betteracs/lawbuddy-14b

kto_law

This model is a fine-tuned version of openthaigpt/openthaigpt1.5-14b-instruct on the law_th_kto dataset. It achieves the following results on the evaluation set:

• Loss: 0.5569
• Rewards/chosen: 2.2727
• Logps/chosen: -127.1557
• Kl: 25.3337

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-06
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3.0

Training results

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1