Warkawik/code_example

1---2license: bigcode-openrail-m3library_name: peft4tags:5- generated_from_trainer6base_model: bigcode/starcoderbase-1b7model-index:8- name: code_example9  results: []10---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# code_example16 17This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on an unknown dataset.18It achieves the following results on the evaluation set:19- Loss: 1.059620 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: 0.000539- train_batch_size: 1640- eval_batch_size: 1641- seed: 4242- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0843- lr_scheduler_type: cosine44- lr_scheduler_warmup_steps: 3045- training_steps: 200046 47### Training results48 49| Training Loss | Epoch | Step | Validation Loss |50|:-------------:|:-----:|:----:|:---------------:|51| 0.9662        | 0.05  | 100  | 0.9184          |52| 0.9899        | 0.1   | 200  | 0.9461          |53| 0.6517        | 0.15  | 300  | 0.9698          |54| 0.8963        | 0.2   | 400  | 0.9823          |55| 0.9498        | 0.25  | 500  | 0.9727          |56| 0.5741        | 0.3   | 600  | 1.0098          |57| 0.7985        | 0.35  | 700  | 1.0212          |58| 0.8268        | 0.4   | 800  | 1.0123          |59| 0.5209        | 0.45  | 900  | 1.0178          |60| 0.7512        | 0.5   | 1000 | 1.0302          |61| 0.7718        | 0.55  | 1100 | 1.0342          |62| 0.4746        | 0.6   | 1200 | 1.0492          |63| 0.6964        | 0.65  | 1300 | 1.0394          |64| 0.6844        | 0.7   | 1400 | 1.0471          |65| 0.5396        | 0.75  | 1500 | 1.0495          |66| 0.6569        | 0.8   | 1600 | 1.0553          |67| 0.6005        | 0.85  | 1700 | 1.0609          |68| 0.6015        | 0.9   | 1800 | 1.0632          |69| 0.5552        | 0.95  | 1900 | 1.0620          |70| 0.5883        | 1.0   | 2000 | 1.0596          |71 72 73### Framework versions74 75- PEFT 0.8.276- Transformers 4.37.277- Pytorch 2.1.0+cu12178- Datasets 2.17.179- Tokenizers 0.15.2