RafaelZequeira's picture
Upload tokenizer
787e89b verified
metadata
license: bigcode-openrail-m
tags:
  - generated_from_trainer
base_model: bigcode/starcoderbase-1b
model-index:
  - name: starcoderbase-1b-cucumber-copilot
    results: []

starcoderbase-1b-cucumber-copilot

This model is a fine-tuned version of bigcode/starcoderbase-1b on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6377

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: 16
  • eval_batch_size: 16
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 256
  • total_eval_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 30
  • training_steps: 1000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.6697 0.25 250 0.6523
0.4537 0.5 500 0.6328
0.3829 0.75 750 0.6309
0.3245 1.0 1000 0.6377

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.2.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.1