# Accuracy changes dramatically

**URL:** <https://discuss.huggingface.co/t/accuracy-changes-dramatically/2180>\
**Category:** 🤗Transformers\
**Created:** [November 23, 2020, 9:26pm UTC](https://discuss.huggingface.co/t/accuracy-changes-dramatically/2180 "2020-11-23T21:26:20Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![burakisikli](https://avatars.discourse-cdn.com/v4/letter/b/0ea827/32.png) [@burakisikli](https://discuss.huggingface.co/u/burakisikli)\
**Post date:** [November 23, 2020, 9:26pm UTC](https://discuss.huggingface.co/t/accuracy-changes-dramatically/2180/1 "2020-11-23T21:26:20Z")

</div>

Hi,  
I tried to fine tune a bert model for text classification task using same parameters(learning rate, warmup step, batch size, number of epoch) in pytorch and tensorflow. If I use tensorflow, the validation accuracy changes dramatically. In pytorch accuracy is around %96, in tensorflow %76. One thing I noticed is the gpu memory usage difference (pytorch: ~12gb, tf ~8gb). Shouldn’t we expect it to be the similar accuracy?

- `transformers` version: 3.5.1
- Platform: Linux-4.19.112±x86\_64-with-Ubuntu-18.04-bionic
- Python version: 3.6.9
- PyTorch version (GPU?): 1.7.0+cu101 (True)
- Tensorflow version (GPU?): 2.3.0 (True)
- Using GPU in script?: Yes
- Using distributed or parallel set-up in script?: No

```python
from transformers import TFBertForSequenceClassification

model = TFBertForSequenceClassification.from_pretrained('bert-base-uncased', num_labels = num_labels)

optimizer = tf.keras.optimizers.Adam(learning_rate=lr_schedule) 
model.compile(optimizer=optimizer, loss=model.compute_loss, metrics=['accuracy']) 
history = model.fit(train_dataset.shuffle(1000).batch(32), epochs=epochs, batch_size=32)

```