|
--- |
|
license: apache-2.0 |
|
base_model: distilbert/distilroberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: distilroberta_base_amazon |
|
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. --> |
|
|
|
# distilroberta_base_amazon |
|
|
|
This model is a fine-tuned version of [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7775 |
|
- Accuracy: 0.7826 |
|
- F1 Macro: 0.7137 |
|
- F1 Micro: 0.7826 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- total_train_batch_size: 64 |
|
- total_eval_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 2.2364 | 0.26 | 50 | 1.9915 | 0.5487 | 0.3934 | 0.5487 | |
|
| 1.4061 | 0.53 | 100 | 1.3136 | 0.6449 | 0.5030 | 0.6449 | |
|
| 1.1502 | 0.79 | 150 | 1.1137 | 0.6937 | 0.5697 | 0.6937 | |
|
| 1.0396 | 1.05 | 200 | 0.9888 | 0.7358 | 0.6345 | 0.7358 | |
|
| 0.86 | 1.32 | 250 | 0.9200 | 0.7437 | 0.6560 | 0.7437 | |
|
| 0.9646 | 1.58 | 300 | 0.8704 | 0.7497 | 0.6626 | 0.7497 | |
|
| 0.8749 | 1.84 | 350 | 0.8367 | 0.7708 | 0.6960 | 0.7708 | |
|
| 0.8031 | 2.11 | 400 | 0.8125 | 0.7767 | 0.7069 | 0.7767 | |
|
| 0.7728 | 2.37 | 450 | 0.7912 | 0.7787 | 0.7085 | 0.7787 | |
|
| 0.7164 | 2.63 | 500 | 0.7829 | 0.7793 | 0.7068 | 0.7793 | |
|
| 0.7533 | 2.89 | 550 | 0.7775 | 0.7826 | 0.7137 | 0.7826 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|