metadata
license: mit
tags:
- summarization
- generated_from_trainer
metrics:
- rouge
model-index:
- name: mbart-large-50-finetuned-stocks-event-all
results: []
mbart-large-50-finetuned-stocks-event-all
This model is a fine-tuned version of facebook/mbart-large-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5518
- Rouge1: 0.5383
- Rouge2: 0.4868
- Rougel: 0.5387
- Rougelsum: 0.5362
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: 5.6e-05
- 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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 2.2097 | 1.0 | 97 | 0.5821 | 0.5174 | 0.4646 | 0.5137 | 0.5111 |
| 0.5315 | 2.0 | 194 | 0.4826 | 0.5169 | 0.4709 | 0.5186 | 0.5168 |
| 0.3602 | 3.0 | 291 | 0.4677 | 0.5319 | 0.4811 | 0.5344 | 0.5304 |
| 0.2639 | 4.0 | 388 | 0.4724 | 0.5319 | 0.4750 | 0.5335 | 0.5318 |
| 0.1715 | 5.0 | 485 | 0.4504 | 0.5331 | 0.4790 | 0.5337 | 0.5323 |
| 0.1136 | 6.0 | 582 | 0.4894 | 0.5321 | 0.4886 | 0.5324 | 0.5295 |
| 0.0618 | 7.0 | 679 | 0.5445 | 0.5456 | 0.4959 | 0.5473 | 0.5438 |
| 0.0347 | 8.0 | 776 | 0.5518 | 0.5383 | 0.4868 | 0.5387 | 0.5362 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2