Qwen3-4B-SFT-science-1e-5/README.md

library_name, license, base_model, tags, model-index

library_name	license	base_model	tags	model-index
transformers	other	Qwen/Qwen3-4B	llama-factory full generated_from_trainer	name results Qwen3-4B-SFT-science-1e-5

Qwen3-4B-SFT-science-1e-5

This model is a fine-tuned version of Qwen/Qwen3-4B on the dolci_science_train dataset. It achieves the following results on the evaluation set:

• Loss: 0.6778

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: 1e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• total_eval_batch_size: 8
• 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: cosine
• lr_scheduler_warmup_steps: 0.05
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.8065	0.2985	230	0.7250
0.6763	0.5969	460	0.7040
0.7030	0.8954	690	0.6914
0.6122	1.1933	920	0.6877
0.6361	1.4918	1150	0.6827
0.6499	1.7903	1380	0.6778
0.5879	2.0882	1610	0.6838
0.5390	2.3867	1840	0.6826
0.6058	2.6852	2070	0.6820
0.6097	2.9836	2300	0.6816

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2