jlpan/starcoder-java2py-program2

1---2license: bigcode-openrail-m3base_model: bigcode/starcoder4tags:5- generated_from_trainer6model-index:7- name: starcoder-java2py-program28  results: []9library_name: peft10---11 12<!-- This model card has been generated automatically according to the information the Trainer had access to. You13should probably proofread and complete it, then remove this comment. -->14 15# starcoder-java2py-program216 17This model is a fine-tuned version of [bigcode/starcoder](https://huggingface.co/bigcode/starcoder) on an unknown dataset.18It achieves the following results on the evaluation set:19- Loss: 0.111020 21## Model description22 23More information needed24 25## Intended uses & limitations26 27More information needed28 29## Training and evaluation data30 31More information needed32 33## Training procedure34 35### Training hyperparameters36 37The following hyperparameters were used during training:38- learning_rate: 2e-0539- train_batch_size: 440- eval_batch_size: 441- seed: 4242- gradient_accumulation_steps: 843- total_train_batch_size: 3244- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0845- lr_scheduler_type: cosine46- lr_scheduler_warmup_steps: 1047- training_steps: 15048 49### Training results50 51| Training Loss | Epoch | Step | Validation Loss |52|:-------------:|:-----:|:----:|:---------------:|53| 0.1128        | 0.17  | 25   | 0.1122          |54| 0.1148        | 0.33  | 50   | 0.1116          |55| 0.1127        | 0.5   | 75   | 0.1113          |56| 0.1149        | 0.67  | 100  | 0.1111          |57| 0.1171        | 0.83  | 125  | 0.1110          |58| 0.1149        | 1.04  | 150  | 0.1110          |59 60 61### Framework versions62 63- PEFT 0.5.0.dev064- PEFT 0.5.0.dev065- Transformers 4.32.0.dev066- Pytorch 2.0.1+cu11767- Datasets 2.12.068- Tokenizers 0.13.369