trungtienluong's picture
trungtienluong/test_5
fd0f608 verified
metadata
license: mit
library_name: peft
tags:
  - generated_from_trainer
base_model: HuggingFaceH4/zephyr-7b-beta
model-index:
  - name: experiments500czephymodel
    results: []

experiments500czephymodel

This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-beta on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3517

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: 3e-05
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 7
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.3397 0.88 50 0.3425
0.2345 1.77 100 0.2845
0.1679 2.65 150 0.2735
0.1024 3.54 200 0.2875
0.0716 4.42 250 0.3028
0.0466 5.31 300 0.3367
0.0387 6.19 350 0.3430

Framework versions

  • PEFT 0.11.1
  • Transformers 4.36.0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.2
  • Tokenizers 0.15.2