learning_rate: 0.0001
train_batch_size: 1
eval_batch_size: 1
seed: 14
gradient_accumulation_steps: 128
total_train_batch_size: 128
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.03
num_epochs: 3

Training Loss	Epoch	Step	Validation Loss
0.0399	0.3328	26	0.0229
0.0147	0.6656	52	0.0099
0.011	0.9984	78	0.0065
0.0117	1.32	104	0.0059
0.0072	1.6528	130	0.0058
0.0105	1.9856	156	0.0060
0.0034	2.3072	182	0.0059
0.0044	2.64	208	0.0059
0.0031	2.9728	234	0.0051

paulo037/20260503T212213Z-conll03_ner-baseline-2b-10k-4400ba1f

20260503T212213Z-conll03_ner-baseline-2b-10k-4400ba1f