|
--- |
|
license: apache-2.0 |
|
base_model: facebook/bart-large |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: bart-finetuned-eli5_base_best |
|
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. --> |
|
|
|
# bart-finetuned-eli5_base_best |
|
|
|
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co./facebook/bart-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1849 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 2 |
|
- 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 1.3965 | 0.1 | 500 | 1.2495 | |
|
| 1.3676 | 0.2 | 1000 | 1.2362 | |
|
| 1.3024 | 0.3 | 1500 | 1.2294 | |
|
| 1.2331 | 0.4 | 2000 | 1.2301 | |
|
| 1.2476 | 0.5 | 2500 | 1.2266 | |
|
| 1.2049 | 0.6 | 3000 | 1.2202 | |
|
| 1.1811 | 0.7 | 3500 | 1.2857 | |
|
| 1.2227 | 0.8 | 4000 | 1.2702 | |
|
| 1.2629 | 0.9 | 4500 | 1.2206 | |
|
| 1.1233 | 1.0 | 5000 | 1.2187 | |
|
| 1.1995 | 1.1 | 5500 | 1.1957 | |
|
| 1.0835 | 1.2 | 6000 | 1.2026 | |
|
| 1.1033 | 1.3 | 6500 | 1.2250 | |
|
| 1.127 | 1.4 | 7000 | 1.2091 | |
|
| 1.0964 | 1.5 | 7500 | 1.1929 | |
|
| 1.1321 | 1.6 | 8000 | 1.1827 | |
|
| 1.051 | 1.7 | 8500 | 1.1791 | |
|
| 1.054 | 1.8 | 9000 | 1.1926 | |
|
| 1.0034 | 1.9 | 9500 | 1.1769 | |
|
| 1.0645 | 2.0 | 10000 | 1.1849 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0.dev0 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|