sobamchan/roberta-base-mean-softmax-450

SentenceTransformer based on FacebookAI/roberta-base

This is a sentence-transformers model finetuned from FacebookAI/roberta-base on the all-nli 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: FacebookAI/roberta-base
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • all-nli
• Language: en

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: RobertaModel 
  (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("sentence_transformers_model_id")
# Run inference
sentences = [
    'The little boy is jumping into a puddle on the street.',
    'The boy is outside.',
    'The dog is playing with a ball.',
]
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

all-nli

• Dataset: all-nli at d482672
• Size: 942,069 training samples
• Columns: premise, hypothesis, and label
• Approximate statistics based on the first 1000 samples:

  	premise	hypothesis	label
  type	string	string	int
  details	min: 6 tokens mean: 17.4 tokens max: 50 tokens	min: 5 tokens mean: 10.69 tokens max: 31 tokens	0: ~33.40% 1: ~33.30% 2: ~33.30%

• Samples:

  premise	hypothesis	label
  A person on a horse jumps over a broken down airplane.	A person is training his horse for a competition.	1
  A person on a horse jumps over a broken down airplane.	A person is at a diner, ordering an omelette.	2
  A person on a horse jumps over a broken down airplane.	A person is outdoors, on a horse.	0

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Evaluation Dataset

all-nli

• Dataset: all-nli at d482672
• Size: 19,657 evaluation samples
• Columns: premise, hypothesis, and label
• Approximate statistics based on the first 1000 samples:

  	premise	hypothesis	label
  type	string	string	int
  details	min: 6 tokens mean: 18.46 tokens max: 60 tokens	min: 5 tokens mean: 10.57 tokens max: 24 tokens	0: ~33.10% 1: ~33.30% 2: ~33.60%

• Samples:

  premise	hypothesis	label
  Two women are embracing while holding to go packages.	The sisters are hugging goodbye while holding to go packages after just eating lunch.	1
  Two women are embracing while holding to go packages.	Two woman are holding packages.	0
  Two women are embracing while holding to go packages.	The men are fighting outside a deli.	2

• 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: 128
• per_device_eval_batch_size: 128
• learning_rate: 1e-05
• 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: 128
• per_device_eval_batch_size: 128
• 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: 1e-05
• 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
• max_steps: -1
• 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: 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: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss
0.0007	5	-	4.4994
0.0014	10	-	4.4981
0.0020	15	-	4.4960
0.0027	20	-	4.4930
0.0034	25	-	4.4890
0.0041	30	-	4.4842
0.0048	35	-	4.4784
0.0054	40	-	4.4716
0.0061	45	-	4.4636
0.0068	50	-	4.4543
0.0075	55	-	4.4438
0.0082	60	-	4.4321
0.0088	65	-	4.4191
0.0095	70	-	4.4042
0.0102	75	-	4.3875
0.0109	80	-	4.3686
0.0115	85	-	4.3474
0.0122	90	-	4.3236
0.0129	95	-	4.2968
0.0136	100	4.4995	4.2666
0.0143	105	-	4.2326
0.0149	110	-	4.1947
0.0156	115	-	4.1516
0.0163	120	-	4.1029
0.0170	125	-	4.0476
0.0177	130	-	3.9850
0.0183	135	-	3.9162
0.0190	140	-	3.8397
0.0197	145	-	3.7522
0.0204	150	-	3.6521
0.0211	155	-	3.5388
0.0217	160	-	3.4114
0.0224	165	-	3.2701
0.0231	170	-	3.1147
0.0238	175	-	2.9471
0.0245	180	-	2.7710
0.0251	185	-	2.5909
0.0258	190	-	2.4127
0.0265	195	-	2.2439
0.0272	200	3.6918	2.0869
0.0279	205	-	1.9477
0.0285	210	-	1.8274
0.0292	215	-	1.7156
0.0299	220	-	1.6211
0.0306	225	-	1.5416
0.0312	230	-	1.4732
0.0319	235	-	1.4176
0.0326	240	-	1.3702
0.0333	245	-	1.3269
0.0340	250	-	1.2892
0.0346	255	-	1.2563
0.0353	260	-	1.2281
0.0360	265	-	1.2024
0.0367	270	-	1.1796
0.0374	275	-	1.1601
0.0380	280	-	1.1428
0.0387	285	-	1.1271
0.0394	290	-	1.1129
0.0401	295	-	1.1002
0.0408	300	1.7071	1.0876
0.0414	305	-	1.0761
0.0421	310	-	1.0658
0.0428	315	-	1.0554
0.0435	320	-	1.0458
0.0442	325	-	1.0365
0.0448	330	-	1.0276
0.0455	335	-	1.0180
0.0462	340	-	1.0086
0.0469	345	-	0.9996
0.0476	350	-	0.9920
0.0482	355	-	0.9846
0.0489	360	-	0.9782
0.0496	365	-	0.9715
0.0503	370	-	0.9641
0.0510	375	-	0.9572
0.0516	380	-	0.9503
0.0523	385	-	0.9444
0.0530	390	-	0.9384
0.0537	395	-	0.9329
0.0543	400	1.2083	0.9276
0.0550	405	-	0.9220
0.0557	410	-	0.9166
0.0564	415	-	0.9114
0.0571	420	-	0.9062
0.0577	425	-	0.9006
0.0584	430	-	0.8960
0.0591	435	-	0.8931
0.0598	440	-	0.8904
0.0605	445	-	0.8865
0.0611	450	-	0.8822

Framework Versions

• Python: 3.12.8
• Sentence Transformers: 3.4.1
• Transformers: 4.48.3
• PyTorch: 2.2.0+cu121
• Accelerate: 1.3.0
• Datasets: 3.2.0
• Tokenizers: 0.21.0

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}
}