mrm8488/santacoder-finetuned-the-stack-bash

1---2license: openrail3tags:4- generated_from_trainer5model-index:6- name: santacoder-finetuned-the-stack-bash7  results: []8---9 10<!-- This model card has been generated automatically according to the information the Trainer had access to. You11should probably proofread and complete it, then remove this comment. -->12 13# santacoder-finetuned-the-stack-bash14 15This model is a fine-tuned version of [bigcode/santacoder](https://huggingface.co/bigcode/santacoder) on an unknown dataset.16It achieves the following results on the evaluation set:17- Loss: nan18 19## Model description20 21More information needed22 23## Intended uses & limitations24 25More information needed26 27## Training and evaluation data28 29More information needed30 31## Training procedure32 33### Training hyperparameters34 35The following hyperparameters were used during training:36- learning_rate: 5e-0537- train_batch_size: 238- eval_batch_size: 839- seed: 4240- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0841- lr_scheduler_type: cosine42- lr_scheduler_warmup_steps: 10043- training_steps: 50044- mixed_precision_training: Native AMP45 46### Training results47 48| Training Loss | Epoch | Step | Validation Loss |49|:-------------:|:-----:|:----:|:---------------:|50| 1.4569        | 0.5   | 250  | 1.7821          |51| 0.0           | 1.0   | 500  | nan             |52 53 54### Framework versions55 56- Transformers 4.25.157- Pytorch 1.13.1+cu11658- Datasets 2.8.059- Tokenizers 0.13.260