This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. It maps sentences & paragraphs to a 384-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-MiniLM-L6-v2
Maximum Sequence Length: 256 tokens
Output Dimensionality: 384 dimensions
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': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, '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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("dataera2013/midterm-small-model-2")
# Run inference
sentences = [
    'QUESTION #1\\n',
    'On the other hand, our believer highlights the positive aspects and opportunities for growth in this space. Increased awareness and education about healthy social media habits, the potential for community support, the availability of digital wellbeing tools, positive content creation, and the therapeutic benefits of online platforms all offer avenues for promoting mental health and wellbeing.\n\n[CONCLUSION]',
    "[INTRO]\n\nWelcome to the Health Innovations podcast, where we explore the latest advances in medical research. Today, we dive into the topic of the most promising breakthroughs in cancer treatment. We'll hear from two perspectives - one skeptical and one optimistic - to provide a balanced view on the opportunities and challenges in this field.\n\n[SKEPTIC PERSPECTIVE]\n\nWhile the advancements in medical research for cancer treatment are promising, we must acknowledge the hurdles that come with them. Immunotherapy faces issues with response variability and severe side effects that need careful management. Clinical trials may not always represent the diversity of the population, and long-term effects can differ from short-term benefits.",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

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

Evaluation

Metrics

Information Retrieval

Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.5417
cosine_accuracy@3	0.625
cosine_accuracy@5	0.7083
cosine_accuracy@10	0.9167
cosine_precision@1	0.5417
cosine_precision@3	0.2083
cosine_precision@5	0.1417
cosine_precision@10	0.0917
cosine_recall@1	0.5417
cosine_recall@3	0.625
cosine_recall@5	0.7083
cosine_recall@10	0.9167
cosine_ndcg@10	0.6893
cosine_mrr@10	0.622
cosine_map@100	0.6293

Training Details

Training Dataset

Unnamed Dataset

Size: 64 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 64 samples:
sentence_0 sentence_1
type string string
details
min: 7 tokens
mean: 74.97 tokens
max: 200 tokens
min: 72 tokens
mean: 110.72 tokens
max: 140 tokens

Samples:

sentence_0	sentence_1
`QUESTION #1\n`	Tech & Science Podcast Blog[object Object][object Object][object Object][object Object]Tech & Science Podcast Transcripts[object Object][object Object]Are Humans Dumb?[object Object]Topic: are humans dumb[object Object][object Object][INTRO][object Object][object Object]Welcome to our podcast where we delve into the intriguing question: Are humans dumb? Today, we will explore this topic from two contrasting perspectives - skepticism and belief. Let's navigate through the complexities of human cognition and behavior to uncover the opportunities, risks, key questions, and potential solutions surrounding this thought-provoking issue.[object Object][object Object][SKEPTIC PERSPECTIVE]
QUESTION #2\n...\n\nContext:\nTech & Science Podcast Blog\n\n\n\nTech & Science Podcast Transcripts\n\nAre Humans Dumb?\nTopic: are humans dumb\n\n[INTRO]\n\nWelcome to our podcast where we delve into the intriguing question: Are humans dumb? Today, we will explore this topic from two contrasting perspectives - skepticism and belief. Let's navigate through the complexities of human cognition and behavior to uncover the opportunities, risks, key questions, and potential solutions surrounding this thought-provoking issue.\n\n[SKEPTIC PERSPECTIVE]\n", additional_kwargs={}, response_metadata={})]	Tech & Science Podcast Blog[object Object][object Object][object Object][object Object]Tech & Science Podcast Transcripts[object Object][object Object]Are Humans Dumb?[object Object]Topic: are humans dumb[object Object][object Object][INTRO][object Object][object Object]Welcome to our podcast where we delve into the intriguing question: Are humans dumb? Today, we will explore this topic from two contrasting perspectives - skepticism and belief. Let's navigate through the complexities of human cognition and behavior to uncover the opportunities, risks, key questions, and potential solutions surrounding this thought-provoking issue.[object Object][object Object][SKEPTIC PERSPECTIVE]
`QUESTION #1\n`	Let's start with the skeptic's viewpoint. When examining the information related to human intelligence, it's essential to consider the evolutionary perspective. The study suggesting a decline in human cognition over time raises crucial questions about intelligence trends. However, we must critically assess the study's methodology and sample size to validate its findings. How can we ensure the accuracy of such studies and their implications for human cognition?[object Object][object Object][Transition to Subjectivity in Judging Intelligence]

Loss: MatryoshkaLoss with these parameters:
json
1{ 2 "loss": "MultipleNegativesRankingLoss", 3 "matryoshka_dims": [ 4 384, 5 192, 6 96, 7 48 8 ], 9 "matryoshka_weights": [ 10 1, 11 1, 12 1, 13 1 14 ], 15 "n_dims_per_step": -1 16}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 5
per_device_eval_batch_size: 5
num_train_epochs: 5
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 5
per_device_eval_batch_size: 5
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: 5
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: None
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
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
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	cosine_ndcg@10
1.0	13	0.6893
2.0	26	0.6893
3.0	39	0.6893
3.8462	50	0.6893
4.0	52	0.6893
5.0	65	0.6893
1.0	13	0.6893
2.0	26	0.6893
3.0	39	0.6893
3.8462	50	0.6893
4.0	52	0.6893
5.0	65	0.6893

Framework Versions

Python: 3.13.1
Sentence Transformers: 3.4.1
Transformers: 4.48.3
PyTorch: 2.6.0+cu124
Accelerate: 1.3.0
Datasets: 3.2.0
Tokenizers: 0.21.0

Citation

BibTeX

Sentence Transformers

bibtex

@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",
}

MatryoshkaLoss

bibtex

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

bibtex

@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}
}

	sentence_0	sentence_1
type	string	string
details	min: 7 tokens mean: 74.97 tokens max: 200 tokens	min: 72 tokens mean: 110.72 tokens max: 140 tokens