# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("ai-maker-space/Transformers-Workshop-BART-Summarization")
model = AutoModelForSeq2SeqLM.from_pretrained("ai-maker-space/Transformers-Workshop-BART-Summarization")Quick Links
bart-base-finetuned-CNN-DailyNews
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9584
- Rouge1: 0.1977
- Rouge2: 0.1321
- Rougel: 0.1792
- Rougelsum: 0.1884
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: 5.6e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 2.6767 | 1.0 | 63 | 1.8911 | 0.1745 | 0.0915 | 0.1536 | 0.1644 |
| 2.0691 | 2.0 | 126 | 1.5904 | 0.1777 | 0.1003 | 0.1579 | 0.1677 |
| 1.8047 | 3.0 | 189 | 1.3652 | 0.1778 | 0.1029 | 0.1587 | 0.1663 |
| 1.6345 | 4.0 | 252 | 1.2317 | 0.1959 | 0.1226 | 0.1751 | 0.1842 |
| 1.4837 | 5.0 | 315 | 1.1099 | 0.2015 | 0.1265 | 0.1796 | 0.1911 |
| 1.3904 | 6.0 | 378 | 1.0267 | 0.2004 | 0.1278 | 0.1799 | 0.1893 |
| 1.2876 | 7.0 | 441 | 0.9788 | 0.1978 | 0.1307 | 0.1784 | 0.1878 |
| 1.2578 | 8.0 | 504 | 0.9584 | 0.1977 | 0.1321 | 0.1792 | 0.1884 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 4
Model tree for ai-maker-space/Transformers-Workshop-BART-Summarization
Base model
facebook/bart-base
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("summarization", model="ai-maker-space/Transformers-Workshop-BART-Summarization")