ft-poc / README.md
Farisya's picture
Farisya/ft-poc
9316b78 verified
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
model-index:
  - name: ft-poc
    results: []

ft-poc

This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5077

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: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 2
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
3.6207 0.91 5 2.8472
2.1794 2.0 11 1.9461
1.8396 2.91 16 1.4070
1.0288 4.0 22 0.8795
0.7943 4.91 27 0.6335
0.5105 6.0 33 0.5606
0.5624 6.91 38 0.5307
0.4441 8.0 44 0.5145
0.5156 8.91 49 0.5080
0.2438 9.09 50 0.5077

Framework versions

  • PEFT 0.10.0
  • Transformers 4.38.1
  • Pytorch 2.1.2
  • Datasets 2.18.0
  • Tokenizers 0.15.2