narySt's picture
Add files using upload-large-folder tool
a0cf2a5 verified
Raw
History Blame Contribute Delete
450 kB
[2026-05-24 11:17:08] CUDA_VISIBLE_DEVICES: 0
[2026-05-24 11:17:08] Number of processes: 1
[2026-05-24 11:17:08] Mixed precision: bf16
[2026-05-24 11:17:08] ============================================================
[2026-05-24 11:17:08] Routing Evolution Experiment | N=8.0
[2026-05-24 11:17:08] ============================================================
[2026-05-24 11:17:08] Config:
model:
config_path: /workspace/byte-llms-code/hnet_project/configs/hnet_2stage_XL_code.json
checkpoint_path: /workspace/byte-llms-code/hnet_project/checkpoints/hnet_2stage_XL_code.pt
training:
epochs: 3
max_steps: null
batch_size: 8
eval_batch_size: 24
gradient_accumulation_steps: 4
lr: 0.0001
weight_decay: 0.1
betas:
- 0.9
- 0.95
eps: 1.0e-08
lr_scheduler: wsd
warmup_ratio: 0.1
decay_ratio: 0.2
warmup_steps: 100
min_lr_ratio: 0.1
lr_multiplier:
- 2.0
- 1.5
- 1.0
load_balancing_weight: 0.5
load_balancing_N: 8.0
max_grad_norm: 1.0
use_amp: true
resume: false
resume_checkpoint: null
warmup_model: true
data:
path: /workspace/byte-llms-code/code_completion_exp/datasets/data_V4_full
max_context_len: 4096
max_target_len: 256
num_workers: 0
pin_memory: true
max_train_samples: 150000
max_val_samples: null
logging:
log_interval: 10
save_interval: 3000
eval_interval: 1000
save_every_epoch: false
model_only_checkpoints: true
tracking:
enabled: true
backend: wandb
project: routing-evolution
run_name: routing_N8.0
entity: null
base_url: https://wandb.platun0v.ru
local_dir: outputs/2026-05-24/N_8.0
paths:
output_dir: outputs/2026-05-24/N_8.0
seed: 42
device: cuda
[2026-05-24 11:17:11] Loading model...
[2026-05-24 11:17:16] Loaded pretrained: /workspace/byte-llms-code/hnet_project/checkpoints/hnet_2stage_XL_code.pt
[2026-05-24 11:17:17] Applied LR multipliers: [2.0, 1.5, 1.0]
[2026-05-24 11:17:17] Warming up model...
[2026-05-24 11:18:03] Total params: 1,654,090,112
[2026-05-24 11:18:03] Trainable params: 1,654,090,112
[2026-05-24 11:18:03] Creating dataloaders...
[2026-05-24 11:18:03] Train dataset size: 150000 (max_train_samples=150000) | Epochs: 3
[2026-05-24 11:18:03] Max steps: 14062, Steps per epoch: 18750
[2026-05-24 11:18:03] Starting training...
[2026-05-24 11:18:03]
============================================================
[2026-05-24 11:18:03] EPOCH 1/3 (step 0)
[2026-05-24 11:18:03] ============================================================
[2026-05-24 11:18:38] Epoch 1 | Step 10 | Loss: 1.5086 | LM: 0.6793 | LB: 1.7564 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.354 | HR1: 0.470/SR1: 0.448 | LR: 1.06e-05
[2026-05-24 11:18:50] Epoch 1 | Step 20 | Loss: 1.5035 | LM: 0.6312 | LB: 1.7635 | CL0: 2.8 | CL1: 2.1 | HR0: 0.355/SR0: 0.354 | HR1: 0.473/SR1: 0.451 | LR: 1.13e-05
[2026-05-24 11:19:02] Epoch 1 | Step 30 | Loss: 1.4908 | LM: 0.6222 | LB: 1.7533 | CL0: 2.9 | CL1: 2.1 | HR0: 0.350/SR0: 0.350 | HR1: 0.473/SR1: 0.450 | LR: 1.19e-05
[2026-05-24 11:19:15] Epoch 1 | Step 40 | Loss: 1.4835 | LM: 0.6124 | LB: 1.7629 | CL0: 2.9 | CL1: 2.1 | HR0: 0.352/SR0: 0.351 | HR1: 0.474/SR1: 0.452 | LR: 1.26e-05
[2026-05-24 11:19:27] Epoch 1 | Step 50 | Loss: 1.4638 | LM: 0.5956 | LB: 1.7561 | CL0: 2.9 | CL1: 2.1 | HR0: 0.352/SR0: 0.351 | HR1: 0.472/SR1: 0.450 | LR: 1.32e-05
[2026-05-24 11:19:38] Epoch 1 | Step 60 | Loss: 1.4418 | LM: 0.5733 | LB: 1.7613 | CL0: 2.9 | CL1: 2.1 | HR0: 0.352/SR0: 0.351 | HR1: 0.474/SR1: 0.451 | LR: 1.38e-05
[2026-05-24 11:19:50] Epoch 1 | Step 70 | Loss: 1.4292 | LM: 0.5543 | LB: 1.7564 | CL0: 2.9 | CL1: 2.1 | HR0: 0.352/SR0: 0.351 | HR1: 0.473/SR1: 0.450 | LR: 1.45e-05
[2026-05-24 11:20:02] Epoch 1 | Step 80 | Loss: 1.4109 | LM: 0.5301 | LB: 1.7566 | CL0: 2.8 | CL1: 2.1 | HR0: 0.353/SR0: 0.352 | HR1: 0.472/SR1: 0.450 | LR: 1.51e-05
[2026-05-24 11:20:13] Epoch 1 | Step 90 | Loss: 1.4014 | LM: 0.5225 | LB: 1.7575 | CL0: 2.8 | CL1: 2.1 | HR0: 0.353/SR0: 0.352 | HR1: 0.472/SR1: 0.450 | LR: 1.58e-05
[2026-05-24 11:20:25] Epoch 1 | Step 100 | Loss: 1.3862 | LM: 0.5097 | LB: 1.7571 | CL0: 2.8 | CL1: 2.1 | HR0: 0.353/SR0: 0.352 | HR1: 0.472/SR1: 0.450 | LR: 1.64e-05
[2026-05-24 11:20:37] Epoch 1 | Step 110 | Loss: 1.3763 | LM: 0.4952 | LB: 1.7563 | CL0: 2.8 | CL1: 2.1 | HR0: 0.354/SR0: 0.353 | HR1: 0.471/SR1: 0.449 | LR: 1.70e-05
[2026-05-24 11:20:50] Epoch 1 | Step 120 | Loss: 1.3659 | LM: 0.4884 | LB: 1.7567 | CL0: 2.8 | CL1: 2.1 | HR0: 0.354/SR0: 0.353 | HR1: 0.472/SR1: 0.449 | LR: 1.77e-05
[2026-05-24 11:21:02] Epoch 1 | Step 130 | Loss: 1.3532 | LM: 0.4763 | LB: 1.7520 | CL0: 2.8 | CL1: 2.1 | HR0: 0.354/SR0: 0.353 | HR1: 0.470/SR1: 0.447 | LR: 1.83e-05
[2026-05-24 11:21:13] Epoch 1 | Step 140 | Loss: 1.3433 | LM: 0.4625 | LB: 1.7495 | CL0: 2.8 | CL1: 2.1 | HR0: 0.355/SR0: 0.354 | HR1: 0.468/SR1: 0.446 | LR: 1.90e-05
[2026-05-24 11:21:25] Epoch 1 | Step 150 | Loss: 1.3329 | LM: 0.4544 | LB: 1.7476 | CL0: 2.8 | CL1: 2.1 | HR0: 0.356/SR0: 0.354 | HR1: 0.467/SR1: 0.445 | LR: 1.96e-05
[2026-05-24 11:21:37] Epoch 1 | Step 160 | Loss: 1.3254 | LM: 0.4525 | LB: 1.7423 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.354 | HR1: 0.466/SR1: 0.444 | LR: 2.02e-05
[2026-05-24 11:21:50] Epoch 1 | Step 170 | Loss: 1.3171 | LM: 0.4462 | LB: 1.7397 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.465/SR1: 0.443 | LR: 2.09e-05
[2026-05-24 11:22:02] Epoch 1 | Step 180 | Loss: 1.3070 | LM: 0.4399 | LB: 1.7335 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.463/SR1: 0.441 | LR: 2.15e-05
[2026-05-24 11:22:14] Epoch 1 | Step 190 | Loss: 1.3005 | LM: 0.4349 | LB: 1.7316 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.462/SR1: 0.440 | LR: 2.22e-05
[2026-05-24 11:22:26] Epoch 1 | Step 200 | Loss: 1.2947 | LM: 0.4315 | LB: 1.7268 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.353 | HR1: 0.461/SR1: 0.439 | LR: 2.28e-05
[2026-05-24 11:22:38] Epoch 1 | Step 210 | Loss: 1.2880 | LM: 0.4249 | LB: 1.7234 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.353 | HR1: 0.460/SR1: 0.438 | LR: 2.34e-05
[2026-05-24 11:22:50] Epoch 1 | Step 220 | Loss: 1.2832 | LM: 0.4232 | LB: 1.7204 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.459/SR1: 0.437 | LR: 2.41e-05
[2026-05-24 11:23:02] Epoch 1 | Step 230 | Loss: 1.2761 | LM: 0.4190 | LB: 1.7171 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.457/SR1: 0.435 | LR: 2.47e-05
[2026-05-24 11:23:13] Epoch 1 | Step 240 | Loss: 1.2715 | LM: 0.4182 | LB: 1.7135 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.456/SR1: 0.434 | LR: 2.54e-05
[2026-05-24 11:23:25] Epoch 1 | Step 250 | Loss: 1.2653 | LM: 0.4143 | LB: 1.7095 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.353 | HR1: 0.455/SR1: 0.433 | LR: 2.60e-05
[2026-05-24 11:23:37] Epoch 1 | Step 260 | Loss: 1.2601 | LM: 0.4100 | LB: 1.7057 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.352 | HR1: 0.454/SR1: 0.432 | LR: 2.66e-05
[2026-05-24 11:23:49] Epoch 1 | Step 270 | Loss: 1.2554 | LM: 0.4071 | LB: 1.7017 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.352 | HR1: 0.453/SR1: 0.431 | LR: 2.73e-05
[2026-05-24 11:24:02] Epoch 1 | Step 280 | Loss: 1.2504 | LM: 0.4023 | LB: 1.6986 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.352 | HR1: 0.451/SR1: 0.429 | LR: 2.79e-05
[2026-05-24 11:24:14] Epoch 1 | Step 290 | Loss: 1.2467 | LM: 0.4010 | LB: 1.6946 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.450/SR1: 0.428 | LR: 2.86e-05
[2026-05-24 11:24:27] Epoch 1 | Step 300 | Loss: 1.2434 | LM: 0.4000 | LB: 1.6910 | CL0: 2.8 | CL1: 2.2 | HR0: 0.355/SR0: 0.353 | HR1: 0.449/SR1: 0.426 | LR: 2.92e-05
[2026-05-24 11:24:39] Epoch 1 | Step 310 | Loss: 1.2389 | LM: 0.3972 | LB: 1.6868 | CL0: 2.8 | CL1: 2.2 | HR0: 0.354/SR0: 0.352 | HR1: 0.447/SR1: 0.425 | LR: 2.98e-05
[2026-05-24 11:24:51] Epoch 1 | Step 320 | Loss: 1.2351 | LM: 0.3954 | LB: 1.6834 | CL0: 2.8 | CL1: 2.3 | HR0: 0.354/SR0: 0.352 | HR1: 0.446/SR1: 0.424 | LR: 3.05e-05
[2026-05-24 11:25:03] Epoch 1 | Step 330 | Loss: 1.2318 | LM: 0.3951 | LB: 1.6800 | CL0: 2.8 | CL1: 2.3 | HR0: 0.354/SR0: 0.352 | HR1: 0.445/SR1: 0.422 | LR: 3.11e-05
[2026-05-24 11:25:14] Epoch 1 | Step 340 | Loss: 1.2268 | LM: 0.3918 | LB: 1.6768 | CL0: 2.8 | CL1: 2.3 | HR0: 0.354/SR0: 0.352 | HR1: 0.444/SR1: 0.421 | LR: 3.18e-05
[2026-05-24 11:25:25] Epoch 1 | Step 350 | Loss: 1.2231 | LM: 0.3914 | LB: 1.6723 | CL0: 2.8 | CL1: 2.3 | HR0: 0.354/SR0: 0.352 | HR1: 0.442/SR1: 0.419 | LR: 3.24e-05
[2026-05-24 11:25:37] Epoch 1 | Step 360 | Loss: 1.2195 | LM: 0.3897 | LB: 1.6680 | CL0: 2.8 | CL1: 2.3 | HR0: 0.354/SR0: 0.352 | HR1: 0.441/SR1: 0.418 | LR: 3.30e-05
[2026-05-24 11:25:48] Epoch 1 | Step 370 | Loss: 1.2157 | LM: 0.3877 | LB: 1.6638 | CL0: 2.8 | CL1: 2.3 | HR0: 0.355/SR0: 0.352 | HR1: 0.439/SR1: 0.416 | LR: 3.37e-05
[2026-05-24 11:25:59] Epoch 1 | Step 380 | Loss: 1.2111 | LM: 0.3854 | LB: 1.6586 | CL0: 2.8 | CL1: 2.3 | HR0: 0.355/SR0: 0.352 | HR1: 0.437/SR1: 0.413 | LR: 3.43e-05
[2026-05-24 11:26:10] Epoch 1 | Step 390 | Loss: 1.2065 | LM: 0.3827 | LB: 1.6531 | CL0: 2.8 | CL1: 2.3 | HR0: 0.355/SR0: 0.352 | HR1: 0.435/SR1: 0.411 | LR: 3.50e-05
[2026-05-24 11:26:21] Epoch 1 | Step 400 | Loss: 1.2028 | LM: 0.3823 | LB: 1.6468 | CL0: 2.8 | CL1: 2.3 | HR0: 0.354/SR0: 0.352 | HR1: 0.432/SR1: 0.409 | LR: 3.56e-05
[2026-05-24 11:26:32] Epoch 1 | Step 410 | Loss: 1.1991 | LM: 0.3829 | LB: 1.6408 | CL0: 2.8 | CL1: 2.4 | HR0: 0.355/SR0: 0.352 | HR1: 0.429/SR1: 0.406 | LR: 3.62e-05
[2026-05-24 11:26:44] Epoch 1 | Step 420 | Loss: 1.1957 | LM: 0.3821 | LB: 1.6344 | CL0: 2.8 | CL1: 2.4 | HR0: 0.355/SR0: 0.352 | HR1: 0.427/SR1: 0.403 | LR: 3.69e-05
[2026-05-24 11:26:55] Epoch 1 | Step 430 | Loss: 1.1926 | LM: 0.3830 | LB: 1.6277 | CL0: 2.8 | CL1: 2.4 | HR0: 0.355/SR0: 0.352 | HR1: 0.423/SR1: 0.400 | LR: 3.75e-05
[2026-05-24 11:27:06] Epoch 1 | Step 440 | Loss: 1.1884 | LM: 0.3807 | LB: 1.6212 | CL0: 2.8 | CL1: 2.4 | HR0: 0.354/SR0: 0.352 | HR1: 0.421/SR1: 0.397 | LR: 3.82e-05
[2026-05-24 11:27:17] Epoch 1 | Step 450 | Loss: 1.1842 | LM: 0.3798 | LB: 1.6151 | CL0: 2.8 | CL1: 2.4 | HR0: 0.354/SR0: 0.352 | HR1: 0.418/SR1: 0.394 | LR: 3.88e-05
[2026-05-24 11:27:28] Epoch 1 | Step 460 | Loss: 1.1808 | LM: 0.3794 | LB: 1.6089 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.352 | HR1: 0.414/SR1: 0.390 | LR: 3.94e-05
[2026-05-24 11:27:40] Epoch 1 | Step 470 | Loss: 1.1775 | LM: 0.3787 | LB: 1.6024 | CL0: 2.8 | CL1: 2.5 | HR0: 0.354/SR0: 0.352 | HR1: 0.411/SR1: 0.387 | LR: 4.01e-05
[2026-05-24 11:27:51] Epoch 1 | Step 480 | Loss: 1.1736 | LM: 0.3772 | LB: 1.5961 | CL0: 2.8 | CL1: 2.5 | HR0: 0.355/SR0: 0.352 | HR1: 0.408/SR1: 0.384 | LR: 4.07e-05
[2026-05-24 11:28:02] Epoch 1 | Step 490 | Loss: 1.1697 | LM: 0.3781 | LB: 1.5901 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.352 | HR1: 0.405/SR1: 0.381 | LR: 4.14e-05
[2026-05-24 11:28:14] Epoch 1 | Step 500 | Loss: 1.1669 | LM: 0.3778 | LB: 1.5848 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.352 | HR1: 0.401/SR1: 0.378 | LR: 4.20e-05
[2026-05-24 11:28:25] Epoch 1 | Step 510 | Loss: 1.1643 | LM: 0.3780 | LB: 1.5795 | CL0: 2.8 | CL1: 2.6 | HR0: 0.355/SR0: 0.352 | HR1: 0.398/SR1: 0.375 | LR: 4.26e-05
[2026-05-24 11:28:36] Epoch 1 | Step 520 | Loss: 1.1611 | LM: 0.3766 | LB: 1.5743 | CL0: 2.8 | CL1: 2.7 | HR0: 0.355/SR0: 0.352 | HR1: 0.395/SR1: 0.372 | LR: 4.33e-05
[2026-05-24 11:28:47] Epoch 1 | Step 530 | Loss: 1.1580 | LM: 0.3763 | LB: 1.5687 | CL0: 2.8 | CL1: 2.7 | HR0: 0.355/SR0: 0.352 | HR1: 0.393/SR1: 0.369 | LR: 4.39e-05
[2026-05-24 11:28:59] Epoch 1 | Step 540 | Loss: 1.1541 | LM: 0.3752 | LB: 1.5634 | CL0: 2.8 | CL1: 2.7 | HR0: 0.355/SR0: 0.352 | HR1: 0.390/SR1: 0.366 | LR: 4.46e-05
[2026-05-24 11:29:10] Epoch 1 | Step 550 | Loss: 1.1506 | LM: 0.3739 | LB: 1.5577 | CL0: 2.8 | CL1: 2.7 | HR0: 0.355/SR0: 0.351 | HR1: 0.387/SR1: 0.363 | LR: 4.52e-05
[2026-05-24 11:29:21] Epoch 1 | Step 560 | Loss: 1.1478 | LM: 0.3733 | LB: 1.5524 | CL0: 2.8 | CL1: 2.8 | HR0: 0.355/SR0: 0.351 | HR1: 0.384/SR1: 0.360 | LR: 4.58e-05
[2026-05-24 11:29:32] Epoch 1 | Step 570 | Loss: 1.1457 | LM: 0.3734 | LB: 1.5479 | CL0: 2.8 | CL1: 2.8 | HR0: 0.355/SR0: 0.351 | HR1: 0.382/SR1: 0.358 | LR: 4.65e-05
[2026-05-24 11:29:44] Epoch 1 | Step 580 | Loss: 1.1436 | LM: 0.3747 | LB: 1.5433 | CL0: 2.8 | CL1: 2.8 | HR0: 0.355/SR0: 0.351 | HR1: 0.379/SR1: 0.355 | LR: 4.71e-05
[2026-05-24 11:29:56] Epoch 1 | Step 590 | Loss: 1.1412 | LM: 0.3735 | LB: 1.5385 | CL0: 2.8 | CL1: 2.8 | HR0: 0.354/SR0: 0.351 | HR1: 0.377/SR1: 0.353 | LR: 4.78e-05
[2026-05-24 11:30:07] Epoch 1 | Step 600 | Loss: 1.1391 | LM: 0.3739 | LB: 1.5339 | CL0: 2.8 | CL1: 2.9 | HR0: 0.354/SR0: 0.351 | HR1: 0.375/SR1: 0.351 | LR: 4.84e-05
[2026-05-24 11:30:18] Epoch 1 | Step 610 | Loss: 1.1363 | LM: 0.3733 | LB: 1.5297 | CL0: 2.8 | CL1: 2.9 | HR0: 0.354/SR0: 0.351 | HR1: 0.372/SR1: 0.348 | LR: 4.90e-05
[2026-05-24 11:30:29] Epoch 1 | Step 620 | Loss: 1.1337 | LM: 0.3724 | LB: 1.5253 | CL0: 2.8 | CL1: 2.9 | HR0: 0.354/SR0: 0.351 | HR1: 0.370/SR1: 0.346 | LR: 4.97e-05
[2026-05-24 11:30:40] Epoch 1 | Step 630 | Loss: 1.1312 | LM: 0.3721 | LB: 1.5218 | CL0: 2.8 | CL1: 2.9 | HR0: 0.354/SR0: 0.351 | HR1: 0.368/SR1: 0.344 | LR: 5.03e-05
[2026-05-24 11:30:52] Epoch 1 | Step 640 | Loss: 1.1289 | LM: 0.3725 | LB: 1.5179 | CL0: 2.8 | CL1: 3.0 | HR0: 0.354/SR0: 0.351 | HR1: 0.366/SR1: 0.341 | LR: 5.10e-05
[2026-05-24 11:31:03] Epoch 1 | Step 650 | Loss: 1.1266 | LM: 0.3716 | LB: 1.5143 | CL0: 2.8 | CL1: 3.0 | HR0: 0.355/SR0: 0.351 | HR1: 0.363/SR1: 0.339 | LR: 5.16e-05
[2026-05-24 11:31:14] Epoch 1 | Step 660 | Loss: 1.1248 | LM: 0.3719 | LB: 1.5104 | CL0: 2.8 | CL1: 3.0 | HR0: 0.354/SR0: 0.351 | HR1: 0.361/SR1: 0.337 | LR: 5.22e-05
[2026-05-24 11:31:25] Epoch 1 | Step 670 | Loss: 1.1228 | LM: 0.3722 | LB: 1.5066 | CL0: 2.8 | CL1: 3.0 | HR0: 0.354/SR0: 0.350 | HR1: 0.359/SR1: 0.335 | LR: 5.29e-05
[2026-05-24 11:31:36] Epoch 1 | Step 680 | Loss: 1.1204 | LM: 0.3724 | LB: 1.5029 | CL0: 2.8 | CL1: 3.1 | HR0: 0.354/SR0: 0.350 | HR1: 0.357/SR1: 0.333 | LR: 5.35e-05
[2026-05-24 11:31:47] Epoch 1 | Step 690 | Loss: 1.1191 | LM: 0.3722 | LB: 1.4993 | CL0: 2.8 | CL1: 3.1 | HR0: 0.354/SR0: 0.350 | HR1: 0.354/SR1: 0.330 | LR: 5.42e-05
[2026-05-24 11:31:58] Epoch 1 | Step 700 | Loss: 1.1169 | LM: 0.3712 | LB: 1.4956 | CL0: 2.8 | CL1: 3.1 | HR0: 0.354/SR0: 0.350 | HR1: 0.353/SR1: 0.328 | LR: 5.48e-05
[2026-05-24 11:32:09] Epoch 1 | Step 710 | Loss: 1.1150 | LM: 0.3709 | LB: 1.4922 | CL0: 2.8 | CL1: 3.1 | HR0: 0.354/SR0: 0.350 | HR1: 0.351/SR1: 0.327 | LR: 5.54e-05
[2026-05-24 11:32:20] Epoch 1 | Step 720 | Loss: 1.1131 | LM: 0.3707 | LB: 1.4890 | CL0: 2.8 | CL1: 3.2 | HR0: 0.354/SR0: 0.350 | HR1: 0.349/SR1: 0.325 | LR: 5.61e-05
[2026-05-24 11:32:32] Epoch 1 | Step 730 | Loss: 1.1119 | LM: 0.3712 | LB: 1.4856 | CL0: 2.8 | CL1: 3.2 | HR0: 0.354/SR0: 0.350 | HR1: 0.347/SR1: 0.323 | LR: 5.67e-05
[2026-05-24 11:32:43] Epoch 1 | Step 740 | Loss: 1.1099 | LM: 0.3706 | LB: 1.4823 | CL0: 2.8 | CL1: 3.2 | HR0: 0.354/SR0: 0.349 | HR1: 0.345/SR1: 0.321 | LR: 5.74e-05
[2026-05-24 11:32:53] Epoch 1 | Step 750 | Loss: 1.1084 | LM: 0.3706 | LB: 1.4788 | CL0: 2.8 | CL1: 3.2 | HR0: 0.354/SR0: 0.349 | HR1: 0.343/SR1: 0.319 | LR: 5.80e-05
[2026-05-24 11:33:05] Epoch 1 | Step 760 | Loss: 1.1070 | LM: 0.3707 | LB: 1.4759 | CL0: 2.8 | CL1: 3.3 | HR0: 0.353/SR0: 0.349 | HR1: 0.341/SR1: 0.318 | LR: 5.86e-05
[2026-05-24 11:33:16] Epoch 1 | Step 770 | Loss: 1.1045 | LM: 0.3699 | LB: 1.4730 | CL0: 2.8 | CL1: 3.3 | HR0: 0.353/SR0: 0.349 | HR1: 0.340/SR1: 0.316 | LR: 5.93e-05
[2026-05-24 11:33:27] Epoch 1 | Step 780 | Loss: 1.1027 | LM: 0.3693 | LB: 1.4699 | CL0: 2.8 | CL1: 3.3 | HR0: 0.353/SR0: 0.349 | HR1: 0.338/SR1: 0.314 | LR: 5.99e-05
[2026-05-24 11:33:38] Epoch 1 | Step 790 | Loss: 1.1010 | LM: 0.3691 | LB: 1.4671 | CL0: 2.8 | CL1: 3.3 | HR0: 0.353/SR0: 0.349 | HR1: 0.337/SR1: 0.313 | LR: 6.06e-05
[2026-05-24 11:33:51] Epoch 1 | Step 800 | Loss: 1.0999 | LM: 0.3696 | LB: 1.4644 | CL0: 2.8 | CL1: 3.3 | HR0: 0.353/SR0: 0.349 | HR1: 0.335/SR1: 0.311 | LR: 6.12e-05
[2026-05-24 11:34:02] Epoch 1 | Step 810 | Loss: 1.0987 | LM: 0.3703 | LB: 1.4616 | CL0: 2.8 | CL1: 3.4 | HR0: 0.353/SR0: 0.348 | HR1: 0.333/SR1: 0.309 | LR: 6.18e-05
[2026-05-24 11:34:14] Epoch 1 | Step 820 | Loss: 1.0978 | LM: 0.3707 | LB: 1.4590 | CL0: 2.8 | CL1: 3.4 | HR0: 0.353/SR0: 0.348 | HR1: 0.331/SR1: 0.307 | LR: 6.25e-05
[2026-05-24 11:34:25] Epoch 1 | Step 830 | Loss: 1.0962 | LM: 0.3705 | LB: 1.4563 | CL0: 2.8 | CL1: 3.4 | HR0: 0.353/SR0: 0.348 | HR1: 0.330/SR1: 0.306 | LR: 6.31e-05
[2026-05-24 11:34:37] Epoch 1 | Step 840 | Loss: 1.0947 | LM: 0.3704 | LB: 1.4537 | CL0: 2.8 | CL1: 3.4 | HR0: 0.353/SR0: 0.348 | HR1: 0.328/SR1: 0.304 | LR: 6.38e-05
[2026-05-24 11:34:49] Epoch 1 | Step 850 | Loss: 1.0938 | LM: 0.3706 | LB: 1.4508 | CL0: 2.8 | CL1: 3.4 | HR0: 0.353/SR0: 0.348 | HR1: 0.327/SR1: 0.303 | LR: 6.44e-05
[2026-05-24 11:34:59] Epoch 1 | Step 860 | Loss: 1.0924 | LM: 0.3706 | LB: 1.4484 | CL0: 2.8 | CL1: 3.5 | HR0: 0.353/SR0: 0.348 | HR1: 0.325/SR1: 0.301 | LR: 6.50e-05
[2026-05-24 11:35:10] Epoch 1 | Step 870 | Loss: 1.0909 | LM: 0.3698 | LB: 1.4461 | CL0: 2.8 | CL1: 3.5 | HR0: 0.353/SR0: 0.348 | HR1: 0.324/SR1: 0.300 | LR: 6.57e-05
[2026-05-24 11:35:22] Epoch 1 | Step 880 | Loss: 1.0894 | LM: 0.3695 | LB: 1.4433 | CL0: 2.8 | CL1: 3.5 | HR0: 0.353/SR0: 0.347 | HR1: 0.322/SR1: 0.298 | LR: 6.63e-05
[2026-05-24 11:35:33] Epoch 1 | Step 890 | Loss: 1.0885 | LM: 0.3697 | LB: 1.4408 | CL0: 2.9 | CL1: 3.5 | HR0: 0.352/SR0: 0.347 | HR1: 0.320/SR1: 0.297 | LR: 6.70e-05
[2026-05-24 11:35:43] Epoch 1 | Step 900 | Loss: 1.0869 | LM: 0.3687 | LB: 1.4385 | CL0: 2.9 | CL1: 3.6 | HR0: 0.352/SR0: 0.347 | HR1: 0.319/SR1: 0.295 | LR: 6.76e-05
[2026-05-24 11:35:55] Epoch 1 | Step 910 | Loss: 1.0856 | LM: 0.3685 | LB: 1.4364 | CL0: 2.9 | CL1: 3.6 | HR0: 0.352/SR0: 0.347 | HR1: 0.318/SR1: 0.294 | LR: 6.83e-05
[2026-05-24 11:36:05] Epoch 1 | Step 920 | Loss: 1.0843 | LM: 0.3685 | LB: 1.4341 | CL0: 2.9 | CL1: 3.6 | HR0: 0.352/SR0: 0.347 | HR1: 0.316/SR1: 0.293 | LR: 6.89e-05
[2026-05-24 11:36:16] Epoch 1 | Step 930 | Loss: 1.0831 | LM: 0.3682 | LB: 1.4318 | CL0: 2.9 | CL1: 3.6 | HR0: 0.352/SR0: 0.347 | HR1: 0.315/SR1: 0.291 | LR: 6.95e-05
[2026-05-24 11:36:27] Epoch 1 | Step 940 | Loss: 1.0815 | LM: 0.3674 | LB: 1.4297 | CL0: 2.9 | CL1: 3.6 | HR0: 0.352/SR0: 0.346 | HR1: 0.314/SR1: 0.290 | LR: 7.02e-05
[2026-05-24 11:36:38] Epoch 1 | Step 950 | Loss: 1.0806 | LM: 0.3677 | LB: 1.4277 | CL0: 2.9 | CL1: 3.6 | HR0: 0.352/SR0: 0.346 | HR1: 0.312/SR1: 0.289 | LR: 7.08e-05
[2026-05-24 11:36:49] Epoch 1 | Step 960 | Loss: 1.0798 | LM: 0.3678 | LB: 1.4252 | CL0: 2.9 | CL1: 3.7 | HR0: 0.352/SR0: 0.346 | HR1: 0.311/SR1: 0.287 | LR: 7.15e-05
[2026-05-24 11:37:00] Epoch 1 | Step 970 | Loss: 1.0786 | LM: 0.3673 | LB: 1.4231 | CL0: 2.9 | CL1: 3.7 | HR0: 0.352/SR0: 0.346 | HR1: 0.310/SR1: 0.286 | LR: 7.21e-05
[2026-05-24 11:37:11] Epoch 1 | Step 980 | Loss: 1.0775 | LM: 0.3673 | LB: 1.4212 | CL0: 2.9 | CL1: 3.7 | HR0: 0.352/SR0: 0.346 | HR1: 0.309/SR1: 0.285 | LR: 7.27e-05
[2026-05-24 11:37:22] Epoch 1 | Step 990 | Loss: 1.0763 | LM: 0.3670 | LB: 1.4189 | CL0: 2.9 | CL1: 3.7 | HR0: 0.351/SR0: 0.346 | HR1: 0.307/SR1: 0.284 | LR: 7.34e-05
[2026-05-24 11:37:33] Epoch 1 | Step 1000 | Loss: 1.0751 | LM: 0.3676 | LB: 1.4170 | CL0: 2.9 | CL1: 3.7 | HR0: 0.351/SR0: 0.345 | HR1: 0.306/SR1: 0.283 | LR: 7.40e-05
[2026-05-24 11:37:35] Validation | Batch 10/1463 | Loss: 0.9285 | LM_LOSS: 0.3354 | LB_LOSS: 1.1862
[2026-05-24 11:37:37] Validation | Batch 20/1463 | Loss: 0.9393 | LM_LOSS: 0.3406 | LB_LOSS: 1.1974
[2026-05-24 11:37:39] Validation | Batch 30/1463 | Loss: 0.9466 | LM_LOSS: 0.3463 | LB_LOSS: 1.2005
[2026-05-24 11:37:41] Validation | Batch 40/1463 | Loss: 0.9571 | LM_LOSS: 0.3547 | LB_LOSS: 1.2049
[2026-05-24 11:37:43] Validation | Batch 50/1463 | Loss: 0.9659 | LM_LOSS: 0.3650 | LB_LOSS: 1.2018
[2026-05-24 11:37:46] Validation | Batch 60/1463 | Loss: 0.9679 | LM_LOSS: 0.3671 | LB_LOSS: 1.2016
[2026-05-24 11:37:48] Validation | Batch 70/1463 | Loss: 0.9685 | LM_LOSS: 0.3673 | LB_LOSS: 1.2023
[2026-05-24 11:37:51] Validation | Batch 80/1463 | Loss: 0.9698 | LM_LOSS: 0.3685 | LB_LOSS: 1.2027
[2026-05-24 11:37:53] Validation | Batch 90/1463 | Loss: 0.9695 | LM_LOSS: 0.3683 | LB_LOSS: 1.2024
[2026-05-24 11:37:55] Validation | Batch 100/1463 | Loss: 0.9703 | LM_LOSS: 0.3691 | LB_LOSS: 1.2024
[2026-05-24 11:37:57] Validation | Batch 110/1463 | Loss: 0.9700 | LM_LOSS: 0.3681 | LB_LOSS: 1.2038
[2026-05-24 11:37:59] Validation | Batch 120/1463 | Loss: 0.9713 | LM_LOSS: 0.3692 | LB_LOSS: 1.2040
[2026-05-24 11:38:01] Validation | Batch 130/1463 | Loss: 0.9735 | LM_LOSS: 0.3714 | LB_LOSS: 1.2042
[2026-05-24 11:38:03] Validation | Batch 140/1463 | Loss: 0.9736 | LM_LOSS: 0.3717 | LB_LOSS: 1.2038
[2026-05-24 11:38:05] Validation | Batch 150/1463 | Loss: 0.9718 | LM_LOSS: 0.3698 | LB_LOSS: 1.2042
[2026-05-24 11:38:08] Validation | Batch 160/1463 | Loss: 0.9721 | LM_LOSS: 0.3704 | LB_LOSS: 1.2035
[2026-05-24 11:38:10] Validation | Batch 170/1463 | Loss: 0.9719 | LM_LOSS: 0.3701 | LB_LOSS: 1.2036
[2026-05-24 11:38:12] Validation | Batch 180/1463 | Loss: 0.9724 | LM_LOSS: 0.3707 | LB_LOSS: 1.2035
[2026-05-24 11:38:14] Validation | Batch 190/1463 | Loss: 0.9734 | LM_LOSS: 0.3715 | LB_LOSS: 1.2038
[2026-05-24 11:38:16] Validation | Batch 200/1463 | Loss: 0.9729 | LM_LOSS: 0.3709 | LB_LOSS: 1.2039
[2026-05-24 11:38:18] Validation | Batch 210/1463 | Loss: 0.9731 | LM_LOSS: 0.3712 | LB_LOSS: 1.2039
[2026-05-24 11:38:21] Validation | Batch 220/1463 | Loss: 0.9728 | LM_LOSS: 0.3708 | LB_LOSS: 1.2040
[2026-05-24 11:38:23] Validation | Batch 230/1463 | Loss: 0.9741 | LM_LOSS: 0.3723 | LB_LOSS: 1.2036
[2026-05-24 11:38:25] Validation | Batch 240/1463 | Loss: 0.9749 | LM_LOSS: 0.3731 | LB_LOSS: 1.2036
[2026-05-24 11:38:27] Validation | Batch 250/1463 | Loss: 0.9745 | LM_LOSS: 0.3727 | LB_LOSS: 1.2038
[2026-05-24 11:38:29] Validation | Batch 260/1463 | Loss: 0.9763 | LM_LOSS: 0.3741 | LB_LOSS: 1.2044
[2026-05-24 11:38:31] Validation | Batch 270/1463 | Loss: 0.9752 | LM_LOSS: 0.3729 | LB_LOSS: 1.2045
[2026-05-24 11:38:34] Validation | Batch 280/1463 | Loss: 0.9762 | LM_LOSS: 0.3739 | LB_LOSS: 1.2047
[2026-05-24 11:38:36] Validation | Batch 290/1463 | Loss: 0.9755 | LM_LOSS: 0.3732 | LB_LOSS: 1.2047
[2026-05-24 11:38:38] Validation | Batch 300/1463 | Loss: 0.9759 | LM_LOSS: 0.3733 | LB_LOSS: 1.2052
[2026-05-24 11:38:40] Validation | Batch 310/1463 | Loss: 0.9767 | LM_LOSS: 0.3742 | LB_LOSS: 1.2051
[2026-05-24 11:38:42] Validation | Batch 320/1463 | Loss: 0.9750 | LM_LOSS: 0.3728 | LB_LOSS: 1.2043
[2026-05-24 11:38:44] Validation | Batch 330/1463 | Loss: 0.9752 | LM_LOSS: 0.3730 | LB_LOSS: 1.2043
[2026-05-24 11:38:46] Validation | Batch 340/1463 | Loss: 0.9746 | LM_LOSS: 0.3724 | LB_LOSS: 1.2043
[2026-05-24 11:38:48] Validation | Batch 350/1463 | Loss: 0.9752 | LM_LOSS: 0.3731 | LB_LOSS: 1.2043
[2026-05-24 11:38:50] Validation | Batch 360/1463 | Loss: 0.9750 | LM_LOSS: 0.3728 | LB_LOSS: 1.2045
[2026-05-24 11:38:52] Validation | Batch 370/1463 | Loss: 0.9751 | LM_LOSS: 0.3727 | LB_LOSS: 1.2047
[2026-05-24 11:38:54] Validation | Batch 380/1463 | Loss: 0.9746 | LM_LOSS: 0.3725 | LB_LOSS: 1.2043
[2026-05-24 11:38:56] Validation | Batch 390/1463 | Loss: 0.9753 | LM_LOSS: 0.3731 | LB_LOSS: 1.2044
[2026-05-24 11:38:58] Validation | Batch 400/1463 | Loss: 0.9754 | LM_LOSS: 0.3731 | LB_LOSS: 1.2046
[2026-05-24 11:39:00] Validation | Batch 410/1463 | Loss: 0.9752 | LM_LOSS: 0.3728 | LB_LOSS: 1.2048
[2026-05-24 11:39:02] Validation | Batch 420/1463 | Loss: 0.9755 | LM_LOSS: 0.3730 | LB_LOSS: 1.2050
[2026-05-24 11:39:05] Validation | Batch 430/1463 | Loss: 0.9749 | LM_LOSS: 0.3723 | LB_LOSS: 1.2051
[2026-05-24 11:39:07] Validation | Batch 440/1463 | Loss: 0.9751 | LM_LOSS: 0.3726 | LB_LOSS: 1.2051
[2026-05-24 11:39:08] Validation | Batch 450/1463 | Loss: 0.9749 | LM_LOSS: 0.3723 | LB_LOSS: 1.2052
[2026-05-24 11:39:11] Validation | Batch 460/1463 | Loss: 0.9752 | LM_LOSS: 0.3726 | LB_LOSS: 1.2052
[2026-05-24 11:39:13] Validation | Batch 470/1463 | Loss: 0.9758 | LM_LOSS: 0.3734 | LB_LOSS: 1.2049
[2026-05-24 11:39:15] Validation | Batch 480/1463 | Loss: 0.9757 | LM_LOSS: 0.3733 | LB_LOSS: 1.2047
[2026-05-24 11:39:18] Validation | Batch 490/1463 | Loss: 0.9756 | LM_LOSS: 0.3732 | LB_LOSS: 1.2047
[2026-05-24 11:39:20] Validation | Batch 500/1463 | Loss: 0.9753 | LM_LOSS: 0.3730 | LB_LOSS: 1.2046
[2026-05-24 11:39:22] Validation | Batch 510/1463 | Loss: 0.9747 | LM_LOSS: 0.3724 | LB_LOSS: 1.2047
[2026-05-24 11:39:24] Validation | Batch 520/1463 | Loss: 0.9742 | LM_LOSS: 0.3717 | LB_LOSS: 1.2049
[2026-05-24 11:39:26] Validation | Batch 530/1463 | Loss: 0.9743 | LM_LOSS: 0.3719 | LB_LOSS: 1.2048
[2026-05-24 11:39:28] Validation | Batch 540/1463 | Loss: 0.9748 | LM_LOSS: 0.3723 | LB_LOSS: 1.2050
[2026-05-24 11:39:30] Validation | Batch 550/1463 | Loss: 0.9744 | LM_LOSS: 0.3718 | LB_LOSS: 1.2052
[2026-05-24 11:39:32] Validation | Batch 560/1463 | Loss: 0.9750 | LM_LOSS: 0.3722 | LB_LOSS: 1.2055
[2026-05-24 11:39:34] Validation | Batch 570/1463 | Loss: 0.9749 | LM_LOSS: 0.3722 | LB_LOSS: 1.2054
[2026-05-24 11:39:36] Validation | Batch 580/1463 | Loss: 0.9747 | LM_LOSS: 0.3721 | LB_LOSS: 1.2054
[2026-05-24 11:39:39] Validation | Batch 590/1463 | Loss: 0.9747 | LM_LOSS: 0.3719 | LB_LOSS: 1.2056
[2026-05-24 11:39:41] Validation | Batch 600/1463 | Loss: 0.9751 | LM_LOSS: 0.3722 | LB_LOSS: 1.2058
[2026-05-24 11:39:44] Validation | Batch 610/1463 | Loss: 0.9753 | LM_LOSS: 0.3723 | LB_LOSS: 1.2059
[2026-05-24 11:39:46] Validation | Batch 620/1463 | Loss: 0.9747 | LM_LOSS: 0.3718 | LB_LOSS: 1.2058
[2026-05-24 11:39:48] Validation | Batch 630/1463 | Loss: 0.9744 | LM_LOSS: 0.3714 | LB_LOSS: 1.2060
[2026-05-24 11:39:50] Validation | Batch 640/1463 | Loss: 0.9742 | LM_LOSS: 0.3711 | LB_LOSS: 1.2061
[2026-05-24 11:39:52] Validation | Batch 650/1463 | Loss: 0.9735 | LM_LOSS: 0.3705 | LB_LOSS: 1.2061
[2026-05-24 11:39:54] Validation | Batch 660/1463 | Loss: 0.9729 | LM_LOSS: 0.3700 | LB_LOSS: 1.2059
[2026-05-24 11:39:56] Validation | Batch 670/1463 | Loss: 0.9725 | LM_LOSS: 0.3697 | LB_LOSS: 1.2057
[2026-05-24 11:39:57] Validation | Batch 680/1463 | Loss: 0.9723 | LM_LOSS: 0.3695 | LB_LOSS: 1.2055
[2026-05-24 11:40:00] Validation | Batch 690/1463 | Loss: 0.9727 | LM_LOSS: 0.3699 | LB_LOSS: 1.2057
[2026-05-24 11:40:02] Validation | Batch 700/1463 | Loss: 0.9726 | LM_LOSS: 0.3697 | LB_LOSS: 1.2056
[2026-05-24 11:40:04] Validation | Batch 710/1463 | Loss: 0.9732 | LM_LOSS: 0.3703 | LB_LOSS: 1.2058
[2026-05-24 11:40:06] Validation | Batch 720/1463 | Loss: 0.9741 | LM_LOSS: 0.3711 | LB_LOSS: 1.2060
[2026-05-24 11:40:08] Validation | Batch 730/1463 | Loss: 0.9737 | LM_LOSS: 0.3707 | LB_LOSS: 1.2059
[2026-05-24 11:40:10] Validation | Batch 740/1463 | Loss: 0.9734 | LM_LOSS: 0.3704 | LB_LOSS: 1.2060
[2026-05-24 11:40:11] Validation | Batch 750/1463 | Loss: 0.9732 | LM_LOSS: 0.3703 | LB_LOSS: 1.2059
[2026-05-24 11:40:13] Validation | Batch 760/1463 | Loss: 0.9729 | LM_LOSS: 0.3700 | LB_LOSS: 1.2059
[2026-05-24 11:40:15] Validation | Batch 770/1463 | Loss: 0.9727 | LM_LOSS: 0.3696 | LB_LOSS: 1.2060
[2026-05-24 11:40:17] Validation | Batch 780/1463 | Loss: 0.9723 | LM_LOSS: 0.3694 | LB_LOSS: 1.2059
[2026-05-24 11:40:18] Validation | Batch 790/1463 | Loss: 0.9724 | LM_LOSS: 0.3695 | LB_LOSS: 1.2058
[2026-05-24 11:40:20] Validation | Batch 800/1463 | Loss: 0.9723 | LM_LOSS: 0.3694 | LB_LOSS: 1.2058
[2026-05-24 11:40:22] Validation | Batch 810/1463 | Loss: 0.9718 | LM_LOSS: 0.3690 | LB_LOSS: 1.2055
[2026-05-24 11:40:24] Validation | Batch 820/1463 | Loss: 0.9719 | LM_LOSS: 0.3692 | LB_LOSS: 1.2055
[2026-05-24 11:40:27] Validation | Batch 830/1463 | Loss: 0.9721 | LM_LOSS: 0.3694 | LB_LOSS: 1.2055
[2026-05-24 11:40:29] Validation | Batch 840/1463 | Loss: 0.9722 | LM_LOSS: 0.3693 | LB_LOSS: 1.2057
[2026-05-24 11:40:31] Validation | Batch 850/1463 | Loss: 0.9723 | LM_LOSS: 0.3695 | LB_LOSS: 1.2057
[2026-05-24 11:40:33] Validation | Batch 860/1463 | Loss: 0.9723 | LM_LOSS: 0.3694 | LB_LOSS: 1.2059
[2026-05-24 11:40:36] Validation | Batch 870/1463 | Loss: 0.9725 | LM_LOSS: 0.3696 | LB_LOSS: 1.2059
[2026-05-24 11:40:37] Validation | Batch 880/1463 | Loss: 0.9717 | LM_LOSS: 0.3688 | LB_LOSS: 1.2059
[2026-05-24 11:40:39] Validation | Batch 890/1463 | Loss: 0.9715 | LM_LOSS: 0.3687 | LB_LOSS: 1.2057
[2026-05-24 11:40:42] Validation | Batch 900/1463 | Loss: 0.9712 | LM_LOSS: 0.3684 | LB_LOSS: 1.2057
[2026-05-24 11:40:44] Validation | Batch 910/1463 | Loss: 0.9711 | LM_LOSS: 0.3683 | LB_LOSS: 1.2057
[2026-05-24 11:40:46] Validation | Batch 920/1463 | Loss: 0.9713 | LM_LOSS: 0.3684 | LB_LOSS: 1.2057
[2026-05-24 11:40:48] Validation | Batch 930/1463 | Loss: 0.9710 | LM_LOSS: 0.3682 | LB_LOSS: 1.2056
[2026-05-24 11:40:50] Validation | Batch 940/1463 | Loss: 0.9706 | LM_LOSS: 0.3679 | LB_LOSS: 1.2055
[2026-05-24 11:40:53] Validation | Batch 950/1463 | Loss: 0.9709 | LM_LOSS: 0.3682 | LB_LOSS: 1.2054
[2026-05-24 11:40:55] Validation | Batch 960/1463 | Loss: 0.9710 | LM_LOSS: 0.3684 | LB_LOSS: 1.2054
[2026-05-24 11:40:57] Validation | Batch 970/1463 | Loss: 0.9711 | LM_LOSS: 0.3685 | LB_LOSS: 1.2053
[2026-05-24 11:41:00] Validation | Batch 980/1463 | Loss: 0.9713 | LM_LOSS: 0.3687 | LB_LOSS: 1.2052
[2026-05-24 11:41:01] Validation | Batch 990/1463 | Loss: 0.9716 | LM_LOSS: 0.3689 | LB_LOSS: 1.2053
[2026-05-24 11:41:03] Validation | Batch 1000/1463 | Loss: 0.9723 | LM_LOSS: 0.3696 | LB_LOSS: 1.2053
[2026-05-24 11:41:06] Validation | Batch 1010/1463 | Loss: 0.9723 | LM_LOSS: 0.3695 | LB_LOSS: 1.2055
[2026-05-24 11:41:08] Validation | Batch 1020/1463 | Loss: 0.9724 | LM_LOSS: 0.3697 | LB_LOSS: 1.2056
[2026-05-24 11:41:11] Validation | Batch 1030/1463 | Loss: 0.9728 | LM_LOSS: 0.3700 | LB_LOSS: 1.2056
[2026-05-24 11:41:12] Validation | Batch 1040/1463 | Loss: 0.9723 | LM_LOSS: 0.3695 | LB_LOSS: 1.2056
[2026-05-24 11:41:15] Validation | Batch 1050/1463 | Loss: 0.9721 | LM_LOSS: 0.3693 | LB_LOSS: 1.2054
[2026-05-24 11:41:17] Validation | Batch 1060/1463 | Loss: 0.9720 | LM_LOSS: 0.3693 | LB_LOSS: 1.2054
[2026-05-24 11:41:19] Validation | Batch 1070/1463 | Loss: 0.9721 | LM_LOSS: 0.3694 | LB_LOSS: 1.2055
[2026-05-24 11:41:21] Validation | Batch 1080/1463 | Loss: 0.9718 | LM_LOSS: 0.3690 | LB_LOSS: 1.2057
[2026-05-24 11:41:23] Validation | Batch 1090/1463 | Loss: 0.9718 | LM_LOSS: 0.3690 | LB_LOSS: 1.2055
[2026-05-24 11:41:25] Validation | Batch 1100/1463 | Loss: 0.9716 | LM_LOSS: 0.3689 | LB_LOSS: 1.2054
[2026-05-24 11:41:27] Validation | Batch 1110/1463 | Loss: 0.9716 | LM_LOSS: 0.3689 | LB_LOSS: 1.2054
[2026-05-24 11:41:29] Validation | Batch 1120/1463 | Loss: 0.9715 | LM_LOSS: 0.3688 | LB_LOSS: 1.2055
[2026-05-24 11:41:31] Validation | Batch 1130/1463 | Loss: 0.9713 | LM_LOSS: 0.3686 | LB_LOSS: 1.2054
[2026-05-24 11:41:33] Validation | Batch 1140/1463 | Loss: 0.9715 | LM_LOSS: 0.3688 | LB_LOSS: 1.2054
[2026-05-24 11:41:36] Validation | Batch 1150/1463 | Loss: 0.9713 | LM_LOSS: 0.3686 | LB_LOSS: 1.2054
[2026-05-24 11:41:38] Validation | Batch 1160/1463 | Loss: 0.9713 | LM_LOSS: 0.3686 | LB_LOSS: 1.2054
[2026-05-24 11:41:40] Validation | Batch 1170/1463 | Loss: 0.9714 | LM_LOSS: 0.3687 | LB_LOSS: 1.2054
[2026-05-24 11:41:42] Validation | Batch 1180/1463 | Loss: 0.9714 | LM_LOSS: 0.3687 | LB_LOSS: 1.2054
[2026-05-24 11:41:44] Validation | Batch 1190/1463 | Loss: 0.9716 | LM_LOSS: 0.3688 | LB_LOSS: 1.2054
[2026-05-24 11:41:47] Validation | Batch 1200/1463 | Loss: 0.9717 | LM_LOSS: 0.3689 | LB_LOSS: 1.2055
[2026-05-24 11:41:49] Validation | Batch 1210/1463 | Loss: 0.9720 | LM_LOSS: 0.3692 | LB_LOSS: 1.2056
[2026-05-24 11:41:51] Validation | Batch 1220/1463 | Loss: 0.9724 | LM_LOSS: 0.3696 | LB_LOSS: 1.2056
[2026-05-24 11:41:53] Validation | Batch 1230/1463 | Loss: 0.9723 | LM_LOSS: 0.3695 | LB_LOSS: 1.2055
[2026-05-24 11:41:55] Validation | Batch 1240/1463 | Loss: 0.9727 | LM_LOSS: 0.3699 | LB_LOSS: 1.2055
[2026-05-24 11:41:57] Validation | Batch 1250/1463 | Loss: 0.9730 | LM_LOSS: 0.3702 | LB_LOSS: 1.2055
[2026-05-24 11:42:00] Validation | Batch 1260/1463 | Loss: 0.9730 | LM_LOSS: 0.3702 | LB_LOSS: 1.2056
[2026-05-24 11:42:02] Validation | Batch 1270/1463 | Loss: 0.9728 | LM_LOSS: 0.3700 | LB_LOSS: 1.2057
[2026-05-24 11:42:04] Validation | Batch 1280/1463 | Loss: 0.9726 | LM_LOSS: 0.3699 | LB_LOSS: 1.2055
[2026-05-24 11:42:06] Validation | Batch 1290/1463 | Loss: 0.9726 | LM_LOSS: 0.3698 | LB_LOSS: 1.2055
[2026-05-24 11:42:08] Validation | Batch 1300/1463 | Loss: 0.9725 | LM_LOSS: 0.3697 | LB_LOSS: 1.2055
[2026-05-24 11:42:10] Validation | Batch 1310/1463 | Loss: 0.9724 | LM_LOSS: 0.3696 | LB_LOSS: 1.2055
[2026-05-24 11:42:12] Validation | Batch 1320/1463 | Loss: 0.9724 | LM_LOSS: 0.3697 | LB_LOSS: 1.2055
[2026-05-24 11:42:14] Validation | Batch 1330/1463 | Loss: 0.9725 | LM_LOSS: 0.3697 | LB_LOSS: 1.2055
[2026-05-24 11:42:16] Validation | Batch 1340/1463 | Loss: 0.9727 | LM_LOSS: 0.3699 | LB_LOSS: 1.2055
[2026-05-24 11:42:18] Validation | Batch 1350/1463 | Loss: 0.9727 | LM_LOSS: 0.3700 | LB_LOSS: 1.2055
[2026-05-24 11:42:21] Validation | Batch 1360/1463 | Loss: 0.9730 | LM_LOSS: 0.3703 | LB_LOSS: 1.2054
[2026-05-24 11:42:23] Validation | Batch 1370/1463 | Loss: 0.9733 | LM_LOSS: 0.3705 | LB_LOSS: 1.2055
[2026-05-24 11:42:25] Validation | Batch 1380/1463 | Loss: 0.9730 | LM_LOSS: 0.3703 | LB_LOSS: 1.2054
[2026-05-24 11:42:27] Validation | Batch 1390/1463 | Loss: 0.9730 | LM_LOSS: 0.3702 | LB_LOSS: 1.2055
[2026-05-24 11:42:29] Validation | Batch 1400/1463 | Loss: 0.9732 | LM_LOSS: 0.3706 | LB_LOSS: 1.2053
[2026-05-24 11:42:31] Validation | Batch 1410/1463 | Loss: 0.9734 | LM_LOSS: 0.3708 | LB_LOSS: 1.2053
[2026-05-24 11:42:33] Validation | Batch 1420/1463 | Loss: 0.9734 | LM_LOSS: 0.3707 | LB_LOSS: 1.2054
[2026-05-24 11:42:35] Validation | Batch 1430/1463 | Loss: 0.9735 | LM_LOSS: 0.3708 | LB_LOSS: 1.2054
[2026-05-24 11:42:38] Validation | Batch 1440/1463 | Loss: 0.9739 | LM_LOSS: 0.3712 | LB_LOSS: 1.2054
[2026-05-24 11:42:40] Validation | Batch 1450/1463 | Loss: 0.9735 | LM_LOSS: 0.3709 | LB_LOSS: 1.2053
[2026-05-24 11:42:42] Validation | Batch 1460/1463 | Loss: 0.9739 | LM_LOSS: 0.3712 | LB_LOSS: 1.2053
[2026-05-24 11:42:43] Validation | Batch 1463/1463 | Loss: 0.9737 | LM_LOSS: 0.3710 | LB_LOSS: 1.2053
[2026-05-24 11:42:43] Validation | Loss: 0.9737 | LM_LOSS: 0.3710 | LB_LOSS: 1.2053 | PPL: 1.45 | Time: 309.44s
[2026-05-24 11:42:47] New best model saved! Val loss: 0.9737
[2026-05-24 11:42:57] Epoch 1 | Step 1010 | Loss: 1.0741 | LM: 0.3681 | LB: 1.4148 | CL0: 2.9 | CL1: 3.8 | HR0: 0.351/SR0: 0.345 | HR1: 0.305/SR1: 0.281 | LR: 7.47e-05
[2026-05-24 11:43:08] Epoch 1 | Step 1020 | Loss: 1.0731 | LM: 0.3678 | LB: 1.4128 | CL0: 2.9 | CL1: 3.8 | HR0: 0.351/SR0: 0.345 | HR1: 0.304/SR1: 0.280 | LR: 7.53e-05
[2026-05-24 11:43:19] Epoch 1 | Step 1030 | Loss: 1.0719 | LM: 0.3686 | LB: 1.4108 | CL0: 2.9 | CL1: 3.8 | HR0: 0.351/SR0: 0.345 | HR1: 0.302/SR1: 0.279 | LR: 7.59e-05
[2026-05-24 11:43:31] Epoch 1 | Step 1040 | Loss: 1.0709 | LM: 0.3691 | LB: 1.4089 | CL0: 2.9 | CL1: 3.8 | HR0: 0.351/SR0: 0.345 | HR1: 0.301/SR1: 0.278 | LR: 7.66e-05
[2026-05-24 11:43:43] Epoch 1 | Step 1050 | Loss: 1.0700 | LM: 0.3689 | LB: 1.4072 | CL0: 2.9 | CL1: 3.8 | HR0: 0.351/SR0: 0.344 | HR1: 0.300/SR1: 0.277 | LR: 7.72e-05
[2026-05-24 11:43:54] Epoch 1 | Step 1060 | Loss: 1.0690 | LM: 0.3693 | LB: 1.4053 | CL0: 2.9 | CL1: 3.9 | HR0: 0.351/SR0: 0.344 | HR1: 0.299/SR1: 0.276 | LR: 7.79e-05
[2026-05-24 11:44:06] Epoch 1 | Step 1070 | Loss: 1.0681 | LM: 0.3685 | LB: 1.4036 | CL0: 2.9 | CL1: 3.9 | HR0: 0.351/SR0: 0.344 | HR1: 0.298/SR1: 0.275 | LR: 7.85e-05
[2026-05-24 11:44:18] Epoch 1 | Step 1080 | Loss: 1.0669 | LM: 0.3678 | LB: 1.4018 | CL0: 2.9 | CL1: 3.9 | HR0: 0.350/SR0: 0.344 | HR1: 0.297/SR1: 0.274 | LR: 7.91e-05
[2026-05-24 11:44:30] Epoch 1 | Step 1090 | Loss: 1.0659 | LM: 0.3675 | LB: 1.3999 | CL0: 2.9 | CL1: 3.9 | HR0: 0.350/SR0: 0.344 | HR1: 0.296/SR1: 0.273 | LR: 7.98e-05
[2026-05-24 11:44:40] Epoch 1 | Step 1100 | Loss: 1.0650 | LM: 0.3676 | LB: 1.3980 | CL0: 2.9 | CL1: 3.9 | HR0: 0.350/SR0: 0.343 | HR1: 0.294/SR1: 0.271 | LR: 8.04e-05
[2026-05-24 11:44:51] Epoch 1 | Step 1110 | Loss: 1.0640 | LM: 0.3673 | LB: 1.3963 | CL0: 2.9 | CL1: 3.9 | HR0: 0.350/SR0: 0.343 | HR1: 0.294/SR1: 0.271 | LR: 8.11e-05
[2026-05-24 11:45:01] Epoch 1 | Step 1120 | Loss: 1.0636 | LM: 0.3677 | LB: 1.3945 | CL0: 2.9 | CL1: 4.0 | HR0: 0.350/SR0: 0.343 | HR1: 0.292/SR1: 0.269 | LR: 8.17e-05
[2026-05-24 11:45:12] Epoch 1 | Step 1130 | Loss: 1.0625 | LM: 0.3671 | LB: 1.3933 | CL0: 2.9 | CL1: 4.0 | HR0: 0.350/SR0: 0.343 | HR1: 0.292/SR1: 0.269 | LR: 8.23e-05
[2026-05-24 11:45:24] Epoch 1 | Step 1140 | Loss: 1.0618 | LM: 0.3672 | LB: 1.3917 | CL0: 2.9 | CL1: 4.0 | HR0: 0.350/SR0: 0.343 | HR1: 0.291/SR1: 0.268 | LR: 8.30e-05
[2026-05-24 11:45:35] Epoch 1 | Step 1150 | Loss: 1.0610 | LM: 0.3673 | LB: 1.3900 | CL0: 2.9 | CL1: 4.0 | HR0: 0.349/SR0: 0.342 | HR1: 0.290/SR1: 0.267 | LR: 8.36e-05
[2026-05-24 11:45:46] Epoch 1 | Step 1160 | Loss: 1.0602 | LM: 0.3672 | LB: 1.3882 | CL0: 2.9 | CL1: 4.0 | HR0: 0.349/SR0: 0.342 | HR1: 0.289/SR1: 0.266 | LR: 8.43e-05
[2026-05-24 11:45:56] Epoch 1 | Step 1170 | Loss: 1.0594 | LM: 0.3673 | LB: 1.3866 | CL0: 2.9 | CL1: 4.0 | HR0: 0.349/SR0: 0.342 | HR1: 0.288/SR1: 0.265 | LR: 8.49e-05
[2026-05-24 11:46:07] Epoch 1 | Step 1180 | Loss: 1.0588 | LM: 0.3674 | LB: 1.3849 | CL0: 2.9 | CL1: 4.1 | HR0: 0.349/SR0: 0.342 | HR1: 0.287/SR1: 0.264 | LR: 8.55e-05
[2026-05-24 11:46:18] Epoch 1 | Step 1190 | Loss: 1.0580 | LM: 0.3676 | LB: 1.3833 | CL0: 2.9 | CL1: 4.1 | HR0: 0.349/SR0: 0.342 | HR1: 0.286/SR1: 0.263 | LR: 8.62e-05
[2026-05-24 11:46:29] Epoch 1 | Step 1200 | Loss: 1.0571 | LM: 0.3675 | LB: 1.3818 | CL0: 2.9 | CL1: 4.1 | HR0: 0.349/SR0: 0.341 | HR1: 0.285/SR1: 0.262 | LR: 8.68e-05
[2026-05-24 11:46:40] Epoch 1 | Step 1210 | Loss: 1.0565 | LM: 0.3680 | LB: 1.3802 | CL0: 2.9 | CL1: 4.1 | HR0: 0.349/SR0: 0.341 | HR1: 0.284/SR1: 0.261 | LR: 8.75e-05
[2026-05-24 11:46:51] Epoch 1 | Step 1220 | Loss: 1.0557 | LM: 0.3684 | LB: 1.3788 | CL0: 2.9 | CL1: 4.1 | HR0: 0.349/SR0: 0.341 | HR1: 0.283/SR1: 0.260 | LR: 8.81e-05
[2026-05-24 11:47:02] Epoch 1 | Step 1230 | Loss: 1.0548 | LM: 0.3683 | LB: 1.3770 | CL0: 2.9 | CL1: 4.1 | HR0: 0.348/SR0: 0.341 | HR1: 0.282/SR1: 0.260 | LR: 8.87e-05
[2026-05-24 11:47:13] Epoch 1 | Step 1240 | Loss: 1.0543 | LM: 0.3685 | LB: 1.3756 | CL0: 2.9 | CL1: 4.1 | HR0: 0.348/SR0: 0.340 | HR1: 0.281/SR1: 0.259 | LR: 8.94e-05
[2026-05-24 11:47:24] Epoch 1 | Step 1250 | Loss: 1.0537 | LM: 0.3689 | LB: 1.3743 | CL0: 2.9 | CL1: 4.2 | HR0: 0.348/SR0: 0.340 | HR1: 0.281/SR1: 0.258 | LR: 9.00e-05
[2026-05-24 11:47:34] Epoch 1 | Step 1260 | Loss: 1.0529 | LM: 0.3688 | LB: 1.3728 | CL0: 2.9 | CL1: 4.2 | HR0: 0.348/SR0: 0.340 | HR1: 0.280/SR1: 0.257 | LR: 9.07e-05
[2026-05-24 11:47:45] Epoch 1 | Step 1270 | Loss: 1.0519 | LM: 0.3685 | LB: 1.3714 | CL0: 2.9 | CL1: 4.2 | HR0: 0.348/SR0: 0.340 | HR1: 0.279/SR1: 0.256 | LR: 9.13e-05
[2026-05-24 11:47:56] Epoch 1 | Step 1280 | Loss: 1.0511 | LM: 0.3689 | LB: 1.3700 | CL0: 2.9 | CL1: 4.2 | HR0: 0.348/SR0: 0.340 | HR1: 0.278/SR1: 0.255 | LR: 9.19e-05
[2026-05-24 11:48:07] Epoch 1 | Step 1290 | Loss: 1.0506 | LM: 0.3689 | LB: 1.3686 | CL0: 2.9 | CL1: 4.2 | HR0: 0.348/SR0: 0.340 | HR1: 0.277/SR1: 0.254 | LR: 9.26e-05
[2026-05-24 11:48:19] Epoch 1 | Step 1300 | Loss: 1.0501 | LM: 0.3693 | LB: 1.3672 | CL0: 2.9 | CL1: 4.2 | HR0: 0.348/SR0: 0.339 | HR1: 0.276/SR1: 0.254 | LR: 9.32e-05
[2026-05-24 11:48:31] Epoch 1 | Step 1310 | Loss: 1.0496 | LM: 0.3704 | LB: 1.3657 | CL0: 2.9 | CL1: 4.3 | HR0: 0.347/SR0: 0.339 | HR1: 0.275/SR1: 0.253 | LR: 9.39e-05
[2026-05-24 11:48:42] Epoch 1 | Step 1320 | Loss: 1.0486 | LM: 0.3704 | LB: 1.3642 | CL0: 2.9 | CL1: 4.3 | HR0: 0.347/SR0: 0.339 | HR1: 0.275/SR1: 0.252 | LR: 9.45e-05
[2026-05-24 11:48:54] Epoch 1 | Step 1330 | Loss: 1.0480 | LM: 0.3702 | LB: 1.3629 | CL0: 2.9 | CL1: 4.3 | HR0: 0.347/SR0: 0.339 | HR1: 0.274/SR1: 0.252 | LR: 9.51e-05
[2026-05-24 11:49:06] Epoch 1 | Step 1340 | Loss: 1.0472 | LM: 0.3699 | LB: 1.3616 | CL0: 2.9 | CL1: 4.3 | HR0: 0.347/SR0: 0.338 | HR1: 0.273/SR1: 0.251 | LR: 9.58e-05
[2026-05-24 11:49:17] Epoch 1 | Step 1350 | Loss: 1.0464 | LM: 0.3699 | LB: 1.3601 | CL0: 2.9 | CL1: 4.3 | HR0: 0.347/SR0: 0.338 | HR1: 0.272/SR1: 0.250 | LR: 9.64e-05
[2026-05-24 11:49:29] Epoch 1 | Step 1360 | Loss: 1.0458 | LM: 0.3698 | LB: 1.3588 | CL0: 2.9 | CL1: 4.3 | HR0: 0.346/SR0: 0.338 | HR1: 0.272/SR1: 0.250 | LR: 9.71e-05
[2026-05-24 11:49:40] Epoch 1 | Step 1370 | Loss: 1.0450 | LM: 0.3697 | LB: 1.3575 | CL0: 2.9 | CL1: 4.3 | HR0: 0.346/SR0: 0.338 | HR1: 0.271/SR1: 0.249 | LR: 9.77e-05
[2026-05-24 11:49:52] Epoch 1 | Step 1380 | Loss: 1.0443 | LM: 0.3699 | LB: 1.3561 | CL0: 2.9 | CL1: 4.4 | HR0: 0.346/SR0: 0.337 | HR1: 0.270/SR1: 0.248 | LR: 9.83e-05
[2026-05-24 11:50:03] Epoch 1 | Step 1390 | Loss: 1.0436 | LM: 0.3699 | LB: 1.3547 | CL0: 2.9 | CL1: 4.4 | HR0: 0.346/SR0: 0.337 | HR1: 0.269/SR1: 0.247 | LR: 9.90e-05
[2026-05-24 11:50:15] Epoch 1 | Step 1400 | Loss: 1.0430 | LM: 0.3704 | LB: 1.3532 | CL0: 2.9 | CL1: 4.4 | HR0: 0.346/SR0: 0.337 | HR1: 0.269/SR1: 0.246 | LR: 9.96e-05
[2026-05-24 11:50:27] Epoch 1 | Step 1410 | Loss: 1.0423 | LM: 0.3709 | LB: 1.3519 | CL0: 2.9 | CL1: 4.4 | HR0: 0.345/SR0: 0.337 | HR1: 0.268/SR1: 0.246 | LR: 1.00e-04
[2026-05-24 11:50:39] Epoch 1 | Step 1420 | Loss: 1.0418 | LM: 0.3708 | LB: 1.3505 | CL0: 2.9 | CL1: 4.4 | HR0: 0.345/SR0: 0.336 | HR1: 0.267/SR1: 0.245 | LR: 1.00e-04
[2026-05-24 11:50:50] Epoch 1 | Step 1430 | Loss: 1.0410 | LM: 0.3704 | LB: 1.3493 | CL0: 2.9 | CL1: 4.4 | HR0: 0.345/SR0: 0.336 | HR1: 0.266/SR1: 0.244 | LR: 1.00e-04
[2026-05-24 11:51:02] Epoch 1 | Step 1440 | Loss: 1.0404 | LM: 0.3703 | LB: 1.3481 | CL0: 2.9 | CL1: 4.4 | HR0: 0.345/SR0: 0.336 | HR1: 0.266/SR1: 0.244 | LR: 1.00e-04
[2026-05-24 11:51:13] Epoch 1 | Step 1450 | Loss: 1.0398 | LM: 0.3704 | LB: 1.3469 | CL0: 2.9 | CL1: 4.4 | HR0: 0.345/SR0: 0.336 | HR1: 0.265/SR1: 0.243 | LR: 1.00e-04
[2026-05-24 11:51:25] Epoch 1 | Step 1460 | Loss: 1.0392 | LM: 0.3707 | LB: 1.3455 | CL0: 2.9 | CL1: 4.5 | HR0: 0.345/SR0: 0.335 | HR1: 0.264/SR1: 0.242 | LR: 1.00e-04
[2026-05-24 11:51:37] Epoch 1 | Step 1470 | Loss: 1.0385 | LM: 0.3705 | LB: 1.3443 | CL0: 2.9 | CL1: 4.5 | HR0: 0.344/SR0: 0.335 | HR1: 0.264/SR1: 0.242 | LR: 1.00e-04
[2026-05-24 11:51:49] Epoch 1 | Step 1480 | Loss: 1.0380 | LM: 0.3708 | LB: 1.3430 | CL0: 2.9 | CL1: 4.5 | HR0: 0.344/SR0: 0.335 | HR1: 0.263/SR1: 0.241 | LR: 1.00e-04
[2026-05-24 11:52:01] Epoch 1 | Step 1490 | Loss: 1.0374 | LM: 0.3710 | LB: 1.3418 | CL0: 2.9 | CL1: 4.5 | HR0: 0.344/SR0: 0.334 | HR1: 0.263/SR1: 0.241 | LR: 1.00e-04
[2026-05-24 11:52:12] Epoch 1 | Step 1500 | Loss: 1.0367 | LM: 0.3709 | LB: 1.3405 | CL0: 2.9 | CL1: 4.5 | HR0: 0.344/SR0: 0.334 | HR1: 0.262/SR1: 0.240 | LR: 1.00e-04
[2026-05-24 11:52:24] Epoch 1 | Step 1510 | Loss: 1.0361 | LM: 0.3709 | LB: 1.3393 | CL0: 2.9 | CL1: 4.5 | HR0: 0.344/SR0: 0.334 | HR1: 0.261/SR1: 0.239 | LR: 1.00e-04
[2026-05-24 11:52:35] Epoch 1 | Step 1520 | Loss: 1.0354 | LM: 0.3706 | LB: 1.3381 | CL0: 2.9 | CL1: 4.5 | HR0: 0.344/SR0: 0.334 | HR1: 0.261/SR1: 0.239 | LR: 1.00e-04
[2026-05-24 11:52:47] Epoch 1 | Step 1530 | Loss: 1.0346 | LM: 0.3702 | LB: 1.3369 | CL0: 2.9 | CL1: 4.5 | HR0: 0.343/SR0: 0.333 | HR1: 0.260/SR1: 0.238 | LR: 1.00e-04
[2026-05-24 11:52:59] Epoch 1 | Step 1540 | Loss: 1.0339 | LM: 0.3700 | LB: 1.3358 | CL0: 2.9 | CL1: 4.5 | HR0: 0.343/SR0: 0.333 | HR1: 0.259/SR1: 0.238 | LR: 1.00e-04
[2026-05-24 11:53:11] Epoch 1 | Step 1550 | Loss: 1.0334 | LM: 0.3699 | LB: 1.3345 | CL0: 2.9 | CL1: 4.6 | HR0: 0.343/SR0: 0.333 | HR1: 0.259/SR1: 0.237 | LR: 1.00e-04
[2026-05-24 11:53:23] Epoch 1 | Step 1560 | Loss: 1.0329 | LM: 0.3700 | LB: 1.3333 | CL0: 2.9 | CL1: 4.6 | HR0: 0.343/SR0: 0.333 | HR1: 0.258/SR1: 0.236 | LR: 1.00e-04
[2026-05-24 11:53:34] Epoch 1 | Step 1570 | Loss: 1.0323 | LM: 0.3695 | LB: 1.3321 | CL0: 2.9 | CL1: 4.6 | HR0: 0.343/SR0: 0.332 | HR1: 0.257/SR1: 0.236 | LR: 1.00e-04
[2026-05-24 11:53:46] Epoch 1 | Step 1580 | Loss: 1.0318 | LM: 0.3698 | LB: 1.3309 | CL0: 2.9 | CL1: 4.6 | HR0: 0.342/SR0: 0.332 | HR1: 0.257/SR1: 0.235 | LR: 1.00e-04
[2026-05-24 11:53:58] Epoch 1 | Step 1590 | Loss: 1.0309 | LM: 0.3697 | LB: 1.3297 | CL0: 2.9 | CL1: 4.6 | HR0: 0.342/SR0: 0.332 | HR1: 0.256/SR1: 0.234 | LR: 1.00e-04
[2026-05-24 11:54:09] Epoch 1 | Step 1600 | Loss: 1.0304 | LM: 0.3700 | LB: 1.3285 | CL0: 2.9 | CL1: 4.6 | HR0: 0.342/SR0: 0.331 | HR1: 0.256/SR1: 0.234 | LR: 1.00e-04
[2026-05-24 11:54:21] Epoch 1 | Step 1610 | Loss: 1.0298 | LM: 0.3701 | LB: 1.3274 | CL0: 2.9 | CL1: 4.6 | HR0: 0.342/SR0: 0.331 | HR1: 0.255/SR1: 0.233 | LR: 1.00e-04
[2026-05-24 11:54:33] Epoch 1 | Step 1620 | Loss: 1.0291 | LM: 0.3704 | LB: 1.3264 | CL0: 2.9 | CL1: 4.6 | HR0: 0.342/SR0: 0.331 | HR1: 0.255/SR1: 0.233 | LR: 1.00e-04
[2026-05-24 11:54:44] Epoch 1 | Step 1630 | Loss: 1.0286 | LM: 0.3702 | LB: 1.3253 | CL0: 2.9 | CL1: 4.6 | HR0: 0.341/SR0: 0.331 | HR1: 0.254/SR1: 0.232 | LR: 1.00e-04
[2026-05-24 11:54:56] Epoch 1 | Step 1640 | Loss: 1.0281 | LM: 0.3702 | LB: 1.3242 | CL0: 2.9 | CL1: 4.6 | HR0: 0.341/SR0: 0.330 | HR1: 0.254/SR1: 0.232 | LR: 1.00e-04
[2026-05-24 11:55:07] Epoch 1 | Step 1650 | Loss: 1.0275 | LM: 0.3698 | LB: 1.3232 | CL0: 3.0 | CL1: 4.7 | HR0: 0.341/SR0: 0.330 | HR1: 0.253/SR1: 0.231 | LR: 1.00e-04
[2026-05-24 11:55:19] Epoch 1 | Step 1660 | Loss: 1.0269 | LM: 0.3696 | LB: 1.3222 | CL0: 3.0 | CL1: 4.7 | HR0: 0.341/SR0: 0.330 | HR1: 0.252/SR1: 0.231 | LR: 1.00e-04
[2026-05-24 11:55:31] Epoch 1 | Step 1670 | Loss: 1.0263 | LM: 0.3695 | LB: 1.3211 | CL0: 3.0 | CL1: 4.7 | HR0: 0.341/SR0: 0.330 | HR1: 0.252/SR1: 0.230 | LR: 1.00e-04
[2026-05-24 11:55:42] Epoch 1 | Step 1680 | Loss: 1.0257 | LM: 0.3694 | LB: 1.3201 | CL0: 3.0 | CL1: 4.7 | HR0: 0.341/SR0: 0.329 | HR1: 0.252/SR1: 0.230 | LR: 1.00e-04
[2026-05-24 11:55:54] Epoch 1 | Step 1690 | Loss: 1.0252 | LM: 0.3695 | LB: 1.3190 | CL0: 3.0 | CL1: 4.7 | HR0: 0.340/SR0: 0.329 | HR1: 0.251/SR1: 0.229 | LR: 1.00e-04
[2026-05-24 11:56:05] Epoch 1 | Step 1700 | Loss: 1.0243 | LM: 0.3690 | LB: 1.3179 | CL0: 3.0 | CL1: 4.7 | HR0: 0.340/SR0: 0.329 | HR1: 0.251/SR1: 0.229 | LR: 1.00e-04
[2026-05-24 11:56:17] Epoch 1 | Step 1710 | Loss: 1.0238 | LM: 0.3690 | LB: 1.3169 | CL0: 3.0 | CL1: 4.7 | HR0: 0.340/SR0: 0.329 | HR1: 0.250/SR1: 0.228 | LR: 1.00e-04
[2026-05-24 11:56:29] Epoch 1 | Step 1720 | Loss: 1.0235 | LM: 0.3691 | LB: 1.3158 | CL0: 3.0 | CL1: 4.7 | HR0: 0.340/SR0: 0.328 | HR1: 0.249/SR1: 0.228 | LR: 1.00e-04
[2026-05-24 11:56:40] Epoch 1 | Step 1730 | Loss: 1.0231 | LM: 0.3691 | LB: 1.3148 | CL0: 3.0 | CL1: 4.7 | HR0: 0.340/SR0: 0.328 | HR1: 0.249/SR1: 0.227 | LR: 1.00e-04
[2026-05-24 11:56:52] Epoch 1 | Step 1740 | Loss: 1.0223 | LM: 0.3689 | LB: 1.3138 | CL0: 3.0 | CL1: 4.7 | HR0: 0.339/SR0: 0.328 | HR1: 0.248/SR1: 0.227 | LR: 1.00e-04
[2026-05-24 11:57:04] Epoch 1 | Step 1750 | Loss: 1.0218 | LM: 0.3690 | LB: 1.3127 | CL0: 3.0 | CL1: 4.7 | HR0: 0.339/SR0: 0.327 | HR1: 0.248/SR1: 0.226 | LR: 1.00e-04
[2026-05-24 11:57:15] Epoch 1 | Step 1760 | Loss: 1.0211 | LM: 0.3690 | LB: 1.3116 | CL0: 3.0 | CL1: 4.8 | HR0: 0.339/SR0: 0.327 | HR1: 0.247/SR1: 0.226 | LR: 1.00e-04
[2026-05-24 11:57:27] Epoch 1 | Step 1770 | Loss: 1.0206 | LM: 0.3692 | LB: 1.3105 | CL0: 3.0 | CL1: 4.8 | HR0: 0.339/SR0: 0.327 | HR1: 0.247/SR1: 0.225 | LR: 1.00e-04
[2026-05-24 11:57:39] Epoch 1 | Step 1780 | Loss: 1.0201 | LM: 0.3694 | LB: 1.3096 | CL0: 3.0 | CL1: 4.8 | HR0: 0.339/SR0: 0.327 | HR1: 0.246/SR1: 0.225 | LR: 1.00e-04
[2026-05-24 11:57:50] Epoch 1 | Step 1790 | Loss: 1.0198 | LM: 0.3694 | LB: 1.3087 | CL0: 3.0 | CL1: 4.8 | HR0: 0.338/SR0: 0.326 | HR1: 0.246/SR1: 0.224 | LR: 1.00e-04
[2026-05-24 11:58:02] Epoch 1 | Step 1800 | Loss: 1.0193 | LM: 0.3697 | LB: 1.3076 | CL0: 3.0 | CL1: 4.8 | HR0: 0.338/SR0: 0.326 | HR1: 0.246/SR1: 0.224 | LR: 1.00e-04
[2026-05-24 11:58:14] Epoch 1 | Step 1810 | Loss: 1.0188 | LM: 0.3692 | LB: 1.3066 | CL0: 3.0 | CL1: 4.8 | HR0: 0.338/SR0: 0.326 | HR1: 0.245/SR1: 0.223 | LR: 1.00e-04
[2026-05-24 11:58:25] Epoch 1 | Step 1820 | Loss: 1.0183 | LM: 0.3694 | LB: 1.3057 | CL0: 3.0 | CL1: 4.8 | HR0: 0.338/SR0: 0.325 | HR1: 0.245/SR1: 0.223 | LR: 1.00e-04
[2026-05-24 11:58:37] Epoch 1 | Step 1830 | Loss: 1.0178 | LM: 0.3695 | LB: 1.3047 | CL0: 3.0 | CL1: 4.8 | HR0: 0.338/SR0: 0.325 | HR1: 0.244/SR1: 0.223 | LR: 1.00e-04
[2026-05-24 11:58:49] Epoch 1 | Step 1840 | Loss: 1.0174 | LM: 0.3696 | LB: 1.3038 | CL0: 3.0 | CL1: 4.8 | HR0: 0.337/SR0: 0.325 | HR1: 0.244/SR1: 0.222 | LR: 1.00e-04
[2026-05-24 11:59:00] Epoch 1 | Step 1850 | Loss: 1.0170 | LM: 0.3696 | LB: 1.3029 | CL0: 3.0 | CL1: 4.8 | HR0: 0.337/SR0: 0.325 | HR1: 0.243/SR1: 0.222 | LR: 1.00e-04
[2026-05-24 11:59:12] Epoch 1 | Step 1860 | Loss: 1.0165 | LM: 0.3693 | LB: 1.3020 | CL0: 3.0 | CL1: 4.8 | HR0: 0.337/SR0: 0.324 | HR1: 0.243/SR1: 0.221 | LR: 1.00e-04
[2026-05-24 11:59:24] Epoch 1 | Step 1870 | Loss: 1.0160 | LM: 0.3693 | LB: 1.3011 | CL0: 3.0 | CL1: 4.8 | HR0: 0.337/SR0: 0.324 | HR1: 0.243/SR1: 0.221 | LR: 1.00e-04
[2026-05-24 11:59:35] Epoch 1 | Step 1880 | Loss: 1.0154 | LM: 0.3693 | LB: 1.3002 | CL0: 3.0 | CL1: 4.8 | HR0: 0.337/SR0: 0.324 | HR1: 0.242/SR1: 0.221 | LR: 1.00e-04
[2026-05-24 11:59:47] Epoch 1 | Step 1890 | Loss: 1.0151 | LM: 0.3695 | LB: 1.2994 | CL0: 3.0 | CL1: 4.9 | HR0: 0.337/SR0: 0.324 | HR1: 0.242/SR1: 0.220 | LR: 1.00e-04
[2026-05-24 11:59:58] Epoch 1 | Step 1900 | Loss: 1.0148 | LM: 0.3698 | LB: 1.2984 | CL0: 3.0 | CL1: 4.9 | HR0: 0.336/SR0: 0.323 | HR1: 0.241/SR1: 0.220 | LR: 1.00e-04
[2026-05-24 12:00:10] Epoch 1 | Step 1910 | Loss: 1.0143 | LM: 0.3700 | LB: 1.2975 | CL0: 3.0 | CL1: 4.9 | HR0: 0.336/SR0: 0.323 | HR1: 0.241/SR1: 0.219 | LR: 1.00e-04
[2026-05-24 12:00:22] Epoch 1 | Step 1920 | Loss: 1.0137 | LM: 0.3704 | LB: 1.2966 | CL0: 3.0 | CL1: 4.9 | HR0: 0.336/SR0: 0.323 | HR1: 0.240/SR1: 0.219 | LR: 1.00e-04
[2026-05-24 12:00:33] Epoch 1 | Step 1930 | Loss: 1.0133 | LM: 0.3705 | LB: 1.2957 | CL0: 3.0 | CL1: 4.9 | HR0: 0.336/SR0: 0.323 | HR1: 0.240/SR1: 0.218 | LR: 1.00e-04
[2026-05-24 12:00:45] Epoch 1 | Step 1940 | Loss: 1.0129 | LM: 0.3706 | LB: 1.2948 | CL0: 3.0 | CL1: 4.9 | HR0: 0.336/SR0: 0.322 | HR1: 0.240/SR1: 0.218 | LR: 1.00e-04
[2026-05-24 12:00:56] Epoch 1 | Step 1950 | Loss: 1.0124 | LM: 0.3706 | LB: 1.2940 | CL0: 3.0 | CL1: 4.9 | HR0: 0.335/SR0: 0.322 | HR1: 0.239/SR1: 0.218 | LR: 1.00e-04
[2026-05-24 12:01:08] Epoch 1 | Step 1960 | Loss: 1.0119 | LM: 0.3705 | LB: 1.2932 | CL0: 3.0 | CL1: 4.9 | HR0: 0.335/SR0: 0.322 | HR1: 0.239/SR1: 0.217 | LR: 1.00e-04
[2026-05-24 12:01:20] Epoch 1 | Step 1970 | Loss: 1.0114 | LM: 0.3707 | LB: 1.2922 | CL0: 3.0 | CL1: 4.9 | HR0: 0.335/SR0: 0.322 | HR1: 0.238/SR1: 0.217 | LR: 1.00e-04
[2026-05-24 12:01:31] Epoch 1 | Step 1980 | Loss: 1.0108 | LM: 0.3706 | LB: 1.2913 | CL0: 3.0 | CL1: 4.9 | HR0: 0.335/SR0: 0.321 | HR1: 0.238/SR1: 0.217 | LR: 1.00e-04
[2026-05-24 12:01:42] Epoch 1 | Step 1990 | Loss: 1.0104 | LM: 0.3708 | LB: 1.2905 | CL0: 3.0 | CL1: 4.9 | HR0: 0.335/SR0: 0.321 | HR1: 0.238/SR1: 0.216 | LR: 1.00e-04
[2026-05-24 12:01:54] Epoch 1 | Step 2000 | Loss: 1.0098 | LM: 0.3706 | LB: 1.2897 | CL0: 3.0 | CL1: 4.9 | HR0: 0.335/SR0: 0.321 | HR1: 0.237/SR1: 0.216 | LR: 1.00e-04
[2026-05-24 12:01:56] Validation | Batch 10/1463 | Loss: 0.8743 | LM_LOSS: 0.3217 | LB_LOSS: 1.1052
[2026-05-24 12:01:57] Validation | Batch 20/1463 | Loss: 0.8888 | LM_LOSS: 0.3322 | LB_LOSS: 1.1131
[2026-05-24 12:01:59] Validation | Batch 30/1463 | Loss: 0.8960 | LM_LOSS: 0.3385 | LB_LOSS: 1.1150
[2026-05-24 12:02:01] Validation | Batch 40/1463 | Loss: 0.9066 | LM_LOSS: 0.3475 | LB_LOSS: 1.1181
[2026-05-24 12:02:03] Validation | Batch 50/1463 | Loss: 0.9149 | LM_LOSS: 0.3567 | LB_LOSS: 1.1164
[2026-05-24 12:02:05] Validation | Batch 60/1463 | Loss: 0.9157 | LM_LOSS: 0.3576 | LB_LOSS: 1.1162
[2026-05-24 12:02:07] Validation | Batch 70/1463 | Loss: 0.9166 | LM_LOSS: 0.3584 | LB_LOSS: 1.1165
[2026-05-24 12:02:10] Validation | Batch 80/1463 | Loss: 0.9184 | LM_LOSS: 0.3600 | LB_LOSS: 1.1167
[2026-05-24 12:02:11] Validation | Batch 90/1463 | Loss: 0.9175 | LM_LOSS: 0.3593 | LB_LOSS: 1.1165
[2026-05-24 12:02:13] Validation | Batch 100/1463 | Loss: 0.9179 | LM_LOSS: 0.3597 | LB_LOSS: 1.1165
[2026-05-24 12:02:15] Validation | Batch 110/1463 | Loss: 0.9164 | LM_LOSS: 0.3576 | LB_LOSS: 1.1175
[2026-05-24 12:02:17] Validation | Batch 120/1463 | Loss: 0.9182 | LM_LOSS: 0.3593 | LB_LOSS: 1.1179
[2026-05-24 12:02:18] Validation | Batch 130/1463 | Loss: 0.9204 | LM_LOSS: 0.3614 | LB_LOSS: 1.1179
[2026-05-24 12:02:21] Validation | Batch 140/1463 | Loss: 0.9212 | LM_LOSS: 0.3624 | LB_LOSS: 1.1176
[2026-05-24 12:02:23] Validation | Batch 150/1463 | Loss: 0.9197 | LM_LOSS: 0.3607 | LB_LOSS: 1.1180
[2026-05-24 12:02:25] Validation | Batch 160/1463 | Loss: 0.9202 | LM_LOSS: 0.3614 | LB_LOSS: 1.1176
[2026-05-24 12:02:27] Validation | Batch 170/1463 | Loss: 0.9199 | LM_LOSS: 0.3611 | LB_LOSS: 1.1177
[2026-05-24 12:02:29] Validation | Batch 180/1463 | Loss: 0.9211 | LM_LOSS: 0.3622 | LB_LOSS: 1.1177
[2026-05-24 12:02:31] Validation | Batch 190/1463 | Loss: 0.9220 | LM_LOSS: 0.3631 | LB_LOSS: 1.1179
[2026-05-24 12:02:32] Validation | Batch 200/1463 | Loss: 0.9220 | LM_LOSS: 0.3630 | LB_LOSS: 1.1179
[2026-05-24 12:02:34] Validation | Batch 210/1463 | Loss: 0.9224 | LM_LOSS: 0.3635 | LB_LOSS: 1.1179
[2026-05-24 12:02:36] Validation | Batch 220/1463 | Loss: 0.9218 | LM_LOSS: 0.3628 | LB_LOSS: 1.1180
[2026-05-24 12:02:38] Validation | Batch 230/1463 | Loss: 0.9235 | LM_LOSS: 0.3647 | LB_LOSS: 1.1176
[2026-05-24 12:02:40] Validation | Batch 240/1463 | Loss: 0.9244 | LM_LOSS: 0.3656 | LB_LOSS: 1.1175
[2026-05-24 12:02:42] Validation | Batch 250/1463 | Loss: 0.9235 | LM_LOSS: 0.3647 | LB_LOSS: 1.1176
[2026-05-24 12:02:44] Validation | Batch 260/1463 | Loss: 0.9254 | LM_LOSS: 0.3663 | LB_LOSS: 1.1181
[2026-05-24 12:02:46] Validation | Batch 270/1463 | Loss: 0.9240 | LM_LOSS: 0.3649 | LB_LOSS: 1.1182
[2026-05-24 12:02:48] Validation | Batch 280/1463 | Loss: 0.9249 | LM_LOSS: 0.3658 | LB_LOSS: 1.1183
[2026-05-24 12:02:50] Validation | Batch 290/1463 | Loss: 0.9243 | LM_LOSS: 0.3651 | LB_LOSS: 1.1183
[2026-05-24 12:02:52] Validation | Batch 300/1463 | Loss: 0.9247 | LM_LOSS: 0.3654 | LB_LOSS: 1.1186
[2026-05-24 12:02:54] Validation | Batch 310/1463 | Loss: 0.9256 | LM_LOSS: 0.3663 | LB_LOSS: 1.1186
[2026-05-24 12:02:55] Validation | Batch 320/1463 | Loss: 0.9237 | LM_LOSS: 0.3647 | LB_LOSS: 1.1181
[2026-05-24 12:02:57] Validation | Batch 330/1463 | Loss: 0.9239 | LM_LOSS: 0.3648 | LB_LOSS: 1.1181
[2026-05-24 12:02:59] Validation | Batch 340/1463 | Loss: 0.9234 | LM_LOSS: 0.3644 | LB_LOSS: 1.1181
[2026-05-24 12:03:01] Validation | Batch 350/1463 | Loss: 0.9240 | LM_LOSS: 0.3650 | LB_LOSS: 1.1181
[2026-05-24 12:03:03] Validation | Batch 360/1463 | Loss: 0.9237 | LM_LOSS: 0.3646 | LB_LOSS: 1.1182
[2026-05-24 12:03:04] Validation | Batch 370/1463 | Loss: 0.9237 | LM_LOSS: 0.3646 | LB_LOSS: 1.1184
[2026-05-24 12:03:06] Validation | Batch 380/1463 | Loss: 0.9235 | LM_LOSS: 0.3645 | LB_LOSS: 1.1181
[2026-05-24 12:03:08] Validation | Batch 390/1463 | Loss: 0.9244 | LM_LOSS: 0.3653 | LB_LOSS: 1.1181
[2026-05-24 12:03:10] Validation | Batch 400/1463 | Loss: 0.9244 | LM_LOSS: 0.3652 | LB_LOSS: 1.1183
[2026-05-24 12:03:12] Validation | Batch 410/1463 | Loss: 0.9241 | LM_LOSS: 0.3649 | LB_LOSS: 1.1185
[2026-05-24 12:03:14] Validation | Batch 420/1463 | Loss: 0.9242 | LM_LOSS: 0.3650 | LB_LOSS: 1.1185
[2026-05-24 12:03:16] Validation | Batch 430/1463 | Loss: 0.9237 | LM_LOSS: 0.3644 | LB_LOSS: 1.1187
[2026-05-24 12:03:18] Validation | Batch 440/1463 | Loss: 0.9241 | LM_LOSS: 0.3647 | LB_LOSS: 1.1188
[2026-05-24 12:03:19] Validation | Batch 450/1463 | Loss: 0.9238 | LM_LOSS: 0.3643 | LB_LOSS: 1.1189
[2026-05-24 12:03:21] Validation | Batch 460/1463 | Loss: 0.9238 | LM_LOSS: 0.3643 | LB_LOSS: 1.1189
[2026-05-24 12:03:23] Validation | Batch 470/1463 | Loss: 0.9244 | LM_LOSS: 0.3651 | LB_LOSS: 1.1187
[2026-05-24 12:03:26] Validation | Batch 480/1463 | Loss: 0.9242 | LM_LOSS: 0.3649 | LB_LOSS: 1.1185
[2026-05-24 12:03:27] Validation | Batch 490/1463 | Loss: 0.9240 | LM_LOSS: 0.3647 | LB_LOSS: 1.1185
[2026-05-24 12:03:30] Validation | Batch 500/1463 | Loss: 0.9237 | LM_LOSS: 0.3645 | LB_LOSS: 1.1185
[2026-05-24 12:03:32] Validation | Batch 510/1463 | Loss: 0.9234 | LM_LOSS: 0.3642 | LB_LOSS: 1.1185
[2026-05-24 12:03:33] Validation | Batch 520/1463 | Loss: 0.9230 | LM_LOSS: 0.3636 | LB_LOSS: 1.1186
[2026-05-24 12:03:35] Validation | Batch 530/1463 | Loss: 0.9231 | LM_LOSS: 0.3638 | LB_LOSS: 1.1186
[2026-05-24 12:03:37] Validation | Batch 540/1463 | Loss: 0.9236 | LM_LOSS: 0.3642 | LB_LOSS: 1.1187
[2026-05-24 12:03:38] Validation | Batch 550/1463 | Loss: 0.9231 | LM_LOSS: 0.3637 | LB_LOSS: 1.1188
[2026-05-24 12:03:40] Validation | Batch 560/1463 | Loss: 0.9237 | LM_LOSS: 0.3641 | LB_LOSS: 1.1191
[2026-05-24 12:03:42] Validation | Batch 570/1463 | Loss: 0.9237 | LM_LOSS: 0.3642 | LB_LOSS: 1.1190
[2026-05-24 12:03:45] Validation | Batch 580/1463 | Loss: 0.9234 | LM_LOSS: 0.3640 | LB_LOSS: 1.1190
[2026-05-24 12:03:47] Validation | Batch 590/1463 | Loss: 0.9234 | LM_LOSS: 0.3639 | LB_LOSS: 1.1191
[2026-05-24 12:03:49] Validation | Batch 600/1463 | Loss: 0.9238 | LM_LOSS: 0.3642 | LB_LOSS: 1.1193
[2026-05-24 12:03:51] Validation | Batch 610/1463 | Loss: 0.9238 | LM_LOSS: 0.3642 | LB_LOSS: 1.1193
[2026-05-24 12:03:53] Validation | Batch 620/1463 | Loss: 0.9234 | LM_LOSS: 0.3637 | LB_LOSS: 1.1193
[2026-05-24 12:03:55] Validation | Batch 630/1463 | Loss: 0.9231 | LM_LOSS: 0.3634 | LB_LOSS: 1.1194
[2026-05-24 12:03:57] Validation | Batch 640/1463 | Loss: 0.9229 | LM_LOSS: 0.3631 | LB_LOSS: 1.1195
[2026-05-24 12:03:58] Validation | Batch 650/1463 | Loss: 0.9223 | LM_LOSS: 0.3625 | LB_LOSS: 1.1194
[2026-05-24 12:04:00] Validation | Batch 660/1463 | Loss: 0.9217 | LM_LOSS: 0.3620 | LB_LOSS: 1.1193
[2026-05-24 12:04:02] Validation | Batch 670/1463 | Loss: 0.9214 | LM_LOSS: 0.3617 | LB_LOSS: 1.1192
[2026-05-24 12:04:04] Validation | Batch 680/1463 | Loss: 0.9212 | LM_LOSS: 0.3616 | LB_LOSS: 1.1191
[2026-05-24 12:04:06] Validation | Batch 690/1463 | Loss: 0.9216 | LM_LOSS: 0.3620 | LB_LOSS: 1.1192
[2026-05-24 12:04:08] Validation | Batch 700/1463 | Loss: 0.9215 | LM_LOSS: 0.3619 | LB_LOSS: 1.1191
[2026-05-24 12:04:09] Validation | Batch 710/1463 | Loss: 0.9220 | LM_LOSS: 0.3624 | LB_LOSS: 1.1193
[2026-05-24 12:04:12] Validation | Batch 720/1463 | Loss: 0.9228 | LM_LOSS: 0.3631 | LB_LOSS: 1.1194
[2026-05-24 12:04:13] Validation | Batch 730/1463 | Loss: 0.9224 | LM_LOSS: 0.3627 | LB_LOSS: 1.1194
[2026-05-24 12:04:15] Validation | Batch 740/1463 | Loss: 0.9222 | LM_LOSS: 0.3625 | LB_LOSS: 1.1194
[2026-05-24 12:04:16] Validation | Batch 750/1463 | Loss: 0.9220 | LM_LOSS: 0.3624 | LB_LOSS: 1.1194
[2026-05-24 12:04:18] Validation | Batch 760/1463 | Loss: 0.9217 | LM_LOSS: 0.3620 | LB_LOSS: 1.1194
[2026-05-24 12:04:20] Validation | Batch 770/1463 | Loss: 0.9214 | LM_LOSS: 0.3617 | LB_LOSS: 1.1195
[2026-05-24 12:04:21] Validation | Batch 780/1463 | Loss: 0.9211 | LM_LOSS: 0.3614 | LB_LOSS: 1.1194
[2026-05-24 12:04:23] Validation | Batch 790/1463 | Loss: 0.9212 | LM_LOSS: 0.3616 | LB_LOSS: 1.1193
[2026-05-24 12:04:25] Validation | Batch 800/1463 | Loss: 0.9211 | LM_LOSS: 0.3615 | LB_LOSS: 1.1193
[2026-05-24 12:04:26] Validation | Batch 810/1463 | Loss: 0.9207 | LM_LOSS: 0.3611 | LB_LOSS: 1.1192
[2026-05-24 12:04:28] Validation | Batch 820/1463 | Loss: 0.9209 | LM_LOSS: 0.3613 | LB_LOSS: 1.1191
[2026-05-24 12:04:30] Validation | Batch 830/1463 | Loss: 0.9211 | LM_LOSS: 0.3616 | LB_LOSS: 1.1191
[2026-05-24 12:04:33] Validation | Batch 840/1463 | Loss: 0.9211 | LM_LOSS: 0.3615 | LB_LOSS: 1.1193
[2026-05-24 12:04:35] Validation | Batch 850/1463 | Loss: 0.9213 | LM_LOSS: 0.3616 | LB_LOSS: 1.1193
[2026-05-24 12:04:37] Validation | Batch 860/1463 | Loss: 0.9212 | LM_LOSS: 0.3615 | LB_LOSS: 1.1193
[2026-05-24 12:04:38] Validation | Batch 870/1463 | Loss: 0.9212 | LM_LOSS: 0.3615 | LB_LOSS: 1.1194
[2026-05-24 12:04:40] Validation | Batch 880/1463 | Loss: 0.9205 | LM_LOSS: 0.3608 | LB_LOSS: 1.1193
[2026-05-24 12:04:42] Validation | Batch 890/1463 | Loss: 0.9204 | LM_LOSS: 0.3608 | LB_LOSS: 1.1192
[2026-05-24 12:04:44] Validation | Batch 900/1463 | Loss: 0.9201 | LM_LOSS: 0.3605 | LB_LOSS: 1.1192
[2026-05-24 12:04:46] Validation | Batch 910/1463 | Loss: 0.9200 | LM_LOSS: 0.3604 | LB_LOSS: 1.1192
[2026-05-24 12:04:48] Validation | Batch 920/1463 | Loss: 0.9202 | LM_LOSS: 0.3606 | LB_LOSS: 1.1192
[2026-05-24 12:04:50] Validation | Batch 930/1463 | Loss: 0.9199 | LM_LOSS: 0.3603 | LB_LOSS: 1.1192
[2026-05-24 12:04:52] Validation | Batch 940/1463 | Loss: 0.9195 | LM_LOSS: 0.3600 | LB_LOSS: 1.1190
[2026-05-24 12:04:54] Validation | Batch 950/1463 | Loss: 0.9199 | LM_LOSS: 0.3603 | LB_LOSS: 1.1190
[2026-05-24 12:04:56] Validation | Batch 960/1463 | Loss: 0.9199 | LM_LOSS: 0.3604 | LB_LOSS: 1.1190
[2026-05-24 12:04:58] Validation | Batch 970/1463 | Loss: 0.9199 | LM_LOSS: 0.3605 | LB_LOSS: 1.1189
[2026-05-24 12:05:00] Validation | Batch 980/1463 | Loss: 0.9202 | LM_LOSS: 0.3608 | LB_LOSS: 1.1188
[2026-05-24 12:05:02] Validation | Batch 990/1463 | Loss: 0.9205 | LM_LOSS: 0.3610 | LB_LOSS: 1.1189
[2026-05-24 12:05:04] Validation | Batch 1000/1463 | Loss: 0.9211 | LM_LOSS: 0.3617 | LB_LOSS: 1.1189
[2026-05-24 12:05:06] Validation | Batch 1010/1463 | Loss: 0.9212 | LM_LOSS: 0.3617 | LB_LOSS: 1.1190
[2026-05-24 12:05:08] Validation | Batch 1020/1463 | Loss: 0.9214 | LM_LOSS: 0.3618 | LB_LOSS: 1.1191
[2026-05-24 12:05:10] Validation | Batch 1030/1463 | Loss: 0.9218 | LM_LOSS: 0.3622 | LB_LOSS: 1.1192
[2026-05-24 12:05:12] Validation | Batch 1040/1463 | Loss: 0.9213 | LM_LOSS: 0.3617 | LB_LOSS: 1.1191
[2026-05-24 12:05:14] Validation | Batch 1050/1463 | Loss: 0.9212 | LM_LOSS: 0.3617 | LB_LOSS: 1.1190
[2026-05-24 12:05:16] Validation | Batch 1060/1463 | Loss: 0.9211 | LM_LOSS: 0.3616 | LB_LOSS: 1.1190
[2026-05-24 12:05:18] Validation | Batch 1070/1463 | Loss: 0.9212 | LM_LOSS: 0.3617 | LB_LOSS: 1.1191
[2026-05-24 12:05:20] Validation | Batch 1080/1463 | Loss: 0.9209 | LM_LOSS: 0.3613 | LB_LOSS: 1.1191
[2026-05-24 12:05:22] Validation | Batch 1090/1463 | Loss: 0.9209 | LM_LOSS: 0.3614 | LB_LOSS: 1.1190
[2026-05-24 12:05:23] Validation | Batch 1100/1463 | Loss: 0.9208 | LM_LOSS: 0.3614 | LB_LOSS: 1.1189
[2026-05-24 12:05:25] Validation | Batch 1110/1463 | Loss: 0.9208 | LM_LOSS: 0.3614 | LB_LOSS: 1.1190
[2026-05-24 12:05:27] Validation | Batch 1120/1463 | Loss: 0.9207 | LM_LOSS: 0.3612 | LB_LOSS: 1.1190
[2026-05-24 12:05:29] Validation | Batch 1130/1463 | Loss: 0.9205 | LM_LOSS: 0.3610 | LB_LOSS: 1.1190
[2026-05-24 12:05:31] Validation | Batch 1140/1463 | Loss: 0.9207 | LM_LOSS: 0.3612 | LB_LOSS: 1.1190
[2026-05-24 12:05:33] Validation | Batch 1150/1463 | Loss: 0.9206 | LM_LOSS: 0.3611 | LB_LOSS: 1.1189
[2026-05-24 12:05:35] Validation | Batch 1160/1463 | Loss: 0.9205 | LM_LOSS: 0.3611 | LB_LOSS: 1.1190
[2026-05-24 12:05:37] Validation | Batch 1170/1463 | Loss: 0.9205 | LM_LOSS: 0.3610 | LB_LOSS: 1.1190
[2026-05-24 12:05:39] Validation | Batch 1180/1463 | Loss: 0.9205 | LM_LOSS: 0.3610 | LB_LOSS: 1.1190
[2026-05-24 12:05:41] Validation | Batch 1190/1463 | Loss: 0.9206 | LM_LOSS: 0.3611 | LB_LOSS: 1.1190
[2026-05-24 12:05:43] Validation | Batch 1200/1463 | Loss: 0.9207 | LM_LOSS: 0.3612 | LB_LOSS: 1.1190
[2026-05-24 12:05:45] Validation | Batch 1210/1463 | Loss: 0.9210 | LM_LOSS: 0.3615 | LB_LOSS: 1.1190
[2026-05-24 12:05:47] Validation | Batch 1220/1463 | Loss: 0.9214 | LM_LOSS: 0.3619 | LB_LOSS: 1.1191
[2026-05-24 12:05:49] Validation | Batch 1230/1463 | Loss: 0.9213 | LM_LOSS: 0.3618 | LB_LOSS: 1.1190
[2026-05-24 12:05:51] Validation | Batch 1240/1463 | Loss: 0.9217 | LM_LOSS: 0.3621 | LB_LOSS: 1.1190
[2026-05-24 12:05:53] Validation | Batch 1250/1463 | Loss: 0.9219 | LM_LOSS: 0.3624 | LB_LOSS: 1.1190
[2026-05-24 12:05:55] Validation | Batch 1260/1463 | Loss: 0.9219 | LM_LOSS: 0.3623 | LB_LOSS: 1.1191
[2026-05-24 12:05:57] Validation | Batch 1270/1463 | Loss: 0.9217 | LM_LOSS: 0.3621 | LB_LOSS: 1.1191
[2026-05-24 12:05:59] Validation | Batch 1280/1463 | Loss: 0.9214 | LM_LOSS: 0.3619 | LB_LOSS: 1.1190
[2026-05-24 12:06:01] Validation | Batch 1290/1463 | Loss: 0.9214 | LM_LOSS: 0.3619 | LB_LOSS: 1.1190
[2026-05-24 12:06:03] Validation | Batch 1300/1463 | Loss: 0.9212 | LM_LOSS: 0.3617 | LB_LOSS: 1.1190
[2026-05-24 12:06:05] Validation | Batch 1310/1463 | Loss: 0.9211 | LM_LOSS: 0.3616 | LB_LOSS: 1.1190
[2026-05-24 12:06:06] Validation | Batch 1320/1463 | Loss: 0.9212 | LM_LOSS: 0.3617 | LB_LOSS: 1.1190
[2026-05-24 12:06:08] Validation | Batch 1330/1463 | Loss: 0.9212 | LM_LOSS: 0.3618 | LB_LOSS: 1.1189
[2026-05-24 12:06:10] Validation | Batch 1340/1463 | Loss: 0.9215 | LM_LOSS: 0.3621 | LB_LOSS: 1.1190
[2026-05-24 12:06:12] Validation | Batch 1350/1463 | Loss: 0.9216 | LM_LOSS: 0.3621 | LB_LOSS: 1.1190
[2026-05-24 12:06:14] Validation | Batch 1360/1463 | Loss: 0.9218 | LM_LOSS: 0.3624 | LB_LOSS: 1.1189
[2026-05-24 12:06:16] Validation | Batch 1370/1463 | Loss: 0.9221 | LM_LOSS: 0.3626 | LB_LOSS: 1.1190
[2026-05-24 12:06:18] Validation | Batch 1380/1463 | Loss: 0.9219 | LM_LOSS: 0.3624 | LB_LOSS: 1.1189
[2026-05-24 12:06:20] Validation | Batch 1390/1463 | Loss: 0.9218 | LM_LOSS: 0.3624 | LB_LOSS: 1.1190
[2026-05-24 12:06:22] Validation | Batch 1400/1463 | Loss: 0.9221 | LM_LOSS: 0.3627 | LB_LOSS: 1.1189
[2026-05-24 12:06:23] Validation | Batch 1410/1463 | Loss: 0.9223 | LM_LOSS: 0.3629 | LB_LOSS: 1.1189
[2026-05-24 12:06:25] Validation | Batch 1420/1463 | Loss: 0.9223 | LM_LOSS: 0.3629 | LB_LOSS: 1.1189
[2026-05-24 12:06:27] Validation | Batch 1430/1463 | Loss: 0.9224 | LM_LOSS: 0.3630 | LB_LOSS: 1.1189
[2026-05-24 12:06:29] Validation | Batch 1440/1463 | Loss: 0.9228 | LM_LOSS: 0.3634 | LB_LOSS: 1.1189
[2026-05-24 12:06:31] Validation | Batch 1450/1463 | Loss: 0.9225 | LM_LOSS: 0.3631 | LB_LOSS: 1.1189
[2026-05-24 12:06:33] Validation | Batch 1460/1463 | Loss: 0.9228 | LM_LOSS: 0.3634 | LB_LOSS: 1.1188
[2026-05-24 12:06:34] Validation | Batch 1463/1463 | Loss: 0.9227 | LM_LOSS: 0.3633 | LB_LOSS: 1.1188
[2026-05-24 12:06:34] Validation | Loss: 0.9227 | LM_LOSS: 0.3633 | LB_LOSS: 1.1188 | PPL: 1.44 | Time: 279.93s
[2026-05-24 12:06:38] New best model saved! Val loss: 0.9227
[2026-05-24 12:06:49] Epoch 1 | Step 2010 | Loss: 1.0095 | LM: 0.3705 | LB: 1.2889 | CL0: 3.0 | CL1: 5.0 | HR0: 0.334/SR0: 0.321 | HR1: 0.237/SR1: 0.215 | LR: 1.00e-04
[2026-05-24 12:07:01] Epoch 1 | Step 2020 | Loss: 1.0092 | LM: 0.3706 | LB: 1.2880 | CL0: 3.0 | CL1: 5.0 | HR0: 0.334/SR0: 0.320 | HR1: 0.237/SR1: 0.215 | LR: 1.00e-04
[2026-05-24 12:07:12] Epoch 1 | Step 2030 | Loss: 1.0086 | LM: 0.3703 | LB: 1.2872 | CL0: 3.0 | CL1: 5.0 | HR0: 0.334/SR0: 0.320 | HR1: 0.236/SR1: 0.215 | LR: 1.00e-04
[2026-05-24 12:07:23] Epoch 1 | Step 2040 | Loss: 1.0083 | LM: 0.3709 | LB: 1.2863 | CL0: 3.0 | CL1: 5.0 | HR0: 0.334/SR0: 0.320 | HR1: 0.236/SR1: 0.214 | LR: 1.00e-04
[2026-05-24 12:07:34] Epoch 1 | Step 2050 | Loss: 1.0080 | LM: 0.3706 | LB: 1.2855 | CL0: 3.0 | CL1: 5.0 | HR0: 0.334/SR0: 0.319 | HR1: 0.236/SR1: 0.214 | LR: 1.00e-04
[2026-05-24 12:07:45] Epoch 1 | Step 2060 | Loss: 1.0075 | LM: 0.3708 | LB: 1.2846 | CL0: 3.0 | CL1: 5.0 | HR0: 0.333/SR0: 0.319 | HR1: 0.235/SR1: 0.214 | LR: 1.00e-04
[2026-05-24 12:07:55] Epoch 1 | Step 2070 | Loss: 1.0071 | LM: 0.3710 | LB: 1.2838 | CL0: 3.0 | CL1: 5.0 | HR0: 0.333/SR0: 0.319 | HR1: 0.235/SR1: 0.213 | LR: 1.00e-04
[2026-05-24 12:08:06] Epoch 1 | Step 2080 | Loss: 1.0067 | LM: 0.3713 | LB: 1.2830 | CL0: 3.0 | CL1: 5.0 | HR0: 0.333/SR0: 0.319 | HR1: 0.235/SR1: 0.213 | LR: 1.00e-04
[2026-05-24 12:08:17] Epoch 1 | Step 2090 | Loss: 1.0061 | LM: 0.3708 | LB: 1.2822 | CL0: 3.0 | CL1: 5.0 | HR0: 0.333/SR0: 0.318 | HR1: 0.234/SR1: 0.213 | LR: 1.00e-04
[2026-05-24 12:08:28] Epoch 1 | Step 2100 | Loss: 1.0058 | LM: 0.3710 | LB: 1.2815 | CL0: 3.0 | CL1: 5.0 | HR0: 0.333/SR0: 0.318 | HR1: 0.234/SR1: 0.212 | LR: 1.00e-04
[2026-05-24 12:08:39] Epoch 1 | Step 2110 | Loss: 1.0054 | LM: 0.3710 | LB: 1.2807 | CL0: 3.0 | CL1: 5.0 | HR0: 0.333/SR0: 0.318 | HR1: 0.233/SR1: 0.212 | LR: 1.00e-04
[2026-05-24 12:08:49] Epoch 1 | Step 2120 | Loss: 1.0049 | LM: 0.3708 | LB: 1.2799 | CL0: 3.0 | CL1: 5.0 | HR0: 0.332/SR0: 0.318 | HR1: 0.233/SR1: 0.212 | LR: 1.00e-04
[2026-05-24 12:09:00] Epoch 1 | Step 2130 | Loss: 1.0046 | LM: 0.3710 | LB: 1.2792 | CL0: 3.0 | CL1: 5.0 | HR0: 0.332/SR0: 0.318 | HR1: 0.233/SR1: 0.211 | LR: 1.00e-04
[2026-05-24 12:09:11] Epoch 1 | Step 2140 | Loss: 1.0041 | LM: 0.3708 | LB: 1.2784 | CL0: 3.0 | CL1: 5.0 | HR0: 0.332/SR0: 0.317 | HR1: 0.232/SR1: 0.211 | LR: 1.00e-04
[2026-05-24 12:09:22] Epoch 1 | Step 2150 | Loss: 1.0038 | LM: 0.3708 | LB: 1.2777 | CL0: 3.0 | CL1: 5.0 | HR0: 0.332/SR0: 0.317 | HR1: 0.232/SR1: 0.211 | LR: 1.00e-04
[2026-05-24 12:09:32] Epoch 1 | Step 2160 | Loss: 1.0035 | LM: 0.3708 | LB: 1.2770 | CL0: 3.0 | CL1: 5.0 | HR0: 0.332/SR0: 0.317 | HR1: 0.232/SR1: 0.210 | LR: 1.00e-04
[2026-05-24 12:09:44] Epoch 1 | Step 2170 | Loss: 1.0031 | LM: 0.3709 | LB: 1.2762 | CL0: 3.0 | CL1: 5.0 | HR0: 0.332/SR0: 0.317 | HR1: 0.231/SR1: 0.210 | LR: 1.00e-04
[2026-05-24 12:09:54] Epoch 1 | Step 2180 | Loss: 1.0026 | LM: 0.3707 | LB: 1.2755 | CL0: 3.0 | CL1: 5.1 | HR0: 0.331/SR0: 0.316 | HR1: 0.231/SR1: 0.210 | LR: 1.00e-04
[2026-05-24 12:10:05] Epoch 1 | Step 2190 | Loss: 1.0024 | LM: 0.3708 | LB: 1.2746 | CL0: 3.0 | CL1: 5.1 | HR0: 0.331/SR0: 0.316 | HR1: 0.231/SR1: 0.209 | LR: 1.00e-04
[2026-05-24 12:10:16] Epoch 1 | Step 2200 | Loss: 1.0020 | LM: 0.3707 | LB: 1.2739 | CL0: 3.0 | CL1: 5.1 | HR0: 0.331/SR0: 0.316 | HR1: 0.230/SR1: 0.209 | LR: 1.00e-04
[2026-05-24 12:10:26] Epoch 1 | Step 2210 | Loss: 1.0016 | LM: 0.3707 | LB: 1.2732 | CL0: 3.1 | CL1: 5.1 | HR0: 0.331/SR0: 0.316 | HR1: 0.230/SR1: 0.209 | LR: 1.00e-04
[2026-05-24 12:10:37] Epoch 1 | Step 2220 | Loss: 1.0013 | LM: 0.3709 | LB: 1.2724 | CL0: 3.1 | CL1: 5.1 | HR0: 0.331/SR0: 0.315 | HR1: 0.230/SR1: 0.208 | LR: 1.00e-04
[2026-05-24 12:10:48] Epoch 1 | Step 2230 | Loss: 1.0010 | LM: 0.3710 | LB: 1.2717 | CL0: 3.1 | CL1: 5.1 | HR0: 0.330/SR0: 0.315 | HR1: 0.229/SR1: 0.208 | LR: 1.00e-04
[2026-05-24 12:10:59] Epoch 1 | Step 2240 | Loss: 1.0006 | LM: 0.3707 | LB: 1.2711 | CL0: 3.1 | CL1: 5.1 | HR0: 0.330/SR0: 0.315 | HR1: 0.229/SR1: 0.208 | LR: 1.00e-04
[2026-05-24 12:11:10] Epoch 1 | Step 2250 | Loss: 1.0004 | LM: 0.3708 | LB: 1.2703 | CL0: 3.1 | CL1: 5.1 | HR0: 0.330/SR0: 0.315 | HR1: 0.229/SR1: 0.207 | LR: 1.00e-04
[2026-05-24 12:11:21] Epoch 1 | Step 2260 | Loss: 1.0000 | LM: 0.3710 | LB: 1.2696 | CL0: 3.1 | CL1: 5.1 | HR0: 0.330/SR0: 0.314 | HR1: 0.228/SR1: 0.207 | LR: 1.00e-04
[2026-05-24 12:11:31] Epoch 1 | Step 2270 | Loss: 0.9997 | LM: 0.3709 | LB: 1.2689 | CL0: 3.1 | CL1: 5.1 | HR0: 0.330/SR0: 0.314 | HR1: 0.228/SR1: 0.207 | LR: 1.00e-04
[2026-05-24 12:11:42] Epoch 1 | Step 2280 | Loss: 0.9995 | LM: 0.3711 | LB: 1.2683 | CL0: 3.1 | CL1: 5.1 | HR0: 0.330/SR0: 0.314 | HR1: 0.228/SR1: 0.207 | LR: 1.00e-04
[2026-05-24 12:11:52] Epoch 1 | Step 2290 | Loss: 0.9991 | LM: 0.3711 | LB: 1.2675 | CL0: 3.1 | CL1: 5.1 | HR0: 0.329/SR0: 0.314 | HR1: 0.228/SR1: 0.206 | LR: 1.00e-04
[2026-05-24 12:12:03] Epoch 1 | Step 2300 | Loss: 0.9990 | LM: 0.3711 | LB: 1.2669 | CL0: 3.1 | CL1: 5.1 | HR0: 0.329/SR0: 0.314 | HR1: 0.227/SR1: 0.206 | LR: 1.00e-04
[2026-05-24 12:12:14] Epoch 1 | Step 2310 | Loss: 0.9986 | LM: 0.3710 | LB: 1.2662 | CL0: 3.1 | CL1: 5.1 | HR0: 0.329/SR0: 0.313 | HR1: 0.227/SR1: 0.206 | LR: 1.00e-04
[2026-05-24 12:12:25] Epoch 1 | Step 2320 | Loss: 0.9983 | LM: 0.3708 | LB: 1.2655 | CL0: 3.1 | CL1: 5.1 | HR0: 0.329/SR0: 0.313 | HR1: 0.227/SR1: 0.206 | LR: 1.00e-04
[2026-05-24 12:12:35] Epoch 1 | Step 2330 | Loss: 0.9980 | LM: 0.3707 | LB: 1.2648 | CL0: 3.1 | CL1: 5.1 | HR0: 0.329/SR0: 0.313 | HR1: 0.226/SR1: 0.205 | LR: 1.00e-04
[2026-05-24 12:12:46] Epoch 1 | Step 2340 | Loss: 0.9977 | LM: 0.3708 | LB: 1.2641 | CL0: 3.1 | CL1: 5.2 | HR0: 0.329/SR0: 0.313 | HR1: 0.226/SR1: 0.205 | LR: 1.00e-04
[2026-05-24 12:12:56] Epoch 1 | Step 2350 | Loss: 0.9974 | LM: 0.3707 | LB: 1.2634 | CL0: 3.1 | CL1: 5.2 | HR0: 0.328/SR0: 0.312 | HR1: 0.226/SR1: 0.205 | LR: 1.00e-04
[2026-05-24 12:13:07] Epoch 1 | Step 2360 | Loss: 0.9972 | LM: 0.3707 | LB: 1.2628 | CL0: 3.1 | CL1: 5.2 | HR0: 0.328/SR0: 0.312 | HR1: 0.226/SR1: 0.204 | LR: 1.00e-04
[2026-05-24 12:13:18] Epoch 1 | Step 2370 | Loss: 0.9967 | LM: 0.3705 | LB: 1.2621 | CL0: 3.1 | CL1: 5.2 | HR0: 0.328/SR0: 0.312 | HR1: 0.225/SR1: 0.204 | LR: 1.00e-04
[2026-05-24 12:13:29] Epoch 1 | Step 2380 | Loss: 0.9966 | LM: 0.3707 | LB: 1.2615 | CL0: 3.1 | CL1: 5.2 | HR0: 0.328/SR0: 0.312 | HR1: 0.225/SR1: 0.204 | LR: 1.00e-04
[2026-05-24 12:13:40] Epoch 1 | Step 2390 | Loss: 0.9962 | LM: 0.3706 | LB: 1.2608 | CL0: 3.1 | CL1: 5.2 | HR0: 0.328/SR0: 0.311 | HR1: 0.225/SR1: 0.203 | LR: 1.00e-04
[2026-05-24 12:13:51] Epoch 1 | Step 2400 | Loss: 0.9959 | LM: 0.3705 | LB: 1.2601 | CL0: 3.1 | CL1: 5.2 | HR0: 0.328/SR0: 0.311 | HR1: 0.224/SR1: 0.203 | LR: 1.00e-04
[2026-05-24 12:14:02] Epoch 1 | Step 2410 | Loss: 0.9956 | LM: 0.3707 | LB: 1.2595 | CL0: 3.1 | CL1: 5.2 | HR0: 0.328/SR0: 0.311 | HR1: 0.224/SR1: 0.203 | LR: 1.00e-04
[2026-05-24 12:14:12] Epoch 1 | Step 2420 | Loss: 0.9952 | LM: 0.3706 | LB: 1.2589 | CL0: 3.1 | CL1: 5.2 | HR0: 0.327/SR0: 0.311 | HR1: 0.224/SR1: 0.203 | LR: 1.00e-04
[2026-05-24 12:14:24] Epoch 1 | Step 2430 | Loss: 0.9951 | LM: 0.3707 | LB: 1.2583 | CL0: 3.1 | CL1: 5.2 | HR0: 0.327/SR0: 0.311 | HR1: 0.224/SR1: 0.203 | LR: 1.00e-04
[2026-05-24 12:14:35] Epoch 1 | Step 2440 | Loss: 0.9948 | LM: 0.3706 | LB: 1.2577 | CL0: 3.1 | CL1: 5.2 | HR0: 0.327/SR0: 0.310 | HR1: 0.223/SR1: 0.202 | LR: 1.00e-04
[2026-05-24 12:14:46] Epoch 1 | Step 2450 | Loss: 0.9945 | LM: 0.3705 | LB: 1.2570 | CL0: 3.1 | CL1: 5.2 | HR0: 0.327/SR0: 0.310 | HR1: 0.223/SR1: 0.202 | LR: 1.00e-04
[2026-05-24 12:14:57] Epoch 1 | Step 2460 | Loss: 0.9940 | LM: 0.3704 | LB: 1.2563 | CL0: 3.1 | CL1: 5.2 | HR0: 0.327/SR0: 0.310 | HR1: 0.223/SR1: 0.202 | LR: 1.00e-04
[2026-05-24 12:15:09] Epoch 1 | Step 2470 | Loss: 0.9936 | LM: 0.3701 | LB: 1.2557 | CL0: 3.1 | CL1: 5.2 | HR0: 0.327/SR0: 0.310 | HR1: 0.223/SR1: 0.201 | LR: 1.00e-04
[2026-05-24 12:15:20] Epoch 1 | Step 2480 | Loss: 0.9934 | LM: 0.3704 | LB: 1.2551 | CL0: 3.1 | CL1: 5.2 | HR0: 0.326/SR0: 0.309 | HR1: 0.222/SR1: 0.201 | LR: 1.00e-04
[2026-05-24 12:15:31] Epoch 1 | Step 2490 | Loss: 0.9931 | LM: 0.3706 | LB: 1.2545 | CL0: 3.1 | CL1: 5.2 | HR0: 0.326/SR0: 0.309 | HR1: 0.222/SR1: 0.201 | LR: 1.00e-04
[2026-05-24 12:15:41] Epoch 1 | Step 2500 | Loss: 0.9928 | LM: 0.3704 | LB: 1.2538 | CL0: 3.1 | CL1: 5.2 | HR0: 0.326/SR0: 0.309 | HR1: 0.222/SR1: 0.201 | LR: 1.00e-04
[2026-05-24 12:15:52] Epoch 1 | Step 2510 | Loss: 0.9925 | LM: 0.3705 | LB: 1.2532 | CL0: 3.1 | CL1: 5.2 | HR0: 0.326/SR0: 0.309 | HR1: 0.222/SR1: 0.200 | LR: 1.00e-04
[2026-05-24 12:16:03] Epoch 1 | Step 2520 | Loss: 0.9924 | LM: 0.3705 | LB: 1.2525 | CL0: 3.1 | CL1: 5.2 | HR0: 0.326/SR0: 0.308 | HR1: 0.221/SR1: 0.200 | LR: 1.00e-04
[2026-05-24 12:16:13] Epoch 1 | Step 2530 | Loss: 0.9921 | LM: 0.3706 | LB: 1.2519 | CL0: 3.1 | CL1: 5.3 | HR0: 0.326/SR0: 0.308 | HR1: 0.221/SR1: 0.200 | LR: 1.00e-04
[2026-05-24 12:16:24] Epoch 1 | Step 2540 | Loss: 0.9918 | LM: 0.3708 | LB: 1.2513 | CL0: 3.1 | CL1: 5.3 | HR0: 0.325/SR0: 0.308 | HR1: 0.221/SR1: 0.200 | LR: 1.00e-04
[2026-05-24 12:16:35] Epoch 1 | Step 2550 | Loss: 0.9916 | LM: 0.3710 | LB: 1.2507 | CL0: 3.1 | CL1: 5.3 | HR0: 0.325/SR0: 0.308 | HR1: 0.220/SR1: 0.199 | LR: 1.00e-04
[2026-05-24 12:16:45] Epoch 1 | Step 2560 | Loss: 0.9913 | LM: 0.3711 | LB: 1.2500 | CL0: 3.1 | CL1: 5.3 | HR0: 0.325/SR0: 0.307 | HR1: 0.220/SR1: 0.199 | LR: 1.00e-04
[2026-05-24 12:16:56] Epoch 1 | Step 2570 | Loss: 0.9911 | LM: 0.3711 | LB: 1.2494 | CL0: 3.1 | CL1: 5.3 | HR0: 0.325/SR0: 0.307 | HR1: 0.220/SR1: 0.199 | LR: 1.00e-04
[2026-05-24 12:17:07] Epoch 1 | Step 2580 | Loss: 0.9909 | LM: 0.3711 | LB: 1.2488 | CL0: 3.1 | CL1: 5.3 | HR0: 0.325/SR0: 0.307 | HR1: 0.220/SR1: 0.199 | LR: 1.00e-04
[2026-05-24 12:17:17] Epoch 1 | Step 2590 | Loss: 0.9907 | LM: 0.3713 | LB: 1.2482 | CL0: 3.1 | CL1: 5.3 | HR0: 0.324/SR0: 0.307 | HR1: 0.220/SR1: 0.199 | LR: 1.00e-04
[2026-05-24 12:17:29] Epoch 1 | Step 2600 | Loss: 0.9904 | LM: 0.3712 | LB: 1.2476 | CL0: 3.1 | CL1: 5.3 | HR0: 0.324/SR0: 0.307 | HR1: 0.219/SR1: 0.198 | LR: 1.00e-04
[2026-05-24 12:17:40] Epoch 1 | Step 2610 | Loss: 0.9899 | LM: 0.3710 | LB: 1.2470 | CL0: 3.1 | CL1: 5.3 | HR0: 0.324/SR0: 0.306 | HR1: 0.219/SR1: 0.198 | LR: 1.00e-04
[2026-05-24 12:17:52] Epoch 1 | Step 2620 | Loss: 0.9896 | LM: 0.3708 | LB: 1.2464 | CL0: 3.1 | CL1: 5.3 | HR0: 0.324/SR0: 0.306 | HR1: 0.219/SR1: 0.198 | LR: 1.00e-04
[2026-05-24 12:18:03] Epoch 1 | Step 2630 | Loss: 0.9894 | LM: 0.3709 | LB: 1.2458 | CL0: 3.1 | CL1: 5.3 | HR0: 0.324/SR0: 0.306 | HR1: 0.219/SR1: 0.198 | LR: 1.00e-04
[2026-05-24 12:18:15] Epoch 1 | Step 2640 | Loss: 0.9891 | LM: 0.3708 | LB: 1.2452 | CL0: 3.1 | CL1: 5.3 | HR0: 0.324/SR0: 0.306 | HR1: 0.218/SR1: 0.197 | LR: 1.00e-04
[2026-05-24 12:18:26] Epoch 1 | Step 2650 | Loss: 0.9889 | LM: 0.3710 | LB: 1.2446 | CL0: 3.1 | CL1: 5.3 | HR0: 0.323/SR0: 0.305 | HR1: 0.218/SR1: 0.197 | LR: 1.00e-04
[2026-05-24 12:18:37] Epoch 1 | Step 2660 | Loss: 0.9888 | LM: 0.3710 | LB: 1.2440 | CL0: 3.1 | CL1: 5.3 | HR0: 0.323/SR0: 0.305 | HR1: 0.218/SR1: 0.197 | LR: 1.00e-04
[2026-05-24 12:18:48] Epoch 1 | Step 2670 | Loss: 0.9886 | LM: 0.3712 | LB: 1.2435 | CL0: 3.1 | CL1: 5.3 | HR0: 0.323/SR0: 0.305 | HR1: 0.218/SR1: 0.197 | LR: 1.00e-04
[2026-05-24 12:18:59] Epoch 1 | Step 2680 | Loss: 0.9884 | LM: 0.3713 | LB: 1.2429 | CL0: 3.1 | CL1: 5.3 | HR0: 0.323/SR0: 0.305 | HR1: 0.217/SR1: 0.197 | LR: 1.00e-04
[2026-05-24 12:19:09] Epoch 1 | Step 2690 | Loss: 0.9882 | LM: 0.3715 | LB: 1.2424 | CL0: 3.1 | CL1: 5.3 | HR0: 0.323/SR0: 0.304 | HR1: 0.217/SR1: 0.196 | LR: 1.00e-04
[2026-05-24 12:19:20] Epoch 1 | Step 2700 | Loss: 0.9878 | LM: 0.3713 | LB: 1.2418 | CL0: 3.1 | CL1: 5.3 | HR0: 0.323/SR0: 0.304 | HR1: 0.217/SR1: 0.196 | LR: 1.00e-04
[2026-05-24 12:19:30] Epoch 1 | Step 2710 | Loss: 0.9874 | LM: 0.3714 | LB: 1.2413 | CL0: 3.1 | CL1: 5.3 | HR0: 0.323/SR0: 0.304 | HR1: 0.217/SR1: 0.196 | LR: 1.00e-04
[2026-05-24 12:19:41] Epoch 1 | Step 2720 | Loss: 0.9871 | LM: 0.3713 | LB: 1.2407 | CL0: 3.1 | CL1: 5.3 | HR0: 0.322/SR0: 0.304 | HR1: 0.217/SR1: 0.196 | LR: 1.00e-04
[2026-05-24 12:19:51] Epoch 1 | Step 2730 | Loss: 0.9869 | LM: 0.3713 | LB: 1.2401 | CL0: 3.1 | CL1: 5.3 | HR0: 0.322/SR0: 0.304 | HR1: 0.216/SR1: 0.195 | LR: 1.00e-04
[2026-05-24 12:20:02] Epoch 1 | Step 2740 | Loss: 0.9865 | LM: 0.3714 | LB: 1.2396 | CL0: 3.1 | CL1: 5.3 | HR0: 0.322/SR0: 0.303 | HR1: 0.216/SR1: 0.195 | LR: 1.00e-04
[2026-05-24 12:20:13] Epoch 1 | Step 2750 | Loss: 0.9863 | LM: 0.3713 | LB: 1.2390 | CL0: 3.1 | CL1: 5.3 | HR0: 0.322/SR0: 0.303 | HR1: 0.216/SR1: 0.195 | LR: 1.00e-04
[2026-05-24 12:20:23] Epoch 1 | Step 2760 | Loss: 0.9860 | LM: 0.3712 | LB: 1.2385 | CL0: 3.1 | CL1: 5.4 | HR0: 0.322/SR0: 0.303 | HR1: 0.216/SR1: 0.195 | LR: 1.00e-04
[2026-05-24 12:20:34] Epoch 1 | Step 2770 | Loss: 0.9858 | LM: 0.3711 | LB: 1.2379 | CL0: 3.1 | CL1: 5.4 | HR0: 0.322/SR0: 0.303 | HR1: 0.216/SR1: 0.195 | LR: 1.00e-04
[2026-05-24 12:20:45] Epoch 1 | Step 2780 | Loss: 0.9857 | LM: 0.3713 | LB: 1.2374 | CL0: 3.1 | CL1: 5.4 | HR0: 0.321/SR0: 0.303 | HR1: 0.215/SR1: 0.194 | LR: 1.00e-04
[2026-05-24 12:20:56] Epoch 1 | Step 2790 | Loss: 0.9855 | LM: 0.3714 | LB: 1.2369 | CL0: 3.2 | CL1: 5.4 | HR0: 0.321/SR0: 0.302 | HR1: 0.215/SR1: 0.194 | LR: 1.00e-04
[2026-05-24 12:21:06] Epoch 1 | Step 2800 | Loss: 0.9854 | LM: 0.3717 | LB: 1.2363 | CL0: 3.2 | CL1: 5.4 | HR0: 0.321/SR0: 0.302 | HR1: 0.215/SR1: 0.194 | LR: 1.00e-04
[2026-05-24 12:21:17] Epoch 1 | Step 2810 | Loss: 0.9851 | LM: 0.3715 | LB: 1.2357 | CL0: 3.2 | CL1: 5.4 | HR0: 0.321/SR0: 0.302 | HR1: 0.215/SR1: 0.194 | LR: 1.00e-04
[2026-05-24 12:21:27] Epoch 1 | Step 2820 | Loss: 0.9849 | LM: 0.3715 | LB: 1.2352 | CL0: 3.2 | CL1: 5.4 | HR0: 0.321/SR0: 0.302 | HR1: 0.215/SR1: 0.194 | LR: 1.00e-04
[2026-05-24 12:21:38] Epoch 1 | Step 2830 | Loss: 0.9848 | LM: 0.3717 | LB: 1.2347 | CL0: 3.2 | CL1: 5.4 | HR0: 0.321/SR0: 0.301 | HR1: 0.214/SR1: 0.193 | LR: 1.00e-04
[2026-05-24 12:21:49] Epoch 1 | Step 2840 | Loss: 0.9846 | LM: 0.3717 | LB: 1.2342 | CL0: 3.2 | CL1: 5.4 | HR0: 0.320/SR0: 0.301 | HR1: 0.214/SR1: 0.193 | LR: 1.00e-04
[2026-05-24 12:22:00] Epoch 1 | Step 2850 | Loss: 0.9843 | LM: 0.3718 | LB: 1.2337 | CL0: 3.2 | CL1: 5.4 | HR0: 0.320/SR0: 0.301 | HR1: 0.214/SR1: 0.193 | LR: 1.00e-04
[2026-05-24 12:22:11] Epoch 1 | Step 2860 | Loss: 0.9840 | LM: 0.3717 | LB: 1.2332 | CL0: 3.2 | CL1: 5.4 | HR0: 0.320/SR0: 0.301 | HR1: 0.214/SR1: 0.193 | LR: 1.00e-04
[2026-05-24 12:22:21] Epoch 1 | Step 2870 | Loss: 0.9839 | LM: 0.3716 | LB: 1.2327 | CL0: 3.2 | CL1: 5.4 | HR0: 0.320/SR0: 0.301 | HR1: 0.214/SR1: 0.193 | LR: 1.00e-04
[2026-05-24 12:22:32] Epoch 1 | Step 2880 | Loss: 0.9837 | LM: 0.3720 | LB: 1.2322 | CL0: 3.2 | CL1: 5.4 | HR0: 0.320/SR0: 0.300 | HR1: 0.213/SR1: 0.193 | LR: 1.00e-04
[2026-05-24 12:22:43] Epoch 1 | Step 2890 | Loss: 0.9834 | LM: 0.3720 | LB: 1.2317 | CL0: 3.2 | CL1: 5.4 | HR0: 0.320/SR0: 0.300 | HR1: 0.213/SR1: 0.192 | LR: 1.00e-04
[2026-05-24 12:22:53] Epoch 1 | Step 2900 | Loss: 0.9832 | LM: 0.3719 | LB: 1.2311 | CL0: 3.2 | CL1: 5.4 | HR0: 0.319/SR0: 0.300 | HR1: 0.213/SR1: 0.192 | LR: 1.00e-04
[2026-05-24 12:23:04] Epoch 1 | Step 2910 | Loss: 0.9830 | LM: 0.3719 | LB: 1.2305 | CL0: 3.2 | CL1: 5.4 | HR0: 0.319/SR0: 0.300 | HR1: 0.213/SR1: 0.192 | LR: 1.00e-04
[2026-05-24 12:23:14] Epoch 1 | Step 2920 | Loss: 0.9828 | LM: 0.3720 | LB: 1.2300 | CL0: 3.2 | CL1: 5.4 | HR0: 0.319/SR0: 0.299 | HR1: 0.213/SR1: 0.192 | LR: 1.00e-04
[2026-05-24 12:23:25] Epoch 1 | Step 2930 | Loss: 0.9826 | LM: 0.3718 | LB: 1.2295 | CL0: 3.2 | CL1: 5.4 | HR0: 0.319/SR0: 0.299 | HR1: 0.213/SR1: 0.192 | LR: 1.00e-04
[2026-05-24 12:23:36] Epoch 1 | Step 2940 | Loss: 0.9824 | LM: 0.3719 | LB: 1.2289 | CL0: 3.2 | CL1: 5.4 | HR0: 0.319/SR0: 0.299 | HR1: 0.212/SR1: 0.192 | LR: 1.00e-04
[2026-05-24 12:23:46] Epoch 1 | Step 2950 | Loss: 0.9822 | LM: 0.3718 | LB: 1.2285 | CL0: 3.2 | CL1: 5.4 | HR0: 0.319/SR0: 0.299 | HR1: 0.212/SR1: 0.191 | LR: 1.00e-04
[2026-05-24 12:23:57] Epoch 1 | Step 2960 | Loss: 0.9819 | LM: 0.3718 | LB: 1.2280 | CL0: 3.2 | CL1: 5.4 | HR0: 0.318/SR0: 0.299 | HR1: 0.212/SR1: 0.191 | LR: 1.00e-04
[2026-05-24 12:24:07] Epoch 1 | Step 2970 | Loss: 0.9816 | LM: 0.3716 | LB: 1.2274 | CL0: 3.2 | CL1: 5.4 | HR0: 0.318/SR0: 0.298 | HR1: 0.212/SR1: 0.191 | LR: 1.00e-04
[2026-05-24 12:24:18] Epoch 1 | Step 2980 | Loss: 0.9814 | LM: 0.3717 | LB: 1.2269 | CL0: 3.2 | CL1: 5.4 | HR0: 0.318/SR0: 0.298 | HR1: 0.212/SR1: 0.191 | LR: 1.00e-04
[2026-05-24 12:24:29] Epoch 1 | Step 2990 | Loss: 0.9812 | LM: 0.3717 | LB: 1.2264 | CL0: 3.2 | CL1: 5.4 | HR0: 0.318/SR0: 0.298 | HR1: 0.211/SR1: 0.191 | LR: 1.00e-04
[2026-05-24 12:24:39] Epoch 1 | Step 3000 | Loss: 0.9810 | LM: 0.3718 | LB: 1.2260 | CL0: 3.2 | CL1: 5.4 | HR0: 0.318/SR0: 0.298 | HR1: 0.211/SR1: 0.191 | LR: 1.00e-04
[2026-05-24 12:24:43] Checkpoint saved: outputs/2026-05-24/N_8.0/checkpoints/checkpoint_step_3000.pt
[2026-05-24 12:24:50] Validation | Batch 10/1463 | Loss: 0.8796 | LM_LOSS: 0.3476 | LB_LOSS: 1.0641
[2026-05-24 12:24:52] Validation | Batch 20/1463 | Loss: 0.8899 | LM_LOSS: 0.3550 | LB_LOSS: 1.0700
[2026-05-24 12:24:54] Validation | Batch 30/1463 | Loss: 0.8985 | LM_LOSS: 0.3626 | LB_LOSS: 1.0718
[2026-05-24 12:24:55] Validation | Batch 40/1463 | Loss: 0.9092 | LM_LOSS: 0.3722 | LB_LOSS: 1.0741
[2026-05-24 12:24:57] Validation | Batch 50/1463 | Loss: 0.9185 | LM_LOSS: 0.3820 | LB_LOSS: 1.0729
[2026-05-24 12:24:59] Validation | Batch 60/1463 | Loss: 0.9208 | LM_LOSS: 0.3844 | LB_LOSS: 1.0728
[2026-05-24 12:25:01] Validation | Batch 70/1463 | Loss: 0.9208 | LM_LOSS: 0.3843 | LB_LOSS: 1.0730
[2026-05-24 12:25:03] Validation | Batch 80/1463 | Loss: 0.9224 | LM_LOSS: 0.3858 | LB_LOSS: 1.0732
[2026-05-24 12:25:05] Validation | Batch 90/1463 | Loss: 0.9218 | LM_LOSS: 0.3853 | LB_LOSS: 1.0730
[2026-05-24 12:25:07] Validation | Batch 100/1463 | Loss: 0.9224 | LM_LOSS: 0.3859 | LB_LOSS: 1.0731
[2026-05-24 12:25:09] Validation | Batch 110/1463 | Loss: 0.9209 | LM_LOSS: 0.3840 | LB_LOSS: 1.0738
[2026-05-24 12:25:10] Validation | Batch 120/1463 | Loss: 0.9226 | LM_LOSS: 0.3856 | LB_LOSS: 1.0740
[2026-05-24 12:25:12] Validation | Batch 130/1463 | Loss: 0.9247 | LM_LOSS: 0.3877 | LB_LOSS: 1.0740
[2026-05-24 12:25:14] Validation | Batch 140/1463 | Loss: 0.9257 | LM_LOSS: 0.3888 | LB_LOSS: 1.0738
[2026-05-24 12:25:16] Validation | Batch 150/1463 | Loss: 0.9239 | LM_LOSS: 0.3868 | LB_LOSS: 1.0741
[2026-05-24 12:25:17] Validation | Batch 160/1463 | Loss: 0.9248 | LM_LOSS: 0.3879 | LB_LOSS: 1.0739
[2026-05-24 12:25:19] Validation | Batch 170/1463 | Loss: 0.9245 | LM_LOSS: 0.3875 | LB_LOSS: 1.0739
[2026-05-24 12:25:21] Validation | Batch 180/1463 | Loss: 0.9251 | LM_LOSS: 0.3881 | LB_LOSS: 1.0740
[2026-05-24 12:25:23] Validation | Batch 190/1463 | Loss: 0.9256 | LM_LOSS: 0.3885 | LB_LOSS: 1.0741
[2026-05-24 12:25:25] Validation | Batch 200/1463 | Loss: 0.9255 | LM_LOSS: 0.3884 | LB_LOSS: 1.0742
[2026-05-24 12:25:26] Validation | Batch 210/1463 | Loss: 0.9258 | LM_LOSS: 0.3887 | LB_LOSS: 1.0742
[2026-05-24 12:25:28] Validation | Batch 220/1463 | Loss: 0.9250 | LM_LOSS: 0.3879 | LB_LOSS: 1.0743
[2026-05-24 12:25:30] Validation | Batch 230/1463 | Loss: 0.9269 | LM_LOSS: 0.3899 | LB_LOSS: 1.0739
[2026-05-24 12:25:32] Validation | Batch 240/1463 | Loss: 0.9278 | LM_LOSS: 0.3909 | LB_LOSS: 1.0739
[2026-05-24 12:25:34] Validation | Batch 250/1463 | Loss: 0.9270 | LM_LOSS: 0.3900 | LB_LOSS: 1.0739
[2026-05-24 12:25:36] Validation | Batch 260/1463 | Loss: 0.9287 | LM_LOSS: 0.3915 | LB_LOSS: 1.0743
[2026-05-24 12:25:38] Validation | Batch 270/1463 | Loss: 0.9273 | LM_LOSS: 0.3901 | LB_LOSS: 1.0743
[2026-05-24 12:25:39] Validation | Batch 280/1463 | Loss: 0.9284 | LM_LOSS: 0.3912 | LB_LOSS: 1.0744
[2026-05-24 12:25:41] Validation | Batch 290/1463 | Loss: 0.9276 | LM_LOSS: 0.3904 | LB_LOSS: 1.0744
[2026-05-24 12:25:43] Validation | Batch 300/1463 | Loss: 0.9283 | LM_LOSS: 0.3910 | LB_LOSS: 1.0746
[2026-05-24 12:25:45] Validation | Batch 310/1463 | Loss: 0.9291 | LM_LOSS: 0.3918 | LB_LOSS: 1.0746
[2026-05-24 12:25:46] Validation | Batch 320/1463 | Loss: 0.9276 | LM_LOSS: 0.3904 | LB_LOSS: 1.0742
[2026-05-24 12:25:48] Validation | Batch 330/1463 | Loss: 0.9275 | LM_LOSS: 0.3904 | LB_LOSS: 1.0743
[2026-05-24 12:25:50] Validation | Batch 340/1463 | Loss: 0.9270 | LM_LOSS: 0.3898 | LB_LOSS: 1.0743
[2026-05-24 12:25:52] Validation | Batch 350/1463 | Loss: 0.9272 | LM_LOSS: 0.3900 | LB_LOSS: 1.0743
[2026-05-24 12:25:53] Validation | Batch 360/1463 | Loss: 0.9271 | LM_LOSS: 0.3899 | LB_LOSS: 1.0744
[2026-05-24 12:25:55] Validation | Batch 370/1463 | Loss: 0.9270 | LM_LOSS: 0.3898 | LB_LOSS: 1.0745
[2026-05-24 12:25:56] Validation | Batch 380/1463 | Loss: 0.9269 | LM_LOSS: 0.3897 | LB_LOSS: 1.0743
[2026-05-24 12:25:58] Validation | Batch 390/1463 | Loss: 0.9279 | LM_LOSS: 0.3908 | LB_LOSS: 1.0743
[2026-05-24 12:26:00] Validation | Batch 400/1463 | Loss: 0.9277 | LM_LOSS: 0.3905 | LB_LOSS: 1.0744
[2026-05-24 12:26:02] Validation | Batch 410/1463 | Loss: 0.9277 | LM_LOSS: 0.3904 | LB_LOSS: 1.0746
[2026-05-24 12:26:03] Validation | Batch 420/1463 | Loss: 0.9279 | LM_LOSS: 0.3906 | LB_LOSS: 1.0746
[2026-05-24 12:26:05] Validation | Batch 430/1463 | Loss: 0.9276 | LM_LOSS: 0.3903 | LB_LOSS: 1.0747
[2026-05-24 12:26:07] Validation | Batch 440/1463 | Loss: 0.9279 | LM_LOSS: 0.3905 | LB_LOSS: 1.0748
[2026-05-24 12:26:09] Validation | Batch 450/1463 | Loss: 0.9277 | LM_LOSS: 0.3902 | LB_LOSS: 1.0749
[2026-05-24 12:26:11] Validation | Batch 460/1463 | Loss: 0.9276 | LM_LOSS: 0.3901 | LB_LOSS: 1.0749
[2026-05-24 12:26:13] Validation | Batch 470/1463 | Loss: 0.9282 | LM_LOSS: 0.3908 | LB_LOSS: 1.0748
[2026-05-24 12:26:14] Validation | Batch 480/1463 | Loss: 0.9280 | LM_LOSS: 0.3907 | LB_LOSS: 1.0747
[2026-05-24 12:26:16] Validation | Batch 490/1463 | Loss: 0.9278 | LM_LOSS: 0.3905 | LB_LOSS: 1.0747
[2026-05-24 12:26:18] Validation | Batch 500/1463 | Loss: 0.9275 | LM_LOSS: 0.3902 | LB_LOSS: 1.0747
[2026-05-24 12:26:20] Validation | Batch 510/1463 | Loss: 0.9270 | LM_LOSS: 0.3897 | LB_LOSS: 1.0747
[2026-05-24 12:26:22] Validation | Batch 520/1463 | Loss: 0.9266 | LM_LOSS: 0.3892 | LB_LOSS: 1.0748
[2026-05-24 12:26:23] Validation | Batch 530/1463 | Loss: 0.9268 | LM_LOSS: 0.3895 | LB_LOSS: 1.0747
[2026-05-24 12:26:25] Validation | Batch 540/1463 | Loss: 0.9272 | LM_LOSS: 0.3898 | LB_LOSS: 1.0748
[2026-05-24 12:26:26] Validation | Batch 550/1463 | Loss: 0.9269 | LM_LOSS: 0.3894 | LB_LOSS: 1.0749
[2026-05-24 12:26:28] Validation | Batch 560/1463 | Loss: 0.9273 | LM_LOSS: 0.3897 | LB_LOSS: 1.0750
[2026-05-24 12:26:30] Validation | Batch 570/1463 | Loss: 0.9274 | LM_LOSS: 0.3899 | LB_LOSS: 1.0750
[2026-05-24 12:26:32] Validation | Batch 580/1463 | Loss: 0.9271 | LM_LOSS: 0.3896 | LB_LOSS: 1.0750
[2026-05-24 12:26:34] Validation | Batch 590/1463 | Loss: 0.9271 | LM_LOSS: 0.3896 | LB_LOSS: 1.0751
[2026-05-24 12:26:36] Validation | Batch 600/1463 | Loss: 0.9275 | LM_LOSS: 0.3899 | LB_LOSS: 1.0752
[2026-05-24 12:26:38] Validation | Batch 610/1463 | Loss: 0.9276 | LM_LOSS: 0.3900 | LB_LOSS: 1.0752
[2026-05-24 12:26:40] Validation | Batch 620/1463 | Loss: 0.9269 | LM_LOSS: 0.3893 | LB_LOSS: 1.0752
[2026-05-24 12:26:42] Validation | Batch 630/1463 | Loss: 0.9266 | LM_LOSS: 0.3890 | LB_LOSS: 1.0753
[2026-05-24 12:26:43] Validation | Batch 640/1463 | Loss: 0.9266 | LM_LOSS: 0.3889 | LB_LOSS: 1.0754
[2026-05-24 12:26:45] Validation | Batch 650/1463 | Loss: 0.9260 | LM_LOSS: 0.3883 | LB_LOSS: 1.0754
[2026-05-24 12:26:46] Validation | Batch 660/1463 | Loss: 0.9254 | LM_LOSS: 0.3877 | LB_LOSS: 1.0753
[2026-05-24 12:26:48] Validation | Batch 670/1463 | Loss: 0.9251 | LM_LOSS: 0.3874 | LB_LOSS: 1.0753
[2026-05-24 12:26:50] Validation | Batch 680/1463 | Loss: 0.9250 | LM_LOSS: 0.3874 | LB_LOSS: 1.0752
[2026-05-24 12:26:52] Validation | Batch 690/1463 | Loss: 0.9254 | LM_LOSS: 0.3878 | LB_LOSS: 1.0752
[2026-05-24 12:26:53] Validation | Batch 700/1463 | Loss: 0.9254 | LM_LOSS: 0.3878 | LB_LOSS: 1.0752
[2026-05-24 12:26:55] Validation | Batch 710/1463 | Loss: 0.9258 | LM_LOSS: 0.3882 | LB_LOSS: 1.0753
[2026-05-24 12:26:57] Validation | Batch 720/1463 | Loss: 0.9267 | LM_LOSS: 0.3890 | LB_LOSS: 1.0754
[2026-05-24 12:26:58] Validation | Batch 730/1463 | Loss: 0.9263 | LM_LOSS: 0.3887 | LB_LOSS: 1.0754
[2026-05-24 12:27:00] Validation | Batch 740/1463 | Loss: 0.9261 | LM_LOSS: 0.3884 | LB_LOSS: 1.0754
[2026-05-24 12:27:01] Validation | Batch 750/1463 | Loss: 0.9260 | LM_LOSS: 0.3883 | LB_LOSS: 1.0753
[2026-05-24 12:27:03] Validation | Batch 760/1463 | Loss: 0.9256 | LM_LOSS: 0.3879 | LB_LOSS: 1.0753
[2026-05-24 12:27:04] Validation | Batch 770/1463 | Loss: 0.9254 | LM_LOSS: 0.3877 | LB_LOSS: 1.0754
[2026-05-24 12:27:06] Validation | Batch 780/1463 | Loss: 0.9250 | LM_LOSS: 0.3874 | LB_LOSS: 1.0753
[2026-05-24 12:27:07] Validation | Batch 790/1463 | Loss: 0.9252 | LM_LOSS: 0.3876 | LB_LOSS: 1.0752
[2026-05-24 12:27:09] Validation | Batch 800/1463 | Loss: 0.9251 | LM_LOSS: 0.3874 | LB_LOSS: 1.0752
[2026-05-24 12:27:11] Validation | Batch 810/1463 | Loss: 0.9247 | LM_LOSS: 0.3871 | LB_LOSS: 1.0752
[2026-05-24 12:27:12] Validation | Batch 820/1463 | Loss: 0.9248 | LM_LOSS: 0.3873 | LB_LOSS: 1.0751
[2026-05-24 12:27:14] Validation | Batch 830/1463 | Loss: 0.9249 | LM_LOSS: 0.3874 | LB_LOSS: 1.0752
[2026-05-24 12:27:16] Validation | Batch 840/1463 | Loss: 0.9249 | LM_LOSS: 0.3873 | LB_LOSS: 1.0752
[2026-05-24 12:27:18] Validation | Batch 850/1463 | Loss: 0.9251 | LM_LOSS: 0.3875 | LB_LOSS: 1.0752
[2026-05-24 12:27:20] Validation | Batch 860/1463 | Loss: 0.9251 | LM_LOSS: 0.3875 | LB_LOSS: 1.0753
[2026-05-24 12:27:22] Validation | Batch 870/1463 | Loss: 0.9252 | LM_LOSS: 0.3875 | LB_LOSS: 1.0753
[2026-05-24 12:27:23] Validation | Batch 880/1463 | Loss: 0.9244 | LM_LOSS: 0.3868 | LB_LOSS: 1.0753
[2026-05-24 12:27:25] Validation | Batch 890/1463 | Loss: 0.9244 | LM_LOSS: 0.3868 | LB_LOSS: 1.0752
[2026-05-24 12:27:27] Validation | Batch 900/1463 | Loss: 0.9240 | LM_LOSS: 0.3864 | LB_LOSS: 1.0752
[2026-05-24 12:27:29] Validation | Batch 910/1463 | Loss: 0.9239 | LM_LOSS: 0.3863 | LB_LOSS: 1.0752
[2026-05-24 12:27:31] Validation | Batch 920/1463 | Loss: 0.9241 | LM_LOSS: 0.3865 | LB_LOSS: 1.0752
[2026-05-24 12:27:32] Validation | Batch 930/1463 | Loss: 0.9237 | LM_LOSS: 0.3861 | LB_LOSS: 1.0752
[2026-05-24 12:27:34] Validation | Batch 940/1463 | Loss: 0.9234 | LM_LOSS: 0.3858 | LB_LOSS: 1.0751
[2026-05-24 12:27:36] Validation | Batch 950/1463 | Loss: 0.9237 | LM_LOSS: 0.3861 | LB_LOSS: 1.0751
[2026-05-24 12:27:38] Validation | Batch 960/1463 | Loss: 0.9237 | LM_LOSS: 0.3862 | LB_LOSS: 1.0751
[2026-05-24 12:27:40] Validation | Batch 970/1463 | Loss: 0.9239 | LM_LOSS: 0.3864 | LB_LOSS: 1.0750
[2026-05-24 12:27:42] Validation | Batch 980/1463 | Loss: 0.9242 | LM_LOSS: 0.3867 | LB_LOSS: 1.0750
[2026-05-24 12:27:43] Validation | Batch 990/1463 | Loss: 0.9244 | LM_LOSS: 0.3870 | LB_LOSS: 1.0750
[2026-05-24 12:27:45] Validation | Batch 1000/1463 | Loss: 0.9251 | LM_LOSS: 0.3876 | LB_LOSS: 1.0750
[2026-05-24 12:27:47] Validation | Batch 1010/1463 | Loss: 0.9251 | LM_LOSS: 0.3875 | LB_LOSS: 1.0751
[2026-05-24 12:27:49] Validation | Batch 1020/1463 | Loss: 0.9252 | LM_LOSS: 0.3876 | LB_LOSS: 1.0751
[2026-05-24 12:27:51] Validation | Batch 1030/1463 | Loss: 0.9256 | LM_LOSS: 0.3880 | LB_LOSS: 1.0752
[2026-05-24 12:27:52] Validation | Batch 1040/1463 | Loss: 0.9251 | LM_LOSS: 0.3875 | LB_LOSS: 1.0752
[2026-05-24 12:27:54] Validation | Batch 1050/1463 | Loss: 0.9249 | LM_LOSS: 0.3874 | LB_LOSS: 1.0751
[2026-05-24 12:27:56] Validation | Batch 1060/1463 | Loss: 0.9248 | LM_LOSS: 0.3872 | LB_LOSS: 1.0751
[2026-05-24 12:27:58] Validation | Batch 1070/1463 | Loss: 0.9248 | LM_LOSS: 0.3873 | LB_LOSS: 1.0751
[2026-05-24 12:28:00] Validation | Batch 1080/1463 | Loss: 0.9246 | LM_LOSS: 0.3870 | LB_LOSS: 1.0752
[2026-05-24 12:28:01] Validation | Batch 1090/1463 | Loss: 0.9246 | LM_LOSS: 0.3870 | LB_LOSS: 1.0751
[2026-05-24 12:28:03] Validation | Batch 1100/1463 | Loss: 0.9245 | LM_LOSS: 0.3870 | LB_LOSS: 1.0750
[2026-05-24 12:28:05] Validation | Batch 1110/1463 | Loss: 0.9246 | LM_LOSS: 0.3870 | LB_LOSS: 1.0750
[2026-05-24 12:28:06] Validation | Batch 1120/1463 | Loss: 0.9244 | LM_LOSS: 0.3869 | LB_LOSS: 1.0751
[2026-05-24 12:28:08] Validation | Batch 1130/1463 | Loss: 0.9242 | LM_LOSS: 0.3867 | LB_LOSS: 1.0750
[2026-05-24 12:28:10] Validation | Batch 1140/1463 | Loss: 0.9244 | LM_LOSS: 0.3869 | LB_LOSS: 1.0751
[2026-05-24 12:28:12] Validation | Batch 1150/1463 | Loss: 0.9244 | LM_LOSS: 0.3869 | LB_LOSS: 1.0750
[2026-05-24 12:28:14] Validation | Batch 1160/1463 | Loss: 0.9244 | LM_LOSS: 0.3869 | LB_LOSS: 1.0750
[2026-05-24 12:28:16] Validation | Batch 1170/1463 | Loss: 0.9244 | LM_LOSS: 0.3869 | LB_LOSS: 1.0750
[2026-05-24 12:28:17] Validation | Batch 1180/1463 | Loss: 0.9244 | LM_LOSS: 0.3869 | LB_LOSS: 1.0750
[2026-05-24 12:28:19] Validation | Batch 1190/1463 | Loss: 0.9245 | LM_LOSS: 0.3870 | LB_LOSS: 1.0750
[2026-05-24 12:28:21] Validation | Batch 1200/1463 | Loss: 0.9247 | LM_LOSS: 0.3871 | LB_LOSS: 1.0751
[2026-05-24 12:28:23] Validation | Batch 1210/1463 | Loss: 0.9249 | LM_LOSS: 0.3874 | LB_LOSS: 1.0751
[2026-05-24 12:28:25] Validation | Batch 1220/1463 | Loss: 0.9253 | LM_LOSS: 0.3877 | LB_LOSS: 1.0751
[2026-05-24 12:28:26] Validation | Batch 1230/1463 | Loss: 0.9251 | LM_LOSS: 0.3876 | LB_LOSS: 1.0751
[2026-05-24 12:28:28] Validation | Batch 1240/1463 | Loss: 0.9255 | LM_LOSS: 0.3879 | LB_LOSS: 1.0751
[2026-05-24 12:28:30] Validation | Batch 1250/1463 | Loss: 0.9256 | LM_LOSS: 0.3881 | LB_LOSS: 1.0751
[2026-05-24 12:28:32] Validation | Batch 1260/1463 | Loss: 0.9256 | LM_LOSS: 0.3880 | LB_LOSS: 1.0752
[2026-05-24 12:28:34] Validation | Batch 1270/1463 | Loss: 0.9254 | LM_LOSS: 0.3878 | LB_LOSS: 1.0752
[2026-05-24 12:28:36] Validation | Batch 1280/1463 | Loss: 0.9251 | LM_LOSS: 0.3876 | LB_LOSS: 1.0751
[2026-05-24 12:28:37] Validation | Batch 1290/1463 | Loss: 0.9252 | LM_LOSS: 0.3876 | LB_LOSS: 1.0751
[2026-05-24 12:28:39] Validation | Batch 1300/1463 | Loss: 0.9250 | LM_LOSS: 0.3874 | LB_LOSS: 1.0751
[2026-05-24 12:28:41] Validation | Batch 1310/1463 | Loss: 0.9248 | LM_LOSS: 0.3873 | LB_LOSS: 1.0751
[2026-05-24 12:28:42] Validation | Batch 1320/1463 | Loss: 0.9249 | LM_LOSS: 0.3873 | LB_LOSS: 1.0751
[2026-05-24 12:28:44] Validation | Batch 1330/1463 | Loss: 0.9249 | LM_LOSS: 0.3874 | LB_LOSS: 1.0750
[2026-05-24 12:28:45] Validation | Batch 1340/1463 | Loss: 0.9252 | LM_LOSS: 0.3876 | LB_LOSS: 1.0751
[2026-05-24 12:28:47] Validation | Batch 1350/1463 | Loss: 0.9252 | LM_LOSS: 0.3877 | LB_LOSS: 1.0751
[2026-05-24 12:28:50] Validation | Batch 1360/1463 | Loss: 0.9254 | LM_LOSS: 0.3879 | LB_LOSS: 1.0750
[2026-05-24 12:28:51] Validation | Batch 1370/1463 | Loss: 0.9257 | LM_LOSS: 0.3882 | LB_LOSS: 1.0751
[2026-05-24 12:28:53] Validation | Batch 1380/1463 | Loss: 0.9255 | LM_LOSS: 0.3880 | LB_LOSS: 1.0750
[2026-05-24 12:28:55] Validation | Batch 1390/1463 | Loss: 0.9255 | LM_LOSS: 0.3879 | LB_LOSS: 1.0751
[2026-05-24 12:28:57] Validation | Batch 1400/1463 | Loss: 0.9257 | LM_LOSS: 0.3882 | LB_LOSS: 1.0750
[2026-05-24 12:28:58] Validation | Batch 1410/1463 | Loss: 0.9259 | LM_LOSS: 0.3884 | LB_LOSS: 1.0750
[2026-05-24 12:29:00] Validation | Batch 1420/1463 | Loss: 0.9260 | LM_LOSS: 0.3885 | LB_LOSS: 1.0750
[2026-05-24 12:29:02] Validation | Batch 1430/1463 | Loss: 0.9261 | LM_LOSS: 0.3886 | LB_LOSS: 1.0750
[2026-05-24 12:29:04] Validation | Batch 1440/1463 | Loss: 0.9266 | LM_LOSS: 0.3891 | LB_LOSS: 1.0750
[2026-05-24 12:29:06] Validation | Batch 1450/1463 | Loss: 0.9262 | LM_LOSS: 0.3887 | LB_LOSS: 1.0750
[2026-05-24 12:29:08] Validation | Batch 1460/1463 | Loss: 0.9265 | LM_LOSS: 0.3890 | LB_LOSS: 1.0750
[2026-05-24 12:29:08] Validation | Batch 1463/1463 | Loss: 0.9264 | LM_LOSS: 0.3889 | LB_LOSS: 1.0750
[2026-05-24 12:29:08] Validation | Loss: 0.9264 | LM_LOSS: 0.3889 | LB_LOSS: 1.0750 | PPL: 1.48 | Time: 259.43s
[2026-05-24 12:29:19] Epoch 1 | Step 3010 | Loss: 0.9809 | LM: 0.3719 | LB: 1.2255 | CL0: 3.2 | CL1: 5.4 | HR0: 0.318/SR0: 0.298 | HR1: 0.211/SR1: 0.190 | LR: 1.00e-04
[2026-05-24 12:29:30] Epoch 1 | Step 3020 | Loss: 0.9807 | LM: 0.3720 | LB: 1.2250 | CL0: 3.2 | CL1: 5.4 | HR0: 0.317/SR0: 0.297 | HR1: 0.211/SR1: 0.190 | LR: 1.00e-04
[2026-05-24 12:29:42] Epoch 1 | Step 3030 | Loss: 0.9803 | LM: 0.3720 | LB: 1.2245 | CL0: 3.2 | CL1: 5.4 | HR0: 0.317/SR0: 0.297 | HR1: 0.211/SR1: 0.190 | LR: 1.00e-04
[2026-05-24 12:29:54] Epoch 1 | Step 3040 | Loss: 0.9802 | LM: 0.3721 | LB: 1.2240 | CL0: 3.2 | CL1: 5.5 | HR0: 0.317/SR0: 0.297 | HR1: 0.211/SR1: 0.190 | LR: 1.00e-04
[2026-05-24 12:30:06] Epoch 1 | Step 3050 | Loss: 0.9800 | LM: 0.3722 | LB: 1.2235 | CL0: 3.2 | CL1: 5.5 | HR0: 0.317/SR0: 0.297 | HR1: 0.210/SR1: 0.190 | LR: 1.00e-04
[2026-05-24 12:30:17] Epoch 1 | Step 3060 | Loss: 0.9797 | LM: 0.3724 | LB: 1.2231 | CL0: 3.2 | CL1: 5.5 | HR0: 0.317/SR0: 0.297 | HR1: 0.210/SR1: 0.190 | LR: 1.00e-04
[2026-05-24 12:30:28] Epoch 1 | Step 3070 | Loss: 0.9795 | LM: 0.3724 | LB: 1.2226 | CL0: 3.2 | CL1: 5.5 | HR0: 0.317/SR0: 0.296 | HR1: 0.210/SR1: 0.189 | LR: 1.00e-04
[2026-05-24 12:30:40] Epoch 1 | Step 3080 | Loss: 0.9793 | LM: 0.3723 | LB: 1.2221 | CL0: 3.2 | CL1: 5.5 | HR0: 0.317/SR0: 0.296 | HR1: 0.210/SR1: 0.189 | LR: 1.00e-04
[2026-05-24 12:30:52] Epoch 1 | Step 3090 | Loss: 0.9792 | LM: 0.3723 | LB: 1.2216 | CL0: 3.2 | CL1: 5.5 | HR0: 0.316/SR0: 0.296 | HR1: 0.210/SR1: 0.189 | LR: 1.00e-04
[2026-05-24 12:31:03] Epoch 1 | Step 3100 | Loss: 0.9790 | LM: 0.3722 | LB: 1.2211 | CL0: 3.2 | CL1: 5.5 | HR0: 0.316/SR0: 0.296 | HR1: 0.209/SR1: 0.189 | LR: 1.00e-04
[2026-05-24 12:31:15] Epoch 1 | Step 3110 | Loss: 0.9787 | LM: 0.3721 | LB: 1.2206 | CL0: 3.2 | CL1: 5.5 | HR0: 0.316/SR0: 0.295 | HR1: 0.209/SR1: 0.189 | LR: 1.00e-04
[2026-05-24 12:31:27] Epoch 1 | Step 3120 | Loss: 0.9787 | LM: 0.3722 | LB: 1.2202 | CL0: 3.2 | CL1: 5.5 | HR0: 0.316/SR0: 0.295 | HR1: 0.209/SR1: 0.188 | LR: 1.00e-04
[2026-05-24 12:31:38] Epoch 1 | Step 3130 | Loss: 0.9785 | LM: 0.3722 | LB: 1.2197 | CL0: 3.2 | CL1: 5.5 | HR0: 0.316/SR0: 0.295 | HR1: 0.209/SR1: 0.188 | LR: 1.00e-04
[2026-05-24 12:31:49] Epoch 1 | Step 3140 | Loss: 0.9783 | LM: 0.3720 | LB: 1.2192 | CL0: 3.2 | CL1: 5.5 | HR0: 0.316/SR0: 0.295 | HR1: 0.209/SR1: 0.188 | LR: 1.00e-04
[2026-05-24 12:32:00] Epoch 1 | Step 3150 | Loss: 0.9782 | LM: 0.3721 | LB: 1.2187 | CL0: 3.2 | CL1: 5.5 | HR0: 0.315/SR0: 0.295 | HR1: 0.209/SR1: 0.188 | LR: 1.00e-04
[2026-05-24 12:32:10] Epoch 1 | Step 3160 | Loss: 0.9781 | LM: 0.3722 | LB: 1.2183 | CL0: 3.2 | CL1: 5.5 | HR0: 0.315/SR0: 0.294 | HR1: 0.208/SR1: 0.188 | LR: 1.00e-04
[2026-05-24 12:32:21] Epoch 1 | Step 3170 | Loss: 0.9780 | LM: 0.3724 | LB: 1.2179 | CL0: 3.2 | CL1: 5.5 | HR0: 0.315/SR0: 0.294 | HR1: 0.208/SR1: 0.188 | LR: 1.00e-04
[2026-05-24 12:32:32] Epoch 1 | Step 3180 | Loss: 0.9779 | LM: 0.3724 | LB: 1.2174 | CL0: 3.2 | CL1: 5.5 | HR0: 0.315/SR0: 0.294 | HR1: 0.208/SR1: 0.188 | LR: 1.00e-04
[2026-05-24 12:32:43] Epoch 1 | Step 3190 | Loss: 0.9778 | LM: 0.3724 | LB: 1.2169 | CL0: 3.2 | CL1: 5.5 | HR0: 0.315/SR0: 0.294 | HR1: 0.208/SR1: 0.187 | LR: 1.00e-04
[2026-05-24 12:32:55] Epoch 1 | Step 3200 | Loss: 0.9775 | LM: 0.3722 | LB: 1.2164 | CL0: 3.2 | CL1: 5.5 | HR0: 0.315/SR0: 0.294 | HR1: 0.208/SR1: 0.187 | LR: 1.00e-04
[2026-05-24 12:33:05] Epoch 1 | Step 3210 | Loss: 0.9773 | LM: 0.3723 | LB: 1.2160 | CL0: 3.2 | CL1: 5.5 | HR0: 0.314/SR0: 0.293 | HR1: 0.208/SR1: 0.187 | LR: 1.00e-04
[2026-05-24 12:33:16] Epoch 1 | Step 3220 | Loss: 0.9773 | LM: 0.3727 | LB: 1.2155 | CL0: 3.2 | CL1: 5.5 | HR0: 0.314/SR0: 0.293 | HR1: 0.207/SR1: 0.187 | LR: 1.00e-04
[2026-05-24 12:33:27] Epoch 1 | Step 3230 | Loss: 0.9771 | LM: 0.3727 | LB: 1.2150 | CL0: 3.2 | CL1: 5.5 | HR0: 0.314/SR0: 0.293 | HR1: 0.207/SR1: 0.187 | LR: 1.00e-04
[2026-05-24 12:33:39] Epoch 1 | Step 3240 | Loss: 0.9770 | LM: 0.3728 | LB: 1.2146 | CL0: 3.2 | CL1: 5.5 | HR0: 0.314/SR0: 0.293 | HR1: 0.207/SR1: 0.187 | LR: 1.00e-04
[2026-05-24 12:33:50] Epoch 1 | Step 3250 | Loss: 0.9768 | LM: 0.3728 | LB: 1.2142 | CL0: 3.2 | CL1: 5.5 | HR0: 0.314/SR0: 0.293 | HR1: 0.207/SR1: 0.186 | LR: 1.00e-04
[2026-05-24 12:34:02] Epoch 1 | Step 3260 | Loss: 0.9766 | LM: 0.3729 | LB: 1.2137 | CL0: 3.2 | CL1: 5.5 | HR0: 0.314/SR0: 0.292 | HR1: 0.207/SR1: 0.186 | LR: 1.00e-04
[2026-05-24 12:34:13] Epoch 1 | Step 3270 | Loss: 0.9764 | LM: 0.3729 | LB: 1.2133 | CL0: 3.2 | CL1: 5.5 | HR0: 0.313/SR0: 0.292 | HR1: 0.207/SR1: 0.186 | LR: 1.00e-04
[2026-05-24 12:34:25] Epoch 1 | Step 3280 | Loss: 0.9764 | LM: 0.3729 | LB: 1.2129 | CL0: 3.2 | CL1: 5.5 | HR0: 0.313/SR0: 0.292 | HR1: 0.207/SR1: 0.186 | LR: 1.00e-04
[2026-05-24 12:34:36] Epoch 1 | Step 3290 | Loss: 0.9761 | LM: 0.3728 | LB: 1.2124 | CL0: 3.2 | CL1: 5.5 | HR0: 0.313/SR0: 0.292 | HR1: 0.206/SR1: 0.186 | LR: 1.00e-04
[2026-05-24 12:34:48] Epoch 1 | Step 3300 | Loss: 0.9760 | LM: 0.3729 | LB: 1.2120 | CL0: 3.2 | CL1: 5.5 | HR0: 0.313/SR0: 0.292 | HR1: 0.206/SR1: 0.186 | LR: 1.00e-04
[2026-05-24 12:34:59] Epoch 1 | Step 3310 | Loss: 0.9759 | LM: 0.3731 | LB: 1.2115 | CL0: 3.2 | CL1: 5.5 | HR0: 0.313/SR0: 0.291 | HR1: 0.206/SR1: 0.186 | LR: 1.00e-04
[2026-05-24 12:35:11] Epoch 1 | Step 3320 | Loss: 0.9757 | LM: 0.3733 | LB: 1.2111 | CL0: 3.2 | CL1: 5.5 | HR0: 0.313/SR0: 0.291 | HR1: 0.206/SR1: 0.186 | LR: 1.00e-04
[2026-05-24 12:35:22] Epoch 1 | Step 3330 | Loss: 0.9756 | LM: 0.3733 | LB: 1.2107 | CL0: 3.2 | CL1: 5.5 | HR0: 0.312/SR0: 0.291 | HR1: 0.206/SR1: 0.185 | LR: 1.00e-04
[2026-05-24 12:35:34] Epoch 1 | Step 3340 | Loss: 0.9755 | LM: 0.3735 | LB: 1.2103 | CL0: 3.3 | CL1: 5.5 | HR0: 0.312/SR0: 0.291 | HR1: 0.206/SR1: 0.185 | LR: 1.00e-04
[2026-05-24 12:35:46] Epoch 1 | Step 3350 | Loss: 0.9754 | LM: 0.3737 | LB: 1.2098 | CL0: 3.3 | CL1: 5.6 | HR0: 0.312/SR0: 0.291 | HR1: 0.206/SR1: 0.185 | LR: 1.00e-04
[2026-05-24 12:35:56] Epoch 1 | Step 3360 | Loss: 0.9753 | LM: 0.3737 | LB: 1.2094 | CL0: 3.3 | CL1: 5.6 | HR0: 0.312/SR0: 0.290 | HR1: 0.205/SR1: 0.185 | LR: 1.00e-04
[2026-05-24 12:36:07] Epoch 1 | Step 3370 | Loss: 0.9751 | LM: 0.3737 | LB: 1.2090 | CL0: 3.3 | CL1: 5.6 | HR0: 0.312/SR0: 0.290 | HR1: 0.205/SR1: 0.185 | LR: 1.00e-04
[2026-05-24 12:36:17] Epoch 1 | Step 3380 | Loss: 0.9751 | LM: 0.3736 | LB: 1.2086 | CL0: 3.3 | CL1: 5.6 | HR0: 0.312/SR0: 0.290 | HR1: 0.205/SR1: 0.185 | LR: 1.00e-04
[2026-05-24 12:36:28] Epoch 1 | Step 3390 | Loss: 0.9749 | LM: 0.3736 | LB: 1.2082 | CL0: 3.3 | CL1: 5.6 | HR0: 0.312/SR0: 0.290 | HR1: 0.205/SR1: 0.185 | LR: 1.00e-04
[2026-05-24 12:36:39] Epoch 1 | Step 3400 | Loss: 0.9747 | LM: 0.3736 | LB: 1.2077 | CL0: 3.3 | CL1: 5.6 | HR0: 0.311/SR0: 0.290 | HR1: 0.205/SR1: 0.184 | LR: 1.00e-04
[2026-05-24 12:36:49] Epoch 1 | Step 3410 | Loss: 0.9746 | LM: 0.3737 | LB: 1.2073 | CL0: 3.3 | CL1: 5.6 | HR0: 0.311/SR0: 0.289 | HR1: 0.205/SR1: 0.184 | LR: 1.00e-04
[2026-05-24 12:37:00] Epoch 1 | Step 3420 | Loss: 0.9745 | LM: 0.3738 | LB: 1.2069 | CL0: 3.3 | CL1: 5.6 | HR0: 0.311/SR0: 0.289 | HR1: 0.204/SR1: 0.184 | LR: 1.00e-04
[2026-05-24 12:37:10] Epoch 1 | Step 3430 | Loss: 0.9743 | LM: 0.3737 | LB: 1.2064 | CL0: 3.3 | CL1: 5.6 | HR0: 0.311/SR0: 0.289 | HR1: 0.204/SR1: 0.184 | LR: 1.00e-04
[2026-05-24 12:37:21] Epoch 1 | Step 3440 | Loss: 0.9742 | LM: 0.3737 | LB: 1.2060 | CL0: 3.3 | CL1: 5.6 | HR0: 0.311/SR0: 0.289 | HR1: 0.204/SR1: 0.184 | LR: 1.00e-04
[2026-05-24 12:37:31] Epoch 1 | Step 3450 | Loss: 0.9740 | LM: 0.3737 | LB: 1.2056 | CL0: 3.3 | CL1: 5.6 | HR0: 0.311/SR0: 0.289 | HR1: 0.204/SR1: 0.184 | LR: 1.00e-04
[2026-05-24 12:37:42] Epoch 1 | Step 3460 | Loss: 0.9739 | LM: 0.3738 | LB: 1.2052 | CL0: 3.3 | CL1: 5.6 | HR0: 0.310/SR0: 0.289 | HR1: 0.204/SR1: 0.184 | LR: 1.00e-04
[2026-05-24 12:37:54] Epoch 1 | Step 3470 | Loss: 0.9737 | LM: 0.3738 | LB: 1.2048 | CL0: 3.3 | CL1: 5.6 | HR0: 0.310/SR0: 0.288 | HR1: 0.204/SR1: 0.183 | LR: 1.00e-04
[2026-05-24 12:38:05] Epoch 1 | Step 3480 | Loss: 0.9737 | LM: 0.3740 | LB: 1.2044 | CL0: 3.3 | CL1: 5.6 | HR0: 0.310/SR0: 0.288 | HR1: 0.204/SR1: 0.183 | LR: 1.00e-04
[2026-05-24 12:38:17] Epoch 1 | Step 3490 | Loss: 0.9737 | LM: 0.3741 | LB: 1.2040 | CL0: 3.3 | CL1: 5.6 | HR0: 0.310/SR0: 0.288 | HR1: 0.203/SR1: 0.183 | LR: 1.00e-04
[2026-05-24 12:38:28] Epoch 1 | Step 3500 | Loss: 0.9737 | LM: 0.3745 | LB: 1.2036 | CL0: 3.3 | CL1: 5.6 | HR0: 0.310/SR0: 0.288 | HR1: 0.203/SR1: 0.183 | LR: 1.00e-04
[2026-05-24 12:38:40] Epoch 1 | Step 3510 | Loss: 0.9737 | LM: 0.3746 | LB: 1.2032 | CL0: 3.3 | CL1: 5.6 | HR0: 0.310/SR0: 0.288 | HR1: 0.203/SR1: 0.183 | LR: 1.00e-04
[2026-05-24 12:38:51] Epoch 1 | Step 3520 | Loss: 0.9735 | LM: 0.3747 | LB: 1.2028 | CL0: 3.3 | CL1: 5.6 | HR0: 0.310/SR0: 0.287 | HR1: 0.203/SR1: 0.183 | LR: 1.00e-04
[2026-05-24 12:39:03] Epoch 1 | Step 3530 | Loss: 0.9734 | LM: 0.3748 | LB: 1.2024 | CL0: 3.3 | CL1: 5.6 | HR0: 0.309/SR0: 0.287 | HR1: 0.203/SR1: 0.183 | LR: 1.00e-04
[2026-05-24 12:39:15] Epoch 1 | Step 3540 | Loss: 0.9732 | LM: 0.3748 | LB: 1.2020 | CL0: 3.3 | CL1: 5.6 | HR0: 0.309/SR0: 0.287 | HR1: 0.203/SR1: 0.182 | LR: 1.00e-04
[2026-05-24 12:39:26] Epoch 1 | Step 3550 | Loss: 0.9731 | LM: 0.3749 | LB: 1.2016 | CL0: 3.3 | CL1: 5.6 | HR0: 0.309/SR0: 0.287 | HR1: 0.203/SR1: 0.182 | LR: 1.00e-04
[2026-05-24 12:39:38] Epoch 1 | Step 3560 | Loss: 0.9730 | LM: 0.3750 | LB: 1.2012 | CL0: 3.3 | CL1: 5.6 | HR0: 0.309/SR0: 0.287 | HR1: 0.202/SR1: 0.182 | LR: 1.00e-04
[2026-05-24 12:39:49] Epoch 1 | Step 3570 | Loss: 0.9728 | LM: 0.3750 | LB: 1.2008 | CL0: 3.3 | CL1: 5.6 | HR0: 0.309/SR0: 0.286 | HR1: 0.202/SR1: 0.182 | LR: 1.00e-04
[2026-05-24 12:40:01] Epoch 1 | Step 3580 | Loss: 0.9726 | LM: 0.3750 | LB: 1.2004 | CL0: 3.3 | CL1: 5.6 | HR0: 0.309/SR0: 0.286 | HR1: 0.202/SR1: 0.182 | LR: 1.00e-04
[2026-05-24 12:40:13] Epoch 1 | Step 3590 | Loss: 0.9725 | LM: 0.3753 | LB: 1.2000 | CL0: 3.3 | CL1: 5.6 | HR0: 0.308/SR0: 0.286 | HR1: 0.202/SR1: 0.182 | LR: 1.00e-04
[2026-05-24 12:40:24] Epoch 1 | Step 3600 | Loss: 0.9724 | LM: 0.3752 | LB: 1.1996 | CL0: 3.3 | CL1: 5.6 | HR0: 0.308/SR0: 0.286 | HR1: 0.202/SR1: 0.182 | LR: 1.00e-04
[2026-05-24 12:40:36] Epoch 1 | Step 3610 | Loss: 0.9722 | LM: 0.3752 | LB: 1.1992 | CL0: 3.3 | CL1: 5.6 | HR0: 0.308/SR0: 0.286 | HR1: 0.202/SR1: 0.181 | LR: 1.00e-04
[2026-05-24 12:40:48] Epoch 1 | Step 3620 | Loss: 0.9722 | LM: 0.3754 | LB: 1.1988 | CL0: 3.3 | CL1: 5.6 | HR0: 0.308/SR0: 0.286 | HR1: 0.202/SR1: 0.181 | LR: 1.00e-04
[2026-05-24 12:40:59] Epoch 1 | Step 3630 | Loss: 0.9720 | LM: 0.3755 | LB: 1.1985 | CL0: 3.3 | CL1: 5.6 | HR0: 0.308/SR0: 0.285 | HR1: 0.201/SR1: 0.181 | LR: 1.00e-04
[2026-05-24 12:41:11] Epoch 1 | Step 3640 | Loss: 0.9720 | LM: 0.3757 | LB: 1.1981 | CL0: 3.3 | CL1: 5.6 | HR0: 0.308/SR0: 0.285 | HR1: 0.201/SR1: 0.181 | LR: 1.00e-04
[2026-05-24 12:41:22] Epoch 1 | Step 3650 | Loss: 0.9719 | LM: 0.3759 | LB: 1.1977 | CL0: 3.3 | CL1: 5.6 | HR0: 0.308/SR0: 0.285 | HR1: 0.201/SR1: 0.181 | LR: 1.00e-04
[2026-05-24 12:41:34] Epoch 1 | Step 3660 | Loss: 0.9718 | LM: 0.3761 | LB: 1.1973 | CL0: 3.3 | CL1: 5.6 | HR0: 0.307/SR0: 0.285 | HR1: 0.201/SR1: 0.181 | LR: 1.00e-04
[2026-05-24 12:41:45] Epoch 1 | Step 3670 | Loss: 0.9718 | LM: 0.3762 | LB: 1.1969 | CL0: 3.3 | CL1: 5.7 | HR0: 0.307/SR0: 0.285 | HR1: 0.201/SR1: 0.181 | LR: 1.00e-04
[2026-05-24 12:41:57] Epoch 1 | Step 3680 | Loss: 0.9716 | LM: 0.3763 | LB: 1.1966 | CL0: 3.3 | CL1: 5.7 | HR0: 0.307/SR0: 0.284 | HR1: 0.201/SR1: 0.181 | LR: 1.00e-04
[2026-05-24 12:42:07] Epoch 1 | Step 3690 | Loss: 0.9715 | LM: 0.3764 | LB: 1.1962 | CL0: 3.3 | CL1: 5.7 | HR0: 0.307/SR0: 0.284 | HR1: 0.201/SR1: 0.181 | LR: 1.00e-04
[2026-05-24 12:42:18] Epoch 1 | Step 3700 | Loss: 0.9714 | LM: 0.3766 | LB: 1.1958 | CL0: 3.3 | CL1: 5.7 | HR0: 0.307/SR0: 0.284 | HR1: 0.201/SR1: 0.180 | LR: 1.00e-04
[2026-05-24 12:42:29] Epoch 1 | Step 3710 | Loss: 0.9712 | LM: 0.3766 | LB: 1.1954 | CL0: 3.3 | CL1: 5.7 | HR0: 0.307/SR0: 0.284 | HR1: 0.200/SR1: 0.180 | LR: 1.00e-04
[2026-05-24 12:42:39] Epoch 1 | Step 3720 | Loss: 0.9712 | LM: 0.3768 | LB: 1.1950 | CL0: 3.3 | CL1: 5.7 | HR0: 0.306/SR0: 0.284 | HR1: 0.200/SR1: 0.180 | LR: 1.00e-04
[2026-05-24 12:42:50] Epoch 1 | Step 3730 | Loss: 0.9712 | LM: 0.3768 | LB: 1.1947 | CL0: 3.3 | CL1: 5.7 | HR0: 0.306/SR0: 0.284 | HR1: 0.200/SR1: 0.180 | LR: 1.00e-04
[2026-05-24 12:43:00] Epoch 1 | Step 3740 | Loss: 0.9711 | LM: 0.3769 | LB: 1.1943 | CL0: 3.3 | CL1: 5.7 | HR0: 0.306/SR0: 0.283 | HR1: 0.200/SR1: 0.180 | LR: 1.00e-04
[2026-05-24 12:43:11] Epoch 1 | Step 3750 | Loss: 0.9710 | LM: 0.3770 | LB: 1.1939 | CL0: 3.3 | CL1: 5.7 | HR0: 0.306/SR0: 0.283 | HR1: 0.200/SR1: 0.180 | LR: 1.00e-04
[2026-05-24 12:43:22] Epoch 1 | Step 3760 | Loss: 0.9709 | LM: 0.3771 | LB: 1.1936 | CL0: 3.3 | CL1: 5.7 | HR0: 0.306/SR0: 0.283 | HR1: 0.200/SR1: 0.180 | LR: 1.00e-04
[2026-05-24 12:43:33] Epoch 1 | Step 3770 | Loss: 0.9708 | LM: 0.3773 | LB: 1.1933 | CL0: 3.3 | CL1: 5.7 | HR0: 0.306/SR0: 0.283 | HR1: 0.200/SR1: 0.180 | LR: 1.00e-04
[2026-05-24 12:43:44] Epoch 1 | Step 3780 | Loss: 0.9706 | LM: 0.3773 | LB: 1.1929 | CL0: 3.3 | CL1: 5.7 | HR0: 0.306/SR0: 0.283 | HR1: 0.200/SR1: 0.180 | LR: 1.00e-04
[2026-05-24 12:43:54] Epoch 1 | Step 3790 | Loss: 0.9707 | LM: 0.3776 | LB: 1.1926 | CL0: 3.3 | CL1: 5.7 | HR0: 0.305/SR0: 0.283 | HR1: 0.200/SR1: 0.179 | LR: 1.00e-04
[2026-05-24 12:44:05] Epoch 1 | Step 3800 | Loss: 0.9706 | LM: 0.3777 | LB: 1.1922 | CL0: 3.3 | CL1: 5.7 | HR0: 0.305/SR0: 0.282 | HR1: 0.199/SR1: 0.179 | LR: 1.00e-04
[2026-05-24 12:44:15] Epoch 1 | Step 3810 | Loss: 0.9705 | LM: 0.3777 | LB: 1.1918 | CL0: 3.3 | CL1: 5.7 | HR0: 0.305/SR0: 0.282 | HR1: 0.199/SR1: 0.179 | LR: 1.00e-04
[2026-05-24 12:44:26] Epoch 1 | Step 3820 | Loss: 0.9703 | LM: 0.3778 | LB: 1.1915 | CL0: 3.3 | CL1: 5.7 | HR0: 0.305/SR0: 0.282 | HR1: 0.199/SR1: 0.179 | LR: 1.00e-04
[2026-05-24 12:44:36] Epoch 1 | Step 3830 | Loss: 0.9702 | LM: 0.3778 | LB: 1.1911 | CL0: 3.3 | CL1: 5.7 | HR0: 0.305/SR0: 0.282 | HR1: 0.199/SR1: 0.179 | LR: 1.00e-04
[2026-05-24 12:44:47] Epoch 1 | Step 3840 | Loss: 0.9700 | LM: 0.3777 | LB: 1.1908 | CL0: 3.3 | CL1: 5.7 | HR0: 0.305/SR0: 0.282 | HR1: 0.199/SR1: 0.179 | LR: 1.00e-04
[2026-05-24 12:44:58] Epoch 1 | Step 3850 | Loss: 0.9700 | LM: 0.3778 | LB: 1.1904 | CL0: 3.3 | CL1: 5.7 | HR0: 0.305/SR0: 0.282 | HR1: 0.199/SR1: 0.179 | LR: 1.00e-04
[2026-05-24 12:45:09] Epoch 1 | Step 3860 | Loss: 0.9700 | LM: 0.3780 | LB: 1.1901 | CL0: 3.3 | CL1: 5.7 | HR0: 0.304/SR0: 0.281 | HR1: 0.199/SR1: 0.179 | LR: 1.00e-04
[2026-05-24 12:45:19] Epoch 1 | Step 3870 | Loss: 0.9699 | LM: 0.3779 | LB: 1.1897 | CL0: 3.3 | CL1: 5.7 | HR0: 0.304/SR0: 0.281 | HR1: 0.199/SR1: 0.179 | LR: 1.00e-04
[2026-05-24 12:45:30] Epoch 1 | Step 3880 | Loss: 0.9698 | LM: 0.3781 | LB: 1.1894 | CL0: 3.4 | CL1: 5.7 | HR0: 0.304/SR0: 0.281 | HR1: 0.199/SR1: 0.179 | LR: 1.00e-04
[2026-05-24 12:45:40] Epoch 1 | Step 3890 | Loss: 0.9698 | LM: 0.3782 | LB: 1.1890 | CL0: 3.4 | CL1: 5.7 | HR0: 0.304/SR0: 0.281 | HR1: 0.198/SR1: 0.178 | LR: 1.00e-04
[2026-05-24 12:45:51] Epoch 1 | Step 3900 | Loss: 0.9697 | LM: 0.3784 | LB: 1.1887 | CL0: 3.4 | CL1: 5.7 | HR0: 0.304/SR0: 0.281 | HR1: 0.198/SR1: 0.178 | LR: 1.00e-04
[2026-05-24 12:46:02] Epoch 1 | Step 3910 | Loss: 0.9696 | LM: 0.3781 | LB: 1.1883 | CL0: 3.4 | CL1: 5.7 | HR0: 0.304/SR0: 0.281 | HR1: 0.198/SR1: 0.178 | LR: 1.00e-04
[2026-05-24 12:46:13] Epoch 1 | Step 3920 | Loss: 0.9695 | LM: 0.3781 | LB: 1.1880 | CL0: 3.4 | CL1: 5.7 | HR0: 0.303/SR0: 0.280 | HR1: 0.198/SR1: 0.178 | LR: 1.00e-04
[2026-05-24 12:46:24] Epoch 1 | Step 3930 | Loss: 0.9694 | LM: 0.3782 | LB: 1.1877 | CL0: 3.4 | CL1: 5.7 | HR0: 0.303/SR0: 0.280 | HR1: 0.198/SR1: 0.178 | LR: 1.00e-04
[2026-05-24 12:46:34] Epoch 1 | Step 3940 | Loss: 0.9693 | LM: 0.3782 | LB: 1.1873 | CL0: 3.4 | CL1: 5.7 | HR0: 0.303/SR0: 0.280 | HR1: 0.198/SR1: 0.178 | LR: 1.00e-04
[2026-05-24 12:46:45] Epoch 1 | Step 3950 | Loss: 0.9692 | LM: 0.3782 | LB: 1.1870 | CL0: 3.4 | CL1: 5.7 | HR0: 0.303/SR0: 0.280 | HR1: 0.198/SR1: 0.178 | LR: 1.00e-04
[2026-05-24 12:46:55] Epoch 1 | Step 3960 | Loss: 0.9692 | LM: 0.3783 | LB: 1.1867 | CL0: 3.4 | CL1: 5.7 | HR0: 0.303/SR0: 0.280 | HR1: 0.198/SR1: 0.178 | LR: 1.00e-04
[2026-05-24 12:47:06] Epoch 1 | Step 3970 | Loss: 0.9691 | LM: 0.3784 | LB: 1.1863 | CL0: 3.4 | CL1: 5.7 | HR0: 0.303/SR0: 0.280 | HR1: 0.198/SR1: 0.178 | LR: 1.00e-04
[2026-05-24 12:47:17] Epoch 1 | Step 3980 | Loss: 0.9690 | LM: 0.3785 | LB: 1.1860 | CL0: 3.4 | CL1: 5.7 | HR0: 0.303/SR0: 0.279 | HR1: 0.198/SR1: 0.178 | LR: 1.00e-04
[2026-05-24 12:47:27] Epoch 1 | Step 3990 | Loss: 0.9690 | LM: 0.3787 | LB: 1.1857 | CL0: 3.4 | CL1: 5.7 | HR0: 0.302/SR0: 0.279 | HR1: 0.197/SR1: 0.178 | LR: 1.00e-04
[2026-05-24 12:47:38] Epoch 1 | Step 4000 | Loss: 0.9690 | LM: 0.3787 | LB: 1.1853 | CL0: 3.4 | CL1: 5.7 | HR0: 0.302/SR0: 0.279 | HR1: 0.197/SR1: 0.177 | LR: 1.00e-04
[2026-05-24 12:47:40] Validation | Batch 10/1463 | Loss: 0.8868 | LM_LOSS: 0.3658 | LB_LOSS: 1.0421
[2026-05-24 12:47:41] Validation | Batch 20/1463 | Loss: 0.9041 | LM_LOSS: 0.3810 | LB_LOSS: 1.0462
[2026-05-24 12:47:43] Validation | Batch 30/1463 | Loss: 0.9118 | LM_LOSS: 0.3878 | LB_LOSS: 1.0479
[2026-05-24 12:47:44] Validation | Batch 40/1463 | Loss: 0.9225 | LM_LOSS: 0.3977 | LB_LOSS: 1.0497
[2026-05-24 12:47:46] Validation | Batch 50/1463 | Loss: 0.9303 | LM_LOSS: 0.4060 | LB_LOSS: 1.0487
[2026-05-24 12:47:48] Validation | Batch 60/1463 | Loss: 0.9332 | LM_LOSS: 0.4088 | LB_LOSS: 1.0487
[2026-05-24 12:47:50] Validation | Batch 70/1463 | Loss: 0.9319 | LM_LOSS: 0.4075 | LB_LOSS: 1.0488
[2026-05-24 12:47:52] Validation | Batch 80/1463 | Loss: 0.9330 | LM_LOSS: 0.4085 | LB_LOSS: 1.0490
[2026-05-24 12:47:54] Validation | Batch 90/1463 | Loss: 0.9316 | LM_LOSS: 0.4072 | LB_LOSS: 1.0489
[2026-05-24 12:47:55] Validation | Batch 100/1463 | Loss: 0.9324 | LM_LOSS: 0.4079 | LB_LOSS: 1.0489
[2026-05-24 12:47:57] Validation | Batch 110/1463 | Loss: 0.9309 | LM_LOSS: 0.4062 | LB_LOSS: 1.0495
[2026-05-24 12:47:58] Validation | Batch 120/1463 | Loss: 0.9319 | LM_LOSS: 0.4071 | LB_LOSS: 1.0496
[2026-05-24 12:48:00] Validation | Batch 130/1463 | Loss: 0.9347 | LM_LOSS: 0.4099 | LB_LOSS: 1.0496
[2026-05-24 12:48:02] Validation | Batch 140/1463 | Loss: 0.9359 | LM_LOSS: 0.4111 | LB_LOSS: 1.0495
[2026-05-24 12:48:04] Validation | Batch 150/1463 | Loss: 0.9344 | LM_LOSS: 0.4095 | LB_LOSS: 1.0498
[2026-05-24 12:48:05] Validation | Batch 160/1463 | Loss: 0.9356 | LM_LOSS: 0.4108 | LB_LOSS: 1.0496
[2026-05-24 12:48:07] Validation | Batch 170/1463 | Loss: 0.9352 | LM_LOSS: 0.4103 | LB_LOSS: 1.0497
[2026-05-24 12:48:09] Validation | Batch 180/1463 | Loss: 0.9360 | LM_LOSS: 0.4112 | LB_LOSS: 1.0498
[2026-05-24 12:48:11] Validation | Batch 190/1463 | Loss: 0.9365 | LM_LOSS: 0.4116 | LB_LOSS: 1.0498
[2026-05-24 12:48:12] Validation | Batch 200/1463 | Loss: 0.9358 | LM_LOSS: 0.4109 | LB_LOSS: 1.0499
[2026-05-24 12:48:14] Validation | Batch 210/1463 | Loss: 0.9364 | LM_LOSS: 0.4115 | LB_LOSS: 1.0499
[2026-05-24 12:48:16] Validation | Batch 220/1463 | Loss: 0.9356 | LM_LOSS: 0.4106 | LB_LOSS: 1.0500
[2026-05-24 12:48:18] Validation | Batch 230/1463 | Loss: 0.9377 | LM_LOSS: 0.4128 | LB_LOSS: 1.0497
[2026-05-24 12:48:19] Validation | Batch 240/1463 | Loss: 0.9383 | LM_LOSS: 0.4135 | LB_LOSS: 1.0497
[2026-05-24 12:48:21] Validation | Batch 250/1463 | Loss: 0.9374 | LM_LOSS: 0.4125 | LB_LOSS: 1.0497
[2026-05-24 12:48:23] Validation | Batch 260/1463 | Loss: 0.9394 | LM_LOSS: 0.4144 | LB_LOSS: 1.0500
[2026-05-24 12:48:25] Validation | Batch 270/1463 | Loss: 0.9383 | LM_LOSS: 0.4133 | LB_LOSS: 1.0500
[2026-05-24 12:48:26] Validation | Batch 280/1463 | Loss: 0.9393 | LM_LOSS: 0.4143 | LB_LOSS: 1.0500
[2026-05-24 12:48:28] Validation | Batch 290/1463 | Loss: 0.9384 | LM_LOSS: 0.4134 | LB_LOSS: 1.0500
[2026-05-24 12:48:29] Validation | Batch 300/1463 | Loss: 0.9392 | LM_LOSS: 0.4141 | LB_LOSS: 1.0502
[2026-05-24 12:48:31] Validation | Batch 310/1463 | Loss: 0.9401 | LM_LOSS: 0.4150 | LB_LOSS: 1.0502
[2026-05-24 12:48:33] Validation | Batch 320/1463 | Loss: 0.9387 | LM_LOSS: 0.4138 | LB_LOSS: 1.0499
[2026-05-24 12:48:35] Validation | Batch 330/1463 | Loss: 0.9387 | LM_LOSS: 0.4137 | LB_LOSS: 1.0500
[2026-05-24 12:48:36] Validation | Batch 340/1463 | Loss: 0.9385 | LM_LOSS: 0.4135 | LB_LOSS: 1.0500
[2026-05-24 12:48:38] Validation | Batch 350/1463 | Loss: 0.9388 | LM_LOSS: 0.4138 | LB_LOSS: 1.0500
[2026-05-24 12:48:39] Validation | Batch 360/1463 | Loss: 0.9390 | LM_LOSS: 0.4139 | LB_LOSS: 1.0500
[2026-05-24 12:48:41] Validation | Batch 370/1463 | Loss: 0.9389 | LM_LOSS: 0.4138 | LB_LOSS: 1.0501
[2026-05-24 12:48:42] Validation | Batch 380/1463 | Loss: 0.9389 | LM_LOSS: 0.4139 | LB_LOSS: 1.0499
[2026-05-24 12:48:44] Validation | Batch 390/1463 | Loss: 0.9399 | LM_LOSS: 0.4149 | LB_LOSS: 1.0500
[2026-05-24 12:48:46] Validation | Batch 400/1463 | Loss: 0.9398 | LM_LOSS: 0.4147 | LB_LOSS: 1.0500
[2026-05-24 12:48:47] Validation | Batch 410/1463 | Loss: 0.9396 | LM_LOSS: 0.4145 | LB_LOSS: 1.0501
[2026-05-24 12:48:49] Validation | Batch 420/1463 | Loss: 0.9399 | LM_LOSS: 0.4148 | LB_LOSS: 1.0502
[2026-05-24 12:48:51] Validation | Batch 430/1463 | Loss: 0.9398 | LM_LOSS: 0.4147 | LB_LOSS: 1.0503
[2026-05-24 12:48:53] Validation | Batch 440/1463 | Loss: 0.9401 | LM_LOSS: 0.4149 | LB_LOSS: 1.0504
[2026-05-24 12:48:54] Validation | Batch 450/1463 | Loss: 0.9400 | LM_LOSS: 0.4147 | LB_LOSS: 1.0505
[2026-05-24 12:48:56] Validation | Batch 460/1463 | Loss: 0.9399 | LM_LOSS: 0.4147 | LB_LOSS: 1.0504
[2026-05-24 12:48:58] Validation | Batch 470/1463 | Loss: 0.9407 | LM_LOSS: 0.4156 | LB_LOSS: 1.0504
[2026-05-24 12:49:00] Validation | Batch 480/1463 | Loss: 0.9406 | LM_LOSS: 0.4155 | LB_LOSS: 1.0503
[2026-05-24 12:49:01] Validation | Batch 490/1463 | Loss: 0.9406 | LM_LOSS: 0.4154 | LB_LOSS: 1.0503
[2026-05-24 12:49:03] Validation | Batch 500/1463 | Loss: 0.9402 | LM_LOSS: 0.4150 | LB_LOSS: 1.0503
[2026-05-24 12:49:05] Validation | Batch 510/1463 | Loss: 0.9395 | LM_LOSS: 0.4143 | LB_LOSS: 1.0503
[2026-05-24 12:49:07] Validation | Batch 520/1463 | Loss: 0.9392 | LM_LOSS: 0.4140 | LB_LOSS: 1.0503
[2026-05-24 12:49:08] Validation | Batch 530/1463 | Loss: 0.9394 | LM_LOSS: 0.4143 | LB_LOSS: 1.0503
[2026-05-24 12:49:10] Validation | Batch 540/1463 | Loss: 0.9399 | LM_LOSS: 0.4147 | LB_LOSS: 1.0503
[2026-05-24 12:49:11] Validation | Batch 550/1463 | Loss: 0.9396 | LM_LOSS: 0.4144 | LB_LOSS: 1.0504
[2026-05-24 12:49:13] Validation | Batch 560/1463 | Loss: 0.9400 | LM_LOSS: 0.4148 | LB_LOSS: 1.0505
[2026-05-24 12:49:15] Validation | Batch 570/1463 | Loss: 0.9401 | LM_LOSS: 0.4148 | LB_LOSS: 1.0505
[2026-05-24 12:49:16] Validation | Batch 580/1463 | Loss: 0.9398 | LM_LOSS: 0.4146 | LB_LOSS: 1.0505
[2026-05-24 12:49:18] Validation | Batch 590/1463 | Loss: 0.9399 | LM_LOSS: 0.4146 | LB_LOSS: 1.0506
[2026-05-24 12:49:20] Validation | Batch 600/1463 | Loss: 0.9402 | LM_LOSS: 0.4149 | LB_LOSS: 1.0507
[2026-05-24 12:49:22] Validation | Batch 610/1463 | Loss: 0.9403 | LM_LOSS: 0.4150 | LB_LOSS: 1.0507
[2026-05-24 12:49:24] Validation | Batch 620/1463 | Loss: 0.9396 | LM_LOSS: 0.4143 | LB_LOSS: 1.0507
[2026-05-24 12:49:25] Validation | Batch 630/1463 | Loss: 0.9394 | LM_LOSS: 0.4140 | LB_LOSS: 1.0507
[2026-05-24 12:49:27] Validation | Batch 640/1463 | Loss: 0.9393 | LM_LOSS: 0.4140 | LB_LOSS: 1.0508
[2026-05-24 12:49:28] Validation | Batch 650/1463 | Loss: 0.9388 | LM_LOSS: 0.4134 | LB_LOSS: 1.0508
[2026-05-24 12:49:30] Validation | Batch 660/1463 | Loss: 0.9383 | LM_LOSS: 0.4130 | LB_LOSS: 1.0507
[2026-05-24 12:49:32] Validation | Batch 670/1463 | Loss: 0.9379 | LM_LOSS: 0.4126 | LB_LOSS: 1.0507
[2026-05-24 12:49:33] Validation | Batch 680/1463 | Loss: 0.9379 | LM_LOSS: 0.4126 | LB_LOSS: 1.0506
[2026-05-24 12:49:35] Validation | Batch 690/1463 | Loss: 0.9383 | LM_LOSS: 0.4129 | LB_LOSS: 1.0507
[2026-05-24 12:49:37] Validation | Batch 700/1463 | Loss: 0.9383 | LM_LOSS: 0.4129 | LB_LOSS: 1.0506
[2026-05-24 12:49:38] Validation | Batch 710/1463 | Loss: 0.9387 | LM_LOSS: 0.4134 | LB_LOSS: 1.0507
[2026-05-24 12:49:40] Validation | Batch 720/1463 | Loss: 0.9395 | LM_LOSS: 0.4141 | LB_LOSS: 1.0508
[2026-05-24 12:49:41] Validation | Batch 730/1463 | Loss: 0.9392 | LM_LOSS: 0.4138 | LB_LOSS: 1.0508
[2026-05-24 12:49:43] Validation | Batch 740/1463 | Loss: 0.9389 | LM_LOSS: 0.4135 | LB_LOSS: 1.0508
[2026-05-24 12:49:44] Validation | Batch 750/1463 | Loss: 0.9388 | LM_LOSS: 0.4134 | LB_LOSS: 1.0507
[2026-05-24 12:49:46] Validation | Batch 760/1463 | Loss: 0.9383 | LM_LOSS: 0.4129 | LB_LOSS: 1.0507
[2026-05-24 12:49:47] Validation | Batch 770/1463 | Loss: 0.9381 | LM_LOSS: 0.4127 | LB_LOSS: 1.0508
[2026-05-24 12:49:49] Validation | Batch 780/1463 | Loss: 0.9380 | LM_LOSS: 0.4126 | LB_LOSS: 1.0507
[2026-05-24 12:49:50] Validation | Batch 790/1463 | Loss: 0.9381 | LM_LOSS: 0.4128 | LB_LOSS: 1.0507
[2026-05-24 12:49:52] Validation | Batch 800/1463 | Loss: 0.9381 | LM_LOSS: 0.4128 | LB_LOSS: 1.0507
[2026-05-24 12:49:53] Validation | Batch 810/1463 | Loss: 0.9376 | LM_LOSS: 0.4123 | LB_LOSS: 1.0506
[2026-05-24 12:49:55] Validation | Batch 820/1463 | Loss: 0.9378 | LM_LOSS: 0.4126 | LB_LOSS: 1.0506
[2026-05-24 12:49:57] Validation | Batch 830/1463 | Loss: 0.9379 | LM_LOSS: 0.4127 | LB_LOSS: 1.0506
[2026-05-24 12:49:59] Validation | Batch 840/1463 | Loss: 0.9378 | LM_LOSS: 0.4125 | LB_LOSS: 1.0507
[2026-05-24 12:50:00] Validation | Batch 850/1463 | Loss: 0.9380 | LM_LOSS: 0.4126 | LB_LOSS: 1.0507
[2026-05-24 12:50:02] Validation | Batch 860/1463 | Loss: 0.9380 | LM_LOSS: 0.4126 | LB_LOSS: 1.0507
[2026-05-24 12:50:04] Validation | Batch 870/1463 | Loss: 0.9381 | LM_LOSS: 0.4127 | LB_LOSS: 1.0507
[2026-05-24 12:50:05] Validation | Batch 880/1463 | Loss: 0.9373 | LM_LOSS: 0.4120 | LB_LOSS: 1.0507
[2026-05-24 12:50:07] Validation | Batch 890/1463 | Loss: 0.9373 | LM_LOSS: 0.4120 | LB_LOSS: 1.0506
[2026-05-24 12:50:09] Validation | Batch 900/1463 | Loss: 0.9370 | LM_LOSS: 0.4116 | LB_LOSS: 1.0506
[2026-05-24 12:50:10] Validation | Batch 910/1463 | Loss: 0.9369 | LM_LOSS: 0.4116 | LB_LOSS: 1.0507
[2026-05-24 12:50:12] Validation | Batch 920/1463 | Loss: 0.9371 | LM_LOSS: 0.4118 | LB_LOSS: 1.0507
[2026-05-24 12:50:14] Validation | Batch 930/1463 | Loss: 0.9367 | LM_LOSS: 0.4114 | LB_LOSS: 1.0507
[2026-05-24 12:50:15] Validation | Batch 940/1463 | Loss: 0.9363 | LM_LOSS: 0.4110 | LB_LOSS: 1.0506
[2026-05-24 12:50:17] Validation | Batch 950/1463 | Loss: 0.9367 | LM_LOSS: 0.4114 | LB_LOSS: 1.0506
[2026-05-24 12:50:19] Validation | Batch 960/1463 | Loss: 0.9368 | LM_LOSS: 0.4115 | LB_LOSS: 1.0506
[2026-05-24 12:50:21] Validation | Batch 970/1463 | Loss: 0.9370 | LM_LOSS: 0.4118 | LB_LOSS: 1.0505
[2026-05-24 12:50:23] Validation | Batch 980/1463 | Loss: 0.9373 | LM_LOSS: 0.4120 | LB_LOSS: 1.0505
[2026-05-24 12:50:24] Validation | Batch 990/1463 | Loss: 0.9375 | LM_LOSS: 0.4122 | LB_LOSS: 1.0505
[2026-05-24 12:50:26] Validation | Batch 1000/1463 | Loss: 0.9381 | LM_LOSS: 0.4128 | LB_LOSS: 1.0505
[2026-05-24 12:50:28] Validation | Batch 1010/1463 | Loss: 0.9381 | LM_LOSS: 0.4128 | LB_LOSS: 1.0506
[2026-05-24 12:50:29] Validation | Batch 1020/1463 | Loss: 0.9383 | LM_LOSS: 0.4130 | LB_LOSS: 1.0506
[2026-05-24 12:50:31] Validation | Batch 1030/1463 | Loss: 0.9388 | LM_LOSS: 0.4134 | LB_LOSS: 1.0507
[2026-05-24 12:50:33] Validation | Batch 1040/1463 | Loss: 0.9383 | LM_LOSS: 0.4130 | LB_LOSS: 1.0506
[2026-05-24 12:50:35] Validation | Batch 1050/1463 | Loss: 0.9382 | LM_LOSS: 0.4129 | LB_LOSS: 1.0506
[2026-05-24 12:50:37] Validation | Batch 1060/1463 | Loss: 0.9380 | LM_LOSS: 0.4127 | LB_LOSS: 1.0506
[2026-05-24 12:50:38] Validation | Batch 1070/1463 | Loss: 0.9382 | LM_LOSS: 0.4129 | LB_LOSS: 1.0506
[2026-05-24 12:50:40] Validation | Batch 1080/1463 | Loss: 0.9379 | LM_LOSS: 0.4125 | LB_LOSS: 1.0506
[2026-05-24 12:50:41] Validation | Batch 1090/1463 | Loss: 0.9379 | LM_LOSS: 0.4126 | LB_LOSS: 1.0506
[2026-05-24 12:50:43] Validation | Batch 1100/1463 | Loss: 0.9378 | LM_LOSS: 0.4126 | LB_LOSS: 1.0505
[2026-05-24 12:50:45] Validation | Batch 1110/1463 | Loss: 0.9379 | LM_LOSS: 0.4126 | LB_LOSS: 1.0505
[2026-05-24 12:50:46] Validation | Batch 1120/1463 | Loss: 0.9377 | LM_LOSS: 0.4124 | LB_LOSS: 1.0506
[2026-05-24 12:50:48] Validation | Batch 1130/1463 | Loss: 0.9374 | LM_LOSS: 0.4121 | LB_LOSS: 1.0506
[2026-05-24 12:50:50] Validation | Batch 1140/1463 | Loss: 0.9376 | LM_LOSS: 0.4124 | LB_LOSS: 1.0506
[2026-05-24 12:50:52] Validation | Batch 1150/1463 | Loss: 0.9376 | LM_LOSS: 0.4124 | LB_LOSS: 1.0505
[2026-05-24 12:50:53] Validation | Batch 1160/1463 | Loss: 0.9376 | LM_LOSS: 0.4124 | LB_LOSS: 1.0505
[2026-05-24 12:50:55] Validation | Batch 1170/1463 | Loss: 0.9376 | LM_LOSS: 0.4123 | LB_LOSS: 1.0505
[2026-05-24 12:50:57] Validation | Batch 1180/1463 | Loss: 0.9376 | LM_LOSS: 0.4123 | LB_LOSS: 1.0505
[2026-05-24 12:50:58] Validation | Batch 1190/1463 | Loss: 0.9377 | LM_LOSS: 0.4124 | LB_LOSS: 1.0505
[2026-05-24 12:51:00] Validation | Batch 1200/1463 | Loss: 0.9379 | LM_LOSS: 0.4126 | LB_LOSS: 1.0505
[2026-05-24 12:51:02] Validation | Batch 1210/1463 | Loss: 0.9382 | LM_LOSS: 0.4129 | LB_LOSS: 1.0506
[2026-05-24 12:51:03] Validation | Batch 1220/1463 | Loss: 0.9385 | LM_LOSS: 0.4132 | LB_LOSS: 1.0506
[2026-05-24 12:51:05] Validation | Batch 1230/1463 | Loss: 0.9384 | LM_LOSS: 0.4131 | LB_LOSS: 1.0506
[2026-05-24 12:51:07] Validation | Batch 1240/1463 | Loss: 0.9388 | LM_LOSS: 0.4135 | LB_LOSS: 1.0506
[2026-05-24 12:51:09] Validation | Batch 1250/1463 | Loss: 0.9390 | LM_LOSS: 0.4137 | LB_LOSS: 1.0506
[2026-05-24 12:51:11] Validation | Batch 1260/1463 | Loss: 0.9390 | LM_LOSS: 0.4137 | LB_LOSS: 1.0506
[2026-05-24 12:51:12] Validation | Batch 1270/1463 | Loss: 0.9388 | LM_LOSS: 0.4135 | LB_LOSS: 1.0507
[2026-05-24 12:51:14] Validation | Batch 1280/1463 | Loss: 0.9385 | LM_LOSS: 0.4132 | LB_LOSS: 1.0506
[2026-05-24 12:51:16] Validation | Batch 1290/1463 | Loss: 0.9386 | LM_LOSS: 0.4133 | LB_LOSS: 1.0506
[2026-05-24 12:51:17] Validation | Batch 1300/1463 | Loss: 0.9383 | LM_LOSS: 0.4130 | LB_LOSS: 1.0506
[2026-05-24 12:51:19] Validation | Batch 1310/1463 | Loss: 0.9383 | LM_LOSS: 0.4130 | LB_LOSS: 1.0506
[2026-05-24 12:51:20] Validation | Batch 1320/1463 | Loss: 0.9384 | LM_LOSS: 0.4131 | LB_LOSS: 1.0506
[2026-05-24 12:51:22] Validation | Batch 1330/1463 | Loss: 0.9384 | LM_LOSS: 0.4131 | LB_LOSS: 1.0505
[2026-05-24 12:51:23] Validation | Batch 1340/1463 | Loss: 0.9386 | LM_LOSS: 0.4133 | LB_LOSS: 1.0506
[2026-05-24 12:51:25] Validation | Batch 1350/1463 | Loss: 0.9386 | LM_LOSS: 0.4133 | LB_LOSS: 1.0505
[2026-05-24 12:51:27] Validation | Batch 1360/1463 | Loss: 0.9388 | LM_LOSS: 0.4136 | LB_LOSS: 1.0505
[2026-05-24 12:51:29] Validation | Batch 1370/1463 | Loss: 0.9392 | LM_LOSS: 0.4139 | LB_LOSS: 1.0506
[2026-05-24 12:51:30] Validation | Batch 1380/1463 | Loss: 0.9391 | LM_LOSS: 0.4138 | LB_LOSS: 1.0505
[2026-05-24 12:51:32] Validation | Batch 1390/1463 | Loss: 0.9390 | LM_LOSS: 0.4137 | LB_LOSS: 1.0506
[2026-05-24 12:51:34] Validation | Batch 1400/1463 | Loss: 0.9393 | LM_LOSS: 0.4140 | LB_LOSS: 1.0505
[2026-05-24 12:51:35] Validation | Batch 1410/1463 | Loss: 0.9395 | LM_LOSS: 0.4142 | LB_LOSS: 1.0505
[2026-05-24 12:51:37] Validation | Batch 1420/1463 | Loss: 0.9396 | LM_LOSS: 0.4143 | LB_LOSS: 1.0505
[2026-05-24 12:51:39] Validation | Batch 1430/1463 | Loss: 0.9397 | LM_LOSS: 0.4145 | LB_LOSS: 1.0505
[2026-05-24 12:51:40] Validation | Batch 1440/1463 | Loss: 0.9402 | LM_LOSS: 0.4149 | LB_LOSS: 1.0505
[2026-05-24 12:51:42] Validation | Batch 1450/1463 | Loss: 0.9398 | LM_LOSS: 0.4145 | LB_LOSS: 1.0505
[2026-05-24 12:51:44] Validation | Batch 1460/1463 | Loss: 0.9400 | LM_LOSS: 0.4148 | LB_LOSS: 1.0505
[2026-05-24 12:51:44] Validation | Batch 1463/1463 | Loss: 0.9399 | LM_LOSS: 0.4147 | LB_LOSS: 1.0505
[2026-05-24 12:51:44] Validation | Loss: 0.9399 | LM_LOSS: 0.4147 | LB_LOSS: 1.0505 | PPL: 1.51 | Time: 246.32s
[2026-05-24 12:51:55] Epoch 1 | Step 4010 | Loss: 0.9688 | LM: 0.3787 | LB: 1.1850 | CL0: 3.4 | CL1: 5.7 | HR0: 0.302/SR0: 0.279 | HR1: 0.197/SR1: 0.177 | LR: 1.00e-04
[2026-05-24 12:52:07] Epoch 1 | Step 4020 | Loss: 0.9687 | LM: 0.3788 | LB: 1.1847 | CL0: 3.4 | CL1: 5.7 | HR0: 0.302/SR0: 0.279 | HR1: 0.197/SR1: 0.177 | LR: 1.00e-04
[2026-05-24 12:52:18] Epoch 1 | Step 4030 | Loss: 0.9687 | LM: 0.3788 | LB: 1.1843 | CL0: 3.4 | CL1: 5.7 | HR0: 0.302/SR0: 0.279 | HR1: 0.197/SR1: 0.177 | LR: 1.00e-04
[2026-05-24 12:52:30] Epoch 1 | Step 4040 | Loss: 0.9687 | LM: 0.3789 | LB: 1.1840 | CL0: 3.4 | CL1: 5.7 | HR0: 0.302/SR0: 0.278 | HR1: 0.197/SR1: 0.177 | LR: 1.00e-04
[2026-05-24 12:52:41] Epoch 1 | Step 4050 | Loss: 0.9686 | LM: 0.3788 | LB: 1.1837 | CL0: 3.4 | CL1: 5.7 | HR0: 0.302/SR0: 0.278 | HR1: 0.197/SR1: 0.177 | LR: 1.00e-04
[2026-05-24 12:52:52] Epoch 1 | Step 4060 | Loss: 0.9686 | LM: 0.3790 | LB: 1.1833 | CL0: 3.4 | CL1: 5.7 | HR0: 0.301/SR0: 0.278 | HR1: 0.197/SR1: 0.177 | LR: 1.00e-04
[2026-05-24 12:53:02] Epoch 1 | Step 4070 | Loss: 0.9685 | LM: 0.3791 | LB: 1.1830 | CL0: 3.4 | CL1: 5.7 | HR0: 0.301/SR0: 0.278 | HR1: 0.197/SR1: 0.177 | LR: 1.00e-04
[2026-05-24 12:53:12] Epoch 1 | Step 4080 | Loss: 0.9685 | LM: 0.3793 | LB: 1.1827 | CL0: 3.4 | CL1: 5.7 | HR0: 0.301/SR0: 0.278 | HR1: 0.196/SR1: 0.177 | LR: 1.00e-04
[2026-05-24 12:53:23] Epoch 1 | Step 4090 | Loss: 0.9684 | LM: 0.3795 | LB: 1.1823 | CL0: 3.4 | CL1: 5.7 | HR0: 0.301/SR0: 0.278 | HR1: 0.196/SR1: 0.177 | LR: 1.00e-04
[2026-05-24 12:53:34] Epoch 1 | Step 4100 | Loss: 0.9684 | LM: 0.3795 | LB: 1.1820 | CL0: 3.4 | CL1: 5.7 | HR0: 0.301/SR0: 0.277 | HR1: 0.196/SR1: 0.176 | LR: 1.00e-04
[2026-05-24 12:53:44] Epoch 1 | Step 4110 | Loss: 0.9684 | LM: 0.3798 | LB: 1.1817 | CL0: 3.4 | CL1: 5.7 | HR0: 0.301/SR0: 0.277 | HR1: 0.196/SR1: 0.176 | LR: 1.00e-04
[2026-05-24 12:53:55] Epoch 1 | Step 4120 | Loss: 0.9683 | LM: 0.3799 | LB: 1.1814 | CL0: 3.4 | CL1: 5.7 | HR0: 0.301/SR0: 0.277 | HR1: 0.196/SR1: 0.176 | LR: 1.00e-04
[2026-05-24 12:54:06] Epoch 1 | Step 4130 | Loss: 0.9682 | LM: 0.3800 | LB: 1.1811 | CL0: 3.4 | CL1: 5.7 | HR0: 0.300/SR0: 0.277 | HR1: 0.196/SR1: 0.176 | LR: 1.00e-04
[2026-05-24 12:54:16] Epoch 1 | Step 4140 | Loss: 0.9681 | LM: 0.3800 | LB: 1.1807 | CL0: 3.4 | CL1: 5.8 | HR0: 0.300/SR0: 0.277 | HR1: 0.196/SR1: 0.176 | LR: 1.00e-04
[2026-05-24 12:54:27] Epoch 1 | Step 4150 | Loss: 0.9680 | LM: 0.3801 | LB: 1.1804 | CL0: 3.4 | CL1: 5.8 | HR0: 0.300/SR0: 0.277 | HR1: 0.196/SR1: 0.176 | LR: 1.00e-04
[2026-05-24 12:54:38] Epoch 1 | Step 4160 | Loss: 0.9680 | LM: 0.3804 | LB: 1.1801 | CL0: 3.4 | CL1: 5.8 | HR0: 0.300/SR0: 0.276 | HR1: 0.196/SR1: 0.176 | LR: 1.00e-04
[2026-05-24 12:54:49] Epoch 1 | Step 4170 | Loss: 0.9680 | LM: 0.3804 | LB: 1.1798 | CL0: 3.4 | CL1: 5.8 | HR0: 0.300/SR0: 0.276 | HR1: 0.195/SR1: 0.176 | LR: 1.00e-04
[2026-05-24 12:55:00] Epoch 1 | Step 4180 | Loss: 0.9679 | LM: 0.3806 | LB: 1.1795 | CL0: 3.4 | CL1: 5.8 | HR0: 0.300/SR0: 0.276 | HR1: 0.195/SR1: 0.176 | LR: 1.00e-04
[2026-05-24 12:55:11] Epoch 1 | Step 4190 | Loss: 0.9678 | LM: 0.3807 | LB: 1.1792 | CL0: 3.4 | CL1: 5.8 | HR0: 0.300/SR0: 0.276 | HR1: 0.195/SR1: 0.175 | LR: 1.00e-04
[2026-05-24 12:55:22] Epoch 1 | Step 4200 | Loss: 0.9678 | LM: 0.3808 | LB: 1.1789 | CL0: 3.4 | CL1: 5.8 | HR0: 0.299/SR0: 0.276 | HR1: 0.195/SR1: 0.175 | LR: 1.00e-04
[2026-05-24 12:55:33] Epoch 1 | Step 4210 | Loss: 0.9677 | LM: 0.3809 | LB: 1.1786 | CL0: 3.4 | CL1: 5.8 | HR0: 0.299/SR0: 0.276 | HR1: 0.195/SR1: 0.175 | LR: 1.00e-04
[2026-05-24 12:55:44] Epoch 1 | Step 4220 | Loss: 0.9676 | LM: 0.3808 | LB: 1.1783 | CL0: 3.4 | CL1: 5.8 | HR0: 0.299/SR0: 0.276 | HR1: 0.195/SR1: 0.175 | LR: 1.00e-04
[2026-05-24 12:55:56] Epoch 1 | Step 4230 | Loss: 0.9676 | LM: 0.3808 | LB: 1.1780 | CL0: 3.4 | CL1: 5.8 | HR0: 0.299/SR0: 0.275 | HR1: 0.195/SR1: 0.175 | LR: 1.00e-04
[2026-05-24 12:56:07] Epoch 1 | Step 4240 | Loss: 0.9675 | LM: 0.3809 | LB: 1.1777 | CL0: 3.4 | CL1: 5.8 | HR0: 0.299/SR0: 0.275 | HR1: 0.195/SR1: 0.175 | LR: 1.00e-04
[2026-05-24 12:56:18] Epoch 1 | Step 4250 | Loss: 0.9675 | LM: 0.3810 | LB: 1.1774 | CL0: 3.4 | CL1: 5.8 | HR0: 0.299/SR0: 0.275 | HR1: 0.195/SR1: 0.175 | LR: 1.00e-04
[2026-05-24 12:56:29] Epoch 1 | Step 4260 | Loss: 0.9674 | LM: 0.3808 | LB: 1.1771 | CL0: 3.4 | CL1: 5.8 | HR0: 0.299/SR0: 0.275 | HR1: 0.195/SR1: 0.175 | LR: 1.00e-04
[2026-05-24 12:56:40] Epoch 1 | Step 4270 | Loss: 0.9673 | LM: 0.3807 | LB: 1.1768 | CL0: 3.4 | CL1: 5.8 | HR0: 0.298/SR0: 0.275 | HR1: 0.195/SR1: 0.175 | LR: 1.00e-04
[2026-05-24 12:56:51] Epoch 1 | Step 4280 | Loss: 0.9672 | LM: 0.3807 | LB: 1.1765 | CL0: 3.4 | CL1: 5.8 | HR0: 0.298/SR0: 0.275 | HR1: 0.194/SR1: 0.175 | LR: 1.00e-04
[2026-05-24 12:57:02] Epoch 1 | Step 4290 | Loss: 0.9673 | LM: 0.3809 | LB: 1.1762 | CL0: 3.4 | CL1: 5.8 | HR0: 0.298/SR0: 0.275 | HR1: 0.194/SR1: 0.175 | LR: 1.00e-04
[2026-05-24 12:57:13] Epoch 1 | Step 4300 | Loss: 0.9673 | LM: 0.3810 | LB: 1.1759 | CL0: 3.4 | CL1: 5.8 | HR0: 0.298/SR0: 0.274 | HR1: 0.194/SR1: 0.175 | LR: 1.00e-04
[2026-05-24 12:57:24] Epoch 1 | Step 4310 | Loss: 0.9672 | LM: 0.3812 | LB: 1.1756 | CL0: 3.4 | CL1: 5.8 | HR0: 0.298/SR0: 0.274 | HR1: 0.194/SR1: 0.174 | LR: 1.00e-04
[2026-05-24 12:57:35] Epoch 1 | Step 4320 | Loss: 0.9672 | LM: 0.3812 | LB: 1.1753 | CL0: 3.4 | CL1: 5.8 | HR0: 0.298/SR0: 0.274 | HR1: 0.194/SR1: 0.174 | LR: 1.00e-04
[2026-05-24 12:57:46] Epoch 1 | Step 4330 | Loss: 0.9671 | LM: 0.3814 | LB: 1.1750 | CL0: 3.4 | CL1: 5.8 | HR0: 0.298/SR0: 0.274 | HR1: 0.194/SR1: 0.174 | LR: 1.00e-04
[2026-05-24 12:57:58] Epoch 1 | Step 4340 | Loss: 0.9671 | LM: 0.3817 | LB: 1.1747 | CL0: 3.4 | CL1: 5.8 | HR0: 0.297/SR0: 0.274 | HR1: 0.194/SR1: 0.174 | LR: 1.00e-04
[2026-05-24 12:58:09] Epoch 1 | Step 4350 | Loss: 0.9671 | LM: 0.3818 | LB: 1.1744 | CL0: 3.4 | CL1: 5.8 | HR0: 0.297/SR0: 0.274 | HR1: 0.194/SR1: 0.174 | LR: 1.00e-04
[2026-05-24 12:58:20] Epoch 1 | Step 4360 | Loss: 0.9670 | LM: 0.3818 | LB: 1.1741 | CL0: 3.4 | CL1: 5.8 | HR0: 0.297/SR0: 0.273 | HR1: 0.194/SR1: 0.174 | LR: 1.00e-04
[2026-05-24 12:58:31] Epoch 1 | Step 4370 | Loss: 0.9669 | LM: 0.3819 | LB: 1.1738 | CL0: 3.4 | CL1: 5.8 | HR0: 0.297/SR0: 0.273 | HR1: 0.194/SR1: 0.174 | LR: 1.00e-04
[2026-05-24 12:58:42] Epoch 1 | Step 4380 | Loss: 0.9667 | LM: 0.3819 | LB: 1.1735 | CL0: 3.4 | CL1: 5.8 | HR0: 0.297/SR0: 0.273 | HR1: 0.194/SR1: 0.174 | LR: 1.00e-04
[2026-05-24 12:58:53] Epoch 1 | Step 4390 | Loss: 0.9667 | LM: 0.3817 | LB: 1.1732 | CL0: 3.4 | CL1: 5.8 | HR0: 0.297/SR0: 0.273 | HR1: 0.193/SR1: 0.174 | LR: 1.00e-04
[2026-05-24 12:59:04] Epoch 1 | Step 4400 | Loss: 0.9667 | LM: 0.3819 | LB: 1.1730 | CL0: 3.4 | CL1: 5.8 | HR0: 0.297/SR0: 0.273 | HR1: 0.193/SR1: 0.174 | LR: 1.00e-04
[2026-05-24 12:59:15] Epoch 1 | Step 4410 | Loss: 0.9665 | LM: 0.3817 | LB: 1.1727 | CL0: 3.4 | CL1: 5.8 | HR0: 0.297/SR0: 0.273 | HR1: 0.193/SR1: 0.174 | LR: 1.00e-04
[2026-05-24 12:59:26] Epoch 1 | Step 4420 | Loss: 0.9664 | LM: 0.3818 | LB: 1.1724 | CL0: 3.5 | CL1: 5.8 | HR0: 0.296/SR0: 0.273 | HR1: 0.193/SR1: 0.174 | LR: 1.00e-04
[2026-05-24 12:59:37] Epoch 1 | Step 4430 | Loss: 0.9664 | LM: 0.3817 | LB: 1.1721 | CL0: 3.5 | CL1: 5.8 | HR0: 0.296/SR0: 0.272 | HR1: 0.193/SR1: 0.173 | LR: 1.00e-04
[2026-05-24 12:59:48] Epoch 1 | Step 4440 | Loss: 0.9663 | LM: 0.3817 | LB: 1.1718 | CL0: 3.5 | CL1: 5.8 | HR0: 0.296/SR0: 0.272 | HR1: 0.193/SR1: 0.173 | LR: 1.00e-04
[2026-05-24 12:59:59] Epoch 1 | Step 4450 | Loss: 0.9662 | LM: 0.3817 | LB: 1.1715 | CL0: 3.5 | CL1: 5.8 | HR0: 0.296/SR0: 0.272 | HR1: 0.193/SR1: 0.173 | LR: 1.00e-04
[2026-05-24 13:00:10] Epoch 1 | Step 4460 | Loss: 0.9660 | LM: 0.3817 | LB: 1.1712 | CL0: 3.5 | CL1: 5.8 | HR0: 0.296/SR0: 0.272 | HR1: 0.193/SR1: 0.173 | LR: 1.00e-04
[2026-05-24 13:00:21] Epoch 1 | Step 4470 | Loss: 0.9660 | LM: 0.3818 | LB: 1.1710 | CL0: 3.5 | CL1: 5.8 | HR0: 0.296/SR0: 0.272 | HR1: 0.193/SR1: 0.173 | LR: 1.00e-04
[2026-05-24 13:00:33] Epoch 1 | Step 4480 | Loss: 0.9660 | LM: 0.3820 | LB: 1.1707 | CL0: 3.5 | CL1: 5.8 | HR0: 0.296/SR0: 0.272 | HR1: 0.193/SR1: 0.173 | LR: 1.00e-04
[2026-05-24 13:00:43] Epoch 1 | Step 4490 | Loss: 0.9659 | LM: 0.3821 | LB: 1.1704 | CL0: 3.5 | CL1: 5.8 | HR0: 0.295/SR0: 0.272 | HR1: 0.193/SR1: 0.173 | LR: 1.00e-04
[2026-05-24 13:00:54] Epoch 1 | Step 4500 | Loss: 0.9659 | LM: 0.3820 | LB: 1.1701 | CL0: 3.5 | CL1: 5.8 | HR0: 0.295/SR0: 0.271 | HR1: 0.192/SR1: 0.173 | LR: 1.00e-04
[2026-05-24 13:01:05] Epoch 1 | Step 4510 | Loss: 0.9659 | LM: 0.3820 | LB: 1.1698 | CL0: 3.5 | CL1: 5.8 | HR0: 0.295/SR0: 0.271 | HR1: 0.192/SR1: 0.173 | LR: 1.00e-04
[2026-05-24 13:01:16] Epoch 1 | Step 4520 | Loss: 0.9659 | LM: 0.3822 | LB: 1.1695 | CL0: 3.5 | CL1: 5.8 | HR0: 0.295/SR0: 0.271 | HR1: 0.192/SR1: 0.173 | LR: 1.00e-04
[2026-05-24 13:01:27] Epoch 1 | Step 4530 | Loss: 0.9657 | LM: 0.3822 | LB: 1.1693 | CL0: 3.5 | CL1: 5.8 | HR0: 0.295/SR0: 0.271 | HR1: 0.192/SR1: 0.173 | LR: 1.00e-04
[2026-05-24 13:01:38] Epoch 1 | Step 4540 | Loss: 0.9657 | LM: 0.3823 | LB: 1.1690 | CL0: 3.5 | CL1: 5.8 | HR0: 0.295/SR0: 0.271 | HR1: 0.192/SR1: 0.173 | LR: 1.00e-04
[2026-05-24 13:01:50] Epoch 1 | Step 4550 | Loss: 0.9656 | LM: 0.3824 | LB: 1.1687 | CL0: 3.5 | CL1: 5.8 | HR0: 0.295/SR0: 0.271 | HR1: 0.192/SR1: 0.173 | LR: 1.00e-04
[2026-05-24 13:02:01] Epoch 1 | Step 4560 | Loss: 0.9655 | LM: 0.3823 | LB: 1.1684 | CL0: 3.5 | CL1: 5.8 | HR0: 0.294/SR0: 0.271 | HR1: 0.192/SR1: 0.172 | LR: 1.00e-04
[2026-05-24 13:02:12] Epoch 1 | Step 4570 | Loss: 0.9655 | LM: 0.3826 | LB: 1.1682 | CL0: 3.5 | CL1: 5.8 | HR0: 0.294/SR0: 0.270 | HR1: 0.192/SR1: 0.172 | LR: 1.00e-04
[2026-05-24 13:02:23] Epoch 1 | Step 4580 | Loss: 0.9654 | LM: 0.3827 | LB: 1.1679 | CL0: 3.5 | CL1: 5.8 | HR0: 0.294/SR0: 0.270 | HR1: 0.192/SR1: 0.172 | LR: 1.00e-04
[2026-05-24 13:02:34] Epoch 1 | Step 4590 | Loss: 0.9653 | LM: 0.3827 | LB: 1.1676 | CL0: 3.5 | CL1: 5.8 | HR0: 0.294/SR0: 0.270 | HR1: 0.192/SR1: 0.172 | LR: 1.00e-04
[2026-05-24 13:02:45] Epoch 1 | Step 4600 | Loss: 0.9653 | LM: 0.3827 | LB: 1.1673 | CL0: 3.5 | CL1: 5.8 | HR0: 0.294/SR0: 0.270 | HR1: 0.192/SR1: 0.172 | LR: 1.00e-04
[2026-05-24 13:02:56] Epoch 1 | Step 4610 | Loss: 0.9653 | LM: 0.3827 | LB: 1.1671 | CL0: 3.5 | CL1: 5.8 | HR0: 0.294/SR0: 0.270 | HR1: 0.192/SR1: 0.172 | LR: 1.00e-04
[2026-05-24 13:03:07] Epoch 1 | Step 4620 | Loss: 0.9652 | LM: 0.3829 | LB: 1.1668 | CL0: 3.5 | CL1: 5.8 | HR0: 0.294/SR0: 0.270 | HR1: 0.191/SR1: 0.172 | LR: 1.00e-04
[2026-05-24 13:03:18] Epoch 1 | Step 4630 | Loss: 0.9651 | LM: 0.3829 | LB: 1.1665 | CL0: 3.5 | CL1: 5.8 | HR0: 0.293/SR0: 0.270 | HR1: 0.191/SR1: 0.172 | LR: 1.00e-04
[2026-05-24 13:03:29] Epoch 1 | Step 4640 | Loss: 0.9651 | LM: 0.3829 | LB: 1.1663 | CL0: 3.5 | CL1: 5.8 | HR0: 0.293/SR0: 0.269 | HR1: 0.191/SR1: 0.172 | LR: 1.00e-04
[2026-05-24 13:03:40] Epoch 1 | Step 4650 | Loss: 0.9650 | LM: 0.3829 | LB: 1.1660 | CL0: 3.5 | CL1: 5.8 | HR0: 0.293/SR0: 0.269 | HR1: 0.191/SR1: 0.172 | LR: 1.00e-04
[2026-05-24 13:03:51] Epoch 1 | Step 4660 | Loss: 0.9649 | LM: 0.3829 | LB: 1.1658 | CL0: 3.5 | CL1: 5.8 | HR0: 0.293/SR0: 0.269 | HR1: 0.191/SR1: 0.172 | LR: 1.00e-04
[2026-05-24 13:04:02] Epoch 1 | Step 4670 | Loss: 0.9649 | LM: 0.3829 | LB: 1.1655 | CL0: 3.5 | CL1: 5.9 | HR0: 0.293/SR0: 0.269 | HR1: 0.191/SR1: 0.171 | LR: 1.00e-04
[2026-05-24 13:04:13] Epoch 1 | Step 4680 | Loss: 0.9647 | LM: 0.3830 | LB: 1.1652 | CL0: 3.5 | CL1: 5.9 | HR0: 0.293/SR0: 0.269 | HR1: 0.191/SR1: 0.171 | LR: 1.00e-04
[2026-05-24 13:04:22] Epoch 1 completed in 6378.82s | Loss: 0.9647 | CL0: 3.5 | CL1: 5.9
[2026-05-24 13:04:22]
============================================================
[2026-05-24 13:04:22] EPOCH 2/3 (step 4687)
[2026-05-24 13:04:22] ============================================================
[2026-05-24 13:04:25] Epoch 2 | Step 4690 | Loss: 0.8900 | LM: 0.3218 | LB: 1.0427 | CL0: 4.3 | CL1: 6.3 | HR0: 0.233/SR0: 0.205 | HR1: 0.160/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:04:36] Epoch 2 | Step 4700 | Loss: 0.9092 | LM: 0.4066 | LB: 1.0437 | CL0: 4.3 | CL1: 6.6 | HR0: 0.233/SR0: 0.207 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 13:04:47] Epoch 2 | Step 4710 | Loss: 0.9140 | LM: 0.4202 | LB: 1.0485 | CL0: 4.2 | CL1: 6.6 | HR0: 0.238/SR0: 0.211 | HR1: 0.155/SR1: 0.138 | LR: 1.00e-04
[2026-05-24 13:04:58] Epoch 2 | Step 4720 | Loss: 0.9093 | LM: 0.4078 | LB: 1.0514 | CL0: 4.2 | CL1: 6.2 | HR0: 0.237/SR0: 0.210 | HR1: 0.166/SR1: 0.147 | LR: 1.00e-04
[2026-05-24 13:05:10] Epoch 2 | Step 4730 | Loss: 0.9079 | LM: 0.4032 | LB: 1.0493 | CL0: 4.3 | CL1: 6.2 | HR0: 0.235/SR0: 0.208 | HR1: 0.165/SR1: 0.145 | LR: 1.00e-04
[2026-05-24 13:05:21] Epoch 2 | Step 4740 | Loss: 0.9027 | LM: 0.3934 | LB: 1.0486 | CL0: 4.3 | CL1: 6.4 | HR0: 0.235/SR0: 0.209 | HR1: 0.161/SR1: 0.142 | LR: 1.00e-04
[2026-05-24 13:05:32] Epoch 2 | Step 4750 | Loss: 0.9013 | LM: 0.3913 | LB: 1.0502 | CL0: 4.2 | CL1: 6.3 | HR0: 0.237/SR0: 0.210 | HR1: 0.164/SR1: 0.144 | LR: 1.00e-04
[2026-05-24 13:05:43] Epoch 2 | Step 4760 | Loss: 0.9010 | LM: 0.3913 | LB: 1.0498 | CL0: 4.3 | CL1: 6.2 | HR0: 0.236/SR0: 0.209 | HR1: 0.165/SR1: 0.145 | LR: 1.00e-04
[2026-05-24 13:05:54] Epoch 2 | Step 4770 | Loss: 0.9012 | LM: 0.3991 | LB: 1.0492 | CL0: 4.3 | CL1: 6.3 | HR0: 0.236/SR0: 0.209 | HR1: 0.162/SR1: 0.143 | LR: 1.00e-04
[2026-05-24 13:06:05] Epoch 2 | Step 4780 | Loss: 0.9004 | LM: 0.4024 | LB: 1.0493 | CL0: 4.3 | CL1: 6.4 | HR0: 0.236/SR0: 0.209 | HR1: 0.160/SR1: 0.141 | LR: 1.00e-04
[2026-05-24 13:06:16] Epoch 2 | Step 4790 | Loss: 0.9034 | LM: 0.4013 | LB: 1.0487 | CL0: 4.3 | CL1: 6.5 | HR0: 0.236/SR0: 0.209 | HR1: 0.159/SR1: 0.140 | LR: 1.00e-04
[2026-05-24 13:06:27] Epoch 2 | Step 4800 | Loss: 0.9031 | LM: 0.4032 | LB: 1.0479 | CL0: 4.3 | CL1: 6.4 | HR0: 0.235/SR0: 0.208 | HR1: 0.159/SR1: 0.141 | LR: 1.00e-04
[2026-05-24 13:06:39] Epoch 2 | Step 4810 | Loss: 0.9053 | LM: 0.4027 | LB: 1.0484 | CL0: 4.3 | CL1: 6.4 | HR0: 0.236/SR0: 0.209 | HR1: 0.159/SR1: 0.141 | LR: 1.00e-04
[2026-05-24 13:06:50] Epoch 2 | Step 4820 | Loss: 0.9044 | LM: 0.4018 | LB: 1.0481 | CL0: 4.3 | CL1: 6.5 | HR0: 0.236/SR0: 0.209 | HR1: 0.159/SR1: 0.140 | LR: 1.00e-04
[2026-05-24 13:07:01] Epoch 2 | Step 4830 | Loss: 0.9055 | LM: 0.3985 | LB: 1.0475 | CL0: 4.3 | CL1: 6.5 | HR0: 0.235/SR0: 0.208 | HR1: 0.158/SR1: 0.140 | LR: 1.00e-04
[2026-05-24 13:07:12] Epoch 2 | Step 4840 | Loss: 0.9069 | LM: 0.4002 | LB: 1.0479 | CL0: 4.3 | CL1: 6.5 | HR0: 0.236/SR0: 0.209 | HR1: 0.158/SR1: 0.140 | LR: 1.00e-04
[2026-05-24 13:07:23] Epoch 2 | Step 4850 | Loss: 0.9054 | LM: 0.3995 | LB: 1.0477 | CL0: 4.3 | CL1: 6.5 | HR0: 0.236/SR0: 0.208 | HR1: 0.158/SR1: 0.140 | LR: 1.00e-04
[2026-05-24 13:07:34] Epoch 2 | Step 4860 | Loss: 0.9059 | LM: 0.3983 | LB: 1.0473 | CL0: 4.3 | CL1: 6.5 | HR0: 0.235/SR0: 0.208 | HR1: 0.158/SR1: 0.140 | LR: 1.00e-04
[2026-05-24 13:07:45] Epoch 2 | Step 4870 | Loss: 0.9067 | LM: 0.3972 | LB: 1.0472 | CL0: 4.3 | CL1: 6.5 | HR0: 0.235/SR0: 0.208 | HR1: 0.158/SR1: 0.140 | LR: 1.00e-04
[2026-05-24 13:07:57] Epoch 2 | Step 4880 | Loss: 0.9080 | LM: 0.3972 | LB: 1.0468 | CL0: 4.3 | CL1: 6.5 | HR0: 0.235/SR0: 0.208 | HR1: 0.158/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:08:08] Epoch 2 | Step 4890 | Loss: 0.9077 | LM: 0.3970 | LB: 1.0463 | CL0: 4.3 | CL1: 6.5 | HR0: 0.234/SR0: 0.207 | HR1: 0.157/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:08:19] Epoch 2 | Step 4900 | Loss: 0.9079 | LM: 0.3972 | LB: 1.0459 | CL0: 4.3 | CL1: 6.5 | HR0: 0.234/SR0: 0.207 | HR1: 0.157/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:08:30] Epoch 2 | Step 4910 | Loss: 0.9087 | LM: 0.3985 | LB: 1.0458 | CL0: 4.3 | CL1: 6.5 | HR0: 0.234/SR0: 0.207 | HR1: 0.157/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:08:41] Epoch 2 | Step 4920 | Loss: 0.9086 | LM: 0.3991 | LB: 1.0457 | CL0: 4.3 | CL1: 6.5 | HR0: 0.233/SR0: 0.207 | HR1: 0.157/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:08:52] Epoch 2 | Step 4930 | Loss: 0.9084 | LM: 0.3990 | LB: 1.0455 | CL0: 4.3 | CL1: 6.5 | HR0: 0.233/SR0: 0.207 | HR1: 0.157/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:09:03] Epoch 2 | Step 4940 | Loss: 0.9094 | LM: 0.3995 | LB: 1.0452 | CL0: 4.3 | CL1: 6.5 | HR0: 0.233/SR0: 0.207 | HR1: 0.157/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:09:14] Epoch 2 | Step 4950 | Loss: 0.9083 | LM: 0.3996 | LB: 1.0451 | CL0: 4.3 | CL1: 6.5 | HR0: 0.233/SR0: 0.206 | HR1: 0.157/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:09:25] Epoch 2 | Step 4960 | Loss: 0.9092 | LM: 0.4011 | LB: 1.0448 | CL0: 4.3 | CL1: 6.5 | HR0: 0.233/SR0: 0.206 | HR1: 0.157/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:09:36] Epoch 2 | Step 4970 | Loss: 0.9091 | LM: 0.3999 | LB: 1.0446 | CL0: 4.3 | CL1: 6.5 | HR0: 0.232/SR0: 0.206 | HR1: 0.157/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:09:47] Epoch 2 | Step 4980 | Loss: 0.9086 | LM: 0.3992 | LB: 1.0444 | CL0: 4.3 | CL1: 6.5 | HR0: 0.232/SR0: 0.206 | HR1: 0.157/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:09:58] Epoch 2 | Step 4990 | Loss: 0.9085 | LM: 0.3989 | LB: 1.0443 | CL0: 4.3 | CL1: 6.5 | HR0: 0.232/SR0: 0.206 | HR1: 0.156/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:10:10] Epoch 2 | Step 5000 | Loss: 0.9090 | LM: 0.3994 | LB: 1.0440 | CL0: 4.3 | CL1: 6.5 | HR0: 0.232/SR0: 0.206 | HR1: 0.156/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:10:11] Validation | Batch 10/1463 | Loss: 0.8914 | LM_LOSS: 0.3751 | LB_LOSS: 1.0326
[2026-05-24 13:10:12] Validation | Batch 20/1463 | Loss: 0.9127 | LM_LOSS: 0.3944 | LB_LOSS: 1.0365
[2026-05-24 13:10:14] Validation | Batch 30/1463 | Loss: 0.9186 | LM_LOSS: 0.3997 | LB_LOSS: 1.0379
[2026-05-24 13:10:16] Validation | Batch 40/1463 | Loss: 0.9288 | LM_LOSS: 0.4091 | LB_LOSS: 1.0394
[2026-05-24 13:10:18] Validation | Batch 50/1463 | Loss: 0.9366 | LM_LOSS: 0.4174 | LB_LOSS: 1.0384
[2026-05-24 13:10:20] Validation | Batch 60/1463 | Loss: 0.9378 | LM_LOSS: 0.4185 | LB_LOSS: 1.0385
[2026-05-24 13:10:22] Validation | Batch 70/1463 | Loss: 0.9367 | LM_LOSS: 0.4173 | LB_LOSS: 1.0387
[2026-05-24 13:10:24] Validation | Batch 80/1463 | Loss: 0.9379 | LM_LOSS: 0.4185 | LB_LOSS: 1.0388
[2026-05-24 13:10:25] Validation | Batch 90/1463 | Loss: 0.9376 | LM_LOSS: 0.4183 | LB_LOSS: 1.0387
[2026-05-24 13:10:27] Validation | Batch 100/1463 | Loss: 0.9378 | LM_LOSS: 0.4183 | LB_LOSS: 1.0388
[2026-05-24 13:10:29] Validation | Batch 110/1463 | Loss: 0.9365 | LM_LOSS: 0.4169 | LB_LOSS: 1.0392
[2026-05-24 13:10:30] Validation | Batch 120/1463 | Loss: 0.9380 | LM_LOSS: 0.4184 | LB_LOSS: 1.0392
[2026-05-24 13:10:32] Validation | Batch 130/1463 | Loss: 0.9410 | LM_LOSS: 0.4214 | LB_LOSS: 1.0392
[2026-05-24 13:10:34] Validation | Batch 140/1463 | Loss: 0.9422 | LM_LOSS: 0.4226 | LB_LOSS: 1.0392
[2026-05-24 13:10:35] Validation | Batch 150/1463 | Loss: 0.9404 | LM_LOSS: 0.4207 | LB_LOSS: 1.0394
[2026-05-24 13:10:37] Validation | Batch 160/1463 | Loss: 0.9416 | LM_LOSS: 0.4219 | LB_LOSS: 1.0392
[2026-05-24 13:10:39] Validation | Batch 170/1463 | Loss: 0.9415 | LM_LOSS: 0.4218 | LB_LOSS: 1.0393
[2026-05-24 13:10:41] Validation | Batch 180/1463 | Loss: 0.9423 | LM_LOSS: 0.4226 | LB_LOSS: 1.0394
[2026-05-24 13:10:42] Validation | Batch 190/1463 | Loss: 0.9429 | LM_LOSS: 0.4231 | LB_LOSS: 1.0395
[2026-05-24 13:10:44] Validation | Batch 200/1463 | Loss: 0.9422 | LM_LOSS: 0.4224 | LB_LOSS: 1.0395
[2026-05-24 13:10:46] Validation | Batch 210/1463 | Loss: 0.9428 | LM_LOSS: 0.4230 | LB_LOSS: 1.0396
[2026-05-24 13:10:48] Validation | Batch 220/1463 | Loss: 0.9418 | LM_LOSS: 0.4220 | LB_LOSS: 1.0397
[2026-05-24 13:10:49] Validation | Batch 230/1463 | Loss: 0.9439 | LM_LOSS: 0.4241 | LB_LOSS: 1.0394
[2026-05-24 13:10:51] Validation | Batch 240/1463 | Loss: 0.9443 | LM_LOSS: 0.4246 | LB_LOSS: 1.0394
[2026-05-24 13:10:53] Validation | Batch 250/1463 | Loss: 0.9434 | LM_LOSS: 0.4237 | LB_LOSS: 1.0394
[2026-05-24 13:10:55] Validation | Batch 260/1463 | Loss: 0.9452 | LM_LOSS: 0.4254 | LB_LOSS: 1.0397
[2026-05-24 13:10:56] Validation | Batch 270/1463 | Loss: 0.9439 | LM_LOSS: 0.4240 | LB_LOSS: 1.0396
[2026-05-24 13:10:58] Validation | Batch 280/1463 | Loss: 0.9450 | LM_LOSS: 0.4252 | LB_LOSS: 1.0397
[2026-05-24 13:11:00] Validation | Batch 290/1463 | Loss: 0.9440 | LM_LOSS: 0.4242 | LB_LOSS: 1.0397
[2026-05-24 13:11:01] Validation | Batch 300/1463 | Loss: 0.9448 | LM_LOSS: 0.4249 | LB_LOSS: 1.0399
[2026-05-24 13:11:03] Validation | Batch 310/1463 | Loss: 0.9456 | LM_LOSS: 0.4257 | LB_LOSS: 1.0398
[2026-05-24 13:11:05] Validation | Batch 320/1463 | Loss: 0.9442 | LM_LOSS: 0.4244 | LB_LOSS: 1.0396
[2026-05-24 13:11:07] Validation | Batch 330/1463 | Loss: 0.9441 | LM_LOSS: 0.4243 | LB_LOSS: 1.0396
[2026-05-24 13:11:08] Validation | Batch 340/1463 | Loss: 0.9439 | LM_LOSS: 0.4241 | LB_LOSS: 1.0397
[2026-05-24 13:11:10] Validation | Batch 350/1463 | Loss: 0.9443 | LM_LOSS: 0.4245 | LB_LOSS: 1.0396
[2026-05-24 13:11:12] Validation | Batch 360/1463 | Loss: 0.9444 | LM_LOSS: 0.4246 | LB_LOSS: 1.0397
[2026-05-24 13:11:13] Validation | Batch 370/1463 | Loss: 0.9445 | LM_LOSS: 0.4246 | LB_LOSS: 1.0397
[2026-05-24 13:11:15] Validation | Batch 380/1463 | Loss: 0.9447 | LM_LOSS: 0.4248 | LB_LOSS: 1.0396
[2026-05-24 13:11:16] Validation | Batch 390/1463 | Loss: 0.9456 | LM_LOSS: 0.4258 | LB_LOSS: 1.0396
[2026-05-24 13:11:18] Validation | Batch 400/1463 | Loss: 0.9455 | LM_LOSS: 0.4257 | LB_LOSS: 1.0397
[2026-05-24 13:11:20] Validation | Batch 410/1463 | Loss: 0.9455 | LM_LOSS: 0.4256 | LB_LOSS: 1.0398
[2026-05-24 13:11:21] Validation | Batch 420/1463 | Loss: 0.9458 | LM_LOSS: 0.4258 | LB_LOSS: 1.0399
[2026-05-24 13:11:23] Validation | Batch 430/1463 | Loss: 0.9459 | LM_LOSS: 0.4259 | LB_LOSS: 1.0399
[2026-05-24 13:11:25] Validation | Batch 440/1463 | Loss: 0.9462 | LM_LOSS: 0.4261 | LB_LOSS: 1.0400
[2026-05-24 13:11:26] Validation | Batch 450/1463 | Loss: 0.9459 | LM_LOSS: 0.4259 | LB_LOSS: 1.0401
[2026-05-24 13:11:28] Validation | Batch 460/1463 | Loss: 0.9459 | LM_LOSS: 0.4259 | LB_LOSS: 1.0400
[2026-05-24 13:11:30] Validation | Batch 470/1463 | Loss: 0.9466 | LM_LOSS: 0.4267 | LB_LOSS: 1.0400
[2026-05-24 13:11:32] Validation | Batch 480/1463 | Loss: 0.9464 | LM_LOSS: 0.4265 | LB_LOSS: 1.0399
[2026-05-24 13:11:34] Validation | Batch 490/1463 | Loss: 0.9464 | LM_LOSS: 0.4264 | LB_LOSS: 1.0399
[2026-05-24 13:11:36] Validation | Batch 500/1463 | Loss: 0.9461 | LM_LOSS: 0.4261 | LB_LOSS: 1.0400
[2026-05-24 13:11:37] Validation | Batch 510/1463 | Loss: 0.9455 | LM_LOSS: 0.4256 | LB_LOSS: 1.0399
[2026-05-24 13:11:39] Validation | Batch 520/1463 | Loss: 0.9453 | LM_LOSS: 0.4253 | LB_LOSS: 1.0400
[2026-05-24 13:11:41] Validation | Batch 530/1463 | Loss: 0.9457 | LM_LOSS: 0.4257 | LB_LOSS: 1.0399
[2026-05-24 13:11:42] Validation | Batch 540/1463 | Loss: 0.9461 | LM_LOSS: 0.4261 | LB_LOSS: 1.0400
[2026-05-24 13:11:43] Validation | Batch 550/1463 | Loss: 0.9458 | LM_LOSS: 0.4258 | LB_LOSS: 1.0400
[2026-05-24 13:11:45] Validation | Batch 560/1463 | Loss: 0.9463 | LM_LOSS: 0.4262 | LB_LOSS: 1.0401
[2026-05-24 13:11:47] Validation | Batch 570/1463 | Loss: 0.9462 | LM_LOSS: 0.4261 | LB_LOSS: 1.0401
[2026-05-24 13:11:49] Validation | Batch 580/1463 | Loss: 0.9459 | LM_LOSS: 0.4258 | LB_LOSS: 1.0401
[2026-05-24 13:11:51] Validation | Batch 590/1463 | Loss: 0.9459 | LM_LOSS: 0.4258 | LB_LOSS: 1.0402
[2026-05-24 13:11:53] Validation | Batch 600/1463 | Loss: 0.9462 | LM_LOSS: 0.4261 | LB_LOSS: 1.0402
[2026-05-24 13:11:54] Validation | Batch 610/1463 | Loss: 0.9464 | LM_LOSS: 0.4262 | LB_LOSS: 1.0402
[2026-05-24 13:11:56] Validation | Batch 620/1463 | Loss: 0.9456 | LM_LOSS: 0.4255 | LB_LOSS: 1.0402
[2026-05-24 13:11:58] Validation | Batch 630/1463 | Loss: 0.9454 | LM_LOSS: 0.4252 | LB_LOSS: 1.0403
[2026-05-24 13:11:59] Validation | Batch 640/1463 | Loss: 0.9452 | LM_LOSS: 0.4250 | LB_LOSS: 1.0403
[2026-05-24 13:12:01] Validation | Batch 650/1463 | Loss: 0.9447 | LM_LOSS: 0.4246 | LB_LOSS: 1.0404
[2026-05-24 13:12:03] Validation | Batch 660/1463 | Loss: 0.9442 | LM_LOSS: 0.4241 | LB_LOSS: 1.0403
[2026-05-24 13:12:04] Validation | Batch 670/1463 | Loss: 0.9438 | LM_LOSS: 0.4237 | LB_LOSS: 1.0403
[2026-05-24 13:12:06] Validation | Batch 680/1463 | Loss: 0.9438 | LM_LOSS: 0.4237 | LB_LOSS: 1.0402
[2026-05-24 13:12:08] Validation | Batch 690/1463 | Loss: 0.9442 | LM_LOSS: 0.4240 | LB_LOSS: 1.0403
[2026-05-24 13:12:09] Validation | Batch 700/1463 | Loss: 0.9441 | LM_LOSS: 0.4240 | LB_LOSS: 1.0402
[2026-05-24 13:12:11] Validation | Batch 710/1463 | Loss: 0.9446 | LM_LOSS: 0.4245 | LB_LOSS: 1.0403
[2026-05-24 13:12:13] Validation | Batch 720/1463 | Loss: 0.9454 | LM_LOSS: 0.4252 | LB_LOSS: 1.0404
[2026-05-24 13:12:14] Validation | Batch 730/1463 | Loss: 0.9452 | LM_LOSS: 0.4250 | LB_LOSS: 1.0404
[2026-05-24 13:12:16] Validation | Batch 740/1463 | Loss: 0.9450 | LM_LOSS: 0.4248 | LB_LOSS: 1.0403
[2026-05-24 13:12:17] Validation | Batch 750/1463 | Loss: 0.9447 | LM_LOSS: 0.4246 | LB_LOSS: 1.0403
[2026-05-24 13:12:19] Validation | Batch 760/1463 | Loss: 0.9444 | LM_LOSS: 0.4242 | LB_LOSS: 1.0403
[2026-05-24 13:12:20] Validation | Batch 770/1463 | Loss: 0.9441 | LM_LOSS: 0.4239 | LB_LOSS: 1.0404
[2026-05-24 13:12:22] Validation | Batch 780/1463 | Loss: 0.9439 | LM_LOSS: 0.4238 | LB_LOSS: 1.0403
[2026-05-24 13:12:23] Validation | Batch 790/1463 | Loss: 0.9442 | LM_LOSS: 0.4241 | LB_LOSS: 1.0402
[2026-05-24 13:12:25] Validation | Batch 800/1463 | Loss: 0.9441 | LM_LOSS: 0.4239 | LB_LOSS: 1.0402
[2026-05-24 13:12:26] Validation | Batch 810/1463 | Loss: 0.9436 | LM_LOSS: 0.4235 | LB_LOSS: 1.0402
[2026-05-24 13:12:28] Validation | Batch 820/1463 | Loss: 0.9438 | LM_LOSS: 0.4237 | LB_LOSS: 1.0402
[2026-05-24 13:12:30] Validation | Batch 830/1463 | Loss: 0.9439 | LM_LOSS: 0.4238 | LB_LOSS: 1.0402
[2026-05-24 13:12:32] Validation | Batch 840/1463 | Loss: 0.9437 | LM_LOSS: 0.4236 | LB_LOSS: 1.0403
[2026-05-24 13:12:33] Validation | Batch 850/1463 | Loss: 0.9439 | LM_LOSS: 0.4238 | LB_LOSS: 1.0403
[2026-05-24 13:12:35] Validation | Batch 860/1463 | Loss: 0.9440 | LM_LOSS: 0.4238 | LB_LOSS: 1.0403
[2026-05-24 13:12:37] Validation | Batch 870/1463 | Loss: 0.9442 | LM_LOSS: 0.4240 | LB_LOSS: 1.0403
[2026-05-24 13:12:38] Validation | Batch 880/1463 | Loss: 0.9435 | LM_LOSS: 0.4233 | LB_LOSS: 1.0403
[2026-05-24 13:12:40] Validation | Batch 890/1463 | Loss: 0.9434 | LM_LOSS: 0.4233 | LB_LOSS: 1.0403
[2026-05-24 13:12:42] Validation | Batch 900/1463 | Loss: 0.9432 | LM_LOSS: 0.4231 | LB_LOSS: 1.0402
[2026-05-24 13:12:44] Validation | Batch 910/1463 | Loss: 0.9432 | LM_LOSS: 0.4230 | LB_LOSS: 1.0403
[2026-05-24 13:12:45] Validation | Batch 920/1463 | Loss: 0.9433 | LM_LOSS: 0.4232 | LB_LOSS: 1.0403
[2026-05-24 13:12:47] Validation | Batch 930/1463 | Loss: 0.9429 | LM_LOSS: 0.4228 | LB_LOSS: 1.0403
[2026-05-24 13:12:49] Validation | Batch 940/1463 | Loss: 0.9425 | LM_LOSS: 0.4224 | LB_LOSS: 1.0402
[2026-05-24 13:12:50] Validation | Batch 950/1463 | Loss: 0.9429 | LM_LOSS: 0.4228 | LB_LOSS: 1.0402
[2026-05-24 13:12:52] Validation | Batch 960/1463 | Loss: 0.9430 | LM_LOSS: 0.4229 | LB_LOSS: 1.0402
[2026-05-24 13:12:54] Validation | Batch 970/1463 | Loss: 0.9431 | LM_LOSS: 0.4230 | LB_LOSS: 1.0401
[2026-05-24 13:12:56] Validation | Batch 980/1463 | Loss: 0.9434 | LM_LOSS: 0.4233 | LB_LOSS: 1.0401
[2026-05-24 13:12:57] Validation | Batch 990/1463 | Loss: 0.9436 | LM_LOSS: 0.4235 | LB_LOSS: 1.0401
[2026-05-24 13:12:59] Validation | Batch 1000/1463 | Loss: 0.9441 | LM_LOSS: 0.4241 | LB_LOSS: 1.0401
[2026-05-24 13:13:01] Validation | Batch 1010/1463 | Loss: 0.9441 | LM_LOSS: 0.4240 | LB_LOSS: 1.0402
[2026-05-24 13:13:02] Validation | Batch 1020/1463 | Loss: 0.9444 | LM_LOSS: 0.4243 | LB_LOSS: 1.0402
[2026-05-24 13:13:04] Validation | Batch 1030/1463 | Loss: 0.9449 | LM_LOSS: 0.4248 | LB_LOSS: 1.0402
[2026-05-24 13:13:06] Validation | Batch 1040/1463 | Loss: 0.9444 | LM_LOSS: 0.4243 | LB_LOSS: 1.0402
[2026-05-24 13:13:08] Validation | Batch 1050/1463 | Loss: 0.9443 | LM_LOSS: 0.4242 | LB_LOSS: 1.0402
[2026-05-24 13:13:09] Validation | Batch 1060/1463 | Loss: 0.9442 | LM_LOSS: 0.4241 | LB_LOSS: 1.0402
[2026-05-24 13:13:11] Validation | Batch 1070/1463 | Loss: 0.9443 | LM_LOSS: 0.4242 | LB_LOSS: 1.0402
[2026-05-24 13:13:12] Validation | Batch 1080/1463 | Loss: 0.9439 | LM_LOSS: 0.4238 | LB_LOSS: 1.0402
[2026-05-24 13:13:14] Validation | Batch 1090/1463 | Loss: 0.9438 | LM_LOSS: 0.4238 | LB_LOSS: 1.0401
[2026-05-24 13:13:16] Validation | Batch 1100/1463 | Loss: 0.9438 | LM_LOSS: 0.4238 | LB_LOSS: 1.0401
[2026-05-24 13:13:17] Validation | Batch 1110/1463 | Loss: 0.9439 | LM_LOSS: 0.4238 | LB_LOSS: 1.0401
[2026-05-24 13:13:19] Validation | Batch 1120/1463 | Loss: 0.9438 | LM_LOSS: 0.4237 | LB_LOSS: 1.0402
[2026-05-24 13:13:21] Validation | Batch 1130/1463 | Loss: 0.9434 | LM_LOSS: 0.4234 | LB_LOSS: 1.0401
[2026-05-24 13:13:22] Validation | Batch 1140/1463 | Loss: 0.9437 | LM_LOSS: 0.4236 | LB_LOSS: 1.0401
[2026-05-24 13:13:24] Validation | Batch 1150/1463 | Loss: 0.9437 | LM_LOSS: 0.4236 | LB_LOSS: 1.0401
[2026-05-24 13:13:26] Validation | Batch 1160/1463 | Loss: 0.9437 | LM_LOSS: 0.4236 | LB_LOSS: 1.0401
[2026-05-24 13:13:27] Validation | Batch 1170/1463 | Loss: 0.9436 | LM_LOSS: 0.4236 | LB_LOSS: 1.0401
[2026-05-24 13:13:29] Validation | Batch 1180/1463 | Loss: 0.9436 | LM_LOSS: 0.4236 | LB_LOSS: 1.0401
[2026-05-24 13:13:31] Validation | Batch 1190/1463 | Loss: 0.9437 | LM_LOSS: 0.4237 | LB_LOSS: 1.0401
[2026-05-24 13:13:33] Validation | Batch 1200/1463 | Loss: 0.9439 | LM_LOSS: 0.4239 | LB_LOSS: 1.0401
[2026-05-24 13:13:34] Validation | Batch 1210/1463 | Loss: 0.9442 | LM_LOSS: 0.4242 | LB_LOSS: 1.0401
[2026-05-24 13:13:36] Validation | Batch 1220/1463 | Loss: 0.9446 | LM_LOSS: 0.4245 | LB_LOSS: 1.0402
[2026-05-24 13:13:37] Validation | Batch 1230/1463 | Loss: 0.9445 | LM_LOSS: 0.4244 | LB_LOSS: 1.0402
[2026-05-24 13:13:39] Validation | Batch 1240/1463 | Loss: 0.9449 | LM_LOSS: 0.4248 | LB_LOSS: 1.0402
[2026-05-24 13:13:41] Validation | Batch 1250/1463 | Loss: 0.9451 | LM_LOSS: 0.4250 | LB_LOSS: 1.0402
[2026-05-24 13:13:43] Validation | Batch 1260/1463 | Loss: 0.9451 | LM_LOSS: 0.4250 | LB_LOSS: 1.0402
[2026-05-24 13:13:44] Validation | Batch 1270/1463 | Loss: 0.9448 | LM_LOSS: 0.4247 | LB_LOSS: 1.0402
[2026-05-24 13:13:46] Validation | Batch 1280/1463 | Loss: 0.9446 | LM_LOSS: 0.4245 | LB_LOSS: 1.0402
[2026-05-24 13:13:48] Validation | Batch 1290/1463 | Loss: 0.9447 | LM_LOSS: 0.4246 | LB_LOSS: 1.0402
[2026-05-24 13:13:49] Validation | Batch 1300/1463 | Loss: 0.9444 | LM_LOSS: 0.4243 | LB_LOSS: 1.0402
[2026-05-24 13:13:51] Validation | Batch 1310/1463 | Loss: 0.9443 | LM_LOSS: 0.4242 | LB_LOSS: 1.0402
[2026-05-24 13:13:52] Validation | Batch 1320/1463 | Loss: 0.9443 | LM_LOSS: 0.4243 | LB_LOSS: 1.0402
[2026-05-24 13:13:54] Validation | Batch 1330/1463 | Loss: 0.9443 | LM_LOSS: 0.4242 | LB_LOSS: 1.0401
[2026-05-24 13:13:55] Validation | Batch 1340/1463 | Loss: 0.9445 | LM_LOSS: 0.4244 | LB_LOSS: 1.0401
[2026-05-24 13:13:57] Validation | Batch 1350/1463 | Loss: 0.9445 | LM_LOSS: 0.4245 | LB_LOSS: 1.0401
[2026-05-24 13:13:59] Validation | Batch 1360/1463 | Loss: 0.9447 | LM_LOSS: 0.4247 | LB_LOSS: 1.0401
[2026-05-24 13:14:00] Validation | Batch 1370/1463 | Loss: 0.9451 | LM_LOSS: 0.4250 | LB_LOSS: 1.0402
[2026-05-24 13:14:02] Validation | Batch 1380/1463 | Loss: 0.9449 | LM_LOSS: 0.4249 | LB_LOSS: 1.0401
[2026-05-24 13:14:04] Validation | Batch 1390/1463 | Loss: 0.9448 | LM_LOSS: 0.4247 | LB_LOSS: 1.0401
[2026-05-24 13:14:05] Validation | Batch 1400/1463 | Loss: 0.9451 | LM_LOSS: 0.4250 | LB_LOSS: 1.0401
[2026-05-24 13:14:07] Validation | Batch 1410/1463 | Loss: 0.9452 | LM_LOSS: 0.4252 | LB_LOSS: 1.0401
[2026-05-24 13:14:08] Validation | Batch 1420/1463 | Loss: 0.9453 | LM_LOSS: 0.4253 | LB_LOSS: 1.0401
[2026-05-24 13:14:10] Validation | Batch 1430/1463 | Loss: 0.9454 | LM_LOSS: 0.4254 | LB_LOSS: 1.0401
[2026-05-24 13:14:12] Validation | Batch 1440/1463 | Loss: 0.9459 | LM_LOSS: 0.4258 | LB_LOSS: 1.0401
[2026-05-24 13:14:13] Validation | Batch 1450/1463 | Loss: 0.9455 | LM_LOSS: 0.4254 | LB_LOSS: 1.0401
[2026-05-24 13:14:15] Validation | Batch 1460/1463 | Loss: 0.9457 | LM_LOSS: 0.4257 | LB_LOSS: 1.0401
[2026-05-24 13:14:16] Validation | Batch 1463/1463 | Loss: 0.9456 | LM_LOSS: 0.4256 | LB_LOSS: 1.0401
[2026-05-24 13:14:16] Validation | Loss: 0.9456 | LM_LOSS: 0.4256 | LB_LOSS: 1.0401 | PPL: 1.53 | Time: 246.29s
[2026-05-24 13:14:27] Epoch 2 | Step 5010 | Loss: 0.9084 | LM: 0.3976 | LB: 1.0442 | CL0: 4.3 | CL1: 6.5 | HR0: 0.232/SR0: 0.206 | HR1: 0.157/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:14:37] Epoch 2 | Step 5020 | Loss: 0.9087 | LM: 0.3962 | LB: 1.0441 | CL0: 4.3 | CL1: 6.5 | HR0: 0.232/SR0: 0.205 | HR1: 0.157/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:14:48] Epoch 2 | Step 5030 | Loss: 0.9089 | LM: 0.3968 | LB: 1.0438 | CL0: 4.3 | CL1: 6.5 | HR0: 0.231/SR0: 0.205 | HR1: 0.157/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:14:59] Epoch 2 | Step 5040 | Loss: 0.9083 | LM: 0.3963 | LB: 1.0438 | CL0: 4.3 | CL1: 6.5 | HR0: 0.231/SR0: 0.205 | HR1: 0.156/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:15:10] Epoch 2 | Step 5050 | Loss: 0.9079 | LM: 0.3960 | LB: 1.0436 | CL0: 4.3 | CL1: 6.5 | HR0: 0.231/SR0: 0.205 | HR1: 0.156/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:15:22] Epoch 2 | Step 5060 | Loss: 0.9079 | LM: 0.3977 | LB: 1.0434 | CL0: 4.4 | CL1: 6.5 | HR0: 0.231/SR0: 0.205 | HR1: 0.156/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:15:33] Epoch 2 | Step 5070 | Loss: 0.9074 | LM: 0.3977 | LB: 1.0432 | CL0: 4.4 | CL1: 6.5 | HR0: 0.231/SR0: 0.205 | HR1: 0.156/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:15:44] Epoch 2 | Step 5080 | Loss: 0.9071 | LM: 0.3987 | LB: 1.0432 | CL0: 4.4 | CL1: 6.5 | HR0: 0.231/SR0: 0.205 | HR1: 0.156/SR1: 0.139 | LR: 1.00e-04
[2026-05-24 13:15:56] Epoch 2 | Step 5090 | Loss: 0.9068 | LM: 0.3988 | LB: 1.0431 | CL0: 4.4 | CL1: 6.5 | HR0: 0.231/SR0: 0.205 | HR1: 0.156/SR1: 0.138 | LR: 1.00e-04
[2026-05-24 13:16:07] Epoch 2 | Step 5100 | Loss: 0.9070 | LM: 0.3987 | LB: 1.0430 | CL0: 4.4 | CL1: 6.5 | HR0: 0.231/SR0: 0.205 | HR1: 0.156/SR1: 0.138 | LR: 1.00e-04
[2026-05-24 13:16:18] Epoch 2 | Step 5110 | Loss: 0.9071 | LM: 0.3961 | LB: 1.0428 | CL0: 4.4 | CL1: 6.6 | HR0: 0.230/SR0: 0.204 | HR1: 0.156/SR1: 0.138 | LR: 1.00e-04
[2026-05-24 13:16:29] Epoch 2 | Step 5120 | Loss: 0.9076 | LM: 0.3985 | LB: 1.0429 | CL0: 4.4 | CL1: 6.5 | HR0: 0.230/SR0: 0.204 | HR1: 0.156/SR1: 0.138 | LR: 1.00e-04
[2026-05-24 13:16:39] Epoch 2 | Step 5130 | Loss: 0.9078 | LM: 0.3998 | LB: 1.0429 | CL0: 4.4 | CL1: 6.5 | HR0: 0.230/SR0: 0.204 | HR1: 0.156/SR1: 0.138 | LR: 1.00e-04
[2026-05-24 13:16:50] Epoch 2 | Step 5140 | Loss: 0.9078 | LM: 0.4007 | LB: 1.0427 | CL0: 4.4 | CL1: 6.6 | HR0: 0.230/SR0: 0.204 | HR1: 0.156/SR1: 0.138 | LR: 1.00e-04
[2026-05-24 13:17:00] Epoch 2 | Step 5150 | Loss: 0.9075 | LM: 0.4000 | LB: 1.0426 | CL0: 4.4 | CL1: 6.6 | HR0: 0.230/SR0: 0.204 | HR1: 0.155/SR1: 0.138 | LR: 1.00e-04
[2026-05-24 13:17:11] Epoch 2 | Step 5160 | Loss: 0.9074 | LM: 0.4003 | LB: 1.0425 | CL0: 4.4 | CL1: 6.6 | HR0: 0.230/SR0: 0.204 | HR1: 0.155/SR1: 0.138 | LR: 1.00e-04
[2026-05-24 13:17:22] Epoch 2 | Step 5170 | Loss: 0.9071 | LM: 0.3993 | LB: 1.0425 | CL0: 4.4 | CL1: 6.6 | HR0: 0.230/SR0: 0.204 | HR1: 0.155/SR1: 0.138 | LR: 1.00e-04
[2026-05-24 13:17:32] Epoch 2 | Step 5180 | Loss: 0.9076 | LM: 0.3994 | LB: 1.0423 | CL0: 4.4 | CL1: 6.6 | HR0: 0.230/SR0: 0.204 | HR1: 0.155/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:17:43] Epoch 2 | Step 5190 | Loss: 0.9077 | LM: 0.3993 | LB: 1.0422 | CL0: 4.4 | CL1: 6.6 | HR0: 0.230/SR0: 0.204 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:17:53] Epoch 2 | Step 5200 | Loss: 0.9084 | LM: 0.4001 | LB: 1.0421 | CL0: 4.4 | CL1: 6.6 | HR0: 0.229/SR0: 0.204 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:18:04] Epoch 2 | Step 5210 | Loss: 0.9087 | LM: 0.3989 | LB: 1.0420 | CL0: 4.4 | CL1: 6.6 | HR0: 0.229/SR0: 0.204 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:18:14] Epoch 2 | Step 5220 | Loss: 0.9093 | LM: 0.3997 | LB: 1.0421 | CL0: 4.4 | CL1: 6.6 | HR0: 0.230/SR0: 0.204 | HR1: 0.155/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:18:25] Epoch 2 | Step 5230 | Loss: 0.9095 | LM: 0.4002 | LB: 1.0421 | CL0: 4.4 | CL1: 6.6 | HR0: 0.230/SR0: 0.204 | HR1: 0.155/SR1: 0.138 | LR: 1.00e-04
[2026-05-24 13:18:36] Epoch 2 | Step 5240 | Loss: 0.9095 | LM: 0.4007 | LB: 1.0420 | CL0: 4.4 | CL1: 6.6 | HR0: 0.229/SR0: 0.204 | HR1: 0.155/SR1: 0.138 | LR: 1.00e-04
[2026-05-24 13:18:46] Epoch 2 | Step 5250 | Loss: 0.9096 | LM: 0.4011 | LB: 1.0419 | CL0: 4.4 | CL1: 6.6 | HR0: 0.229/SR0: 0.204 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:18:57] Epoch 2 | Step 5260 | Loss: 0.9101 | LM: 0.4016 | LB: 1.0419 | CL0: 4.4 | CL1: 6.6 | HR0: 0.229/SR0: 0.204 | HR1: 0.155/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:19:08] Epoch 2 | Step 5270 | Loss: 0.9101 | LM: 0.4016 | LB: 1.0419 | CL0: 4.4 | CL1: 6.6 | HR0: 0.229/SR0: 0.204 | HR1: 0.155/SR1: 0.138 | LR: 1.00e-04
[2026-05-24 13:19:18] Epoch 2 | Step 5280 | Loss: 0.9106 | LM: 0.4028 | LB: 1.0418 | CL0: 4.4 | CL1: 6.6 | HR0: 0.229/SR0: 0.204 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:19:29] Epoch 2 | Step 5290 | Loss: 0.9110 | LM: 0.4021 | LB: 1.0419 | CL0: 4.4 | CL1: 6.6 | HR0: 0.229/SR0: 0.204 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:19:40] Epoch 2 | Step 5300 | Loss: 0.9112 | LM: 0.4024 | LB: 1.0418 | CL0: 4.4 | CL1: 6.6 | HR0: 0.229/SR0: 0.204 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:19:50] Epoch 2 | Step 5310 | Loss: 0.9114 | LM: 0.4028 | LB: 1.0417 | CL0: 4.4 | CL1: 6.6 | HR0: 0.229/SR0: 0.203 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:20:01] Epoch 2 | Step 5320 | Loss: 0.9113 | LM: 0.4022 | LB: 1.0416 | CL0: 4.4 | CL1: 6.6 | HR0: 0.229/SR0: 0.203 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:20:12] Epoch 2 | Step 5330 | Loss: 0.9112 | LM: 0.4022 | LB: 1.0417 | CL0: 4.4 | CL1: 6.6 | HR0: 0.229/SR0: 0.203 | HR1: 0.155/SR1: 0.138 | LR: 1.00e-04
[2026-05-24 13:20:22] Epoch 2 | Step 5340 | Loss: 0.9110 | LM: 0.4024 | LB: 1.0416 | CL0: 4.4 | CL1: 6.6 | HR0: 0.229/SR0: 0.203 | HR1: 0.155/SR1: 0.138 | LR: 1.00e-04
[2026-05-24 13:20:33] Epoch 2 | Step 5350 | Loss: 0.9107 | LM: 0.4016 | LB: 1.0414 | CL0: 4.4 | CL1: 6.6 | HR0: 0.229/SR0: 0.203 | HR1: 0.155/SR1: 0.138 | LR: 1.00e-04
[2026-05-24 13:20:44] Epoch 2 | Step 5360 | Loss: 0.9107 | LM: 0.4005 | LB: 1.0413 | CL0: 4.4 | CL1: 6.6 | HR0: 0.228/SR0: 0.203 | HR1: 0.155/SR1: 0.138 | LR: 1.00e-04
[2026-05-24 13:20:55] Epoch 2 | Step 5370 | Loss: 0.9111 | LM: 0.4004 | LB: 1.0412 | CL0: 4.4 | CL1: 6.6 | HR0: 0.228/SR0: 0.203 | HR1: 0.155/SR1: 0.138 | LR: 1.00e-04
[2026-05-24 13:21:05] Epoch 2 | Step 5380 | Loss: 0.9108 | LM: 0.4004 | LB: 1.0411 | CL0: 4.4 | CL1: 6.6 | HR0: 0.228/SR0: 0.203 | HR1: 0.155/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:21:16] Epoch 2 | Step 5390 | Loss: 0.9106 | LM: 0.4003 | LB: 1.0411 | CL0: 4.4 | CL1: 6.6 | HR0: 0.228/SR0: 0.203 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:21:27] Epoch 2 | Step 5400 | Loss: 0.9105 | LM: 0.3993 | LB: 1.0410 | CL0: 4.4 | CL1: 6.6 | HR0: 0.228/SR0: 0.203 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:21:37] Epoch 2 | Step 5410 | Loss: 0.9107 | LM: 0.3988 | LB: 1.0409 | CL0: 4.4 | CL1: 6.6 | HR0: 0.228/SR0: 0.203 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:21:48] Epoch 2 | Step 5420 | Loss: 0.9106 | LM: 0.3988 | LB: 1.0408 | CL0: 4.4 | CL1: 6.6 | HR0: 0.228/SR0: 0.203 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:21:59] Epoch 2 | Step 5430 | Loss: 0.9109 | LM: 0.3990 | LB: 1.0407 | CL0: 4.4 | CL1: 6.6 | HR0: 0.228/SR0: 0.202 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:22:09] Epoch 2 | Step 5440 | Loss: 0.9107 | LM: 0.3988 | LB: 1.0406 | CL0: 4.4 | CL1: 6.6 | HR0: 0.228/SR0: 0.202 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:22:20] Epoch 2 | Step 5450 | Loss: 0.9106 | LM: 0.3988 | LB: 1.0405 | CL0: 4.4 | CL1: 6.7 | HR0: 0.228/SR0: 0.202 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:22:31] Epoch 2 | Step 5460 | Loss: 0.9110 | LM: 0.3992 | LB: 1.0405 | CL0: 4.4 | CL1: 6.7 | HR0: 0.228/SR0: 0.202 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:22:41] Epoch 2 | Step 5470 | Loss: 0.9109 | LM: 0.3989 | LB: 1.0405 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:22:52] Epoch 2 | Step 5480 | Loss: 0.9109 | LM: 0.3989 | LB: 1.0404 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:23:03] Epoch 2 | Step 5490 | Loss: 0.9106 | LM: 0.3990 | LB: 1.0405 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:23:13] Epoch 2 | Step 5500 | Loss: 0.9107 | LM: 0.3992 | LB: 1.0405 | CL0: 4.4 | CL1: 6.7 | HR0: 0.228/SR0: 0.202 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:23:24] Epoch 2 | Step 5510 | Loss: 0.9106 | LM: 0.3990 | LB: 1.0405 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:23:35] Epoch 2 | Step 5520 | Loss: 0.9110 | LM: 0.3985 | LB: 1.0404 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:23:46] Epoch 2 | Step 5530 | Loss: 0.9108 | LM: 0.3984 | LB: 1.0405 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:23:57] Epoch 2 | Step 5540 | Loss: 0.9106 | LM: 0.3983 | LB: 1.0406 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:24:08] Epoch 2 | Step 5550 | Loss: 0.9107 | LM: 0.3992 | LB: 1.0406 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:24:18] Epoch 2 | Step 5560 | Loss: 0.9107 | LM: 0.3984 | LB: 1.0405 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:24:30] Epoch 2 | Step 5570 | Loss: 0.9105 | LM: 0.3977 | LB: 1.0404 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:24:41] Epoch 2 | Step 5580 | Loss: 0.9104 | LM: 0.3975 | LB: 1.0403 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:24:53] Epoch 2 | Step 5590 | Loss: 0.9104 | LM: 0.3977 | LB: 1.0402 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:25:05] Epoch 2 | Step 5600 | Loss: 0.9105 | LM: 0.3980 | LB: 1.0402 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:25:16] Epoch 2 | Step 5610 | Loss: 0.9108 | LM: 0.3983 | LB: 1.0403 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:25:27] Epoch 2 | Step 5620 | Loss: 0.9108 | LM: 0.3984 | LB: 1.0402 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:25:38] Epoch 2 | Step 5630 | Loss: 0.9107 | LM: 0.3983 | LB: 1.0401 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:25:49] Epoch 2 | Step 5640 | Loss: 0.9108 | LM: 0.3981 | LB: 1.0402 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:25:59] Epoch 2 | Step 5650 | Loss: 0.9108 | LM: 0.3981 | LB: 1.0401 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:26:10] Epoch 2 | Step 5660 | Loss: 0.9109 | LM: 0.3974 | LB: 1.0401 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:26:20] Epoch 2 | Step 5670 | Loss: 0.9108 | LM: 0.3974 | LB: 1.0399 | CL0: 4.4 | CL1: 6.7 | HR0: 0.227/SR0: 0.202 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:26:31] Epoch 2 | Step 5680 | Loss: 0.9112 | LM: 0.3976 | LB: 1.0399 | CL0: 4.4 | CL1: 6.7 | HR0: 0.226/SR0: 0.202 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:26:41] Epoch 2 | Step 5690 | Loss: 0.9112 | LM: 0.3971 | LB: 1.0398 | CL0: 4.4 | CL1: 6.7 | HR0: 0.226/SR0: 0.202 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:26:52] Epoch 2 | Step 5700 | Loss: 0.9110 | LM: 0.3974 | LB: 1.0398 | CL0: 4.4 | CL1: 6.7 | HR0: 0.226/SR0: 0.202 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:27:03] Epoch 2 | Step 5710 | Loss: 0.9113 | LM: 0.3975 | LB: 1.0398 | CL0: 4.4 | CL1: 6.7 | HR0: 0.226/SR0: 0.202 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:27:13] Epoch 2 | Step 5720 | Loss: 0.9117 | LM: 0.3982 | LB: 1.0398 | CL0: 4.4 | CL1: 6.7 | HR0: 0.226/SR0: 0.202 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:27:24] Epoch 2 | Step 5730 | Loss: 0.9120 | LM: 0.3983 | LB: 1.0397 | CL0: 4.4 | CL1: 6.7 | HR0: 0.226/SR0: 0.202 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:27:35] Epoch 2 | Step 5740 | Loss: 0.9122 | LM: 0.3981 | LB: 1.0396 | CL0: 4.5 | CL1: 6.7 | HR0: 0.226/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:27:45] Epoch 2 | Step 5750 | Loss: 0.9124 | LM: 0.3979 | LB: 1.0396 | CL0: 4.5 | CL1: 6.7 | HR0: 0.226/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:27:55] Epoch 2 | Step 5760 | Loss: 0.9127 | LM: 0.3982 | LB: 1.0396 | CL0: 4.5 | CL1: 6.7 | HR0: 0.226/SR0: 0.201 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:28:06] Epoch 2 | Step 5770 | Loss: 0.9126 | LM: 0.3980 | LB: 1.0395 | CL0: 4.5 | CL1: 6.7 | HR0: 0.226/SR0: 0.201 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:28:17] Epoch 2 | Step 5780 | Loss: 0.9128 | LM: 0.3981 | LB: 1.0396 | CL0: 4.5 | CL1: 6.7 | HR0: 0.226/SR0: 0.201 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:28:28] Epoch 2 | Step 5790 | Loss: 0.9132 | LM: 0.3983 | LB: 1.0396 | CL0: 4.5 | CL1: 6.6 | HR0: 0.226/SR0: 0.201 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:28:38] Epoch 2 | Step 5800 | Loss: 0.9134 | LM: 0.3985 | LB: 1.0395 | CL0: 4.5 | CL1: 6.7 | HR0: 0.226/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:28:48] Epoch 2 | Step 5810 | Loss: 0.9135 | LM: 0.3986 | LB: 1.0394 | CL0: 4.5 | CL1: 6.7 | HR0: 0.226/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:28:59] Epoch 2 | Step 5820 | Loss: 0.9139 | LM: 0.3985 | LB: 1.0394 | CL0: 4.5 | CL1: 6.7 | HR0: 0.226/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:29:10] Epoch 2 | Step 5830 | Loss: 0.9140 | LM: 0.3979 | LB: 1.0394 | CL0: 4.5 | CL1: 6.7 | HR0: 0.226/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:29:20] Epoch 2 | Step 5840 | Loss: 0.9143 | LM: 0.3980 | LB: 1.0394 | CL0: 4.5 | CL1: 6.7 | HR0: 0.226/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:29:31] Epoch 2 | Step 5850 | Loss: 0.9144 | LM: 0.3976 | LB: 1.0393 | CL0: 4.5 | CL1: 6.7 | HR0: 0.226/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:29:41] Epoch 2 | Step 5860 | Loss: 0.9143 | LM: 0.3973 | LB: 1.0393 | CL0: 4.5 | CL1: 6.7 | HR0: 0.226/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:29:52] Epoch 2 | Step 5870 | Loss: 0.9142 | LM: 0.3972 | LB: 1.0393 | CL0: 4.5 | CL1: 6.7 | HR0: 0.226/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:30:02] Epoch 2 | Step 5880 | Loss: 0.9141 | LM: 0.3969 | LB: 1.0392 | CL0: 4.5 | CL1: 6.7 | HR0: 0.226/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:30:13] Epoch 2 | Step 5890 | Loss: 0.9143 | LM: 0.3966 | LB: 1.0392 | CL0: 4.5 | CL1: 6.7 | HR0: 0.225/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:30:23] Epoch 2 | Step 5900 | Loss: 0.9144 | LM: 0.3969 | LB: 1.0392 | CL0: 4.5 | CL1: 6.7 | HR0: 0.225/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:30:34] Epoch 2 | Step 5910 | Loss: 0.9143 | LM: 0.3966 | LB: 1.0391 | CL0: 4.5 | CL1: 6.7 | HR0: 0.225/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:30:44] Epoch 2 | Step 5920 | Loss: 0.9143 | LM: 0.3966 | LB: 1.0391 | CL0: 4.5 | CL1: 6.7 | HR0: 0.225/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:30:55] Epoch 2 | Step 5930 | Loss: 0.9145 | LM: 0.3972 | LB: 1.0391 | CL0: 4.5 | CL1: 6.7 | HR0: 0.225/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:31:06] Epoch 2 | Step 5940 | Loss: 0.9147 | LM: 0.3971 | LB: 1.0391 | CL0: 4.5 | CL1: 6.7 | HR0: 0.225/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:31:16] Epoch 2 | Step 5950 | Loss: 0.9147 | LM: 0.3970 | LB: 1.0390 | CL0: 4.5 | CL1: 6.7 | HR0: 0.225/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:31:27] Epoch 2 | Step 5960 | Loss: 0.9144 | LM: 0.3974 | LB: 1.0389 | CL0: 4.5 | CL1: 6.7 | HR0: 0.225/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:31:38] Epoch 2 | Step 5970 | Loss: 0.9142 | LM: 0.3969 | LB: 1.0389 | CL0: 4.5 | CL1: 6.7 | HR0: 0.225/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:31:48] Epoch 2 | Step 5980 | Loss: 0.9143 | LM: 0.3971 | LB: 1.0388 | CL0: 4.5 | CL1: 6.7 | HR0: 0.225/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:31:58] Epoch 2 | Step 5990 | Loss: 0.9143 | LM: 0.3970 | LB: 1.0388 | CL0: 4.5 | CL1: 6.7 | HR0: 0.225/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:32:09] Epoch 2 | Step 6000 | Loss: 0.9142 | LM: 0.3971 | LB: 1.0388 | CL0: 4.5 | CL1: 6.7 | HR0: 0.225/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:32:14] Checkpoint saved: outputs/2026-05-24/N_8.0/checkpoints/checkpoint_step_6000.pt
[2026-05-24 13:32:19] Validation | Batch 10/1463 | Loss: 0.8917 | LM_LOSS: 0.3777 | LB_LOSS: 1.0280
[2026-05-24 13:32:20] Validation | Batch 20/1463 | Loss: 0.9109 | LM_LOSS: 0.3949 | LB_LOSS: 1.0318
[2026-05-24 13:32:22] Validation | Batch 30/1463 | Loss: 0.9177 | LM_LOSS: 0.4012 | LB_LOSS: 1.0330
[2026-05-24 13:32:24] Validation | Batch 40/1463 | Loss: 0.9276 | LM_LOSS: 0.4104 | LB_LOSS: 1.0344
[2026-05-24 13:32:25] Validation | Batch 50/1463 | Loss: 0.9350 | LM_LOSS: 0.4182 | LB_LOSS: 1.0336
[2026-05-24 13:32:27] Validation | Batch 60/1463 | Loss: 0.9366 | LM_LOSS: 0.4197 | LB_LOSS: 1.0337
[2026-05-24 13:32:29] Validation | Batch 70/1463 | Loss: 0.9342 | LM_LOSS: 0.4173 | LB_LOSS: 1.0338
[2026-05-24 13:32:31] Validation | Batch 80/1463 | Loss: 0.9355 | LM_LOSS: 0.4185 | LB_LOSS: 1.0340
[2026-05-24 13:32:33] Validation | Batch 90/1463 | Loss: 0.9342 | LM_LOSS: 0.4172 | LB_LOSS: 1.0340
[2026-05-24 13:32:34] Validation | Batch 100/1463 | Loss: 0.9352 | LM_LOSS: 0.4182 | LB_LOSS: 1.0341
[2026-05-24 13:32:36] Validation | Batch 110/1463 | Loss: 0.9336 | LM_LOSS: 0.4164 | LB_LOSS: 1.0344
[2026-05-24 13:32:37] Validation | Batch 120/1463 | Loss: 0.9354 | LM_LOSS: 0.4182 | LB_LOSS: 1.0344
[2026-05-24 13:32:39] Validation | Batch 130/1463 | Loss: 0.9389 | LM_LOSS: 0.4217 | LB_LOSS: 1.0344
[2026-05-24 13:32:41] Validation | Batch 140/1463 | Loss: 0.9401 | LM_LOSS: 0.4229 | LB_LOSS: 1.0344
[2026-05-24 13:32:43] Validation | Batch 150/1463 | Loss: 0.9384 | LM_LOSS: 0.4211 | LB_LOSS: 1.0346
[2026-05-24 13:32:44] Validation | Batch 160/1463 | Loss: 0.9399 | LM_LOSS: 0.4227 | LB_LOSS: 1.0344
[2026-05-24 13:32:46] Validation | Batch 170/1463 | Loss: 0.9396 | LM_LOSS: 0.4224 | LB_LOSS: 1.0345
[2026-05-24 13:32:48] Validation | Batch 180/1463 | Loss: 0.9410 | LM_LOSS: 0.4237 | LB_LOSS: 1.0346
[2026-05-24 13:32:49] Validation | Batch 190/1463 | Loss: 0.9414 | LM_LOSS: 0.4241 | LB_LOSS: 1.0346
[2026-05-24 13:32:51] Validation | Batch 200/1463 | Loss: 0.9408 | LM_LOSS: 0.4235 | LB_LOSS: 1.0347
[2026-05-24 13:32:53] Validation | Batch 210/1463 | Loss: 0.9414 | LM_LOSS: 0.4241 | LB_LOSS: 1.0347
[2026-05-24 13:32:54] Validation | Batch 220/1463 | Loss: 0.9405 | LM_LOSS: 0.4231 | LB_LOSS: 1.0348
[2026-05-24 13:32:56] Validation | Batch 230/1463 | Loss: 0.9426 | LM_LOSS: 0.4252 | LB_LOSS: 1.0346
[2026-05-24 13:32:58] Validation | Batch 240/1463 | Loss: 0.9432 | LM_LOSS: 0.4259 | LB_LOSS: 1.0345
[2026-05-24 13:33:00] Validation | Batch 250/1463 | Loss: 0.9424 | LM_LOSS: 0.4251 | LB_LOSS: 1.0346
[2026-05-24 13:33:01] Validation | Batch 260/1463 | Loss: 0.9444 | LM_LOSS: 0.4270 | LB_LOSS: 1.0348
[2026-05-24 13:33:03] Validation | Batch 270/1463 | Loss: 0.9434 | LM_LOSS: 0.4260 | LB_LOSS: 1.0348
[2026-05-24 13:33:05] Validation | Batch 280/1463 | Loss: 0.9445 | LM_LOSS: 0.4271 | LB_LOSS: 1.0348
[2026-05-24 13:33:06] Validation | Batch 290/1463 | Loss: 0.9435 | LM_LOSS: 0.4261 | LB_LOSS: 1.0348
[2026-05-24 13:33:08] Validation | Batch 300/1463 | Loss: 0.9441 | LM_LOSS: 0.4266 | LB_LOSS: 1.0350
[2026-05-24 13:33:09] Validation | Batch 310/1463 | Loss: 0.9449 | LM_LOSS: 0.4274 | LB_LOSS: 1.0350
[2026-05-24 13:33:11] Validation | Batch 320/1463 | Loss: 0.9432 | LM_LOSS: 0.4258 | LB_LOSS: 1.0347
[2026-05-24 13:33:13] Validation | Batch 330/1463 | Loss: 0.9433 | LM_LOSS: 0.4259 | LB_LOSS: 1.0348
[2026-05-24 13:33:14] Validation | Batch 340/1463 | Loss: 0.9431 | LM_LOSS: 0.4257 | LB_LOSS: 1.0348
[2026-05-24 13:33:16] Validation | Batch 350/1463 | Loss: 0.9436 | LM_LOSS: 0.4262 | LB_LOSS: 1.0348
[2026-05-24 13:33:17] Validation | Batch 360/1463 | Loss: 0.9436 | LM_LOSS: 0.4262 | LB_LOSS: 1.0348
[2026-05-24 13:33:19] Validation | Batch 370/1463 | Loss: 0.9437 | LM_LOSS: 0.4263 | LB_LOSS: 1.0349
[2026-05-24 13:33:20] Validation | Batch 380/1463 | Loss: 0.9437 | LM_LOSS: 0.4263 | LB_LOSS: 1.0348
[2026-05-24 13:33:22] Validation | Batch 390/1463 | Loss: 0.9447 | LM_LOSS: 0.4273 | LB_LOSS: 1.0348
[2026-05-24 13:33:24] Validation | Batch 400/1463 | Loss: 0.9447 | LM_LOSS: 0.4273 | LB_LOSS: 1.0349
[2026-05-24 13:33:25] Validation | Batch 410/1463 | Loss: 0.9448 | LM_LOSS: 0.4273 | LB_LOSS: 1.0350
[2026-05-24 13:33:27] Validation | Batch 420/1463 | Loss: 0.9451 | LM_LOSS: 0.4276 | LB_LOSS: 1.0350
[2026-05-24 13:33:29] Validation | Batch 430/1463 | Loss: 0.9450 | LM_LOSS: 0.4275 | LB_LOSS: 1.0351
[2026-05-24 13:33:30] Validation | Batch 440/1463 | Loss: 0.9452 | LM_LOSS: 0.4276 | LB_LOSS: 1.0352
[2026-05-24 13:33:32] Validation | Batch 450/1463 | Loss: 0.9448 | LM_LOSS: 0.4272 | LB_LOSS: 1.0352
[2026-05-24 13:33:34] Validation | Batch 460/1463 | Loss: 0.9449 | LM_LOSS: 0.4273 | LB_LOSS: 1.0352
[2026-05-24 13:33:35] Validation | Batch 470/1463 | Loss: 0.9455 | LM_LOSS: 0.4279 | LB_LOSS: 1.0351
[2026-05-24 13:33:37] Validation | Batch 480/1463 | Loss: 0.9452 | LM_LOSS: 0.4277 | LB_LOSS: 1.0351
[2026-05-24 13:33:39] Validation | Batch 490/1463 | Loss: 0.9450 | LM_LOSS: 0.4275 | LB_LOSS: 1.0351
[2026-05-24 13:33:41] Validation | Batch 500/1463 | Loss: 0.9448 | LM_LOSS: 0.4272 | LB_LOSS: 1.0351
[2026-05-24 13:33:43] Validation | Batch 510/1463 | Loss: 0.9442 | LM_LOSS: 0.4267 | LB_LOSS: 1.0351
[2026-05-24 13:33:44] Validation | Batch 520/1463 | Loss: 0.9440 | LM_LOSS: 0.4265 | LB_LOSS: 1.0351
[2026-05-24 13:33:45] Validation | Batch 530/1463 | Loss: 0.9443 | LM_LOSS: 0.4268 | LB_LOSS: 1.0351
[2026-05-24 13:33:47] Validation | Batch 540/1463 | Loss: 0.9447 | LM_LOSS: 0.4271 | LB_LOSS: 1.0351
[2026-05-24 13:33:48] Validation | Batch 550/1463 | Loss: 0.9444 | LM_LOSS: 0.4268 | LB_LOSS: 1.0351
[2026-05-24 13:33:50] Validation | Batch 560/1463 | Loss: 0.9449 | LM_LOSS: 0.4273 | LB_LOSS: 1.0352
[2026-05-24 13:33:52] Validation | Batch 570/1463 | Loss: 0.9448 | LM_LOSS: 0.4271 | LB_LOSS: 1.0352
[2026-05-24 13:33:53] Validation | Batch 580/1463 | Loss: 0.9446 | LM_LOSS: 0.4270 | LB_LOSS: 1.0352
[2026-05-24 13:33:55] Validation | Batch 590/1463 | Loss: 0.9445 | LM_LOSS: 0.4269 | LB_LOSS: 1.0353
[2026-05-24 13:33:57] Validation | Batch 600/1463 | Loss: 0.9448 | LM_LOSS: 0.4271 | LB_LOSS: 1.0354
[2026-05-24 13:33:59] Validation | Batch 610/1463 | Loss: 0.9449 | LM_LOSS: 0.4273 | LB_LOSS: 1.0354
[2026-05-24 13:34:01] Validation | Batch 620/1463 | Loss: 0.9442 | LM_LOSS: 0.4265 | LB_LOSS: 1.0354
[2026-05-24 13:34:02] Validation | Batch 630/1463 | Loss: 0.9440 | LM_LOSS: 0.4263 | LB_LOSS: 1.0354
[2026-05-24 13:34:04] Validation | Batch 640/1463 | Loss: 0.9438 | LM_LOSS: 0.4260 | LB_LOSS: 1.0354
[2026-05-24 13:34:05] Validation | Batch 650/1463 | Loss: 0.9432 | LM_LOSS: 0.4255 | LB_LOSS: 1.0355
[2026-05-24 13:34:07] Validation | Batch 660/1463 | Loss: 0.9426 | LM_LOSS: 0.4249 | LB_LOSS: 1.0354
[2026-05-24 13:34:08] Validation | Batch 670/1463 | Loss: 0.9422 | LM_LOSS: 0.4245 | LB_LOSS: 1.0354
[2026-05-24 13:34:10] Validation | Batch 680/1463 | Loss: 0.9422 | LM_LOSS: 0.4245 | LB_LOSS: 1.0353
[2026-05-24 13:34:12] Validation | Batch 690/1463 | Loss: 0.9425 | LM_LOSS: 0.4248 | LB_LOSS: 1.0354
[2026-05-24 13:34:13] Validation | Batch 700/1463 | Loss: 0.9425 | LM_LOSS: 0.4248 | LB_LOSS: 1.0353
[2026-05-24 13:34:15] Validation | Batch 710/1463 | Loss: 0.9429 | LM_LOSS: 0.4252 | LB_LOSS: 1.0354
[2026-05-24 13:34:16] Validation | Batch 720/1463 | Loss: 0.9437 | LM_LOSS: 0.4260 | LB_LOSS: 1.0355
[2026-05-24 13:34:18] Validation | Batch 730/1463 | Loss: 0.9436 | LM_LOSS: 0.4258 | LB_LOSS: 1.0355
[2026-05-24 13:34:19] Validation | Batch 740/1463 | Loss: 0.9433 | LM_LOSS: 0.4256 | LB_LOSS: 1.0354
[2026-05-24 13:34:21] Validation | Batch 750/1463 | Loss: 0.9431 | LM_LOSS: 0.4254 | LB_LOSS: 1.0354
[2026-05-24 13:34:22] Validation | Batch 760/1463 | Loss: 0.9427 | LM_LOSS: 0.4250 | LB_LOSS: 1.0354
[2026-05-24 13:34:24] Validation | Batch 770/1463 | Loss: 0.9425 | LM_LOSS: 0.4247 | LB_LOSS: 1.0355
[2026-05-24 13:34:25] Validation | Batch 780/1463 | Loss: 0.9424 | LM_LOSS: 0.4247 | LB_LOSS: 1.0354
[2026-05-24 13:34:26] Validation | Batch 790/1463 | Loss: 0.9427 | LM_LOSS: 0.4250 | LB_LOSS: 1.0353
[2026-05-24 13:34:28] Validation | Batch 800/1463 | Loss: 0.9425 | LM_LOSS: 0.4248 | LB_LOSS: 1.0353
[2026-05-24 13:34:29] Validation | Batch 810/1463 | Loss: 0.9420 | LM_LOSS: 0.4244 | LB_LOSS: 1.0353
[2026-05-24 13:34:31] Validation | Batch 820/1463 | Loss: 0.9422 | LM_LOSS: 0.4245 | LB_LOSS: 1.0353
[2026-05-24 13:34:33] Validation | Batch 830/1463 | Loss: 0.9422 | LM_LOSS: 0.4246 | LB_LOSS: 1.0353
[2026-05-24 13:34:35] Validation | Batch 840/1463 | Loss: 0.9422 | LM_LOSS: 0.4245 | LB_LOSS: 1.0354
[2026-05-24 13:34:36] Validation | Batch 850/1463 | Loss: 0.9424 | LM_LOSS: 0.4247 | LB_LOSS: 1.0354
[2026-05-24 13:34:38] Validation | Batch 860/1463 | Loss: 0.9425 | LM_LOSS: 0.4248 | LB_LOSS: 1.0354
[2026-05-24 13:34:40] Validation | Batch 870/1463 | Loss: 0.9426 | LM_LOSS: 0.4249 | LB_LOSS: 1.0354
[2026-05-24 13:34:41] Validation | Batch 880/1463 | Loss: 0.9420 | LM_LOSS: 0.4242 | LB_LOSS: 1.0354
[2026-05-24 13:34:43] Validation | Batch 890/1463 | Loss: 0.9420 | LM_LOSS: 0.4243 | LB_LOSS: 1.0354
[2026-05-24 13:34:44] Validation | Batch 900/1463 | Loss: 0.9417 | LM_LOSS: 0.4240 | LB_LOSS: 1.0353
[2026-05-24 13:34:46] Validation | Batch 910/1463 | Loss: 0.9418 | LM_LOSS: 0.4241 | LB_LOSS: 1.0354
[2026-05-24 13:34:48] Validation | Batch 920/1463 | Loss: 0.9420 | LM_LOSS: 0.4243 | LB_LOSS: 1.0354
[2026-05-24 13:34:49] Validation | Batch 930/1463 | Loss: 0.9416 | LM_LOSS: 0.4239 | LB_LOSS: 1.0354
[2026-05-24 13:34:51] Validation | Batch 940/1463 | Loss: 0.9412 | LM_LOSS: 0.4235 | LB_LOSS: 1.0353
[2026-05-24 13:34:53] Validation | Batch 950/1463 | Loss: 0.9416 | LM_LOSS: 0.4240 | LB_LOSS: 1.0353
[2026-05-24 13:34:54] Validation | Batch 960/1463 | Loss: 0.9417 | LM_LOSS: 0.4240 | LB_LOSS: 1.0353
[2026-05-24 13:34:56] Validation | Batch 970/1463 | Loss: 0.9418 | LM_LOSS: 0.4242 | LB_LOSS: 1.0352
[2026-05-24 13:34:58] Validation | Batch 980/1463 | Loss: 0.9422 | LM_LOSS: 0.4245 | LB_LOSS: 1.0352
[2026-05-24 13:34:59] Validation | Batch 990/1463 | Loss: 0.9423 | LM_LOSS: 0.4247 | LB_LOSS: 1.0352
[2026-05-24 13:35:01] Validation | Batch 1000/1463 | Loss: 0.9429 | LM_LOSS: 0.4253 | LB_LOSS: 1.0352
[2026-05-24 13:35:03] Validation | Batch 1010/1463 | Loss: 0.9429 | LM_LOSS: 0.4253 | LB_LOSS: 1.0353
[2026-05-24 13:35:05] Validation | Batch 1020/1463 | Loss: 0.9433 | LM_LOSS: 0.4256 | LB_LOSS: 1.0353
[2026-05-24 13:35:07] Validation | Batch 1030/1463 | Loss: 0.9438 | LM_LOSS: 0.4261 | LB_LOSS: 1.0354
[2026-05-24 13:35:08] Validation | Batch 1040/1463 | Loss: 0.9433 | LM_LOSS: 0.4256 | LB_LOSS: 1.0353
[2026-05-24 13:35:10] Validation | Batch 1050/1463 | Loss: 0.9432 | LM_LOSS: 0.4255 | LB_LOSS: 1.0353
[2026-05-24 13:35:12] Validation | Batch 1060/1463 | Loss: 0.9430 | LM_LOSS: 0.4254 | LB_LOSS: 1.0353
[2026-05-24 13:35:13] Validation | Batch 1070/1463 | Loss: 0.9432 | LM_LOSS: 0.4255 | LB_LOSS: 1.0353
[2026-05-24 13:35:15] Validation | Batch 1080/1463 | Loss: 0.9428 | LM_LOSS: 0.4252 | LB_LOSS: 1.0353
[2026-05-24 13:35:16] Validation | Batch 1090/1463 | Loss: 0.9428 | LM_LOSS: 0.4252 | LB_LOSS: 1.0353
[2026-05-24 13:35:18] Validation | Batch 1100/1463 | Loss: 0.9427 | LM_LOSS: 0.4251 | LB_LOSS: 1.0352
[2026-05-24 13:35:19] Validation | Batch 1110/1463 | Loss: 0.9428 | LM_LOSS: 0.4251 | LB_LOSS: 1.0352
[2026-05-24 13:35:21] Validation | Batch 1120/1463 | Loss: 0.9426 | LM_LOSS: 0.4250 | LB_LOSS: 1.0353
[2026-05-24 13:35:23] Validation | Batch 1130/1463 | Loss: 0.9423 | LM_LOSS: 0.4247 | LB_LOSS: 1.0352
[2026-05-24 13:35:25] Validation | Batch 1140/1463 | Loss: 0.9425 | LM_LOSS: 0.4249 | LB_LOSS: 1.0353
[2026-05-24 13:35:26] Validation | Batch 1150/1463 | Loss: 0.9425 | LM_LOSS: 0.4249 | LB_LOSS: 1.0352
[2026-05-24 13:35:28] Validation | Batch 1160/1463 | Loss: 0.9425 | LM_LOSS: 0.4249 | LB_LOSS: 1.0352
[2026-05-24 13:35:30] Validation | Batch 1170/1463 | Loss: 0.9425 | LM_LOSS: 0.4249 | LB_LOSS: 1.0352
[2026-05-24 13:35:31] Validation | Batch 1180/1463 | Loss: 0.9425 | LM_LOSS: 0.4248 | LB_LOSS: 1.0352
[2026-05-24 13:35:33] Validation | Batch 1190/1463 | Loss: 0.9426 | LM_LOSS: 0.4250 | LB_LOSS: 1.0352
[2026-05-24 13:35:35] Validation | Batch 1200/1463 | Loss: 0.9427 | LM_LOSS: 0.4251 | LB_LOSS: 1.0352
[2026-05-24 13:35:36] Validation | Batch 1210/1463 | Loss: 0.9430 | LM_LOSS: 0.4254 | LB_LOSS: 1.0353
[2026-05-24 13:35:38] Validation | Batch 1220/1463 | Loss: 0.9434 | LM_LOSS: 0.4257 | LB_LOSS: 1.0353
[2026-05-24 13:35:39] Validation | Batch 1230/1463 | Loss: 0.9432 | LM_LOSS: 0.4256 | LB_LOSS: 1.0353
[2026-05-24 13:35:41] Validation | Batch 1240/1463 | Loss: 0.9436 | LM_LOSS: 0.4260 | LB_LOSS: 1.0353
[2026-05-24 13:35:43] Validation | Batch 1250/1463 | Loss: 0.9438 | LM_LOSS: 0.4262 | LB_LOSS: 1.0353
[2026-05-24 13:35:45] Validation | Batch 1260/1463 | Loss: 0.9438 | LM_LOSS: 0.4261 | LB_LOSS: 1.0353
[2026-05-24 13:35:46] Validation | Batch 1270/1463 | Loss: 0.9436 | LM_LOSS: 0.4259 | LB_LOSS: 1.0353
[2026-05-24 13:35:48] Validation | Batch 1280/1463 | Loss: 0.9433 | LM_LOSS: 0.4257 | LB_LOSS: 1.0353
[2026-05-24 13:35:50] Validation | Batch 1290/1463 | Loss: 0.9434 | LM_LOSS: 0.4258 | LB_LOSS: 1.0353
[2026-05-24 13:35:51] Validation | Batch 1300/1463 | Loss: 0.9431 | LM_LOSS: 0.4255 | LB_LOSS: 1.0353
[2026-05-24 13:35:53] Validation | Batch 1310/1463 | Loss: 0.9431 | LM_LOSS: 0.4254 | LB_LOSS: 1.0353
[2026-05-24 13:35:54] Validation | Batch 1320/1463 | Loss: 0.9431 | LM_LOSS: 0.4255 | LB_LOSS: 1.0353
[2026-05-24 13:35:56] Validation | Batch 1330/1463 | Loss: 0.9431 | LM_LOSS: 0.4255 | LB_LOSS: 1.0352
[2026-05-24 13:35:57] Validation | Batch 1340/1463 | Loss: 0.9433 | LM_LOSS: 0.4256 | LB_LOSS: 1.0353
[2026-05-24 13:35:59] Validation | Batch 1350/1463 | Loss: 0.9433 | LM_LOSS: 0.4256 | LB_LOSS: 1.0352
[2026-05-24 13:36:01] Validation | Batch 1360/1463 | Loss: 0.9435 | LM_LOSS: 0.4259 | LB_LOSS: 1.0352
[2026-05-24 13:36:03] Validation | Batch 1370/1463 | Loss: 0.9439 | LM_LOSS: 0.4262 | LB_LOSS: 1.0353
[2026-05-24 13:36:04] Validation | Batch 1380/1463 | Loss: 0.9437 | LM_LOSS: 0.4261 | LB_LOSS: 1.0352
[2026-05-24 13:36:06] Validation | Batch 1390/1463 | Loss: 0.9435 | LM_LOSS: 0.4259 | LB_LOSS: 1.0353
[2026-05-24 13:36:07] Validation | Batch 1400/1463 | Loss: 0.9438 | LM_LOSS: 0.4262 | LB_LOSS: 1.0352
[2026-05-24 13:36:09] Validation | Batch 1410/1463 | Loss: 0.9440 | LM_LOSS: 0.4264 | LB_LOSS: 1.0352
[2026-05-24 13:36:10] Validation | Batch 1420/1463 | Loss: 0.9441 | LM_LOSS: 0.4264 | LB_LOSS: 1.0352
[2026-05-24 13:36:12] Validation | Batch 1430/1463 | Loss: 0.9442 | LM_LOSS: 0.4265 | LB_LOSS: 1.0352
[2026-05-24 13:36:14] Validation | Batch 1440/1463 | Loss: 0.9446 | LM_LOSS: 0.4269 | LB_LOSS: 1.0352
[2026-05-24 13:36:15] Validation | Batch 1450/1463 | Loss: 0.9442 | LM_LOSS: 0.4266 | LB_LOSS: 1.0352
[2026-05-24 13:36:17] Validation | Batch 1460/1463 | Loss: 0.9445 | LM_LOSS: 0.4269 | LB_LOSS: 1.0352
[2026-05-24 13:36:18] Validation | Batch 1463/1463 | Loss: 0.9443 | LM_LOSS: 0.4268 | LB_LOSS: 1.0352
[2026-05-24 13:36:18] Validation | Loss: 0.9443 | LM_LOSS: 0.4268 | LB_LOSS: 1.0352 | PPL: 1.53 | Time: 240.19s
[2026-05-24 13:36:28] Epoch 2 | Step 6010 | Loss: 0.9143 | LM: 0.3969 | LB: 1.0387 | CL0: 4.5 | CL1: 6.7 | HR0: 0.225/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:36:39] Epoch 2 | Step 6020 | Loss: 0.9141 | LM: 0.3969 | LB: 1.0386 | CL0: 4.5 | CL1: 6.7 | HR0: 0.225/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:36:49] Epoch 2 | Step 6030 | Loss: 0.9142 | LM: 0.3971 | LB: 1.0386 | CL0: 4.5 | CL1: 6.7 | HR0: 0.225/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:37:00] Epoch 2 | Step 6040 | Loss: 0.9143 | LM: 0.3968 | LB: 1.0386 | CL0: 4.5 | CL1: 6.7 | HR0: 0.225/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:37:11] Epoch 2 | Step 6050 | Loss: 0.9145 | LM: 0.3973 | LB: 1.0386 | CL0: 4.5 | CL1: 6.7 | HR0: 0.225/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:37:21] Epoch 2 | Step 6060 | Loss: 0.9144 | LM: 0.3973 | LB: 1.0386 | CL0: 4.5 | CL1: 6.7 | HR0: 0.224/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:37:32] Epoch 2 | Step 6070 | Loss: 0.9144 | LM: 0.3971 | LB: 1.0385 | CL0: 4.5 | CL1: 6.7 | HR0: 0.224/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:37:42] Epoch 2 | Step 6080 | Loss: 0.9146 | LM: 0.3975 | LB: 1.0385 | CL0: 4.5 | CL1: 6.7 | HR0: 0.224/SR0: 0.200 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:37:54] Epoch 2 | Step 6090 | Loss: 0.9145 | LM: 0.3973 | LB: 1.0386 | CL0: 4.5 | CL1: 6.7 | HR0: 0.224/SR0: 0.201 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:38:05] Epoch 2 | Step 6100 | Loss: 0.9147 | LM: 0.3975 | LB: 1.0385 | CL0: 4.5 | CL1: 6.7 | HR0: 0.224/SR0: 0.200 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:38:17] Epoch 2 | Step 6110 | Loss: 0.9147 | LM: 0.3978 | LB: 1.0385 | CL0: 4.5 | CL1: 6.7 | HR0: 0.224/SR0: 0.200 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:38:28] Epoch 2 | Step 6120 | Loss: 0.9146 | LM: 0.3977 | LB: 1.0385 | CL0: 4.5 | CL1: 6.7 | HR0: 0.224/SR0: 0.200 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:38:40] Epoch 2 | Step 6130 | Loss: 0.9144 | LM: 0.3976 | LB: 1.0384 | CL0: 4.5 | CL1: 6.7 | HR0: 0.224/SR0: 0.200 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:38:51] Epoch 2 | Step 6140 | Loss: 0.9142 | LM: 0.3973 | LB: 1.0384 | CL0: 4.5 | CL1: 6.7 | HR0: 0.224/SR0: 0.200 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:39:03] Epoch 2 | Step 6150 | Loss: 0.9144 | LM: 0.3975 | LB: 1.0384 | CL0: 4.5 | CL1: 6.7 | HR0: 0.224/SR0: 0.200 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:39:15] Epoch 2 | Step 6160 | Loss: 0.9143 | LM: 0.3975 | LB: 1.0383 | CL0: 4.5 | CL1: 6.7 | HR0: 0.224/SR0: 0.200 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:39:26] Epoch 2 | Step 6170 | Loss: 0.9143 | LM: 0.3973 | LB: 1.0382 | CL0: 4.5 | CL1: 6.7 | HR0: 0.224/SR0: 0.200 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:39:38] Epoch 2 | Step 6180 | Loss: 0.9145 | LM: 0.3972 | LB: 1.0382 | CL0: 4.5 | CL1: 6.7 | HR0: 0.224/SR0: 0.200 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:39:49] Epoch 2 | Step 6190 | Loss: 0.9144 | LM: 0.3971 | LB: 1.0382 | CL0: 4.5 | CL1: 6.6 | HR0: 0.224/SR0: 0.200 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:40:01] Epoch 2 | Step 6200 | Loss: 0.9144 | LM: 0.3972 | LB: 1.0382 | CL0: 4.5 | CL1: 6.7 | HR0: 0.224/SR0: 0.200 | HR1: 0.153/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:40:12] Epoch 2 | Step 6210 | Loss: 0.9145 | LM: 0.3973 | LB: 1.0382 | CL0: 4.5 | CL1: 6.6 | HR0: 0.224/SR0: 0.200 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:40:24] Epoch 2 | Step 6220 | Loss: 0.9146 | LM: 0.3975 | LB: 1.0381 | CL0: 4.5 | CL1: 6.6 | HR0: 0.224/SR0: 0.200 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:40:35] Epoch 2 | Step 6230 | Loss: 0.9146 | LM: 0.3974 | LB: 1.0381 | CL0: 4.5 | CL1: 6.6 | HR0: 0.224/SR0: 0.200 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:40:47] Epoch 2 | Step 6240 | Loss: 0.9148 | LM: 0.3976 | LB: 1.0381 | CL0: 4.5 | CL1: 6.6 | HR0: 0.224/SR0: 0.200 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:40:58] Epoch 2 | Step 6250 | Loss: 0.9148 | LM: 0.3978 | LB: 1.0381 | CL0: 4.5 | CL1: 6.6 | HR0: 0.224/SR0: 0.200 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:41:10] Epoch 2 | Step 6260 | Loss: 0.9148 | LM: 0.3980 | LB: 1.0380 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.200 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:41:21] Epoch 2 | Step 6270 | Loss: 0.9149 | LM: 0.3980 | LB: 1.0380 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.200 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:41:31] Epoch 2 | Step 6280 | Loss: 0.9147 | LM: 0.3975 | LB: 1.0380 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.200 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:41:42] Epoch 2 | Step 6290 | Loss: 0.9148 | LM: 0.3979 | LB: 1.0379 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.200 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:41:53] Epoch 2 | Step 6300 | Loss: 0.9147 | LM: 0.3977 | LB: 1.0379 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.200 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:42:04] Epoch 2 | Step 6310 | Loss: 0.9147 | LM: 0.3974 | LB: 1.0379 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.200 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:42:15] Epoch 2 | Step 6320 | Loss: 0.9147 | LM: 0.3972 | LB: 1.0378 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.200 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:42:26] Epoch 2 | Step 6330 | Loss: 0.9147 | LM: 0.3969 | LB: 1.0378 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.200 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:42:38] Epoch 2 | Step 6340 | Loss: 0.9148 | LM: 0.3966 | LB: 1.0378 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.200 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:42:49] Epoch 2 | Step 6350 | Loss: 0.9150 | LM: 0.3969 | LB: 1.0377 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.200 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:43:01] Epoch 2 | Step 6360 | Loss: 0.9149 | LM: 0.3968 | LB: 1.0377 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.199 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:43:12] Epoch 2 | Step 6370 | Loss: 0.9149 | LM: 0.3965 | LB: 1.0376 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.199 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:43:24] Epoch 2 | Step 6380 | Loss: 0.9150 | LM: 0.3967 | LB: 1.0376 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.199 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:43:35] Epoch 2 | Step 6390 | Loss: 0.9149 | LM: 0.3968 | LB: 1.0376 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.199 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:43:46] Epoch 2 | Step 6400 | Loss: 0.9152 | LM: 0.3973 | LB: 1.0376 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.199 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:43:57] Epoch 2 | Step 6410 | Loss: 0.9151 | LM: 0.3970 | LB: 1.0375 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.199 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:44:08] Epoch 2 | Step 6420 | Loss: 0.9151 | LM: 0.3972 | LB: 1.0375 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.199 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:44:18] Epoch 2 | Step 6430 | Loss: 0.9150 | LM: 0.3967 | LB: 1.0374 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.199 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:44:29] Epoch 2 | Step 6440 | Loss: 0.9150 | LM: 0.3966 | LB: 1.0374 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.199 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:44:39] Epoch 2 | Step 6450 | Loss: 0.9149 | LM: 0.3962 | LB: 1.0374 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.199 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:44:50] Epoch 2 | Step 6460 | Loss: 0.9150 | LM: 0.3960 | LB: 1.0374 | CL0: 4.5 | CL1: 6.6 | HR0: 0.223/SR0: 0.199 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:45:01] Epoch 2 | Step 6470 | Loss: 0.9151 | LM: 0.3963 | LB: 1.0374 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:45:11] Epoch 2 | Step 6480 | Loss: 0.9152 | LM: 0.3964 | LB: 1.0374 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.137 | LR: 1.00e-04
[2026-05-24 13:45:22] Epoch 2 | Step 6490 | Loss: 0.9151 | LM: 0.3963 | LB: 1.0373 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:45:32] Epoch 2 | Step 6500 | Loss: 0.9152 | LM: 0.3962 | LB: 1.0373 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:45:43] Epoch 2 | Step 6510 | Loss: 0.9152 | LM: 0.3962 | LB: 1.0372 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:45:54] Epoch 2 | Step 6520 | Loss: 0.9151 | LM: 0.3961 | LB: 1.0372 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:46:05] Epoch 2 | Step 6530 | Loss: 0.9152 | LM: 0.3959 | LB: 1.0371 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:46:15] Epoch 2 | Step 6540 | Loss: 0.9151 | LM: 0.3959 | LB: 1.0371 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:46:26] Epoch 2 | Step 6550 | Loss: 0.9151 | LM: 0.3960 | LB: 1.0371 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:46:36] Epoch 2 | Step 6560 | Loss: 0.9151 | LM: 0.3959 | LB: 1.0370 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:46:47] Epoch 2 | Step 6570 | Loss: 0.9149 | LM: 0.3954 | LB: 1.0370 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:46:57] Epoch 2 | Step 6580 | Loss: 0.9149 | LM: 0.3957 | LB: 1.0370 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:47:08] Epoch 2 | Step 6590 | Loss: 0.9149 | LM: 0.3957 | LB: 1.0369 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:47:19] Epoch 2 | Step 6600 | Loss: 0.9149 | LM: 0.3955 | LB: 1.0369 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:47:29] Epoch 2 | Step 6610 | Loss: 0.9151 | LM: 0.3958 | LB: 1.0369 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:47:40] Epoch 2 | Step 6620 | Loss: 0.9151 | LM: 0.3956 | LB: 1.0368 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:47:50] Epoch 2 | Step 6630 | Loss: 0.9150 | LM: 0.3955 | LB: 1.0368 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:48:01] Epoch 2 | Step 6640 | Loss: 0.9151 | LM: 0.3957 | LB: 1.0369 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:48:12] Epoch 2 | Step 6650 | Loss: 0.9151 | LM: 0.3958 | LB: 1.0368 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:48:22] Epoch 2 | Step 6660 | Loss: 0.9151 | LM: 0.3956 | LB: 1.0368 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:48:33] Epoch 2 | Step 6670 | Loss: 0.9151 | LM: 0.3954 | LB: 1.0368 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:48:44] Epoch 2 | Step 6680 | Loss: 0.9153 | LM: 0.3958 | LB: 1.0368 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:48:54] Epoch 2 | Step 6690 | Loss: 0.9153 | LM: 0.3957 | LB: 1.0367 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:49:05] Epoch 2 | Step 6700 | Loss: 0.9155 | LM: 0.3960 | LB: 1.0367 | CL0: 4.5 | CL1: 6.6 | HR0: 0.222/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:49:15] Epoch 2 | Step 6710 | Loss: 0.9154 | LM: 0.3960 | LB: 1.0367 | CL0: 4.5 | CL1: 6.6 | HR0: 0.221/SR0: 0.199 | HR1: 0.154/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:49:26] Epoch 2 | Step 6720 | Loss: 0.9153 | LM: 0.3957 | LB: 1.0367 | CL0: 4.5 | CL1: 6.6 | HR0: 0.221/SR0: 0.199 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:49:37] Epoch 2 | Step 6730 | Loss: 0.9153 | LM: 0.3958 | LB: 1.0366 | CL0: 4.5 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:49:47] Epoch 2 | Step 6740 | Loss: 0.9152 | LM: 0.3959 | LB: 1.0366 | CL0: 4.5 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:49:58] Epoch 2 | Step 6750 | Loss: 0.9153 | LM: 0.3959 | LB: 1.0365 | CL0: 4.5 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:50:09] Epoch 2 | Step 6760 | Loss: 0.9152 | LM: 0.3959 | LB: 1.0365 | CL0: 4.5 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:50:19] Epoch 2 | Step 6770 | Loss: 0.9152 | LM: 0.3959 | LB: 1.0365 | CL0: 4.5 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:50:30] Epoch 2 | Step 6780 | Loss: 0.9150 | LM: 0.3956 | LB: 1.0364 | CL0: 4.6 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:50:40] Epoch 2 | Step 6790 | Loss: 0.9152 | LM: 0.3959 | LB: 1.0364 | CL0: 4.6 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:50:51] Epoch 2 | Step 6800 | Loss: 0.9152 | LM: 0.3962 | LB: 1.0363 | CL0: 4.6 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:51:02] Epoch 2 | Step 6810 | Loss: 0.9152 | LM: 0.3963 | LB: 1.0363 | CL0: 4.6 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:51:12] Epoch 2 | Step 6820 | Loss: 0.9152 | LM: 0.3963 | LB: 1.0363 | CL0: 4.6 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:51:23] Epoch 2 | Step 6830 | Loss: 0.9151 | LM: 0.3960 | LB: 1.0363 | CL0: 4.6 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:51:33] Epoch 2 | Step 6840 | Loss: 0.9150 | LM: 0.3960 | LB: 1.0363 | CL0: 4.6 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:51:44] Epoch 2 | Step 6850 | Loss: 0.9149 | LM: 0.3963 | LB: 1.0363 | CL0: 4.6 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:51:55] Epoch 2 | Step 6860 | Loss: 0.9150 | LM: 0.3963 | LB: 1.0362 | CL0: 4.6 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:52:05] Epoch 2 | Step 6870 | Loss: 0.9151 | LM: 0.3962 | LB: 1.0362 | CL0: 4.6 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:52:16] Epoch 2 | Step 6880 | Loss: 0.9151 | LM: 0.3962 | LB: 1.0362 | CL0: 4.6 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:52:26] Epoch 2 | Step 6890 | Loss: 0.9149 | LM: 0.3962 | LB: 1.0362 | CL0: 4.6 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:52:37] Epoch 2 | Step 6900 | Loss: 0.9149 | LM: 0.3961 | LB: 1.0362 | CL0: 4.6 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:52:48] Epoch 2 | Step 6910 | Loss: 0.9148 | LM: 0.3961 | LB: 1.0361 | CL0: 4.6 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:52:58] Epoch 2 | Step 6920 | Loss: 0.9149 | LM: 0.3963 | LB: 1.0361 | CL0: 4.6 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:53:09] Epoch 2 | Step 6930 | Loss: 0.9150 | LM: 0.3963 | LB: 1.0361 | CL0: 4.6 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:53:19] Epoch 2 | Step 6940 | Loss: 0.9151 | LM: 0.3964 | LB: 1.0360 | CL0: 4.6 | CL1: 6.7 | HR0: 0.221/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:53:30] Epoch 2 | Step 6950 | Loss: 0.9151 | LM: 0.3965 | LB: 1.0360 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:53:41] Epoch 2 | Step 6960 | Loss: 0.9152 | LM: 0.3967 | LB: 1.0359 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:53:51] Epoch 2 | Step 6970 | Loss: 0.9152 | LM: 0.3968 | LB: 1.0359 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:54:02] Epoch 2 | Step 6980 | Loss: 0.9153 | LM: 0.3969 | LB: 1.0359 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:54:12] Epoch 2 | Step 6990 | Loss: 0.9152 | LM: 0.3967 | LB: 1.0359 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:54:23] Epoch 2 | Step 7000 | Loss: 0.9151 | LM: 0.3967 | LB: 1.0359 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:54:24] Validation | Batch 10/1463 | Loss: 0.8947 | LM_LOSS: 0.3823 | LB_LOSS: 1.0248
[2026-05-24 13:54:26] Validation | Batch 20/1463 | Loss: 0.9129 | LM_LOSS: 0.3985 | LB_LOSS: 1.0287
[2026-05-24 13:54:28] Validation | Batch 30/1463 | Loss: 0.9184 | LM_LOSS: 0.4035 | LB_LOSS: 1.0298
[2026-05-24 13:54:29] Validation | Batch 40/1463 | Loss: 0.9275 | LM_LOSS: 0.4119 | LB_LOSS: 1.0311
[2026-05-24 13:54:31] Validation | Batch 50/1463 | Loss: 0.9332 | LM_LOSS: 0.4181 | LB_LOSS: 1.0303
[2026-05-24 13:54:33] Validation | Batch 60/1463 | Loss: 0.9344 | LM_LOSS: 0.4191 | LB_LOSS: 1.0305
[2026-05-24 13:54:35] Validation | Batch 70/1463 | Loss: 0.9330 | LM_LOSS: 0.4178 | LB_LOSS: 1.0305
[2026-05-24 13:54:37] Validation | Batch 80/1463 | Loss: 0.9338 | LM_LOSS: 0.4185 | LB_LOSS: 1.0307
[2026-05-24 13:54:38] Validation | Batch 90/1463 | Loss: 0.9326 | LM_LOSS: 0.4173 | LB_LOSS: 1.0307
[2026-05-24 13:54:40] Validation | Batch 100/1463 | Loss: 0.9336 | LM_LOSS: 0.4182 | LB_LOSS: 1.0308
[2026-05-24 13:54:41] Validation | Batch 110/1463 | Loss: 0.9323 | LM_LOSS: 0.4168 | LB_LOSS: 1.0311
[2026-05-24 13:54:43] Validation | Batch 120/1463 | Loss: 0.9340 | LM_LOSS: 0.4185 | LB_LOSS: 1.0310
[2026-05-24 13:54:44] Validation | Batch 130/1463 | Loss: 0.9373 | LM_LOSS: 0.4218 | LB_LOSS: 1.0310
[2026-05-24 13:54:46] Validation | Batch 140/1463 | Loss: 0.9382 | LM_LOSS: 0.4227 | LB_LOSS: 1.0311
[2026-05-24 13:54:48] Validation | Batch 150/1463 | Loss: 0.9365 | LM_LOSS: 0.4209 | LB_LOSS: 1.0312
[2026-05-24 13:54:49] Validation | Batch 160/1463 | Loss: 0.9380 | LM_LOSS: 0.4225 | LB_LOSS: 1.0310
[2026-05-24 13:54:51] Validation | Batch 170/1463 | Loss: 0.9377 | LM_LOSS: 0.4222 | LB_LOSS: 1.0311
[2026-05-24 13:54:53] Validation | Batch 180/1463 | Loss: 0.9390 | LM_LOSS: 0.4234 | LB_LOSS: 1.0312
[2026-05-24 13:54:55] Validation | Batch 190/1463 | Loss: 0.9394 | LM_LOSS: 0.4238 | LB_LOSS: 1.0313
[2026-05-24 13:54:56] Validation | Batch 200/1463 | Loss: 0.9387 | LM_LOSS: 0.4230 | LB_LOSS: 1.0314
[2026-05-24 13:54:58] Validation | Batch 210/1463 | Loss: 0.9393 | LM_LOSS: 0.4236 | LB_LOSS: 1.0314
[2026-05-24 13:55:00] Validation | Batch 220/1463 | Loss: 0.9383 | LM_LOSS: 0.4225 | LB_LOSS: 1.0315
[2026-05-24 13:55:01] Validation | Batch 230/1463 | Loss: 0.9404 | LM_LOSS: 0.4247 | LB_LOSS: 1.0313
[2026-05-24 13:55:03] Validation | Batch 240/1463 | Loss: 0.9410 | LM_LOSS: 0.4254 | LB_LOSS: 1.0313
[2026-05-24 13:55:05] Validation | Batch 250/1463 | Loss: 0.9400 | LM_LOSS: 0.4243 | LB_LOSS: 1.0313
[2026-05-24 13:55:06] Validation | Batch 260/1463 | Loss: 0.9418 | LM_LOSS: 0.4260 | LB_LOSS: 1.0315
[2026-05-24 13:55:08] Validation | Batch 270/1463 | Loss: 0.9406 | LM_LOSS: 0.4249 | LB_LOSS: 1.0315
[2026-05-24 13:55:10] Validation | Batch 280/1463 | Loss: 0.9417 | LM_LOSS: 0.4259 | LB_LOSS: 1.0315
[2026-05-24 13:55:11] Validation | Batch 290/1463 | Loss: 0.9406 | LM_LOSS: 0.4249 | LB_LOSS: 1.0315
[2026-05-24 13:55:13] Validation | Batch 300/1463 | Loss: 0.9412 | LM_LOSS: 0.4253 | LB_LOSS: 1.0317
[2026-05-24 13:55:15] Validation | Batch 310/1463 | Loss: 0.9421 | LM_LOSS: 0.4263 | LB_LOSS: 1.0317
[2026-05-24 13:55:16] Validation | Batch 320/1463 | Loss: 0.9404 | LM_LOSS: 0.4247 | LB_LOSS: 1.0314
[2026-05-24 13:55:18] Validation | Batch 330/1463 | Loss: 0.9404 | LM_LOSS: 0.4246 | LB_LOSS: 1.0315
[2026-05-24 13:55:19] Validation | Batch 340/1463 | Loss: 0.9401 | LM_LOSS: 0.4244 | LB_LOSS: 1.0315
[2026-05-24 13:55:21] Validation | Batch 350/1463 | Loss: 0.9407 | LM_LOSS: 0.4249 | LB_LOSS: 1.0315
[2026-05-24 13:55:22] Validation | Batch 360/1463 | Loss: 0.9407 | LM_LOSS: 0.4249 | LB_LOSS: 1.0315
[2026-05-24 13:55:24] Validation | Batch 370/1463 | Loss: 0.9407 | LM_LOSS: 0.4248 | LB_LOSS: 1.0316
[2026-05-24 13:55:25] Validation | Batch 380/1463 | Loss: 0.9407 | LM_LOSS: 0.4249 | LB_LOSS: 1.0315
[2026-05-24 13:55:27] Validation | Batch 390/1463 | Loss: 0.9417 | LM_LOSS: 0.4259 | LB_LOSS: 1.0316
[2026-05-24 13:55:29] Validation | Batch 400/1463 | Loss: 0.9417 | LM_LOSS: 0.4259 | LB_LOSS: 1.0316
[2026-05-24 13:55:30] Validation | Batch 410/1463 | Loss: 0.9416 | LM_LOSS: 0.4258 | LB_LOSS: 1.0317
[2026-05-24 13:55:32] Validation | Batch 420/1463 | Loss: 0.9418 | LM_LOSS: 0.4260 | LB_LOSS: 1.0317
[2026-05-24 13:55:34] Validation | Batch 430/1463 | Loss: 0.9417 | LM_LOSS: 0.4258 | LB_LOSS: 1.0318
[2026-05-24 13:55:35] Validation | Batch 440/1463 | Loss: 0.9420 | LM_LOSS: 0.4260 | LB_LOSS: 1.0319
[2026-05-24 13:55:37] Validation | Batch 450/1463 | Loss: 0.9416 | LM_LOSS: 0.4256 | LB_LOSS: 1.0319
[2026-05-24 13:55:38] Validation | Batch 460/1463 | Loss: 0.9414 | LM_LOSS: 0.4255 | LB_LOSS: 1.0319
[2026-05-24 13:55:40] Validation | Batch 470/1463 | Loss: 0.9421 | LM_LOSS: 0.4262 | LB_LOSS: 1.0318
[2026-05-24 13:55:42] Validation | Batch 480/1463 | Loss: 0.9418 | LM_LOSS: 0.4260 | LB_LOSS: 1.0318
[2026-05-24 13:55:44] Validation | Batch 490/1463 | Loss: 0.9417 | LM_LOSS: 0.4258 | LB_LOSS: 1.0318
[2026-05-24 13:55:46] Validation | Batch 500/1463 | Loss: 0.9414 | LM_LOSS: 0.4255 | LB_LOSS: 1.0318
[2026-05-24 13:55:47] Validation | Batch 510/1463 | Loss: 0.9409 | LM_LOSS: 0.4250 | LB_LOSS: 1.0318
[2026-05-24 13:55:49] Validation | Batch 520/1463 | Loss: 0.9406 | LM_LOSS: 0.4247 | LB_LOSS: 1.0318
[2026-05-24 13:55:50] Validation | Batch 530/1463 | Loss: 0.9409 | LM_LOSS: 0.4250 | LB_LOSS: 1.0318
[2026-05-24 13:55:52] Validation | Batch 540/1463 | Loss: 0.9413 | LM_LOSS: 0.4253 | LB_LOSS: 1.0318
[2026-05-24 13:55:53] Validation | Batch 550/1463 | Loss: 0.9410 | LM_LOSS: 0.4251 | LB_LOSS: 1.0319
[2026-05-24 13:55:55] Validation | Batch 560/1463 | Loss: 0.9415 | LM_LOSS: 0.4256 | LB_LOSS: 1.0320
[2026-05-24 13:55:56] Validation | Batch 570/1463 | Loss: 0.9415 | LM_LOSS: 0.4255 | LB_LOSS: 1.0320
[2026-05-24 13:55:58] Validation | Batch 580/1463 | Loss: 0.9413 | LM_LOSS: 0.4253 | LB_LOSS: 1.0319
[2026-05-24 13:56:00] Validation | Batch 590/1463 | Loss: 0.9412 | LM_LOSS: 0.4252 | LB_LOSS: 1.0320
[2026-05-24 13:56:02] Validation | Batch 600/1463 | Loss: 0.9415 | LM_LOSS: 0.4255 | LB_LOSS: 1.0321
[2026-05-24 13:56:04] Validation | Batch 610/1463 | Loss: 0.9416 | LM_LOSS: 0.4256 | LB_LOSS: 1.0321
[2026-05-24 13:56:05] Validation | Batch 620/1463 | Loss: 0.9410 | LM_LOSS: 0.4249 | LB_LOSS: 1.0321
[2026-05-24 13:56:07] Validation | Batch 630/1463 | Loss: 0.9407 | LM_LOSS: 0.4246 | LB_LOSS: 1.0321
[2026-05-24 13:56:08] Validation | Batch 640/1463 | Loss: 0.9405 | LM_LOSS: 0.4244 | LB_LOSS: 1.0321
[2026-05-24 13:56:10] Validation | Batch 650/1463 | Loss: 0.9399 | LM_LOSS: 0.4238 | LB_LOSS: 1.0322
[2026-05-24 13:56:11] Validation | Batch 660/1463 | Loss: 0.9394 | LM_LOSS: 0.4234 | LB_LOSS: 1.0321
[2026-05-24 13:56:13] Validation | Batch 670/1463 | Loss: 0.9390 | LM_LOSS: 0.4229 | LB_LOSS: 1.0321
[2026-05-24 13:56:14] Validation | Batch 680/1463 | Loss: 0.9390 | LM_LOSS: 0.4230 | LB_LOSS: 1.0321
[2026-05-24 13:56:16] Validation | Batch 690/1463 | Loss: 0.9393 | LM_LOSS: 0.4233 | LB_LOSS: 1.0321
[2026-05-24 13:56:18] Validation | Batch 700/1463 | Loss: 0.9394 | LM_LOSS: 0.4234 | LB_LOSS: 1.0321
[2026-05-24 13:56:19] Validation | Batch 710/1463 | Loss: 0.9399 | LM_LOSS: 0.4238 | LB_LOSS: 1.0321
[2026-05-24 13:56:21] Validation | Batch 720/1463 | Loss: 0.9406 | LM_LOSS: 0.4245 | LB_LOSS: 1.0322
[2026-05-24 13:56:22] Validation | Batch 730/1463 | Loss: 0.9403 | LM_LOSS: 0.4242 | LB_LOSS: 1.0322
[2026-05-24 13:56:24] Validation | Batch 740/1463 | Loss: 0.9401 | LM_LOSS: 0.4240 | LB_LOSS: 1.0322
[2026-05-24 13:56:25] Validation | Batch 750/1463 | Loss: 0.9398 | LM_LOSS: 0.4237 | LB_LOSS: 1.0321
[2026-05-24 13:56:27] Validation | Batch 760/1463 | Loss: 0.9394 | LM_LOSS: 0.4233 | LB_LOSS: 1.0321
[2026-05-24 13:56:28] Validation | Batch 770/1463 | Loss: 0.9392 | LM_LOSS: 0.4231 | LB_LOSS: 1.0322
[2026-05-24 13:56:30] Validation | Batch 780/1463 | Loss: 0.9391 | LM_LOSS: 0.4230 | LB_LOSS: 1.0321
[2026-05-24 13:56:31] Validation | Batch 790/1463 | Loss: 0.9394 | LM_LOSS: 0.4234 | LB_LOSS: 1.0321
[2026-05-24 13:56:32] Validation | Batch 800/1463 | Loss: 0.9393 | LM_LOSS: 0.4233 | LB_LOSS: 1.0321
[2026-05-24 13:56:34] Validation | Batch 810/1463 | Loss: 0.9388 | LM_LOSS: 0.4228 | LB_LOSS: 1.0320
[2026-05-24 13:56:35] Validation | Batch 820/1463 | Loss: 0.9390 | LM_LOSS: 0.4230 | LB_LOSS: 1.0320
[2026-05-24 13:56:37] Validation | Batch 830/1463 | Loss: 0.9391 | LM_LOSS: 0.4231 | LB_LOSS: 1.0320
[2026-05-24 13:56:39] Validation | Batch 840/1463 | Loss: 0.9390 | LM_LOSS: 0.4229 | LB_LOSS: 1.0321
[2026-05-24 13:56:41] Validation | Batch 850/1463 | Loss: 0.9392 | LM_LOSS: 0.4231 | LB_LOSS: 1.0321
[2026-05-24 13:56:42] Validation | Batch 860/1463 | Loss: 0.9391 | LM_LOSS: 0.4230 | LB_LOSS: 1.0321
[2026-05-24 13:56:44] Validation | Batch 870/1463 | Loss: 0.9393 | LM_LOSS: 0.4232 | LB_LOSS: 1.0322
[2026-05-24 13:56:45] Validation | Batch 880/1463 | Loss: 0.9386 | LM_LOSS: 0.4225 | LB_LOSS: 1.0321
[2026-05-24 13:56:47] Validation | Batch 890/1463 | Loss: 0.9387 | LM_LOSS: 0.4226 | LB_LOSS: 1.0321
[2026-05-24 13:56:49] Validation | Batch 900/1463 | Loss: 0.9384 | LM_LOSS: 0.4223 | LB_LOSS: 1.0321
[2026-05-24 13:56:50] Validation | Batch 910/1463 | Loss: 0.9384 | LM_LOSS: 0.4223 | LB_LOSS: 1.0321
[2026-05-24 13:56:52] Validation | Batch 920/1463 | Loss: 0.9386 | LM_LOSS: 0.4226 | LB_LOSS: 1.0321
[2026-05-24 13:56:54] Validation | Batch 930/1463 | Loss: 0.9383 | LM_LOSS: 0.4222 | LB_LOSS: 1.0321
[2026-05-24 13:56:55] Validation | Batch 940/1463 | Loss: 0.9379 | LM_LOSS: 0.4218 | LB_LOSS: 1.0320
[2026-05-24 13:56:57] Validation | Batch 950/1463 | Loss: 0.9382 | LM_LOSS: 0.4222 | LB_LOSS: 1.0320
[2026-05-24 13:56:59] Validation | Batch 960/1463 | Loss: 0.9384 | LM_LOSS: 0.4223 | LB_LOSS: 1.0320
[2026-05-24 13:57:01] Validation | Batch 970/1463 | Loss: 0.9385 | LM_LOSS: 0.4225 | LB_LOSS: 1.0320
[2026-05-24 13:57:02] Validation | Batch 980/1463 | Loss: 0.9388 | LM_LOSS: 0.4229 | LB_LOSS: 1.0320
[2026-05-24 13:57:04] Validation | Batch 990/1463 | Loss: 0.9390 | LM_LOSS: 0.4230 | LB_LOSS: 1.0319
[2026-05-24 13:57:05] Validation | Batch 1000/1463 | Loss: 0.9396 | LM_LOSS: 0.4236 | LB_LOSS: 1.0320
[2026-05-24 13:57:07] Validation | Batch 1010/1463 | Loss: 0.9397 | LM_LOSS: 0.4237 | LB_LOSS: 1.0320
[2026-05-24 13:57:09] Validation | Batch 1020/1463 | Loss: 0.9400 | LM_LOSS: 0.4239 | LB_LOSS: 1.0321
[2026-05-24 13:57:11] Validation | Batch 1030/1463 | Loss: 0.9404 | LM_LOSS: 0.4244 | LB_LOSS: 1.0321
[2026-05-24 13:57:12] Validation | Batch 1040/1463 | Loss: 0.9399 | LM_LOSS: 0.4239 | LB_LOSS: 1.0321
[2026-05-24 13:57:14] Validation | Batch 1050/1463 | Loss: 0.9398 | LM_LOSS: 0.4238 | LB_LOSS: 1.0320
[2026-05-24 13:57:16] Validation | Batch 1060/1463 | Loss: 0.9396 | LM_LOSS: 0.4237 | LB_LOSS: 1.0320
[2026-05-24 13:57:17] Validation | Batch 1070/1463 | Loss: 0.9398 | LM_LOSS: 0.4238 | LB_LOSS: 1.0320
[2026-05-24 13:57:19] Validation | Batch 1080/1463 | Loss: 0.9395 | LM_LOSS: 0.4235 | LB_LOSS: 1.0320
[2026-05-24 13:57:20] Validation | Batch 1090/1463 | Loss: 0.9395 | LM_LOSS: 0.4235 | LB_LOSS: 1.0320
[2026-05-24 13:57:22] Validation | Batch 1100/1463 | Loss: 0.9394 | LM_LOSS: 0.4235 | LB_LOSS: 1.0320
[2026-05-24 13:57:23] Validation | Batch 1110/1463 | Loss: 0.9394 | LM_LOSS: 0.4234 | LB_LOSS: 1.0320
[2026-05-24 13:57:25] Validation | Batch 1120/1463 | Loss: 0.9393 | LM_LOSS: 0.4233 | LB_LOSS: 1.0320
[2026-05-24 13:57:27] Validation | Batch 1130/1463 | Loss: 0.9390 | LM_LOSS: 0.4230 | LB_LOSS: 1.0320
[2026-05-24 13:57:28] Validation | Batch 1140/1463 | Loss: 0.9392 | LM_LOSS: 0.4233 | LB_LOSS: 1.0320
[2026-05-24 13:57:30] Validation | Batch 1150/1463 | Loss: 0.9393 | LM_LOSS: 0.4233 | LB_LOSS: 1.0320
[2026-05-24 13:57:32] Validation | Batch 1160/1463 | Loss: 0.9392 | LM_LOSS: 0.4232 | LB_LOSS: 1.0320
[2026-05-24 13:57:34] Validation | Batch 1170/1463 | Loss: 0.9391 | LM_LOSS: 0.4232 | LB_LOSS: 1.0319
[2026-05-24 13:57:35] Validation | Batch 1180/1463 | Loss: 0.9391 | LM_LOSS: 0.4231 | LB_LOSS: 1.0320
[2026-05-24 13:57:37] Validation | Batch 1190/1463 | Loss: 0.9393 | LM_LOSS: 0.4233 | LB_LOSS: 1.0320
[2026-05-24 13:57:39] Validation | Batch 1200/1463 | Loss: 0.9395 | LM_LOSS: 0.4235 | LB_LOSS: 1.0320
[2026-05-24 13:57:40] Validation | Batch 1210/1463 | Loss: 0.9398 | LM_LOSS: 0.4238 | LB_LOSS: 1.0320
[2026-05-24 13:57:42] Validation | Batch 1220/1463 | Loss: 0.9402 | LM_LOSS: 0.4242 | LB_LOSS: 1.0320
[2026-05-24 13:57:43] Validation | Batch 1230/1463 | Loss: 0.9401 | LM_LOSS: 0.4241 | LB_LOSS: 1.0320
[2026-05-24 13:57:45] Validation | Batch 1240/1463 | Loss: 0.9405 | LM_LOSS: 0.4245 | LB_LOSS: 1.0320
[2026-05-24 13:57:47] Validation | Batch 1250/1463 | Loss: 0.9407 | LM_LOSS: 0.4247 | LB_LOSS: 1.0320
[2026-05-24 13:57:48] Validation | Batch 1260/1463 | Loss: 0.9406 | LM_LOSS: 0.4246 | LB_LOSS: 1.0320
[2026-05-24 13:57:50] Validation | Batch 1270/1463 | Loss: 0.9404 | LM_LOSS: 0.4244 | LB_LOSS: 1.0321
[2026-05-24 13:57:52] Validation | Batch 1280/1463 | Loss: 0.9402 | LM_LOSS: 0.4242 | LB_LOSS: 1.0320
[2026-05-24 13:57:53] Validation | Batch 1290/1463 | Loss: 0.9403 | LM_LOSS: 0.4243 | LB_LOSS: 1.0320
[2026-05-24 13:57:55] Validation | Batch 1300/1463 | Loss: 0.9400 | LM_LOSS: 0.4240 | LB_LOSS: 1.0320
[2026-05-24 13:57:57] Validation | Batch 1310/1463 | Loss: 0.9400 | LM_LOSS: 0.4240 | LB_LOSS: 1.0320
[2026-05-24 13:57:58] Validation | Batch 1320/1463 | Loss: 0.9400 | LM_LOSS: 0.4240 | LB_LOSS: 1.0320
[2026-05-24 13:57:59] Validation | Batch 1330/1463 | Loss: 0.9400 | LM_LOSS: 0.4240 | LB_LOSS: 1.0320
[2026-05-24 13:58:01] Validation | Batch 1340/1463 | Loss: 0.9402 | LM_LOSS: 0.4242 | LB_LOSS: 1.0320
[2026-05-24 13:58:03] Validation | Batch 1350/1463 | Loss: 0.9402 | LM_LOSS: 0.4242 | LB_LOSS: 1.0320
[2026-05-24 13:58:05] Validation | Batch 1360/1463 | Loss: 0.9405 | LM_LOSS: 0.4245 | LB_LOSS: 1.0320
[2026-05-24 13:58:06] Validation | Batch 1370/1463 | Loss: 0.9409 | LM_LOSS: 0.4249 | LB_LOSS: 1.0320
[2026-05-24 13:58:08] Validation | Batch 1380/1463 | Loss: 0.9407 | LM_LOSS: 0.4247 | LB_LOSS: 1.0320
[2026-05-24 13:58:09] Validation | Batch 1390/1463 | Loss: 0.9405 | LM_LOSS: 0.4245 | LB_LOSS: 1.0320
[2026-05-24 13:58:11] Validation | Batch 1400/1463 | Loss: 0.9408 | LM_LOSS: 0.4248 | LB_LOSS: 1.0319
[2026-05-24 13:58:12] Validation | Batch 1410/1463 | Loss: 0.9410 | LM_LOSS: 0.4250 | LB_LOSS: 1.0319
[2026-05-24 13:58:14] Validation | Batch 1420/1463 | Loss: 0.9410 | LM_LOSS: 0.4250 | LB_LOSS: 1.0320
[2026-05-24 13:58:16] Validation | Batch 1430/1463 | Loss: 0.9411 | LM_LOSS: 0.4251 | LB_LOSS: 1.0319
[2026-05-24 13:58:17] Validation | Batch 1440/1463 | Loss: 0.9415 | LM_LOSS: 0.4255 | LB_LOSS: 1.0320
[2026-05-24 13:58:19] Validation | Batch 1450/1463 | Loss: 0.9412 | LM_LOSS: 0.4252 | LB_LOSS: 1.0319
[2026-05-24 13:58:21] Validation | Batch 1460/1463 | Loss: 0.9415 | LM_LOSS: 0.4255 | LB_LOSS: 1.0319
[2026-05-24 13:58:21] Validation | Batch 1463/1463 | Loss: 0.9413 | LM_LOSS: 0.4254 | LB_LOSS: 1.0319
[2026-05-24 13:58:21] Validation | Loss: 0.9413 | LM_LOSS: 0.4254 | LB_LOSS: 1.0319 | PPL: 1.53 | Time: 238.15s
[2026-05-24 13:58:32] Epoch 2 | Step 7010 | Loss: 0.9151 | LM: 0.3972 | LB: 1.0359 | CL0: 4.6 | CL1: 6.6 | HR0: 0.220/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:58:43] Epoch 2 | Step 7020 | Loss: 0.9152 | LM: 0.3974 | LB: 1.0358 | CL0: 4.6 | CL1: 6.6 | HR0: 0.220/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:58:53] Epoch 2 | Step 7030 | Loss: 0.9152 | LM: 0.3977 | LB: 1.0358 | CL0: 4.6 | CL1: 6.6 | HR0: 0.220/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:59:04] Epoch 2 | Step 7040 | Loss: 0.9153 | LM: 0.3978 | LB: 1.0358 | CL0: 4.6 | CL1: 6.6 | HR0: 0.220/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:59:15] Epoch 2 | Step 7050 | Loss: 0.9155 | LM: 0.3980 | LB: 1.0358 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:59:25] Epoch 2 | Step 7060 | Loss: 0.9154 | LM: 0.3980 | LB: 1.0357 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:59:36] Epoch 2 | Step 7070 | Loss: 0.9153 | LM: 0.3982 | LB: 1.0357 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.198 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:59:47] Epoch 2 | Step 7080 | Loss: 0.9155 | LM: 0.3982 | LB: 1.0357 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 13:59:57] Epoch 2 | Step 7090 | Loss: 0.9154 | LM: 0.3981 | LB: 1.0357 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:00:08] Epoch 2 | Step 7100 | Loss: 0.9155 | LM: 0.3981 | LB: 1.0356 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:00:18] Epoch 2 | Step 7110 | Loss: 0.9155 | LM: 0.3978 | LB: 1.0356 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:00:29] Epoch 2 | Step 7120 | Loss: 0.9154 | LM: 0.3977 | LB: 1.0355 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:00:39] Epoch 2 | Step 7130 | Loss: 0.9153 | LM: 0.3975 | LB: 1.0355 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:00:50] Epoch 2 | Step 7140 | Loss: 0.9153 | LM: 0.3975 | LB: 1.0355 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:01:01] Epoch 2 | Step 7150 | Loss: 0.9154 | LM: 0.3977 | LB: 1.0355 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:01:11] Epoch 2 | Step 7160 | Loss: 0.9155 | LM: 0.3976 | LB: 1.0355 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:01:22] Epoch 2 | Step 7170 | Loss: 0.9155 | LM: 0.3975 | LB: 1.0355 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:01:33] Epoch 2 | Step 7180 | Loss: 0.9155 | LM: 0.3974 | LB: 1.0354 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:01:45] Epoch 2 | Step 7190 | Loss: 0.9155 | LM: 0.3974 | LB: 1.0354 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:01:55] Epoch 2 | Step 7200 | Loss: 0.9154 | LM: 0.3974 | LB: 1.0354 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:02:06] Epoch 2 | Step 7210 | Loss: 0.9154 | LM: 0.3974 | LB: 1.0353 | CL0: 4.6 | CL1: 6.7 | HR0: 0.220/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:02:17] Epoch 2 | Step 7220 | Loss: 0.9154 | LM: 0.3977 | LB: 1.0353 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:02:28] Epoch 2 | Step 7230 | Loss: 0.9153 | LM: 0.3975 | LB: 1.0353 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:02:40] Epoch 2 | Step 7240 | Loss: 0.9154 | LM: 0.3978 | LB: 1.0353 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:02:51] Epoch 2 | Step 7250 | Loss: 0.9154 | LM: 0.3980 | LB: 1.0352 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:03:02] Epoch 2 | Step 7260 | Loss: 0.9156 | LM: 0.3981 | LB: 1.0352 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:03:13] Epoch 2 | Step 7270 | Loss: 0.9155 | LM: 0.3980 | LB: 1.0352 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:03:24] Epoch 2 | Step 7280 | Loss: 0.9156 | LM: 0.3982 | LB: 1.0352 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:03:35] Epoch 2 | Step 7290 | Loss: 0.9156 | LM: 0.3983 | LB: 1.0351 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:03:46] Epoch 2 | Step 7300 | Loss: 0.9157 | LM: 0.3985 | LB: 1.0351 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:03:57] Epoch 2 | Step 7310 | Loss: 0.9156 | LM: 0.3983 | LB: 1.0351 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:04:09] Epoch 2 | Step 7320 | Loss: 0.9156 | LM: 0.3983 | LB: 1.0351 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:04:21] Epoch 2 | Step 7330 | Loss: 0.9155 | LM: 0.3981 | LB: 1.0351 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:04:32] Epoch 2 | Step 7340 | Loss: 0.9155 | LM: 0.3981 | LB: 1.0350 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:04:43] Epoch 2 | Step 7350 | Loss: 0.9154 | LM: 0.3982 | LB: 1.0350 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:04:55] Epoch 2 | Step 7360 | Loss: 0.9154 | LM: 0.3982 | LB: 1.0350 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:05:06] Epoch 2 | Step 7370 | Loss: 0.9154 | LM: 0.3982 | LB: 1.0350 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:05:18] Epoch 2 | Step 7380 | Loss: 0.9154 | LM: 0.3983 | LB: 1.0350 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:05:30] Epoch 2 | Step 7390 | Loss: 0.9155 | LM: 0.3985 | LB: 1.0349 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:05:41] Epoch 2 | Step 7400 | Loss: 0.9155 | LM: 0.3984 | LB: 1.0349 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:05:53] Epoch 2 | Step 7410 | Loss: 0.9155 | LM: 0.3983 | LB: 1.0349 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:06:04] Epoch 2 | Step 7420 | Loss: 0.9155 | LM: 0.3983 | LB: 1.0349 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:06:16] Epoch 2 | Step 7430 | Loss: 0.9155 | LM: 0.3986 | LB: 1.0348 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:06:27] Epoch 2 | Step 7440 | Loss: 0.9155 | LM: 0.3985 | LB: 1.0348 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.197 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:06:39] Epoch 2 | Step 7450 | Loss: 0.9155 | LM: 0.3983 | LB: 1.0348 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:06:50] Epoch 2 | Step 7460 | Loss: 0.9155 | LM: 0.3984 | LB: 1.0348 | CL0: 4.6 | CL1: 6.7 | HR0: 0.219/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:07:01] Epoch 2 | Step 7470 | Loss: 0.9154 | LM: 0.3985 | LB: 1.0347 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:07:11] Epoch 2 | Step 7480 | Loss: 0.9154 | LM: 0.3985 | LB: 1.0347 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:07:22] Epoch 2 | Step 7490 | Loss: 0.9154 | LM: 0.3987 | LB: 1.0347 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:07:33] Epoch 2 | Step 7500 | Loss: 0.9156 | LM: 0.3989 | LB: 1.0347 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:07:43] Epoch 2 | Step 7510 | Loss: 0.9156 | LM: 0.3987 | LB: 1.0346 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:07:54] Epoch 2 | Step 7520 | Loss: 0.9156 | LM: 0.3988 | LB: 1.0346 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:08:04] Epoch 2 | Step 7530 | Loss: 0.9157 | LM: 0.3988 | LB: 1.0346 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:08:15] Epoch 2 | Step 7540 | Loss: 0.9157 | LM: 0.3989 | LB: 1.0346 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:08:26] Epoch 2 | Step 7550 | Loss: 0.9157 | LM: 0.3990 | LB: 1.0346 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:08:37] Epoch 2 | Step 7560 | Loss: 0.9157 | LM: 0.3990 | LB: 1.0345 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:08:47] Epoch 2 | Step 7570 | Loss: 0.9157 | LM: 0.3990 | LB: 1.0345 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:08:58] Epoch 2 | Step 7580 | Loss: 0.9157 | LM: 0.3991 | LB: 1.0345 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:09:08] Epoch 2 | Step 7590 | Loss: 0.9158 | LM: 0.3994 | LB: 1.0344 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:09:19] Epoch 2 | Step 7600 | Loss: 0.9158 | LM: 0.3995 | LB: 1.0344 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:09:30] Epoch 2 | Step 7610 | Loss: 0.9158 | LM: 0.3994 | LB: 1.0344 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:09:40] Epoch 2 | Step 7620 | Loss: 0.9158 | LM: 0.3995 | LB: 1.0344 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:09:51] Epoch 2 | Step 7630 | Loss: 0.9158 | LM: 0.3994 | LB: 1.0344 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:10:01] Epoch 2 | Step 7640 | Loss: 0.9158 | LM: 0.3994 | LB: 1.0344 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:10:12] Epoch 2 | Step 7650 | Loss: 0.9159 | LM: 0.3997 | LB: 1.0343 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:10:23] Epoch 2 | Step 7660 | Loss: 0.9159 | LM: 0.3996 | LB: 1.0343 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:10:34] Epoch 2 | Step 7670 | Loss: 0.9159 | LM: 0.3995 | LB: 1.0343 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:10:45] Epoch 2 | Step 7680 | Loss: 0.9158 | LM: 0.3994 | LB: 1.0343 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:10:56] Epoch 2 | Step 7690 | Loss: 0.9158 | LM: 0.3995 | LB: 1.0343 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:11:07] Epoch 2 | Step 7700 | Loss: 0.9159 | LM: 0.3995 | LB: 1.0342 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:11:18] Epoch 2 | Step 7710 | Loss: 0.9159 | LM: 0.3996 | LB: 1.0342 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:11:29] Epoch 2 | Step 7720 | Loss: 0.9160 | LM: 0.3999 | LB: 1.0342 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:11:41] Epoch 2 | Step 7730 | Loss: 0.9160 | LM: 0.3998 | LB: 1.0342 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:11:52] Epoch 2 | Step 7740 | Loss: 0.9162 | LM: 0.4001 | LB: 1.0342 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:12:03] Epoch 2 | Step 7750 | Loss: 0.9163 | LM: 0.4003 | LB: 1.0342 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:12:14] Epoch 2 | Step 7760 | Loss: 0.9163 | LM: 0.4004 | LB: 1.0342 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:12:25] Epoch 2 | Step 7770 | Loss: 0.9163 | LM: 0.4004 | LB: 1.0341 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:12:36] Epoch 2 | Step 7780 | Loss: 0.9164 | LM: 0.4005 | LB: 1.0341 | CL0: 4.6 | CL1: 6.7 | HR0: 0.218/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:12:47] Epoch 2 | Step 7790 | Loss: 0.9165 | LM: 0.4007 | LB: 1.0341 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:12:58] Epoch 2 | Step 7800 | Loss: 0.9164 | LM: 0.4006 | LB: 1.0341 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:13:08] Epoch 2 | Step 7810 | Loss: 0.9165 | LM: 0.4007 | LB: 1.0340 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:13:20] Epoch 2 | Step 7820 | Loss: 0.9166 | LM: 0.4007 | LB: 1.0340 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:13:31] Epoch 2 | Step 7830 | Loss: 0.9167 | LM: 0.4009 | LB: 1.0340 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:13:42] Epoch 2 | Step 7840 | Loss: 0.9167 | LM: 0.4010 | LB: 1.0340 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:13:53] Epoch 2 | Step 7850 | Loss: 0.9167 | LM: 0.4010 | LB: 1.0340 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:14:04] Epoch 2 | Step 7860 | Loss: 0.9166 | LM: 0.4008 | LB: 1.0340 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:14:15] Epoch 2 | Step 7870 | Loss: 0.9166 | LM: 0.4009 | LB: 1.0339 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.196 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:14:26] Epoch 2 | Step 7880 | Loss: 0.9166 | LM: 0.4011 | LB: 1.0339 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:14:36] Epoch 2 | Step 7890 | Loss: 0.9165 | LM: 0.4008 | LB: 1.0339 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:14:47] Epoch 2 | Step 7900 | Loss: 0.9166 | LM: 0.4009 | LB: 1.0339 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:14:57] Epoch 2 | Step 7910 | Loss: 0.9165 | LM: 0.4009 | LB: 1.0339 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:15:08] Epoch 2 | Step 7920 | Loss: 0.9164 | LM: 0.4010 | LB: 1.0339 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:15:18] Epoch 2 | Step 7930 | Loss: 0.9164 | LM: 0.4009 | LB: 1.0338 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:15:29] Epoch 2 | Step 7940 | Loss: 0.9163 | LM: 0.4009 | LB: 1.0338 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:15:39] Epoch 2 | Step 7950 | Loss: 0.9163 | LM: 0.4009 | LB: 1.0338 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:15:50] Epoch 2 | Step 7960 | Loss: 0.9164 | LM: 0.4011 | LB: 1.0338 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:16:01] Epoch 2 | Step 7970 | Loss: 0.9165 | LM: 0.4011 | LB: 1.0337 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:16:11] Epoch 2 | Step 7980 | Loss: 0.9165 | LM: 0.4011 | LB: 1.0337 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:16:22] Epoch 2 | Step 7990 | Loss: 0.9164 | LM: 0.4008 | LB: 1.0337 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:16:32] Epoch 2 | Step 8000 | Loss: 0.9165 | LM: 0.4010 | LB: 1.0337 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:16:34] Validation | Batch 10/1463 | Loss: 0.9061 | LM_LOSS: 0.3970 | LB_LOSS: 1.0181
[2026-05-24 14:16:35] Validation | Batch 20/1463 | Loss: 0.9191 | LM_LOSS: 0.4089 | LB_LOSS: 1.0205
[2026-05-24 14:16:37] Validation | Batch 30/1463 | Loss: 0.9251 | LM_LOSS: 0.4143 | LB_LOSS: 1.0216
[2026-05-24 14:16:38] Validation | Batch 40/1463 | Loss: 0.9336 | LM_LOSS: 0.4223 | LB_LOSS: 1.0226
[2026-05-24 14:16:40] Validation | Batch 50/1463 | Loss: 0.9400 | LM_LOSS: 0.4290 | LB_LOSS: 1.0220
[2026-05-24 14:16:42] Validation | Batch 60/1463 | Loss: 0.9417 | LM_LOSS: 0.4306 | LB_LOSS: 1.0221
[2026-05-24 14:16:44] Validation | Batch 70/1463 | Loss: 0.9412 | LM_LOSS: 0.4301 | LB_LOSS: 1.0223
[2026-05-24 14:16:45] Validation | Batch 80/1463 | Loss: 0.9412 | LM_LOSS: 0.4300 | LB_LOSS: 1.0224
[2026-05-24 14:16:47] Validation | Batch 90/1463 | Loss: 0.9411 | LM_LOSS: 0.4300 | LB_LOSS: 1.0224
[2026-05-24 14:16:48] Validation | Batch 100/1463 | Loss: 0.9416 | LM_LOSS: 0.4304 | LB_LOSS: 1.0224
[2026-05-24 14:16:50] Validation | Batch 110/1463 | Loss: 0.9402 | LM_LOSS: 0.4289 | LB_LOSS: 1.0227
[2026-05-24 14:16:51] Validation | Batch 120/1463 | Loss: 0.9415 | LM_LOSS: 0.4301 | LB_LOSS: 1.0227
[2026-05-24 14:16:53] Validation | Batch 130/1463 | Loss: 0.9449 | LM_LOSS: 0.4335 | LB_LOSS: 1.0227
[2026-05-24 14:16:55] Validation | Batch 140/1463 | Loss: 0.9458 | LM_LOSS: 0.4344 | LB_LOSS: 1.0228
[2026-05-24 14:16:56] Validation | Batch 150/1463 | Loss: 0.9437 | LM_LOSS: 0.4322 | LB_LOSS: 1.0229
[2026-05-24 14:16:58] Validation | Batch 160/1463 | Loss: 0.9452 | LM_LOSS: 0.4338 | LB_LOSS: 1.0228
[2026-05-24 14:17:00] Validation | Batch 170/1463 | Loss: 0.9451 | LM_LOSS: 0.4337 | LB_LOSS: 1.0229
[2026-05-24 14:17:01] Validation | Batch 180/1463 | Loss: 0.9461 | LM_LOSS: 0.4347 | LB_LOSS: 1.0230
[2026-05-24 14:17:03] Validation | Batch 190/1463 | Loss: 0.9469 | LM_LOSS: 0.4354 | LB_LOSS: 1.0230
[2026-05-24 14:17:05] Validation | Batch 200/1463 | Loss: 0.9460 | LM_LOSS: 0.4345 | LB_LOSS: 1.0230
[2026-05-24 14:17:06] Validation | Batch 210/1463 | Loss: 0.9464 | LM_LOSS: 0.4348 | LB_LOSS: 1.0231
[2026-05-24 14:17:08] Validation | Batch 220/1463 | Loss: 0.9453 | LM_LOSS: 0.4337 | LB_LOSS: 1.0232
[2026-05-24 14:17:10] Validation | Batch 230/1463 | Loss: 0.9470 | LM_LOSS: 0.4355 | LB_LOSS: 1.0230
[2026-05-24 14:17:11] Validation | Batch 240/1463 | Loss: 0.9476 | LM_LOSS: 0.4362 | LB_LOSS: 1.0230
[2026-05-24 14:17:13] Validation | Batch 250/1463 | Loss: 0.9464 | LM_LOSS: 0.4349 | LB_LOSS: 1.0230
[2026-05-24 14:17:15] Validation | Batch 260/1463 | Loss: 0.9483 | LM_LOSS: 0.4367 | LB_LOSS: 1.0232
[2026-05-24 14:17:16] Validation | Batch 270/1463 | Loss: 0.9472 | LM_LOSS: 0.4356 | LB_LOSS: 1.0232
[2026-05-24 14:17:18] Validation | Batch 280/1463 | Loss: 0.9484 | LM_LOSS: 0.4368 | LB_LOSS: 1.0232
[2026-05-24 14:17:20] Validation | Batch 290/1463 | Loss: 0.9471 | LM_LOSS: 0.4355 | LB_LOSS: 1.0232
[2026-05-24 14:17:21] Validation | Batch 300/1463 | Loss: 0.9479 | LM_LOSS: 0.4363 | LB_LOSS: 1.0233
[2026-05-24 14:17:23] Validation | Batch 310/1463 | Loss: 0.9489 | LM_LOSS: 0.4373 | LB_LOSS: 1.0233
[2026-05-24 14:17:24] Validation | Batch 320/1463 | Loss: 0.9473 | LM_LOSS: 0.4358 | LB_LOSS: 1.0231
[2026-05-24 14:17:26] Validation | Batch 330/1463 | Loss: 0.9474 | LM_LOSS: 0.4358 | LB_LOSS: 1.0232
[2026-05-24 14:17:27] Validation | Batch 340/1463 | Loss: 0.9470 | LM_LOSS: 0.4354 | LB_LOSS: 1.0232
[2026-05-24 14:17:29] Validation | Batch 350/1463 | Loss: 0.9473 | LM_LOSS: 0.4357 | LB_LOSS: 1.0232
[2026-05-24 14:17:31] Validation | Batch 360/1463 | Loss: 0.9474 | LM_LOSS: 0.4358 | LB_LOSS: 1.0232
[2026-05-24 14:17:32] Validation | Batch 370/1463 | Loss: 0.9475 | LM_LOSS: 0.4359 | LB_LOSS: 1.0232
[2026-05-24 14:17:33] Validation | Batch 380/1463 | Loss: 0.9475 | LM_LOSS: 0.4359 | LB_LOSS: 1.0231
[2026-05-24 14:17:35] Validation | Batch 390/1463 | Loss: 0.9485 | LM_LOSS: 0.4369 | LB_LOSS: 1.0231
[2026-05-24 14:17:37] Validation | Batch 400/1463 | Loss: 0.9483 | LM_LOSS: 0.4367 | LB_LOSS: 1.0232
[2026-05-24 14:17:38] Validation | Batch 410/1463 | Loss: 0.9483 | LM_LOSS: 0.4367 | LB_LOSS: 1.0232
[2026-05-24 14:17:40] Validation | Batch 420/1463 | Loss: 0.9485 | LM_LOSS: 0.4369 | LB_LOSS: 1.0233
[2026-05-24 14:17:42] Validation | Batch 430/1463 | Loss: 0.9483 | LM_LOSS: 0.4367 | LB_LOSS: 1.0233
[2026-05-24 14:17:43] Validation | Batch 440/1463 | Loss: 0.9487 | LM_LOSS: 0.4370 | LB_LOSS: 1.0234
[2026-05-24 14:17:45] Validation | Batch 450/1463 | Loss: 0.9483 | LM_LOSS: 0.4366 | LB_LOSS: 1.0234
[2026-05-24 14:17:46] Validation | Batch 460/1463 | Loss: 0.9483 | LM_LOSS: 0.4366 | LB_LOSS: 1.0234
[2026-05-24 14:17:48] Validation | Batch 470/1463 | Loss: 0.9489 | LM_LOSS: 0.4372 | LB_LOSS: 1.0234
[2026-05-24 14:17:50] Validation | Batch 480/1463 | Loss: 0.9486 | LM_LOSS: 0.4369 | LB_LOSS: 1.0233
[2026-05-24 14:17:51] Validation | Batch 490/1463 | Loss: 0.9483 | LM_LOSS: 0.4366 | LB_LOSS: 1.0233
[2026-05-24 14:17:53] Validation | Batch 500/1463 | Loss: 0.9479 | LM_LOSS: 0.4362 | LB_LOSS: 1.0234
[2026-05-24 14:17:55] Validation | Batch 510/1463 | Loss: 0.9475 | LM_LOSS: 0.4358 | LB_LOSS: 1.0234
[2026-05-24 14:17:56] Validation | Batch 520/1463 | Loss: 0.9472 | LM_LOSS: 0.4355 | LB_LOSS: 1.0234
[2026-05-24 14:17:58] Validation | Batch 530/1463 | Loss: 0.9477 | LM_LOSS: 0.4360 | LB_LOSS: 1.0234
[2026-05-24 14:17:59] Validation | Batch 540/1463 | Loss: 0.9480 | LM_LOSS: 0.4363 | LB_LOSS: 1.0234
[2026-05-24 14:18:01] Validation | Batch 550/1463 | Loss: 0.9477 | LM_LOSS: 0.4360 | LB_LOSS: 1.0234
[2026-05-24 14:18:02] Validation | Batch 560/1463 | Loss: 0.9481 | LM_LOSS: 0.4364 | LB_LOSS: 1.0235
[2026-05-24 14:18:04] Validation | Batch 570/1463 | Loss: 0.9481 | LM_LOSS: 0.4364 | LB_LOSS: 1.0235
[2026-05-24 14:18:06] Validation | Batch 580/1463 | Loss: 0.9479 | LM_LOSS: 0.4361 | LB_LOSS: 1.0235
[2026-05-24 14:18:08] Validation | Batch 590/1463 | Loss: 0.9478 | LM_LOSS: 0.4360 | LB_LOSS: 1.0236
[2026-05-24 14:18:09] Validation | Batch 600/1463 | Loss: 0.9480 | LM_LOSS: 0.4362 | LB_LOSS: 1.0236
[2026-05-24 14:18:11] Validation | Batch 610/1463 | Loss: 0.9481 | LM_LOSS: 0.4363 | LB_LOSS: 1.0236
[2026-05-24 14:18:13] Validation | Batch 620/1463 | Loss: 0.9476 | LM_LOSS: 0.4358 | LB_LOSS: 1.0236
[2026-05-24 14:18:14] Validation | Batch 630/1463 | Loss: 0.9474 | LM_LOSS: 0.4355 | LB_LOSS: 1.0236
[2026-05-24 14:18:16] Validation | Batch 640/1463 | Loss: 0.9472 | LM_LOSS: 0.4353 | LB_LOSS: 1.0237
[2026-05-24 14:18:17] Validation | Batch 650/1463 | Loss: 0.9466 | LM_LOSS: 0.4347 | LB_LOSS: 1.0237
[2026-05-24 14:18:19] Validation | Batch 660/1463 | Loss: 0.9460 | LM_LOSS: 0.4342 | LB_LOSS: 1.0236
[2026-05-24 14:18:20] Validation | Batch 670/1463 | Loss: 0.9456 | LM_LOSS: 0.4338 | LB_LOSS: 1.0236
[2026-05-24 14:18:22] Validation | Batch 680/1463 | Loss: 0.9457 | LM_LOSS: 0.4339 | LB_LOSS: 1.0236
[2026-05-24 14:18:23] Validation | Batch 690/1463 | Loss: 0.9460 | LM_LOSS: 0.4342 | LB_LOSS: 1.0236
[2026-05-24 14:18:25] Validation | Batch 700/1463 | Loss: 0.9461 | LM_LOSS: 0.4343 | LB_LOSS: 1.0236
[2026-05-24 14:18:26] Validation | Batch 710/1463 | Loss: 0.9464 | LM_LOSS: 0.4346 | LB_LOSS: 1.0236
[2026-05-24 14:18:28] Validation | Batch 720/1463 | Loss: 0.9472 | LM_LOSS: 0.4354 | LB_LOSS: 1.0237
[2026-05-24 14:18:29] Validation | Batch 730/1463 | Loss: 0.9471 | LM_LOSS: 0.4352 | LB_LOSS: 1.0237
[2026-05-24 14:18:31] Validation | Batch 740/1463 | Loss: 0.9468 | LM_LOSS: 0.4350 | LB_LOSS: 1.0236
[2026-05-24 14:18:32] Validation | Batch 750/1463 | Loss: 0.9467 | LM_LOSS: 0.4348 | LB_LOSS: 1.0236
[2026-05-24 14:18:34] Validation | Batch 760/1463 | Loss: 0.9463 | LM_LOSS: 0.4345 | LB_LOSS: 1.0236
[2026-05-24 14:18:35] Validation | Batch 770/1463 | Loss: 0.9461 | LM_LOSS: 0.4343 | LB_LOSS: 1.0237
[2026-05-24 14:18:37] Validation | Batch 780/1463 | Loss: 0.9460 | LM_LOSS: 0.4342 | LB_LOSS: 1.0236
[2026-05-24 14:18:38] Validation | Batch 790/1463 | Loss: 0.9463 | LM_LOSS: 0.4345 | LB_LOSS: 1.0236
[2026-05-24 14:18:39] Validation | Batch 800/1463 | Loss: 0.9463 | LM_LOSS: 0.4345 | LB_LOSS: 1.0236
[2026-05-24 14:18:41] Validation | Batch 810/1463 | Loss: 0.9458 | LM_LOSS: 0.4341 | LB_LOSS: 1.0235
[2026-05-24 14:18:42] Validation | Batch 820/1463 | Loss: 0.9459 | LM_LOSS: 0.4342 | LB_LOSS: 1.0235
[2026-05-24 14:18:44] Validation | Batch 830/1463 | Loss: 0.9461 | LM_LOSS: 0.4343 | LB_LOSS: 1.0235
[2026-05-24 14:18:46] Validation | Batch 840/1463 | Loss: 0.9459 | LM_LOSS: 0.4341 | LB_LOSS: 1.0236
[2026-05-24 14:18:48] Validation | Batch 850/1463 | Loss: 0.9461 | LM_LOSS: 0.4343 | LB_LOSS: 1.0236
[2026-05-24 14:18:49] Validation | Batch 860/1463 | Loss: 0.9460 | LM_LOSS: 0.4342 | LB_LOSS: 1.0236
[2026-05-24 14:18:51] Validation | Batch 870/1463 | Loss: 0.9462 | LM_LOSS: 0.4343 | LB_LOSS: 1.0236
[2026-05-24 14:18:52] Validation | Batch 880/1463 | Loss: 0.9454 | LM_LOSS: 0.4336 | LB_LOSS: 1.0236
[2026-05-24 14:18:54] Validation | Batch 890/1463 | Loss: 0.9455 | LM_LOSS: 0.4337 | LB_LOSS: 1.0236
[2026-05-24 14:18:55] Validation | Batch 900/1463 | Loss: 0.9452 | LM_LOSS: 0.4334 | LB_LOSS: 1.0236
[2026-05-24 14:18:57] Validation | Batch 910/1463 | Loss: 0.9452 | LM_LOSS: 0.4334 | LB_LOSS: 1.0236
[2026-05-24 14:18:59] Validation | Batch 920/1463 | Loss: 0.9454 | LM_LOSS: 0.4336 | LB_LOSS: 1.0236
[2026-05-24 14:19:00] Validation | Batch 930/1463 | Loss: 0.9451 | LM_LOSS: 0.4333 | LB_LOSS: 1.0236
[2026-05-24 14:19:02] Validation | Batch 940/1463 | Loss: 0.9447 | LM_LOSS: 0.4329 | LB_LOSS: 1.0236
[2026-05-24 14:19:04] Validation | Batch 950/1463 | Loss: 0.9450 | LM_LOSS: 0.4332 | LB_LOSS: 1.0236
[2026-05-24 14:19:05] Validation | Batch 960/1463 | Loss: 0.9451 | LM_LOSS: 0.4333 | LB_LOSS: 1.0235
[2026-05-24 14:19:07] Validation | Batch 970/1463 | Loss: 0.9453 | LM_LOSS: 0.4335 | LB_LOSS: 1.0235
[2026-05-24 14:19:09] Validation | Batch 980/1463 | Loss: 0.9456 | LM_LOSS: 0.4338 | LB_LOSS: 1.0235
[2026-05-24 14:19:10] Validation | Batch 990/1463 | Loss: 0.9458 | LM_LOSS: 0.4340 | LB_LOSS: 1.0235
[2026-05-24 14:19:12] Validation | Batch 1000/1463 | Loss: 0.9464 | LM_LOSS: 0.4346 | LB_LOSS: 1.0235
[2026-05-24 14:19:14] Validation | Batch 1010/1463 | Loss: 0.9465 | LM_LOSS: 0.4347 | LB_LOSS: 1.0236
[2026-05-24 14:19:15] Validation | Batch 1020/1463 | Loss: 0.9467 | LM_LOSS: 0.4349 | LB_LOSS: 1.0236
[2026-05-24 14:19:17] Validation | Batch 1030/1463 | Loss: 0.9472 | LM_LOSS: 0.4354 | LB_LOSS: 1.0236
[2026-05-24 14:19:19] Validation | Batch 1040/1463 | Loss: 0.9466 | LM_LOSS: 0.4348 | LB_LOSS: 1.0236
[2026-05-24 14:19:20] Validation | Batch 1050/1463 | Loss: 0.9465 | LM_LOSS: 0.4347 | LB_LOSS: 1.0236
[2026-05-24 14:19:22] Validation | Batch 1060/1463 | Loss: 0.9463 | LM_LOSS: 0.4346 | LB_LOSS: 1.0235
[2026-05-24 14:19:24] Validation | Batch 1070/1463 | Loss: 0.9464 | LM_LOSS: 0.4346 | LB_LOSS: 1.0236
[2026-05-24 14:19:25] Validation | Batch 1080/1463 | Loss: 0.9461 | LM_LOSS: 0.4343 | LB_LOSS: 1.0236
[2026-05-24 14:19:27] Validation | Batch 1090/1463 | Loss: 0.9461 | LM_LOSS: 0.4343 | LB_LOSS: 1.0235
[2026-05-24 14:19:28] Validation | Batch 1100/1463 | Loss: 0.9460 | LM_LOSS: 0.4343 | LB_LOSS: 1.0235
[2026-05-24 14:19:30] Validation | Batch 1110/1463 | Loss: 0.9461 | LM_LOSS: 0.4343 | LB_LOSS: 1.0235
[2026-05-24 14:19:31] Validation | Batch 1120/1463 | Loss: 0.9459 | LM_LOSS: 0.4341 | LB_LOSS: 1.0235
[2026-05-24 14:19:33] Validation | Batch 1130/1463 | Loss: 0.9455 | LM_LOSS: 0.4338 | LB_LOSS: 1.0235
[2026-05-24 14:19:35] Validation | Batch 1140/1463 | Loss: 0.9457 | LM_LOSS: 0.4340 | LB_LOSS: 1.0235
[2026-05-24 14:19:36] Validation | Batch 1150/1463 | Loss: 0.9457 | LM_LOSS: 0.4340 | LB_LOSS: 1.0235
[2026-05-24 14:19:38] Validation | Batch 1160/1463 | Loss: 0.9457 | LM_LOSS: 0.4340 | LB_LOSS: 1.0235
[2026-05-24 14:19:40] Validation | Batch 1170/1463 | Loss: 0.9456 | LM_LOSS: 0.4339 | LB_LOSS: 1.0235
[2026-05-24 14:19:41] Validation | Batch 1180/1463 | Loss: 0.9456 | LM_LOSS: 0.4338 | LB_LOSS: 1.0235
[2026-05-24 14:19:43] Validation | Batch 1190/1463 | Loss: 0.9458 | LM_LOSS: 0.4340 | LB_LOSS: 1.0235
[2026-05-24 14:19:45] Validation | Batch 1200/1463 | Loss: 0.9460 | LM_LOSS: 0.4343 | LB_LOSS: 1.0235
[2026-05-24 14:19:46] Validation | Batch 1210/1463 | Loss: 0.9463 | LM_LOSS: 0.4345 | LB_LOSS: 1.0235
[2026-05-24 14:19:48] Validation | Batch 1220/1463 | Loss: 0.9467 | LM_LOSS: 0.4349 | LB_LOSS: 1.0236
[2026-05-24 14:19:49] Validation | Batch 1230/1463 | Loss: 0.9466 | LM_LOSS: 0.4348 | LB_LOSS: 1.0236
[2026-05-24 14:19:51] Validation | Batch 1240/1463 | Loss: 0.9470 | LM_LOSS: 0.4352 | LB_LOSS: 1.0236
[2026-05-24 14:19:53] Validation | Batch 1250/1463 | Loss: 0.9472 | LM_LOSS: 0.4354 | LB_LOSS: 1.0236
[2026-05-24 14:19:54] Validation | Batch 1260/1463 | Loss: 0.9472 | LM_LOSS: 0.4354 | LB_LOSS: 1.0236
[2026-05-24 14:19:56] Validation | Batch 1270/1463 | Loss: 0.9470 | LM_LOSS: 0.4352 | LB_LOSS: 1.0236
[2026-05-24 14:19:58] Validation | Batch 1280/1463 | Loss: 0.9468 | LM_LOSS: 0.4350 | LB_LOSS: 1.0236
[2026-05-24 14:19:59] Validation | Batch 1290/1463 | Loss: 0.9469 | LM_LOSS: 0.4351 | LB_LOSS: 1.0236
[2026-05-24 14:20:01] Validation | Batch 1300/1463 | Loss: 0.9466 | LM_LOSS: 0.4348 | LB_LOSS: 1.0236
[2026-05-24 14:20:03] Validation | Batch 1310/1463 | Loss: 0.9465 | LM_LOSS: 0.4348 | LB_LOSS: 1.0236
[2026-05-24 14:20:04] Validation | Batch 1320/1463 | Loss: 0.9466 | LM_LOSS: 0.4348 | LB_LOSS: 1.0236
[2026-05-24 14:20:05] Validation | Batch 1330/1463 | Loss: 0.9465 | LM_LOSS: 0.4348 | LB_LOSS: 1.0235
[2026-05-24 14:20:07] Validation | Batch 1340/1463 | Loss: 0.9467 | LM_LOSS: 0.4349 | LB_LOSS: 1.0235
[2026-05-24 14:20:08] Validation | Batch 1350/1463 | Loss: 0.9467 | LM_LOSS: 0.4349 | LB_LOSS: 1.0235
[2026-05-24 14:20:10] Validation | Batch 1360/1463 | Loss: 0.9470 | LM_LOSS: 0.4352 | LB_LOSS: 1.0235
[2026-05-24 14:20:12] Validation | Batch 1370/1463 | Loss: 0.9473 | LM_LOSS: 0.4356 | LB_LOSS: 1.0236
[2026-05-24 14:20:13] Validation | Batch 1380/1463 | Loss: 0.9471 | LM_LOSS: 0.4353 | LB_LOSS: 1.0235
[2026-05-24 14:20:15] Validation | Batch 1390/1463 | Loss: 0.9470 | LM_LOSS: 0.4352 | LB_LOSS: 1.0235
[2026-05-24 14:20:17] Validation | Batch 1400/1463 | Loss: 0.9472 | LM_LOSS: 0.4355 | LB_LOSS: 1.0235
[2026-05-24 14:20:18] Validation | Batch 1410/1463 | Loss: 0.9474 | LM_LOSS: 0.4357 | LB_LOSS: 1.0235
[2026-05-24 14:20:19] Validation | Batch 1420/1463 | Loss: 0.9475 | LM_LOSS: 0.4358 | LB_LOSS: 1.0235
[2026-05-24 14:20:21] Validation | Batch 1430/1463 | Loss: 0.9477 | LM_LOSS: 0.4360 | LB_LOSS: 1.0235
[2026-05-24 14:20:23] Validation | Batch 1440/1463 | Loss: 0.9481 | LM_LOSS: 0.4363 | LB_LOSS: 1.0235
[2026-05-24 14:20:24] Validation | Batch 1450/1463 | Loss: 0.9477 | LM_LOSS: 0.4360 | LB_LOSS: 1.0235
[2026-05-24 14:20:26] Validation | Batch 1460/1463 | Loss: 0.9480 | LM_LOSS: 0.4363 | LB_LOSS: 1.0235
[2026-05-24 14:20:27] Validation | Batch 1463/1463 | Loss: 0.9479 | LM_LOSS: 0.4362 | LB_LOSS: 1.0235
[2026-05-24 14:20:27] Validation | Loss: 0.9479 | LM_LOSS: 0.4362 | LB_LOSS: 1.0235 | PPL: 1.55 | Time: 234.46s
[2026-05-24 14:20:38] Epoch 2 | Step 8010 | Loss: 0.9165 | LM: 0.4009 | LB: 1.0336 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:20:48] Epoch 2 | Step 8020 | Loss: 0.9166 | LM: 0.4010 | LB: 1.0336 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:20:59] Epoch 2 | Step 8030 | Loss: 0.9166 | LM: 0.4010 | LB: 1.0336 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:21:09] Epoch 2 | Step 8040 | Loss: 0.9167 | LM: 0.4011 | LB: 1.0336 | CL0: 4.6 | CL1: 6.7 | HR0: 0.217/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:21:20] Epoch 2 | Step 8050 | Loss: 0.9167 | LM: 0.4010 | LB: 1.0336 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:21:32] Epoch 2 | Step 8060 | Loss: 0.9166 | LM: 0.4008 | LB: 1.0335 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:21:43] Epoch 2 | Step 8070 | Loss: 0.9166 | LM: 0.4007 | LB: 1.0335 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:21:55] Epoch 2 | Step 8080 | Loss: 0.9167 | LM: 0.4008 | LB: 1.0335 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:22:06] Epoch 2 | Step 8090 | Loss: 0.9167 | LM: 0.4007 | LB: 1.0335 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:22:18] Epoch 2 | Step 8100 | Loss: 0.9166 | LM: 0.4007 | LB: 1.0334 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:22:29] Epoch 2 | Step 8110 | Loss: 0.9167 | LM: 0.4008 | LB: 1.0334 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:22:41] Epoch 2 | Step 8120 | Loss: 0.9167 | LM: 0.4007 | LB: 1.0334 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:22:53] Epoch 2 | Step 8130 | Loss: 0.9167 | LM: 0.4007 | LB: 1.0334 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:23:04] Epoch 2 | Step 8140 | Loss: 0.9167 | LM: 0.4007 | LB: 1.0333 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:23:16] Epoch 2 | Step 8150 | Loss: 0.9168 | LM: 0.4007 | LB: 1.0333 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:23:27] Epoch 2 | Step 8160 | Loss: 0.9168 | LM: 0.4008 | LB: 1.0333 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:23:39] Epoch 2 | Step 8170 | Loss: 0.9169 | LM: 0.4011 | LB: 1.0333 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:23:51] Epoch 2 | Step 8180 | Loss: 0.9170 | LM: 0.4013 | LB: 1.0333 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:24:02] Epoch 2 | Step 8190 | Loss: 0.9171 | LM: 0.4014 | LB: 1.0332 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:24:14] Epoch 2 | Step 8200 | Loss: 0.9172 | LM: 0.4014 | LB: 1.0332 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:24:26] Epoch 2 | Step 8210 | Loss: 0.9172 | LM: 0.4016 | LB: 1.0332 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:24:37] Epoch 2 | Step 8220 | Loss: 0.9172 | LM: 0.4014 | LB: 1.0332 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.195 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:24:48] Epoch 2 | Step 8230 | Loss: 0.9172 | LM: 0.4015 | LB: 1.0332 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:24:59] Epoch 2 | Step 8240 | Loss: 0.9172 | LM: 0.4015 | LB: 1.0332 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:25:10] Epoch 2 | Step 8250 | Loss: 0.9173 | LM: 0.4016 | LB: 1.0331 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:25:21] Epoch 2 | Step 8260 | Loss: 0.9174 | LM: 0.4016 | LB: 1.0331 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:25:33] Epoch 2 | Step 8270 | Loss: 0.9174 | LM: 0.4016 | LB: 1.0331 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:25:44] Epoch 2 | Step 8280 | Loss: 0.9175 | LM: 0.4017 | LB: 1.0331 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:25:55] Epoch 2 | Step 8290 | Loss: 0.9175 | LM: 0.4017 | LB: 1.0331 | CL0: 4.7 | CL1: 6.7 | HR0: 0.216/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:26:06] Epoch 2 | Step 8300 | Loss: 0.9175 | LM: 0.4017 | LB: 1.0330 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:26:17] Epoch 2 | Step 8310 | Loss: 0.9174 | LM: 0.4017 | LB: 1.0330 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:26:28] Epoch 2 | Step 8320 | Loss: 0.9174 | LM: 0.4017 | LB: 1.0330 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:26:39] Epoch 2 | Step 8330 | Loss: 0.9175 | LM: 0.4018 | LB: 1.0330 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:26:50] Epoch 2 | Step 8340 | Loss: 0.9174 | LM: 0.4017 | LB: 1.0329 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:27:01] Epoch 2 | Step 8350 | Loss: 0.9175 | LM: 0.4018 | LB: 1.0329 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:27:12] Epoch 2 | Step 8360 | Loss: 0.9176 | LM: 0.4021 | LB: 1.0329 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:27:23] Epoch 2 | Step 8370 | Loss: 0.9177 | LM: 0.4019 | LB: 1.0328 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:27:34] Epoch 2 | Step 8380 | Loss: 0.9176 | LM: 0.4018 | LB: 1.0328 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:27:45] Epoch 2 | Step 8390 | Loss: 0.9177 | LM: 0.4019 | LB: 1.0328 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:27:56] Epoch 2 | Step 8400 | Loss: 0.9177 | LM: 0.4020 | LB: 1.0328 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:28:08] Epoch 2 | Step 8410 | Loss: 0.9177 | LM: 0.4019 | LB: 1.0327 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:28:19] Epoch 2 | Step 8420 | Loss: 0.9177 | LM: 0.4019 | LB: 1.0327 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:28:30] Epoch 2 | Step 8430 | Loss: 0.9177 | LM: 0.4021 | LB: 1.0327 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:28:41] Epoch 2 | Step 8440 | Loss: 0.9178 | LM: 0.4023 | LB: 1.0327 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:28:52] Epoch 2 | Step 8450 | Loss: 0.9178 | LM: 0.4024 | LB: 1.0327 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:29:03] Epoch 2 | Step 8460 | Loss: 0.9178 | LM: 0.4023 | LB: 1.0326 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:29:14] Epoch 2 | Step 8470 | Loss: 0.9177 | LM: 0.4021 | LB: 1.0326 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:29:25] Epoch 2 | Step 8480 | Loss: 0.9177 | LM: 0.4019 | LB: 1.0326 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:29:36] Epoch 2 | Step 8490 | Loss: 0.9178 | LM: 0.4021 | LB: 1.0325 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:29:47] Epoch 2 | Step 8500 | Loss: 0.9178 | LM: 0.4021 | LB: 1.0325 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:29:58] Epoch 2 | Step 8510 | Loss: 0.9178 | LM: 0.4022 | LB: 1.0325 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:30:09] Epoch 2 | Step 8520 | Loss: 0.9179 | LM: 0.4023 | LB: 1.0325 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:30:20] Epoch 2 | Step 8530 | Loss: 0.9179 | LM: 0.4025 | LB: 1.0324 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:30:31] Epoch 2 | Step 8540 | Loss: 0.9179 | LM: 0.4023 | LB: 1.0324 | CL0: 4.7 | CL1: 6.7 | HR0: 0.215/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:30:43] Epoch 2 | Step 8550 | Loss: 0.9179 | LM: 0.4023 | LB: 1.0324 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:30:54] Epoch 2 | Step 8560 | Loss: 0.9179 | LM: 0.4023 | LB: 1.0324 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:31:04] Epoch 2 | Step 8570 | Loss: 0.9179 | LM: 0.4023 | LB: 1.0324 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:31:16] Epoch 2 | Step 8580 | Loss: 0.9179 | LM: 0.4023 | LB: 1.0324 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.194 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:31:26] Epoch 2 | Step 8590 | Loss: 0.9179 | LM: 0.4023 | LB: 1.0323 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:31:37] Epoch 2 | Step 8600 | Loss: 0.9179 | LM: 0.4023 | LB: 1.0323 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:31:48] Epoch 2 | Step 8610 | Loss: 0.9180 | LM: 0.4023 | LB: 1.0323 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:32:00] Epoch 2 | Step 8620 | Loss: 0.9181 | LM: 0.4025 | LB: 1.0323 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:32:11] Epoch 2 | Step 8630 | Loss: 0.9180 | LM: 0.4025 | LB: 1.0322 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:32:22] Epoch 2 | Step 8640 | Loss: 0.9180 | LM: 0.4023 | LB: 1.0322 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:32:33] Epoch 2 | Step 8650 | Loss: 0.9180 | LM: 0.4023 | LB: 1.0322 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:32:44] Epoch 2 | Step 8660 | Loss: 0.9179 | LM: 0.4023 | LB: 1.0322 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:32:55] Epoch 2 | Step 8670 | Loss: 0.9179 | LM: 0.4021 | LB: 1.0322 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:33:06] Epoch 2 | Step 8680 | Loss: 0.9180 | LM: 0.4020 | LB: 1.0321 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:33:17] Epoch 2 | Step 8690 | Loss: 0.9180 | LM: 0.4021 | LB: 1.0321 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:33:28] Epoch 2 | Step 8700 | Loss: 0.9180 | LM: 0.4023 | LB: 1.0321 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:33:39] Epoch 2 | Step 8710 | Loss: 0.9180 | LM: 0.4024 | LB: 1.0321 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:33:50] Epoch 2 | Step 8720 | Loss: 0.9181 | LM: 0.4024 | LB: 1.0321 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:34:01] Epoch 2 | Step 8730 | Loss: 0.9181 | LM: 0.4027 | LB: 1.0320 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:34:12] Epoch 2 | Step 8740 | Loss: 0.9181 | LM: 0.4027 | LB: 1.0320 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:34:23] Epoch 2 | Step 8750 | Loss: 0.9183 | LM: 0.4027 | LB: 1.0320 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:34:34] Epoch 2 | Step 8760 | Loss: 0.9183 | LM: 0.4028 | LB: 1.0320 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:34:45] Epoch 2 | Step 8770 | Loss: 0.9184 | LM: 0.4029 | LB: 1.0320 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:34:56] Epoch 2 | Step 8780 | Loss: 0.9184 | LM: 0.4027 | LB: 1.0319 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:35:07] Epoch 2 | Step 8790 | Loss: 0.9184 | LM: 0.4028 | LB: 1.0319 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:35:18] Epoch 2 | Step 8800 | Loss: 0.9185 | LM: 0.4028 | LB: 1.0319 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:35:29] Epoch 2 | Step 8810 | Loss: 0.9185 | LM: 0.4030 | LB: 1.0319 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:35:40] Epoch 2 | Step 8820 | Loss: 0.9186 | LM: 0.4031 | LB: 1.0318 | CL0: 4.7 | CL1: 6.7 | HR0: 0.214/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:35:51] Epoch 2 | Step 8830 | Loss: 0.9185 | LM: 0.4033 | LB: 1.0318 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:36:02] Epoch 2 | Step 8840 | Loss: 0.9185 | LM: 0.4034 | LB: 1.0318 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:36:13] Epoch 2 | Step 8850 | Loss: 0.9187 | LM: 0.4035 | LB: 1.0318 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:36:24] Epoch 2 | Step 8860 | Loss: 0.9186 | LM: 0.4035 | LB: 1.0317 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:36:35] Epoch 2 | Step 8870 | Loss: 0.9186 | LM: 0.4035 | LB: 1.0317 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:36:46] Epoch 2 | Step 8880 | Loss: 0.9187 | LM: 0.4036 | LB: 1.0317 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:36:57] Epoch 2 | Step 8890 | Loss: 0.9186 | LM: 0.4037 | LB: 1.0317 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:37:09] Epoch 2 | Step 8900 | Loss: 0.9187 | LM: 0.4036 | LB: 1.0317 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:37:20] Epoch 2 | Step 8910 | Loss: 0.9187 | LM: 0.4039 | LB: 1.0317 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:37:31] Epoch 2 | Step 8920 | Loss: 0.9187 | LM: 0.4039 | LB: 1.0316 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:37:42] Epoch 2 | Step 8930 | Loss: 0.9187 | LM: 0.4040 | LB: 1.0316 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:37:53] Epoch 2 | Step 8940 | Loss: 0.9186 | LM: 0.4039 | LB: 1.0316 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:38:04] Epoch 2 | Step 8950 | Loss: 0.9186 | LM: 0.4038 | LB: 1.0315 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:38:15] Epoch 2 | Step 8960 | Loss: 0.9186 | LM: 0.4039 | LB: 1.0315 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.193 | HR1: 0.153/SR1: 0.136 | LR: 1.00e-04
[2026-05-24 14:38:27] Epoch 2 | Step 8970 | Loss: 0.9187 | LM: 0.4040 | LB: 1.0315 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:38:38] Epoch 2 | Step 8980 | Loss: 0.9187 | LM: 0.4041 | LB: 1.0315 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:38:48] Epoch 2 | Step 8990 | Loss: 0.9188 | LM: 0.4041 | LB: 1.0314 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:38:59] Epoch 2 | Step 9000 | Loss: 0.9188 | LM: 0.4040 | LB: 1.0314 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:39:03] Checkpoint saved: outputs/2026-05-24/N_8.0/checkpoints/checkpoint_step_9000.pt
[2026-05-24 14:39:09] Validation | Batch 10/1463 | Loss: 0.9075 | LM_LOSS: 0.3997 | LB_LOSS: 1.0155
[2026-05-24 14:39:10] Validation | Batch 20/1463 | Loss: 0.9175 | LM_LOSS: 0.4087 | LB_LOSS: 1.0176
[2026-05-24 14:39:12] Validation | Batch 30/1463 | Loss: 0.9230 | LM_LOSS: 0.4137 | LB_LOSS: 1.0185
[2026-05-24 14:39:13] Validation | Batch 40/1463 | Loss: 0.9323 | LM_LOSS: 0.4226 | LB_LOSS: 1.0193
[2026-05-24 14:39:15] Validation | Batch 50/1463 | Loss: 0.9390 | LM_LOSS: 0.4296 | LB_LOSS: 1.0188
[2026-05-24 14:39:17] Validation | Batch 60/1463 | Loss: 0.9409 | LM_LOSS: 0.4315 | LB_LOSS: 1.0189
[2026-05-24 14:39:19] Validation | Batch 70/1463 | Loss: 0.9403 | LM_LOSS: 0.4308 | LB_LOSS: 1.0190
[2026-05-24 14:39:21] Validation | Batch 80/1463 | Loss: 0.9412 | LM_LOSS: 0.4317 | LB_LOSS: 1.0191
[2026-05-24 14:39:22] Validation | Batch 90/1463 | Loss: 0.9411 | LM_LOSS: 0.4316 | LB_LOSS: 1.0191
[2026-05-24 14:39:24] Validation | Batch 100/1463 | Loss: 0.9423 | LM_LOSS: 0.4327 | LB_LOSS: 1.0191
[2026-05-24 14:39:26] Validation | Batch 110/1463 | Loss: 0.9410 | LM_LOSS: 0.4313 | LB_LOSS: 1.0194
[2026-05-24 14:39:27] Validation | Batch 120/1463 | Loss: 0.9426 | LM_LOSS: 0.4329 | LB_LOSS: 1.0194
[2026-05-24 14:39:28] Validation | Batch 130/1463 | Loss: 0.9459 | LM_LOSS: 0.4362 | LB_LOSS: 1.0194
[2026-05-24 14:39:30] Validation | Batch 140/1463 | Loss: 0.9470 | LM_LOSS: 0.4373 | LB_LOSS: 1.0195
[2026-05-24 14:39:32] Validation | Batch 150/1463 | Loss: 0.9449 | LM_LOSS: 0.4351 | LB_LOSS: 1.0196
[2026-05-24 14:39:34] Validation | Batch 160/1463 | Loss: 0.9461 | LM_LOSS: 0.4363 | LB_LOSS: 1.0195
[2026-05-24 14:39:35] Validation | Batch 170/1463 | Loss: 0.9461 | LM_LOSS: 0.4363 | LB_LOSS: 1.0196
[2026-05-24 14:39:37] Validation | Batch 180/1463 | Loss: 0.9469 | LM_LOSS: 0.4371 | LB_LOSS: 1.0196
[2026-05-24 14:39:39] Validation | Batch 190/1463 | Loss: 0.9475 | LM_LOSS: 0.4376 | LB_LOSS: 1.0196
[2026-05-24 14:39:40] Validation | Batch 200/1463 | Loss: 0.9468 | LM_LOSS: 0.4369 | LB_LOSS: 1.0197
[2026-05-24 14:39:42] Validation | Batch 210/1463 | Loss: 0.9473 | LM_LOSS: 0.4375 | LB_LOSS: 1.0197
[2026-05-24 14:39:44] Validation | Batch 220/1463 | Loss: 0.9463 | LM_LOSS: 0.4364 | LB_LOSS: 1.0198
[2026-05-24 14:39:46] Validation | Batch 230/1463 | Loss: 0.9480 | LM_LOSS: 0.4381 | LB_LOSS: 1.0197
[2026-05-24 14:39:47] Validation | Batch 240/1463 | Loss: 0.9485 | LM_LOSS: 0.4387 | LB_LOSS: 1.0196
[2026-05-24 14:39:49] Validation | Batch 250/1463 | Loss: 0.9473 | LM_LOSS: 0.4375 | LB_LOSS: 1.0197
[2026-05-24 14:39:51] Validation | Batch 260/1463 | Loss: 0.9493 | LM_LOSS: 0.4393 | LB_LOSS: 1.0198
[2026-05-24 14:39:52] Validation | Batch 270/1463 | Loss: 0.9482 | LM_LOSS: 0.4383 | LB_LOSS: 1.0198
[2026-05-24 14:39:54] Validation | Batch 280/1463 | Loss: 0.9493 | LM_LOSS: 0.4394 | LB_LOSS: 1.0198
[2026-05-24 14:39:56] Validation | Batch 290/1463 | Loss: 0.9482 | LM_LOSS: 0.4383 | LB_LOSS: 1.0198
[2026-05-24 14:39:57] Validation | Batch 300/1463 | Loss: 0.9491 | LM_LOSS: 0.4392 | LB_LOSS: 1.0199
[2026-05-24 14:39:59] Validation | Batch 310/1463 | Loss: 0.9500 | LM_LOSS: 0.4400 | LB_LOSS: 1.0199
[2026-05-24 14:40:00] Validation | Batch 320/1463 | Loss: 0.9483 | LM_LOSS: 0.4384 | LB_LOSS: 1.0198
[2026-05-24 14:40:02] Validation | Batch 330/1463 | Loss: 0.9483 | LM_LOSS: 0.4384 | LB_LOSS: 1.0198
[2026-05-24 14:40:04] Validation | Batch 340/1463 | Loss: 0.9479 | LM_LOSS: 0.4380 | LB_LOSS: 1.0198
[2026-05-24 14:40:05] Validation | Batch 350/1463 | Loss: 0.9481 | LM_LOSS: 0.4382 | LB_LOSS: 1.0198
[2026-05-24 14:40:07] Validation | Batch 360/1463 | Loss: 0.9482 | LM_LOSS: 0.4383 | LB_LOSS: 1.0198
[2026-05-24 14:40:08] Validation | Batch 370/1463 | Loss: 0.9482 | LM_LOSS: 0.4382 | LB_LOSS: 1.0198
[2026-05-24 14:40:10] Validation | Batch 380/1463 | Loss: 0.9479 | LM_LOSS: 0.4381 | LB_LOSS: 1.0197
[2026-05-24 14:40:12] Validation | Batch 390/1463 | Loss: 0.9491 | LM_LOSS: 0.4392 | LB_LOSS: 1.0197
[2026-05-24 14:40:13] Validation | Batch 400/1463 | Loss: 0.9489 | LM_LOSS: 0.4390 | LB_LOSS: 1.0198
[2026-05-24 14:40:15] Validation | Batch 410/1463 | Loss: 0.9487 | LM_LOSS: 0.4388 | LB_LOSS: 1.0198
[2026-05-24 14:40:17] Validation | Batch 420/1463 | Loss: 0.9491 | LM_LOSS: 0.4392 | LB_LOSS: 1.0199
[2026-05-24 14:40:19] Validation | Batch 430/1463 | Loss: 0.9489 | LM_LOSS: 0.4389 | LB_LOSS: 1.0200
[2026-05-24 14:40:20] Validation | Batch 440/1463 | Loss: 0.9493 | LM_LOSS: 0.4393 | LB_LOSS: 1.0200
[2026-05-24 14:40:21] Validation | Batch 450/1463 | Loss: 0.9489 | LM_LOSS: 0.4389 | LB_LOSS: 1.0200
[2026-05-24 14:40:23] Validation | Batch 460/1463 | Loss: 0.9490 | LM_LOSS: 0.4390 | LB_LOSS: 1.0200
[2026-05-24 14:40:25] Validation | Batch 470/1463 | Loss: 0.9496 | LM_LOSS: 0.4396 | LB_LOSS: 1.0200
[2026-05-24 14:40:27] Validation | Batch 480/1463 | Loss: 0.9493 | LM_LOSS: 0.4393 | LB_LOSS: 1.0200
[2026-05-24 14:40:28] Validation | Batch 490/1463 | Loss: 0.9490 | LM_LOSS: 0.4390 | LB_LOSS: 1.0199
[2026-05-24 14:40:30] Validation | Batch 500/1463 | Loss: 0.9486 | LM_LOSS: 0.4386 | LB_LOSS: 1.0200
[2026-05-24 14:40:32] Validation | Batch 510/1463 | Loss: 0.9481 | LM_LOSS: 0.4381 | LB_LOSS: 1.0200
[2026-05-24 14:40:33] Validation | Batch 520/1463 | Loss: 0.9478 | LM_LOSS: 0.4378 | LB_LOSS: 1.0200
[2026-05-24 14:40:35] Validation | Batch 530/1463 | Loss: 0.9482 | LM_LOSS: 0.4383 | LB_LOSS: 1.0200
[2026-05-24 14:40:36] Validation | Batch 540/1463 | Loss: 0.9486 | LM_LOSS: 0.4386 | LB_LOSS: 1.0200
[2026-05-24 14:40:38] Validation | Batch 550/1463 | Loss: 0.9484 | LM_LOSS: 0.4384 | LB_LOSS: 1.0200
[2026-05-24 14:40:40] Validation | Batch 560/1463 | Loss: 0.9488 | LM_LOSS: 0.4388 | LB_LOSS: 1.0201
[2026-05-24 14:40:41] Validation | Batch 570/1463 | Loss: 0.9488 | LM_LOSS: 0.4387 | LB_LOSS: 1.0201
[2026-05-24 14:40:43] Validation | Batch 580/1463 | Loss: 0.9485 | LM_LOSS: 0.4384 | LB_LOSS: 1.0201
[2026-05-24 14:40:45] Validation | Batch 590/1463 | Loss: 0.9484 | LM_LOSS: 0.4383 | LB_LOSS: 1.0202
[2026-05-24 14:40:47] Validation | Batch 600/1463 | Loss: 0.9487 | LM_LOSS: 0.4386 | LB_LOSS: 1.0202
[2026-05-24 14:40:48] Validation | Batch 610/1463 | Loss: 0.9487 | LM_LOSS: 0.4386 | LB_LOSS: 1.0202
[2026-05-24 14:40:50] Validation | Batch 620/1463 | Loss: 0.9482 | LM_LOSS: 0.4381 | LB_LOSS: 1.0202
[2026-05-24 14:40:52] Validation | Batch 630/1463 | Loss: 0.9480 | LM_LOSS: 0.4379 | LB_LOSS: 1.0202
[2026-05-24 14:40:53] Validation | Batch 640/1463 | Loss: 0.9478 | LM_LOSS: 0.4377 | LB_LOSS: 1.0203
[2026-05-24 14:40:55] Validation | Batch 650/1463 | Loss: 0.9472 | LM_LOSS: 0.4370 | LB_LOSS: 1.0203
[2026-05-24 14:40:56] Validation | Batch 660/1463 | Loss: 0.9466 | LM_LOSS: 0.4365 | LB_LOSS: 1.0202
[2026-05-24 14:40:58] Validation | Batch 670/1463 | Loss: 0.9463 | LM_LOSS: 0.4362 | LB_LOSS: 1.0202
[2026-05-24 14:40:59] Validation | Batch 680/1463 | Loss: 0.9463 | LM_LOSS: 0.4363 | LB_LOSS: 1.0202
[2026-05-24 14:41:01] Validation | Batch 690/1463 | Loss: 0.9466 | LM_LOSS: 0.4365 | LB_LOSS: 1.0202
[2026-05-24 14:41:03] Validation | Batch 700/1463 | Loss: 0.9467 | LM_LOSS: 0.4366 | LB_LOSS: 1.0202
[2026-05-24 14:41:04] Validation | Batch 710/1463 | Loss: 0.9470 | LM_LOSS: 0.4369 | LB_LOSS: 1.0202
[2026-05-24 14:41:06] Validation | Batch 720/1463 | Loss: 0.9478 | LM_LOSS: 0.4377 | LB_LOSS: 1.0203
[2026-05-24 14:41:07] Validation | Batch 730/1463 | Loss: 0.9477 | LM_LOSS: 0.4376 | LB_LOSS: 1.0203
[2026-05-24 14:41:09] Validation | Batch 740/1463 | Loss: 0.9475 | LM_LOSS: 0.4374 | LB_LOSS: 1.0202
[2026-05-24 14:41:10] Validation | Batch 750/1463 | Loss: 0.9473 | LM_LOSS: 0.4372 | LB_LOSS: 1.0202
[2026-05-24 14:41:12] Validation | Batch 760/1463 | Loss: 0.9470 | LM_LOSS: 0.4369 | LB_LOSS: 1.0202
[2026-05-24 14:41:13] Validation | Batch 770/1463 | Loss: 0.9468 | LM_LOSS: 0.4367 | LB_LOSS: 1.0202
[2026-05-24 14:41:15] Validation | Batch 780/1463 | Loss: 0.9468 | LM_LOSS: 0.4367 | LB_LOSS: 1.0202
[2026-05-24 14:41:16] Validation | Batch 790/1463 | Loss: 0.9471 | LM_LOSS: 0.4371 | LB_LOSS: 1.0202
[2026-05-24 14:41:18] Validation | Batch 800/1463 | Loss: 0.9471 | LM_LOSS: 0.4370 | LB_LOSS: 1.0202
[2026-05-24 14:41:19] Validation | Batch 810/1463 | Loss: 0.9467 | LM_LOSS: 0.4366 | LB_LOSS: 1.0201
[2026-05-24 14:41:21] Validation | Batch 820/1463 | Loss: 0.9468 | LM_LOSS: 0.4368 | LB_LOSS: 1.0201
[2026-05-24 14:41:23] Validation | Batch 830/1463 | Loss: 0.9470 | LM_LOSS: 0.4369 | LB_LOSS: 1.0201
[2026-05-24 14:41:24] Validation | Batch 840/1463 | Loss: 0.9469 | LM_LOSS: 0.4368 | LB_LOSS: 1.0202
[2026-05-24 14:41:26] Validation | Batch 850/1463 | Loss: 0.9470 | LM_LOSS: 0.4369 | LB_LOSS: 1.0202
[2026-05-24 14:41:28] Validation | Batch 860/1463 | Loss: 0.9469 | LM_LOSS: 0.4368 | LB_LOSS: 1.0202
[2026-05-24 14:41:29] Validation | Batch 870/1463 | Loss: 0.9472 | LM_LOSS: 0.4371 | LB_LOSS: 1.0202
[2026-05-24 14:41:31] Validation | Batch 880/1463 | Loss: 0.9464 | LM_LOSS: 0.4363 | LB_LOSS: 1.0202
[2026-05-24 14:41:33] Validation | Batch 890/1463 | Loss: 0.9464 | LM_LOSS: 0.4363 | LB_LOSS: 1.0202
[2026-05-24 14:41:34] Validation | Batch 900/1463 | Loss: 0.9460 | LM_LOSS: 0.4360 | LB_LOSS: 1.0202
[2026-05-24 14:41:36] Validation | Batch 910/1463 | Loss: 0.9461 | LM_LOSS: 0.4360 | LB_LOSS: 1.0202
[2026-05-24 14:41:38] Validation | Batch 920/1463 | Loss: 0.9463 | LM_LOSS: 0.4362 | LB_LOSS: 1.0202
[2026-05-24 14:41:39] Validation | Batch 930/1463 | Loss: 0.9459 | LM_LOSS: 0.4358 | LB_LOSS: 1.0202
[2026-05-24 14:41:41] Validation | Batch 940/1463 | Loss: 0.9456 | LM_LOSS: 0.4355 | LB_LOSS: 1.0202
[2026-05-24 14:41:43] Validation | Batch 950/1463 | Loss: 0.9459 | LM_LOSS: 0.4358 | LB_LOSS: 1.0202
[2026-05-24 14:41:44] Validation | Batch 960/1463 | Loss: 0.9460 | LM_LOSS: 0.4359 | LB_LOSS: 1.0201
[2026-05-24 14:41:46] Validation | Batch 970/1463 | Loss: 0.9462 | LM_LOSS: 0.4362 | LB_LOSS: 1.0201
[2026-05-24 14:41:48] Validation | Batch 980/1463 | Loss: 0.9465 | LM_LOSS: 0.4365 | LB_LOSS: 1.0201
[2026-05-24 14:41:49] Validation | Batch 990/1463 | Loss: 0.9466 | LM_LOSS: 0.4366 | LB_LOSS: 1.0201
[2026-05-24 14:41:51] Validation | Batch 1000/1463 | Loss: 0.9471 | LM_LOSS: 0.4371 | LB_LOSS: 1.0201
[2026-05-24 14:41:53] Validation | Batch 1010/1463 | Loss: 0.9472 | LM_LOSS: 0.4371 | LB_LOSS: 1.0202
[2026-05-24 14:41:54] Validation | Batch 1020/1463 | Loss: 0.9474 | LM_LOSS: 0.4373 | LB_LOSS: 1.0202
[2026-05-24 14:41:56] Validation | Batch 1030/1463 | Loss: 0.9479 | LM_LOSS: 0.4378 | LB_LOSS: 1.0202
[2026-05-24 14:41:58] Validation | Batch 1040/1463 | Loss: 0.9474 | LM_LOSS: 0.4373 | LB_LOSS: 1.0202
[2026-05-24 14:42:00] Validation | Batch 1050/1463 | Loss: 0.9472 | LM_LOSS: 0.4371 | LB_LOSS: 1.0202
[2026-05-24 14:42:01] Validation | Batch 1060/1463 | Loss: 0.9471 | LM_LOSS: 0.4370 | LB_LOSS: 1.0202
[2026-05-24 14:42:03] Validation | Batch 1070/1463 | Loss: 0.9471 | LM_LOSS: 0.4371 | LB_LOSS: 1.0202
[2026-05-24 14:42:05] Validation | Batch 1080/1463 | Loss: 0.9469 | LM_LOSS: 0.4368 | LB_LOSS: 1.0202
[2026-05-24 14:42:06] Validation | Batch 1090/1463 | Loss: 0.9468 | LM_LOSS: 0.4367 | LB_LOSS: 1.0201
[2026-05-24 14:42:08] Validation | Batch 1100/1463 | Loss: 0.9468 | LM_LOSS: 0.4367 | LB_LOSS: 1.0201
[2026-05-24 14:42:09] Validation | Batch 1110/1463 | Loss: 0.9468 | LM_LOSS: 0.4367 | LB_LOSS: 1.0201
[2026-05-24 14:42:11] Validation | Batch 1120/1463 | Loss: 0.9467 | LM_LOSS: 0.4366 | LB_LOSS: 1.0202
[2026-05-24 14:42:13] Validation | Batch 1130/1463 | Loss: 0.9463 | LM_LOSS: 0.4362 | LB_LOSS: 1.0201
[2026-05-24 14:42:14] Validation | Batch 1140/1463 | Loss: 0.9465 | LM_LOSS: 0.4364 | LB_LOSS: 1.0202
[2026-05-24 14:42:16] Validation | Batch 1150/1463 | Loss: 0.9464 | LM_LOSS: 0.4364 | LB_LOSS: 1.0201
[2026-05-24 14:42:18] Validation | Batch 1160/1463 | Loss: 0.9464 | LM_LOSS: 0.4364 | LB_LOSS: 1.0201
[2026-05-24 14:42:19] Validation | Batch 1170/1463 | Loss: 0.9463 | LM_LOSS: 0.4363 | LB_LOSS: 1.0201
[2026-05-24 14:42:21] Validation | Batch 1180/1463 | Loss: 0.9463 | LM_LOSS: 0.4362 | LB_LOSS: 1.0201
[2026-05-24 14:42:23] Validation | Batch 1190/1463 | Loss: 0.9465 | LM_LOSS: 0.4364 | LB_LOSS: 1.0201
[2026-05-24 14:42:24] Validation | Batch 1200/1463 | Loss: 0.9467 | LM_LOSS: 0.4366 | LB_LOSS: 1.0201
[2026-05-24 14:42:26] Validation | Batch 1210/1463 | Loss: 0.9470 | LM_LOSS: 0.4370 | LB_LOSS: 1.0201
[2026-05-24 14:42:28] Validation | Batch 1220/1463 | Loss: 0.9474 | LM_LOSS: 0.4373 | LB_LOSS: 1.0202
[2026-05-24 14:42:29] Validation | Batch 1230/1463 | Loss: 0.9473 | LM_LOSS: 0.4372 | LB_LOSS: 1.0202
[2026-05-24 14:42:31] Validation | Batch 1240/1463 | Loss: 0.9477 | LM_LOSS: 0.4376 | LB_LOSS: 1.0202
[2026-05-24 14:42:32] Validation | Batch 1250/1463 | Loss: 0.9479 | LM_LOSS: 0.4378 | LB_LOSS: 1.0202
[2026-05-24 14:42:34] Validation | Batch 1260/1463 | Loss: 0.9479 | LM_LOSS: 0.4378 | LB_LOSS: 1.0202
[2026-05-24 14:42:36] Validation | Batch 1270/1463 | Loss: 0.9477 | LM_LOSS: 0.4376 | LB_LOSS: 1.0202
[2026-05-24 14:42:38] Validation | Batch 1280/1463 | Loss: 0.9475 | LM_LOSS: 0.4374 | LB_LOSS: 1.0202
[2026-05-24 14:42:39] Validation | Batch 1290/1463 | Loss: 0.9475 | LM_LOSS: 0.4374 | LB_LOSS: 1.0202
[2026-05-24 14:42:41] Validation | Batch 1300/1463 | Loss: 0.9473 | LM_LOSS: 0.4372 | LB_LOSS: 1.0202
[2026-05-24 14:42:43] Validation | Batch 1310/1463 | Loss: 0.9472 | LM_LOSS: 0.4372 | LB_LOSS: 1.0202
[2026-05-24 14:42:44] Validation | Batch 1320/1463 | Loss: 0.9473 | LM_LOSS: 0.4372 | LB_LOSS: 1.0202
[2026-05-24 14:42:45] Validation | Batch 1330/1463 | Loss: 0.9472 | LM_LOSS: 0.4372 | LB_LOSS: 1.0201
[2026-05-24 14:42:47] Validation | Batch 1340/1463 | Loss: 0.9474 | LM_LOSS: 0.4373 | LB_LOSS: 1.0202
[2026-05-24 14:42:49] Validation | Batch 1350/1463 | Loss: 0.9474 | LM_LOSS: 0.4373 | LB_LOSS: 1.0201
[2026-05-24 14:42:51] Validation | Batch 1360/1463 | Loss: 0.9477 | LM_LOSS: 0.4376 | LB_LOSS: 1.0201
[2026-05-24 14:42:52] Validation | Batch 1370/1463 | Loss: 0.9481 | LM_LOSS: 0.4380 | LB_LOSS: 1.0202
[2026-05-24 14:42:54] Validation | Batch 1380/1463 | Loss: 0.9478 | LM_LOSS: 0.4378 | LB_LOSS: 1.0201
[2026-05-24 14:42:55] Validation | Batch 1390/1463 | Loss: 0.9477 | LM_LOSS: 0.4376 | LB_LOSS: 1.0202
[2026-05-24 14:42:57] Validation | Batch 1400/1463 | Loss: 0.9479 | LM_LOSS: 0.4378 | LB_LOSS: 1.0201
[2026-05-24 14:42:58] Validation | Batch 1410/1463 | Loss: 0.9481 | LM_LOSS: 0.4380 | LB_LOSS: 1.0201
[2026-05-24 14:43:00] Validation | Batch 1420/1463 | Loss: 0.9482 | LM_LOSS: 0.4381 | LB_LOSS: 1.0201
[2026-05-24 14:43:02] Validation | Batch 1430/1463 | Loss: 0.9483 | LM_LOSS: 0.4382 | LB_LOSS: 1.0201
[2026-05-24 14:43:03] Validation | Batch 1440/1463 | Loss: 0.9487 | LM_LOSS: 0.4386 | LB_LOSS: 1.0201
[2026-05-24 14:43:05] Validation | Batch 1450/1463 | Loss: 0.9484 | LM_LOSS: 0.4383 | LB_LOSS: 1.0201
[2026-05-24 14:43:07] Validation | Batch 1460/1463 | Loss: 0.9487 | LM_LOSS: 0.4386 | LB_LOSS: 1.0201
[2026-05-24 14:43:07] Validation | Batch 1463/1463 | Loss: 0.9486 | LM_LOSS: 0.4385 | LB_LOSS: 1.0201
[2026-05-24 14:43:07] Validation | Loss: 0.9486 | LM_LOSS: 0.4385 | LB_LOSS: 1.0201 | PPL: 1.55 | Time: 240.19s
[2026-05-24 14:43:18] Epoch 2 | Step 9010 | Loss: 0.9187 | LM: 0.4039 | LB: 1.0314 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:43:30] Epoch 2 | Step 9020 | Loss: 0.9187 | LM: 0.4039 | LB: 1.0314 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:43:41] Epoch 2 | Step 9030 | Loss: 0.9187 | LM: 0.4039 | LB: 1.0314 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:43:52] Epoch 2 | Step 9040 | Loss: 0.9187 | LM: 0.4039 | LB: 1.0313 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:44:03] Epoch 2 | Step 9050 | Loss: 0.9187 | LM: 0.4040 | LB: 1.0313 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:44:14] Epoch 2 | Step 9060 | Loss: 0.9187 | LM: 0.4041 | LB: 1.0313 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:44:25] Epoch 2 | Step 9070 | Loss: 0.9188 | LM: 0.4040 | LB: 1.0313 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:44:36] Epoch 2 | Step 9080 | Loss: 0.9188 | LM: 0.4040 | LB: 1.0313 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:44:47] Epoch 2 | Step 9090 | Loss: 0.9188 | LM: 0.4040 | LB: 1.0312 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:44:58] Epoch 2 | Step 9100 | Loss: 0.9188 | LM: 0.4041 | LB: 1.0312 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:45:09] Epoch 2 | Step 9110 | Loss: 0.9188 | LM: 0.4040 | LB: 1.0312 | CL0: 4.7 | CL1: 6.7 | HR0: 0.213/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:45:20] Epoch 2 | Step 9120 | Loss: 0.9189 | LM: 0.4041 | LB: 1.0312 | CL0: 4.7 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:45:31] Epoch 2 | Step 9130 | Loss: 0.9188 | LM: 0.4040 | LB: 1.0311 | CL0: 4.7 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:45:42] Epoch 2 | Step 9140 | Loss: 0.9190 | LM: 0.4042 | LB: 1.0312 | CL0: 4.7 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:45:53] Epoch 2 | Step 9150 | Loss: 0.9189 | LM: 0.4042 | LB: 1.0311 | CL0: 4.7 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:46:04] Epoch 2 | Step 9160 | Loss: 0.9189 | LM: 0.4042 | LB: 1.0311 | CL0: 4.7 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:46:16] Epoch 2 | Step 9170 | Loss: 0.9189 | LM: 0.4042 | LB: 1.0311 | CL0: 4.7 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:46:26] Epoch 2 | Step 9180 | Loss: 0.9189 | LM: 0.4041 | LB: 1.0311 | CL0: 4.7 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:46:38] Epoch 2 | Step 9190 | Loss: 0.9189 | LM: 0.4042 | LB: 1.0311 | CL0: 4.7 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:46:48] Epoch 2 | Step 9200 | Loss: 0.9189 | LM: 0.4042 | LB: 1.0310 | CL0: 4.7 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:47:00] Epoch 2 | Step 9210 | Loss: 0.9189 | LM: 0.4041 | LB: 1.0310 | CL0: 4.7 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.153/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:47:11] Epoch 2 | Step 9220 | Loss: 0.9189 | LM: 0.4041 | LB: 1.0310 | CL0: 4.7 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.152/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:47:22] Epoch 2 | Step 9230 | Loss: 0.9190 | LM: 0.4042 | LB: 1.0310 | CL0: 4.8 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.152/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:47:33] Epoch 2 | Step 9240 | Loss: 0.9190 | LM: 0.4042 | LB: 1.0310 | CL0: 4.8 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.152/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:47:44] Epoch 2 | Step 9250 | Loss: 0.9191 | LM: 0.4043 | LB: 1.0310 | CL0: 4.8 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.152/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:47:55] Epoch 2 | Step 9260 | Loss: 0.9191 | LM: 0.4043 | LB: 1.0310 | CL0: 4.8 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.152/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:48:06] Epoch 2 | Step 9270 | Loss: 0.9191 | LM: 0.4042 | LB: 1.0310 | CL0: 4.8 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.152/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:48:17] Epoch 2 | Step 9280 | Loss: 0.9191 | LM: 0.4043 | LB: 1.0310 | CL0: 4.8 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.152/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:48:28] Epoch 2 | Step 9290 | Loss: 0.9191 | LM: 0.4044 | LB: 1.0309 | CL0: 4.8 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.152/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:48:40] Epoch 2 | Step 9300 | Loss: 0.9192 | LM: 0.4045 | LB: 1.0309 | CL0: 4.8 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.152/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:48:51] Epoch 2 | Step 9310 | Loss: 0.9193 | LM: 0.4045 | LB: 1.0309 | CL0: 4.8 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.152/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:49:02] Epoch 2 | Step 9320 | Loss: 0.9194 | LM: 0.4046 | LB: 1.0309 | CL0: 4.8 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.152/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:49:13] Epoch 2 | Step 9330 | Loss: 0.9193 | LM: 0.4047 | LB: 1.0309 | CL0: 4.8 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.152/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:49:24] Epoch 2 | Step 9340 | Loss: 0.9194 | LM: 0.4047 | LB: 1.0308 | CL0: 4.8 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.152/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:49:35] Epoch 2 | Step 9350 | Loss: 0.9195 | LM: 0.4048 | LB: 1.0308 | CL0: 4.8 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.152/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:49:46] Epoch 2 | Step 9360 | Loss: 0.9195 | LM: 0.4048 | LB: 1.0308 | CL0: 4.8 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.152/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:49:57] Epoch 2 | Step 9370 | Loss: 0.9195 | LM: 0.4049 | LB: 1.0308 | CL0: 4.8 | CL1: 6.7 | HR0: 0.212/SR0: 0.192 | HR1: 0.152/SR1: 0.135 | LR: 1.00e-04
[2026-05-24 14:50:02] Epoch 2 completed in 6340.59s | Loss: 0.9195 | CL0: 4.8 | CL1: 6.7
[2026-05-24 14:50:02]
============================================================
[2026-05-24 14:50:02] EPOCH 3/3 (step 9374)
[2026-05-24 14:50:02] ============================================================
[2026-05-24 14:50:09] Epoch 3 | Step 9380 | Loss: 0.8990 | LM: 0.3603 | LB: 1.0197 | CL0: 5.2 | CL1: 7.0 | HR0: 0.194/SR0: 0.179 | HR1: 0.146/SR1: 0.131 | LR: 1.00e-04
[2026-05-24 14:50:19] Epoch 3 | Step 9390 | Loss: 0.9020 | LM: 0.3825 | LB: 1.0213 | CL0: 5.1 | CL1: 6.8 | HR0: 0.197/SR0: 0.181 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:50:30] Epoch 3 | Step 9400 | Loss: 0.8921 | LM: 0.3803 | LB: 1.0209 | CL0: 5.1 | CL1: 6.7 | HR0: 0.196/SR0: 0.181 | HR1: 0.151/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 14:50:40] Epoch 3 | Step 9410 | Loss: 0.8899 | LM: 0.3635 | LB: 1.0204 | CL0: 5.1 | CL1: 6.9 | HR0: 0.195/SR0: 0.180 | HR1: 0.147/SR1: 0.131 | LR: 1.00e-04
[2026-05-24 14:50:51] Epoch 3 | Step 9420 | Loss: 0.8786 | LM: 0.3494 | LB: 1.0197 | CL0: 5.2 | CL1: 7.0 | HR0: 0.195/SR0: 0.179 | HR1: 0.146/SR1: 0.129 | LR: 1.00e-04
[2026-05-24 14:51:01] Epoch 3 | Step 9430 | Loss: 0.8767 | LM: 0.3520 | LB: 1.0220 | CL0: 5.1 | CL1: 6.8 | HR0: 0.197/SR0: 0.181 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:51:12] Epoch 3 | Step 9440 | Loss: 0.8723 | LM: 0.3422 | LB: 1.0214 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:51:23] Epoch 3 | Step 9450 | Loss: 0.8779 | LM: 0.3509 | LB: 1.0220 | CL0: 5.1 | CL1: 6.9 | HR0: 0.198/SR0: 0.182 | HR1: 0.148/SR1: 0.132 | LR: 1.00e-04
[2026-05-24 14:51:35] Epoch 3 | Step 9460 | Loss: 0.8755 | LM: 0.3519 | LB: 1.0216 | CL0: 5.1 | CL1: 6.9 | HR0: 0.198/SR0: 0.181 | HR1: 0.147/SR1: 0.131 | LR: 1.00e-04
[2026-05-24 14:51:46] Epoch 3 | Step 9470 | Loss: 0.8722 | LM: 0.3504 | LB: 1.0219 | CL0: 5.1 | CL1: 6.9 | HR0: 0.198/SR0: 0.181 | HR1: 0.148/SR1: 0.132 | LR: 1.00e-04
[2026-05-24 14:51:58] Epoch 3 | Step 9480 | Loss: 0.8704 | LM: 0.3556 | LB: 1.0218 | CL0: 5.1 | CL1: 6.9 | HR0: 0.197/SR0: 0.181 | HR1: 0.149/SR1: 0.132 | LR: 1.00e-04
[2026-05-24 14:52:09] Epoch 3 | Step 9490 | Loss: 0.8692 | LM: 0.3516 | LB: 1.0220 | CL0: 5.1 | CL1: 6.8 | HR0: 0.197/SR0: 0.181 | HR1: 0.151/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 14:52:21] Epoch 3 | Step 9500 | Loss: 0.8696 | LM: 0.3535 | LB: 1.0222 | CL0: 5.1 | CL1: 6.8 | HR0: 0.198/SR0: 0.181 | HR1: 0.151/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 14:52:32] Epoch 3 | Step 9510 | Loss: 0.8669 | LM: 0.3475 | LB: 1.0233 | CL0: 5.1 | CL1: 6.8 | HR0: 0.199/SR0: 0.182 | HR1: 0.150/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 14:52:44] Epoch 3 | Step 9520 | Loss: 0.8675 | LM: 0.3498 | LB: 1.0236 | CL0: 5.1 | CL1: 6.8 | HR0: 0.199/SR0: 0.183 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:52:56] Epoch 3 | Step 9530 | Loss: 0.8692 | LM: 0.3545 | LB: 1.0237 | CL0: 5.1 | CL1: 6.8 | HR0: 0.200/SR0: 0.183 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:53:07] Epoch 3 | Step 9540 | Loss: 0.8678 | LM: 0.3513 | LB: 1.0233 | CL0: 5.1 | CL1: 6.8 | HR0: 0.199/SR0: 0.182 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:53:19] Epoch 3 | Step 9550 | Loss: 0.8680 | LM: 0.3502 | LB: 1.0233 | CL0: 5.1 | CL1: 6.8 | HR0: 0.199/SR0: 0.182 | HR1: 0.150/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 14:53:30] Epoch 3 | Step 9560 | Loss: 0.8656 | LM: 0.3469 | LB: 1.0233 | CL0: 5.1 | CL1: 6.8 | HR0: 0.199/SR0: 0.182 | HR1: 0.151/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 14:53:42] Epoch 3 | Step 9570 | Loss: 0.8664 | LM: 0.3520 | LB: 1.0235 | CL0: 5.1 | CL1: 6.8 | HR0: 0.199/SR0: 0.182 | HR1: 0.150/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 14:53:53] Epoch 3 | Step 9580 | Loss: 0.8667 | LM: 0.3525 | LB: 1.0236 | CL0: 5.1 | CL1: 6.8 | HR0: 0.199/SR0: 0.183 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:54:05] Epoch 3 | Step 9590 | Loss: 0.8656 | LM: 0.3517 | LB: 1.0232 | CL0: 5.1 | CL1: 6.8 | HR0: 0.199/SR0: 0.182 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:54:16] Epoch 3 | Step 9600 | Loss: 0.8665 | LM: 0.3498 | LB: 1.0230 | CL0: 5.1 | CL1: 6.8 | HR0: 0.199/SR0: 0.182 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:54:28] Epoch 3 | Step 9610 | Loss: 0.8654 | LM: 0.3469 | LB: 1.0230 | CL0: 5.1 | CL1: 6.8 | HR0: 0.199/SR0: 0.182 | HR1: 0.150/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 14:54:39] Epoch 3 | Step 9620 | Loss: 0.8643 | LM: 0.3495 | LB: 1.0229 | CL0: 5.1 | CL1: 6.7 | HR0: 0.198/SR0: 0.182 | HR1: 0.151/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 14:54:50] Epoch 3 | Step 9630 | Loss: 0.8654 | LM: 0.3510 | LB: 1.0228 | CL0: 5.1 | CL1: 6.8 | HR0: 0.198/SR0: 0.182 | HR1: 0.150/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 14:55:01] Epoch 3 | Step 9640 | Loss: 0.8648 | LM: 0.3511 | LB: 1.0227 | CL0: 5.1 | CL1: 6.8 | HR0: 0.198/SR0: 0.182 | HR1: 0.151/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 14:55:13] Epoch 3 | Step 9650 | Loss: 0.8638 | LM: 0.3495 | LB: 1.0225 | CL0: 5.1 | CL1: 6.8 | HR0: 0.198/SR0: 0.181 | HR1: 0.150/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 14:55:24] Epoch 3 | Step 9660 | Loss: 0.8633 | LM: 0.3504 | LB: 1.0224 | CL0: 5.1 | CL1: 6.8 | HR0: 0.198/SR0: 0.181 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:55:35] Epoch 3 | Step 9670 | Loss: 0.8634 | LM: 0.3507 | LB: 1.0223 | CL0: 5.1 | CL1: 6.8 | HR0: 0.198/SR0: 0.181 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:55:46] Epoch 3 | Step 9680 | Loss: 0.8629 | LM: 0.3510 | LB: 1.0221 | CL0: 5.1 | CL1: 6.8 | HR0: 0.197/SR0: 0.181 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:55:57] Epoch 3 | Step 9690 | Loss: 0.8631 | LM: 0.3502 | LB: 1.0219 | CL0: 5.1 | CL1: 6.8 | HR0: 0.197/SR0: 0.181 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:56:08] Epoch 3 | Step 9700 | Loss: 0.8655 | LM: 0.3515 | LB: 1.0220 | CL0: 5.1 | CL1: 6.8 | HR0: 0.197/SR0: 0.181 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:56:19] Epoch 3 | Step 9710 | Loss: 0.8657 | LM: 0.3511 | LB: 1.0218 | CL0: 5.1 | CL1: 6.9 | HR0: 0.197/SR0: 0.181 | HR1: 0.149/SR1: 0.132 | LR: 1.00e-04
[2026-05-24 14:56:30] Epoch 3 | Step 9720 | Loss: 0.8653 | LM: 0.3491 | LB: 1.0217 | CL0: 5.1 | CL1: 6.9 | HR0: 0.197/SR0: 0.181 | HR1: 0.148/SR1: 0.132 | LR: 1.00e-04
[2026-05-24 14:56:41] Epoch 3 | Step 9730 | Loss: 0.8652 | LM: 0.3510 | LB: 1.0215 | CL0: 5.1 | CL1: 6.9 | HR0: 0.197/SR0: 0.180 | HR1: 0.148/SR1: 0.132 | LR: 1.00e-04
[2026-05-24 14:56:52] Epoch 3 | Step 9740 | Loss: 0.8649 | LM: 0.3518 | LB: 1.0216 | CL0: 5.1 | CL1: 6.9 | HR0: 0.197/SR0: 0.181 | HR1: 0.148/SR1: 0.132 | LR: 1.00e-04
[2026-05-24 14:57:04] Epoch 3 | Step 9750 | Loss: 0.8648 | LM: 0.3503 | LB: 1.0218 | CL0: 5.1 | CL1: 6.9 | HR0: 0.197/SR0: 0.181 | HR1: 0.149/SR1: 0.132 | LR: 1.00e-04
[2026-05-24 14:57:15] Epoch 3 | Step 9760 | Loss: 0.8650 | LM: 0.3506 | LB: 1.0218 | CL0: 5.1 | CL1: 6.8 | HR0: 0.197/SR0: 0.181 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:57:26] Epoch 3 | Step 9770 | Loss: 0.8654 | LM: 0.3518 | LB: 1.0218 | CL0: 5.1 | CL1: 6.8 | HR0: 0.197/SR0: 0.181 | HR1: 0.149/SR1: 0.132 | LR: 1.00e-04
[2026-05-24 14:57:37] Epoch 3 | Step 9780 | Loss: 0.8657 | LM: 0.3516 | LB: 1.0217 | CL0: 5.1 | CL1: 6.8 | HR0: 0.197/SR0: 0.181 | HR1: 0.149/SR1: 0.132 | LR: 1.00e-04
[2026-05-24 14:57:48] Epoch 3 | Step 9790 | Loss: 0.8655 | LM: 0.3531 | LB: 1.0216 | CL0: 5.1 | CL1: 6.8 | HR0: 0.197/SR0: 0.180 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:57:59] Epoch 3 | Step 9800 | Loss: 0.8651 | LM: 0.3530 | LB: 1.0216 | CL0: 5.1 | CL1: 6.8 | HR0: 0.197/SR0: 0.180 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:58:11] Epoch 3 | Step 9810 | Loss: 0.8649 | LM: 0.3527 | LB: 1.0216 | CL0: 5.1 | CL1: 6.8 | HR0: 0.197/SR0: 0.180 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:58:22] Epoch 3 | Step 9820 | Loss: 0.8645 | LM: 0.3528 | LB: 1.0216 | CL0: 5.1 | CL1: 6.8 | HR0: 0.197/SR0: 0.180 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:58:33] Epoch 3 | Step 9830 | Loss: 0.8648 | LM: 0.3539 | LB: 1.0216 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:58:44] Epoch 3 | Step 9840 | Loss: 0.8652 | LM: 0.3539 | LB: 1.0217 | CL0: 5.1 | CL1: 6.8 | HR0: 0.197/SR0: 0.180 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:58:55] Epoch 3 | Step 9850 | Loss: 0.8651 | LM: 0.3523 | LB: 1.0215 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:59:06] Epoch 3 | Step 9860 | Loss: 0.8656 | LM: 0.3519 | LB: 1.0214 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:59:17] Epoch 3 | Step 9870 | Loss: 0.8659 | LM: 0.3513 | LB: 1.0214 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:59:28] Epoch 3 | Step 9880 | Loss: 0.8661 | LM: 0.3523 | LB: 1.0215 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:59:39] Epoch 3 | Step 9890 | Loss: 0.8662 | LM: 0.3519 | LB: 1.0214 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 14:59:50] Epoch 3 | Step 9900 | Loss: 0.8659 | LM: 0.3517 | LB: 1.0214 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:00:01] Epoch 3 | Step 9910 | Loss: 0.8664 | LM: 0.3531 | LB: 1.0213 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:00:12] Epoch 3 | Step 9920 | Loss: 0.8660 | LM: 0.3534 | LB: 1.0213 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:00:23] Epoch 3 | Step 9930 | Loss: 0.8651 | LM: 0.3515 | LB: 1.0213 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:00:34] Epoch 3 | Step 9940 | Loss: 0.8654 | LM: 0.3522 | LB: 1.0213 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:00:45] Epoch 3 | Step 9950 | Loss: 0.8658 | LM: 0.3530 | LB: 1.0213 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:00:56] Epoch 3 | Step 9960 | Loss: 0.8658 | LM: 0.3534 | LB: 1.0213 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:01:07] Epoch 3 | Step 9970 | Loss: 0.8655 | LM: 0.3530 | LB: 1.0212 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:01:18] Epoch 3 | Step 9980 | Loss: 0.8654 | LM: 0.3527 | LB: 1.0212 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:01:28] Epoch 3 | Step 9990 | Loss: 0.8658 | LM: 0.3535 | LB: 1.0211 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:01:39] Epoch 3 | Step 10000 | Loss: 0.8658 | LM: 0.3538 | LB: 1.0211 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:01:40] Validation | Batch 10/1463 | Loss: 0.9291 | LM_LOSS: 0.4222 | LB_LOSS: 1.0138
[2026-05-24 15:01:42] Validation | Batch 20/1463 | Loss: 0.9362 | LM_LOSS: 0.4284 | LB_LOSS: 1.0156
[2026-05-24 15:01:44] Validation | Batch 30/1463 | Loss: 0.9402 | LM_LOSS: 0.4319 | LB_LOSS: 1.0165
[2026-05-24 15:01:45] Validation | Batch 40/1463 | Loss: 0.9500 | LM_LOSS: 0.4414 | LB_LOSS: 1.0172
[2026-05-24 15:01:46] Validation | Batch 50/1463 | Loss: 0.9560 | LM_LOSS: 0.4476 | LB_LOSS: 1.0167
[2026-05-24 15:01:48] Validation | Batch 60/1463 | Loss: 0.9580 | LM_LOSS: 0.4496 | LB_LOSS: 1.0169
[2026-05-24 15:01:50] Validation | Batch 70/1463 | Loss: 0.9560 | LM_LOSS: 0.4475 | LB_LOSS: 1.0170
[2026-05-24 15:01:52] Validation | Batch 80/1463 | Loss: 0.9560 | LM_LOSS: 0.4475 | LB_LOSS: 1.0171
[2026-05-24 15:01:53] Validation | Batch 90/1463 | Loss: 0.9554 | LM_LOSS: 0.4469 | LB_LOSS: 1.0170
[2026-05-24 15:01:55] Validation | Batch 100/1463 | Loss: 0.9560 | LM_LOSS: 0.4475 | LB_LOSS: 1.0170
[2026-05-24 15:01:57] Validation | Batch 110/1463 | Loss: 0.9544 | LM_LOSS: 0.4458 | LB_LOSS: 1.0173
[2026-05-24 15:01:58] Validation | Batch 120/1463 | Loss: 0.9563 | LM_LOSS: 0.4477 | LB_LOSS: 1.0173
[2026-05-24 15:01:59] Validation | Batch 130/1463 | Loss: 0.9600 | LM_LOSS: 0.4513 | LB_LOSS: 1.0173
[2026-05-24 15:02:01] Validation | Batch 140/1463 | Loss: 0.9612 | LM_LOSS: 0.4525 | LB_LOSS: 1.0173
[2026-05-24 15:02:03] Validation | Batch 150/1463 | Loss: 0.9587 | LM_LOSS: 0.4499 | LB_LOSS: 1.0175
[2026-05-24 15:02:04] Validation | Batch 160/1463 | Loss: 0.9599 | LM_LOSS: 0.4512 | LB_LOSS: 1.0174
[2026-05-24 15:02:06] Validation | Batch 170/1463 | Loss: 0.9597 | LM_LOSS: 0.4510 | LB_LOSS: 1.0175
[2026-05-24 15:02:08] Validation | Batch 180/1463 | Loss: 0.9605 | LM_LOSS: 0.4518 | LB_LOSS: 1.0175
[2026-05-24 15:02:09] Validation | Batch 190/1463 | Loss: 0.9609 | LM_LOSS: 0.4522 | LB_LOSS: 1.0175
[2026-05-24 15:02:11] Validation | Batch 200/1463 | Loss: 0.9608 | LM_LOSS: 0.4520 | LB_LOSS: 1.0175
[2026-05-24 15:02:12] Validation | Batch 210/1463 | Loss: 0.9616 | LM_LOSS: 0.4528 | LB_LOSS: 1.0176
[2026-05-24 15:02:14] Validation | Batch 220/1463 | Loss: 0.9609 | LM_LOSS: 0.4521 | LB_LOSS: 1.0177
[2026-05-24 15:02:16] Validation | Batch 230/1463 | Loss: 0.9622 | LM_LOSS: 0.4534 | LB_LOSS: 1.0175
[2026-05-24 15:02:17] Validation | Batch 240/1463 | Loss: 0.9624 | LM_LOSS: 0.4537 | LB_LOSS: 1.0175
[2026-05-24 15:02:19] Validation | Batch 250/1463 | Loss: 0.9609 | LM_LOSS: 0.4522 | LB_LOSS: 1.0175
[2026-05-24 15:02:21] Validation | Batch 260/1463 | Loss: 0.9632 | LM_LOSS: 0.4543 | LB_LOSS: 1.0177
[2026-05-24 15:02:22] Validation | Batch 270/1463 | Loss: 0.9621 | LM_LOSS: 0.4533 | LB_LOSS: 1.0177
[2026-05-24 15:02:24] Validation | Batch 280/1463 | Loss: 0.9632 | LM_LOSS: 0.4544 | LB_LOSS: 1.0177
[2026-05-24 15:02:26] Validation | Batch 290/1463 | Loss: 0.9619 | LM_LOSS: 0.4531 | LB_LOSS: 1.0177
[2026-05-24 15:02:27] Validation | Batch 300/1463 | Loss: 0.9627 | LM_LOSS: 0.4538 | LB_LOSS: 1.0178
[2026-05-24 15:02:29] Validation | Batch 310/1463 | Loss: 0.9636 | LM_LOSS: 0.4547 | LB_LOSS: 1.0178
[2026-05-24 15:02:30] Validation | Batch 320/1463 | Loss: 0.9618 | LM_LOSS: 0.4530 | LB_LOSS: 1.0176
[2026-05-24 15:02:32] Validation | Batch 330/1463 | Loss: 0.9617 | LM_LOSS: 0.4529 | LB_LOSS: 1.0177
[2026-05-24 15:02:33] Validation | Batch 340/1463 | Loss: 0.9613 | LM_LOSS: 0.4525 | LB_LOSS: 1.0177
[2026-05-24 15:02:35] Validation | Batch 350/1463 | Loss: 0.9615 | LM_LOSS: 0.4527 | LB_LOSS: 1.0176
[2026-05-24 15:02:36] Validation | Batch 360/1463 | Loss: 0.9616 | LM_LOSS: 0.4528 | LB_LOSS: 1.0177
[2026-05-24 15:02:38] Validation | Batch 370/1463 | Loss: 0.9617 | LM_LOSS: 0.4528 | LB_LOSS: 1.0177
[2026-05-24 15:02:39] Validation | Batch 380/1463 | Loss: 0.9614 | LM_LOSS: 0.4526 | LB_LOSS: 1.0176
[2026-05-24 15:02:41] Validation | Batch 390/1463 | Loss: 0.9625 | LM_LOSS: 0.4537 | LB_LOSS: 1.0176
[2026-05-24 15:02:42] Validation | Batch 400/1463 | Loss: 0.9622 | LM_LOSS: 0.4534 | LB_LOSS: 1.0176
[2026-05-24 15:02:44] Validation | Batch 410/1463 | Loss: 0.9620 | LM_LOSS: 0.4532 | LB_LOSS: 1.0177
[2026-05-24 15:02:45] Validation | Batch 420/1463 | Loss: 0.9624 | LM_LOSS: 0.4536 | LB_LOSS: 1.0177
[2026-05-24 15:02:47] Validation | Batch 430/1463 | Loss: 0.9622 | LM_LOSS: 0.4533 | LB_LOSS: 1.0178
[2026-05-24 15:02:49] Validation | Batch 440/1463 | Loss: 0.9626 | LM_LOSS: 0.4537 | LB_LOSS: 1.0178
[2026-05-24 15:02:50] Validation | Batch 450/1463 | Loss: 0.9622 | LM_LOSS: 0.4533 | LB_LOSS: 1.0179
[2026-05-24 15:02:52] Validation | Batch 460/1463 | Loss: 0.9622 | LM_LOSS: 0.4533 | LB_LOSS: 1.0178
[2026-05-24 15:02:53] Validation | Batch 470/1463 | Loss: 0.9627 | LM_LOSS: 0.4538 | LB_LOSS: 1.0178
[2026-05-24 15:02:55] Validation | Batch 480/1463 | Loss: 0.9624 | LM_LOSS: 0.4535 | LB_LOSS: 1.0178
[2026-05-24 15:02:57] Validation | Batch 490/1463 | Loss: 0.9620 | LM_LOSS: 0.4531 | LB_LOSS: 1.0178
[2026-05-24 15:02:59] Validation | Batch 500/1463 | Loss: 0.9618 | LM_LOSS: 0.4529 | LB_LOSS: 1.0178
[2026-05-24 15:03:00] Validation | Batch 510/1463 | Loss: 0.9612 | LM_LOSS: 0.4523 | LB_LOSS: 1.0178
[2026-05-24 15:03:02] Validation | Batch 520/1463 | Loss: 0.9610 | LM_LOSS: 0.4520 | LB_LOSS: 1.0179
[2026-05-24 15:03:03] Validation | Batch 530/1463 | Loss: 0.9615 | LM_LOSS: 0.4526 | LB_LOSS: 1.0178
[2026-05-24 15:03:04] Validation | Batch 540/1463 | Loss: 0.9619 | LM_LOSS: 0.4530 | LB_LOSS: 1.0179
[2026-05-24 15:03:06] Validation | Batch 550/1463 | Loss: 0.9617 | LM_LOSS: 0.4527 | LB_LOSS: 1.0179
[2026-05-24 15:03:07] Validation | Batch 560/1463 | Loss: 0.9623 | LM_LOSS: 0.4533 | LB_LOSS: 1.0179
[2026-05-24 15:03:09] Validation | Batch 570/1463 | Loss: 0.9623 | LM_LOSS: 0.4533 | LB_LOSS: 1.0179
[2026-05-24 15:03:11] Validation | Batch 580/1463 | Loss: 0.9619 | LM_LOSS: 0.4529 | LB_LOSS: 1.0179
[2026-05-24 15:03:12] Validation | Batch 590/1463 | Loss: 0.9618 | LM_LOSS: 0.4528 | LB_LOSS: 1.0180
[2026-05-24 15:03:14] Validation | Batch 600/1463 | Loss: 0.9621 | LM_LOSS: 0.4531 | LB_LOSS: 1.0180
[2026-05-24 15:03:16] Validation | Batch 610/1463 | Loss: 0.9621 | LM_LOSS: 0.4531 | LB_LOSS: 1.0180
[2026-05-24 15:03:17] Validation | Batch 620/1463 | Loss: 0.9617 | LM_LOSS: 0.4527 | LB_LOSS: 1.0180
[2026-05-24 15:03:19] Validation | Batch 630/1463 | Loss: 0.9615 | LM_LOSS: 0.4525 | LB_LOSS: 1.0181
[2026-05-24 15:03:20] Validation | Batch 640/1463 | Loss: 0.9615 | LM_LOSS: 0.4524 | LB_LOSS: 1.0181
[2026-05-24 15:03:22] Validation | Batch 650/1463 | Loss: 0.9608 | LM_LOSS: 0.4518 | LB_LOSS: 1.0181
[2026-05-24 15:03:23] Validation | Batch 660/1463 | Loss: 0.9603 | LM_LOSS: 0.4512 | LB_LOSS: 1.0181
[2026-05-24 15:03:25] Validation | Batch 670/1463 | Loss: 0.9599 | LM_LOSS: 0.4508 | LB_LOSS: 1.0181
[2026-05-24 15:03:26] Validation | Batch 680/1463 | Loss: 0.9600 | LM_LOSS: 0.4510 | LB_LOSS: 1.0180
[2026-05-24 15:03:28] Validation | Batch 690/1463 | Loss: 0.9604 | LM_LOSS: 0.4514 | LB_LOSS: 1.0180
[2026-05-24 15:03:29] Validation | Batch 700/1463 | Loss: 0.9605 | LM_LOSS: 0.4515 | LB_LOSS: 1.0180
[2026-05-24 15:03:31] Validation | Batch 710/1463 | Loss: 0.9608 | LM_LOSS: 0.4517 | LB_LOSS: 1.0181
[2026-05-24 15:03:33] Validation | Batch 720/1463 | Loss: 0.9615 | LM_LOSS: 0.4524 | LB_LOSS: 1.0181
[2026-05-24 15:03:34] Validation | Batch 730/1463 | Loss: 0.9614 | LM_LOSS: 0.4524 | LB_LOSS: 1.0181
[2026-05-24 15:03:35] Validation | Batch 740/1463 | Loss: 0.9612 | LM_LOSS: 0.4522 | LB_LOSS: 1.0181
[2026-05-24 15:03:37] Validation | Batch 750/1463 | Loss: 0.9610 | LM_LOSS: 0.4520 | LB_LOSS: 1.0181
[2026-05-24 15:03:38] Validation | Batch 760/1463 | Loss: 0.9607 | LM_LOSS: 0.4516 | LB_LOSS: 1.0180
[2026-05-24 15:03:39] Validation | Batch 770/1463 | Loss: 0.9606 | LM_LOSS: 0.4515 | LB_LOSS: 1.0181
[2026-05-24 15:03:41] Validation | Batch 780/1463 | Loss: 0.9605 | LM_LOSS: 0.4515 | LB_LOSS: 1.0180
[2026-05-24 15:03:42] Validation | Batch 790/1463 | Loss: 0.9608 | LM_LOSS: 0.4518 | LB_LOSS: 1.0180
[2026-05-24 15:03:44] Validation | Batch 800/1463 | Loss: 0.9608 | LM_LOSS: 0.4518 | LB_LOSS: 1.0180
[2026-05-24 15:03:45] Validation | Batch 810/1463 | Loss: 0.9604 | LM_LOSS: 0.4514 | LB_LOSS: 1.0180
[2026-05-24 15:03:47] Validation | Batch 820/1463 | Loss: 0.9605 | LM_LOSS: 0.4515 | LB_LOSS: 1.0179
[2026-05-24 15:03:48] Validation | Batch 830/1463 | Loss: 0.9606 | LM_LOSS: 0.4517 | LB_LOSS: 1.0180
[2026-05-24 15:03:50] Validation | Batch 840/1463 | Loss: 0.9605 | LM_LOSS: 0.4515 | LB_LOSS: 1.0180
[2026-05-24 15:03:52] Validation | Batch 850/1463 | Loss: 0.9607 | LM_LOSS: 0.4517 | LB_LOSS: 1.0180
[2026-05-24 15:03:53] Validation | Batch 860/1463 | Loss: 0.9607 | LM_LOSS: 0.4517 | LB_LOSS: 1.0180
[2026-05-24 15:03:55] Validation | Batch 870/1463 | Loss: 0.9609 | LM_LOSS: 0.4519 | LB_LOSS: 1.0181
[2026-05-24 15:03:56] Validation | Batch 880/1463 | Loss: 0.9601 | LM_LOSS: 0.4511 | LB_LOSS: 1.0180
[2026-05-24 15:03:58] Validation | Batch 890/1463 | Loss: 0.9601 | LM_LOSS: 0.4511 | LB_LOSS: 1.0180
[2026-05-24 15:03:59] Validation | Batch 900/1463 | Loss: 0.9597 | LM_LOSS: 0.4507 | LB_LOSS: 1.0180
[2026-05-24 15:04:01] Validation | Batch 910/1463 | Loss: 0.9597 | LM_LOSS: 0.4507 | LB_LOSS: 1.0180
[2026-05-24 15:04:03] Validation | Batch 920/1463 | Loss: 0.9600 | LM_LOSS: 0.4510 | LB_LOSS: 1.0180
[2026-05-24 15:04:04] Validation | Batch 930/1463 | Loss: 0.9595 | LM_LOSS: 0.4505 | LB_LOSS: 1.0180
[2026-05-24 15:04:06] Validation | Batch 940/1463 | Loss: 0.9592 | LM_LOSS: 0.4502 | LB_LOSS: 1.0180
[2026-05-24 15:04:08] Validation | Batch 950/1463 | Loss: 0.9595 | LM_LOSS: 0.4505 | LB_LOSS: 1.0180
[2026-05-24 15:04:09] Validation | Batch 960/1463 | Loss: 0.9596 | LM_LOSS: 0.4507 | LB_LOSS: 1.0180
[2026-05-24 15:04:11] Validation | Batch 970/1463 | Loss: 0.9600 | LM_LOSS: 0.4510 | LB_LOSS: 1.0179
[2026-05-24 15:04:13] Validation | Batch 980/1463 | Loss: 0.9603 | LM_LOSS: 0.4513 | LB_LOSS: 1.0179
[2026-05-24 15:04:14] Validation | Batch 990/1463 | Loss: 0.9604 | LM_LOSS: 0.4514 | LB_LOSS: 1.0179
[2026-05-24 15:04:15] Validation | Batch 1000/1463 | Loss: 0.9610 | LM_LOSS: 0.4520 | LB_LOSS: 1.0179
[2026-05-24 15:04:17] Validation | Batch 1010/1463 | Loss: 0.9610 | LM_LOSS: 0.4520 | LB_LOSS: 1.0180
[2026-05-24 15:04:19] Validation | Batch 1020/1463 | Loss: 0.9614 | LM_LOSS: 0.4524 | LB_LOSS: 1.0180
[2026-05-24 15:04:21] Validation | Batch 1030/1463 | Loss: 0.9619 | LM_LOSS: 0.4529 | LB_LOSS: 1.0180
[2026-05-24 15:04:22] Validation | Batch 1040/1463 | Loss: 0.9613 | LM_LOSS: 0.4523 | LB_LOSS: 1.0180
[2026-05-24 15:04:24] Validation | Batch 1050/1463 | Loss: 0.9611 | LM_LOSS: 0.4521 | LB_LOSS: 1.0180
[2026-05-24 15:04:25] Validation | Batch 1060/1463 | Loss: 0.9610 | LM_LOSS: 0.4520 | LB_LOSS: 1.0180
[2026-05-24 15:04:27] Validation | Batch 1070/1463 | Loss: 0.9612 | LM_LOSS: 0.4522 | LB_LOSS: 1.0180
[2026-05-24 15:04:28] Validation | Batch 1080/1463 | Loss: 0.9609 | LM_LOSS: 0.4519 | LB_LOSS: 1.0180
[2026-05-24 15:04:30] Validation | Batch 1090/1463 | Loss: 0.9608 | LM_LOSS: 0.4518 | LB_LOSS: 1.0180
[2026-05-24 15:04:32] Validation | Batch 1100/1463 | Loss: 0.9607 | LM_LOSS: 0.4517 | LB_LOSS: 1.0180
[2026-05-24 15:04:33] Validation | Batch 1110/1463 | Loss: 0.9608 | LM_LOSS: 0.4518 | LB_LOSS: 1.0180
[2026-05-24 15:04:35] Validation | Batch 1120/1463 | Loss: 0.9606 | LM_LOSS: 0.4516 | LB_LOSS: 1.0180
[2026-05-24 15:04:36] Validation | Batch 1130/1463 | Loss: 0.9602 | LM_LOSS: 0.4512 | LB_LOSS: 1.0180
[2026-05-24 15:04:38] Validation | Batch 1140/1463 | Loss: 0.9604 | LM_LOSS: 0.4514 | LB_LOSS: 1.0180
[2026-05-24 15:04:40] Validation | Batch 1150/1463 | Loss: 0.9604 | LM_LOSS: 0.4514 | LB_LOSS: 1.0180
[2026-05-24 15:04:41] Validation | Batch 1160/1463 | Loss: 0.9603 | LM_LOSS: 0.4513 | LB_LOSS: 1.0180
[2026-05-24 15:04:43] Validation | Batch 1170/1463 | Loss: 0.9602 | LM_LOSS: 0.4512 | LB_LOSS: 1.0180
[2026-05-24 15:04:44] Validation | Batch 1180/1463 | Loss: 0.9601 | LM_LOSS: 0.4511 | LB_LOSS: 1.0180
[2026-05-24 15:04:46] Validation | Batch 1190/1463 | Loss: 0.9603 | LM_LOSS: 0.4513 | LB_LOSS: 1.0180
[2026-05-24 15:04:48] Validation | Batch 1200/1463 | Loss: 0.9604 | LM_LOSS: 0.4514 | LB_LOSS: 1.0180
[2026-05-24 15:04:49] Validation | Batch 1210/1463 | Loss: 0.9608 | LM_LOSS: 0.4518 | LB_LOSS: 1.0180
[2026-05-24 15:04:51] Validation | Batch 1220/1463 | Loss: 0.9612 | LM_LOSS: 0.4522 | LB_LOSS: 1.0180
[2026-05-24 15:04:52] Validation | Batch 1230/1463 | Loss: 0.9611 | LM_LOSS: 0.4521 | LB_LOSS: 1.0180
[2026-05-24 15:04:54] Validation | Batch 1240/1463 | Loss: 0.9615 | LM_LOSS: 0.4525 | LB_LOSS: 1.0180
[2026-05-24 15:04:55] Validation | Batch 1250/1463 | Loss: 0.9617 | LM_LOSS: 0.4527 | LB_LOSS: 1.0180
[2026-05-24 15:04:57] Validation | Batch 1260/1463 | Loss: 0.9617 | LM_LOSS: 0.4527 | LB_LOSS: 1.0180
[2026-05-24 15:04:59] Validation | Batch 1270/1463 | Loss: 0.9616 | LM_LOSS: 0.4525 | LB_LOSS: 1.0180
[2026-05-24 15:05:00] Validation | Batch 1280/1463 | Loss: 0.9613 | LM_LOSS: 0.4523 | LB_LOSS: 1.0180
[2026-05-24 15:05:02] Validation | Batch 1290/1463 | Loss: 0.9614 | LM_LOSS: 0.4524 | LB_LOSS: 1.0180
[2026-05-24 15:05:03] Validation | Batch 1300/1463 | Loss: 0.9612 | LM_LOSS: 0.4521 | LB_LOSS: 1.0180
[2026-05-24 15:05:05] Validation | Batch 1310/1463 | Loss: 0.9611 | LM_LOSS: 0.4521 | LB_LOSS: 1.0180
[2026-05-24 15:05:06] Validation | Batch 1320/1463 | Loss: 0.9611 | LM_LOSS: 0.4521 | LB_LOSS: 1.0180
[2026-05-24 15:05:08] Validation | Batch 1330/1463 | Loss: 0.9611 | LM_LOSS: 0.4521 | LB_LOSS: 1.0180
[2026-05-24 15:05:09] Validation | Batch 1340/1463 | Loss: 0.9612 | LM_LOSS: 0.4522 | LB_LOSS: 1.0180
[2026-05-24 15:05:11] Validation | Batch 1350/1463 | Loss: 0.9613 | LM_LOSS: 0.4523 | LB_LOSS: 1.0180
[2026-05-24 15:05:13] Validation | Batch 1360/1463 | Loss: 0.9615 | LM_LOSS: 0.4526 | LB_LOSS: 1.0180
[2026-05-24 15:05:14] Validation | Batch 1370/1463 | Loss: 0.9620 | LM_LOSS: 0.4530 | LB_LOSS: 1.0180
[2026-05-24 15:05:16] Validation | Batch 1380/1463 | Loss: 0.9618 | LM_LOSS: 0.4528 | LB_LOSS: 1.0180
[2026-05-24 15:05:17] Validation | Batch 1390/1463 | Loss: 0.9616 | LM_LOSS: 0.4526 | LB_LOSS: 1.0180
[2026-05-24 15:05:19] Validation | Batch 1400/1463 | Loss: 0.9619 | LM_LOSS: 0.4529 | LB_LOSS: 1.0180
[2026-05-24 15:05:20] Validation | Batch 1410/1463 | Loss: 0.9621 | LM_LOSS: 0.4531 | LB_LOSS: 1.0180
[2026-05-24 15:05:22] Validation | Batch 1420/1463 | Loss: 0.9621 | LM_LOSS: 0.4532 | LB_LOSS: 1.0180
[2026-05-24 15:05:23] Validation | Batch 1430/1463 | Loss: 0.9622 | LM_LOSS: 0.4532 | LB_LOSS: 1.0180
[2026-05-24 15:05:25] Validation | Batch 1440/1463 | Loss: 0.9626 | LM_LOSS: 0.4536 | LB_LOSS: 1.0180
[2026-05-24 15:05:27] Validation | Batch 1450/1463 | Loss: 0.9622 | LM_LOSS: 0.4533 | LB_LOSS: 1.0179
[2026-05-24 15:05:28] Validation | Batch 1460/1463 | Loss: 0.9625 | LM_LOSS: 0.4536 | LB_LOSS: 1.0179
[2026-05-24 15:05:29] Validation | Batch 1463/1463 | Loss: 0.9624 | LM_LOSS: 0.4535 | LB_LOSS: 1.0179
[2026-05-24 15:05:29] Validation | Loss: 0.9624 | LM_LOSS: 0.4535 | LB_LOSS: 1.0179 | PPL: 1.57 | Time: 229.61s
[2026-05-24 15:05:40] Epoch 3 | Step 10010 | Loss: 0.8657 | LM: 0.3541 | LB: 1.0210 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:05:52] Epoch 3 | Step 10020 | Loss: 0.8654 | LM: 0.3544 | LB: 1.0210 | CL0: 5.1 | CL1: 6.8 | HR0: 0.196/SR0: 0.180 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:06:03] Epoch 3 | Step 10030 | Loss: 0.8650 | LM: 0.3540 | LB: 1.0209 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:06:14] Epoch 3 | Step 10040 | Loss: 0.8648 | LM: 0.3537 | LB: 1.0209 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:06:25] Epoch 3 | Step 10050 | Loss: 0.8647 | LM: 0.3534 | LB: 1.0209 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:06:36] Epoch 3 | Step 10060 | Loss: 0.8649 | LM: 0.3537 | LB: 1.0208 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:06:47] Epoch 3 | Step 10070 | Loss: 0.8650 | LM: 0.3541 | LB: 1.0209 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:06:58] Epoch 3 | Step 10080 | Loss: 0.8656 | LM: 0.3553 | LB: 1.0208 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:07:09] Epoch 3 | Step 10090 | Loss: 0.8661 | LM: 0.3552 | LB: 1.0209 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:07:20] Epoch 3 | Step 10100 | Loss: 0.8657 | LM: 0.3546 | LB: 1.0209 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:07:31] Epoch 3 | Step 10110 | Loss: 0.8659 | LM: 0.3549 | LB: 1.0209 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:07:42] Epoch 3 | Step 10120 | Loss: 0.8664 | LM: 0.3553 | LB: 1.0209 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:07:53] Epoch 3 | Step 10130 | Loss: 0.8666 | LM: 0.3553 | LB: 1.0208 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:08:05] Epoch 3 | Step 10140 | Loss: 0.8661 | LM: 0.3548 | LB: 1.0208 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:08:16] Epoch 3 | Step 10150 | Loss: 0.8663 | LM: 0.3550 | LB: 1.0208 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:08:28] Epoch 3 | Step 10160 | Loss: 0.8663 | LM: 0.3553 | LB: 1.0208 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:08:39] Epoch 3 | Step 10170 | Loss: 0.8665 | LM: 0.3546 | LB: 1.0208 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:08:51] Epoch 3 | Step 10180 | Loss: 0.8664 | LM: 0.3549 | LB: 1.0208 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:09:02] Epoch 3 | Step 10190 | Loss: 0.8666 | LM: 0.3547 | LB: 1.0208 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:09:14] Epoch 3 | Step 10200 | Loss: 0.8663 | LM: 0.3536 | LB: 1.0208 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:09:26] Epoch 3 | Step 10210 | Loss: 0.8665 | LM: 0.3535 | LB: 1.0208 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:09:37] Epoch 3 | Step 10220 | Loss: 0.8663 | LM: 0.3538 | LB: 1.0209 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 15:09:49] Epoch 3 | Step 10230 | Loss: 0.8667 | LM: 0.3545 | LB: 1.0208 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:10:00] Epoch 3 | Step 10240 | Loss: 0.8670 | LM: 0.3548 | LB: 1.0209 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:10:12] Epoch 3 | Step 10250 | Loss: 0.8670 | LM: 0.3550 | LB: 1.0209 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:10:23] Epoch 3 | Step 10260 | Loss: 0.8672 | LM: 0.3547 | LB: 1.0209 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:10:35] Epoch 3 | Step 10270 | Loss: 0.8668 | LM: 0.3548 | LB: 1.0208 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:10:47] Epoch 3 | Step 10280 | Loss: 0.8668 | LM: 0.3547 | LB: 1.0208 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:10:58] Epoch 3 | Step 10290 | Loss: 0.8670 | LM: 0.3551 | LB: 1.0208 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:11:10] Epoch 3 | Step 10300 | Loss: 0.8670 | LM: 0.3553 | LB: 1.0207 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:11:21] Epoch 3 | Step 10310 | Loss: 0.8666 | LM: 0.3550 | LB: 1.0207 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:11:33] Epoch 3 | Step 10320 | Loss: 0.8665 | LM: 0.3549 | LB: 1.0207 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:11:44] Epoch 3 | Step 10330 | Loss: 0.8666 | LM: 0.3552 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:11:56] Epoch 3 | Step 10340 | Loss: 0.8668 | LM: 0.3556 | LB: 1.0207 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:12:07] Epoch 3 | Step 10350 | Loss: 0.8669 | LM: 0.3557 | LB: 1.0207 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:12:19] Epoch 3 | Step 10360 | Loss: 0.8670 | LM: 0.3559 | LB: 1.0207 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:12:30] Epoch 3 | Step 10370 | Loss: 0.8673 | LM: 0.3560 | LB: 1.0207 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:12:42] Epoch 3 | Step 10380 | Loss: 0.8670 | LM: 0.3554 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:12:53] Epoch 3 | Step 10390 | Loss: 0.8671 | LM: 0.3555 | LB: 1.0207 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:13:05] Epoch 3 | Step 10400 | Loss: 0.8674 | LM: 0.3561 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:13:16] Epoch 3 | Step 10410 | Loss: 0.8672 | LM: 0.3562 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:13:28] Epoch 3 | Step 10420 | Loss: 0.8677 | LM: 0.3571 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:13:39] Epoch 3 | Step 10430 | Loss: 0.8676 | LM: 0.3572 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.195/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:13:51] Epoch 3 | Step 10440 | Loss: 0.8672 | LM: 0.3569 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:14:02] Epoch 3 | Step 10450 | Loss: 0.8672 | LM: 0.3567 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:14:14] Epoch 3 | Step 10460 | Loss: 0.8672 | LM: 0.3567 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:14:25] Epoch 3 | Step 10470 | Loss: 0.8674 | LM: 0.3566 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:14:36] Epoch 3 | Step 10480 | Loss: 0.8674 | LM: 0.3564 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:14:48] Epoch 3 | Step 10490 | Loss: 0.8676 | LM: 0.3568 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:15:00] Epoch 3 | Step 10500 | Loss: 0.8676 | LM: 0.3569 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:15:11] Epoch 3 | Step 10510 | Loss: 0.8673 | LM: 0.3565 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:15:23] Epoch 3 | Step 10520 | Loss: 0.8676 | LM: 0.3567 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:15:34] Epoch 3 | Step 10530 | Loss: 0.8677 | LM: 0.3572 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:15:45] Epoch 3 | Step 10540 | Loss: 0.8676 | LM: 0.3572 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:15:56] Epoch 3 | Step 10550 | Loss: 0.8676 | LM: 0.3574 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:16:07] Epoch 3 | Step 10560 | Loss: 0.8676 | LM: 0.3574 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:16:18] Epoch 3 | Step 10570 | Loss: 0.8676 | LM: 0.3577 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:16:30] Epoch 3 | Step 10580 | Loss: 0.8677 | LM: 0.3580 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:16:41] Epoch 3 | Step 10590 | Loss: 0.8678 | LM: 0.3584 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:16:52] Epoch 3 | Step 10600 | Loss: 0.8678 | LM: 0.3583 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:17:03] Epoch 3 | Step 10610 | Loss: 0.8677 | LM: 0.3582 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:17:14] Epoch 3 | Step 10620 | Loss: 0.8676 | LM: 0.3579 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:17:25] Epoch 3 | Step 10630 | Loss: 0.8677 | LM: 0.3585 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:17:36] Epoch 3 | Step 10640 | Loss: 0.8680 | LM: 0.3589 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 15:17:47] Epoch 3 | Step 10650 | Loss: 0.8681 | LM: 0.3588 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 15:17:59] Epoch 3 | Step 10660 | Loss: 0.8680 | LM: 0.3587 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 15:18:10] Epoch 3 | Step 10670 | Loss: 0.8680 | LM: 0.3589 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 15:18:21] Epoch 3 | Step 10680 | Loss: 0.8679 | LM: 0.3590 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 15:18:32] Epoch 3 | Step 10690 | Loss: 0.8678 | LM: 0.3593 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 15:18:43] Epoch 3 | Step 10700 | Loss: 0.8683 | LM: 0.3601 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.134 | LR: 1.00e-04
[2026-05-24 15:18:54] Epoch 3 | Step 10710 | Loss: 0.8682 | LM: 0.3601 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:19:05] Epoch 3 | Step 10720 | Loss: 0.8683 | LM: 0.3601 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:19:16] Epoch 3 | Step 10730 | Loss: 0.8686 | LM: 0.3603 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:19:27] Epoch 3 | Step 10740 | Loss: 0.8684 | LM: 0.3602 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:19:38] Epoch 3 | Step 10750 | Loss: 0.8684 | LM: 0.3602 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:19:49] Epoch 3 | Step 10760 | Loss: 0.8682 | LM: 0.3598 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:20:00] Epoch 3 | Step 10770 | Loss: 0.8684 | LM: 0.3608 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:20:11] Epoch 3 | Step 10780 | Loss: 0.8683 | LM: 0.3605 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:20:23] Epoch 3 | Step 10790 | Loss: 0.8682 | LM: 0.3606 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:20:34] Epoch 3 | Step 10800 | Loss: 0.8684 | LM: 0.3603 | LB: 1.0206 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:20:44] Epoch 3 | Step 10810 | Loss: 0.8685 | LM: 0.3605 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:20:55] Epoch 3 | Step 10820 | Loss: 0.8687 | LM: 0.3605 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:21:06] Epoch 3 | Step 10830 | Loss: 0.8686 | LM: 0.3602 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:21:18] Epoch 3 | Step 10840 | Loss: 0.8684 | LM: 0.3600 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:21:29] Epoch 3 | Step 10850 | Loss: 0.8686 | LM: 0.3601 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.179 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:21:41] Epoch 3 | Step 10860 | Loss: 0.8686 | LM: 0.3599 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:21:52] Epoch 3 | Step 10870 | Loss: 0.8688 | LM: 0.3598 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:22:04] Epoch 3 | Step 10880 | Loss: 0.8690 | LM: 0.3599 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:22:14] Epoch 3 | Step 10890 | Loss: 0.8689 | LM: 0.3597 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:22:25] Epoch 3 | Step 10900 | Loss: 0.8690 | LM: 0.3598 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:22:35] Epoch 3 | Step 10910 | Loss: 0.8691 | LM: 0.3599 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:22:46] Epoch 3 | Step 10920 | Loss: 0.8690 | LM: 0.3602 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:22:57] Epoch 3 | Step 10930 | Loss: 0.8691 | LM: 0.3603 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:23:07] Epoch 3 | Step 10940 | Loss: 0.8690 | LM: 0.3602 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:23:18] Epoch 3 | Step 10950 | Loss: 0.8692 | LM: 0.3602 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:23:28] Epoch 3 | Step 10960 | Loss: 0.8693 | LM: 0.3607 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:23:39] Epoch 3 | Step 10970 | Loss: 0.8693 | LM: 0.3604 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:23:50] Epoch 3 | Step 10980 | Loss: 0.8692 | LM: 0.3602 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:24:00] Epoch 3 | Step 10990 | Loss: 0.8693 | LM: 0.3601 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:24:11] Epoch 3 | Step 11000 | Loss: 0.8692 | LM: 0.3598 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:24:12] Validation | Batch 10/1463 | Loss: 0.9229 | LM_LOSS: 0.4153 | LB_LOSS: 1.0152
[2026-05-24 15:24:13] Validation | Batch 20/1463 | Loss: 0.9322 | LM_LOSS: 0.4230 | LB_LOSS: 1.0183
[2026-05-24 15:24:15] Validation | Batch 30/1463 | Loss: 0.9344 | LM_LOSS: 0.4249 | LB_LOSS: 1.0190
[2026-05-24 15:24:17] Validation | Batch 40/1463 | Loss: 0.9453 | LM_LOSS: 0.4354 | LB_LOSS: 1.0199
[2026-05-24 15:24:18] Validation | Batch 50/1463 | Loss: 0.9505 | LM_LOSS: 0.4410 | LB_LOSS: 1.0191
[2026-05-24 15:24:20] Validation | Batch 60/1463 | Loss: 0.9513 | LM_LOSS: 0.4416 | LB_LOSS: 1.0194
[2026-05-24 15:24:22] Validation | Batch 70/1463 | Loss: 0.9502 | LM_LOSS: 0.4405 | LB_LOSS: 1.0194
[2026-05-24 15:24:24] Validation | Batch 80/1463 | Loss: 0.9508 | LM_LOSS: 0.4410 | LB_LOSS: 1.0197
[2026-05-24 15:24:25] Validation | Batch 90/1463 | Loss: 0.9499 | LM_LOSS: 0.4400 | LB_LOSS: 1.0197
[2026-05-24 15:24:27] Validation | Batch 100/1463 | Loss: 0.9504 | LM_LOSS: 0.4405 | LB_LOSS: 1.0198
[2026-05-24 15:24:29] Validation | Batch 110/1463 | Loss: 0.9488 | LM_LOSS: 0.4387 | LB_LOSS: 1.0200
[2026-05-24 15:24:30] Validation | Batch 120/1463 | Loss: 0.9500 | LM_LOSS: 0.4400 | LB_LOSS: 1.0200
[2026-05-24 15:24:31] Validation | Batch 130/1463 | Loss: 0.9536 | LM_LOSS: 0.4436 | LB_LOSS: 1.0200
[2026-05-24 15:24:33] Validation | Batch 140/1463 | Loss: 0.9549 | LM_LOSS: 0.4449 | LB_LOSS: 1.0200
[2026-05-24 15:24:35] Validation | Batch 150/1463 | Loss: 0.9529 | LM_LOSS: 0.4428 | LB_LOSS: 1.0201
[2026-05-24 15:24:36] Validation | Batch 160/1463 | Loss: 0.9542 | LM_LOSS: 0.4442 | LB_LOSS: 1.0200
[2026-05-24 15:24:38] Validation | Batch 170/1463 | Loss: 0.9537 | LM_LOSS: 0.4437 | LB_LOSS: 1.0200
[2026-05-24 15:24:40] Validation | Batch 180/1463 | Loss: 0.9546 | LM_LOSS: 0.4445 | LB_LOSS: 1.0202
[2026-05-24 15:24:41] Validation | Batch 190/1463 | Loss: 0.9549 | LM_LOSS: 0.4449 | LB_LOSS: 1.0202
[2026-05-24 15:24:43] Validation | Batch 200/1463 | Loss: 0.9540 | LM_LOSS: 0.4438 | LB_LOSS: 1.0203
[2026-05-24 15:24:45] Validation | Batch 210/1463 | Loss: 0.9547 | LM_LOSS: 0.4446 | LB_LOSS: 1.0203
[2026-05-24 15:24:46] Validation | Batch 220/1463 | Loss: 0.9537 | LM_LOSS: 0.4435 | LB_LOSS: 1.0204
[2026-05-24 15:24:48] Validation | Batch 230/1463 | Loss: 0.9550 | LM_LOSS: 0.4449 | LB_LOSS: 1.0202
[2026-05-24 15:24:50] Validation | Batch 240/1463 | Loss: 0.9554 | LM_LOSS: 0.4453 | LB_LOSS: 1.0202
[2026-05-24 15:24:51] Validation | Batch 250/1463 | Loss: 0.9538 | LM_LOSS: 0.4437 | LB_LOSS: 1.0202
[2026-05-24 15:24:53] Validation | Batch 260/1463 | Loss: 0.9560 | LM_LOSS: 0.4458 | LB_LOSS: 1.0204
[2026-05-24 15:24:55] Validation | Batch 270/1463 | Loss: 0.9549 | LM_LOSS: 0.4447 | LB_LOSS: 1.0204
[2026-05-24 15:24:56] Validation | Batch 280/1463 | Loss: 0.9558 | LM_LOSS: 0.4456 | LB_LOSS: 1.0204
[2026-05-24 15:24:58] Validation | Batch 290/1463 | Loss: 0.9544 | LM_LOSS: 0.4442 | LB_LOSS: 1.0204
[2026-05-24 15:24:59] Validation | Batch 300/1463 | Loss: 0.9552 | LM_LOSS: 0.4450 | LB_LOSS: 1.0205
[2026-05-24 15:25:01] Validation | Batch 310/1463 | Loss: 0.9563 | LM_LOSS: 0.4461 | LB_LOSS: 1.0205
[2026-05-24 15:25:02] Validation | Batch 320/1463 | Loss: 0.9546 | LM_LOSS: 0.4445 | LB_LOSS: 1.0203
[2026-05-24 15:25:04] Validation | Batch 330/1463 | Loss: 0.9546 | LM_LOSS: 0.4444 | LB_LOSS: 1.0203
[2026-05-24 15:25:05] Validation | Batch 340/1463 | Loss: 0.9542 | LM_LOSS: 0.4440 | LB_LOSS: 1.0204
[2026-05-24 15:25:07] Validation | Batch 350/1463 | Loss: 0.9545 | LM_LOSS: 0.4443 | LB_LOSS: 1.0203
[2026-05-24 15:25:09] Validation | Batch 360/1463 | Loss: 0.9546 | LM_LOSS: 0.4444 | LB_LOSS: 1.0204
[2026-05-24 15:25:10] Validation | Batch 370/1463 | Loss: 0.9547 | LM_LOSS: 0.4445 | LB_LOSS: 1.0204
[2026-05-24 15:25:12] Validation | Batch 380/1463 | Loss: 0.9544 | LM_LOSS: 0.4442 | LB_LOSS: 1.0204
[2026-05-24 15:25:13] Validation | Batch 390/1463 | Loss: 0.9557 | LM_LOSS: 0.4454 | LB_LOSS: 1.0204
[2026-05-24 15:25:15] Validation | Batch 400/1463 | Loss: 0.9555 | LM_LOSS: 0.4453 | LB_LOSS: 1.0204
[2026-05-24 15:25:16] Validation | Batch 410/1463 | Loss: 0.9553 | LM_LOSS: 0.4451 | LB_LOSS: 1.0205
[2026-05-24 15:25:18] Validation | Batch 420/1463 | Loss: 0.9557 | LM_LOSS: 0.4455 | LB_LOSS: 1.0205
[2026-05-24 15:25:20] Validation | Batch 430/1463 | Loss: 0.9555 | LM_LOSS: 0.4452 | LB_LOSS: 1.0206
[2026-05-24 15:25:21] Validation | Batch 440/1463 | Loss: 0.9561 | LM_LOSS: 0.4458 | LB_LOSS: 1.0207
[2026-05-24 15:25:23] Validation | Batch 450/1463 | Loss: 0.9557 | LM_LOSS: 0.4454 | LB_LOSS: 1.0207
[2026-05-24 15:25:25] Validation | Batch 460/1463 | Loss: 0.9559 | LM_LOSS: 0.4455 | LB_LOSS: 1.0206
[2026-05-24 15:25:26] Validation | Batch 470/1463 | Loss: 0.9564 | LM_LOSS: 0.4461 | LB_LOSS: 1.0206
[2026-05-24 15:25:28] Validation | Batch 480/1463 | Loss: 0.9562 | LM_LOSS: 0.4459 | LB_LOSS: 1.0206
[2026-05-24 15:25:30] Validation | Batch 490/1463 | Loss: 0.9559 | LM_LOSS: 0.4456 | LB_LOSS: 1.0206
[2026-05-24 15:25:31] Validation | Batch 500/1463 | Loss: 0.9557 | LM_LOSS: 0.4454 | LB_LOSS: 1.0206
[2026-05-24 15:25:33] Validation | Batch 510/1463 | Loss: 0.9551 | LM_LOSS: 0.4448 | LB_LOSS: 1.0206
[2026-05-24 15:25:34] Validation | Batch 520/1463 | Loss: 0.9550 | LM_LOSS: 0.4446 | LB_LOSS: 1.0206
[2026-05-24 15:25:36] Validation | Batch 530/1463 | Loss: 0.9555 | LM_LOSS: 0.4452 | LB_LOSS: 1.0206
[2026-05-24 15:25:37] Validation | Batch 540/1463 | Loss: 0.9560 | LM_LOSS: 0.4457 | LB_LOSS: 1.0206
[2026-05-24 15:25:39] Validation | Batch 550/1463 | Loss: 0.9557 | LM_LOSS: 0.4454 | LB_LOSS: 1.0206
[2026-05-24 15:25:40] Validation | Batch 560/1463 | Loss: 0.9563 | LM_LOSS: 0.4459 | LB_LOSS: 1.0207
[2026-05-24 15:25:42] Validation | Batch 570/1463 | Loss: 0.9563 | LM_LOSS: 0.4460 | LB_LOSS: 1.0207
[2026-05-24 15:25:44] Validation | Batch 580/1463 | Loss: 0.9559 | LM_LOSS: 0.4456 | LB_LOSS: 1.0207
[2026-05-24 15:25:46] Validation | Batch 590/1463 | Loss: 0.9559 | LM_LOSS: 0.4455 | LB_LOSS: 1.0208
[2026-05-24 15:25:47] Validation | Batch 600/1463 | Loss: 0.9561 | LM_LOSS: 0.4456 | LB_LOSS: 1.0208
[2026-05-24 15:25:49] Validation | Batch 610/1463 | Loss: 0.9561 | LM_LOSS: 0.4457 | LB_LOSS: 1.0208
[2026-05-24 15:25:51] Validation | Batch 620/1463 | Loss: 0.9557 | LM_LOSS: 0.4452 | LB_LOSS: 1.0208
[2026-05-24 15:25:52] Validation | Batch 630/1463 | Loss: 0.9553 | LM_LOSS: 0.4449 | LB_LOSS: 1.0208
[2026-05-24 15:25:54] Validation | Batch 640/1463 | Loss: 0.9551 | LM_LOSS: 0.4447 | LB_LOSS: 1.0208
[2026-05-24 15:25:55] Validation | Batch 650/1463 | Loss: 0.9545 | LM_LOSS: 0.4441 | LB_LOSS: 1.0209
[2026-05-24 15:25:57] Validation | Batch 660/1463 | Loss: 0.9540 | LM_LOSS: 0.4436 | LB_LOSS: 1.0209
[2026-05-24 15:25:58] Validation | Batch 670/1463 | Loss: 0.9536 | LM_LOSS: 0.4432 | LB_LOSS: 1.0208
[2026-05-24 15:26:00] Validation | Batch 680/1463 | Loss: 0.9537 | LM_LOSS: 0.4433 | LB_LOSS: 1.0208
[2026-05-24 15:26:01] Validation | Batch 690/1463 | Loss: 0.9541 | LM_LOSS: 0.4436 | LB_LOSS: 1.0208
[2026-05-24 15:26:03] Validation | Batch 700/1463 | Loss: 0.9541 | LM_LOSS: 0.4437 | LB_LOSS: 1.0208
[2026-05-24 15:26:04] Validation | Batch 710/1463 | Loss: 0.9544 | LM_LOSS: 0.4440 | LB_LOSS: 1.0209
[2026-05-24 15:26:06] Validation | Batch 720/1463 | Loss: 0.9552 | LM_LOSS: 0.4447 | LB_LOSS: 1.0209
[2026-05-24 15:26:07] Validation | Batch 730/1463 | Loss: 0.9552 | LM_LOSS: 0.4448 | LB_LOSS: 1.0209
[2026-05-24 15:26:09] Validation | Batch 740/1463 | Loss: 0.9550 | LM_LOSS: 0.4446 | LB_LOSS: 1.0209
[2026-05-24 15:26:10] Validation | Batch 750/1463 | Loss: 0.9549 | LM_LOSS: 0.4444 | LB_LOSS: 1.0209
[2026-05-24 15:26:12] Validation | Batch 760/1463 | Loss: 0.9546 | LM_LOSS: 0.4441 | LB_LOSS: 1.0209
[2026-05-24 15:26:13] Validation | Batch 770/1463 | Loss: 0.9545 | LM_LOSS: 0.4440 | LB_LOSS: 1.0209
[2026-05-24 15:26:15] Validation | Batch 780/1463 | Loss: 0.9544 | LM_LOSS: 0.4440 | LB_LOSS: 1.0209
[2026-05-24 15:26:16] Validation | Batch 790/1463 | Loss: 0.9547 | LM_LOSS: 0.4443 | LB_LOSS: 1.0208
[2026-05-24 15:26:17] Validation | Batch 800/1463 | Loss: 0.9547 | LM_LOSS: 0.4443 | LB_LOSS: 1.0208
[2026-05-24 15:26:19] Validation | Batch 810/1463 | Loss: 0.9542 | LM_LOSS: 0.4438 | LB_LOSS: 1.0208
[2026-05-24 15:26:20] Validation | Batch 820/1463 | Loss: 0.9544 | LM_LOSS: 0.4440 | LB_LOSS: 1.0208
[2026-05-24 15:26:22] Validation | Batch 830/1463 | Loss: 0.9545 | LM_LOSS: 0.4441 | LB_LOSS: 1.0208
[2026-05-24 15:26:24] Validation | Batch 840/1463 | Loss: 0.9544 | LM_LOSS: 0.4440 | LB_LOSS: 1.0208
[2026-05-24 15:26:26] Validation | Batch 850/1463 | Loss: 0.9547 | LM_LOSS: 0.4443 | LB_LOSS: 1.0209
[2026-05-24 15:26:27] Validation | Batch 860/1463 | Loss: 0.9547 | LM_LOSS: 0.4442 | LB_LOSS: 1.0209
[2026-05-24 15:26:29] Validation | Batch 870/1463 | Loss: 0.9549 | LM_LOSS: 0.4444 | LB_LOSS: 1.0209
[2026-05-24 15:26:30] Validation | Batch 880/1463 | Loss: 0.9541 | LM_LOSS: 0.4437 | LB_LOSS: 1.0209
[2026-05-24 15:26:32] Validation | Batch 890/1463 | Loss: 0.9540 | LM_LOSS: 0.4436 | LB_LOSS: 1.0208
[2026-05-24 15:26:33] Validation | Batch 900/1463 | Loss: 0.9537 | LM_LOSS: 0.4432 | LB_LOSS: 1.0208
[2026-05-24 15:26:35] Validation | Batch 910/1463 | Loss: 0.9537 | LM_LOSS: 0.4432 | LB_LOSS: 1.0208
[2026-05-24 15:26:37] Validation | Batch 920/1463 | Loss: 0.9540 | LM_LOSS: 0.4436 | LB_LOSS: 1.0209
[2026-05-24 15:26:38] Validation | Batch 930/1463 | Loss: 0.9535 | LM_LOSS: 0.4431 | LB_LOSS: 1.0208
[2026-05-24 15:26:40] Validation | Batch 940/1463 | Loss: 0.9531 | LM_LOSS: 0.4427 | LB_LOSS: 1.0208
[2026-05-24 15:26:42] Validation | Batch 950/1463 | Loss: 0.9535 | LM_LOSS: 0.4431 | LB_LOSS: 1.0208
[2026-05-24 15:26:43] Validation | Batch 960/1463 | Loss: 0.9536 | LM_LOSS: 0.4432 | LB_LOSS: 1.0208
[2026-05-24 15:26:45] Validation | Batch 970/1463 | Loss: 0.9538 | LM_LOSS: 0.4434 | LB_LOSS: 1.0208
[2026-05-24 15:26:47] Validation | Batch 980/1463 | Loss: 0.9542 | LM_LOSS: 0.4438 | LB_LOSS: 1.0207
[2026-05-24 15:26:48] Validation | Batch 990/1463 | Loss: 0.9543 | LM_LOSS: 0.4439 | LB_LOSS: 1.0207
[2026-05-24 15:26:50] Validation | Batch 1000/1463 | Loss: 0.9549 | LM_LOSS: 0.4445 | LB_LOSS: 1.0208
[2026-05-24 15:26:51] Validation | Batch 1010/1463 | Loss: 0.9550 | LM_LOSS: 0.4446 | LB_LOSS: 1.0208
[2026-05-24 15:26:53] Validation | Batch 1020/1463 | Loss: 0.9553 | LM_LOSS: 0.4449 | LB_LOSS: 1.0209
[2026-05-24 15:26:55] Validation | Batch 1030/1463 | Loss: 0.9559 | LM_LOSS: 0.4454 | LB_LOSS: 1.0209
[2026-05-24 15:26:56] Validation | Batch 1040/1463 | Loss: 0.9553 | LM_LOSS: 0.4448 | LB_LOSS: 1.0208
[2026-05-24 15:26:58] Validation | Batch 1050/1463 | Loss: 0.9551 | LM_LOSS: 0.4447 | LB_LOSS: 1.0208
[2026-05-24 15:27:00] Validation | Batch 1060/1463 | Loss: 0.9550 | LM_LOSS: 0.4446 | LB_LOSS: 1.0208
[2026-05-24 15:27:01] Validation | Batch 1070/1463 | Loss: 0.9551 | LM_LOSS: 0.4447 | LB_LOSS: 1.0208
[2026-05-24 15:27:03] Validation | Batch 1080/1463 | Loss: 0.9548 | LM_LOSS: 0.4444 | LB_LOSS: 1.0208
[2026-05-24 15:27:04] Validation | Batch 1090/1463 | Loss: 0.9547 | LM_LOSS: 0.4443 | LB_LOSS: 1.0208
[2026-05-24 15:27:06] Validation | Batch 1100/1463 | Loss: 0.9546 | LM_LOSS: 0.4443 | LB_LOSS: 1.0208
[2026-05-24 15:27:07] Validation | Batch 1110/1463 | Loss: 0.9547 | LM_LOSS: 0.4443 | LB_LOSS: 1.0208
[2026-05-24 15:27:09] Validation | Batch 1120/1463 | Loss: 0.9545 | LM_LOSS: 0.4441 | LB_LOSS: 1.0208
[2026-05-24 15:27:11] Validation | Batch 1130/1463 | Loss: 0.9541 | LM_LOSS: 0.4437 | LB_LOSS: 1.0208
[2026-05-24 15:27:12] Validation | Batch 1140/1463 | Loss: 0.9543 | LM_LOSS: 0.4440 | LB_LOSS: 1.0208
[2026-05-24 15:27:14] Validation | Batch 1150/1463 | Loss: 0.9543 | LM_LOSS: 0.4439 | LB_LOSS: 1.0208
[2026-05-24 15:27:16] Validation | Batch 1160/1463 | Loss: 0.9543 | LM_LOSS: 0.4439 | LB_LOSS: 1.0208
[2026-05-24 15:27:17] Validation | Batch 1170/1463 | Loss: 0.9541 | LM_LOSS: 0.4437 | LB_LOSS: 1.0207
[2026-05-24 15:27:19] Validation | Batch 1180/1463 | Loss: 0.9540 | LM_LOSS: 0.4436 | LB_LOSS: 1.0208
[2026-05-24 15:27:21] Validation | Batch 1190/1463 | Loss: 0.9542 | LM_LOSS: 0.4438 | LB_LOSS: 1.0208
[2026-05-24 15:27:22] Validation | Batch 1200/1463 | Loss: 0.9543 | LM_LOSS: 0.4440 | LB_LOSS: 1.0208
[2026-05-24 15:27:24] Validation | Batch 1210/1463 | Loss: 0.9547 | LM_LOSS: 0.4444 | LB_LOSS: 1.0208
[2026-05-24 15:27:25] Validation | Batch 1220/1463 | Loss: 0.9551 | LM_LOSS: 0.4447 | LB_LOSS: 1.0208
[2026-05-24 15:27:27] Validation | Batch 1230/1463 | Loss: 0.9550 | LM_LOSS: 0.4447 | LB_LOSS: 1.0208
[2026-05-24 15:27:28] Validation | Batch 1240/1463 | Loss: 0.9554 | LM_LOSS: 0.4450 | LB_LOSS: 1.0208
[2026-05-24 15:27:30] Validation | Batch 1250/1463 | Loss: 0.9557 | LM_LOSS: 0.4453 | LB_LOSS: 1.0208
[2026-05-24 15:27:32] Validation | Batch 1260/1463 | Loss: 0.9556 | LM_LOSS: 0.4452 | LB_LOSS: 1.0208
[2026-05-24 15:27:33] Validation | Batch 1270/1463 | Loss: 0.9555 | LM_LOSS: 0.4450 | LB_LOSS: 1.0208
[2026-05-24 15:27:35] Validation | Batch 1280/1463 | Loss: 0.9552 | LM_LOSS: 0.4448 | LB_LOSS: 1.0208
[2026-05-24 15:27:37] Validation | Batch 1290/1463 | Loss: 0.9553 | LM_LOSS: 0.4449 | LB_LOSS: 1.0208
[2026-05-24 15:27:38] Validation | Batch 1300/1463 | Loss: 0.9550 | LM_LOSS: 0.4446 | LB_LOSS: 1.0208
[2026-05-24 15:27:40] Validation | Batch 1310/1463 | Loss: 0.9549 | LM_LOSS: 0.4445 | LB_LOSS: 1.0208
[2026-05-24 15:27:41] Validation | Batch 1320/1463 | Loss: 0.9550 | LM_LOSS: 0.4446 | LB_LOSS: 1.0208
[2026-05-24 15:27:43] Validation | Batch 1330/1463 | Loss: 0.9549 | LM_LOSS: 0.4445 | LB_LOSS: 1.0208
[2026-05-24 15:27:44] Validation | Batch 1340/1463 | Loss: 0.9551 | LM_LOSS: 0.4447 | LB_LOSS: 1.0208
[2026-05-24 15:27:46] Validation | Batch 1350/1463 | Loss: 0.9551 | LM_LOSS: 0.4448 | LB_LOSS: 1.0207
[2026-05-24 15:27:48] Validation | Batch 1360/1463 | Loss: 0.9554 | LM_LOSS: 0.4450 | LB_LOSS: 1.0208
[2026-05-24 15:27:49] Validation | Batch 1370/1463 | Loss: 0.9559 | LM_LOSS: 0.4455 | LB_LOSS: 1.0208
[2026-05-24 15:27:51] Validation | Batch 1380/1463 | Loss: 0.9556 | LM_LOSS: 0.4453 | LB_LOSS: 1.0207
[2026-05-24 15:27:52] Validation | Batch 1390/1463 | Loss: 0.9555 | LM_LOSS: 0.4451 | LB_LOSS: 1.0208
[2026-05-24 15:27:54] Validation | Batch 1400/1463 | Loss: 0.9558 | LM_LOSS: 0.4454 | LB_LOSS: 1.0207
[2026-05-24 15:27:55] Validation | Batch 1410/1463 | Loss: 0.9559 | LM_LOSS: 0.4456 | LB_LOSS: 1.0207
[2026-05-24 15:27:57] Validation | Batch 1420/1463 | Loss: 0.9560 | LM_LOSS: 0.4457 | LB_LOSS: 1.0207
[2026-05-24 15:27:59] Validation | Batch 1430/1463 | Loss: 0.9561 | LM_LOSS: 0.4457 | LB_LOSS: 1.0207
[2026-05-24 15:28:00] Validation | Batch 1440/1463 | Loss: 0.9565 | LM_LOSS: 0.4462 | LB_LOSS: 1.0208
[2026-05-24 15:28:02] Validation | Batch 1450/1463 | Loss: 0.9562 | LM_LOSS: 0.4458 | LB_LOSS: 1.0207
[2026-05-24 15:28:03] Validation | Batch 1460/1463 | Loss: 0.9565 | LM_LOSS: 0.4462 | LB_LOSS: 1.0207
[2026-05-24 15:28:04] Validation | Batch 1463/1463 | Loss: 0.9564 | LM_LOSS: 0.4461 | LB_LOSS: 1.0207
[2026-05-24 15:28:04] Validation | Loss: 0.9564 | LM_LOSS: 0.4461 | LB_LOSS: 1.0207 | PPL: 1.56 | Time: 233.28s
[2026-05-24 15:28:15] Epoch 3 | Step 11010 | Loss: 0.8692 | LM: 0.3598 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.149/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:28:25] Epoch 3 | Step 11020 | Loss: 0.8693 | LM: 0.3602 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:28:36] Epoch 3 | Step 11030 | Loss: 0.8691 | LM: 0.3600 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:28:46] Epoch 3 | Step 11040 | Loss: 0.8692 | LM: 0.3603 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:28:57] Epoch 3 | Step 11050 | Loss: 0.8691 | LM: 0.3602 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:29:07] Epoch 3 | Step 11060 | Loss: 0.8693 | LM: 0.3603 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:29:18] Epoch 3 | Step 11070 | Loss: 0.8692 | LM: 0.3602 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:29:29] Epoch 3 | Step 11080 | Loss: 0.8695 | LM: 0.3604 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:29:39] Epoch 3 | Step 11090 | Loss: 0.8695 | LM: 0.3604 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:29:50] Epoch 3 | Step 11100 | Loss: 0.8695 | LM: 0.3609 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:30:01] Epoch 3 | Step 11110 | Loss: 0.8694 | LM: 0.3608 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:30:11] Epoch 3 | Step 11120 | Loss: 0.8695 | LM: 0.3609 | LB: 1.0205 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:30:22] Epoch 3 | Step 11130 | Loss: 0.8696 | LM: 0.3609 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:30:32] Epoch 3 | Step 11140 | Loss: 0.8697 | LM: 0.3612 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:30:43] Epoch 3 | Step 11150 | Loss: 0.8698 | LM: 0.3614 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:30:54] Epoch 3 | Step 11160 | Loss: 0.8699 | LM: 0.3612 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:31:04] Epoch 3 | Step 11170 | Loss: 0.8700 | LM: 0.3615 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:31:15] Epoch 3 | Step 11180 | Loss: 0.8700 | LM: 0.3618 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:31:26] Epoch 3 | Step 11190 | Loss: 0.8700 | LM: 0.3618 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:31:36] Epoch 3 | Step 11200 | Loss: 0.8700 | LM: 0.3617 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:31:47] Epoch 3 | Step 11210 | Loss: 0.8700 | LM: 0.3614 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:31:57] Epoch 3 | Step 11220 | Loss: 0.8700 | LM: 0.3611 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:32:08] Epoch 3 | Step 11230 | Loss: 0.8699 | LM: 0.3607 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:32:19] Epoch 3 | Step 11240 | Loss: 0.8701 | LM: 0.3608 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:32:30] Epoch 3 | Step 11250 | Loss: 0.8702 | LM: 0.3610 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:32:40] Epoch 3 | Step 11260 | Loss: 0.8702 | LM: 0.3609 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:32:51] Epoch 3 | Step 11270 | Loss: 0.8701 | LM: 0.3610 | LB: 1.0204 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:33:01] Epoch 3 | Step 11280 | Loss: 0.8702 | LM: 0.3611 | LB: 1.0203 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:33:12] Epoch 3 | Step 11290 | Loss: 0.8703 | LM: 0.3614 | LB: 1.0203 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-04
[2026-05-24 15:33:22] Epoch 3 | Step 11300 | Loss: 0.8702 | LM: 0.3612 | LB: 1.0203 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.99e-05
[2026-05-24 15:33:33] Epoch 3 | Step 11310 | Loss: 0.8702 | LM: 0.3611 | LB: 1.0203 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.99e-05
[2026-05-24 15:33:44] Epoch 3 | Step 11320 | Loss: 0.8702 | LM: 0.3609 | LB: 1.0203 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.99e-05
[2026-05-24 15:33:54] Epoch 3 | Step 11330 | Loss: 0.8702 | LM: 0.3612 | LB: 1.0203 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.98e-05
[2026-05-24 15:34:05] Epoch 3 | Step 11340 | Loss: 0.8703 | LM: 0.3612 | LB: 1.0203 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.98e-05
[2026-05-24 15:34:15] Epoch 3 | Step 11350 | Loss: 0.8702 | LM: 0.3611 | LB: 1.0203 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.97e-05
[2026-05-24 15:34:26] Epoch 3 | Step 11360 | Loss: 0.8702 | LM: 0.3612 | LB: 1.0203 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.97e-05
[2026-05-24 15:34:36] Epoch 3 | Step 11370 | Loss: 0.8700 | LM: 0.3607 | LB: 1.0203 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.96e-05
[2026-05-24 15:34:47] Epoch 3 | Step 11380 | Loss: 0.8700 | LM: 0.3607 | LB: 1.0203 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.95e-05
[2026-05-24 15:34:58] Epoch 3 | Step 11390 | Loss: 0.8702 | LM: 0.3610 | LB: 1.0203 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.95e-05
[2026-05-24 15:35:09] Epoch 3 | Step 11400 | Loss: 0.8702 | LM: 0.3612 | LB: 1.0202 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.94e-05
[2026-05-24 15:35:20] Epoch 3 | Step 11410 | Loss: 0.8704 | LM: 0.3612 | LB: 1.0203 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.93e-05
[2026-05-24 15:35:32] Epoch 3 | Step 11420 | Loss: 0.8703 | LM: 0.3612 | LB: 1.0203 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.92e-05
[2026-05-24 15:35:42] Epoch 3 | Step 11430 | Loss: 0.8703 | LM: 0.3614 | LB: 1.0202 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.91e-05
[2026-05-24 15:35:54] Epoch 3 | Step 11440 | Loss: 0.8703 | LM: 0.3616 | LB: 1.0202 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.90e-05
[2026-05-24 15:36:05] Epoch 3 | Step 11450 | Loss: 0.8703 | LM: 0.3614 | LB: 1.0202 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.89e-05
[2026-05-24 15:36:16] Epoch 3 | Step 11460 | Loss: 0.8703 | LM: 0.3616 | LB: 1.0202 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.88e-05
[2026-05-24 15:36:27] Epoch 3 | Step 11470 | Loss: 0.8704 | LM: 0.3616 | LB: 1.0202 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.86e-05
[2026-05-24 15:36:38] Epoch 3 | Step 11480 | Loss: 0.8705 | LM: 0.3615 | LB: 1.0202 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.85e-05
[2026-05-24 15:36:49] Epoch 3 | Step 11490 | Loss: 0.8706 | LM: 0.3617 | LB: 1.0202 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.84e-05
[2026-05-24 15:37:00] Epoch 3 | Step 11500 | Loss: 0.8706 | LM: 0.3619 | LB: 1.0202 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.83e-05
[2026-05-24 15:37:11] Epoch 3 | Step 11510 | Loss: 0.8706 | LM: 0.3620 | LB: 1.0202 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.81e-05
[2026-05-24 15:37:22] Epoch 3 | Step 11520 | Loss: 0.8707 | LM: 0.3620 | LB: 1.0202 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.80e-05
[2026-05-24 15:37:33] Epoch 3 | Step 11530 | Loss: 0.8710 | LM: 0.3622 | LB: 1.0202 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.78e-05
[2026-05-24 15:37:44] Epoch 3 | Step 11540 | Loss: 0.8710 | LM: 0.3621 | LB: 1.0201 | CL0: 5.2 | CL1: 6.8 | HR0: 0.194/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.77e-05
[2026-05-24 15:37:56] Epoch 3 | Step 11550 | Loss: 0.8711 | LM: 0.3623 | LB: 1.0201 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.75e-05
[2026-05-24 15:38:07] Epoch 3 | Step 11560 | Loss: 0.8712 | LM: 0.3624 | LB: 1.0201 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.73e-05
[2026-05-24 15:38:18] Epoch 3 | Step 11570 | Loss: 0.8713 | LM: 0.3626 | LB: 1.0201 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.72e-05
[2026-05-24 15:38:29] Epoch 3 | Step 11580 | Loss: 0.8713 | LM: 0.3627 | LB: 1.0201 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.70e-05
[2026-05-24 15:38:40] Epoch 3 | Step 11590 | Loss: 0.8714 | LM: 0.3631 | LB: 1.0202 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.68e-05
[2026-05-24 15:38:51] Epoch 3 | Step 11600 | Loss: 0.8712 | LM: 0.3627 | LB: 1.0201 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.66e-05
[2026-05-24 15:39:02] Epoch 3 | Step 11610 | Loss: 0.8713 | LM: 0.3626 | LB: 1.0201 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.64e-05
[2026-05-24 15:39:13] Epoch 3 | Step 11620 | Loss: 0.8713 | LM: 0.3623 | LB: 1.0201 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.62e-05
[2026-05-24 15:39:24] Epoch 3 | Step 11630 | Loss: 0.8714 | LM: 0.3625 | LB: 1.0201 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.60e-05
[2026-05-24 15:39:35] Epoch 3 | Step 11640 | Loss: 0.8714 | LM: 0.3623 | LB: 1.0201 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.58e-05
[2026-05-24 15:39:46] Epoch 3 | Step 11650 | Loss: 0.8713 | LM: 0.3622 | LB: 1.0201 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.56e-05
[2026-05-24 15:39:57] Epoch 3 | Step 11660 | Loss: 0.8714 | LM: 0.3622 | LB: 1.0201 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.54e-05
[2026-05-24 15:40:08] Epoch 3 | Step 11670 | Loss: 0.8714 | LM: 0.3623 | LB: 1.0201 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.51e-05
[2026-05-24 15:40:19] Epoch 3 | Step 11680 | Loss: 0.8714 | LM: 0.3623 | LB: 1.0201 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.49e-05
[2026-05-24 15:40:30] Epoch 3 | Step 11690 | Loss: 0.8716 | LM: 0.3624 | LB: 1.0201 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.47e-05
[2026-05-24 15:40:41] Epoch 3 | Step 11700 | Loss: 0.8717 | LM: 0.3625 | LB: 1.0201 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.44e-05
[2026-05-24 15:40:52] Epoch 3 | Step 11710 | Loss: 0.8717 | LM: 0.3623 | LB: 1.0200 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.42e-05
[2026-05-24 15:41:02] Epoch 3 | Step 11720 | Loss: 0.8719 | LM: 0.3624 | LB: 1.0200 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.39e-05
[2026-05-24 15:41:13] Epoch 3 | Step 11730 | Loss: 0.8719 | LM: 0.3622 | LB: 1.0200 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.37e-05
[2026-05-24 15:41:23] Epoch 3 | Step 11740 | Loss: 0.8721 | LM: 0.3623 | LB: 1.0200 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.34e-05
[2026-05-24 15:41:34] Epoch 3 | Step 11750 | Loss: 0.8721 | LM: 0.3624 | LB: 1.0200 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.32e-05
[2026-05-24 15:41:44] Epoch 3 | Step 11760 | Loss: 0.8720 | LM: 0.3622 | LB: 1.0200 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.29e-05
[2026-05-24 15:41:55] Epoch 3 | Step 11770 | Loss: 0.8722 | LM: 0.3625 | LB: 1.0200 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.26e-05
[2026-05-24 15:42:06] Epoch 3 | Step 11780 | Loss: 0.8723 | LM: 0.3625 | LB: 1.0200 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.23e-05
[2026-05-24 15:42:16] Epoch 3 | Step 11790 | Loss: 0.8723 | LM: 0.3625 | LB: 1.0200 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.21e-05
[2026-05-24 15:42:27] Epoch 3 | Step 11800 | Loss: 0.8724 | LM: 0.3627 | LB: 1.0200 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.18e-05
[2026-05-24 15:42:37] Epoch 3 | Step 11810 | Loss: 0.8723 | LM: 0.3625 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.15e-05
[2026-05-24 15:42:48] Epoch 3 | Step 11820 | Loss: 0.8723 | LM: 0.3625 | LB: 1.0200 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.12e-05
[2026-05-24 15:42:59] Epoch 3 | Step 11830 | Loss: 0.8724 | LM: 0.3626 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.09e-05
[2026-05-24 15:43:09] Epoch 3 | Step 11840 | Loss: 0.8724 | LM: 0.3627 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.06e-05
[2026-05-24 15:43:20] Epoch 3 | Step 11850 | Loss: 0.8724 | LM: 0.3627 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 9.03e-05
[2026-05-24 15:43:31] Epoch 3 | Step 11860 | Loss: 0.8724 | LM: 0.3627 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.99e-05
[2026-05-24 15:43:41] Epoch 3 | Step 11870 | Loss: 0.8725 | LM: 0.3627 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.96e-05
[2026-05-24 15:43:52] Epoch 3 | Step 11880 | Loss: 0.8724 | LM: 0.3627 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.93e-05
[2026-05-24 15:44:03] Epoch 3 | Step 11890 | Loss: 0.8726 | LM: 0.3628 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.90e-05
[2026-05-24 15:44:14] Epoch 3 | Step 11900 | Loss: 0.8727 | LM: 0.3630 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.86e-05
[2026-05-24 15:44:24] Epoch 3 | Step 11910 | Loss: 0.8727 | LM: 0.3633 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.83e-05
[2026-05-24 15:44:34] Epoch 3 | Step 11920 | Loss: 0.8728 | LM: 0.3635 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.80e-05
[2026-05-24 15:44:45] Epoch 3 | Step 11930 | Loss: 0.8728 | LM: 0.3635 | LB: 1.0198 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.76e-05
[2026-05-24 15:44:56] Epoch 3 | Step 11940 | Loss: 0.8728 | LM: 0.3634 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.73e-05
[2026-05-24 15:45:06] Epoch 3 | Step 11950 | Loss: 0.8729 | LM: 0.3634 | LB: 1.0198 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.69e-05
[2026-05-24 15:45:17] Epoch 3 | Step 11960 | Loss: 0.8730 | LM: 0.3635 | LB: 1.0198 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.66e-05
[2026-05-24 15:45:28] Epoch 3 | Step 11970 | Loss: 0.8731 | LM: 0.3635 | LB: 1.0198 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.62e-05
[2026-05-24 15:45:39] Epoch 3 | Step 11980 | Loss: 0.8730 | LM: 0.3639 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.58e-05
[2026-05-24 15:45:49] Epoch 3 | Step 11990 | Loss: 0.8730 | LM: 0.3638 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.55e-05
[2026-05-24 15:45:59] Epoch 3 | Step 12000 | Loss: 0.8730 | LM: 0.3635 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.51e-05
[2026-05-24 15:46:03] Checkpoint saved: outputs/2026-05-24/N_8.0/checkpoints/checkpoint_step_12000.pt
[2026-05-24 15:46:09] Validation | Batch 10/1463 | Loss: 0.9179 | LM_LOSS: 0.4109 | LB_LOSS: 1.0140
[2026-05-24 15:46:10] Validation | Batch 20/1463 | Loss: 0.9282 | LM_LOSS: 0.4197 | LB_LOSS: 1.0169
[2026-05-24 15:46:12] Validation | Batch 30/1463 | Loss: 0.9311 | LM_LOSS: 0.4223 | LB_LOSS: 1.0175
[2026-05-24 15:46:13] Validation | Batch 40/1463 | Loss: 0.9416 | LM_LOSS: 0.4324 | LB_LOSS: 1.0184
[2026-05-24 15:46:15] Validation | Batch 50/1463 | Loss: 0.9466 | LM_LOSS: 0.4377 | LB_LOSS: 1.0177
[2026-05-24 15:46:17] Validation | Batch 60/1463 | Loss: 0.9469 | LM_LOSS: 0.4379 | LB_LOSS: 1.0180
[2026-05-24 15:46:19] Validation | Batch 70/1463 | Loss: 0.9461 | LM_LOSS: 0.4371 | LB_LOSS: 1.0180
[2026-05-24 15:46:20] Validation | Batch 80/1463 | Loss: 0.9468 | LM_LOSS: 0.4377 | LB_LOSS: 1.0182
[2026-05-24 15:46:22] Validation | Batch 90/1463 | Loss: 0.9464 | LM_LOSS: 0.4373 | LB_LOSS: 1.0182
[2026-05-24 15:46:23] Validation | Batch 100/1463 | Loss: 0.9470 | LM_LOSS: 0.4379 | LB_LOSS: 1.0183
[2026-05-24 15:46:25] Validation | Batch 110/1463 | Loss: 0.9454 | LM_LOSS: 0.4361 | LB_LOSS: 1.0185
[2026-05-24 15:46:26] Validation | Batch 120/1463 | Loss: 0.9468 | LM_LOSS: 0.4376 | LB_LOSS: 1.0185
[2026-05-24 15:46:28] Validation | Batch 130/1463 | Loss: 0.9503 | LM_LOSS: 0.4411 | LB_LOSS: 1.0185
[2026-05-24 15:46:30] Validation | Batch 140/1463 | Loss: 0.9514 | LM_LOSS: 0.4421 | LB_LOSS: 1.0186
[2026-05-24 15:46:31] Validation | Batch 150/1463 | Loss: 0.9490 | LM_LOSS: 0.4397 | LB_LOSS: 1.0186
[2026-05-24 15:46:33] Validation | Batch 160/1463 | Loss: 0.9501 | LM_LOSS: 0.4409 | LB_LOSS: 1.0185
[2026-05-24 15:46:35] Validation | Batch 170/1463 | Loss: 0.9497 | LM_LOSS: 0.4404 | LB_LOSS: 1.0186
[2026-05-24 15:46:36] Validation | Batch 180/1463 | Loss: 0.9505 | LM_LOSS: 0.4412 | LB_LOSS: 1.0187
[2026-05-24 15:46:38] Validation | Batch 190/1463 | Loss: 0.9512 | LM_LOSS: 0.4418 | LB_LOSS: 1.0187
[2026-05-24 15:46:39] Validation | Batch 200/1463 | Loss: 0.9505 | LM_LOSS: 0.4411 | LB_LOSS: 1.0187
[2026-05-24 15:46:41] Validation | Batch 210/1463 | Loss: 0.9511 | LM_LOSS: 0.4417 | LB_LOSS: 1.0188
[2026-05-24 15:46:43] Validation | Batch 220/1463 | Loss: 0.9500 | LM_LOSS: 0.4405 | LB_LOSS: 1.0189
[2026-05-24 15:46:44] Validation | Batch 230/1463 | Loss: 0.9514 | LM_LOSS: 0.4420 | LB_LOSS: 1.0187
[2026-05-24 15:46:46] Validation | Batch 240/1463 | Loss: 0.9519 | LM_LOSS: 0.4426 | LB_LOSS: 1.0187
[2026-05-24 15:46:48] Validation | Batch 250/1463 | Loss: 0.9504 | LM_LOSS: 0.4410 | LB_LOSS: 1.0187
[2026-05-24 15:46:49] Validation | Batch 260/1463 | Loss: 0.9528 | LM_LOSS: 0.4434 | LB_LOSS: 1.0189
[2026-05-24 15:46:51] Validation | Batch 270/1463 | Loss: 0.9517 | LM_LOSS: 0.4423 | LB_LOSS: 1.0188
[2026-05-24 15:46:53] Validation | Batch 280/1463 | Loss: 0.9529 | LM_LOSS: 0.4435 | LB_LOSS: 1.0189
[2026-05-24 15:46:54] Validation | Batch 290/1463 | Loss: 0.9516 | LM_LOSS: 0.4421 | LB_LOSS: 1.0188
[2026-05-24 15:46:55] Validation | Batch 300/1463 | Loss: 0.9525 | LM_LOSS: 0.4430 | LB_LOSS: 1.0190
[2026-05-24 15:46:57] Validation | Batch 310/1463 | Loss: 0.9534 | LM_LOSS: 0.4440 | LB_LOSS: 1.0190
[2026-05-24 15:46:59] Validation | Batch 320/1463 | Loss: 0.9516 | LM_LOSS: 0.4423 | LB_LOSS: 1.0188
[2026-05-24 15:47:00] Validation | Batch 330/1463 | Loss: 0.9517 | LM_LOSS: 0.4423 | LB_LOSS: 1.0188
[2026-05-24 15:47:02] Validation | Batch 340/1463 | Loss: 0.9513 | LM_LOSS: 0.4419 | LB_LOSS: 1.0188
[2026-05-24 15:47:04] Validation | Batch 350/1463 | Loss: 0.9518 | LM_LOSS: 0.4423 | LB_LOSS: 1.0188
[2026-05-24 15:47:05] Validation | Batch 360/1463 | Loss: 0.9519 | LM_LOSS: 0.4424 | LB_LOSS: 1.0188
[2026-05-24 15:47:06] Validation | Batch 370/1463 | Loss: 0.9520 | LM_LOSS: 0.4426 | LB_LOSS: 1.0189
[2026-05-24 15:47:08] Validation | Batch 380/1463 | Loss: 0.9519 | LM_LOSS: 0.4425 | LB_LOSS: 1.0188
[2026-05-24 15:47:09] Validation | Batch 390/1463 | Loss: 0.9529 | LM_LOSS: 0.4435 | LB_LOSS: 1.0189
[2026-05-24 15:47:11] Validation | Batch 400/1463 | Loss: 0.9528 | LM_LOSS: 0.4433 | LB_LOSS: 1.0189
[2026-05-24 15:47:13] Validation | Batch 410/1463 | Loss: 0.9526 | LM_LOSS: 0.4432 | LB_LOSS: 1.0189
[2026-05-24 15:47:14] Validation | Batch 420/1463 | Loss: 0.9529 | LM_LOSS: 0.4434 | LB_LOSS: 1.0190
[2026-05-24 15:47:16] Validation | Batch 430/1463 | Loss: 0.9527 | LM_LOSS: 0.4432 | LB_LOSS: 1.0190
[2026-05-24 15:47:17] Validation | Batch 440/1463 | Loss: 0.9532 | LM_LOSS: 0.4437 | LB_LOSS: 1.0191
[2026-05-24 15:47:19] Validation | Batch 450/1463 | Loss: 0.9528 | LM_LOSS: 0.4433 | LB_LOSS: 1.0191
[2026-05-24 15:47:21] Validation | Batch 460/1463 | Loss: 0.9529 | LM_LOSS: 0.4433 | LB_LOSS: 1.0191
[2026-05-24 15:47:22] Validation | Batch 470/1463 | Loss: 0.9535 | LM_LOSS: 0.4440 | LB_LOSS: 1.0191
[2026-05-24 15:47:24] Validation | Batch 480/1463 | Loss: 0.9532 | LM_LOSS: 0.4437 | LB_LOSS: 1.0190
[2026-05-24 15:47:26] Validation | Batch 490/1463 | Loss: 0.9530 | LM_LOSS: 0.4435 | LB_LOSS: 1.0190
[2026-05-24 15:47:28] Validation | Batch 500/1463 | Loss: 0.9528 | LM_LOSS: 0.4433 | LB_LOSS: 1.0191
[2026-05-24 15:47:29] Validation | Batch 510/1463 | Loss: 0.9523 | LM_LOSS: 0.4427 | LB_LOSS: 1.0190
[2026-05-24 15:47:30] Validation | Batch 520/1463 | Loss: 0.9519 | LM_LOSS: 0.4424 | LB_LOSS: 1.0191
[2026-05-24 15:47:32] Validation | Batch 530/1463 | Loss: 0.9524 | LM_LOSS: 0.4429 | LB_LOSS: 1.0190
[2026-05-24 15:47:33] Validation | Batch 540/1463 | Loss: 0.9528 | LM_LOSS: 0.4433 | LB_LOSS: 1.0191
[2026-05-24 15:47:35] Validation | Batch 550/1463 | Loss: 0.9525 | LM_LOSS: 0.4430 | LB_LOSS: 1.0191
[2026-05-24 15:47:36] Validation | Batch 560/1463 | Loss: 0.9531 | LM_LOSS: 0.4435 | LB_LOSS: 1.0192
[2026-05-24 15:47:38] Validation | Batch 570/1463 | Loss: 0.9532 | LM_LOSS: 0.4436 | LB_LOSS: 1.0192
[2026-05-24 15:47:40] Validation | Batch 580/1463 | Loss: 0.9528 | LM_LOSS: 0.4433 | LB_LOSS: 1.0192
[2026-05-24 15:47:42] Validation | Batch 590/1463 | Loss: 0.9528 | LM_LOSS: 0.4432 | LB_LOSS: 1.0192
[2026-05-24 15:47:43] Validation | Batch 600/1463 | Loss: 0.9529 | LM_LOSS: 0.4433 | LB_LOSS: 1.0193
[2026-05-24 15:47:45] Validation | Batch 610/1463 | Loss: 0.9529 | LM_LOSS: 0.4433 | LB_LOSS: 1.0193
[2026-05-24 15:47:47] Validation | Batch 620/1463 | Loss: 0.9525 | LM_LOSS: 0.4429 | LB_LOSS: 1.0193
[2026-05-24 15:47:48] Validation | Batch 630/1463 | Loss: 0.9522 | LM_LOSS: 0.4425 | LB_LOSS: 1.0193
[2026-05-24 15:47:50] Validation | Batch 640/1463 | Loss: 0.9520 | LM_LOSS: 0.4424 | LB_LOSS: 1.0193
[2026-05-24 15:47:51] Validation | Batch 650/1463 | Loss: 0.9514 | LM_LOSS: 0.4418 | LB_LOSS: 1.0193
[2026-05-24 15:47:53] Validation | Batch 660/1463 | Loss: 0.9511 | LM_LOSS: 0.4414 | LB_LOSS: 1.0193
[2026-05-24 15:47:54] Validation | Batch 670/1463 | Loss: 0.9507 | LM_LOSS: 0.4410 | LB_LOSS: 1.0193
[2026-05-24 15:47:55] Validation | Batch 680/1463 | Loss: 0.9507 | LM_LOSS: 0.4410 | LB_LOSS: 1.0192
[2026-05-24 15:47:57] Validation | Batch 690/1463 | Loss: 0.9511 | LM_LOSS: 0.4414 | LB_LOSS: 1.0193
[2026-05-24 15:47:59] Validation | Batch 700/1463 | Loss: 0.9511 | LM_LOSS: 0.4415 | LB_LOSS: 1.0192
[2026-05-24 15:48:00] Validation | Batch 710/1463 | Loss: 0.9515 | LM_LOSS: 0.4418 | LB_LOSS: 1.0193
[2026-05-24 15:48:02] Validation | Batch 720/1463 | Loss: 0.9522 | LM_LOSS: 0.4426 | LB_LOSS: 1.0193
[2026-05-24 15:48:03] Validation | Batch 730/1463 | Loss: 0.9522 | LM_LOSS: 0.4426 | LB_LOSS: 1.0194
[2026-05-24 15:48:05] Validation | Batch 740/1463 | Loss: 0.9520 | LM_LOSS: 0.4423 | LB_LOSS: 1.0193
[2026-05-24 15:48:06] Validation | Batch 750/1463 | Loss: 0.9518 | LM_LOSS: 0.4421 | LB_LOSS: 1.0193
[2026-05-24 15:48:07] Validation | Batch 760/1463 | Loss: 0.9514 | LM_LOSS: 0.4417 | LB_LOSS: 1.0193
[2026-05-24 15:48:09] Validation | Batch 770/1463 | Loss: 0.9513 | LM_LOSS: 0.4416 | LB_LOSS: 1.0193
[2026-05-24 15:48:10] Validation | Batch 780/1463 | Loss: 0.9512 | LM_LOSS: 0.4416 | LB_LOSS: 1.0193
[2026-05-24 15:48:11] Validation | Batch 790/1463 | Loss: 0.9516 | LM_LOSS: 0.4419 | LB_LOSS: 1.0192
[2026-05-24 15:48:13] Validation | Batch 800/1463 | Loss: 0.9515 | LM_LOSS: 0.4419 | LB_LOSS: 1.0193
[2026-05-24 15:48:15] Validation | Batch 810/1463 | Loss: 0.9511 | LM_LOSS: 0.4415 | LB_LOSS: 1.0192
[2026-05-24 15:48:16] Validation | Batch 820/1463 | Loss: 0.9512 | LM_LOSS: 0.4416 | LB_LOSS: 1.0192
[2026-05-24 15:48:18] Validation | Batch 830/1463 | Loss: 0.9513 | LM_LOSS: 0.4417 | LB_LOSS: 1.0192
[2026-05-24 15:48:20] Validation | Batch 840/1463 | Loss: 0.9512 | LM_LOSS: 0.4415 | LB_LOSS: 1.0193
[2026-05-24 15:48:21] Validation | Batch 850/1463 | Loss: 0.9514 | LM_LOSS: 0.4417 | LB_LOSS: 1.0193
[2026-05-24 15:48:23] Validation | Batch 860/1463 | Loss: 0.9514 | LM_LOSS: 0.4418 | LB_LOSS: 1.0193
[2026-05-24 15:48:24] Validation | Batch 870/1463 | Loss: 0.9516 | LM_LOSS: 0.4419 | LB_LOSS: 1.0193
[2026-05-24 15:48:26] Validation | Batch 880/1463 | Loss: 0.9508 | LM_LOSS: 0.4412 | LB_LOSS: 1.0193
[2026-05-24 15:48:27] Validation | Batch 890/1463 | Loss: 0.9508 | LM_LOSS: 0.4412 | LB_LOSS: 1.0193
[2026-05-24 15:48:29] Validation | Batch 900/1463 | Loss: 0.9504 | LM_LOSS: 0.4408 | LB_LOSS: 1.0193
[2026-05-24 15:48:31] Validation | Batch 910/1463 | Loss: 0.9505 | LM_LOSS: 0.4408 | LB_LOSS: 1.0193
[2026-05-24 15:48:33] Validation | Batch 920/1463 | Loss: 0.9508 | LM_LOSS: 0.4411 | LB_LOSS: 1.0193
[2026-05-24 15:48:34] Validation | Batch 930/1463 | Loss: 0.9503 | LM_LOSS: 0.4407 | LB_LOSS: 1.0193
[2026-05-24 15:48:36] Validation | Batch 940/1463 | Loss: 0.9500 | LM_LOSS: 0.4404 | LB_LOSS: 1.0192
[2026-05-24 15:48:37] Validation | Batch 950/1463 | Loss: 0.9504 | LM_LOSS: 0.4408 | LB_LOSS: 1.0192
[2026-05-24 15:48:39] Validation | Batch 960/1463 | Loss: 0.9505 | LM_LOSS: 0.4409 | LB_LOSS: 1.0192
[2026-05-24 15:48:41] Validation | Batch 970/1463 | Loss: 0.9507 | LM_LOSS: 0.4411 | LB_LOSS: 1.0192
[2026-05-24 15:48:42] Validation | Batch 980/1463 | Loss: 0.9511 | LM_LOSS: 0.4415 | LB_LOSS: 1.0192
[2026-05-24 15:48:44] Validation | Batch 990/1463 | Loss: 0.9512 | LM_LOSS: 0.4416 | LB_LOSS: 1.0192
[2026-05-24 15:48:45] Validation | Batch 1000/1463 | Loss: 0.9519 | LM_LOSS: 0.4423 | LB_LOSS: 1.0192
[2026-05-24 15:48:47] Validation | Batch 1010/1463 | Loss: 0.9520 | LM_LOSS: 0.4423 | LB_LOSS: 1.0193
[2026-05-24 15:48:49] Validation | Batch 1020/1463 | Loss: 0.9523 | LM_LOSS: 0.4426 | LB_LOSS: 1.0193
[2026-05-24 15:48:51] Validation | Batch 1030/1463 | Loss: 0.9528 | LM_LOSS: 0.4431 | LB_LOSS: 1.0193
[2026-05-24 15:48:52] Validation | Batch 1040/1463 | Loss: 0.9522 | LM_LOSS: 0.4426 | LB_LOSS: 1.0193
[2026-05-24 15:48:54] Validation | Batch 1050/1463 | Loss: 0.9521 | LM_LOSS: 0.4425 | LB_LOSS: 1.0192
[2026-05-24 15:48:55] Validation | Batch 1060/1463 | Loss: 0.9520 | LM_LOSS: 0.4424 | LB_LOSS: 1.0192
[2026-05-24 15:48:57] Validation | Batch 1070/1463 | Loss: 0.9521 | LM_LOSS: 0.4425 | LB_LOSS: 1.0192
[2026-05-24 15:48:58] Validation | Batch 1080/1463 | Loss: 0.9518 | LM_LOSS: 0.4422 | LB_LOSS: 1.0192
[2026-05-24 15:49:00] Validation | Batch 1090/1463 | Loss: 0.9518 | LM_LOSS: 0.4422 | LB_LOSS: 1.0192
[2026-05-24 15:49:01] Validation | Batch 1100/1463 | Loss: 0.9517 | LM_LOSS: 0.4421 | LB_LOSS: 1.0192
[2026-05-24 15:49:03] Validation | Batch 1110/1463 | Loss: 0.9517 | LM_LOSS: 0.4421 | LB_LOSS: 1.0192
[2026-05-24 15:49:04] Validation | Batch 1120/1463 | Loss: 0.9515 | LM_LOSS: 0.4419 | LB_LOSS: 1.0192
[2026-05-24 15:49:06] Validation | Batch 1130/1463 | Loss: 0.9511 | LM_LOSS: 0.4415 | LB_LOSS: 1.0192
[2026-05-24 15:49:08] Validation | Batch 1140/1463 | Loss: 0.9514 | LM_LOSS: 0.4418 | LB_LOSS: 1.0192
[2026-05-24 15:49:10] Validation | Batch 1150/1463 | Loss: 0.9513 | LM_LOSS: 0.4417 | LB_LOSS: 1.0192
[2026-05-24 15:49:11] Validation | Batch 1160/1463 | Loss: 0.9513 | LM_LOSS: 0.4417 | LB_LOSS: 1.0192
[2026-05-24 15:49:13] Validation | Batch 1170/1463 | Loss: 0.9511 | LM_LOSS: 0.4415 | LB_LOSS: 1.0192
[2026-05-24 15:49:14] Validation | Batch 1180/1463 | Loss: 0.9511 | LM_LOSS: 0.4415 | LB_LOSS: 1.0192
[2026-05-24 15:49:16] Validation | Batch 1190/1463 | Loss: 0.9513 | LM_LOSS: 0.4417 | LB_LOSS: 1.0192
[2026-05-24 15:49:18] Validation | Batch 1200/1463 | Loss: 0.9514 | LM_LOSS: 0.4418 | LB_LOSS: 1.0192
[2026-05-24 15:49:19] Validation | Batch 1210/1463 | Loss: 0.9518 | LM_LOSS: 0.4422 | LB_LOSS: 1.0192
[2026-05-24 15:49:21] Validation | Batch 1220/1463 | Loss: 0.9521 | LM_LOSS: 0.4425 | LB_LOSS: 1.0192
[2026-05-24 15:49:22] Validation | Batch 1230/1463 | Loss: 0.9520 | LM_LOSS: 0.4424 | LB_LOSS: 1.0192
[2026-05-24 15:49:24] Validation | Batch 1240/1463 | Loss: 0.9524 | LM_LOSS: 0.4428 | LB_LOSS: 1.0192
[2026-05-24 15:49:25] Validation | Batch 1250/1463 | Loss: 0.9527 | LM_LOSS: 0.4431 | LB_LOSS: 1.0192
[2026-05-24 15:49:27] Validation | Batch 1260/1463 | Loss: 0.9526 | LM_LOSS: 0.4430 | LB_LOSS: 1.0193
[2026-05-24 15:49:29] Validation | Batch 1270/1463 | Loss: 0.9524 | LM_LOSS: 0.4428 | LB_LOSS: 1.0193
[2026-05-24 15:49:30] Validation | Batch 1280/1463 | Loss: 0.9522 | LM_LOSS: 0.4426 | LB_LOSS: 1.0192
[2026-05-24 15:49:32] Validation | Batch 1290/1463 | Loss: 0.9522 | LM_LOSS: 0.4426 | LB_LOSS: 1.0192
[2026-05-24 15:49:34] Validation | Batch 1300/1463 | Loss: 0.9519 | LM_LOSS: 0.4423 | LB_LOSS: 1.0192
[2026-05-24 15:49:35] Validation | Batch 1310/1463 | Loss: 0.9518 | LM_LOSS: 0.4422 | LB_LOSS: 1.0192
[2026-05-24 15:49:36] Validation | Batch 1320/1463 | Loss: 0.9519 | LM_LOSS: 0.4423 | LB_LOSS: 1.0192
[2026-05-24 15:49:38] Validation | Batch 1330/1463 | Loss: 0.9518 | LM_LOSS: 0.4422 | LB_LOSS: 1.0192
[2026-05-24 15:49:39] Validation | Batch 1340/1463 | Loss: 0.9520 | LM_LOSS: 0.4424 | LB_LOSS: 1.0192
[2026-05-24 15:49:41] Validation | Batch 1350/1463 | Loss: 0.9520 | LM_LOSS: 0.4424 | LB_LOSS: 1.0192
[2026-05-24 15:49:43] Validation | Batch 1360/1463 | Loss: 0.9523 | LM_LOSS: 0.4427 | LB_LOSS: 1.0192
[2026-05-24 15:49:44] Validation | Batch 1370/1463 | Loss: 0.9527 | LM_LOSS: 0.4431 | LB_LOSS: 1.0192
[2026-05-24 15:49:46] Validation | Batch 1380/1463 | Loss: 0.9526 | LM_LOSS: 0.4430 | LB_LOSS: 1.0192
[2026-05-24 15:49:47] Validation | Batch 1390/1463 | Loss: 0.9525 | LM_LOSS: 0.4429 | LB_LOSS: 1.0192
[2026-05-24 15:49:49] Validation | Batch 1400/1463 | Loss: 0.9528 | LM_LOSS: 0.4432 | LB_LOSS: 1.0192
[2026-05-24 15:49:50] Validation | Batch 1410/1463 | Loss: 0.9530 | LM_LOSS: 0.4434 | LB_LOSS: 1.0192
[2026-05-24 15:49:52] Validation | Batch 1420/1463 | Loss: 0.9531 | LM_LOSS: 0.4435 | LB_LOSS: 1.0192
[2026-05-24 15:49:54] Validation | Batch 1430/1463 | Loss: 0.9532 | LM_LOSS: 0.4436 | LB_LOSS: 1.0192
[2026-05-24 15:49:55] Validation | Batch 1440/1463 | Loss: 0.9536 | LM_LOSS: 0.4440 | LB_LOSS: 1.0192
[2026-05-24 15:49:57] Validation | Batch 1450/1463 | Loss: 0.9532 | LM_LOSS: 0.4437 | LB_LOSS: 1.0192
[2026-05-24 15:49:58] Validation | Batch 1460/1463 | Loss: 0.9536 | LM_LOSS: 0.4440 | LB_LOSS: 1.0191
[2026-05-24 15:49:59] Validation | Batch 1463/1463 | Loss: 0.9535 | LM_LOSS: 0.4439 | LB_LOSS: 1.0191
[2026-05-24 15:49:59] Validation | Loss: 0.9535 | LM_LOSS: 0.4439 | LB_LOSS: 1.0191 | PPL: 1.56 | Time: 231.69s
[2026-05-24 15:50:10] Epoch 3 | Step 12010 | Loss: 0.8729 | LM: 0.3636 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.47e-05
[2026-05-24 15:50:20] Epoch 3 | Step 12020 | Loss: 0.8729 | LM: 0.3639 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.44e-05
[2026-05-24 15:50:31] Epoch 3 | Step 12030 | Loss: 0.8729 | LM: 0.3639 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.40e-05
[2026-05-24 15:50:41] Epoch 3 | Step 12040 | Loss: 0.8731 | LM: 0.3642 | LB: 1.0198 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.36e-05
[2026-05-24 15:50:52] Epoch 3 | Step 12050 | Loss: 0.8730 | LM: 0.3641 | LB: 1.0198 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 8.32e-05
[2026-05-24 15:51:02] Epoch 3 | Step 12060 | Loss: 0.8730 | LM: 0.3641 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.28e-05
[2026-05-24 15:51:13] Epoch 3 | Step 12070 | Loss: 0.8730 | LM: 0.3642 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.24e-05
[2026-05-24 15:51:24] Epoch 3 | Step 12080 | Loss: 0.8730 | LM: 0.3644 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.20e-05
[2026-05-24 15:51:34] Epoch 3 | Step 12090 | Loss: 0.8729 | LM: 0.3643 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.16e-05
[2026-05-24 15:51:45] Epoch 3 | Step 12100 | Loss: 0.8728 | LM: 0.3641 | LB: 1.0200 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.12e-05
[2026-05-24 15:51:56] Epoch 3 | Step 12110 | Loss: 0.8727 | LM: 0.3640 | LB: 1.0200 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.08e-05
[2026-05-24 15:52:06] Epoch 3 | Step 12120 | Loss: 0.8726 | LM: 0.3638 | LB: 1.0200 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 8.04e-05
[2026-05-24 15:52:17] Epoch 3 | Step 12130 | Loss: 0.8726 | LM: 0.3637 | LB: 1.0200 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 7.99e-05
[2026-05-24 15:52:28] Epoch 3 | Step 12140 | Loss: 0.8726 | LM: 0.3639 | LB: 1.0200 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 7.95e-05
[2026-05-24 15:52:38] Epoch 3 | Step 12150 | Loss: 0.8727 | LM: 0.3639 | LB: 1.0200 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 7.91e-05
[2026-05-24 15:52:49] Epoch 3 | Step 12160 | Loss: 0.8727 | LM: 0.3638 | LB: 1.0200 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 7.87e-05
[2026-05-24 15:52:59] Epoch 3 | Step 12170 | Loss: 0.8727 | LM: 0.3639 | LB: 1.0200 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.178 | HR1: 0.150/SR1: 0.133 | LR: 7.83e-05
[2026-05-24 15:53:10] Epoch 3 | Step 12180 | Loss: 0.8727 | LM: 0.3639 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 7.78e-05
[2026-05-24 15:53:21] Epoch 3 | Step 12190 | Loss: 0.8727 | LM: 0.3639 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 7.74e-05
[2026-05-24 15:53:31] Epoch 3 | Step 12200 | Loss: 0.8727 | LM: 0.3639 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 7.69e-05
[2026-05-24 15:53:42] Epoch 3 | Step 12210 | Loss: 0.8728 | LM: 0.3639 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 7.65e-05
[2026-05-24 15:53:52] Epoch 3 | Step 12220 | Loss: 0.8729 | LM: 0.3642 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 7.61e-05
[2026-05-24 15:54:03] Epoch 3 | Step 12230 | Loss: 0.8728 | LM: 0.3642 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 7.56e-05
[2026-05-24 15:54:13] Epoch 3 | Step 12240 | Loss: 0.8728 | LM: 0.3642 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 7.52e-05
[2026-05-24 15:54:24] Epoch 3 | Step 12250 | Loss: 0.8729 | LM: 0.3643 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 7.47e-05
[2026-05-24 15:54:34] Epoch 3 | Step 12260 | Loss: 0.8728 | LM: 0.3642 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 7.43e-05
[2026-05-24 15:54:45] Epoch 3 | Step 12270 | Loss: 0.8728 | LM: 0.3640 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 7.38e-05
[2026-05-24 15:54:55] Epoch 3 | Step 12280 | Loss: 0.8729 | LM: 0.3641 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 7.34e-05
[2026-05-24 15:55:06] Epoch 3 | Step 12290 | Loss: 0.8728 | LM: 0.3640 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 7.29e-05
[2026-05-24 15:55:16] Epoch 3 | Step 12300 | Loss: 0.8729 | LM: 0.3641 | LB: 1.0199 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 7.24e-05
[2026-05-24 15:55:27] Epoch 3 | Step 12310 | Loss: 0.8729 | LM: 0.3644 | LB: 1.0198 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 7.20e-05
[2026-05-24 15:55:37] Epoch 3 | Step 12320 | Loss: 0.8728 | LM: 0.3643 | LB: 1.0198 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 7.15e-05
[2026-05-24 15:55:48] Epoch 3 | Step 12330 | Loss: 0.8729 | LM: 0.3644 | LB: 1.0198 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 7.10e-05
[2026-05-24 15:55:58] Epoch 3 | Step 12340 | Loss: 0.8731 | LM: 0.3647 | LB: 1.0198 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 7.06e-05
[2026-05-24 15:56:09] Epoch 3 | Step 12350 | Loss: 0.8731 | LM: 0.3649 | LB: 1.0198 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 7.01e-05
[2026-05-24 15:56:20] Epoch 3 | Step 12360 | Loss: 0.8731 | LM: 0.3646 | LB: 1.0198 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.96e-05
[2026-05-24 15:56:30] Epoch 3 | Step 12370 | Loss: 0.8730 | LM: 0.3646 | LB: 1.0198 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.91e-05
[2026-05-24 15:56:41] Epoch 3 | Step 12380 | Loss: 0.8731 | LM: 0.3647 | LB: 1.0198 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.87e-05
[2026-05-24 15:56:52] Epoch 3 | Step 12390 | Loss: 0.8731 | LM: 0.3647 | LB: 1.0198 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.82e-05
[2026-05-24 15:57:03] Epoch 3 | Step 12400 | Loss: 0.8732 | LM: 0.3647 | LB: 1.0198 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.77e-05
[2026-05-24 15:57:14] Epoch 3 | Step 12410 | Loss: 0.8732 | LM: 0.3647 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.72e-05
[2026-05-24 15:57:25] Epoch 3 | Step 12420 | Loss: 0.8732 | LM: 0.3647 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.67e-05
[2026-05-24 15:57:36] Epoch 3 | Step 12430 | Loss: 0.8732 | LM: 0.3647 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.62e-05
[2026-05-24 15:57:47] Epoch 3 | Step 12440 | Loss: 0.8731 | LM: 0.3645 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.58e-05
[2026-05-24 15:57:58] Epoch 3 | Step 12450 | Loss: 0.8731 | LM: 0.3645 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.53e-05
[2026-05-24 15:58:10] Epoch 3 | Step 12460 | Loss: 0.8730 | LM: 0.3644 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.48e-05
[2026-05-24 15:58:21] Epoch 3 | Step 12470 | Loss: 0.8731 | LM: 0.3645 | LB: 1.0198 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.43e-05
[2026-05-24 15:58:32] Epoch 3 | Step 12480 | Loss: 0.8732 | LM: 0.3646 | LB: 1.0198 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.38e-05
[2026-05-24 15:58:43] Epoch 3 | Step 12490 | Loss: 0.8732 | LM: 0.3645 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.33e-05
[2026-05-24 15:58:54] Epoch 3 | Step 12500 | Loss: 0.8732 | LM: 0.3644 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.28e-05
[2026-05-24 15:59:05] Epoch 3 | Step 12510 | Loss: 0.8733 | LM: 0.3647 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.23e-05
[2026-05-24 15:59:16] Epoch 3 | Step 12520 | Loss: 0.8733 | LM: 0.3646 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.18e-05
[2026-05-24 15:59:27] Epoch 3 | Step 12530 | Loss: 0.8733 | LM: 0.3645 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.13e-05
[2026-05-24 15:59:38] Epoch 3 | Step 12540 | Loss: 0.8733 | LM: 0.3644 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.08e-05
[2026-05-24 15:59:49] Epoch 3 | Step 12550 | Loss: 0.8733 | LM: 0.3643 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 6.03e-05
[2026-05-24 16:00:00] Epoch 3 | Step 12560 | Loss: 0.8734 | LM: 0.3644 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.193/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.98e-05
[2026-05-24 16:00:12] Epoch 3 | Step 12570 | Loss: 0.8733 | LM: 0.3643 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.93e-05
[2026-05-24 16:00:23] Epoch 3 | Step 12580 | Loss: 0.8733 | LM: 0.3641 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.88e-05
[2026-05-24 16:00:34] Epoch 3 | Step 12590 | Loss: 0.8733 | LM: 0.3642 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.83e-05
[2026-05-24 16:00:44] Epoch 3 | Step 12600 | Loss: 0.8733 | LM: 0.3642 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.78e-05
[2026-05-24 16:00:55] Epoch 3 | Step 12610 | Loss: 0.8733 | LM: 0.3643 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.73e-05
[2026-05-24 16:01:05] Epoch 3 | Step 12620 | Loss: 0.8734 | LM: 0.3642 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.68e-05
[2026-05-24 16:01:16] Epoch 3 | Step 12630 | Loss: 0.8733 | LM: 0.3641 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.63e-05
[2026-05-24 16:01:27] Epoch 3 | Step 12640 | Loss: 0.8734 | LM: 0.3642 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.58e-05
[2026-05-24 16:01:37] Epoch 3 | Step 12650 | Loss: 0.8735 | LM: 0.3642 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.53e-05
[2026-05-24 16:01:47] Epoch 3 | Step 12660 | Loss: 0.8734 | LM: 0.3641 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.48e-05
[2026-05-24 16:01:58] Epoch 3 | Step 12670 | Loss: 0.8734 | LM: 0.3641 | LB: 1.0197 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.43e-05
[2026-05-24 16:02:09] Epoch 3 | Step 12680 | Loss: 0.8734 | LM: 0.3641 | LB: 1.0196 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.38e-05
[2026-05-24 16:02:19] Epoch 3 | Step 12690 | Loss: 0.8733 | LM: 0.3640 | LB: 1.0196 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.33e-05
[2026-05-24 16:02:30] Epoch 3 | Step 12700 | Loss: 0.8733 | LM: 0.3640 | LB: 1.0196 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.28e-05
[2026-05-24 16:02:40] Epoch 3 | Step 12710 | Loss: 0.8733 | LM: 0.3641 | LB: 1.0196 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.23e-05
[2026-05-24 16:02:51] Epoch 3 | Step 12720 | Loss: 0.8732 | LM: 0.3639 | LB: 1.0196 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.18e-05
[2026-05-24 16:03:01] Epoch 3 | Step 12730 | Loss: 0.8733 | LM: 0.3640 | LB: 1.0196 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.13e-05
[2026-05-24 16:03:12] Epoch 3 | Step 12740 | Loss: 0.8733 | LM: 0.3640 | LB: 1.0196 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.08e-05
[2026-05-24 16:03:22] Epoch 3 | Step 12750 | Loss: 0.8733 | LM: 0.3641 | LB: 1.0196 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 5.03e-05
[2026-05-24 16:03:33] Epoch 3 | Step 12760 | Loss: 0.8733 | LM: 0.3641 | LB: 1.0196 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.98e-05
[2026-05-24 16:03:44] Epoch 3 | Step 12770 | Loss: 0.8734 | LM: 0.3641 | LB: 1.0196 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.93e-05
[2026-05-24 16:03:54] Epoch 3 | Step 12780 | Loss: 0.8735 | LM: 0.3642 | LB: 1.0196 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.88e-05
[2026-05-24 16:04:05] Epoch 3 | Step 12790 | Loss: 0.8735 | LM: 0.3642 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.83e-05
[2026-05-24 16:04:16] Epoch 3 | Step 12800 | Loss: 0.8735 | LM: 0.3643 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.78e-05
[2026-05-24 16:04:26] Epoch 3 | Step 12810 | Loss: 0.8735 | LM: 0.3644 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.73e-05
[2026-05-24 16:04:37] Epoch 3 | Step 12820 | Loss: 0.8735 | LM: 0.3644 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.68e-05
[2026-05-24 16:04:47] Epoch 3 | Step 12830 | Loss: 0.8735 | LM: 0.3645 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.63e-05
[2026-05-24 16:04:58] Epoch 3 | Step 12840 | Loss: 0.8735 | LM: 0.3645 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.58e-05
[2026-05-24 16:05:09] Epoch 3 | Step 12850 | Loss: 0.8736 | LM: 0.3646 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.53e-05
[2026-05-24 16:05:19] Epoch 3 | Step 12860 | Loss: 0.8736 | LM: 0.3647 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.48e-05
[2026-05-24 16:05:30] Epoch 3 | Step 12870 | Loss: 0.8736 | LM: 0.3645 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.43e-05
[2026-05-24 16:05:40] Epoch 3 | Step 12880 | Loss: 0.8737 | LM: 0.3646 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.39e-05
[2026-05-24 16:05:51] Epoch 3 | Step 12890 | Loss: 0.8737 | LM: 0.3647 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.34e-05
[2026-05-24 16:06:01] Epoch 3 | Step 12900 | Loss: 0.8737 | LM: 0.3646 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.29e-05
[2026-05-24 16:06:13] Epoch 3 | Step 12910 | Loss: 0.8737 | LM: 0.3647 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.24e-05
[2026-05-24 16:06:24] Epoch 3 | Step 12920 | Loss: 0.8738 | LM: 0.3649 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.19e-05
[2026-05-24 16:06:35] Epoch 3 | Step 12930 | Loss: 0.8738 | LM: 0.3649 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.14e-05
[2026-05-24 16:06:46] Epoch 3 | Step 12940 | Loss: 0.8738 | LM: 0.3649 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.10e-05
[2026-05-24 16:06:57] Epoch 3 | Step 12950 | Loss: 0.8738 | LM: 0.3651 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.05e-05
[2026-05-24 16:07:08] Epoch 3 | Step 12960 | Loss: 0.8738 | LM: 0.3650 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 4.00e-05
[2026-05-24 16:07:19] Epoch 3 | Step 12970 | Loss: 0.8738 | LM: 0.3649 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.95e-05
[2026-05-24 16:07:30] Epoch 3 | Step 12980 | Loss: 0.8738 | LM: 0.3648 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.91e-05
[2026-05-24 16:07:41] Epoch 3 | Step 12990 | Loss: 0.8737 | LM: 0.3647 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.86e-05
[2026-05-24 16:07:52] Epoch 3 | Step 13000 | Loss: 0.8737 | LM: 0.3648 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.81e-05
[2026-05-24 16:07:54] Validation | Batch 10/1463 | Loss: 0.9213 | LM_LOSS: 0.4153 | LB_LOSS: 1.0119
[2026-05-24 16:07:55] Validation | Batch 20/1463 | Loss: 0.9284 | LM_LOSS: 0.4213 | LB_LOSS: 1.0142
[2026-05-24 16:07:57] Validation | Batch 30/1463 | Loss: 0.9300 | LM_LOSS: 0.4226 | LB_LOSS: 1.0149
[2026-05-24 16:07:58] Validation | Batch 40/1463 | Loss: 0.9415 | LM_LOSS: 0.4337 | LB_LOSS: 1.0157
[2026-05-24 16:08:00] Validation | Batch 50/1463 | Loss: 0.9458 | LM_LOSS: 0.4383 | LB_LOSS: 1.0151
[2026-05-24 16:08:02] Validation | Batch 60/1463 | Loss: 0.9469 | LM_LOSS: 0.4393 | LB_LOSS: 1.0153
[2026-05-24 16:08:04] Validation | Batch 70/1463 | Loss: 0.9457 | LM_LOSS: 0.4381 | LB_LOSS: 1.0153
[2026-05-24 16:08:05] Validation | Batch 80/1463 | Loss: 0.9468 | LM_LOSS: 0.4390 | LB_LOSS: 1.0155
[2026-05-24 16:08:07] Validation | Batch 90/1463 | Loss: 0.9463 | LM_LOSS: 0.4386 | LB_LOSS: 1.0155
[2026-05-24 16:08:08] Validation | Batch 100/1463 | Loss: 0.9474 | LM_LOSS: 0.4396 | LB_LOSS: 1.0155
[2026-05-24 16:08:10] Validation | Batch 110/1463 | Loss: 0.9457 | LM_LOSS: 0.4378 | LB_LOSS: 1.0157
[2026-05-24 16:08:12] Validation | Batch 120/1463 | Loss: 0.9468 | LM_LOSS: 0.4389 | LB_LOSS: 1.0157
[2026-05-24 16:08:13] Validation | Batch 130/1463 | Loss: 0.9506 | LM_LOSS: 0.4427 | LB_LOSS: 1.0157
[2026-05-24 16:08:15] Validation | Batch 140/1463 | Loss: 0.9517 | LM_LOSS: 0.4438 | LB_LOSS: 1.0158
[2026-05-24 16:08:17] Validation | Batch 150/1463 | Loss: 0.9491 | LM_LOSS: 0.4412 | LB_LOSS: 1.0159
[2026-05-24 16:08:18] Validation | Batch 160/1463 | Loss: 0.9503 | LM_LOSS: 0.4424 | LB_LOSS: 1.0158
[2026-05-24 16:08:20] Validation | Batch 170/1463 | Loss: 0.9500 | LM_LOSS: 0.4420 | LB_LOSS: 1.0158
[2026-05-24 16:08:22] Validation | Batch 180/1463 | Loss: 0.9508 | LM_LOSS: 0.4428 | LB_LOSS: 1.0159
[2026-05-24 16:08:23] Validation | Batch 190/1463 | Loss: 0.9515 | LM_LOSS: 0.4435 | LB_LOSS: 1.0159
[2026-05-24 16:08:25] Validation | Batch 200/1463 | Loss: 0.9511 | LM_LOSS: 0.4431 | LB_LOSS: 1.0160
[2026-05-24 16:08:27] Validation | Batch 210/1463 | Loss: 0.9517 | LM_LOSS: 0.4437 | LB_LOSS: 1.0160
[2026-05-24 16:08:28] Validation | Batch 220/1463 | Loss: 0.9507 | LM_LOSS: 0.4426 | LB_LOSS: 1.0161
[2026-05-24 16:08:30] Validation | Batch 230/1463 | Loss: 0.9520 | LM_LOSS: 0.4440 | LB_LOSS: 1.0159
[2026-05-24 16:08:32] Validation | Batch 240/1463 | Loss: 0.9524 | LM_LOSS: 0.4445 | LB_LOSS: 1.0159
[2026-05-24 16:08:33] Validation | Batch 250/1463 | Loss: 0.9507 | LM_LOSS: 0.4428 | LB_LOSS: 1.0159
[2026-05-24 16:08:35] Validation | Batch 260/1463 | Loss: 0.9530 | LM_LOSS: 0.4450 | LB_LOSS: 1.0161
[2026-05-24 16:08:36] Validation | Batch 270/1463 | Loss: 0.9518 | LM_LOSS: 0.4438 | LB_LOSS: 1.0161
[2026-05-24 16:08:38] Validation | Batch 280/1463 | Loss: 0.9531 | LM_LOSS: 0.4451 | LB_LOSS: 1.0161
[2026-05-24 16:08:40] Validation | Batch 290/1463 | Loss: 0.9518 | LM_LOSS: 0.4438 | LB_LOSS: 1.0161
[2026-05-24 16:08:41] Validation | Batch 300/1463 | Loss: 0.9527 | LM_LOSS: 0.4446 | LB_LOSS: 1.0162
[2026-05-24 16:08:43] Validation | Batch 310/1463 | Loss: 0.9537 | LM_LOSS: 0.4457 | LB_LOSS: 1.0162
[2026-05-24 16:08:44] Validation | Batch 320/1463 | Loss: 0.9520 | LM_LOSS: 0.4440 | LB_LOSS: 1.0160
[2026-05-24 16:08:46] Validation | Batch 330/1463 | Loss: 0.9519 | LM_LOSS: 0.4439 | LB_LOSS: 1.0160
[2026-05-24 16:08:47] Validation | Batch 340/1463 | Loss: 0.9515 | LM_LOSS: 0.4435 | LB_LOSS: 1.0160
[2026-05-24 16:08:49] Validation | Batch 350/1463 | Loss: 0.9520 | LM_LOSS: 0.4440 | LB_LOSS: 1.0160
[2026-05-24 16:08:50] Validation | Batch 360/1463 | Loss: 0.9520 | LM_LOSS: 0.4440 | LB_LOSS: 1.0160
[2026-05-24 16:08:52] Validation | Batch 370/1463 | Loss: 0.9522 | LM_LOSS: 0.4441 | LB_LOSS: 1.0161
[2026-05-24 16:08:53] Validation | Batch 380/1463 | Loss: 0.9521 | LM_LOSS: 0.4441 | LB_LOSS: 1.0160
[2026-05-24 16:08:55] Validation | Batch 390/1463 | Loss: 0.9532 | LM_LOSS: 0.4451 | LB_LOSS: 1.0160
[2026-05-24 16:08:56] Validation | Batch 400/1463 | Loss: 0.9529 | LM_LOSS: 0.4449 | LB_LOSS: 1.0160
[2026-05-24 16:08:58] Validation | Batch 410/1463 | Loss: 0.9526 | LM_LOSS: 0.4446 | LB_LOSS: 1.0161
[2026-05-24 16:08:59] Validation | Batch 420/1463 | Loss: 0.9528 | LM_LOSS: 0.4448 | LB_LOSS: 1.0161
[2026-05-24 16:09:01] Validation | Batch 430/1463 | Loss: 0.9526 | LM_LOSS: 0.4445 | LB_LOSS: 1.0162
[2026-05-24 16:09:03] Validation | Batch 440/1463 | Loss: 0.9530 | LM_LOSS: 0.4449 | LB_LOSS: 1.0163
[2026-05-24 16:09:04] Validation | Batch 450/1463 | Loss: 0.9527 | LM_LOSS: 0.4445 | LB_LOSS: 1.0163
[2026-05-24 16:09:06] Validation | Batch 460/1463 | Loss: 0.9526 | LM_LOSS: 0.4445 | LB_LOSS: 1.0162
[2026-05-24 16:09:07] Validation | Batch 470/1463 | Loss: 0.9533 | LM_LOSS: 0.4452 | LB_LOSS: 1.0162
[2026-05-24 16:09:09] Validation | Batch 480/1463 | Loss: 0.9529 | LM_LOSS: 0.4448 | LB_LOSS: 1.0162
[2026-05-24 16:09:11] Validation | Batch 490/1463 | Loss: 0.9526 | LM_LOSS: 0.4445 | LB_LOSS: 1.0162
[2026-05-24 16:09:13] Validation | Batch 500/1463 | Loss: 0.9524 | LM_LOSS: 0.4442 | LB_LOSS: 1.0162
[2026-05-24 16:09:14] Validation | Batch 510/1463 | Loss: 0.9519 | LM_LOSS: 0.4437 | LB_LOSS: 1.0162
[2026-05-24 16:09:16] Validation | Batch 520/1463 | Loss: 0.9517 | LM_LOSS: 0.4435 | LB_LOSS: 1.0163
[2026-05-24 16:09:17] Validation | Batch 530/1463 | Loss: 0.9522 | LM_LOSS: 0.4441 | LB_LOSS: 1.0162
[2026-05-24 16:09:18] Validation | Batch 540/1463 | Loss: 0.9526 | LM_LOSS: 0.4445 | LB_LOSS: 1.0162
[2026-05-24 16:09:20] Validation | Batch 550/1463 | Loss: 0.9523 | LM_LOSS: 0.4442 | LB_LOSS: 1.0163
[2026-05-24 16:09:21] Validation | Batch 560/1463 | Loss: 0.9530 | LM_LOSS: 0.4448 | LB_LOSS: 1.0163
[2026-05-24 16:09:23] Validation | Batch 570/1463 | Loss: 0.9532 | LM_LOSS: 0.4450 | LB_LOSS: 1.0163
[2026-05-24 16:09:25] Validation | Batch 580/1463 | Loss: 0.9528 | LM_LOSS: 0.4446 | LB_LOSS: 1.0163
[2026-05-24 16:09:26] Validation | Batch 590/1463 | Loss: 0.9528 | LM_LOSS: 0.4446 | LB_LOSS: 1.0164
[2026-05-24 16:09:28] Validation | Batch 600/1463 | Loss: 0.9530 | LM_LOSS: 0.4448 | LB_LOSS: 1.0164
[2026-05-24 16:09:30] Validation | Batch 610/1463 | Loss: 0.9530 | LM_LOSS: 0.4447 | LB_LOSS: 1.0164
[2026-05-24 16:09:31] Validation | Batch 620/1463 | Loss: 0.9525 | LM_LOSS: 0.4443 | LB_LOSS: 1.0164
[2026-05-24 16:09:33] Validation | Batch 630/1463 | Loss: 0.9522 | LM_LOSS: 0.4439 | LB_LOSS: 1.0164
[2026-05-24 16:09:34] Validation | Batch 640/1463 | Loss: 0.9519 | LM_LOSS: 0.4437 | LB_LOSS: 1.0165
[2026-05-24 16:09:36] Validation | Batch 650/1463 | Loss: 0.9513 | LM_LOSS: 0.4431 | LB_LOSS: 1.0165
[2026-05-24 16:09:37] Validation | Batch 660/1463 | Loss: 0.9509 | LM_LOSS: 0.4427 | LB_LOSS: 1.0165
[2026-05-24 16:09:39] Validation | Batch 670/1463 | Loss: 0.9505 | LM_LOSS: 0.4423 | LB_LOSS: 1.0164
[2026-05-24 16:09:40] Validation | Batch 680/1463 | Loss: 0.9506 | LM_LOSS: 0.4424 | LB_LOSS: 1.0164
[2026-05-24 16:09:42] Validation | Batch 690/1463 | Loss: 0.9510 | LM_LOSS: 0.4427 | LB_LOSS: 1.0164
[2026-05-24 16:09:43] Validation | Batch 700/1463 | Loss: 0.9510 | LM_LOSS: 0.4428 | LB_LOSS: 1.0164
[2026-05-24 16:09:45] Validation | Batch 710/1463 | Loss: 0.9513 | LM_LOSS: 0.4430 | LB_LOSS: 1.0165
[2026-05-24 16:09:47] Validation | Batch 720/1463 | Loss: 0.9520 | LM_LOSS: 0.4438 | LB_LOSS: 1.0165
[2026-05-24 16:09:48] Validation | Batch 730/1463 | Loss: 0.9520 | LM_LOSS: 0.4437 | LB_LOSS: 1.0165
[2026-05-24 16:09:49] Validation | Batch 740/1463 | Loss: 0.9517 | LM_LOSS: 0.4435 | LB_LOSS: 1.0165
[2026-05-24 16:09:51] Validation | Batch 750/1463 | Loss: 0.9515 | LM_LOSS: 0.4433 | LB_LOSS: 1.0165
[2026-05-24 16:09:52] Validation | Batch 760/1463 | Loss: 0.9512 | LM_LOSS: 0.4430 | LB_LOSS: 1.0164
[2026-05-24 16:09:53] Validation | Batch 770/1463 | Loss: 0.9511 | LM_LOSS: 0.4429 | LB_LOSS: 1.0165
[2026-05-24 16:09:55] Validation | Batch 780/1463 | Loss: 0.9510 | LM_LOSS: 0.4428 | LB_LOSS: 1.0164
[2026-05-24 16:09:56] Validation | Batch 790/1463 | Loss: 0.9513 | LM_LOSS: 0.4431 | LB_LOSS: 1.0164
[2026-05-24 16:09:58] Validation | Batch 800/1463 | Loss: 0.9513 | LM_LOSS: 0.4431 | LB_LOSS: 1.0164
[2026-05-24 16:09:59] Validation | Batch 810/1463 | Loss: 0.9508 | LM_LOSS: 0.4427 | LB_LOSS: 1.0164
[2026-05-24 16:10:01] Validation | Batch 820/1463 | Loss: 0.9510 | LM_LOSS: 0.4428 | LB_LOSS: 1.0164
[2026-05-24 16:10:02] Validation | Batch 830/1463 | Loss: 0.9510 | LM_LOSS: 0.4429 | LB_LOSS: 1.0164
[2026-05-24 16:10:04] Validation | Batch 840/1463 | Loss: 0.9509 | LM_LOSS: 0.4427 | LB_LOSS: 1.0164
[2026-05-24 16:10:06] Validation | Batch 850/1463 | Loss: 0.9511 | LM_LOSS: 0.4429 | LB_LOSS: 1.0164
[2026-05-24 16:10:07] Validation | Batch 860/1463 | Loss: 0.9511 | LM_LOSS: 0.4428 | LB_LOSS: 1.0165
[2026-05-24 16:10:09] Validation | Batch 870/1463 | Loss: 0.9512 | LM_LOSS: 0.4430 | LB_LOSS: 1.0165
[2026-05-24 16:10:10] Validation | Batch 880/1463 | Loss: 0.9505 | LM_LOSS: 0.4422 | LB_LOSS: 1.0165
[2026-05-24 16:10:12] Validation | Batch 890/1463 | Loss: 0.9504 | LM_LOSS: 0.4422 | LB_LOSS: 1.0164
[2026-05-24 16:10:13] Validation | Batch 900/1463 | Loss: 0.9501 | LM_LOSS: 0.4419 | LB_LOSS: 1.0164
[2026-05-24 16:10:15] Validation | Batch 910/1463 | Loss: 0.9501 | LM_LOSS: 0.4419 | LB_LOSS: 1.0164
[2026-05-24 16:10:17] Validation | Batch 920/1463 | Loss: 0.9505 | LM_LOSS: 0.4423 | LB_LOSS: 1.0164
[2026-05-24 16:10:18] Validation | Batch 930/1463 | Loss: 0.9500 | LM_LOSS: 0.4418 | LB_LOSS: 1.0164
[2026-05-24 16:10:20] Validation | Batch 940/1463 | Loss: 0.9497 | LM_LOSS: 0.4415 | LB_LOSS: 1.0164
[2026-05-24 16:10:21] Validation | Batch 950/1463 | Loss: 0.9500 | LM_LOSS: 0.4418 | LB_LOSS: 1.0164
[2026-05-24 16:10:23] Validation | Batch 960/1463 | Loss: 0.9501 | LM_LOSS: 0.4419 | LB_LOSS: 1.0164
[2026-05-24 16:10:25] Validation | Batch 970/1463 | Loss: 0.9504 | LM_LOSS: 0.4422 | LB_LOSS: 1.0163
[2026-05-24 16:10:26] Validation | Batch 980/1463 | Loss: 0.9507 | LM_LOSS: 0.4425 | LB_LOSS: 1.0163
[2026-05-24 16:10:28] Validation | Batch 990/1463 | Loss: 0.9508 | LM_LOSS: 0.4426 | LB_LOSS: 1.0163
[2026-05-24 16:10:29] Validation | Batch 1000/1463 | Loss: 0.9514 | LM_LOSS: 0.4432 | LB_LOSS: 1.0163
[2026-05-24 16:10:31] Validation | Batch 1010/1463 | Loss: 0.9514 | LM_LOSS: 0.4432 | LB_LOSS: 1.0164
[2026-05-24 16:10:33] Validation | Batch 1020/1463 | Loss: 0.9517 | LM_LOSS: 0.4435 | LB_LOSS: 1.0164
[2026-05-24 16:10:34] Validation | Batch 1030/1463 | Loss: 0.9523 | LM_LOSS: 0.4440 | LB_LOSS: 1.0164
[2026-05-24 16:10:36] Validation | Batch 1040/1463 | Loss: 0.9517 | LM_LOSS: 0.4435 | LB_LOSS: 1.0164
[2026-05-24 16:10:38] Validation | Batch 1050/1463 | Loss: 0.9516 | LM_LOSS: 0.4434 | LB_LOSS: 1.0164
[2026-05-24 16:10:39] Validation | Batch 1060/1463 | Loss: 0.9515 | LM_LOSS: 0.4433 | LB_LOSS: 1.0164
[2026-05-24 16:10:41] Validation | Batch 1070/1463 | Loss: 0.9516 | LM_LOSS: 0.4434 | LB_LOSS: 1.0164
[2026-05-24 16:10:42] Validation | Batch 1080/1463 | Loss: 0.9513 | LM_LOSS: 0.4431 | LB_LOSS: 1.0164
[2026-05-24 16:10:44] Validation | Batch 1090/1463 | Loss: 0.9513 | LM_LOSS: 0.4431 | LB_LOSS: 1.0164
[2026-05-24 16:10:45] Validation | Batch 1100/1463 | Loss: 0.9512 | LM_LOSS: 0.4430 | LB_LOSS: 1.0164
[2026-05-24 16:10:47] Validation | Batch 1110/1463 | Loss: 0.9512 | LM_LOSS: 0.4430 | LB_LOSS: 1.0164
[2026-05-24 16:10:48] Validation | Batch 1120/1463 | Loss: 0.9510 | LM_LOSS: 0.4428 | LB_LOSS: 1.0164
[2026-05-24 16:10:50] Validation | Batch 1130/1463 | Loss: 0.9506 | LM_LOSS: 0.4424 | LB_LOSS: 1.0164
[2026-05-24 16:10:52] Validation | Batch 1140/1463 | Loss: 0.9509 | LM_LOSS: 0.4427 | LB_LOSS: 1.0164
[2026-05-24 16:10:53] Validation | Batch 1150/1463 | Loss: 0.9508 | LM_LOSS: 0.4426 | LB_LOSS: 1.0164
[2026-05-24 16:10:55] Validation | Batch 1160/1463 | Loss: 0.9508 | LM_LOSS: 0.4426 | LB_LOSS: 1.0164
[2026-05-24 16:10:56] Validation | Batch 1170/1463 | Loss: 0.9506 | LM_LOSS: 0.4425 | LB_LOSS: 1.0164
[2026-05-24 16:10:58] Validation | Batch 1180/1463 | Loss: 0.9506 | LM_LOSS: 0.4424 | LB_LOSS: 1.0164
[2026-05-24 16:11:00] Validation | Batch 1190/1463 | Loss: 0.9508 | LM_LOSS: 0.4426 | LB_LOSS: 1.0164
[2026-05-24 16:11:01] Validation | Batch 1200/1463 | Loss: 0.9509 | LM_LOSS: 0.4427 | LB_LOSS: 1.0164
[2026-05-24 16:11:03] Validation | Batch 1210/1463 | Loss: 0.9513 | LM_LOSS: 0.4431 | LB_LOSS: 1.0164
[2026-05-24 16:11:04] Validation | Batch 1220/1463 | Loss: 0.9516 | LM_LOSS: 0.4434 | LB_LOSS: 1.0164
[2026-05-24 16:11:06] Validation | Batch 1230/1463 | Loss: 0.9516 | LM_LOSS: 0.4434 | LB_LOSS: 1.0164
[2026-05-24 16:11:07] Validation | Batch 1240/1463 | Loss: 0.9519 | LM_LOSS: 0.4437 | LB_LOSS: 1.0164
[2026-05-24 16:11:09] Validation | Batch 1250/1463 | Loss: 0.9522 | LM_LOSS: 0.4440 | LB_LOSS: 1.0164
[2026-05-24 16:11:11] Validation | Batch 1260/1463 | Loss: 0.9522 | LM_LOSS: 0.4440 | LB_LOSS: 1.0164
[2026-05-24 16:11:12] Validation | Batch 1270/1463 | Loss: 0.9520 | LM_LOSS: 0.4438 | LB_LOSS: 1.0164
[2026-05-24 16:11:14] Validation | Batch 1280/1463 | Loss: 0.9518 | LM_LOSS: 0.4436 | LB_LOSS: 1.0164
[2026-05-24 16:11:16] Validation | Batch 1290/1463 | Loss: 0.9518 | LM_LOSS: 0.4436 | LB_LOSS: 1.0164
[2026-05-24 16:11:17] Validation | Batch 1300/1463 | Loss: 0.9515 | LM_LOSS: 0.4433 | LB_LOSS: 1.0164
[2026-05-24 16:11:19] Validation | Batch 1310/1463 | Loss: 0.9514 | LM_LOSS: 0.4432 | LB_LOSS: 1.0164
[2026-05-24 16:11:20] Validation | Batch 1320/1463 | Loss: 0.9515 | LM_LOSS: 0.4433 | LB_LOSS: 1.0164
[2026-05-24 16:11:21] Validation | Batch 1330/1463 | Loss: 0.9514 | LM_LOSS: 0.4432 | LB_LOSS: 1.0164
[2026-05-24 16:11:23] Validation | Batch 1340/1463 | Loss: 0.9516 | LM_LOSS: 0.4434 | LB_LOSS: 1.0164
[2026-05-24 16:11:24] Validation | Batch 1350/1463 | Loss: 0.9517 | LM_LOSS: 0.4435 | LB_LOSS: 1.0164
[2026-05-24 16:11:26] Validation | Batch 1360/1463 | Loss: 0.9519 | LM_LOSS: 0.4438 | LB_LOSS: 1.0164
[2026-05-24 16:11:28] Validation | Batch 1370/1463 | Loss: 0.9524 | LM_LOSS: 0.4442 | LB_LOSS: 1.0164
[2026-05-24 16:11:29] Validation | Batch 1380/1463 | Loss: 0.9522 | LM_LOSS: 0.4440 | LB_LOSS: 1.0164
[2026-05-24 16:11:31] Validation | Batch 1390/1463 | Loss: 0.9521 | LM_LOSS: 0.4439 | LB_LOSS: 1.0164
[2026-05-24 16:11:32] Validation | Batch 1400/1463 | Loss: 0.9524 | LM_LOSS: 0.4442 | LB_LOSS: 1.0164
[2026-05-24 16:11:34] Validation | Batch 1410/1463 | Loss: 0.9526 | LM_LOSS: 0.4444 | LB_LOSS: 1.0164
[2026-05-24 16:11:35] Validation | Batch 1420/1463 | Loss: 0.9527 | LM_LOSS: 0.4445 | LB_LOSS: 1.0164
[2026-05-24 16:11:37] Validation | Batch 1430/1463 | Loss: 0.9528 | LM_LOSS: 0.4446 | LB_LOSS: 1.0164
[2026-05-24 16:11:38] Validation | Batch 1440/1463 | Loss: 0.9532 | LM_LOSS: 0.4450 | LB_LOSS: 1.0164
[2026-05-24 16:11:40] Validation | Batch 1450/1463 | Loss: 0.9528 | LM_LOSS: 0.4446 | LB_LOSS: 1.0163
[2026-05-24 16:11:42] Validation | Batch 1460/1463 | Loss: 0.9531 | LM_LOSS: 0.4449 | LB_LOSS: 1.0163
[2026-05-24 16:11:42] Validation | Batch 1463/1463 | Loss: 0.9530 | LM_LOSS: 0.4448 | LB_LOSS: 1.0163
[2026-05-24 16:11:42] Validation | Loss: 0.9530 | LM_LOSS: 0.4448 | LB_LOSS: 1.0163 | PPL: 1.56 | Time: 230.16s
[2026-05-24 16:11:53] Epoch 3 | Step 13010 | Loss: 0.8737 | LM: 0.3650 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.77e-05
[2026-05-24 16:12:04] Epoch 3 | Step 13020 | Loss: 0.8737 | LM: 0.3650 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.72e-05
[2026-05-24 16:12:14] Epoch 3 | Step 13030 | Loss: 0.8737 | LM: 0.3650 | LB: 1.0195 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.67e-05
[2026-05-24 16:12:25] Epoch 3 | Step 13040 | Loss: 0.8738 | LM: 0.3651 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.63e-05
[2026-05-24 16:12:36] Epoch 3 | Step 13050 | Loss: 0.8736 | LM: 0.3651 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.58e-05
[2026-05-24 16:12:47] Epoch 3 | Step 13060 | Loss: 0.8736 | LM: 0.3652 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.54e-05
[2026-05-24 16:12:58] Epoch 3 | Step 13070 | Loss: 0.8737 | LM: 0.3651 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.49e-05
[2026-05-24 16:13:09] Epoch 3 | Step 13080 | Loss: 0.8736 | LM: 0.3650 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.45e-05
[2026-05-24 16:13:20] Epoch 3 | Step 13090 | Loss: 0.8736 | LM: 0.3651 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.40e-05
[2026-05-24 16:13:32] Epoch 3 | Step 13100 | Loss: 0.8735 | LM: 0.3651 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.36e-05
[2026-05-24 16:13:43] Epoch 3 | Step 13110 | Loss: 0.8736 | LM: 0.3652 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.31e-05
[2026-05-24 16:13:54] Epoch 3 | Step 13120 | Loss: 0.8735 | LM: 0.3651 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.27e-05
[2026-05-24 16:14:05] Epoch 3 | Step 13130 | Loss: 0.8735 | LM: 0.3650 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.23e-05
[2026-05-24 16:14:15] Epoch 3 | Step 13140 | Loss: 0.8735 | LM: 0.3650 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.18e-05
[2026-05-24 16:14:26] Epoch 3 | Step 13150 | Loss: 0.8734 | LM: 0.3649 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.14e-05
[2026-05-24 16:14:36] Epoch 3 | Step 13160 | Loss: 0.8734 | LM: 0.3648 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.10e-05
[2026-05-24 16:14:47] Epoch 3 | Step 13170 | Loss: 0.8734 | LM: 0.3649 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.06e-05
[2026-05-24 16:14:58] Epoch 3 | Step 13180 | Loss: 0.8734 | LM: 0.3651 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 3.01e-05
[2026-05-24 16:15:08] Epoch 3 | Step 13190 | Loss: 0.8733 | LM: 0.3649 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.97e-05
[2026-05-24 16:15:19] Epoch 3 | Step 13200 | Loss: 0.8733 | LM: 0.3648 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.93e-05
[2026-05-24 16:15:30] Epoch 3 | Step 13210 | Loss: 0.8734 | LM: 0.3649 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.89e-05
[2026-05-24 16:15:40] Epoch 3 | Step 13220 | Loss: 0.8734 | LM: 0.3650 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.85e-05
[2026-05-24 16:15:51] Epoch 3 | Step 13230 | Loss: 0.8735 | LM: 0.3651 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.81e-05
[2026-05-24 16:16:01] Epoch 3 | Step 13240 | Loss: 0.8734 | LM: 0.3650 | LB: 1.0194 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.77e-05
[2026-05-24 16:16:12] Epoch 3 | Step 13250 | Loss: 0.8734 | LM: 0.3650 | LB: 1.0193 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.73e-05
[2026-05-24 16:16:23] Epoch 3 | Step 13260 | Loss: 0.8733 | LM: 0.3650 | LB: 1.0193 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.69e-05
[2026-05-24 16:16:33] Epoch 3 | Step 13270 | Loss: 0.8733 | LM: 0.3649 | LB: 1.0193 | CL0: 5.2 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.65e-05
[2026-05-24 16:16:44] Epoch 3 | Step 13280 | Loss: 0.8733 | LM: 0.3648 | LB: 1.0193 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.61e-05
[2026-05-24 16:16:54] Epoch 3 | Step 13290 | Loss: 0.8733 | LM: 0.3648 | LB: 1.0193 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.57e-05
[2026-05-24 16:17:05] Epoch 3 | Step 13300 | Loss: 0.8733 | LM: 0.3647 | LB: 1.0193 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.53e-05
[2026-05-24 16:17:15] Epoch 3 | Step 13310 | Loss: 0.8732 | LM: 0.3647 | LB: 1.0193 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.50e-05
[2026-05-24 16:17:26] Epoch 3 | Step 13320 | Loss: 0.8733 | LM: 0.3646 | LB: 1.0193 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.46e-05
[2026-05-24 16:17:37] Epoch 3 | Step 13330 | Loss: 0.8733 | LM: 0.3646 | LB: 1.0193 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.42e-05
[2026-05-24 16:17:47] Epoch 3 | Step 13340 | Loss: 0.8733 | LM: 0.3647 | LB: 1.0193 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.39e-05
[2026-05-24 16:17:58] Epoch 3 | Step 13350 | Loss: 0.8733 | LM: 0.3648 | LB: 1.0193 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.35e-05
[2026-05-24 16:18:08] Epoch 3 | Step 13360 | Loss: 0.8733 | LM: 0.3648 | LB: 1.0193 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.31e-05
[2026-05-24 16:18:19] Epoch 3 | Step 13370 | Loss: 0.8733 | LM: 0.3648 | LB: 1.0193 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.28e-05
[2026-05-24 16:18:29] Epoch 3 | Step 13380 | Loss: 0.8734 | LM: 0.3649 | LB: 1.0193 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.24e-05
[2026-05-24 16:18:40] Epoch 3 | Step 13390 | Loss: 0.8734 | LM: 0.3649 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.21e-05
[2026-05-24 16:18:50] Epoch 3 | Step 13400 | Loss: 0.8734 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.18e-05
[2026-05-24 16:19:01] Epoch 3 | Step 13410 | Loss: 0.8735 | LM: 0.3651 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.14e-05
[2026-05-24 16:19:12] Epoch 3 | Step 13420 | Loss: 0.8735 | LM: 0.3649 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.11e-05
[2026-05-24 16:19:23] Epoch 3 | Step 13430 | Loss: 0.8734 | LM: 0.3649 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.08e-05
[2026-05-24 16:19:33] Epoch 3 | Step 13440 | Loss: 0.8734 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.04e-05
[2026-05-24 16:19:44] Epoch 3 | Step 13450 | Loss: 0.8734 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 2.01e-05
[2026-05-24 16:19:55] Epoch 3 | Step 13460 | Loss: 0.8733 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 1.98e-05
[2026-05-24 16:20:05] Epoch 3 | Step 13470 | Loss: 0.8733 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 1.95e-05
[2026-05-24 16:20:16] Epoch 3 | Step 13480 | Loss: 0.8732 | LM: 0.3647 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 1.92e-05
[2026-05-24 16:20:26] Epoch 3 | Step 13490 | Loss: 0.8733 | LM: 0.3647 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 1.89e-05
[2026-05-24 16:20:37] Epoch 3 | Step 13500 | Loss: 0.8732 | LM: 0.3647 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 1.86e-05
[2026-05-24 16:20:47] Epoch 3 | Step 13510 | Loss: 0.8733 | LM: 0.3647 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.83e-05
[2026-05-24 16:20:58] Epoch 3 | Step 13520 | Loss: 0.8733 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.80e-05
[2026-05-24 16:21:09] Epoch 3 | Step 13530 | Loss: 0.8734 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.77e-05
[2026-05-24 16:21:19] Epoch 3 | Step 13540 | Loss: 0.8733 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.74e-05
[2026-05-24 16:21:30] Epoch 3 | Step 13550 | Loss: 0.8734 | LM: 0.3650 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.177 | HR1: 0.150/SR1: 0.133 | LR: 1.72e-05
[2026-05-24 16:21:41] Epoch 3 | Step 13560 | Loss: 0.8735 | LM: 0.3649 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.69e-05
[2026-05-24 16:21:52] Epoch 3 | Step 13570 | Loss: 0.8734 | LM: 0.3649 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.66e-05
[2026-05-24 16:22:03] Epoch 3 | Step 13580 | Loss: 0.8734 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.64e-05
[2026-05-24 16:22:14] Epoch 3 | Step 13590 | Loss: 0.8735 | LM: 0.3649 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.61e-05
[2026-05-24 16:22:25] Epoch 3 | Step 13600 | Loss: 0.8735 | LM: 0.3649 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.59e-05
[2026-05-24 16:22:36] Epoch 3 | Step 13610 | Loss: 0.8735 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.56e-05
[2026-05-24 16:22:47] Epoch 3 | Step 13620 | Loss: 0.8734 | LM: 0.3647 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.54e-05
[2026-05-24 16:22:58] Epoch 3 | Step 13630 | Loss: 0.8734 | LM: 0.3647 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.51e-05
[2026-05-24 16:23:08] Epoch 3 | Step 13640 | Loss: 0.8733 | LM: 0.3647 | LB: 1.0191 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.49e-05
[2026-05-24 16:23:19] Epoch 3 | Step 13650 | Loss: 0.8733 | LM: 0.3646 | LB: 1.0191 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.47e-05
[2026-05-24 16:23:29] Epoch 3 | Step 13660 | Loss: 0.8733 | LM: 0.3646 | LB: 1.0191 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.45e-05
[2026-05-24 16:23:40] Epoch 3 | Step 13670 | Loss: 0.8732 | LM: 0.3645 | LB: 1.0191 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.42e-05
[2026-05-24 16:23:51] Epoch 3 | Step 13680 | Loss: 0.8733 | LM: 0.3646 | LB: 1.0191 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.40e-05
[2026-05-24 16:24:01] Epoch 3 | Step 13690 | Loss: 0.8733 | LM: 0.3646 | LB: 1.0191 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.38e-05
[2026-05-24 16:24:12] Epoch 3 | Step 13700 | Loss: 0.8732 | LM: 0.3647 | LB: 1.0191 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.36e-05
[2026-05-24 16:24:22] Epoch 3 | Step 13710 | Loss: 0.8733 | LM: 0.3646 | LB: 1.0191 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.34e-05
[2026-05-24 16:24:33] Epoch 3 | Step 13720 | Loss: 0.8732 | LM: 0.3648 | LB: 1.0191 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.32e-05
[2026-05-24 16:24:43] Epoch 3 | Step 13730 | Loss: 0.8732 | LM: 0.3648 | LB: 1.0191 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.31e-05
[2026-05-24 16:24:54] Epoch 3 | Step 13740 | Loss: 0.8732 | LM: 0.3648 | LB: 1.0191 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.29e-05
[2026-05-24 16:25:05] Epoch 3 | Step 13750 | Loss: 0.8732 | LM: 0.3647 | LB: 1.0191 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.27e-05
[2026-05-24 16:25:16] Epoch 3 | Step 13760 | Loss: 0.8732 | LM: 0.3647 | LB: 1.0191 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.25e-05
[2026-05-24 16:25:26] Epoch 3 | Step 13770 | Loss: 0.8732 | LM: 0.3649 | LB: 1.0191 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.24e-05
[2026-05-24 16:25:37] Epoch 3 | Step 13780 | Loss: 0.8732 | LM: 0.3649 | LB: 1.0191 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.22e-05
[2026-05-24 16:25:48] Epoch 3 | Step 13790 | Loss: 0.8732 | LM: 0.3650 | LB: 1.0191 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.21e-05
[2026-05-24 16:25:59] Epoch 3 | Step 13800 | Loss: 0.8731 | LM: 0.3648 | LB: 1.0191 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.19e-05
[2026-05-24 16:26:10] Epoch 3 | Step 13810 | Loss: 0.8732 | LM: 0.3649 | LB: 1.0191 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.18e-05
[2026-05-24 16:26:22] Epoch 3 | Step 13820 | Loss: 0.8732 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.16e-05
[2026-05-24 16:26:33] Epoch 3 | Step 13830 | Loss: 0.8732 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.15e-05
[2026-05-24 16:26:44] Epoch 3 | Step 13840 | Loss: 0.8731 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.14e-05
[2026-05-24 16:26:55] Epoch 3 | Step 13850 | Loss: 0.8730 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.13e-05
[2026-05-24 16:27:06] Epoch 3 | Step 13860 | Loss: 0.8731 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.11e-05
[2026-05-24 16:27:17] Epoch 3 | Step 13870 | Loss: 0.8730 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.10e-05
[2026-05-24 16:27:28] Epoch 3 | Step 13880 | Loss: 0.8730 | LM: 0.3646 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.09e-05
[2026-05-24 16:27:39] Epoch 3 | Step 13890 | Loss: 0.8730 | LM: 0.3647 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.08e-05
[2026-05-24 16:27:50] Epoch 3 | Step 13900 | Loss: 0.8730 | LM: 0.3647 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.07e-05
[2026-05-24 16:28:01] Epoch 3 | Step 13910 | Loss: 0.8730 | LM: 0.3647 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.06e-05
[2026-05-24 16:28:13] Epoch 3 | Step 13920 | Loss: 0.8729 | LM: 0.3647 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.06e-05
[2026-05-24 16:28:24] Epoch 3 | Step 13930 | Loss: 0.8729 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.05e-05
[2026-05-24 16:28:36] Epoch 3 | Step 13940 | Loss: 0.8729 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.04e-05
[2026-05-24 16:28:48] Epoch 3 | Step 13950 | Loss: 0.8729 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.04e-05
[2026-05-24 16:28:59] Epoch 3 | Step 13960 | Loss: 0.8730 | LM: 0.3648 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.03e-05
[2026-05-24 16:29:11] Epoch 3 | Step 13970 | Loss: 0.8729 | LM: 0.3647 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.02e-05
[2026-05-24 16:29:22] Epoch 3 | Step 13980 | Loss: 0.8729 | LM: 0.3646 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.02e-05
[2026-05-24 16:29:34] Epoch 3 | Step 13990 | Loss: 0.8729 | LM: 0.3645 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.01e-05
[2026-05-24 16:29:45] Epoch 3 | Step 14000 | Loss: 0.8729 | LM: 0.3645 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.01e-05
[2026-05-24 16:29:47] Validation | Batch 10/1463 | Loss: 0.9214 | LM_LOSS: 0.4155 | LB_LOSS: 1.0119
[2026-05-24 16:29:48] Validation | Batch 20/1463 | Loss: 0.9279 | LM_LOSS: 0.4208 | LB_LOSS: 1.0142
[2026-05-24 16:29:50] Validation | Batch 30/1463 | Loss: 0.9296 | LM_LOSS: 0.4222 | LB_LOSS: 1.0149
[2026-05-24 16:29:51] Validation | Batch 40/1463 | Loss: 0.9412 | LM_LOSS: 0.4334 | LB_LOSS: 1.0156
[2026-05-24 16:29:53] Validation | Batch 50/1463 | Loss: 0.9458 | LM_LOSS: 0.4382 | LB_LOSS: 1.0151
[2026-05-24 16:29:55] Validation | Batch 60/1463 | Loss: 0.9469 | LM_LOSS: 0.4392 | LB_LOSS: 1.0153
[2026-05-24 16:29:56] Validation | Batch 70/1463 | Loss: 0.9457 | LM_LOSS: 0.4381 | LB_LOSS: 1.0153
[2026-05-24 16:29:58] Validation | Batch 80/1463 | Loss: 0.9467 | LM_LOSS: 0.4389 | LB_LOSS: 1.0155
[2026-05-24 16:30:00] Validation | Batch 90/1463 | Loss: 0.9465 | LM_LOSS: 0.4387 | LB_LOSS: 1.0154
[2026-05-24 16:30:01] Validation | Batch 100/1463 | Loss: 0.9473 | LM_LOSS: 0.4396 | LB_LOSS: 1.0155
[2026-05-24 16:30:03] Validation | Batch 110/1463 | Loss: 0.9456 | LM_LOSS: 0.4377 | LB_LOSS: 1.0157
[2026-05-24 16:30:04] Validation | Batch 120/1463 | Loss: 0.9465 | LM_LOSS: 0.4387 | LB_LOSS: 1.0157
[2026-05-24 16:30:06] Validation | Batch 130/1463 | Loss: 0.9501 | LM_LOSS: 0.4423 | LB_LOSS: 1.0157
[2026-05-24 16:30:07] Validation | Batch 140/1463 | Loss: 0.9512 | LM_LOSS: 0.4434 | LB_LOSS: 1.0158
[2026-05-24 16:30:09] Validation | Batch 150/1463 | Loss: 0.9489 | LM_LOSS: 0.4409 | LB_LOSS: 1.0158
[2026-05-24 16:30:11] Validation | Batch 160/1463 | Loss: 0.9501 | LM_LOSS: 0.4422 | LB_LOSS: 1.0158
[2026-05-24 16:30:12] Validation | Batch 170/1463 | Loss: 0.9498 | LM_LOSS: 0.4419 | LB_LOSS: 1.0158
[2026-05-24 16:30:14] Validation | Batch 180/1463 | Loss: 0.9505 | LM_LOSS: 0.4426 | LB_LOSS: 1.0159
[2026-05-24 16:30:15] Validation | Batch 190/1463 | Loss: 0.9512 | LM_LOSS: 0.4433 | LB_LOSS: 1.0159
[2026-05-24 16:30:17] Validation | Batch 200/1463 | Loss: 0.9508 | LM_LOSS: 0.4429 | LB_LOSS: 1.0159
[2026-05-24 16:30:19] Validation | Batch 210/1463 | Loss: 0.9515 | LM_LOSS: 0.4435 | LB_LOSS: 1.0160
[2026-05-24 16:30:20] Validation | Batch 220/1463 | Loss: 0.9506 | LM_LOSS: 0.4426 | LB_LOSS: 1.0161
[2026-05-24 16:30:22] Validation | Batch 230/1463 | Loss: 0.9519 | LM_LOSS: 0.4439 | LB_LOSS: 1.0159
[2026-05-24 16:30:24] Validation | Batch 240/1463 | Loss: 0.9523 | LM_LOSS: 0.4443 | LB_LOSS: 1.0159
[2026-05-24 16:30:25] Validation | Batch 250/1463 | Loss: 0.9506 | LM_LOSS: 0.4426 | LB_LOSS: 1.0159
[2026-05-24 16:30:27] Validation | Batch 260/1463 | Loss: 0.9529 | LM_LOSS: 0.4448 | LB_LOSS: 1.0161
[2026-05-24 16:30:28] Validation | Batch 270/1463 | Loss: 0.9517 | LM_LOSS: 0.4437 | LB_LOSS: 1.0160
[2026-05-24 16:30:30] Validation | Batch 280/1463 | Loss: 0.9531 | LM_LOSS: 0.4451 | LB_LOSS: 1.0161
[2026-05-24 16:30:32] Validation | Batch 290/1463 | Loss: 0.9518 | LM_LOSS: 0.4438 | LB_LOSS: 1.0160
[2026-05-24 16:30:33] Validation | Batch 300/1463 | Loss: 0.9527 | LM_LOSS: 0.4446 | LB_LOSS: 1.0162
[2026-05-24 16:30:35] Validation | Batch 310/1463 | Loss: 0.9537 | LM_LOSS: 0.4457 | LB_LOSS: 1.0162
[2026-05-24 16:30:36] Validation | Batch 320/1463 | Loss: 0.9520 | LM_LOSS: 0.4440 | LB_LOSS: 1.0160
[2026-05-24 16:30:38] Validation | Batch 330/1463 | Loss: 0.9519 | LM_LOSS: 0.4439 | LB_LOSS: 1.0160
[2026-05-24 16:30:39] Validation | Batch 340/1463 | Loss: 0.9514 | LM_LOSS: 0.4434 | LB_LOSS: 1.0160
[2026-05-24 16:30:41] Validation | Batch 350/1463 | Loss: 0.9518 | LM_LOSS: 0.4438 | LB_LOSS: 1.0160
[2026-05-24 16:30:42] Validation | Batch 360/1463 | Loss: 0.9518 | LM_LOSS: 0.4438 | LB_LOSS: 1.0160
[2026-05-24 16:30:44] Validation | Batch 370/1463 | Loss: 0.9520 | LM_LOSS: 0.4440 | LB_LOSS: 1.0161
[2026-05-24 16:30:45] Validation | Batch 380/1463 | Loss: 0.9519 | LM_LOSS: 0.4439 | LB_LOSS: 1.0160
[2026-05-24 16:30:47] Validation | Batch 390/1463 | Loss: 0.9529 | LM_LOSS: 0.4449 | LB_LOSS: 1.0160
[2026-05-24 16:30:48] Validation | Batch 400/1463 | Loss: 0.9527 | LM_LOSS: 0.4447 | LB_LOSS: 1.0160
[2026-05-24 16:30:50] Validation | Batch 410/1463 | Loss: 0.9524 | LM_LOSS: 0.4444 | LB_LOSS: 1.0161
[2026-05-24 16:30:52] Validation | Batch 420/1463 | Loss: 0.9526 | LM_LOSS: 0.4446 | LB_LOSS: 1.0161
[2026-05-24 16:30:53] Validation | Batch 430/1463 | Loss: 0.9525 | LM_LOSS: 0.4444 | LB_LOSS: 1.0162
[2026-05-24 16:30:55] Validation | Batch 440/1463 | Loss: 0.9529 | LM_LOSS: 0.4447 | LB_LOSS: 1.0162
[2026-05-24 16:30:56] Validation | Batch 450/1463 | Loss: 0.9525 | LM_LOSS: 0.4444 | LB_LOSS: 1.0163
[2026-05-24 16:30:58] Validation | Batch 460/1463 | Loss: 0.9525 | LM_LOSS: 0.4444 | LB_LOSS: 1.0162
[2026-05-24 16:31:00] Validation | Batch 470/1463 | Loss: 0.9532 | LM_LOSS: 0.4451 | LB_LOSS: 1.0162
[2026-05-24 16:31:01] Validation | Batch 480/1463 | Loss: 0.9528 | LM_LOSS: 0.4447 | LB_LOSS: 1.0162
[2026-05-24 16:31:03] Validation | Batch 490/1463 | Loss: 0.9525 | LM_LOSS: 0.4444 | LB_LOSS: 1.0162
[2026-05-24 16:31:05] Validation | Batch 500/1463 | Loss: 0.9522 | LM_LOSS: 0.4441 | LB_LOSS: 1.0162
[2026-05-24 16:31:06] Validation | Batch 510/1463 | Loss: 0.9517 | LM_LOSS: 0.4436 | LB_LOSS: 1.0162
[2026-05-24 16:31:08] Validation | Batch 520/1463 | Loss: 0.9515 | LM_LOSS: 0.4434 | LB_LOSS: 1.0162
[2026-05-24 16:31:09] Validation | Batch 530/1463 | Loss: 0.9520 | LM_LOSS: 0.4439 | LB_LOSS: 1.0162
[2026-05-24 16:31:10] Validation | Batch 540/1463 | Loss: 0.9525 | LM_LOSS: 0.4444 | LB_LOSS: 1.0162
[2026-05-24 16:31:12] Validation | Batch 550/1463 | Loss: 0.9521 | LM_LOSS: 0.4440 | LB_LOSS: 1.0163
[2026-05-24 16:31:13] Validation | Batch 560/1463 | Loss: 0.9528 | LM_LOSS: 0.4447 | LB_LOSS: 1.0163
[2026-05-24 16:31:15] Validation | Batch 570/1463 | Loss: 0.9530 | LM_LOSS: 0.4448 | LB_LOSS: 1.0163
[2026-05-24 16:31:17] Validation | Batch 580/1463 | Loss: 0.9526 | LM_LOSS: 0.4444 | LB_LOSS: 1.0163
[2026-05-24 16:31:19] Validation | Batch 590/1463 | Loss: 0.9525 | LM_LOSS: 0.4443 | LB_LOSS: 1.0164
[2026-05-24 16:31:20] Validation | Batch 600/1463 | Loss: 0.9527 | LM_LOSS: 0.4445 | LB_LOSS: 1.0164
[2026-05-24 16:31:22] Validation | Batch 610/1463 | Loss: 0.9527 | LM_LOSS: 0.4445 | LB_LOSS: 1.0164
[2026-05-24 16:31:24] Validation | Batch 620/1463 | Loss: 0.9522 | LM_LOSS: 0.4440 | LB_LOSS: 1.0164
[2026-05-24 16:31:25] Validation | Batch 630/1463 | Loss: 0.9519 | LM_LOSS: 0.4436 | LB_LOSS: 1.0164
[2026-05-24 16:31:27] Validation | Batch 640/1463 | Loss: 0.9517 | LM_LOSS: 0.4434 | LB_LOSS: 1.0165
[2026-05-24 16:31:28] Validation | Batch 650/1463 | Loss: 0.9511 | LM_LOSS: 0.4428 | LB_LOSS: 1.0165
[2026-05-24 16:31:29] Validation | Batch 660/1463 | Loss: 0.9506 | LM_LOSS: 0.4424 | LB_LOSS: 1.0165
[2026-05-24 16:31:31] Validation | Batch 670/1463 | Loss: 0.9502 | LM_LOSS: 0.4420 | LB_LOSS: 1.0164
[2026-05-24 16:31:32] Validation | Batch 680/1463 | Loss: 0.9503 | LM_LOSS: 0.4421 | LB_LOSS: 1.0164
[2026-05-24 16:31:34] Validation | Batch 690/1463 | Loss: 0.9507 | LM_LOSS: 0.4425 | LB_LOSS: 1.0164
[2026-05-24 16:31:36] Validation | Batch 700/1463 | Loss: 0.9507 | LM_LOSS: 0.4425 | LB_LOSS: 1.0164
[2026-05-24 16:31:37] Validation | Batch 710/1463 | Loss: 0.9510 | LM_LOSS: 0.4428 | LB_LOSS: 1.0165
[2026-05-24 16:31:39] Validation | Batch 720/1463 | Loss: 0.9518 | LM_LOSS: 0.4435 | LB_LOSS: 1.0165
[2026-05-24 16:31:40] Validation | Batch 730/1463 | Loss: 0.9517 | LM_LOSS: 0.4435 | LB_LOSS: 1.0165
[2026-05-24 16:31:41] Validation | Batch 740/1463 | Loss: 0.9515 | LM_LOSS: 0.4433 | LB_LOSS: 1.0165
[2026-05-24 16:31:43] Validation | Batch 750/1463 | Loss: 0.9513 | LM_LOSS: 0.4431 | LB_LOSS: 1.0165
[2026-05-24 16:31:44] Validation | Batch 760/1463 | Loss: 0.9510 | LM_LOSS: 0.4428 | LB_LOSS: 1.0164
[2026-05-24 16:31:46] Validation | Batch 770/1463 | Loss: 0.9509 | LM_LOSS: 0.4426 | LB_LOSS: 1.0165
[2026-05-24 16:31:47] Validation | Batch 780/1463 | Loss: 0.9508 | LM_LOSS: 0.4425 | LB_LOSS: 1.0164
[2026-05-24 16:31:48] Validation | Batch 790/1463 | Loss: 0.9511 | LM_LOSS: 0.4429 | LB_LOSS: 1.0164
[2026-05-24 16:31:50] Validation | Batch 800/1463 | Loss: 0.9510 | LM_LOSS: 0.4428 | LB_LOSS: 1.0164
[2026-05-24 16:31:51] Validation | Batch 810/1463 | Loss: 0.9506 | LM_LOSS: 0.4424 | LB_LOSS: 1.0164
[2026-05-24 16:31:53] Validation | Batch 820/1463 | Loss: 0.9507 | LM_LOSS: 0.4425 | LB_LOSS: 1.0164
[2026-05-24 16:31:54] Validation | Batch 830/1463 | Loss: 0.9508 | LM_LOSS: 0.4426 | LB_LOSS: 1.0164
[2026-05-24 16:31:56] Validation | Batch 840/1463 | Loss: 0.9506 | LM_LOSS: 0.4424 | LB_LOSS: 1.0164
[2026-05-24 16:31:58] Validation | Batch 850/1463 | Loss: 0.9508 | LM_LOSS: 0.4426 | LB_LOSS: 1.0164
[2026-05-24 16:32:00] Validation | Batch 860/1463 | Loss: 0.9508 | LM_LOSS: 0.4426 | LB_LOSS: 1.0165
[2026-05-24 16:32:01] Validation | Batch 870/1463 | Loss: 0.9510 | LM_LOSS: 0.4428 | LB_LOSS: 1.0165
[2026-05-24 16:32:03] Validation | Batch 880/1463 | Loss: 0.9502 | LM_LOSS: 0.4420 | LB_LOSS: 1.0165
[2026-05-24 16:32:04] Validation | Batch 890/1463 | Loss: 0.9502 | LM_LOSS: 0.4420 | LB_LOSS: 1.0164
[2026-05-24 16:32:06] Validation | Batch 900/1463 | Loss: 0.9498 | LM_LOSS: 0.4416 | LB_LOSS: 1.0164
[2026-05-24 16:32:07] Validation | Batch 910/1463 | Loss: 0.9499 | LM_LOSS: 0.4417 | LB_LOSS: 1.0164
[2026-05-24 16:32:09] Validation | Batch 920/1463 | Loss: 0.9502 | LM_LOSS: 0.4420 | LB_LOSS: 1.0164
[2026-05-24 16:32:10] Validation | Batch 930/1463 | Loss: 0.9497 | LM_LOSS: 0.4415 | LB_LOSS: 1.0164
[2026-05-24 16:32:12] Validation | Batch 940/1463 | Loss: 0.9494 | LM_LOSS: 0.4412 | LB_LOSS: 1.0164
[2026-05-24 16:32:14] Validation | Batch 950/1463 | Loss: 0.9498 | LM_LOSS: 0.4416 | LB_LOSS: 1.0164
[2026-05-24 16:32:15] Validation | Batch 960/1463 | Loss: 0.9499 | LM_LOSS: 0.4417 | LB_LOSS: 1.0164
[2026-05-24 16:32:17] Validation | Batch 970/1463 | Loss: 0.9501 | LM_LOSS: 0.4419 | LB_LOSS: 1.0163
[2026-05-24 16:32:19] Validation | Batch 980/1463 | Loss: 0.9505 | LM_LOSS: 0.4423 | LB_LOSS: 1.0163
[2026-05-24 16:32:20] Validation | Batch 990/1463 | Loss: 0.9506 | LM_LOSS: 0.4424 | LB_LOSS: 1.0163
[2026-05-24 16:32:22] Validation | Batch 1000/1463 | Loss: 0.9511 | LM_LOSS: 0.4430 | LB_LOSS: 1.0163
[2026-05-24 16:32:23] Validation | Batch 1010/1463 | Loss: 0.9512 | LM_LOSS: 0.4430 | LB_LOSS: 1.0164
[2026-05-24 16:32:25] Validation | Batch 1020/1463 | Loss: 0.9515 | LM_LOSS: 0.4433 | LB_LOSS: 1.0164
[2026-05-24 16:32:27] Validation | Batch 1030/1463 | Loss: 0.9521 | LM_LOSS: 0.4438 | LB_LOSS: 1.0164
[2026-05-24 16:32:28] Validation | Batch 1040/1463 | Loss: 0.9515 | LM_LOSS: 0.4433 | LB_LOSS: 1.0164
[2026-05-24 16:32:30] Validation | Batch 1050/1463 | Loss: 0.9514 | LM_LOSS: 0.4432 | LB_LOSS: 1.0164
[2026-05-24 16:32:32] Validation | Batch 1060/1463 | Loss: 0.9513 | LM_LOSS: 0.4431 | LB_LOSS: 1.0164
[2026-05-24 16:32:33] Validation | Batch 1070/1463 | Loss: 0.9514 | LM_LOSS: 0.4432 | LB_LOSS: 1.0164
[2026-05-24 16:32:35] Validation | Batch 1080/1463 | Loss: 0.9511 | LM_LOSS: 0.4429 | LB_LOSS: 1.0164
[2026-05-24 16:32:36] Validation | Batch 1090/1463 | Loss: 0.9510 | LM_LOSS: 0.4428 | LB_LOSS: 1.0164
[2026-05-24 16:32:38] Validation | Batch 1100/1463 | Loss: 0.9509 | LM_LOSS: 0.4427 | LB_LOSS: 1.0164
[2026-05-24 16:32:39] Validation | Batch 1110/1463 | Loss: 0.9510 | LM_LOSS: 0.4428 | LB_LOSS: 1.0164
[2026-05-24 16:32:41] Validation | Batch 1120/1463 | Loss: 0.9508 | LM_LOSS: 0.4426 | LB_LOSS: 1.0164
[2026-05-24 16:32:42] Validation | Batch 1130/1463 | Loss: 0.9503 | LM_LOSS: 0.4421 | LB_LOSS: 1.0164
[2026-05-24 16:32:44] Validation | Batch 1140/1463 | Loss: 0.9506 | LM_LOSS: 0.4424 | LB_LOSS: 1.0164
[2026-05-24 16:32:46] Validation | Batch 1150/1463 | Loss: 0.9505 | LM_LOSS: 0.4424 | LB_LOSS: 1.0164
[2026-05-24 16:32:47] Validation | Batch 1160/1463 | Loss: 0.9505 | LM_LOSS: 0.4424 | LB_LOSS: 1.0164
[2026-05-24 16:32:49] Validation | Batch 1170/1463 | Loss: 0.9504 | LM_LOSS: 0.4422 | LB_LOSS: 1.0163
[2026-05-24 16:32:50] Validation | Batch 1180/1463 | Loss: 0.9503 | LM_LOSS: 0.4421 | LB_LOSS: 1.0164
[2026-05-24 16:32:52] Validation | Batch 1190/1463 | Loss: 0.9505 | LM_LOSS: 0.4423 | LB_LOSS: 1.0164
[2026-05-24 16:32:54] Validation | Batch 1200/1463 | Loss: 0.9506 | LM_LOSS: 0.4425 | LB_LOSS: 1.0164
[2026-05-24 16:32:55] Validation | Batch 1210/1463 | Loss: 0.9511 | LM_LOSS: 0.4429 | LB_LOSS: 1.0164
[2026-05-24 16:32:57] Validation | Batch 1220/1463 | Loss: 0.9514 | LM_LOSS: 0.4432 | LB_LOSS: 1.0164
[2026-05-24 16:32:58] Validation | Batch 1230/1463 | Loss: 0.9513 | LM_LOSS: 0.4431 | LB_LOSS: 1.0164
[2026-05-24 16:33:00] Validation | Batch 1240/1463 | Loss: 0.9517 | LM_LOSS: 0.4435 | LB_LOSS: 1.0164
[2026-05-24 16:33:02] Validation | Batch 1250/1463 | Loss: 0.9519 | LM_LOSS: 0.4437 | LB_LOSS: 1.0164
[2026-05-24 16:33:03] Validation | Batch 1260/1463 | Loss: 0.9519 | LM_LOSS: 0.4437 | LB_LOSS: 1.0164
[2026-05-24 16:33:05] Validation | Batch 1270/1463 | Loss: 0.9517 | LM_LOSS: 0.4435 | LB_LOSS: 1.0164
[2026-05-24 16:33:07] Validation | Batch 1280/1463 | Loss: 0.9515 | LM_LOSS: 0.4432 | LB_LOSS: 1.0164
[2026-05-24 16:33:08] Validation | Batch 1290/1463 | Loss: 0.9515 | LM_LOSS: 0.4433 | LB_LOSS: 1.0164
[2026-05-24 16:33:10] Validation | Batch 1300/1463 | Loss: 0.9512 | LM_LOSS: 0.4430 | LB_LOSS: 1.0164
[2026-05-24 16:33:11] Validation | Batch 1310/1463 | Loss: 0.9511 | LM_LOSS: 0.4429 | LB_LOSS: 1.0164
[2026-05-24 16:33:13] Validation | Batch 1320/1463 | Loss: 0.9512 | LM_LOSS: 0.4430 | LB_LOSS: 1.0164
[2026-05-24 16:33:14] Validation | Batch 1330/1463 | Loss: 0.9511 | LM_LOSS: 0.4429 | LB_LOSS: 1.0164
[2026-05-24 16:33:15] Validation | Batch 1340/1463 | Loss: 0.9513 | LM_LOSS: 0.4431 | LB_LOSS: 1.0164
[2026-05-24 16:33:17] Validation | Batch 1350/1463 | Loss: 0.9513 | LM_LOSS: 0.4431 | LB_LOSS: 1.0164
[2026-05-24 16:33:19] Validation | Batch 1360/1463 | Loss: 0.9516 | LM_LOSS: 0.4434 | LB_LOSS: 1.0164
[2026-05-24 16:33:21] Validation | Batch 1370/1463 | Loss: 0.9520 | LM_LOSS: 0.4438 | LB_LOSS: 1.0164
[2026-05-24 16:33:22] Validation | Batch 1380/1463 | Loss: 0.9518 | LM_LOSS: 0.4436 | LB_LOSS: 1.0164
[2026-05-24 16:33:23] Validation | Batch 1390/1463 | Loss: 0.9517 | LM_LOSS: 0.4435 | LB_LOSS: 1.0164
[2026-05-24 16:33:25] Validation | Batch 1400/1463 | Loss: 0.9520 | LM_LOSS: 0.4438 | LB_LOSS: 1.0164
[2026-05-24 16:33:26] Validation | Batch 1410/1463 | Loss: 0.9522 | LM_LOSS: 0.4441 | LB_LOSS: 1.0164
[2026-05-24 16:33:28] Validation | Batch 1420/1463 | Loss: 0.9523 | LM_LOSS: 0.4442 | LB_LOSS: 1.0164
[2026-05-24 16:33:30] Validation | Batch 1430/1463 | Loss: 0.9524 | LM_LOSS: 0.4442 | LB_LOSS: 1.0164
[2026-05-24 16:33:31] Validation | Batch 1440/1463 | Loss: 0.9528 | LM_LOSS: 0.4446 | LB_LOSS: 1.0164
[2026-05-24 16:33:33] Validation | Batch 1450/1463 | Loss: 0.9524 | LM_LOSS: 0.4443 | LB_LOSS: 1.0163
[2026-05-24 16:33:34] Validation | Batch 1460/1463 | Loss: 0.9528 | LM_LOSS: 0.4446 | LB_LOSS: 1.0163
[2026-05-24 16:33:35] Validation | Batch 1463/1463 | Loss: 0.9526 | LM_LOSS: 0.4445 | LB_LOSS: 1.0163
[2026-05-24 16:33:35] Validation | Loss: 0.9526 | LM_LOSS: 0.4445 | LB_LOSS: 1.0163 | PPL: 1.56 | Time: 229.75s
[2026-05-24 16:33:46] Epoch 3 | Step 14010 | Loss: 0.8729 | LM: 0.3645 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.01e-05
[2026-05-24 16:33:58] Epoch 3 | Step 14020 | Loss: 0.8728 | LM: 0.3643 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-05
[2026-05-24 16:34:10] Epoch 3 | Step 14030 | Loss: 0.8729 | LM: 0.3644 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-05
[2026-05-24 16:34:21] Epoch 3 | Step 14040 | Loss: 0.8730 | LM: 0.3644 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-05
[2026-05-24 16:34:33] Epoch 3 | Step 14050 | Loss: 0.8729 | LM: 0.3644 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-05
[2026-05-24 16:34:45] Epoch 3 | Step 14060 | Loss: 0.8730 | LM: 0.3645 | LB: 1.0192 | CL0: 5.3 | CL1: 6.8 | HR0: 0.192/SR0: 0.176 | HR1: 0.150/SR1: 0.133 | LR: 1.00e-05
[2026-05-24 16:34:47] Epoch 3 completed in 6284.36s | Loss: 0.8730 | CL0: 5.3 | CL1: 6.8
[2026-05-24 16:34:47]
Training completed!
[2026-05-24 16:34:51] Final model: outputs/2026-05-24/N_8.0/model_final.pt