Hugging Face's logo

fabiothecarvalho
/
mistral-ate-notes

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
mistral-ate-notes / README.md
fabiothecarvalho's picture
fabiothecarvalho
End of training
6043919 verified
preview code
|
raw
history blame contribute delete
1.54 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.1-GPTQ
model-index:
  - name: mistral-ate-notes
    results: []

mistral-ate-notes

This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.1-GPTQ on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4779

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: 0.0002
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.8962 0.51 20 0.7584
0.5061 1.03 40 0.5648
0.4417 1.54 60 0.4779

Framework versions

  • PEFT 0.7.1
  • Transformers 4.37.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0