Edit model card

llama38binstruct_summarize

This model is a fine-tuned version of NousResearch/Meta-Llama-3-8B-Instruct on the generator dataset. It achieves the following results on the evaluation set:

  • Loss: 2.1068

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: 1
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_steps: 30
  • training_steps: 100

Training results

Training Loss Epoch Step Validation Loss
1.55 1.3158 25 1.5000
0.5276 2.6316 50 1.7814
0.2099 3.9474 75 1.8811
0.0761 5.2632 100 2.1068

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.2
  • Pytorch 2.4.0+cu121
  • Datasets 3.0.0
  • Tokenizers 0.19.1
Downloads last month
4
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for llm-wizard/llama38binstruct_summarize

Adapter
(93)
this model