MeasHalu-3B-Instruct

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

reasoning_test

<!-- This model is a fine-tuned version of [/home/huangruijun/grpo_contract_penalty/test_3b/lora_merge/5500step](https://huggingface.co//home/huangruijun/grpo_contract_penalty/test_3b/lora_merge/5500step) on the reasoning_test dataset. -->

It achieves the following results on the evaluation set:

• Loss: 0.0904

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: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 16
• total_train_batch_size: 32
• total_eval_batch_size: 2
• 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_ratio: 0.1
• num_epochs: 25.0

Training results

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0