formalmathatepfl/qwen3-dropout-0.5

g-- library_name: transformers license: other base_model: Qwen/Qwen3-8B tags: - llama-factory - full - generated_from_trainer model-index: - name: Qwen3-feedback-dropout05 results: []

Qwen3-feedback-dropout05

This model is a fine-tuned version of /mnt/task_runtime/models/Qwen3-8B on the dropout05 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0425

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: 8
• total_train_batch_size: 16
• total_eval_batch_size: 16
• optimizer: Use OptimizerNames.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_ratio: 0.05
• num_epochs: 1.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.0554	0.1253	1000	0.0572
0.0509	0.2506	2000	0.0500
0.0499	0.3759	3000	0.0471
0.0459	0.5012	4000	0.0452
0.0421	0.6265	5000	0.0440
0.0408	0.7518	6000	0.0431
0.0431	0.8771	7000	0.0426

Framework versions

• Transformers 4.57.6
• Pytorch 2.9.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2