Qwen3-4B-SFT-envbench_weave_2500

This model is a fine-tuned version of Qwen/Qwen3-4B on the envbench_weave_2500 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3336
• Accuracy: 0.9056
• Num Input Tokens Seen: 93658048

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• 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: 0.1
• num_epochs: 5.0

Training results

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0a0+df5bbc09d1.nv24.12
• Datasets 3.6.0
• Tokenizers 0.21.1