metadata
license: apache-2.0
base_model: philschmid/flan-t5-base-samsum
tags:
- generated_from_trainer
model-index:
- name: T5-model
results: []
T5-model
This model is a fine-tuned version of philschmid/flan-t5-base-samsum on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7013
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9849 | 0.8 | 10 | 0.8062 |
| 0.9748 | 1.61 | 20 | 0.8026 |
| 0.9772 | 2.41 | 30 | 0.7968 |
| 0.979 | 3.22 | 40 | 0.7889 |
| 0.9729 | 4.02 | 50 | 0.7793 |
| 0.9479 | 4.82 | 60 | 0.7687 |
| 0.9111 | 5.63 | 70 | 0.7577 |
| 0.8956 | 6.43 | 80 | 0.7460 |
| 0.8768 | 7.24 | 90 | 0.7338 |
| 0.8566 | 8.04 | 100 | 0.7224 |
| 0.8342 | 8.84 | 110 | 0.7120 |
| 0.8273 | 9.65 | 120 | 0.7013 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3