library_name, license, base_model, tags, model-index

library_name	license	base_model	tags	model-index
transformers	apache-2.0	Qwen/Qwen3-0.6B	generated_from_trainer	name results sft-count_loss-Qwen3-0.6B-mle0.5-ul0.5-tox0-e4

sft-count_loss-Qwen3-0.6B-mle0.5-ul0.5-tox0-e4

This model is a fine-tuned version of Qwen/Qwen3-0.6B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.9505

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 3e-05
• train_batch_size: 4
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 5
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
2.7934	0.2899	200	1.3768
2.6787	0.5797	400	1.3584
2.7074	0.8696	600	1.3443
1.8508	1.1594	800	1.3934
1.9016	1.4493	1000	1.4017
1.8603	1.7391	1200	1.4073
1.7469	2.0290	1400	1.6987
0.9924	2.3188	1600	1.7187
1.0118	2.6087	1800	1.7246
0.9845	2.8986	2000	1.7222
0.5651	3.1884	2200	1.9391
0.5605	3.4783	2400	1.9573
0.553	3.7681	2600	1.9505

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1