polyalign-qwen2.5-1.5b-en-dpo

<!-- 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. -->

polyalign

This model is a fine-tuned version of sathiiiii/polyalign-qwen2.5-1.5b-en-sft on the polyalign_dpo_train dataset. It achieves the following results on the evaluation set:

• Loss: 0.3536
• Rewards/chosen: -0.9809
• Rewards/rejected: -6.7007
• Rewards/accuracies: 0.8794
• Rewards/margins: 5.7198
• Logps/chosen: -98.1838
• Logps/rejected: -187.1757
• Logits/chosen: 3.7942
• Logits/rejected: 3.8105

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-07
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• 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_ratio: 0.1
• num_epochs: 1.0
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.56.2
• Pytorch 2.9.1+rocm6.3
• Datasets 4.0.0
• Tokenizers 0.22.2