srikarvar/fine_tuned_model_12

SentenceTransformer based on srikarvar/fine_tuned_model_5

This is a sentence-transformers model finetuned from srikarvar/fine_tuned_model_5 on the json dataset. 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: srikarvar/fine_tuned_model_5
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 384 tokens
• Similarity Function: Cosine Similarity
• Training Dataset:
  • json

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': 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.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("srikarvar/fine_tuned_model_12")
# Run inference
sentences = [
    'The `num_services` method gives the quantity of services in the garage.',
    'The `num_services` method returns the number of services in the garage.',
    'It returns the number of entries in the dataset.',
]
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

Binary Classification

• Dataset: pair-class-dev
• Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.9821
cosine_accuracy_threshold	0.9923
cosine_f1	0.991
cosine_f1_threshold	0.9923
cosine_precision	1.0
cosine_recall	0.9821
cosine_ap	1.0
dot_accuracy	0.9821
dot_accuracy_threshold	0.9923
dot_f1	0.991
dot_f1_threshold	0.9923
dot_precision	1.0
dot_recall	0.9821
dot_ap	1.0
manhattan_accuracy	0.9821
manhattan_accuracy_threshold	1.8806
manhattan_f1	0.991
manhattan_f1_threshold	1.8806
manhattan_precision	1.0
manhattan_recall	0.9821
manhattan_ap	1.0
euclidean_accuracy	0.9821
euclidean_accuracy_threshold	0.1216
euclidean_f1	0.991
euclidean_f1_threshold	0.1216
euclidean_precision	1.0
euclidean_recall	0.9821
euclidean_ap	1.0
max_accuracy	0.9821
max_accuracy_threshold	1.8806
max_f1	0.991
max_f1_threshold	1.8806
max_precision	1.0
max_recall	0.9821
max_ap	1.0

Binary Classification

• Dataset: pair-class-test
• Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.9821
cosine_accuracy_threshold	0.9923
cosine_f1	0.991
cosine_f1_threshold	0.9923
cosine_precision	1.0
cosine_recall	0.9821
cosine_ap	1.0
dot_accuracy	0.9821
dot_accuracy_threshold	0.9923
dot_f1	0.991
dot_f1_threshold	0.9923
dot_precision	1.0
dot_recall	0.9821
dot_ap	1.0
manhattan_accuracy	0.9821
manhattan_accuracy_threshold	1.8806
manhattan_f1	0.991
manhattan_f1_threshold	1.8806
manhattan_precision	1.0
manhattan_recall	0.9821
manhattan_ap	1.0
euclidean_accuracy	0.9821
euclidean_accuracy_threshold	0.1216
euclidean_f1	0.991
euclidean_f1_threshold	0.1216
euclidean_precision	1.0
euclidean_recall	0.9821
euclidean_ap	1.0
max_accuracy	0.9821
max_accuracy_threshold	1.8806
max_f1	0.991
max_f1_threshold	1.8806
max_precision	1.0
max_recall	0.9821
max_ap	1.0

Training Details

Training Dataset

json

• Dataset: json
• Size: 560 training samples
• Columns: label, sentence2, and sentence1
• Approximate statistics based on the first 560 samples:

  	label	sentence2	sentence1
  type	int	string	string
  details	1: 100.00%	min: 9 tokens mean: 30.18 tokens max: 98 tokens	min: 8 tokens mean: 30.0 tokens max: 98 tokens

• Samples:

  label	sentence2	sentence1
  1	It is not available in v2.10.0.	No, it doesn't exist in v2.10.0.
  1	You can become a member of the research forum and pose questions to the AI community.	You can join and ask questions in the AI research forum.
  1	No information regarding initializing a project for PyTorch is included in the guide.	The guide does not provide information on how to initialize a project for PyTorch.

• Loss: OnlineContrastiveLoss

Evaluation Dataset

json

• Dataset: json
• Size: 560 evaluation samples
• Columns: label, sentence2, and sentence1
• Approximate statistics based on the first 560 samples:

  	label	sentence2	sentence1
  type	int	string	string
  details	1: 100.00%	min: 15 tokens mean: 32.29 tokens max: 82 tokens	min: 14 tokens mean: 31.96 tokens max: 82 tokens

• Samples:

  label	sentence2	sentence1
  1	The how-to guides for the platform include instructions for Setup, Processing, Streaming, TensorFlow integration, PyTorch integration, Caching, Cloud storage, Indexing, Analytics, and Data Pipelines.	The how-to guides for the platform include Setup, Processing, Streaming, TensorFlow integration, PyTorch integration, Cache management, Cloud storage, Search index, Analytics, and Data Pipelines.
  1	In the absence of a model script, all files in the supported formats will be loaded. However, if a model script is present, it will be downloaded and executed in order to download and prepare the model.	If there’s no model script, all the files in the supported formats are loaded. If there’s a model script, it is downloaded and executed to download and prepare the model.
  1	React, Angular, and Vue are compatible with the Plugin library.	The Plugin library can be used with React, Angular, and Vue.

• Loss: OnlineContrastiveLoss

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• gradient_accumulation_steps: 2
• num_train_epochs: 4
• warmup_ratio: 0.1
• load_best_model_at_end: True
• optim: adamw_torch_fused
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: epoch
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 2
• eval_accumulation_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: 1.0
• num_train_epochs: 4
• 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: True
• 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_fused
• 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
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	pair-class-dev_max_ap	pair-class-test_max_ap
0	0	-	-	1.0	-
1.0	8	-	0.0028	1.0	-
1.25	10	0.1425	-	-	-
2.0	16	-	0.0003	1.0	-
2.5	20	0.002	-	-	-
3.0	24	-	0.0001	1.0	-
3.75	30	0.0008	-	-	-
4.0	32	-	0.0001	1.0	1.0

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.1.0
• Transformers: 4.41.2
• PyTorch: 2.1.2+cu121
• Accelerate: 0.34.2
• Datasets: 2.19.1
• 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",
}