yudude/all-mpnet-base-v2-incident-similarity-tuned

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("yudude/all-mpnet-base-v2-sts")
# Run inference
sentences = [
    " - PTP Unlocked|Reported by & Contact # DU Health Check\nImpact: UE's will roam What groups are engaged: NOCoE\nFull issue description: -PTP Unlocked",
    'DU Health reported PTP unlocked',
    'DU PTP unlocked',
]
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]

Evaluation

Metrics

Semantic Similarity

• Dataset: sts-dev
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8503
spearman_cosine	0.8647
pearson_manhattan	0.8611
spearman_manhattan	0.8633
pearson_euclidean	0.8628
spearman_euclidean	0.8647
pearson_dot	0.8503
spearman_dot	0.8647
pearson_max	0.8628
spearman_max	0.8647

Training Details

Training Dataset

csv

• Dataset: csv
• Size: 60 training samples
• Columns: description, search_key, and label
• Approximate statistics based on the first 60 samples:

  	description	search_key	label
  type	string	string	float
  details	min: 20 tokens mean: 143.83 tokens max: 384 tokens	min: 5 tokens mean: 8.75 tokens max: 13 tokens	min: 0.9 mean: 0.95 max: 0.99

• Samples:

  description	search_key	label
  UE can not camp on network (drive test)	RU Healthcheck is okay	Network drive test shows UE cannot attach
  Samsung Alert : UADPF: 12345 (AAA) - service-off at /0725C-NR	UADPF Service off issue	0.95
  Samsung Alert : UADPF: 12345 (AAA) - - service-off at 0725C-NR	Vendor UADPF service off issue	0.94

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Evaluation Dataset

csv

• Dataset: csv
• Size: 12 evaluation samples
• Columns: description, search_key, and label
• Approximate statistics based on the first 12 samples:

  	description	search_key	label
  type	string	string	float
  details	min: 32 tokens mean: 71.67 tokens max: 109 tokens	min: 5 tokens mean: 7.92 tokens max: 11 tokens	min: 0.9 mean: 0.95 max: 0.99

• Samples:

  description	search_key	label
  Temperature Sensor Fault ALERT		with Temperature: Max cell ST1 29.4
  - PTP Unlocked	Reported by & Contact # DU Health Check Impact: UE's will roam Bridge: https://meet.google.com/oab-hmxd-qsa What groups are engaged: NOCoE Full issue description: -PTP Unlocked	Precision Time Protocol (PTP) unlocked
  - PTP Unlocked	Reported by & Contact # DU Health Check Impact: UE's will roam Bridge: https://meet.google.com/oab-hmxd-qsa What groups are engaged: NOCoE Full issue description: -PTP Unlocked	DU PTP unlocked

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 4
• per_device_eval_batch_size: 4
• learning_rate: 2e-05
• num_train_epochs: 5
• warmup_ratio: 0.1
• fp16: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 4
• per_device_eval_batch_size: 4
• 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: 2e-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: 5
• 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: 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: 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
• eval_use_gather_object: False
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	sts-dev_spearman_cosine
0.2667	4	0.2285	0.1834	0.8813
0.5333	8	0.1028	0.0760	0.8815
0.8	12	0.0409	0.0240	0.8803
1.0667	16	0.0235	0.0080	0.8781
1.3333	20	0.0077	0.0023	0.8750
1.6	24	0.0031	0.0010	0.8721
1.8667	28	0.0009	0.0006	0.8697
2.1333	32	0.0006	0.0006	0.8678
2.4	36	0.0006	0.0006	0.8667
2.6667	40	0.0009	0.0006	0.8660
2.9333	44	0.0004	0.0006	0.8654
3.2	48	0.0007	0.0006	0.8651
3.4667	52	0.0006	0.0006	0.8649
3.7333	56	0.0005	0.0006	0.8648
4.0	60	0.0003	0.0006	0.8647
4.2667	64	0.0007	0.0006	0.8647
4.5333	68	0.0005	0.0006	0.8647
4.8	72	0.0006	0.0006	0.8647

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.2.1
• Transformers: 4.44.2
• PyTorch: 2.5.0+cu121
• Accelerate: 0.34.2
• Datasets: 3.1.0
• 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",
}