grace-pro's picture
one_half_data_high_rank_v2
bee6bd6 verified
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - accuracy
base_model: mistralai/Mistral-7B-v0.1
model-index:
  - name: one_half_data_high_rank_v2
    results: []

one_half_data_high_rank_v2

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6564
  • Precision: 0.8403
  • Recall: 0.9383
  • F1-score: 0.8866
  • Accuracy: 0.8450

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: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1-score Accuracy
0.535 1.0 24544 0.6564 0.8403 0.9383 0.8866 0.8450

Framework versions

  • PEFT 0.9.0
  • Transformers 4.38.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2