metadata
license: apache-2.0
base_model: google/mt5-base
tags:
- generated_from_trainer
model-index:
- name: task_extractor
results: []
task_extractor
This model is a fine-tuned version of google/mt5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5707
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9043 | 0.01 | 1 | 0.6799 |
| 0.6283 | 0.02 | 2 | 0.6568 |
| 0.7768 | 0.03 | 3 | 0.6458 |
| 0.7835 | 0.05 | 4 | 0.6119 |
| 0.7197 | 0.06 | 5 | 0.5945 |
| 0.7789 | 0.07 | 6 | 0.5793 |
| 0.6086 | 0.08 | 7 | 0.5744 |
| 0.7516 | 0.09 | 8 | 0.5689 |
| 0.7567 | 0.1 | 9 | 0.5700 |
| 0.7175 | 0.11 | 10 | 0.5707 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1
- Datasets 2.15.0
- Tokenizers 0.15.0