Culture-and-Morality-Lab/psyembedding-bert-large-uncased

SentenceTransformer

This is a sentence-transformers model trained. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

• —Model Type: Sentence Transformer <!-- - Base model: Unknown -->
• —Maximum Sequence Length: 512 tokens
• —Output Dimensionality: 1024 dimensions
• —Similarity Function: Cosine Similarity <!-- - Training Dataset: Unknown --> <!-- - Language: Unknown --> <!-- - License: Unknown -->

Model Sources

• —Documentation: Sentence Transformers Documentation
• —Repository: Sentence Transformers on GitHub
• —Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 1024, '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})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("Culture-and-Morality-Lab/psyembedding-bert-large-uncased")
# Run inference
sentences = [
    'Every American poet feels that the whole responsibility for contemporary poetry has fallen upon his shoulders, that he is a literary aristocracy of one.',
    "I'm not sure why Spike Lee made this train wreck of a movie and conned poor Stevie Wonder into eternally pairing his beautiful music with this theatrical mess. I also resent the way he uses profanity as a part of the normal prose of professional Blacks. The abuse of his hold on ethnic movie goers is a shame. Scenes which seem to be contrived out the blue and have nothing to do with the theme or sub themes, play as if some college kid wrote this. I especially detest the ludicrous scene where the two leads are playfully sparring for no reason at all and the cops come and rough up Snipes. The overacting of the leads makes one feel as if Spike has no respect for his viewers or he has no clue what a movie is all about. The final scene appears to be thrown in to justify the use of a sledge hammer to tack a point in. This movie also supports the myth that all people of culture use the F-word in casual conversation. I am hoping he will realize that the rest of his movies are in the same pool as this one where he is not growing as a film maker. I think his union with Scorcesee in Clockers was a wise move. He should stick to making documentaries like the Four Little Colored Girls. Shock movies do not an Oscar make.",
    'Many thousands of youth have been deprived of the benefit of education thereby, their morals ruined, and talents irretrievably lost to society, for want of cultivation: while two parties have been idly contending who should bestow it.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.6358, 0.5940],
#         [0.6358, 1.0000, 0.4347],
#         [0.5940, 0.4347, 1.0000]])

<!--

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

Semantic Similarity

• —Dataset: similarity
• —Evaluated with <code>EmbeddingSimilarityEvaluator</code>

<!--

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: 11,180 training samples
• —Columns: <code>sentence0</code>, <code>sentence1</code>, and <code>label</code>
• —Approximate statistics based on the first 1000 samples: | | sentence0 | sentence1 | label | |:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:---------------------------------------------------------------| | type | string | string | float | | details | <ul><li>min: 6 tokens</li><li>mean: 107.53 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 111.53 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.53</li><li>max: 1.0</li></ul> |
• —Samples: | sentence0 | sentence1 | label | |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------| | <code>I AM ANGRY AT YOU BILLJ! YOU GOT PEOPLE BLOCKED FOR AS LONG AS YOU LIVE! I ASKED YOU TO STOP DELETING MY EDITS OR I WILL BLOCK YOU FOR ALl EONS YOU ASSHOLE! WIKIPEDIA IS NOT CENSORED SO STOP REMOVING MY FUCKING MESSAGES OR I WILL BEAT YOU UP SILLY!</code> | <code>The thing is i don't see any shyness from people supporting far right anymore. The life of avg Joe became signicantly shittier after covid and global conflicts. They are very vocal about their distaste. And they blame lefties and immigrants for their problems. So they are vocal and very organized.<br><br>Also most of the public already act demented and noone remembers all the moronic stuff Trump pulled during his presidency.<br><br>I don't see much reason for them to be shy about.</code> | <code>0.4082482904638631</code> | | <code>I understand that you may be confused, but you still shouldn't judge someone's sexual identity. Just because they haven't acted on all of their sexual inclinations, doesn't mean that they don't still have those feelings. Accept others as they present themselves.</code> | <code>The head of the Mormon church has married same sex couples in the temple because they were close family. It's all about $$$.</code> | <code>0.5773502691896258</code> | | <code>Ugh there is so many bad decisions by conservative judges that need to be undone.</code> | <code>you say waste a draft pick on Manziel when we have Mallet. that's why I'm telling you to delete your account. You're retarded</code> | <code>0.5773502691896258</code> |
• —Loss: <code>CosineSimilarityLoss</code> with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }

Training Hyperparameters

Non-Default Hyperparameters

• —eval_strategy: steps
• —per_device_train_batch_size: 32
• —per_device_eval_batch_size: 32
• —fp16: True
• —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: 32
• —per_device_eval_batch_size: 32
• —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: 3
• —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: True
• —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: {'minnumparams': 0, 'xla': False, 'xlafsdpv2': False, 'xlafsdpgrad_ckpt': False}
• —fsdp_transformer_layer_cls_to_wrap: None
• —accelerator_config: {'splitbatches': False, 'dispatchbatches': None, 'evenbatches': True, 'useseedablesampler': True, 'nonblocking': False, 'gradientaccumulationkwargs': 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
• —hub_revision: None
• —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
• —liger_kernel_config: None
• —eval_use_gather_object: False
• —average_tokens_across_devices: False
• —prompts: None
• —batch_sampler: batch_sampler
• —multi_dataset_batch_sampler: round_robin
• —router_mapping: {}
• —learning_rate_mapping: {}

</details>

Training Logs

<details><summary>Click to expand</summary>

</details>

Framework Versions

• —Python: 3.11.9
• —Sentence Transformers: 5.1.0
• —Transformers: 4.53.3
• —PyTorch: 2.5.1
• —Accelerate: 1.10.0
• —Datasets: 2.14.4
• —Tokenizers: 0.21.0

Citation

BibTeX

Sentence Transformers

@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. -->