metadata
license: apache-2.0
base_model: t5-base
tags:
- generated_from_trainer
model-index:
- name: results
results: []
results
This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9081
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.9289 | 0.32 | 10 | 3.2381 |
| 3.5665 | 0.64 | 20 | 2.7374 |
| 3.6622 | 0.96 | 30 | 2.4842 |
| 2.6751 | 1.28 | 40 | 2.2607 |
| 2.649 | 1.6 | 50 | 2.1196 |
| 2.3201 | 1.92 | 60 | 2.0067 |
| 2.2374 | 2.24 | 70 | 1.9490 |
| 2.1954 | 2.56 | 80 | 1.9210 |
| 2.3612 | 2.88 | 90 | 1.9081 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1