I am downloading the model https://huggingface.co/microsoft/Multilingual-MiniLM-L12-H384/tree/main microsoft/Multilingual-MiniLM-L12-H384 and then using it. I am loading model using BertForSequenceClassification
Transformer Version: '4.11.3'
I have written the below code:
def compute_metrics(eval_pred):
logits, labels = eval_pred
predictions = np.argmax(logits, axis=-1)
acc = np.sum(predictions == labels) / predictions.shape[0]
return {"accuracy" : acc}
model = tr.BertForSequenceClassification.from_pretrained("/home/pc/minilm_model",num_labels=2)
model.to(device)
print("hello")
training_args = tr.TrainingArguments(
output_dir='/home/pc/proj/results2', # output directory
num_train_epochs=10, # total number of training epochs
per_device_train_batch_size=16, # batch size per device during training
per_device_eval_batch_size=32, # batch size for evaluation
learning_rate=2e-5,
warmup_steps=1000, # number of warmup steps for learning rate scheduler
weight_decay=0.01, # strength of weight decay
logging_dir='./logs', # directory for storing logs
logging_steps=1000,
evaluation_strategy="epoch",
save_strategy="no"
)
trainer = tr.Trainer(
model=model, # the instantiated