BohdanPetryshyn's picture
Model save
1d52662 verified
metadata
license: llama2
library_name: peft
tags:
  - generated_from_trainer
base_model: codellama/CodeLlama-7b-hf
model-index:
  - name: codellama-7b-openapi-completion-ctx-lvl-fim-no-spm-inf-seq-4096
    results: []

Visualize in Weights & Biases

codellama-7b-openapi-completion-ctx-lvl-fim-no-spm-inf-seq-4096

This model is a fine-tuned version of codellama/CodeLlama-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5167

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: 8
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.05
  • training_steps: 1000

Training results

Training Loss Epoch Step Validation Loss
0.4631 0.1 100 0.4945
0.343 0.2 200 0.4979
0.3397 0.3 300 0.4996
0.3424 0.4 400 0.4979
0.4474 0.5 500 0.5107
0.2682 0.6 600 0.5066
0.3116 0.7 700 0.5159
0.3161 0.8 800 0.5126
0.3364 0.9 900 0.5163
0.3115 1.0 1000 0.5167

Framework versions

  • PEFT 0.10.1.dev0
  • Transformers 4.41.0.dev0
  • Pytorch 2.2.2+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1