch 1 | Step 9220 | Loss: 0.3597 | LM: 0.3506 | LB: 1.0686 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:10:49] Epoch 1 | Step 9230 | Loss: 0.3597 | LM: 0.3506 | LB: 1.0686 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:10:56] Epoch 1 | Step 9240 | Loss: 0.3596 | LM: 0.3505 | LB: 1.0686 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:11:03] Epoch 1 | Step 9250 | Loss: 0.3596 | LM: 0.3504 | LB: 1.0686 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:11:10] Epoch 1 | Step 9260 | Loss: 0.3595 | LM: 0.3505 | LB: 1.0685 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:11:18] Epoch 1 | Step 9270 | Loss: 0.3595 | LM: 0.3504 | LB: 1.0685 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:11:25] Epoch 1 | Step 9280 | Loss: 0.3595 | LM: 0.3504 | LB: 1.0685 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:11:32] Epoch 1 | Step 9290 | Loss: 0.3595 | LM: 0.3504 | LB: 1.0685 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:11:39] Epoch 1 | Step 9300 | Loss: 0.3594 | LM: 0.3503 | LB: 1.0685 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:11:46] Epoch 1 | Step 9310 | Loss: 0.3594 | LM: 0.3503 | LB: 1.0685 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:11:53] Epoch 1 | Step 9320 | Loss: 0.3594 | LM: 0.3503 | LB: 1.0685 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:12:00] Epoch 1 | Step 9330 | Loss: 0.3594 | LM: 0.3503 | LB: 1.0685 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:12:07] Epoch 1 | Step 9340 | Loss: 0.3593 | LM: 0.3502 | LB: 1.0685 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:12:14] Epoch 1 | Step 9350 | Loss: 0.3593 | LM: 0.3502 | LB: 1.0685 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.376/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:12:21] Epoch 1 | Step 9360 | Loss: 0.3592 | LM: 0.3501 | LB: 1.0685 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:12:29] Epoch 1 | Step 9370 | Loss: 0.3592 | LM: 0.3500 | LB: 1.0685 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:12:36] Epoch 1 | Step 9380 | Loss: 0.3592 | LM: 0.3500 | LB: 1.0685 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:12:43] Epoch 1 | Step 9390 | Loss: 0.3591 | LM: 0.3499 | LB: 1.0685 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:12:50] Epoch 1 | Step 9400 | Loss: 0.3591 | LM: 0.3500 | LB: 1.0685 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:12:57] Epoch 1 | Step 9410 | Loss: 0.3591 | LM: 0.3500 | LB: 1.0684 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:13:04] Epoch 1 | Step 9420 | Loss: 0.3592 | LM: 0.3500 | LB: 1.0684 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:13:11] Epoch 1 | Step 9430 | Loss: 0.3592 | LM: 0.3500 | LB: 1.0684 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:13:18] Epoch 1 | Step 9440 | Loss: 0.3591 | LM: 0.3499 | LB: 1.0684 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:13:25] Epoch 1 | Step 9450 | Loss: 0.3591 | LM: 0.3499 | LB: 1.0684 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:13:32] Epoch 1 | Step 9460 | Loss: 0.3591 | LM: 0.3499 | LB: 1.0684 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:13:39] Epoch 1 | Step 9470 | Loss: 0.3590 | LM: 0.3498 | LB: 1.0684 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:13:46] Epoch 1 | Step 9480 | Loss: 0.3589 | LM: 0.3497 | LB: 1.0684 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:13:53] Epoch 1 | Step 9490 | Loss: 0.3589 | LM: 0.3497 | LB: 1.0684 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:14:00] Epoch 1 | Step 9500 | Loss: 0.3589 | LM: 0.3498 | LB: 1.0684 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:14:07] Epoch 1 | Step 9510 | Loss: 0.3589 | LM: 0.3498 | LB: 1.0684 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:14:14] Epoch 1 | Step 9520 | Loss: 0.3589 | LM: 0.3498 | LB: 1.0684 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:14:22] Epoch 1 | Step 9530 | Loss: 0.3589 | LM: 0.3498 | LB: 1.0684 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:14:29] Epoch 1 | Step 9540 | Loss: 0.3589 | LM: 0.3498 | LB: 1.0683 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:14:36] Epoch 1 | Step 9550 | Loss: 0.3589 | LM: 0.3498 | LB: 1.0683 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:14:43] Epoch 1 | Step 9560 | Loss: 0.3589 | LM: 0.3498 | LB: 1.0683 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:14:50] Epoch 1 | Step 9570 | Loss: 0.3589 | LM: 0.3497 | LB: 1.0683 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:14:57] Epoch 1 | Step 9580 | Loss: 0.3588 | LM: 0.3497 | LB: 1.0683 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:15:04] Epoch 1 | Step 9590 | Loss: 0.3588 | LM: 0.3497 | LB: 1.0683 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:15:11] Epoch 1 | Step 9600 | Loss: 0.3588 | LM: 0.3497 | LB: 1.0683 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:15:18] Epoch 1 | Step 9610 | Loss: 0.3587 | LM: 0.3496 | LB: 1.0683 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:15:25] Epoch 1 | Step 9620 | Loss: 0.3587 | LM: 0.3495 | LB: 1.0683 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:15:32] Epoch 1 | Step 9630 | Loss: 0.3588 | LM: 0.3495 | LB: 1.0683 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:15:39] Epoch 1 | Step 9640 | Loss: 0.3587 | LM: 0.3494 | LB: 1.0682 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:15:46] Epoch 1 | Step 9650 | Loss: 0.3587 | LM: 0.3494 | LB: 1.0683 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:15:53] Epoch 1 | Step 9660 | Loss: 0.3587 | LM: 0.3493 | LB: 1.0682 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:16:01] Epoch 1 | Step 9670 | Loss: 0.3587 | LM: 0.3493 | LB: 1.0682 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:16:08] Epoch 1 | Step 9680 | Loss: 0.3586 | LM: 0.3493 | LB: 1.0682 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:16:15] Epoch 1 | Step 9690 | Loss: 0.3586 | LM: 0.3492 | LB: 1.0682 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:16:22] Epoch 1 | Step 9700 | Loss: 0.3586 | LM: 0.3492 | LB: 1.0682 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:16:29] Epoch 1 | Step 9710 | Loss: 0.3586 | LM: 0.3491 | LB: 1.0682 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:16:36] Epoch 1 | Step 9720 | Loss: 0.3585 | LM: 0.3491 | LB: 1.0682 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:16:43] Epoch 1 | Step 9730 | Loss: 0.3585 | LM: 0.3491 | LB: 1.0682 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:16:50] Epoch 1 | Step 9740 | Loss: 0.3585 | LM: 0.3491 | LB: 1.0682 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:16:57] Epoch 1 | Step 9750 | Loss: 0.3585 | LM: 0.3490 | LB: 1.0682 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:17:04] Epoch 1 | Step 9760 | Loss: 0.3584 | LM: 0.3490 | LB: 1.0682 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:17:11] Epoch 1 | Step 9770 | Loss: 0.3584 | LM: 0.3489 | LB: 1.0682 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:17:18] Epoch 1 | Step 9780 | Loss: 0.3584 | LM: 0.3489 | LB: 1.0682 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:17:25] Epoch 1 | Step 9790 | Loss: 0.3584 | LM: 0.3489 | LB: 1.0681 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:17:32] Epoch 1 | Step 9800 | Loss: 0.3583 | LM: 0.3489 | LB: 1.0681 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:17:39] Epoch 1 | Step 9810 | Loss: 0.3583 | LM: 0.3489 | LB: 1.0681 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:17:46] Epoch 1 | Step 9820 | Loss: 0.3583 | LM: 0.3488 | LB: 1.0681 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:17:54] Epoch 1 | Step 9830 | Loss: 0.3582 | LM: 0.3488 | LB: 1.0681 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:18:01] Epoch 1 | Step 9840 | Loss: 0.3583 | LM: 0.3487 | LB: 1.0681 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:18:08] Epoch 1 | Step 9850 | Loss: 0.3582 | LM: 0.3487 | LB: 1.0681 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:18:15] Epoch 1 | Step 9860 | Loss: 0.3582 | LM: 0.3488 | LB: 1.0681 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:18:22] Epoch 1 | Step 9870 | Loss: 0.3582 | LM: 0.3488 | LB: 1.0681 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:18:29] Epoch 1 | Step 9880 | Loss: 0.3582 | LM: 0.3488 | LB: 1.0681 | CL0: 2.9 | CL1: 2.7 | HR0: 0.351/SR0: 0.337 | HR1: 0.375/SR1: 0.368 | LR: 5.00e-05 |
| [2026-04-26 02:18:35] Epoch 1 completed in 7083.67s | Loss: 0.3582 | CL0: 2.9 | CL1: 2.7 |
| [2026-04-26 02:18:35] |
| Training completed! |
| [2026-04-26 02:18:37] Final model: /workspace/byte-llms-code/outputs/lr_sweep/hnet_xl_code_lr_5e-4/model_final.pt |
|
|