datasocietyco/bge-base-en-v1.5-course-recommender-v2

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-v2")
# Run inference
sentences = [
    'React Ecosystem: Forms',
    "A course that builds on the foundations of React framework and expands learners' skills to more advanced concepts.",
    'Course language: 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: 50 training samples
• Columns: name, description, languages, prerequisites, and target_audience
• Approximate statistics based on the first 50 samples:

  	name	description	languages	prerequisites	target_audience
  type	string	string	string	string	string
  details	min: 3 tokens mean: 7.0 tokens max: 16 tokens	min: 16 tokens mean: 43.96 tokens max: 117 tokens	min: 6 tokens mean: 6.6 tokens max: 10 tokens	min: 8 tokens mean: 12.32 tokens max: 21 tokens	min: 12 tokens mean: 22.74 tokens max: 54 tokens

• Samples:

  name	description	languages	prerequisites	target_audience
  Autoencoders	This course takes students through a journey into the world od autoencoders - a set of powerful deep learning models that have a special place in the world of image analysis. By the end of this course students will be able to navigate through the application space of autoencoders and implement autoencoders to perform tasks such as image denoising and more.	Course language: Python	Prerequisite course required: Convolutional Neural Networks (CNN) for Image Recognition	Professionals some Python experience who would like to expand their skillset to more advanced machine learning algorithms for image processing and computer vision.
  Advanced CNN	This course build on the subject of Convolutional Neural Networks and dives into the complex pre-trained state-of-the-art CNN architectures. It also gives students a preview of what transfer learning is and why it is such a powerful concept in Deep Learning. By the end of this course students will be able to have implemented and explored pre-trained models such as ResNet, VGG16, and Inception3.	Course language: Python	Prerequisite course required: Convolutional Neural Networks (CNN) for Image Recognition	Professionals some Python experience who would like to expand their skillset to more advanced machine learning algorithms for image processing, computer vision, and transfer learning.
  Advanced Clustering in R	This course covers the unsupervised learning method called clustering which is used to find patterns or groups in data without the need for labelled data. This course includes application of different methods of clustering on categorical or mixed data, equipping learners to build, evaluate, and interpret these models.	Course language: R	Prerequisite course required: Intermediate Clustering in R	Professionals with some R experience who would like to expand their skillset to learn the core unsupervised learning techniques. Analysts with experience in another similar programming language who would like to learn core unsupervised learning frameworks and packages in R.

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

• Size: 50 evaluation samples
• Columns: name, description, languages, prerequisites, and target_audience
• Approximate statistics based on the first 50 samples:

  	name	description	languages	prerequisites	target_audience
  type	string	string	string	string	string
  details	min: 3 tokens mean: 7.0 tokens max: 16 tokens	min: 16 tokens mean: 43.96 tokens max: 117 tokens	min: 6 tokens mean: 6.6 tokens max: 10 tokens	min: 8 tokens mean: 12.32 tokens max: 21 tokens	min: 12 tokens mean: 22.74 tokens max: 54 tokens

• Samples:

  name	description	languages	prerequisites	target_audience
  Autoencoders	This course takes students through a journey into the world od autoencoders - a set of powerful deep learning models that have a special place in the world of image analysis. By the end of this course students will be able to navigate through the application space of autoencoders and implement autoencoders to perform tasks such as image denoising and more.	Course language: Python	Prerequisite course required: Convolutional Neural Networks (CNN) for Image Recognition	Professionals some Python experience who would like to expand their skillset to more advanced machine learning algorithms for image processing and computer vision.
  Advanced CNN	This course build on the subject of Convolutional Neural Networks and dives into the complex pre-trained state-of-the-art CNN architectures. It also gives students a preview of what transfer learning is and why it is such a powerful concept in Deep Learning. By the end of this course students will be able to have implemented and explored pre-trained models such as ResNet, VGG16, and Inception3.	Course language: Python	Prerequisite course required: Convolutional Neural Networks (CNN) for Image Recognition	Professionals some Python experience who would like to expand their skillset to more advanced machine learning algorithms for image processing, computer vision, and transfer learning.
  Advanced Clustering in R	This course covers the unsupervised learning method called clustering which is used to find patterns or groups in data without the need for labelled data. This course includes application of different methods of clustering on categorical or mixed data, equipping learners to build, evaluate, and interpret these models.	Course language: R	Prerequisite course required: Intermediate Clustering in R	Professionals with some R experience who would like to expand their skillset to learn the core unsupervised learning techniques. Analysts with experience in another similar programming language who would like to learn core unsupervised learning frameworks and packages in R.

• 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
5.0	20	1.0201	0.7447
5.5	40	0.6132	0.5379
6.0	60	0.5127	0.4702

Framework Versions

• Python: 3.9.13
• 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}
}