metadata
license: apache-2.0
base_model: t5-large
tags:
- generated_from_trainer
model-index:
- name: purpose_extractor
results: []
This model extracts purpose from intent.
purpose_extractor
This model is a fine-tuned version of t5-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0203
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1179 | 1.0 | 109 | 0.6176 |
| 0.09 | 2.0 | 218 | 0.1340 |
| 0.0982 | 3.0 | 327 | 0.0781 |
| 0.0015 | 4.0 | 436 | 0.0522 |
| 0.3695 | 5.0 | 545 | 0.0406 |
| 0.0051 | 6.0 | 654 | 0.0310 |
| 0.0294 | 7.0 | 763 | 0.0251 |
| 0.0027 | 8.0 | 872 | 0.0228 |
| 0.015 | 9.0 | 981 | 0.0209 |
| 0.0303 | 10.0 | 1090 | 0.0203 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1
- Datasets 2.15.0
- Tokenizers 0.15.0