> ## Documentation Index
> Fetch the complete documentation index at: https://docs.monostate.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Text Tasks

> Train text classification, regression, and NER models

# Text Tasks

Train models for text classification, regression, and token classification.

## Text Classification

### Quick Start

```bash theme={null}
aitraining text-classification \
  --model bert-base-uncased \
  --data-path ./reviews.csv \
  --text-column text \
  --target-column label \
  --project-name sentiment-model
```

### Parameters

| Parameter                    | Description                          | Default             |
| ---------------------------- | ------------------------------------ | ------------------- |
| `--model`                    | Base model                           | `bert-base-uncased` |
| `--data-path`                | Path to data (CSV, JSON, HF dataset) | None (required)     |
| `--project-name`             | Output directory                     | `project-name`      |
| `--text-column`              | Column with text                     | `text`              |
| `--target-column`            | Column with labels                   | `target`            |
| `--epochs`                   | Training epochs                      | `3`                 |
| `--batch-size`               | Batch size                           | `8`                 |
| `--lr`                       | Learning rate                        | `5e-5`              |
| `--max-seq-length`           | Maximum sequence length              | `128`               |
| `--warmup-ratio`             | Warmup proportion                    | `0.1`               |
| `--weight-decay`             | Weight decay                         | `0.0`               |
| `--early-stopping-patience`  | Early stopping patience              | `5`                 |
| `--early-stopping-threshold` | Early stopping threshold             | `0.01`              |

### Example: Sentiment Analysis

```bash theme={null}
aitraining text-classification \
  --model distilbert-base-uncased \
  --data-path ./sentiment.csv \
  --text-column review \
  --target-column sentiment \
  --project-name sentiment \
  --epochs 5 \
  --batch-size 16
```

## Text Regression

For predicting continuous values from text.

### Quick Start

```bash theme={null}
aitraining text-regression \
  --model bert-base-uncased \
  --data-path ./scores.csv \
  --text-column text \
  --target-column score \
  --project-name score-predictor
```

### Example: Rating Prediction

```bash theme={null}
aitraining text-regression \
  --model microsoft/deberta-v3-base \
  --data-path ./reviews.csv \
  --text-column review_text \
  --target-column rating \
  --project-name rating-predictor \
  --epochs 10
```

## Token Classification (NER)

For named entity recognition and similar tasks.

### Quick Start

```bash theme={null}
aitraining token-classification \
  --model bert-base-cased \
  --data-path ./ner_data.json \
  --tokens-column tokens \
  --tags-column ner_tags \
  --project-name ner-model
```

### Data Format

Your data should have tokenized text and corresponding tags:

```json theme={null}
{
  "tokens": ["John", "lives", "in", "New", "York"],
  "ner_tags": ["B-PER", "O", "O", "B-LOC", "I-LOC"]
}
```

### Parameters

| Parameter          | Description             | Default  |
| ------------------ | ----------------------- | -------- |
| `--tokens-column`  | Column with token lists | `tokens` |
| `--tags-column`    | Column with tag lists   | `tags`   |
| `--max-seq-length` | Maximum sequence length | `128`    |

### Example: Custom NER

```bash theme={null}
aitraining token-classification \
  --model bert-base-cased \
  --data-path ./custom_entities.json \
  --tokens-column words \
  --tags-column labels \
  --project-name custom-ner \
  --epochs 5 \
  --batch-size 16
```

## Sequence-to-Sequence

For translation, summarization, and similar tasks.

### Quick Start

```bash theme={null}
aitraining seq2seq \
  --model t5-small \
  --data-path ./translations.csv \
  --text-column source \
  --target-column target \
  --project-name translator
```

### Parameters

| Parameter             | Description                | Default               |
| --------------------- | -------------------------- | --------------------- |
| `--model`             | Base model                 | `google/flan-t5-base` |
| `--text-column`       | Source text column         | `text`                |
| `--target-column`     | Target text column         | `target`              |
| `--max-seq-length`    | Max source sequence length | `128`                 |
| `--max-target-length` | Max target sequence length | `128`                 |
| `--batch-size`        | Batch size                 | `2`                   |
| `--epochs`            | Training epochs            | `3`                   |
| `--lr`                | Learning rate              | `5e-5`                |

### Example: Summarization

```bash theme={null}
aitraining seq2seq \
  --model facebook/bart-base \
  --data-path ./articles.csv \
  --text-column article \
  --target-column summary \
  --project-name summarizer \
  --epochs 3 \
  --max-seq-length 1024 \
  --max-target-length 128
```

## Extractive QA

For question answering from context.

### Quick Start

```bash theme={null}
aitraining extractive-qa \
  --model bert-base-uncased \
  --data-path ./squad_format.json \
  --project-name qa-model
```

### Parameters

| Parameter           | Description                  | Default    |
| ------------------- | ---------------------------- | ---------- |
| `--text-column`     | Context column               | `context`  |
| `--question-column` | Question column              | `question` |
| `--answer-column`   | Answers column               | `answers`  |
| `--max-seq-length`  | Max sequence length          | `128`      |
| `--max-doc-stride`  | Document stride for chunking | `128`      |

### Data Format

SQuAD-style format:

```json theme={null}
{
  "context": "Paris is the capital of France.",
  "question": "What is the capital of France?",
  "answers": {
    "text": ["Paris"],
    "answer_start": [0]
  }
}
```

## Sentence Transformers

For training sentence embeddings.

### Quick Start

```bash theme={null}
aitraining sentence-transformers \
  --model sentence-transformers/all-MiniLM-L6-v2 \
  --data-path ./pairs.csv \
  --project-name embeddings
```

### Parameters

| Parameter            | Description            | Default      |
| -------------------- | ---------------------- | ------------ |
| `--trainer`          | Training mode          | `pair_score` |
| `--sentence1-column` | First sentence column  | `sentence1`  |
| `--sentence2-column` | Second sentence column | `sentence2`  |
| `--target-column`    | Score/label column     | `None`       |
| `--max-seq-length`   | Max sequence length    | `128`        |
| `--batch-size`       | Batch size             | `8`          |
| `--epochs`           | Training epochs        | `3`          |
| `--lr`               | Learning rate          | `3e-5`       |

### Data Format

Sentence pairs with similarity scores:

```csv theme={null}
sentence1,sentence2,score
"The cat sits.",The feline rests.",0.9
"I love pizza","The sky is blue",0.1
```

## Common Options

All text tasks share these options:

| Option          | Description                             | Default |
| --------------- | --------------------------------------- | ------- |
| `--push-to-hub` | Upload to Hugging Face Hub              | `False` |
| `--username`    | HF username (required if pushing)       | `None`  |
| `--token`       | HF token (required if pushing)          | `None`  |
| `--log`         | Logging: `wandb`, `tensorboard`, `none` | `wandb` |

<Note>
  When using `--push-to-hub`, the repository is created as **private** by default at `{username}/{project-name}`.
</Note>

## Next Steps

<CardGroup cols={2}>
  <Card title="Vision Tasks" href="/cli/vision-tasks">
    Image classification and detection
  </Card>

  <Card title="LLM Training" href="/cli/llm-training">
    Train language models
  </Card>
</CardGroup>