|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: small-mlm-glue-mnli |
|
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. --> |
|
|
|
# small-mlm-glue-mnli |
|
|
|
This model is a fine-tuned version of [google/bert_uncased_L-4_H-512_A-8](https://huggingface.co/google/bert_uncased_L-4_H-512_A-8) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.8314 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 3.0194 | 0.4 | 500 | 2.7922 | |
|
| 3.0037 | 0.8 | 1000 | 2.8022 | |
|
| 2.9388 | 1.2 | 1500 | 2.7826 | |
|
| 2.915 | 1.6 | 2000 | 2.7838 | |
|
| 2.8626 | 2.0 | 2500 | 2.7769 | |
|
| 2.7908 | 2.4 | 3000 | 2.7829 | |
|
| 2.789 | 2.8 | 3500 | 2.7933 | |
|
| 2.7784 | 3.2 | 4000 | 2.8314 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0.dev0 |
|
- Pytorch 1.13.0+cu116 |
|
- Datasets 2.8.1.dev0 |
|
- Tokenizers 0.13.2 |
|
|
