stella-eedi-2024

SentenceTransformer based on dunzhang/stella_en_400M_v5

This is a sentence-transformers model finetuned from dunzhang/stella_en_400M_v5 on the csv dataset. 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: dunzhang/stella_en_400M_v5 <!-- at revision 1bb50bc7bb726810eac2140e62155b88b0df198f -->
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 1024 tokens
• Similarity Function: Cosine Similarity
• Training Dataset:
  • csv

<!-- - **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}) with Transformer model: NewModel 
  (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})
  (2): Dense({'in_features': 1024, 'out_features': 1024, 'bias': True, 'activation_function': 'torch.nn.modules.linear.Identity'})
)

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("Gurveer05/stella-eedi-2024")
# Run inference
sentences = [
    'Construct:  Solve quadratic equations using the quadratic formula where the coefficient of x² is not 1.\n\nQuestion:  Vera wants to solve this equation using the quadratic formula.\n(\n3 h^2-10 h+4=0\n)\n\nWhat should replace the circle?  (? pm square root of (?-?) / bigcirc).\n\nOptions:\nA. 3\nB. 5\nC. 9\nD. 6\n\nCorrect Answer: 6\n\nIncorrect Answer: 3',
    'Misremembers the quadratic formula',
    'Does not know that vertically opposite angles are equal',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

<!-- ### 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.* --> <!-- ## 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

csv

• Dataset: csv
• Size: 2,442 training samples
• Columns: <code>qa_pair_text</code> and <code>MisconceptionName</code>
• Approximate statistics based on the first 1000 samples:

  	qa_pair_text	MisconceptionName
  type	string	string
  details	<ul><li>min: 40 tokens</li><li>mean: 102.66 tokens</li><li>max: 512 tokens</li></ul>	<ul><li>min: 4 tokens</li><li>mean: 15.26 tokens</li><li>max: 39 tokens</li></ul>

• Samples:

  qa_pair_text	MisconceptionName
  <code>Construct: Convert between cm³ and mm³.<br><br>Question: 1 cm^3 is the same as _______ mm^3.<br><br>Options:<br>A. 10<br>B. 100<br>C. 1000<br>D. 10000<br><br>Correct Answer: 1000<br><br>Incorrect Answer: 10</code>	<code>Does not cube the conversion factor when converting cubed units</code>
  <code>Construct: Write algebraic expressions with correct algebraic convention.<br><br>Question: Which answer shows the following calculation using the correct algebraic convention?<br>(<br>y x x+b x 3<br>).<br><br>Options:<br>A. y x+b 3<br>B. x y+3 b<br>C. y+3 b x<br>D. 3 b x y<br><br>Correct Answer: x y+3 b<br><br>Incorrect Answer: 3 b x y</code>	<code>Multiplies all terms together when simplifying an expression</code>
  <code>Construct: Write algebraic expressions with correct algebraic convention.<br><br>Question: Which of the following is the correct way of writing: p divided by q , then add 3 using algebraic convention?<br><br>Options:<br>A. p q+3<br>B. (p / q)+3<br>C. (p / q+3)<br>D. p-q+3<br><br>Correct Answer: (p / q)+3<br><br>Incorrect Answer: p-q+3</code>	<code>Has used a subtraction sign to represent division</code>

• Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Evaluation Dataset

csv

• Dataset: csv
• Size: 1,928 evaluation samples
• Columns: <code>qa_pair_text</code> and <code>MisconceptionName</code>
• Approximate statistics based on the first 1000 samples:

  	qa_pair_text	MisconceptionName
  type	string	string
  details	<ul><li>min: 40 tokens</li><li>mean: 103.34 tokens</li><li>max: 512 tokens</li></ul>	<ul><li>min: 4 tokens</li><li>mean: 14.34 tokens</li><li>max: 40 tokens</li></ul>

• Samples:

  qa_pair_text	MisconceptionName
  <code>Construct: Multiply two decimals together with the same number of decimal places.<br><br>Question: 0.4^2=.<br><br>Options:<br>A. 0.08<br>B. 0.8<br>C. 1.6<br>D. 0.16<br><br>Correct Answer: 0.16<br><br>Incorrect Answer: 0.8</code>	<code>Mixes up squaring and multiplying by 2 or doubling</code>
  <code>Construct: Calculate the cube root of a number.<br><br>Question: 3rd root of (8)=.<br><br>Options:<br>A. 2 . dot{6}<br>B. 4<br>C. 64<br>D. 2<br><br>Correct Answer: 2<br><br>Incorrect Answer: 4</code>	<code>Halves when asked to find the cube root</code>
  <code>Construct: Calculate missing lengths of shapes by geometrical inference, where the lengths given are in the same units.<br><br>Question: What is the area of the shaded section of this composite shape made from rectangles? A composite shape made from two rectangles that form an "L" shape. The base of the shape is horizontal and is 13cm long. The vertical height of the whole shape is 14cm. The horizontal width of the top part of the shape is 6cm. The vertical height of the top rectangle is 8cm. The right handed rectangle is shaded blue.<br><br>Options:<br>A. 48 cm^2<br>B. 104 cm^2<br>C. 42 cm^2<br>D. 56 cm^2<br><br>Correct Answer: 42 cm^2<br><br>Incorrect Answer: 48 cm^2</code>	<code>Uses an incorrect side length when splitting a composite shape into parts</code>

• Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• gradient_accumulation_steps: 32
• weight_decay: 0.01
• num_train_epochs: 20
• lr_scheduler_type: cosine_with_restarts
• warmup_ratio: 0.1
• fp16: True
• load_best_model_at_end: True
• gradient_checkpointing: True
• batch_sampler: no_duplicates

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: 32
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 5e-05
• weight_decay: 0.01
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 20
• max_steps: -1
• lr_scheduler_type: cosine_with_restarts
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• 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: True
• 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: False
• hub_always_push: False
• gradient_checkpointing: True
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• 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
• dispatch_batches: None
• split_batches: 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
• eval_use_gather_object: False
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

</details>

Training Logs

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.1.1
• Transformers: 4.44.2
• PyTorch: 2.4.1+cu121
• Accelerate: 0.34.2
• Datasets: 2.19.2
• Tokenizers: 0.19.1

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",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

<!-- ## 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.* -->