|
--- |
|
license: mit |
|
base_model: facebook/mbart-large-50 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: mbart-large-50-bcoqa |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# mbart-large-50-bcoqa |
|
|
|
This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0137 |
|
|
|
## 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: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 1.8791 | 0.1 | 3500 | 1.7917 | |
|
| 1.579 | 0.2 | 7000 | 1.4741 | |
|
| 1.4918 | 0.3 | 10500 | 1.4246 | |
|
| 1.422 | 0.4 | 14000 | 1.3369 | |
|
| 1.4088 | 0.5 | 17500 | 1.3064 | |
|
| 1.3245 | 0.61 | 21000 | 1.2566 | |
|
| 1.3205 | 0.71 | 24500 | 1.2274 | |
|
| 1.3168 | 0.81 | 28000 | 1.2052 | |
|
| 1.2256 | 0.91 | 31500 | 1.1630 | |
|
| 1.0668 | 1.01 | 35000 | 1.1543 | |
|
| 1.0185 | 1.11 | 38500 | 1.1391 | |
|
| 0.9521 | 1.21 | 42000 | 1.1076 | |
|
| 0.9467 | 1.31 | 45500 | 1.1316 | |
|
| 1.0128 | 1.41 | 49000 | 1.0849 | |
|
| 0.9948 | 1.51 | 52500 | 1.0619 | |
|
| 0.9601 | 1.61 | 56000 | 1.0489 | |
|
| 0.9479 | 1.72 | 59500 | 1.0353 | |
|
| 0.9046 | 1.82 | 63000 | 1.0212 | |
|
| 0.8924 | 1.92 | 66500 | 1.0137 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|
