metadata
license: apache-2.0
base_model: google/flan-t5-small
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: flan_t5_small_scotus
results: []
flan_t5_small_scotus
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: 1.5666
- Accuracy: 0.5364
- F1 Macro: 0.3416
- F1 Micro: 0.5364
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: 0.0005
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 32
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
|---|---|---|---|---|---|---|
| 2.0567 | 0.32 | 50 | 1.9618 | 0.4043 | 0.1221 | 0.4043 |
| 1.6729 | 0.64 | 100 | 1.7861 | 0.4543 | 0.1656 | 0.4543 |
| 1.7754 | 0.96 | 150 | 1.7046 | 0.4664 | 0.2297 | 0.4664 |
| 1.5495 | 1.27 | 200 | 1.6304 | 0.4936 | 0.2712 | 0.4936 |
| 1.4455 | 1.59 | 250 | 1.6284 | 0.5114 | 0.3063 | 0.5114 |
| 1.3035 | 1.91 | 300 | 1.6333 | 0.5164 | 0.3130 | 0.5164 |
| 1.3057 | 2.23 | 350 | 1.5789 | 0.5286 | 0.3341 | 0.5286 |
| 1.2992 | 2.55 | 400 | 1.5673 | 0.5357 | 0.3398 | 0.5357 |
| 1.1637 | 2.87 | 450 | 1.5666 | 0.5364 | 0.3416 | 0.5364 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2