learning_rate: 0.0002
train_batch_size: 2
eval_batch_size: 2
seed: 4234
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Use paged_adamw_32bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 1

Training Loss	Epoch	Step	Validation Loss
0.7684	0.0390	10	0.6517
0.7136	0.0779	20	0.5949
0.6092	0.1169	30	0.5779
0.6011	0.1559	40	0.5638
0.5558	0.1948	50	0.6038
0.6974	0.2338	60	0.5189
0.548	0.2728	70	0.5190
0.5519	0.3117	80	0.4997
0.6448	0.3507	90	0.5379
0.6097	0.3897	100	0.4691
0.5982	0.4286	110	0.4946
0.5577	0.4676	120	0.5205
0.4735	0.5066	130	0.5119
0.531	0.5455	140	0.5022
0.594	0.5845	150	0.4483
0.4909	0.6235	160	0.4713
0.4483	0.6624	170	0.4820
0.5622	0.7014	180	0.4733
0.5791	0.7404	190	0.4495
0.5893	0.7793	200	0.4526
0.4988	0.8183	210	0.4563
0.5362	0.8573	220	0.4597
0.4293	0.8962	230	0.4597
0.4972	0.9352	240	0.4583
0.4901	0.9742	250	0.4613

mtzig/qwen3-8b-tfdark-lora

qwen3-8b-tfdark-lora