llama-2-7b-enhanced2_20

This model is a fine-tuned version of NousResearch/Llama-2-7b-chat-hf on the Mental Health Conversations dataset.

Model description

info

Intended uses & limitations

Evaluation and Testing purposes.

Training and evaluation data

CounselChat dataset of conversations.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 20

Training results

Framework versions

• Transformers 4.31.0
• Pytorch 2.1.0+cu121
• Datasets 2.14.5
• Tokenizers 0.13.3