metadata
license: apache-2.0
base_model: google/flan-t5-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: flan_t5_base_scotus
results: []
flan_t5_base_scotus
This model is a fine-tuned version of google/flan-t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6815
- Accuracy: 0.5057
- F1 Macro: 0.2620
- F1 Micro: 0.5057
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 |
|---|---|---|---|---|---|---|
| 1.9501 | 0.32 | 50 | 1.8292 | 0.4321 | 0.1494 | 0.4321 |
| 1.6556 | 0.64 | 100 | 1.8077 | 0.475 | 0.2243 | 0.475 |
| 1.8655 | 0.96 | 150 | 1.8138 | 0.485 | 0.2288 | 0.485 |
| 1.7747 | 1.27 | 200 | 1.8271 | 0.4671 | 0.2230 | 0.4671 |
| 1.6466 | 1.59 | 250 | 1.8139 | 0.4771 | 0.2300 | 0.4771 |
| 1.5496 | 1.91 | 300 | 1.7897 | 0.4793 | 0.2333 | 0.4793 |
| 1.5551 | 2.23 | 350 | 1.7017 | 0.4993 | 0.2513 | 0.4993 |
| 1.463 | 2.55 | 400 | 1.6897 | 0.505 | 0.2606 | 0.505 |
| 1.4005 | 2.87 | 450 | 1.6815 | 0.5057 | 0.2620 | 0.5057 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2