README.md

---
license:
- apache-2.0
- cc-by-nc-4.0
datasets: pszemraj/fleece2instructions-codealpaca
tags:
  - generated_from_trainer
  - instruct
  - instructions
  - code
metrics:
  - rouge
language:
  - en
widget:
  - text: >
      import torch

      from transformers import AutoTokenizer, AutoModelForSequenceClassification


      checkpoint = "distilbert-base-uncased-finetuned-sst-2-english"

      tokenizer = AutoTokenizer.from_pretrained(checkpoint)

      model = AutoModelForSequenceClassification.from_pretrained(checkpoint)

      sequences = ["I've been waiting for a HuggingFace course my whole life.",
      "So have I!"]


      tokens = tokenizer(sequences, padding=True, truncation=True,
      return_tensors="pt")

      output = model(**tokens)
    example_title: Example One
  - text: >
      import torch

      from tqdm.auto import tqdm


      device = torch.device("cuda") if torch.cuda.is_available() else
      torch.device("cpu")

      model.to(device)


      progress_bar = tqdm(range(num_training_steps))


      model.train()

      for epoch in range(num_epochs):
          for batch in train_dataloader:
              batch = {k: v.to(device) for k, v in batch.items()}
              outputs = model(**batch)
              loss = outputs.loss
              loss.backward()

              optimizer.step()
              lr_scheduler.step()
              optimizer.zero_grad()
              progress_bar.update(1)
    example_title: Example Two
  - text: |
      import evaluate

      metric = evaluate.load("glue", "mrpc")
      model.eval()
      for batch in eval_dataloader:
          batch = {k: v.to(device) for k, v in batch.items()}
          with torch.no_grad():
              outputs = model(**batch)

          logits = outputs.logits
          predictions = torch.argmax(logits, dim=-1)
          metric.add_batch(predictions=predictions, references=batch["labels"])

      metric.compute()
    example_title: Example Three
  - text: |
      git lfs install
      huggingface-cli lfs-enable-largefiles .
      git lfs track "*.bin"
      git add .
      git commit -a -m "add fp32 chkpt"
      git push
    example_title: Example Four
  - text: |
      export interface DocumentParams {
        pageContent: string;

        // eslint-disable-next-line @typescript-eslint/no-explicit-any
        metadata: Record<string, any>;
      }

      /**
       * Interface for interacting with a document.
       */
      export class Document implements DocumentParams {
        pageContent: string;

        // eslint-disable-next-line @typescript-eslint/no-explicit-any
        metadata: Record<string, any>;

        constructor(fields?: Partial<DocumentParams>) {
          this.pageContent = fields?.pageContent ?? this.pageContent;
          this.metadata = fields?.metadata ?? {};
        }
      }
    example_title: Example Five
inference:
  parameters:
    max_length: 96
    num_beams: 4

---


# bart-base-code-instructiongen

Use this text2text model to find out what LLM instructions might be able to generate an arbitary piece of code!

This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the `pszemraj/fleece2instructions-codealpaca` dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0136
- Rouge1: 59.9513
- Rouge2: 33.9118
- Rougel: 55.7815
- Rougelsum: 56.9064
- Gen Len: 29.7146

## Intended uses & limitations

🚨 **note:** as the authors elected to release the [original dataset](https://github.com/sahil280114/codealpaca) under `cc-by-nc`, the license carries over to this model and **cannot be used for commercial activity**. 

> This is just a `base` size model, which does a decent job for its size, but is not perfect. For better quality instructions, check out [bart-large](https://huggingface.co/pszemraj/bart-large-code-instructiongen) or fine tune your own larger model on the dataset :)

Intended use: Research on domain adaptation and/or other improvements to LLMs by extending instruction:text data pairs.

## Training and evaluation data

Refer to the linked dataset card for `pszemraj/fleece2instructions-codealpaca` or the [original dataset](https://github.com/sahil280114/codealpaca) repo.

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 8e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.02
- num_epochs: 3.0

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| 1.1165        | 1.0   | 281  | 1.1090          | 57.9239 | 31.9259 | 53.8737 | 54.9811   | 28.2924 |
| 1.0763        | 2.0   | 563  | 1.0267          | 59.9605 | 34.0298 | 55.7523 | 56.8021   | 29.6966 |
| 0.9595        | 2.99  | 843  | 1.0136          | 59.9513 | 33.9118 | 55.7815 | 56.9064   | 29.7146 |