tinyllama_mole_dpo_ep3

<!-- 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. -->

tinyllama_mole_dpo_ep3

This model is a fine-tuned version of ondevicellm/tinyllama_mole_sft_ultrachat_ep3 on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

• Loss: 0.6285
• Rewards/chosen: -0.3050
• Rewards/rejected: -0.5353
• Rewards/accuracies: 0.6806
• Rewards/margins: 0.2302
• Logps/rejected: -354.2071
• Logps/chosen: -373.1399
• Logits/rejected: -1.6731
• Logits/chosen: -1.8041

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: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 1

Training results

Framework versions

• Transformers 4.37.0
• Pytorch 2.1.2+cu118
• Datasets 2.16.1
• Tokenizers 0.15.0