metadata

base_model: BAAI/bge-large-en-v1.5
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:4370
  - loss:CosineSimilarityLoss
widget:
  - source_sentence: >

      Construct: Recognise a linear graph from its shape

      Subject: Finding the Gradient and Intercept of a Line from the Equation

      Question: Use a graphing program (e.g. Desmos) to plot the following pairs
      of functions.

      \[

      y=3 \text { and } y=-2

      \]


      Tom says both functions are linear


      Katie says both functions are vertical lines


      Who is correct?

      Incorrect Answer: Neither is correct

      Correct Answer: Only

      Tom
    sentences:
      - >-
        Believes the coefficent of x in an expanded quadratic comes from
        multiplying the two numbers in the brackets
      - Does not know the properties of a linear graph
      - Misremembers the quadratic formula
  - source_sentence: >

      Construct: Multiply two decimals together with the same number of decimal
      places

      Subject: Multiplying and Dividing with Decimals

      Question: \( 0.6 \times 0.4= \)

      Incorrect Answer: \( 2.4 \)

      Correct Answer: \( 0.24 \)
    sentences:
      - >-
        When asked to solve simultaneous equations, believes they can just find
        values that work in one equation
      - >-
        Believes the solutions of a quadratic equation are the constants in the
        factorised form
      - >-
        When multiplying decimals, divides by the wrong power of 10 when
        reinserting the decimal
  - source_sentence: >

      Construct: Estimate the volume or capacity of an object

      Subject: Volume of Prisms

      Question: Each of these measurements matches one of these objects. ![An
      image of 4 objects and 4 measurements. The objects are an egg cup, a
      cereal box, a chest of drawers and a piggy bank. And, the measurements are
      87 cm^3, 1013 cm^3, 4172 cm^3 and 197,177 cm^3.]() Which measurement most
      likely matches the egg cup?

      Incorrect Answer: \( 197177 \mathrm{~cm}^{3} \)

      Correct Answer: \( 87 \mathrm{~cm}^{3} \)
    sentences:
      - Confuses quadratic and exponential graphs
      - Cannot estimate the relative volume order, for different objects
      - Does not know how many days are in a leap year
  - source_sentence: |

      Construct: Carry out division  problems involving one negative integer
      Subject: Multiplying and Dividing Negative Numbers
      Question: \( 12 \div(-4)= \)
      Incorrect Answer: \( 3 \)
      Correct Answer: \( -3 \)
    sentences:
      - Believes dividing a positive by a negative gives a positive answer
      - >-
        Believes -a is always smaller than a, ignoring the possibility that a is
        negative
      - Subtracts instead of divides
  - source_sentence: >

      Construct: Construct frequency tables

      Subject: Frequency tables

      Question: Dave has recorded the number of pets his classmates have in the
      frequency table on the right. \begin{tabular}{|c|c|}

      \hline Number of pets & Frequency \\

      \hline \( 0 \) & \( 4 \) \\

      \hline \( 1 \) & \( 6 \) \\

      \hline \( 2 \) & \( 3 \) \\

      \hline \( 3 \) & \( 2 \) \\

      \hline \( 4 \) & \( 5 \) \\

      \hline

      \end{tabular} If Dave wanted to work out the total number of pets own by
      his classmates, what would be a useful column to include?

      Incorrect Answer: Number of pets -

      Frequency

      Correct Answer: Number of pets \( x \) Frequency
    sentences:
      - Subtracts rather than multiplies when calculating total frequency
      - >-
        Does not follow the arrows through a function machine, changes the order
        of the operations asked.
      - >-
        Believes the intersection in a prime factor venn diagram does not
        contribute to the size of the number represented by a circle

SentenceTransformer based on BAAI/bge-large-en-v1.5

This is a sentence-transformers model finetuned from BAAI/bge-large-en-v1.5. 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: BAAI/bge-large-en-v1.5
Maximum Sequence Length: 512 tokens
Output Dimensionality: 1024 tokens
Similarity Function: Cosine Similarity

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': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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:

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("VaggP/bge-fine-tuned")
# Run inference
sentences = [
    '\nConstruct: Construct frequency tables\nSubject: Frequency tables\nQuestion: Dave has recorded the number of pets his classmates have in the frequency table on the right. \\begin{tabular}{|c|c|}\n\\hline Number of pets & Frequency \\\\\n\\hline  $0$  &  $4$  \\\\\n\\hline  $1$  &  $6$  \\\\\n\\hline  $2$  &  $3$  \\\\\n\\hline  $3$  &  $2$  \\\\\n\\hline  $4$  &  $5$  \\\\\n\\hline\n\\end{tabular} If Dave wanted to work out the total number of pets own by his classmates, what would be a useful column to include?\nIncorrect Answer: Number of pets -\nFrequency\nCorrect Answer: Number of pets  $x$  Frequency\n',
    'Subtracts rather than multiplies when calculating total frequency',
    'Does not follow the arrows through a function machine, changes the order of the operations asked.',
]
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]

Training Details

Training Dataset

Unnamed Dataset

Size: 4,370 training samples
Columns: sentence_0, sentence_1, and label
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label
type string string float
details
min: 38 tokens
mean: 98.75 tokens
max: 414 tokens

min: 4 tokens
mean: 14.91 tokens
max: 38 tokens

min: 1.0
mean: 1.0
max: 1.0

	sentence_0	sentence_1	label
type	string	string	float
details	min: 38 tokens mean: 98.75 tokens max: 414 tokens	min: 4 tokens mean: 14.91 tokens max: 38 tokens	min: 1.0 mean: 1.0 max: 1.0

Samples:

sentence_0	sentence_1	label
`Construct: Construct a pictogram involving fractions of symbols Subject: Pictogram Question: This pictogram shows the different types of music Bob has in his music collection. Bob has ( 2 ) rave CDs. How would he display this on the pictogram? Incorrect Answer: Correct Answer:`	`When interpreting a pictogram, thinks each symbol stands for 1`	`1.0`
`Construct: Use brackets to write function machines as calculations Subject: Writing Expressions Question: Tom and Katie are arguing about the result of this Function Machine: Tom says the output is: ( 3 n-12 ) Katie says the output is: ( 3(n-4) ) Who is correct? Incorrect Answer: Only Tom Correct Answer: Both Tom and Katie`	`Does not think a factorised expression is equivalent to its multiplied out form`	`1.0`
`Construct: Interpret linear sections of real life graphs Subject: Real Life Graphs Question: The graph on the right shows the mass of sand in a bucket over time What might the horizontal section represent? Incorrect Answer: Sand is being tipped out Correct Answer: The bucket is full`	`Believes a horizontal line can show a constant rate of change`	`1.0`

Loss: CosineSimilarityLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

num_train_epochs: 1
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: no
prediction_loss_only: True
per_device_train_batch_size: 8
per_device_eval_batch_size: 8
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: 1
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: False
hub_always_push: False
gradient_checkpointing: False
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
use_liger_kernel: False
eval_use_gather_object: False
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	Training Loss
0.9141	500	0.0055

Framework Versions

Python: 3.10.14
Sentence Transformers: 3.2.0
Transformers: 4.45.1
PyTorch: 2.4.0
Accelerate: 0.34.2
Datasets: 3.0.1
Tokenizers: 0.20.0

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",
}