SentenceTransformer based on sentence-transformers/all-mpnet-base-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-mpnet-base-v2 on the csv dataset. It maps sentences & paragraphs to a 768-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: sentence-transformers/all-mpnet-base-v2
Maximum Sequence Length: 384 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- csv

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': 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:

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/mpnet-base-eedi-2024")
# Run inference
sentences = [
    'Construct:  Solve coordinate geometry questions involving ratio.\n\nQuestion:  A straight line on squared paper. Points P, Q and R lie on this line. The leftmost end of the line is labelled P. If you travel right 4 squares and up 1 square you get to point Q. If you then travel 8 squares right and 2 squares up from Q you reach point R. What is the ratio of  P Q: P R  ?\n\nOptions:\nA. 1: 12\nB. 1: 4\nC. 1: 2\nD. 1: 3\n\nCorrect Answer: 1: 3\n\nIncorrect Answer: 1: 2\n\nPredicted Misconception: Misunderstanding the ratio calculation by not considering the correct horizontal and vertical distances between points P, Q, and R.',
    'May have estimated when using ratios with geometry',
    'Thinks x = y is an axis',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

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

Training Details

Training Dataset

csv

Dataset: csv
Size: 12,210 training samples
Columns: qa_pair_text, MisconceptionName, and negative

Approximate statistics based on the first 1000 samples:

	qa_pair_text	MisconceptionName	negative
type	string	string	string
details	min: 54 tokens mean: 123.41 tokens max: 384 tokens	min: 4 tokens mean: 15.16 tokens max: 39 tokens	min: 7 tokens mean: 14.49 tokens max: 40 tokens

Samples:

qa_pair_text	MisconceptionName	negative
`Construct: Construct frequency tables. Question: Dave has recorded the number of pets his classmates have in the frequency table on the right. Number of pets`	Frequency 0	4 1
`Construct: Convert between any other time periods. Question: To work out how many hours in a year you could do... Options: A. 365 x 7 B. 365 x 60 C. 365 x 12 D. 365 x 24 Correct Answer: 365 x 24 Incorrect Answer: 365 x 60 Predicted Misconception: Multiplying days by hours per minute instead of hours per day.`	`Answers as if there are 60 hours in a day`	`Confuses an equation with an expression`
`Construct: Given information about one part, work out other parts. Question: Jess and Heena share some sweets in the ratio 3;: 5 . Jess gets 15 sweets. How many sweets does Heena get? Options: A. 17 B. 9 C. 5 D. 25 Correct Answer: 25 Incorrect Answer: 17 Predicted Misconception: Misunderstanding the direct proportionality between the ratio and actual quantities.`	`Thinks a difference of one part in a ratio means the quantities will differ by one unit`	`Believes dividing two positives will give a negative answer`

Loss: MultipleNegativesRankingLoss with these parameters:

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

Evaluation Dataset

csv

Dataset: csv
Size: 9,640 evaluation samples
Columns: qa_pair_text, MisconceptionName, and negative

Approximate statistics based on the first 1000 samples:

	qa_pair_text	MisconceptionName	negative
type	string	string	string
details	min: 56 tokens mean: 121.43 tokens max: 384 tokens	min: 6 tokens mean: 14.51 tokens max: 39 tokens	min: 6 tokens mean: 13.86 tokens max: 40 tokens

Samples:

qa_pair_text	MisconceptionName	negative
Construct: Identify when rounding a calculation will give an over or under approximation. Question: Tom and Katie are discussing how to estimate the answer to [ 38.8745 / 7.9302 ] Tom says 40 / 7.9302 would give an overestimate. Katie says 38.8745 / 8 would give an overestimate. Who is correct? Options: A. Only Tom B. Only Katie C. Both Tom and Katie D. Neither is correct Correct Answer: Only Tom Incorrect Answer: Neither is correct Predicted Misconception: Rounding both numbers up leads to an overestimate.	`Believes that the larger the dividend, the smaller the answer.`	`Does not know how to calculate the mean`
`Construct: Substitute negative integer values into expressions involving no powers or roots. Question: Amy is trying to work out the distance between these two points: (1,-6) and (-5,2) She labels them like this: x_1`	y_1	x_2
`Construct: Round numbers to three or more decimal places. Question: What is 20.15349 rounded to 3 decimal places? Options: A. 20.153 B. 20.15 C. 20.154 D. 20.253 Correct Answer: 20.153 Incorrect Answer: 20.154 Predicted Misconception: Rounding up the fourth decimal place without considering the fifth decimal place.`	`Rounds up instead of down`	`When dividing decimals, does not realize that the order and position of the digits (relative to each other) has to remain constant.`

Loss: MultipleNegativesRankingLoss 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: 16
learning_rate: 1e-05
weight_decay: 0.01
num_train_epochs: 40
lr_scheduler_type: cosine
lr_scheduler_kwargs: {'num_cycles': 20}
warmup_ratio: 0.1
fp16: True
load_best_model_at_end: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

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: 16
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 1e-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: 40
max_steps: -1
lr_scheduler_type: cosine
lr_scheduler_kwargs: {'num_cycles': 20}
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: 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
eval_use_gather_object: False
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss
0.5026	12	1.6224	-
1.0026	24	1.4736	1.6492
1.5052	36	1.3341	-
2.0052	48	1.1563	1.3401
2.5079	60	1.0641	-
3.0079	72	0.9238	1.1597
3.5105	84	0.8253	-
4.0105	96	0.7101	1.0224
4.5131	108	0.6285	-
5.0131	120	0.5821	0.9944
5.5157	132	0.5676	-
6.0157	144	0.5018	0.9471
6.5183	156	0.4599	-
7.0183	168	0.4403	0.9292
7.5209	180	0.4161	-
8.0209	192	0.3784	0.9107
8.5236	204	0.3503	-
9.0236	216	0.3451	0.9042
9.5262	228	0.3141	-
10.0262	240	0.2916	0.9012
10.5288	252	0.2863	-
11.0288	264	0.2713	0.8977
11.5314	276	0.244	-
12.0314	288	0.2323	0.8922
12.5340	300	0.2293	-
13.0340	312	0.211	0.8933
13.5366	324	0.1972	-
14.0366	336	0.1918	0.9024
14.5393	348	0.1868	-
15.0393	360	0.1704	0.8930
15.5419	372	0.1661	-
16.0419	384	0.1666	0.9077
16.5445	396	0.1558	-
17.0445	408	0.1459	0.9153

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.14
Sentence Transformers: 3.1.1
Transformers: 4.44.0
PyTorch: 2.4.0
Accelerate: 0.33.0
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}
}