atinrao's picture
huggingface.co/atinrao/llama38binstruct-summary-100s
8a4aa8d verified
metadata
license: other
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: NousResearch/Meta-Llama-3-8B-Instruct
datasets:
  - generator
model-index:
  - name: llama38binstruct_summarize
    results: []

llama38binstruct_summarize

This model is a fine-tuned version of NousResearch/Meta-Llama-3-8B-Instruct on the generator dataset. It achieves the following results on the evaluation set:

  • Loss: 1.9058

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: 0.0002
  • train_batch_size: 1
  • 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_steps: 0.03
  • training_steps: 100

Training results

Training Loss Epoch Step Validation Loss
1.5019 1.25 25 1.4253
0.5119 2.5 50 1.8478
0.2398 3.75 75 1.8915
0.1067 5.0 100 1.9058

Framework versions

  • PEFT 0.11.1
  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1