|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: google/mt5-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: mt5-base-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. --> |
|
|
|
|
|
# mt5-base-bcoqa |
|
|
|
|
|
This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.0503 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
|
| 1.7933 | 0.1 | 3500 | 1.4891 | |
|
|
| 1.594 | 0.2 | 7000 | 1.3193 | |
|
|
| 1.4983 | 0.3 | 10500 | 1.2550 | |
|
|
| 1.4311 | 0.4 | 14000 | 1.2163 | |
|
|
| 1.4343 | 0.5 | 17500 | 1.1723 | |
|
|
| 1.3635 | 0.61 | 21000 | 1.1518 | |
|
|
| 1.3782 | 0.71 | 24500 | 1.1331 | |
|
|
| 1.3782 | 0.81 | 28000 | 1.1126 | |
|
|
| 1.3091 | 0.91 | 31500 | 1.1197 | |
|
|
| 1.2328 | 1.01 | 35000 | 1.0967 | |
|
|
| 1.2605 | 1.11 | 38500 | 1.0892 | |
|
|
| 1.183 | 1.21 | 42000 | 1.0872 | |
|
|
| 1.1713 | 1.31 | 45500 | 1.0963 | |
|
|
| 1.2369 | 1.41 | 49000 | 1.0696 | |
|
|
| 1.2542 | 1.51 | 52500 | 1.0672 | |
|
|
| 1.2226 | 1.61 | 56000 | 1.0608 | |
|
|
| 1.2013 | 1.72 | 59500 | 1.0538 | |
|
|
| 1.1776 | 1.82 | 63000 | 1.0516 | |
|
|
| 1.191 | 1.92 | 66500 | 1.0503 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.39.0.dev0 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.16.1 |
|
|
- Tokenizers 0.15.1 |
|
|
|
