Edit model card

starcoder-tune-cpp2py-snippet3

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

  • Loss: 0.3489

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-06
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 16
  • 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: 50
  • training_steps: 500

Training results

Training Loss Epoch Step Validation Loss
0.5147 0.1 50 0.4060
0.4403 0.2 100 0.3419
0.425 0.3 150 0.3437
0.4298 0.4 200 0.3459
0.4259 0.5 250 0.3480
0.4167 0.6 300 0.3487
0.421 0.7 350 0.3485
0.4289 0.8 400 0.3487
0.424 0.9 450 0.3489
0.4163 1.0 500 0.3489

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.1+cu117
  • Datasets 2.12.0
  • Tokenizers 0.13.3
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 jlpan/starcoder-tune-cpp2py-snippet3

Base model

bigcode/starcoder
Finetuned
(31)
this model