metadata

base_model: meta-llama/Llama-2-13b-hf
tags:
  - generated_from_trainer
datasets:
  - cnn_dailymail
model-index:
  - name: 7941_Llama-2-13b-hf
    results: []
library_name: peft

7941_Llama-2-13b-hf

This model is a fine-tuned version of meta-llama/Llama-2-13b-hf on the cnn_dailymail dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

The following bitsandbytes quantization config was used during training:

quant_method: bitsandbytes
load_in_8bit: True
load_in_4bit: False
llm_int8_threshold: 6.0
llm_int8_skip_modules: None
llm_int8_enable_fp32_cpu_offload: False
llm_int8_has_fp16_weight: False
bnb_4bit_quant_type: fp4
bnb_4bit_use_double_quant: False
bnb_4bit_compute_dtype: float32

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Framework versions

PEFT 0.4.0
Transformers 4.36.2
Pytorch 2.1.0+cu121
Datasets 2.15.0
Tokenizers 0.15.0