hoangphu7122002ai's picture
Model save
c7b392c
|
raw
history blame
1.5 kB
metadata
base_model: meta-llama/Llama-2-7b-hf
tags:
  - generated_from_trainer
model-index:
  - name: final_LLama_kpi_qlora
    results: []

final_LLama_kpi_qlora

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1214

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: 6e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
0.0828 0.18 800 nan
0.1073 0.37 1600 0.1464
0.0774 0.55 2400 0.1327
0.0626 0.73 3200 0.1265
0.0673 0.92 4000 0.1214

Framework versions

  • Transformers 4.34.0.dev0
  • Pytorch 2.0.0
  • Datasets 2.11.0
  • Tokenizers 0.14.0