mamba-vs-gpt2
Collection
This repository contains the code for comparing the performance of Mamba vs GPT2 on text classification task • 4 items • Updated
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("date3k2/gpt2")
model = AutoModelForSequenceClassification.from_pretrained("date3k2/gpt2")Quick Links
gpt2
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2777
- Accuracy: 0.8846
- F1: 0.8827
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: 0.0005
- train_batch_size: 8
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.2633 | 0.9997 | 781 | 0.2777 | 0.8846 | 0.8827 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 6
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="date3k2/gpt2")