metadata
license: apache-2.0
base_model: google-t5/t5-large
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: fine_tuned_cb_t5
results: []
fine_tuned_cb_t5
This model is a fine-tuned version of google-t5/t5-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4011
- Accuracy: 0.3636
- F1: 0.3202
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 400
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.7918 | 3.5714 | 50 | 1.4809 | 0.3182 | 0.1536 |
| 0.6056 | 7.1429 | 100 | 1.5671 | 0.3182 | 0.1536 |
| 0.496 | 10.7143 | 150 | 1.6020 | 0.3182 | 0.1536 |
| 0.3563 | 14.2857 | 200 | 1.8622 | 0.2727 | 0.1951 |
| 0.254 | 17.8571 | 250 | 2.1775 | 0.3182 | 0.2636 |
| 0.1867 | 21.4286 | 300 | 2.2009 | 0.3636 | 0.3202 |
| 0.1237 | 25.0 | 350 | 2.3443 | 0.3636 | 0.3202 |
| 0.1154 | 28.5714 | 400 | 2.4011 | 0.3636 | 0.3202 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1