README.md

---
tags:
- generated_from_trainer
model-index:
- name: sentiment-polish-gpt2-large
  results:
  - task:
      type: text-classification
    dataset:
      type: allegro/klej-polemo2-out
      name: klej-polemo2-out
    metrics:
      - type: accuracy
        value: 98.58%
license: mit
datasets:
- clarin-pl/polemo2-official
language:
- pl
metrics:
- accuracy
---

<!-- 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. -->

# sentiment-polish-gpt2-large

This model is a fine-tuned version of [sdadas/polish-gpt2-large](https://huggingface.co/sdadas/polish-gpt2-large) on the [polemo2-official](https://huggingface.co/datasets/clarin-pl/polemo2-official) dataset.
It achieves the following results on the evaluation set:
- epoch: 10.0
- eval_accuracy: 0.9634
- eval_loss: 0.3139
- eval_runtime: 132.9089
- eval_samples_per_second: 197.428
- eval_steps_per_second: 98.714
- step: 65610

## Model description

Trained from [polish-gpt2-large](https://huggingface.co/sdadas/polish-gpt2-large)

## Intended uses & limitations

Sentiment analysis - neutral/negative/positive/ambiguous

## Training and evaluation data

Merged all rows from [polemo2-official](https://huggingface.co/datasets/clarin-pl/polemo2-official) dataset.

Discarded rows with length > 512.

Train/test split: 80%/20%

Datacollator:
```py
data_collator = DataCollatorWithPadding(
  tokenizer=tokenizer,
  padding="longest",
  max_length=MAX_INPUT_LENGTH,
  pad_to_multiple_of=8
)
```

## Training procedure

GPU: 2x RTX 4060Ti 16GB

Training time: 29:16:50

Using accelerate + DeepSpeed

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Evaluation

Evaluated on [allegro/klej-polemo2-out](https://huggingface.co/datasets/allegro/klej-polemo2-out) test dataset.
```py
from datasets import load_dataset
from evaluate import evaluator

data = load_dataset("allegro/klej-polemo2-out", split="test").shuffle(seed=42)
task_evaluator = evaluator("text-classification")

# fix labels
l = {
        "__label__meta_zero": 0,
        "__label__meta_minus_m": 1,
        "__label__meta_plus_m": 2,
        "__label__meta_amb": 3
    }
def fix_labels(examples):
    examples["target"] = l[examples["target"]]
    return examples
data = data.map(fix_labels)

eval_resutls = task_evaluator.compute(
    model_or_pipeline="nie3e/sentiment-polish-gpt2-large",
    data=data,
    label_mapping={"NEUTRAL": 0, "NEGATIVE": 1, "POSITIVE": 2, "AMBIGUOUS": 3},
    input_column="sentence",
    label_column="target"
)

print(eval_resutls)
```

```json
{
    "accuracy": 0.9858299595141701,
    "total_time_in_seconds": 12.71777104900002,
    "samples_per_second": 38.8432845737416,
    "latency_in_seconds": 0.02574447580769235
}
```

### Framework versions

- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1