Hugging Face's logo

bilkultheek
/
YaHaHamaraLlama

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
YaHaHamaraLlama / README.md
bilkultheek's picture
bilkultheek
End of training
cf6813b verified
preview code
|
raw
history blame contribute delete
1.2 kB
metadata
base_model: ahxt/LiteLlama-460M-1T
library_name: peft
license: mit
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: YaHaHamaraLlama
    results: []

YaHaHamaraLlama

This model is a fine-tuned version of ahxt/LiteLlama-460M-1T on the None dataset.

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 5

Training results

Framework versions

  • PEFT 0.12.0
  • Transformers 4.43.3
  • Pytorch 2.3.1+cu121
  • Datasets 2.17.0
  • Tokenizers 0.19.1