advy/llama71b-mentalchat16k

<!-- 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. -->

llama71b-mentalchat16k

This model is a fine-tuned version of meta-llama/Llama-3.1-70B-Instruct on the ShenLab/MentalChat16k dataset. It achieves the following results on the evaluation set:

• —Loss: 0.6542

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: 8e-05
• —trainbatchsize: 1
• —evalbatchsize: 1
• —seed: 42
• —gradientaccumulationsteps: 8
• —totaltrainbatch_size: 8
• —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.03
• —num_epochs: 3
• —mixedprecisiontraining: Native AMP

Training results

LLAMA 3.1 TEST SET EVALUATION:

================================================== ROUGE Scores (Average F-Measure):

• —ROUGE-1: 0.3051
• —ROUGE-2: 0.1122
• —ROUGE-L: 0.1678

BLEU Score:

• —BLEU: 0.0646 ==================================================

Framework versions

• —PEFT 0.18.0
• —Transformers 4.57.1
• —Pytorch 2.5.1+cu124
• —Datasets 4.4.1
• —Tokenizers 0.22.1