jlpan's picture
update model card README.md
0ae564c
metadata
license: bigcode-openrail-m
base_model: bigcode/starcoder
tags:
  - generated_from_trainer
model-index:
  - name: starcoder-finetuned-test_newSnippet
    results: []

starcoder-finetuned-test_newSnippet

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

  • Loss: 0.1863

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-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 256
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 25
  • training_steps: 275

Training results

Training Loss Epoch Step Validation Loss
6.5337 0.09 25 0.7416
0.4715 0.18 50 0.2515
0.2329 0.27 75 0.2060
0.2093 0.36 100 0.1973
0.1994 0.45 125 0.1935
0.1836 1.03 150 0.1893
0.1912 1.12 175 0.1877
0.1947 1.21 200 0.1870
0.194 1.3 225 0.1865
0.1908 1.39 250 0.1863
0.1845 1.48 275 0.1863

Framework versions

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