metadata
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: flan-t5-base-quaso-gen2.3
results: []
flan-t5-base-quaso-gen2.3
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6874
- Rouge1: 0.3710
- Rouge2: 0.1425
- Rougel: 0.3003
- Rougelsum: 0.3523
- Gen Len: 43.495
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
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.8222 | 1.0 | 4577 | 1.7155 | 0.3564 | 0.1316 | 0.2876 | 0.3391 | 36.4483 |
| 1.7824 | 2.0 | 9154 | 1.6988 | 0.3668 | 0.1389 | 0.2958 | 0.3478 | 43.8517 |
| 1.7382 | 3.0 | 13731 | 1.6921 | 0.3670 | 0.1389 | 0.2973 | 0.3485 | 40.3283 |
| 1.7036 | 4.0 | 18308 | 1.6887 | 0.3733 | 0.1422 | 0.3009 | 0.3537 | 42.035 |
| 1.6779 | 5.0 | 22885 | 1.6874 | 0.3710 | 0.1425 | 0.3003 | 0.3523 | 43.495 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1