---
license: apache-2.0
language: en
tags:
  - temporal
  - time-module
  - pieces
  - intent-classification
  - temporal-intent
datasets:
  - Pieces/temporal-intent-classification-dataset-split
base_model: google/flan-t5-base
metrics:
  - accuracy
  - f1
pipeline_tag: text-classification
---

# TIME-Module: Classification — flan-t5-base

## Model Description

Temporal intent classification using the larger flan-t5-base model. Classifies user queries into 6 temporal intent categories.

## Training Details

- **Base Model:** [google/flan-t5-base](https://huggingface.co/google/flan-t5-base)
- **Architecture:** T5ForSequenceClassification
- **Dataset:** [Pieces/temporal-intent-classification-dataset-split](https://huggingface.co/datasets/Pieces/temporal-intent-classification-dataset-split) (15,488 train / 1,721 val / 4,303 test)
- **Training Steps:** 5,000
- **Learning Rate:** 3e-4
- **Batch Size:** 64 × 2
- **Mixed Precision:** bf16
- **Hardware:** NVIDIA RTX 4090 (24 GB)

## Results

| Metric | Value |
|--------|-------|
| accuracy | ~95% |

## Usage

```python
from transformers import pipeline

pipe = pipeline('text-classification', model='Pieces/time-classification-flan-t5-base-best')
result = pipe('What meetings do I have tomorrow?')



```

## Part of the TIME-Module Project

This model is part of the TIME (Temporal Intent, Mapping, and Extraction) module, a suite of models for understanding and processing temporal information in natural language.

**Related models:**
- [Pieces/time-classification-flan-t5-small-split-best](https://huggingface.co/Pieces/time-classification-flan-t5-small-split-best) — Intent classification
- [Pieces/time-mapping-flan-t5-small-quality-best](https://huggingface.co/Pieces/time-mapping-flan-t5-small-quality-best) — Span prediction (best)
- [Pieces/time-mapping-t5gemma-270m-best](https://huggingface.co/Pieces/time-mapping-t5gemma-270m-best) — Span prediction (T5Gemma)

## Citation

```bibtex
@software{time_module,
  title={TIME-Module: Temporal Intent, Mapping, and Extraction},
  author={Pieces},
  year={2026},
  url={https://huggingface.co/Pieces}
}
```