metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
datasets:
- learn3r/summ_screen_fd_bp
model-index:
- name: summ_screen_fd_blueprint_epoch_10
results: []
summ_screen_fd_blueprint_epoch_10
This model is a fine-tuned version of facebook/bart-base on the learn3r/summ_screen_fd_bp dataset. It achieves the following results on the evaluation set:
- Loss: 1.9589
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.519 | 0.97 | 14 | 2.3056 |
| 2.6644 | 1.95 | 28 | 2.1349 |
| 2.3418 | 2.99 | 43 | 2.0616 |
| 2.258 | 3.97 | 57 | 2.0360 |
| 2.169 | 4.94 | 71 | 1.9997 |
| 2.1336 | 5.98 | 86 | 1.9862 |
| 2.0952 | 6.96 | 100 | 1.9754 |
| 2.0666 | 8.0 | 115 | 1.9660 |
| 2.0563 | 8.97 | 129 | 1.9610 |
| 2.0426 | 9.74 | 140 | 1.9589 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3