--- language: en license: apache-2.0 library_name: setfit tags: - setfit - sentence-transformers - text-classification - generated_from_setfit_trainer base_model: sentence-transformers/paraphrase-mpnet-base-v2 metrics: - accuracy widget: - text: great movie, so close to perfection let me get this straight. this is a brilliant brilliant refreshingly brutal movie.i'm glad they didn't soften the general malevolence, but i feel they missed out on what i consider the most pivotal point of the book.paul drinks the water of life. with it his genetic memory is unlocked, he can foresee the actions of people in the future. the golden path is laid out. and so pursues the mind altering awakening, leaving him a husk; trapped in one path of fate - trapped between his own ego and the true path needed for humanity. in the movie, paul drink bad, paul wake up. paul president with superpower!i understand that it's a very hard thing to portray for an audience but i think i was just really hoping for villeneuve to emphasise the importance of that part and it felt quite rushed in that regard.but i doubt they'll make a movie about a big virgin worm so prescience might not matter too much. - text: absolutely breathtaking the movie is the complete cinematic experience. i loved every single line every moment every little thing that makes this movie.the only thing that is bothering me is the thirst so bad for the next part.i felt like i was in the movie riding a sand worm, i was a fremen. i felt the pain the wonder the joy the anger. this felt like reading the book and you just can't stop. the excellence of this movie is not only the cast or the story it is the very making of it. i loved every dialogue that was uttered. its just a masterpiece.though there is a stagnant pace in between it doesn't seem to matter. because most of the second part of the movie is such a cliff hanger. 6 out of 10 found this helpful. was this review helpful? sign in to vote. permalink - text: 'let''s be serious, guys.. appreciate that everyone is entitled to their opinion, so here''s mine: anyone giving this less than a solid 9 needs to re-evaluate themselves as a person. because you either have no imagination or are just generally a negative human. this film has everything and is a modern day great. easily the best cinematic experience i''ve ever had, comparable to films like the dark knight trilogy and the original star wars films.for a nearly three hour long film, basically nobody got up to go for a toilet break and the entire time i felt totally present, gripped by it.don''t listen to anyone on here leaving poor reviews. go and watch the film and see the magic for yourself. 8 out of 13 found this helpful. was this review helpful? sign in to vote. permalink' - text: phenomenal this movie was particularly gorgeous and exciting giving all the key moments and suspense that anybody of the sort would love, this movie brings the suspense and excitement to keep you engaged and always cautious of what's next, a truly wonderful story that is acted so perfectly and well, this adaptation has brung the story alive and in the spotlight proving there is not only a lot to it but also that it has a lot more to come and personally i want to see it all. i left the theater thoroughly wanting even more for the story and continuing on that i can't wait for what is to come of this movie. it is truly a must watch masterpiece. 4 out of 6 found this helpful. was this review helpful? sign in to vote. permalink - text: film of the decade i've always wished to watch films like lord of the rings and star wars in theaters, but i was simply born too late. dune 2 made me feel like i was watching those movies in theaters, the epic sweaping shots, the massive amount of extras, the attention to detail, the costumes, every single fight looked like they spent days choreographing it. the soundtrack was the best i heard since interstellar, and it matched the mood at every point. honestly i thought film was going down, disney is losing it and they own almost everything. but dune 2 restored my hope in movies and actually made me want to pursue a career in film. overall, this movie was epic and easily deserves a 10 star rating. 1 out of 1 found this helpful. was this review helpful? sign in to vote. permalink pipeline_tag: text-classification inference: true --- # SetFit with sentence-transformers/paraphrase-mpnet-base-v2 on data/raw/15239678.jsonl This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A [SetFitHead](huggingface.co/docs/setfit/reference/main#setfit.SetFitHead) instance is used for classification. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. 2. Training a classification head with features from the fine-tuned Sentence Transformer. ## Model Details ### Model Description - **Model Type:** SetFit - **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) - **Classification head:** a [SetFitHead](huggingface.co/docs/setfit/reference/main#setfit.SetFitHead) instance - **Maximum Sequence Length:** 512 tokens - **Number of Classes:** 2 classes - **Language:** en - **License:** apache-2.0 ### Model Sources - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit) - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055) - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit) ### Model Labels | Label | Examples | |:---------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | positive | | | negative | | ## Uses ### Direct Use for Inference First install the SetFit library: ```bash pip install setfit ``` Then you can load this model and run inference. ```python from setfit import SetFitModel # Download from the 🤗 Hub model = SetFitModel.from_pretrained("carlesoctav/SentimentClassifierDune") # Run inference preds = model("phenomenal this movie was particularly gorgeous and exciting giving all the key moments and suspense that anybody of the sort would love, this movie brings the suspense and excitement to keep you engaged and always cautious of what's next, a truly wonderful story that is acted so perfectly and well, this adaptation has brung the story alive and in the spotlight proving there is not only a lot to it but also that it has a lot more to come and personally i want to see it all. i left the theater thoroughly wanting even more for the story and continuing on that i can't wait for what is to come of this movie. it is truly a must watch masterpiece. 4 out of 6 found this helpful. was this review helpful? sign in to vote. permalink") ``` ## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:-------------|:----|:---------|:----| | Word count | 107 | 215.2273 | 972 | | Label | Training Sample Count | |:---------|:----------------------| | negative | 99 | | positive | 99 | ### Training Hyperparameters - batch_size: (16, 16) - num_epochs: (1, 1) - max_steps: -1 - sampling_strategy: oversampling - body_learning_rate: (2e-05, 1e-05) - head_learning_rate: 0.01 - loss: CosineSimilarityLoss - distance_metric: cosine_distance - margin: 0.25 - end_to_end: False - use_amp: False - warmup_proportion: 0.1 - seed: 42 - eval_max_steps: -1 - load_best_model_at_end: True ### Training Results | Epoch | Step | Training Loss | Validation Loss | |:-------:|:--------:|:-------------:|:---------------:| | 0.0008 | 1 | 0.2606 | - | | 0.0404 | 50 | 0.1578 | - | | 0.0808 | 100 | 0.0066 | - | | 0.1212 | 150 | 0.0004 | - | | 0.1616 | 200 | 0.0003 | - | | 0.2019 | 250 | 0.0005 | - | | 0.2423 | 300 | 0.0002 | - | | 0.2827 | 350 | 0.0003 | - | | 0.3231 | 400 | 0.0001 | - | | 0.3635 | 450 | 0.0001 | - | | 0.4039 | 500 | 0.0001 | - | | 0.4443 | 550 | 0.0001 | - | | 0.4847 | 600 | 0.0 | - | | 0.5250 | 650 | 0.0 | - | | 0.5654 | 700 | 0.0 | - | | 0.6058 | 750 | 0.0 | - | | 0.6462 | 800 | 0.0 | - | | 0.6866 | 850 | 0.0 | - | | 0.7270 | 900 | 0.0 | - | | 0.7674 | 950 | 0.0 | - | | 0.8078 | 1000 | 0.0 | - | | 0.8481 | 1050 | 0.0 | - | | 0.8885 | 1100 | 0.0 | - | | 0.9289 | 1150 | 0.0 | - | | 0.9693 | 1200 | 0.0 | - | | **1.0** | **1238** | **-** | **0.1555** | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.10.11 - SetFit: 1.0.3 - Sentence Transformers: 2.5.1 - Transformers: 4.38.2 - PyTorch: 2.0.1 - Datasets: 2.18.0 - Tokenizers: 0.15.2 ## Citation ### BibTeX ```bibtex @article{https://doi.org/10.48550/arxiv.2209.11055, doi = {10.48550/ARXIV.2209.11055}, url = {https://arxiv.org/abs/2209.11055}, author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Efficient Few-Shot Learning Without Prompts}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ```