jlpan/starcoder-php2py-snippet2

1---2license: bigcode-openrail-m3base_model: bigcode/starcoder4tags:5- generated_from_trainer6model-index:7- name: starcoder-php2py-snippet28  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-php2py-snippet216 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: 0.183120 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: 7e-0539- train_batch_size: 1640- eval_batch_size: 1641- seed: 4242- gradient_accumulation_steps: 543- total_train_batch_size: 8044- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0845- lr_scheduler_type: cosine46- lr_scheduler_warmup_steps: 1047- training_steps: 10048 49### Training results50 51| Training Loss | Epoch | Step | Validation Loss |52|:-------------:|:-----:|:----:|:---------------:|53| 0.1912        | 0.25  | 25   | 0.1918          |54| 0.1893        | 0.5   | 50   | 0.1861          |55| 0.182         | 0.75  | 75   | 0.1836          |56| 0.1822        | 1.0   | 100  | 0.1831          |57 58 59### Framework versions60 61- PEFT 0.5.0.dev062- PEFT 0.5.0.dev063- 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