etiennebamas / formalmathatepfl

finetuning_qwen3_8b

This model is a fine-tuned version of Qwen/Qwen3-8B.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

Continued pre-training then finetuning. CPT and finetuning parameters are slightly different than from other models in the repo!

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0001
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• total_eval_batch_size: 32
• 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_steps: 0.03
• num_epochs: 1.0

Training results

Framework versions

• Transformers 5.2.0
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.22.2