metadata
license: mit
base_model: facebook/mbart-large-50
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: mbart-large-50-headline_WithIp
results: []
mbart-large-50-headline_WithIp
This model is a fine-tuned version of facebook/mbart-large-50 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3996
- Rouge1: 0.0
- Rouge2: 0.0
- Rougel: 0.0
- Rougelsum: 0.0
- Gen Len: 16.3524
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
- 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 |
|---|---|---|---|---|---|---|---|---|
| 2.4326 | 1.0 | 202 | 2.2057 | 0.0 | 0.0 | 0.0 | 0.0 | 16.1712 |
| 1.6249 | 2.0 | 404 | 2.1743 | 0.0 | 0.0 | 0.0 | 0.0 | 16.7022 |
| 0.9107 | 3.0 | 606 | 2.2460 | 0.0 | 0.0 | 0.0 | 0.0 | 16.6055 |
| 0.4308 | 4.0 | 808 | 2.3996 | 0.0 | 0.0 | 0.0 | 0.0 | 16.3524 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1