Edit model card

peft-starcoder-lora-a100

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: 5.6557

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 30
  • training_steps: 2000

Training results

Training Loss Epoch Step Validation Loss
5.5246 0.05 100 7.4569
5.6178 0.1 200 7.2622
5.1291 0.15 300 6.4100
5.0522 0.2 400 6.3068
5.2029 0.25 500 6.1171
4.6541 0.3 600 6.0183
5.1002 0.35 700 6.0004
5.0498 0.4 800 5.8895
4.5412 0.45 900 5.8138
5.0007 0.5 1000 5.8342
5.0265 0.55 1100 5.7819
4.4118 0.6 1200 5.7206
4.7825 0.65 1300 5.7364
4.9802 0.7 1400 5.7123
4.3687 0.75 1500 5.6896
4.8847 0.8 1600 5.6759
4.9144 0.85 1700 5.6624
4.2487 0.9 1800 5.6601
4.7984 0.95 1900 5.6640
4.7042 1.0 2000 5.6557

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference API
Unable to determine this model's library. Check the docs .

Model tree for MariaK/peft-starcoder-lora-a100

Finetuned
(16)
this model