File size: 1,642 Bytes
eaa2b79
 
 
 
6a5a9c8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
from datasets import load_dataset

dataset = load_dataset("mteb/tweet_sentiment_extraction")
df = pd.DataFrame(dataset['train'])


from transformers import GPT2Tokenizer

# Loading the dataset to train our model
dataset = load_dataset("mteb/tweet_sentiment_extraction")

tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
tokenizer.pad_token = tokenizer.eos_token
def tokenize_function(examples):
   return tokenizer(examples["text"], padding="max_length", truncation=True)

tokenized_datasets = dataset.map(tokenize_function, batched=True)


small_train_dataset = tokenized_datasets["train"].shuffle(seed=42).select(range(1000))
small_eval_dataset = tokenized_datasets["test"].shuffle(seed=42).select(range(1000))


from transformers import GPT2ForSequenceClassification

model = GPT2ForSequenceClassification.from_pretrained("gpt2", num_labels=3)



import evaluate

metric = evaluate.load("accuracy")

def compute_metrics(eval_pred):
   logits, labels = eval_pred
   predictions = np.argmax(logits, axis=-1)
   return metric.compute(predictions=predictions, references=labels)




from transformers import TrainingArguments, Trainer

training_args = TrainingArguments(
   output_dir="test_trainer",
   #evaluation_strategy="epoch",
   per_device_train_batch_size=1,  # Reduce batch size here
   per_device_eval_batch_size=1,    # Optionally, reduce for evaluation as well
   gradient_accumulation_steps=4
   )


trainer = Trainer(
   model=model,
   args=training_args,
   train_dataset=small_train_dataset,
   eval_dataset=small_eval_dataset,
   compute_metrics=compute_metrics,

)

trainer.train()




import evaluate

trainer.evaluate()