jlpan's picture
update model card README.md
50ad907
metadata
license: bigcode-openrail-m
base_model: bigcode/starcoder
tags:
  - generated_from_trainer
model-index:
  - name: starcoder-cpp2py-newprogram2
    results: []

starcoder-cpp2py-newprogram2

This model is a fine-tuned version of bigcode/starcoder on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1064

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: 2e-05
  • 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_steps: 15
  • training_steps: 150

Training results

Training Loss Epoch Step Validation Loss
0.1118 0.17 25 0.1079
0.1182 0.33 50 0.1073
0.114 0.5 75 0.1068
0.1116 0.67 100 0.1065
0.1125 0.83 125 0.1064
0.11 1.03 150 0.1064

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.1+cu117
  • Datasets 2.12.0
  • Tokenizers 0.13.3