jlpan/starcoder-tune-cpp2py-program3

1---2license: bigcode-openrail-m3base_model: bigcode/starcoder4tags:5- generated_from_trainer6model-index:7- name: starcoder-tune-cpp2py-program38  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-tune-cpp2py-program316 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: 0.266820 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: 4e-0639- train_batch_size: 140- eval_batch_size: 141- seed: 4242- gradient_accumulation_steps: 1643- total_train_batch_size: 1644- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0845- lr_scheduler_type: cosine46- lr_scheduler_warmup_steps: 5047- training_steps: 50048 49### Training results50 51| Training Loss | Epoch | Step | Validation Loss |52|:-------------:|:-----:|:----:|:---------------:|53| 0.2926        | 0.1   | 50   | 0.2730          |54| 0.2937        | 0.2   | 100  | 0.2679          |55| 0.2886        | 0.3   | 150  | 0.2671          |56| 0.2853        | 0.4   | 200  | 0.2669          |57| 0.2891        | 0.5   | 250  | 0.2669          |58| 0.2868        | 0.6   | 300  | 0.2668          |59| 0.2847        | 0.7   | 350  | 0.2668          |60| 0.2882        | 0.8   | 400  | 0.2668          |61| 0.2846        | 0.9   | 450  | 0.2668          |62| 0.2893        | 1.0   | 500  | 0.2668          |63 64 65### Framework versions66 67- PEFT 0.5.0.dev068- PEFT 0.5.0.dev069- PEFT 0.5.0.dev070- PEFT 0.5.0.dev071- PEFT 0.5.0.dev072- PEFT 0.5.0.dev073- PEFT 0.5.0.dev074- PEFT 0.5.0.dev075- Transformers 4.32.0.dev076- Pytorch 2.0.1+cu11777- Datasets 2.12.078- Tokenizers 0.13.379