WooWoofV2
This model is a fine-tuned version of unsloth/meta-llama-3.1-8b-bnb-4bit on an unknown dataset.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 4
- eval_batch_size: 8
- seed: 3407
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 50
Framework versions
- PEFT 0.12.0
- Transformers 4.44.1
- Pytorch 2.3.1
- Datasets 3.0.0
- Tokenizers 0.19.1
- Downloads last month
- 55
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for larry1129/WooWoof_AI
Base model
meta-llama/Meta-Llama-3.1-8B
Adapter
this model
Space using larry1129/WooWoof_AI 1
Evaluation results
- ROUGE-1 F1 Scoreself-reported0.746
- ROUGE-2 F1 Scoreself-reported0.661
- ROUGE-L F1 Scoreself-reported0.725
- BLEU Scoreself-reported0.621
- METEOR Scoreself-reported0.739
- BERTScore Precisionself-reported0.965
- BERTScore Recallself-reported0.965
- BERTScore F1self-reported0.965