Hugging Face's logo

sam2ai
/
llama3_odia_8b_lora_sft_v1.1

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
llama3_odia_8b_lora_sft_v1.1 / README.md
sam2ai's picture
sam2ai
Upload folder using huggingface_hub
a7cf583 verified
preview code
|
raw
history blame contribute delete
1.67 kB
metadata
base_model: OdiaGenAI-LLM/llama_3_8b_odia_pt
library_name: peft
license: other
tags:
  - llama-factory
  - lora
  - generated_from_trainer
model-index:
  - name: sft
    results: []

Visualize in Weights & Biases

sft

This model is a fine-tuned version of OdiaGenAI-LLM/llama_3_8b_odia_pt on the odia_sft dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3962

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: 0.0001
  • train_batch_size: 2
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10.0

Training results

Training Loss Epoch Step Validation Loss
0.1145 8.8889 500 0.3873

Framework versions

  • PEFT 0.11.1
  • Transformers 4.42.3
  • Pytorch 2.3.1+rocm6.0
  • Datasets 2.20.0
  • Tokenizers 0.19.1