Hugging Face's logo

andreaschandra
/
Mistral-7B-v0.1-oasst-top1

PEFT
Safetensors
generated_from_trainer
Model card Files Community
Mistral-7B-v0.1-oasst-top1 / README.md
andreaschandra's picture
andreaschandra
End of training
51fb5e0
preview code
|
raw history blame contribute delete
No virus
1.6 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
model-index:
  - name: Mistral-7B-v0.1-oasst-top1
    results: []

Mistral-7B-v0.1-oasst-top1

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

  • Loss: 2.8934

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: 2
  • eval_batch_size: 2
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.8235 1.0 50 2.2676
1.2795 2.0 100 2.4106
0.9641 3.0 150 2.7605
0.4394 4.0 200 2.8580
0.4801 5.0 250 2.8934

Framework versions

  • PEFT 0.7.1
  • Transformers 4.36.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0