metadata
license: apache-2.0
base_model: google/long-t5-local-base
tags:
- generated_from_trainer
model-index:
- name: long-t5-local-base-ARv1
results: []
long-t5-local-base-ARv1
This model is a fine-tuned version of google/long-t5-local-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.3963
- Exact Match: 10.0
- Gen Len: 3.9
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Exact Match | Gen Len |
---|---|---|---|---|---|
No log | 1.0 | 7 | 19.4103 | 0.0 | 19.0 |
24.1098 | 2.0 | 14 | 16.1054 | 0.0 | 19.0 |
18.4141 | 3.0 | 21 | 13.2155 | 0.0 | 19.0 |
18.4141 | 4.0 | 28 | 10.5562 | 0.0 | 19.0 |
14.3671 | 5.0 | 35 | 7.3648 | 0.0 | 18.68 |
10.2783 | 6.0 | 42 | 5.4277 | 4.0 | 16.44 |
10.2783 | 7.0 | 49 | 4.8687 | 18.0 | 7.88 |
7.6519 | 8.0 | 56 | 4.4226 | 26.0 | 3.06 |
5.7049 | 9.0 | 63 | 4.1797 | 28.0 | 3.06 |
5.0241 | 10.0 | 70 | 4.0197 | 24.0 | 4.74 |
5.0241 | 11.0 | 77 | 3.8360 | 8.0 | 7.58 |
4.1884 | 12.0 | 84 | 3.7251 | 6.0 | 8.74 |
3.3779 | 13.0 | 91 | 3.6448 | 6.0 | 6.94 |
3.3779 | 14.0 | 98 | 3.5611 | 10.0 | 4.66 |
3.149 | 15.0 | 105 | 3.4972 | 6.0 | 4.54 |
3.1238 | 16.0 | 112 | 3.4741 | 8.0 | 3.8 |
3.1238 | 17.0 | 119 | 3.4431 | 8.0 | 3.86 |
3.2917 | 18.0 | 126 | 3.4290 | 10.0 | 3.88 |
3.001 | 19.0 | 133 | 3.4080 | 10.0 | 3.9 |
3.8795 | 20.0 | 140 | 3.3963 | 10.0 | 3.9 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.2.1
- Datasets 2.19.1
- Tokenizers 0.19.1