|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- generator |
|
|
model-index: |
|
|
- name: bert-concat-3 |
|
|
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. --> |
|
|
|
|
|
# bert-concat-3 |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the generator dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 5.8028 |
|
|
|
|
|
## 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: 0.0005 |
|
|
- train_batch_size: 64 |
|
|
- eval_batch_size: 64 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_steps: 1000 |
|
|
- num_epochs: 35 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
|
| 6.5215 | 2.11 | 1000 | 6.1057 | |
|
|
| 5.9958 | 4.22 | 2000 | 6.0199 | |
|
|
| 5.9066 | 6.33 | 3000 | 5.9833 | |
|
|
| 5.8449 | 8.44 | 4000 | 5.9594 | |
|
|
| 5.7913 | 10.55 | 5000 | 5.9176 | |
|
|
| 5.7418 | 12.66 | 6000 | 5.8949 | |
|
|
| 5.6901 | 14.77 | 7000 | 5.8753 | |
|
|
| 5.6485 | 16.88 | 8000 | 5.8592 | |
|
|
| 5.6238 | 18.99 | 9000 | 5.8509 | |
|
|
| 5.6704 | 21.1 | 10000 | 5.8856 | |
|
|
| 5.6375 | 23.21 | 11000 | 5.8703 | |
|
|
| 5.6039 | 25.32 | 12000 | 5.8635 | |
|
|
| 5.5756 | 27.43 | 13000 | 5.8533 | |
|
|
| 5.5437 | 29.54 | 14000 | 5.8408 | |
|
|
| 5.5189 | 31.65 | 15000 | 5.8154 | |
|
|
| 5.4982 | 33.76 | 16000 | 5.8028 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.26.1 |
|
|
- Pytorch 1.11.0+cu113 |
|
|
- Datasets 2.13.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
