metadata
library_name: transformers
license: apache-2.0
base_model: t5-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: T5_128tokens_advice
results: []
T5_128tokens_advice
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4632
- Accuracy: 0.7711
- F1: 0.7652
- Precision: 0.7624
- Recall: 0.7711
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.63 | 1.0 | 199 | 0.5496 | 0.7170 | 0.5988 | 0.5141 | 0.7170 |
| 0.6192 | 2.0 | 398 | 0.5315 | 0.7245 | 0.6768 | 0.6871 | 0.7245 |
| 0.4783 | 3.0 | 597 | 0.4725 | 0.7635 | 0.7403 | 0.7462 | 0.7635 |
| 0.497 | 4.0 | 796 | 0.4565 | 0.7623 | 0.7611 | 0.7601 | 0.7623 |
| 0.4039 | 5.0 | 995 | 0.4632 | 0.7711 | 0.7652 | 0.7624 | 0.7711 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0