Hugging Face's logo

dmusingu
/
Llama-3-8B-sft-lora-ultrachat

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
Llama-3-8B-sft-lora-ultrachat / README.md
dmusingu's picture
dmusingu
End of training
90a2571 verified
preview code
|
raw
history blame contribute delete
1.48 kB
metadata
license: other
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B-Instruct
datasets:
  - generator
model-index:
  - name: Llama-3-8B-sft-lora-ultrachat
    results: []

Llama-3-8B-sft-lora-ultrachat

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

  • Loss: 1.3129

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: 2e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.3036 1.0 278 1.3129

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.2
  • Pytorch 2.3.0a0+40ec155e58.nv24.03
  • Datasets 2.19.1
  • Tokenizers 0.19.1