Hugging Face's logo

AAphid
/
demo-dog

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
demo-dog / README.md
AAphid's picture
AAphid
Upload model
135a011 verified
preview code
|
raw
history blame
1.97 kB
metadata
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
library_name: peft
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: demo-dog
    results: []

demo-dog

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: 0.6948

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
4.9833 0.9655 7 3.8146
3.0951 1.9310 14 2.3176
2.004 2.8966 21 1.2414
1.2664 4.0 29 0.9554
1.332 4.9655 36 0.8682
1.2351 5.9310 43 0.7776
1.1554 6.8966 50 0.7336
0.9713 8.0 58 0.7043
1.0841 8.9655 65 0.6968
1.0226 9.6552 70 0.6948

Framework versions

  • PEFT 0.11.1
  • Transformers 4.41.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1