|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: mini-mlm-tweet |
|
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. --> |
|
|
|
# mini-mlm-tweet |
|
|
|
This model is a fine-tuned version of [google/bert_uncased_L-4_H-256_A-4](https://huggingface.co/google/bert_uncased_L-4_H-256_A-4) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.1171 |
|
|
|
## 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: 3e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant |
|
- num_epochs: 200 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 3.9227 | 11.11 | 500 | 3.8377 | |
|
| 3.4825 | 22.22 | 1000 | 3.7411 | |
|
| 3.2903 | 33.33 | 1500 | 3.8864 | |
|
| 3.1026 | 44.44 | 2000 | 3.6987 | |
|
| 2.9438 | 55.56 | 2500 | 3.9807 | |
|
| 2.8075 | 66.67 | 3000 | 3.8835 | |
|
| 2.6951 | 77.78 | 3500 | 4.1171 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.25.1 |
|
- Pytorch 1.13.0+cu116 |
|
- Datasets 2.7.1 |
|
- Tokenizers 0.13.2 |
|
|