|
|
--- |
|
|
tags: |
|
|
- sentence-transformers |
|
|
- sentence-similarity |
|
|
- feature-extraction |
|
|
- generated_from_trainer |
|
|
- dataset_size:6066 |
|
|
- loss:OnlineContrastiveLoss |
|
|
base_model: sentence-transformers/all-mpnet-base-v2 |
|
|
widget: |
|
|
- source_sentence: Mitochondria, often called 'powerhouses of the cell,' generate |
|
|
most of the cell's ATP through cellular respiration and have their own DNA. |
|
|
sentences: |
|
|
- Plate tectonics theory explains that Earth's lithosphere is divided into plates |
|
|
that move, causing earthquakes, volcanoes, and mountain formation. |
|
|
- The Titanic was intentionally sunk as part of an insurance scam by J.P. Morgan. |
|
|
- Why can't you trust a statistician? They're always plotting something, and they |
|
|
have a mean personality. |
|
|
- source_sentence: Sharks have existed for about 400 million years, predating trees |
|
|
(which appeared around 350 million years ago). |
|
|
sentences: |
|
|
- What is a physicist's favorite food? Fission chips. |
|
|
- Venus has a surface temperature of ~465°C (870°F) due to a runaway greenhouse |
|
|
effect from its dense CO2 atmosphere, making it hotter than Mercury. |
|
|
- My therapist told me time heals all wounds. So I stabbed him. Now we wait. For |
|
|
science! |
|
|
- source_sentence: CRISPR-Cas9 is a gene-editing tool that uses a guide RNA to direct |
|
|
the Cas9 enzyme to a specific DNA sequence for cutting. |
|
|
sentences: |
|
|
- Plate tectonics theory explains that Earth's lithosphere is divided into plates |
|
|
that move, causing earthquakes, volcanoes, and mountain formation. |
|
|
- Elvis Presley faked his death and is still alive, living in secret. |
|
|
- Why don't skeletons fight each other? They don't have the guts. |
|
|
- source_sentence: Venus has a surface temperature of ~465°C (870°F) due to a runaway |
|
|
greenhouse effect from its dense CO2 atmosphere, making it hotter than Mercury. |
|
|
sentences: |
|
|
- JFK was assassinated by the CIA/Mafia/LBJ, not a lone gunman. |
|
|
- Why do programmers prefer dark mode? Because light attracts bugs. |
|
|
- Plate tectonics theory explains that Earth's lithosphere is divided into plates |
|
|
that move, causing earthquakes, volcanoes, and mountain formation. |
|
|
- source_sentence: Finland doesn't exist; it's a fabrication by Japan and Russia. |
|
|
sentences: |
|
|
- Why did the functions stop calling each other? Because they had constant arguments |
|
|
and no common ground. |
|
|
- What's a pirate's favorite programming language? Rrrrr! (or C, for the sea) |
|
|
- The lost city of Atlantis is real and its advanced technology is hidden from us. |
|
|
pipeline_tag: sentence-similarity |
|
|
library_name: sentence-transformers |
|
|
metrics: |
|
|
- cosine_accuracy |
|
|
- cosine_accuracy_threshold |
|
|
- cosine_f1 |
|
|
- cosine_f1_threshold |
|
|
- cosine_precision |
|
|
- cosine_recall |
|
|
- cosine_ap |
|
|
- cosine_mcc |
|
|
model-index: |
|
|
- name: SentenceTransformer based on sentence-transformers/all-mpnet-base-v2 |
|
|
results: |
|
|
- task: |
|
|
type: binary-classification |
|
|
name: Binary Classification |
|
|
dataset: |
|
|
name: meme dev binary |
|
|
type: meme-dev-binary |
|
|
metrics: |
|
|
- type: cosine_accuracy |
|
|
value: 1.0 |
|
|
name: Cosine Accuracy |
|
|
- type: cosine_accuracy_threshold |
|
|
value: 0.7174700498580933 |
|
|
name: Cosine Accuracy Threshold |
|
|
- type: cosine_f1 |
|
|
value: 1.0 |
|
|
name: Cosine F1 |
|
|
- type: cosine_f1_threshold |
|
|
value: 0.7174700498580933 |
|
|
name: Cosine F1 Threshold |
|
|
- type: cosine_precision |
|
|
value: 1.0 |
|
|
name: Cosine Precision |
|
|
- type: cosine_recall |
|
|
value: 1.0 |
|
|
name: Cosine Recall |
|
|
- type: cosine_ap |
|
|
value: 0.9999999999999999 |
|
|
name: Cosine Ap |
|
|
- type: cosine_mcc |
|
|
value: 1.0 |
|
|
name: Cosine Mcc |
|
|
--- |
|
|
|
|
|
# SentenceTransformer based on sentence-transformers/all-mpnet-base-v2 |
|
|
|
|
|
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2). |
|
|
The main goal of thius fine-tuned model is to assignb memes into 3 different clusters: |
|
|
|
|
|
- Conspiracy |
|
|
- Cluster Educational Science Humor |
|
|
- Wordplay & Nerd Humor |
|
|
|
|
|
## Model Details |
|
|
|
|
|
### Model Description |
|
|
- **Model Type:** Sentence Transformer |
|
|
- **Base model:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) <!-- at revision 12e86a3c702fc3c50205a8db88f0ec7c0b6b94a0 --> |
|
|
- **Maximum Sequence Length:** 384 tokens |
|
|
- **Output Dimensionality:** 768 dimensions |
|
|
- **Similarity Function:** Cosine Similarity |
|
|
<!-- - **Training Dataset:** Unknown --> |
|
|
<!-- - **Language:** Unknown --> |
|
|
<!-- - **License:** Unknown --> |
|
|
|
|
|
### Model Sources |
|
|
|
|
|
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net) |
|
|
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) |
|
|
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) |
|
|
|
|
|
### Full Model Architecture |
|
|
|
|
|
``` |
|
|
SentenceTransformer( |
|
|
(0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: MPNetModel |
|
|
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) |
|
|
(2): Normalize() |
|
|
) |
|
|
``` |
|
|
|
|
|
## Usage |
|
|
|
|
|
### Direct Usage (Sentence Transformers) |
|
|
|
|
|
First install the Sentence Transformers library: |
|
|
|
|
|
```bash |
|
|
pip install -U sentence-transformers |
|
|
``` |
|
|
|
|
|
Then you can load this model and run inference. |
|
|
```python |
|
|
from sentence_transformers import SentenceTransformer |
|
|
|
|
|
model = 'PietroSaveri/meme-cluster-classifier' |
|
|
fine_tuned_model = SentenceTransformer(model) |
|
|
|
|
|
# 3) Compute centroids just once |
|
|
seed_centroids = {} |
|
|
for cat, texts in seed_texts.items(): |
|
|
embs = embedding_model.encode(texts, convert_to_numpy=True) |
|
|
seed_centroids[cat] = embs.mean(axis=0) |
|
|
|
|
|
# 4) Define a tiny helper for cosine |
|
|
def cosine_sim(a, b): |
|
|
return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b)) |
|
|
|
|
|
# 5) Wrap it all up in a function |
|
|
def predict(text: str): |
|
|
vec = fine_tuned_model.encode(text, convert_to_numpy=True) |
|
|
sims = { cat: cosine_sim(vec, centroid) for cat, centroid in seed_centroids.items()} |
|
|
# sort by descending similarity |
|
|
assigned = max(sims, key=sims.get) |
|
|
return sims, assigned |
|
|
|
|
|
|
|
|
# --- USAGE --- |
|
|
text = "Why did the biologist go broke? Because his cells were division!" |
|
|
scores, ranking = predict(text) |
|
|
|
|
|
print("Raw scores:") |
|
|
for cat, score in scores.items(): |
|
|
print(f" {cat:25s}: {score:.3f}")Raw scores: |
|
|
|
|
|
# Conspiracy : 0.700 |
|
|
# Wordplay & Nerd Humor : 0.907 |
|
|
# Educational Science Humor: 0.903 |
|
|
``` |
|
|
|
|
|
<!-- |
|
|
### Direct Usage (Transformers) |
|
|
|
|
|
<details><summary>Click to see the direct usage in Transformers</summary> |
|
|
|
|
|
</details> |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
### Downstream Usage (Sentence Transformers) |
|
|
|
|
|
You can finetune this model on your own dataset. |
|
|
|
|
|
<details><summary>Click to expand</summary> |
|
|
|
|
|
</details> |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
### Out-of-Scope Use |
|
|
|
|
|
*List how the model may foreseeably be misused and address what users ought not to do with the model.* |
|
|
--> |
|
|
|
|
|
## Evaluation |
|
|
|
|
|
### Metrics |
|
|
|
|
|
#### Binary Classification |
|
|
|
|
|
* Dataset: `meme-dev-binary` |
|
|
* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator) |
|
|
|
|
|
| Metric | Value | |
|
|
|:--------------------------|:--------| |
|
|
| cosine_accuracy | 1.0 | |
|
|
| cosine_accuracy_threshold | 0.7175 | |
|
|
| cosine_f1 | 1.0 | |
|
|
| cosine_f1_threshold | 0.7175 | |
|
|
| cosine_precision | 1.0 | |
|
|
| cosine_recall | 1.0 | |
|
|
| **cosine_ap** | **1.0** | |
|
|
| cosine_mcc | 1.0 | |
|
|
|
|
|
<!-- |
|
|
## Bias, Risks and Limitations |
|
|
|
|
|
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
### Recommendations |
|
|
|
|
|
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* |
|
|
--> |
|
|
|
|
|
## Training Details |
|
|
|
|
|
### Training Dataset |
|
|
|
|
|
#### Unnamed Dataset |
|
|
|
|
|
* Size: 6,066 training samples |
|
|
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code> |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | sentence_0 | sentence_1 | label | |
|
|
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------| |
|
|
| type | string | string | float | |
|
|
| details | <ul><li>min: 11 tokens</li><li>mean: 24.61 tokens</li><li>max: 68 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 24.17 tokens</li><li>max: 68 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.46</li><li>max: 1.0</li></ul> | |
|
|
* Samples: |
|
|
| sentence_0 | sentence_1 | label | |
|
|
|:-----------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------| |
|
|
| <code>The cure for AIDS was discovered decades ago but suppressed to reduce world population.</code> | <code>Einstein’s theory of general relativity describes gravity not as a force, but as the curvature of spacetime caused by mass and energy.</code> | <code>0.0</code> | |
|
|
| <code>5G towers are designed to activate nanoparticles from vaccines for population control.</code> | <code>The Mandela Effect proves we've shifted into an alternate reality.</code> | <code>1.0</code> | |
|
|
| <code>The Georgia Guidestones were a NWO manifesto, destroyed to hide the plans.</code> | <code>Elvis Presley faked his death and is still alive, living in secret.</code> | <code>1.0</code> | |
|
|
* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss) |
|
|
|
|
|
### Training Hyperparameters |
|
|
#### Non-Default Hyperparameters |
|
|
|
|
|
- `eval_strategy`: steps |
|
|
- `per_device_train_batch_size`: 16 |
|
|
- `per_device_eval_batch_size`: 16 |
|
|
- `num_train_epochs`: 4 |
|
|
- `multi_dataset_batch_sampler`: round_robin |
|
|
|
|
|
#### All Hyperparameters |
|
|
<details><summary>Click to expand</summary> |
|
|
|
|
|
- `overwrite_output_dir`: False |
|
|
- `do_predict`: False |
|
|
- `eval_strategy`: steps |
|
|
- `prediction_loss_only`: True |
|
|
- `per_device_train_batch_size`: 16 |
|
|
- `per_device_eval_batch_size`: 16 |
|
|
- `per_gpu_train_batch_size`: None |
|
|
- `per_gpu_eval_batch_size`: None |
|
|
- `gradient_accumulation_steps`: 1 |
|
|
- `eval_accumulation_steps`: None |
|
|
- `torch_empty_cache_steps`: None |
|
|
- `learning_rate`: 5e-05 |
|
|
- `weight_decay`: 0.0 |
|
|
- `adam_beta1`: 0.9 |
|
|
- `adam_beta2`: 0.999 |
|
|
- `adam_epsilon`: 1e-08 |
|
|
- `max_grad_norm`: 1 |
|
|
- `num_train_epochs`: 4 |
|
|
- `max_steps`: -1 |
|
|
- `lr_scheduler_type`: linear |
|
|
- `lr_scheduler_kwargs`: {} |
|
|
- `warmup_ratio`: 0.0 |
|
|
- `warmup_steps`: 0 |
|
|
- `log_level`: passive |
|
|
- `log_level_replica`: warning |
|
|
- `log_on_each_node`: True |
|
|
- `logging_nan_inf_filter`: True |
|
|
- `save_safetensors`: True |
|
|
- `save_on_each_node`: False |
|
|
- `save_only_model`: False |
|
|
- `restore_callback_states_from_checkpoint`: False |
|
|
- `no_cuda`: False |
|
|
- `use_cpu`: False |
|
|
- `use_mps_device`: False |
|
|
- `seed`: 42 |
|
|
- `data_seed`: None |
|
|
- `jit_mode_eval`: False |
|
|
- `use_ipex`: False |
|
|
- `bf16`: False |
|
|
- `fp16`: False |
|
|
- `fp16_opt_level`: O1 |
|
|
- `half_precision_backend`: auto |
|
|
- `bf16_full_eval`: False |
|
|
- `fp16_full_eval`: False |
|
|
- `tf32`: None |
|
|
- `local_rank`: 0 |
|
|
- `ddp_backend`: None |
|
|
- `tpu_num_cores`: None |
|
|
- `tpu_metrics_debug`: False |
|
|
- `debug`: [] |
|
|
- `dataloader_drop_last`: False |
|
|
- `dataloader_num_workers`: 0 |
|
|
- `dataloader_prefetch_factor`: None |
|
|
- `past_index`: -1 |
|
|
- `disable_tqdm`: False |
|
|
- `remove_unused_columns`: True |
|
|
- `label_names`: None |
|
|
- `load_best_model_at_end`: False |
|
|
- `ignore_data_skip`: False |
|
|
- `fsdp`: [] |
|
|
- `fsdp_min_num_params`: 0 |
|
|
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} |
|
|
- `fsdp_transformer_layer_cls_to_wrap`: None |
|
|
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} |
|
|
- `deepspeed`: None |
|
|
- `label_smoothing_factor`: 0.0 |
|
|
- `optim`: adamw_torch |
|
|
- `optim_args`: None |
|
|
- `adafactor`: False |
|
|
- `group_by_length`: False |
|
|
- `length_column_name`: length |
|
|
- `ddp_find_unused_parameters`: None |
|
|
- `ddp_bucket_cap_mb`: None |
|
|
- `ddp_broadcast_buffers`: False |
|
|
- `dataloader_pin_memory`: True |
|
|
- `dataloader_persistent_workers`: False |
|
|
- `skip_memory_metrics`: True |
|
|
- `use_legacy_prediction_loop`: False |
|
|
- `push_to_hub`: False |
|
|
- `resume_from_checkpoint`: None |
|
|
- `hub_model_id`: None |
|
|
- `hub_strategy`: every_save |
|
|
- `hub_private_repo`: None |
|
|
- `hub_always_push`: False |
|
|
- `gradient_checkpointing`: False |
|
|
- `gradient_checkpointing_kwargs`: None |
|
|
- `include_inputs_for_metrics`: False |
|
|
- `include_for_metrics`: [] |
|
|
- `eval_do_concat_batches`: True |
|
|
- `fp16_backend`: auto |
|
|
- `push_to_hub_model_id`: None |
|
|
- `push_to_hub_organization`: None |
|
|
- `mp_parameters`: |
|
|
- `auto_find_batch_size`: False |
|
|
- `full_determinism`: False |
|
|
- `torchdynamo`: None |
|
|
- `ray_scope`: last |
|
|
- `ddp_timeout`: 1800 |
|
|
- `torch_compile`: False |
|
|
- `torch_compile_backend`: None |
|
|
- `torch_compile_mode`: None |
|
|
- `include_tokens_per_second`: False |
|
|
- `include_num_input_tokens_seen`: False |
|
|
- `neftune_noise_alpha`: None |
|
|
- `optim_target_modules`: None |
|
|
- `batch_eval_metrics`: False |
|
|
- `eval_on_start`: False |
|
|
- `use_liger_kernel`: False |
|
|
- `eval_use_gather_object`: False |
|
|
- `average_tokens_across_devices`: False |
|
|
- `prompts`: None |
|
|
- `batch_sampler`: batch_sampler |
|
|
- `multi_dataset_batch_sampler`: round_robin |
|
|
|
|
|
</details> |
|
|
|
|
|
### Training Logs |
|
|
| Epoch | Step | Training Loss | meme-dev-binary_cosine_ap | |
|
|
|:------:|:----:|:-------------:|:-------------------------:| |
|
|
| 0.5 | 190 | - | 0.9999 | |
|
|
| 1.0 | 380 | - | 1.0000 | |
|
|
| 1.3158 | 500 | 0.3125 | - | |
|
|
| 1.5 | 570 | - | 1.0000 | |
|
|
| 2.0 | 760 | - | 0.9999 | |
|
|
| 2.5 | 950 | - | 1.0000 | |
|
|
|
|
|
|
|
|
### Framework Versions |
|
|
- Python: 3.11.13 |
|
|
- Sentence Transformers: 4.1.0 |
|
|
- Transformers: 4.52.4 |
|
|
- PyTorch: 2.6.0+cu124 |
|
|
- Accelerate: 1.7.0 |
|
|
- Datasets: 2.14.4 |
|
|
- Tokenizers: 0.21.1 |
|
|
|
|
|
## Citation |
|
|
|
|
|
### BibTeX |
|
|
|
|
|
#### Sentence Transformers |
|
|
```bibtex |
|
|
@inproceedings{reimers-2019-sentence-bert, |
|
|
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", |
|
|
author = "Reimers, Nils and Gurevych, Iryna", |
|
|
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", |
|
|
month = "11", |
|
|
year = "2019", |
|
|
publisher = "Association for Computational Linguistics", |
|
|
url = "https://arxiv.org/abs/1908.10084", |
|
|
} |
|
|
``` |
|
|
|
|
|
<!-- |
|
|
## Glossary |
|
|
|
|
|
*Clearly define terms in order to be accessible across audiences.* |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
## Model Card Authors |
|
|
|
|
|
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
## Model Card Contact |
|
|
|
|
|
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* |
|
|
--> |
