ZiHDeng's picture
End of training
6aac8e1 verified
|
raw
history blame
1.53 kB
metadata
license: bigcode-openrail-m
library_name: peft
tags:
  - generated_from_trainer
base_model: bigcode/starcoderbase-1b
model-index:
  - name: peft-lora-starcoder1B-Instruction-ny8-MIX
    results: []

peft-lora-starcoder1B-Instruction-ny8-MIX

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: 0.1670

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: 0.0005
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 30
  • training_steps: 150
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.1662 0.67 100 0.1670

Framework versions

  • PEFT 0.7.1
  • Transformers 4.36.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0