Edit model card

CodeLLAMA3-8BI-300APPS

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

  • Loss: 0.8161

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: 5e-06
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 50
  • training_steps: 300

Training results

Training Loss Epoch Step Validation Loss
0.8319 0.1667 50 0.8777
0.8227 0.3333 100 0.8417
0.7556 0.5 150 0.8246
0.7674 0.6667 200 0.8183
0.8084 0.8333 250 0.8164
0.7494 1.0 300 0.8161

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.19.1
Downloads last month
0
Unable to determine this model’s pipeline type. Check the docs .

Adapter for