metadata
base_model: sentence-transformers/paraphrase-mpnet-base-v2
datasets:
- stanfordnlp/imdb
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: >-
What does the " Executive producer " do in a movie . If I remember
correctly it's the person who raised the financial backing to make the
movie . You might notice in a great number of movies starring Sean Connery
that he is also the executive producer which meant Connery himself raised
the money since he is a major player . Unfortunately it should also be
pointed out that a great number of movies " starring Sean Connery were
solely made because he managed to raise the money since he's a major
Hollywood player , it's usually an indication that when the credits read
that the executive producer and the star of the movie are one and the same
the movie itself is nothing more than a star vehicle with the
story/screenplay not being up to scratch <br /><br />PROTOCOL follows the
saga of one Sunny Davis a kooky bimboesque cocktail waitress who saves a
visiting dignitary and as a reward gets made a top diplomat . Likely ? As
things progress Ms Davis ( Who has problems being able to string two
sentences together ) finds herself in more outlandish and less likely
situations . When I say that PROTOCOL stars Goldie Hawn who is also the
film's executive producer do you understand what I'm saying about the
story/screenplay not being up to scratch ? Exactly
- text: >-
I've seen all four of the movies in this series. Each one strays further
and further from the books. This is the worst one yet. My problem is that
it does not follow the book it is titled after in any way! The directors
and producers should have named it any thing other than "Love's Abiding
Joy." The only thing about this movie that remotely resembles the book are
the names of some of the characters (Willie, Missie, Henry, Clark, Scottie
and Cookie). The names/ages/genders of the children are wrong. The entire
story line is no where in the book.<br /><br />I find it a great
disservice to Janette Oke, her books and her fans to produce a movie under
her title that is not correct in any way. The music is too loud. The
actors are not convincing - they lack emotions.<br /><br />If you want a
good family movie, this might do. It is clean. Don't watch it, though, if
you are hoping for a condensed version of the book. I hope that this will
be the last movie from this series, but I doubt it. If there are more
movies made, I wish Michael Landon, Jr and others would stick closer to
the original plot and story lines. The books are excellent and, if closely
followed, would make excellent movies!
- text: >-
THE ZOMBIE CHRONICLES <br /><br />Aspect ratio: 1.33:1 (Nu-View 3-D)<br
/><br />Sound format: Mono<br /><br />Whilst searching for a (literal)
ghost town in the middle of nowhere, a young reporter (Emmy Smith) picks
up a grizzled hitchhiker (Joseph Haggerty) who tells her two stories
involving flesh-eating zombies reputed to haunt the area.<br /><br />An
ABSOLUTE waste of time, hobbled from the outset by Haggerty's painfully
amateurish performance in a key role. Worse still, the two stories which
make up the bulk of the running time are utterly routine, made worse by
indifferent performances and lackluster direction by Brad Sykes,
previously responsible for the likes of CAMP BLOOD (1999). This isn't a
'fun' movie in the sense that Ed Wood's movies are 'fun' (he, at least,
believed in what he was doing and was sincere in his efforts, despite a
lack of talent); Sykes' home-made movies are, in fact, aggravating, boring
and almost completely devoid of any redeeming virtue, and most viewers
will feel justifiably angry and cheated by such unimaginative,
badly-conceived junk. The 3-D format is utterly wasted here.
- text: >-
If only to avoid making this type of film in the future. This film is
interesting as an experiment but tells no cogent story.<br /><br />One
might feel virtuous for sitting thru it because it touches on so many
IMPORTANT issues but it does so without any discernable motive. The viewer
comes away with no new perspectives (unless one comes up with one while
one's mind wanders, as it will invariably do during this pointless
film).<br /><br />One might better spend one's time staring out a window
at a tree growing.<br /><br />
- text: >-
Sexo Cannibal, or Devil Hunter as it's more commonly known amongst English
speaking audiences, starts with actress & model Laura Crawford (Ursula
Buchfellner as Ursula Fellner) checking out locations for her new film
along with her assistant Jane (Gisela Hahn). After a long days work Laura
is relaxing in the bath of her room when two very dubious character's
named Chris (Werner Pochath) & Thomas (Antonio Mayans) burst in & kidnap
her having been helped by the treacherous Jane. Laura's agent gets on the
blower to rent-a-hero Peter Weston (Al Cliver) who is informed of the
situation, the kidnappers have Laura on an isolated island & are demanding
a 6 million ransom. Peter is told that he will be paid 200,000 to get her
back safely & a further 10% of the 6 million if he brings that back as
well, faster than a rat up a drain pipe Peter & his Vietnam Vet buddy
helicopter pilot Jack are on the island & deciding on how to save Laura.
So, the kidnappers have Laura & Peter has the 6 million but neither want
to hand them over that much. Just to complicate things further this
particular isolated island is home to a primitive tribe (hell, in all the
generations they've lived there they've only managed to build one straw
hut, now that's primitive) who worship some cannibal monster dude (Burt
Altman) with bulging eyes as a God with human sacrifices & this cannibal
has a liking for young, white female flesh & intestines...<br /><br />This
Spanish, French & German co-production was co-written & directed by the
prolific Jesus Franco who also gets the credit for the music as well. Sexo
Cannibal has gained a certain amount of notoriety here in the UK as it was
placed on the 'Video Nasties' list in the early 80's under it's alternate
Devil Hunter title & therefore officially classed as obscene & banned,
having said that I have no idea why as it is one bad film & even Franco,
who isn't afraid to be associated with a turkey, decides he wants to hide
under the pseudonym of Clifford Brown. I'd imagine even the most die-hard
Franco fan would have a hard time defending this thing. The script by
Franco, erm sorry I mean Clifford Brown & Julian Esteban as Julius Valery
who was obviously another one less than impressed with the finished
product & wanted his named removed, is awful. It's as simple & straight
forward as that. For a start the film is so boring it's untrue, the kidnap
plot is one of the dullest I've ever seen without the slightest bit of
tension or excitement involved & the horror side of things don't improve
as we get a big black guy with stupid looking over-sized bloodshot eyes
plus two tame cannibal scenes. As a horror film Sexo Cannibal fails & as
an action adventure it has no more success, this is one to avoid.<br /><br
/>Director Franco shows his usual incompetence throughout, a decapitated
head is achieved by an actor lying on the ground with large leaves placed
around the bottom of his neck to try & give the impression it's not
attached to anything! The cannibal scenes are poor, the action is lame &
it has endless scenes of people randomly walking around the jungle getting
from 'A' to 'B' & not really doing anything when they get there either. It
becomes incredibly dull & tedious to watch after about 10 minutes & don't
forget this thing goes on for 94 minutes in it's uncut state. I also must
mention the hilarious scene when Al Cliver is supposed to be climbing a
cliff, this is achieved by Franco turning his camera on it's side & having
Cliver crawl along the floor! Just look at the way his coat hangs & the
way he never grabs onto to anything as he just pulls himself along! The
gore isn't that great & as far as Euro cannibal films go this is very
tame, there are some gross close ups of the cannibals mouth as it chews
bits of meat, a man is impaled on spikes, there's some blood & a handful
of intestines. There's a fair bit of nudity in Sexo Cannibal & an
unpleasant rape scene.<br /><br />Sexo Cannibal must have had a low budget
& I mean low. This is a shoddy poorly made film with awful special effects
& rock bottom production values. The only decent thing about it is the
jungle setting which at least looks authentic. The music sucks & sound
effects become annoying as there is lots of heavy breathing whenever the
cannibal is on screen. The acting sucks, the whole thing was obviously
dubbed anyway but no one in this thing can act.<br /><br />Sexo Cannibal
is a terrible film that commits the fatal mistake of being as boring as
hell. The only good things I can say is that it has a certain sleazy
atmosphere to it & those close ups of the cannibal chewing meat are pretty
gross. Anyone looking for a decent cinematic experience should give Sexo
Cannibal as wide a berth as possible, one to avoid.
inference: true
model-index:
- name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: stanfordnlp/imdb
type: stanfordnlp/imdb
split: test
metrics:
- type: accuracy
value: 0.8242
name: Accuracy
SetFit with sentence-transformers/paraphrase-mpnet-base-v2
This is a SetFit model trained on the stanfordnlp/imdb dataset that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-mpnet-base-v2 as the Sentence Transformer embedding model. A LogisticRegression instance is used for classification.
The model has been trained using an efficient few-shot learning technique that involves:
- Fine-tuning a Sentence Transformer with contrastive learning.
- 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
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 512 tokens
- Number of Classes: 2 classes
- Training Dataset: stanfordnlp/imdb
Model Sources
- Repository: SetFit on GitHub
- Paper: Efficient Few-Shot Learning Without Prompts
- Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts
Model Labels
| Label | Examples |
|---|---|
| 0 |
|
| 1 |
|
Evaluation
Metrics
| Label | Accuracy |
|---|---|
| all | 0.8242 |
Uses
Direct Use for Inference
First install the SetFit library:
pip install setfit
Then you can load this model and run inference.
from setfit import SetFitModel
# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("setfit_model_id")
# Run inference
preds = model("If only to avoid making this type of film in the future. This film is interesting as an experiment but tells no cogent story.<br /><br />One might feel virtuous for sitting thru it because it touches on so many IMPORTANT issues but it does so without any discernable motive. The viewer comes away with no new perspectives (unless one comes up with one while one's mind wanders, as it will invariably do during this pointless film).<br /><br />One might better spend one's time staring out a window at a tree growing.<br /><br />")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 48 | 244.4571 | 888 |
| Label | Training Sample Count |
|---|---|
| 1 | 7 |
| 0 | 63 |
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 |
|---|---|---|---|
| 0.0039 | 1 | 0.2493 | - |
| 0.1953 | 50 | 0.0016 | - |
| 0.3906 | 100 | 0.0003 | - |
| 0.5859 | 150 | 0.003 | - |
| 0.7812 | 200 | 0.0014 | - |
| 0.9766 | 250 | 0.0002 | - |
| 1.0 | 256 | - | 0.4699 |
- The bold row denotes the saved checkpoint.
Framework Versions
- Python: 3.8.19
- SetFit: 1.0.3
- Sentence Transformers: 3.0.1
- Transformers: 4.39.0
- PyTorch: 2.4.0
- Datasets: 2.20.0
- Tokenizers: 0.15.2
Citation
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}
}