metadata
license: apache-2.0
base_model: google/flan-t5-small
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
model-index:
- name: flan-t5-small-qclassifier_new_0.5-droprob_0.2-smooth_0.1-lr_1e-5-dcy_0.1
results: []
flan-t5-small-qclassifier_new_0.5-droprob_0.2-smooth_0.1-lr_1e-5-dcy_0.1
This model is a fine-tuned version of google/flan-t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6632
- Precision: 0.6023
- Recall: 0.9989
- F1: 0.7515
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: 1e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 0.6734 | 1.0 | 193 | 0.6691 | 0.6014 | 1.0 | 0.7511 |
| 0.6664 | 2.0 | 386 | 0.6632 | 0.6023 | 0.9989 | 0.7515 |
| 0.6599 | 3.0 | 579 | 0.6578 | 0.6085 | 0.9763 | 0.7497 |
| 0.6543 | 4.0 | 772 | 0.6553 | 0.6160 | 0.9558 | 0.7492 |
| 0.6505 | 5.0 | 965 | 0.6516 | 0.6387 | 0.8858 | 0.7422 |
| 0.6481 | 6.0 | 1158 | 0.6512 | 0.6454 | 0.8728 | 0.7421 |
| 0.6457 | 7.0 | 1351 | 0.6505 | 0.6460 | 0.8631 | 0.7389 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1