|
--- |
|
license: apache-2.0 |
|
base_model: distilbert/distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: distilbert_base_uncased_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. --> |
|
|
|
# distilbert_base_uncased_amazon |
|
|
|
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9130 |
|
- Accuracy: 0.7576 |
|
- F1 Macro: 0.6904 |
|
- F1 Micro: 0.7576 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 2.6322 | 0.26 | 50 | 2.5191 | 0.4750 | 0.3209 | 0.4750 | |
|
| 1.9044 | 0.53 | 100 | 1.8323 | 0.6014 | 0.4626 | 0.6014 | |
|
| 1.5127 | 0.79 | 150 | 1.4810 | 0.6574 | 0.5154 | 0.6574 | |
|
| 1.2857 | 1.05 | 200 | 1.2679 | 0.6983 | 0.5795 | 0.6983 | |
|
| 1.0669 | 1.32 | 250 | 1.1415 | 0.7306 | 0.6376 | 0.7306 | |
|
| 1.0931 | 1.58 | 300 | 1.0669 | 0.7312 | 0.6333 | 0.7312 | |
|
| 0.9879 | 1.84 | 350 | 1.0102 | 0.7437 | 0.6542 | 0.7437 | |
|
| 0.8936 | 2.11 | 400 | 0.9650 | 0.7444 | 0.6640 | 0.7444 | |
|
| 0.8345 | 2.37 | 450 | 0.9389 | 0.7582 | 0.6900 | 0.7582 | |
|
| 0.7851 | 2.63 | 500 | 0.9208 | 0.7628 | 0.6924 | 0.7628 | |
|
| 0.8439 | 2.89 | 550 | 0.9130 | 0.7576 | 0.6904 | 0.7576 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|