metadata
license: apache-2.0
base_model: google/flan-t5-base
tags:
- generated_from_trainer
datasets:
- mtc/span_absinth_with_articles_german_faithfulness_detection_dataset
model-index:
- name: >-
google-flan-t5-base_MAX-CONTEXT-LEN-1024_MAX-GEN-LEN-256_span_absinth_faithfulness_multi_label_classification_sugary-trellis-2024-07-15
results: []
google-flan-t5-base_MAX-CONTEXT-LEN-1024_MAX-GEN-LEN-256_span_absinth_faithfulness_multi_label_classification_sugary-trellis-2024-07-15
This model is a fine-tuned version of google/flan-t5-base on the mtc/span_absinth_with_articles_german_faithfulness_detection_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.1605
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9007 | 0.1534 | 100 | 0.5516 |
| 0.2893 | 0.3067 | 200 | 0.2852 |
| 0.2428 | 0.4601 | 300 | 0.2061 |
| 0.2088 | 0.6135 | 400 | 0.1619 |
| 0.1627 | 0.7669 | 500 | 0.1604 |
| 0.1662 | 0.9202 | 600 | 0.1678 |
| 0.1602 | 1.0736 | 700 | 0.1578 |
| 0.1219 | 1.2270 | 800 | 0.1594 |
| 0.1135 | 1.3804 | 900 | 0.1677 |
| 0.1024 | 1.5337 | 1000 | 0.1620 |
| 0.111 | 1.6871 | 1100 | 0.1586 |
| 0.1053 | 1.8405 | 1200 | 0.1542 |
| 0.0922 | 1.9939 | 1300 | 0.1526 |
| 0.087 | 2.1472 | 1400 | 0.1585 |
| 0.1259 | 2.3006 | 1500 | 0.1552 |
| 0.1027 | 2.4540 | 1600 | 0.1584 |
| 0.0771 | 2.6074 | 1700 | 0.1591 |
| 0.0918 | 2.7607 | 1800 | 0.1609 |
| 0.0782 | 2.9141 | 1900 | 0.1604 |
Framework versions
- Transformers 4.42.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1