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

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5. 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: BAAI/bge-base-en-v1.5
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 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': 768, '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("datasocietyco/bge-base-en-v1.5-course-recommender-v3")
# Run inference
sentences = [
    'Intro to JavaScript: Basic Concepts',
    'A course that finalizes the series of introductory JavaScript courses and introduces the students to the basic concepts in the JavaScript ecosystem.',
    'Course language: HTML, JavaScript',
]
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

Unnamed Dataset

Size: 146 training samples
Columns: name, description, languages, prerequisites, target_audience, and merged

Approximate statistics based on the first 146 samples:

	name	description	languages	prerequisites	target_audience	merged
type	string	string	string	string	string	string
details	min: 3 tokens mean: 7.12 tokens max: 16 tokens	min: 13 tokens mean: 41.41 tokens max: 117 tokens	min: 6 tokens mean: 6.65 tokens max: 10 tokens	min: 8 tokens mean: 12.69 tokens max: 21 tokens	min: 5 tokens mean: 23.17 tokens max: 54 tokens	min: 45 tokens mean: 83.04 tokens max: 174 tokens

Samples:

name	description	languages	prerequisites	target_audience	merged
`Introduction to Statistics`	`This course is designed for learners who would like to learn about statistics and apply it for decision-making. This course is a comprehensive review of statistical terms ranging from foundational (mean, median, mode, standard deviation, variance, covariance, correlation) to more complex concepts such as normality in data, confidence intervals, and p-values. Additional topics include how to calculate summary statistics and how to carry out hypothesis testing to inform decisions.`	`Course language: Python`	`Prerequisite course required: Intro to Visualization in Python`	`Professionals some Python experience who would like to expand their skill set to more advanced Python visualization techniques and tools.`	Introduction to Statistics This course is designed for learners who would like to learn about statistics and apply it for decision-making. This course is a comprehensive review of statistical terms ranging from foundational (mean, median, mode, standard deviation, variance, covariance, correlation) to more complex concepts such as normality in data, confidence intervals, and p-values. Additional topics include how to calculate summary statistics and how to carry out hypothesis testing to inform decisions. Course language: Python Prerequisite course required: Intro to Visualization in Python Professionals some Python experience who would like to expand their skill set to more advanced Python visualization techniques and tools.
`Statistics & Probability`	`This course is designed for learners who would like to learn about statistics and apply it for decision-making. This course is a comprehensive review of advanced statistics topics on probability like permutations and combinations, joint probability, conditional probability, marginal probability, and Bayes' theorem that provides a way to revise existing predictions or update probabilities given new or additional evidence.`	`Course language: Python`	`Prerequisite course required: Intermediate Statistics`	`Professionals some Python experience who would like to expand their skill set to more advanced Python visualization techniques and tools.`	Statistics & Probability This course is designed for learners who would like to learn about statistics and apply it for decision-making. This course is a comprehensive review of advanced statistics topics on probability like permutations and combinations, joint probability, conditional probability, marginal probability, and Bayes' theorem that provides a way to revise existing predictions or update probabilities given new or additional evidence. Course language: Python Prerequisite course required: Intermediate Statistics Professionals some Python experience who would like to expand their skill set to more advanced Python visualization techniques and tools.
`Databases: Advanced Relational`	`A deeper dive into the many capabilities of a relational database, how to optimize usage and make sure that your are getting the most use out of your database so that you have a strong base for your applications.`	`Course language: SQL`	`Prerequisite course required: Databases: Relational`	`Professionals who would like to improve on their knowledge of relational databases.`	`Databases: Advanced Relational A deeper dive into the many capabilities of a relational database, how to optimize usage and make sure that your are getting the most use out of your database so that you have a strong base for your applications. Course language: SQL Prerequisite course required: Databases: Relational Professionals who would like to improve on their knowledge of relational databases.`

Loss: MultipleNegativesRankingLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

Size: 37 evaluation samples
Columns: name, description, languages, prerequisites, target_audience, and merged

Approximate statistics based on the first 37 samples:

	name	description	languages	prerequisites	target_audience	merged
type	string	string	string	string	string	string
details	min: 4 tokens mean: 6.84 tokens max: 13 tokens	min: 14 tokens mean: 36.92 tokens max: 84 tokens	min: 6 tokens mean: 6.7 tokens max: 10 tokens	min: 8 tokens mean: 12.05 tokens max: 18 tokens	min: 13 tokens mean: 23.3 tokens max: 48 tokens	min: 47 tokens mean: 77.81 tokens max: 124 tokens

Samples:

name	description	languages	prerequisites	target_audience	merged
`Understanding Different OS Concepts`	`A course that builds foundational knowledge of what an operating system is. It walks through the different core concepts of OS and its inner workings.`	`Course language: TBD`	`Prerequisite course required: Domain & Hosting`	`Professionals who would like to learn the core concepts of Operating system`	`Understanding Different OS Concepts A course that builds foundational knowledge of what an operating system is. It walks through the different core concepts of OS and its inner workings. Course language: TBD Prerequisite course required: Domain & Hosting Professionals who would like to learn the core concepts of Operating system`
`Basic GraphQL: Node.js`	`An introduction to GraphQL, what it is good for and how to use it to query or change data.`	`Course language: JavaScript`	`Prerequisite course required: JSON APIs: Node.js`	`Professionals who would like to learn the core concepts of GraphQL, using Node.js`	`Basic GraphQL: Node.js An introduction to GraphQL, what it is good for and how to use it to query or change data. Course language: JavaScript Prerequisite course required: JSON APIs: Node.js Professionals who would like to learn the core concepts of GraphQL, using Node.js`
`Deep Learning for Text Analysis`	`This course continues on tackling topics in deep learning that address specific problem types. In this course students will be getting to know RNNs and LSTMs - types of neural networks that are often used for solving problems in text analysis.`	`Course language: Python`	`Prerequisite course required: Neural Networks & Deep Learning`	`Professionals who would like to get a base-level understanding of the recurrent neural networks, their subtypes, and their application in text analysis.`	Deep Learning for Text Analysis This course continues on tackling topics in deep learning that address specific problem types. In this course students will be getting to know RNNs and LSTMs - types of neural networks that are often used for solving problems in text analysis. Course language: Python Prerequisite course required: Neural Networks & Deep Learning Professionals who would like to get a base-level understanding of the recurrent neural networks, their subtypes, and their application in text analysis.

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
learning_rate: 3e-06
max_steps: 64
warmup_ratio: 0.1
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: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 3e-06
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 3.0
max_steps: 64
lr_scheduler_type: linear
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: 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: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss
2.0	20	1.4618	1.0396
4.0	40	0.8698	0.8235
6.0	60	0.8096	0.7544

Framework Versions

Python: 3.11.7
Sentence Transformers: 3.1.1
Transformers: 4.45.1
PyTorch: 2.2.2
Accelerate: 0.34.2
Datasets: 3.0.0
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",
}

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}
}