Hugging Face's logo

khiepm209
/
final-zalo-2023

TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
final-zalo-2023 / README.md
khiepm209's picture
khiepm209
Model save
cf8654b
preview code
|
raw
history blame
1.36 kB
metadata
license: apache-2.0
base_model: akjindal53244/Arithmo-Mistral-7B
tags:
  - generated_from_trainer
model-index:
  - name: final-zalo-2023
    results: []

final-zalo-2023

This model is a fine-tuned version of akjindal53244/Arithmo-Mistral-7B on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4636

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: 1.1e-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: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.2973 0.56 1000 0.4636

Framework versions

  • Transformers 4.36.0.dev0
  • Pytorch 2.0.0
  • Datasets 2.1.0
  • Tokenizers 0.15.0