|
--- |
|
license: apache-2.0 |
|
base_model: distilbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- sst2 |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: distilbert_base_SST2 |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: sst2 |
|
type: sst2 |
|
config: default |
|
split: validation |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.8990825688073395 |
|
--- |
|
|
|
<!-- 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_SST2 |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the sst2 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4181 |
|
- Accuracy: 0.8991 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 0.4378 | 0.06 | 500 | 0.3452 | 0.8601 | |
|
| 0.343 | 0.12 | 1000 | 0.3483 | 0.8578 | |
|
| 0.3342 | 0.18 | 1500 | 0.3373 | 0.8704 | |
|
| 0.308 | 0.24 | 2000 | 0.4102 | 0.8819 | |
|
| 0.2932 | 0.3 | 2500 | 0.3546 | 0.8830 | |
|
| 0.3116 | 0.36 | 3000 | 0.3609 | 0.8716 | |
|
| 0.2805 | 0.42 | 3500 | 0.3800 | 0.8945 | |
|
| 0.2655 | 0.48 | 4000 | 0.4131 | 0.8842 | |
|
| 0.2504 | 0.53 | 4500 | 0.4299 | 0.8830 | |
|
| 0.2543 | 0.59 | 5000 | 0.5196 | 0.8727 | |
|
| 0.2409 | 0.65 | 5500 | 0.4387 | 0.8807 | |
|
| 0.2414 | 0.71 | 6000 | 0.4121 | 0.8922 | |
|
| 0.2319 | 0.77 | 6500 | 0.3772 | 0.8830 | |
|
| 0.247 | 0.83 | 7000 | 0.4179 | 0.8876 | |
|
| 0.2233 | 0.89 | 7500 | 0.3544 | 0.8945 | |
|
| 0.2202 | 0.95 | 8000 | 0.4160 | 0.8865 | |
|
| 0.2242 | 1.01 | 8500 | 0.5125 | 0.8784 | |
|
| 0.1296 | 1.07 | 9000 | 0.4212 | 0.8842 | |
|
| 0.1429 | 1.13 | 9500 | 0.4675 | 0.8968 | |
|
| 0.1466 | 1.19 | 10000 | 0.5034 | 0.8922 | |
|
| 0.1626 | 1.25 | 10500 | 0.4431 | 0.8945 | |
|
| 0.1459 | 1.31 | 11000 | 0.5001 | 0.8922 | |
|
| 0.1489 | 1.37 | 11500 | 0.4739 | 0.8968 | |
|
| 0.1591 | 1.43 | 12000 | 0.3852 | 0.8945 | |
|
| 0.1211 | 1.48 | 12500 | 0.4648 | 0.8945 | |
|
| 0.1275 | 1.54 | 13000 | 0.5281 | 0.8956 | |
|
| 0.1302 | 1.6 | 13500 | 0.4411 | 0.8933 | |
|
| 0.1313 | 1.66 | 14000 | 0.4914 | 0.8979 | |
|
| 0.134 | 1.72 | 14500 | 0.3923 | 0.8979 | |
|
| 0.1355 | 1.78 | 15000 | 0.4164 | 0.8956 | |
|
| 0.1263 | 1.84 | 15500 | 0.4293 | 0.8945 | |
|
| 0.1326 | 1.9 | 16000 | 0.4185 | 0.8933 | |
|
| 0.1315 | 1.96 | 16500 | 0.4181 | 0.8991 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
