drferpa's picture
Model save
6d763fd verified
|
raw
history blame
1.23 kB
metadata
base_model: meta-llama/Llama-2-7b-hf
tags:
  - generated_from_trainer
model-index:
  - name: panita-base-model-llama2-7b-v2
    results: []

panita-base-model-llama2-7b-v2

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on an unknown 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: 0.0001
  • train_batch_size: 1
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 32
  • total_train_batch_size: 256
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.14.1