Instructions to use CodeIsAbstract/denoice-finetuned-xsum with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CodeIsAbstract/denoice-finetuned-xsum with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("CodeIsAbstract/denoice-finetuned-xsum") model = AutoModelForSeq2SeqLM.from_pretrained("CodeIsAbstract/denoice-finetuned-xsum", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from CodeIsAbstract/denoice-finetuned-xsum: direct link, hf CLI and curl.
- Browser
- Download file 1.99 kB
-
https://huggingface.co/CodeIsAbstract/denoice-finetuned-xsum/resolve/c7d7c3e2f1800242fc3a3ed458fac00a67bf613f/README.md
- Command line
-
hf download hf://CodeIsAbstract/denoice-finetuned-xsum@c7d7c3e2f1800242fc3a3ed458fac00a67bf613f/README.md
-
curl -L -o README.md https://huggingface.co/CodeIsAbstract/denoice-finetuned-xsum/resolve/c7d7c3e2f1800242fc3a3ed458fac00a67bf613f/README.md
1.99 kB
| license: apache-2.0 | |
| base_model: google/t5-efficient-tiny | |
| tags: | |
| - generated_from_trainer | |
| metrics: | |
| - rouge | |
| model-index: | |
| - name: denoice-finetuned-xsum | |
| results: [] | |
| <!-- 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. --> | |
| # denoice-finetuned-xsum | |
| This model is a fine-tuned version of [google/t5-efficient-tiny](https://huggingface.co/google/t5-efficient-tiny) on an unknown dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.7541 | |
| - Rouge1: 76.26 | |
| - Rouge2: 61.8085 | |
| - Rougel: 76.1635 | |
| - Rougelsum: 76.1928 | |
| - Gen Len: 17.4843 | |
| ## 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: 2e-05 | |
| - train_batch_size: 500 | |
| - eval_batch_size: 500 | |
| - seed: 42 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: linear | |
| - num_epochs: 5 | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | | |
| |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| | |
| | No log | 1.0 | 76 | 0.7604 | 75.9742 | 61.5113 | 75.8301 | 75.8438 | 17.4817 | | |
| | No log | 2.0 | 152 | 0.7574 | 75.9172 | 61.56 | 75.7901 | 75.8489 | 17.4817 | | |
| | No log | 3.0 | 228 | 0.7568 | 76.382 | 61.5593 | 76.1883 | 76.2735 | 17.4791 | | |
| | No log | 4.0 | 304 | 0.7565 | 76.3074 | 61.8211 | 76.1848 | 76.2148 | 17.4843 | | |
| | No log | 5.0 | 380 | 0.7541 | 76.26 | 61.8085 | 76.1635 | 76.1928 | 17.4843 | | |
| ### Framework versions | |
| - Transformers 4.36.2 | |
| - Pytorch 1.13.1 | |
| - Datasets 2.16.1 | |
| - Tokenizers 0.15.0 | |