adria / README.md
ayoubto's picture
ayoubto/mistral-adria
fa546b3 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: adria
    results: []

adria

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: 1.3546

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
2.7622 1.0 48 1.7979
1.56 2.0 96 1.4051
1.2313 3.0 144 1.2441
1.0588 4.0 192 1.1994
0.957 5.0 240 1.1856
0.8864 6.0 288 1.2168
0.8323 7.0 336 1.2345
0.7879 8.0 384 1.2773
0.7565 9.0 432 1.3242
0.7307 10.0 480 1.3546

Framework versions

  • PEFT 0.10.0
  • Transformers 4.39.3
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2