learning_rate: 0.01
train_batch_size: 4
eval_batch_size: 8
seed: 1
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_steps: 1000.0
training_steps: 10000

Training Loss	Epoch	Step	Validation Loss	Chrf
11.8331	0.4669	1000	14.7738	0.0
12.3809	0.9337	2000	4.6722	0.0
6.0802	1.4006	3000	4.6095	0.0
4.8357	1.8674	4000	4.3762	0.1276
4.5247	2.3343	5000	4.2888	0.3189
5.1889	2.8011	6000	4.4439	0.1914
4.5202	3.2680	7000	4.4032	0.0713
4.4625	3.7348	8000	4.2044	0.7015
4.3343	4.2017	9000	4.1771	0.2551
4.2663	4.6685	10000	4.1033	0.8291

Curiousfox/mt5_tai-lo_to_chinese_LoRA_ver1.0.d

outputs