metadata
license: apache-2.0
base_model: google/flan-t5-base
tags:
- generated_from_trainer
model-index:
- name: flan-t5-base-ARv1
results: []
flan-t5-base-ARv1
This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8087
- Exact Match: 17.1569
- Gen Len: 4.0
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: 0.01
- 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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Exact Match | Gen Len |
|---|---|---|---|---|---|
| 0.8486 | 1.0 | 4246 | 0.8367 | 30.085 | 3.0 |
| 0.8316 | 2.0 | 8492 | 0.8192 | 17.1569 | 4.0 |
| 0.8266 | 3.0 | 12738 | 0.8136 | 17.1569 | 4.0 |
| 0.818 | 4.0 | 16984 | 0.8087 | 17.1569 | 4.0 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.2.1
- Datasets 2.19.1
- Tokenizers 0.19.1