Hugging Face's logo

ashkid
/
shakespeare-ft

PEFT
TensorBoard
Safetensors
mistral
Generated from Trainer
4-bit precision
gptq
Model card Files Metrics Community
shakespeare-ft / README.md
ashkid's picture
ashkid
Update README.md
bbb3452 verified
preview code
|
raw
history blame contribute delete
2.49 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
model-index:
  - name: shakespeare-ft
    results: []

Cite

This model is trained from Talebi S. YouTube-Blog. 2024. https://github.com/ShawhinT/YouTube-Blog

shakespeare-ft

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

  • Loss: 0.7122

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: 16
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.3058 0.97 15 1.2255
1.017 2.0 31 1.1220
0.9377 2.97 46 1.0527
0.7699 4.0 62 0.9921
0.728 4.97 77 0.9438
0.6098 6.0 93 0.8995
0.5781 6.97 108 0.8649
0.4823 8.0 124 0.8288
0.4598 8.97 139 0.8065
0.3866 10.0 155 0.7736
0.3693 10.97 170 0.7525
0.3165 12.0 186 0.7422
0.312 12.97 201 0.7276
0.2761 14.0 217 0.7160
0.2815 14.97 232 0.7121
0.2463 15.48 240 0.7122

Framework versions

  • PEFT 0.10.0
  • Transformers 4.39.3
  • Pytorch 2.1.0+cu121
  • Datasets 2.19.0
  • Tokenizers 0.15.2