|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: dpt_2 |
|
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. --> |
|
|
|
# dpt_2 |
|
|
|
- Loss: 4.5960 |
|
|
|
## 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: 4e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- distributed_type: sagemaker_data_parallel |
|
- num_devices: 8 |
|
- total_train_batch_size: 512 |
|
- total_eval_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 250 |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 5.7672 | 1.55 | 500 | 5.7039 | |
|
| 5.1184 | 3.11 | 1000 | 5.0316 | |
|
| 4.9014 | 4.66 | 1500 | 4.7823 | |
|
| 4.738 | 6.21 | 2000 | 4.6616 | |
|
| 4.681 | 7.76 | 2500 | 4.6100 | |
|
| 4.6872 | 9.32 | 3000 | 4.5960 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.13.3 |
|
|
