hyrinmansoor/changAI-nomic-embed-text-v1.5-finetuned

SentenceTransformer

This is a sentence-transformers model trained. 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
• Maximum Sequence Length: 8192 tokens
• Output Dimensionality: 768 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': 8192, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
  (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 = [
    'Who is responsible for the crane in sharjah?',
    '[FIELD] custodian | [TABLE] tabAsset',
    '[TABLE] tabQuality Inspection | desc: Quality Inspection Record',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000,  0.6763, -0.0788],
#         [ 0.6763,  1.0000, -0.0196],
#         [-0.0788, -0.0196,  1.0000]])

Evaluation

Metrics

Semantic Similarity

• Dataset: eval
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	nan
spearman_cosine	nan

Training Details

Training Dataset

Unnamed Dataset

• Size: 24,529 training samples
• Columns: sentence1 and sentence2
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2
  type	string	string
  details	min: 5 tokens mean: 11.98 tokens max: 28 tokens	min: 7 tokens mean: 16.47 tokens max: 41 tokens

• Samples:

  sentence1	sentence2
  which customers have pending follow-ups scheduled for today?	[FIELD] status | [TABLE] tabLead | desc: Filters for leads requiring follow-up
  Give me all milestones due this week across active projects.	[TABLE] tabMilestone Tracker | desc: Milestone tracking
  show me cement bags sent to site last week	[FIELD] posting_date | [TABLE] tabDelivery Note | desc: Filters for last week.

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• learning_rate: 2e-05
• num_train_epochs: 5
• warmup_ratio: 0.1
• warmup_steps: 0.1
• fp16: True
• dataloader_drop_last: True
• dataloader_num_workers: 2
• load_best_model_at_end: True

All Hyperparameters

Click to expand

• do_predict: False
• eval_strategy: epoch
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• 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: None
• warmup_ratio: 0.1
• warmup_steps: 0.1
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• enable_jit_checkpoint: False
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• use_cpu: False
• seed: 42
• data_seed: None
• bf16: False
• fp16: True
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: -1
• ddp_backend: None
• debug: []
• dataloader_drop_last: True
• dataloader_num_workers: 2
• dataloader_prefetch_factor: None
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: True
• ignore_data_skip: False
• fsdp: []
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• parallelism_config: None
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch_fused
• optim_args: None
• group_by_length: False
• length_column_name: length
• project: huggingface
• trackio_space_id: trackio
• 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
• push_to_hub: False
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• hub_revision: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_for_metrics: []
• eval_do_concat_batches: True
• auto_find_batch_size: False
• full_determinism: False
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• include_num_input_tokens_seen: no
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: True
• use_cache: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	eval_spearman_cosine
0.0653	50	1.4199	-
0.1305	100	1.1590	-
0.1958	150	1.1426	-
0.2611	200	0.9971	-
0.3264	250	0.9385	-
0.3916	300	0.8183	-
0.4569	350	0.8028	-
0.5222	400	0.7773	-
0.5875	450	0.7353	-
0.6527	500	0.7948	-
0.7180	550	0.7055	-
0.7833	600	0.6792	-
0.8486	650	0.7091	-
0.9138	700	0.6767	-
0.9791	750	0.6608	-
1.0	766	-	nan
1.0444	800	0.5842	-
1.1097	850	0.5622	-
1.1749	900	0.5592	-
1.2402	950	0.5860	-
1.3055	1000	0.5701	-
1.3708	1050	0.5920	-
1.4360	1100	0.5430	-
1.5013	1150	0.5260	-
1.5666	1200	0.5249	-
1.6319	1250	0.5350	-
1.6971	1300	0.5543	-
1.7624	1350	0.5162	-
1.8277	1400	0.5190	-
1.8930	1450	0.5258	-
1.9582	1500	0.5090	-
2.0	1532	-	nan
2.0235	1550	0.5103	-
2.0888	1600	0.4416	-
2.1540	1650	0.4374	-
2.2193	1700	0.4092	-
2.2846	1750	0.4072	-
2.3499	1800	0.4321	-
2.4151	1850	0.4519	-
2.4804	1900	0.3977	-
2.5457	1950	0.4490	-
2.6110	2000	0.4542	-
2.6762	2050	0.3865	-
2.7415	2100	0.4113	-
2.8068	2150	0.4366	-
2.8721	2200	0.3925	-
2.9373	2250	0.4150	-
3.0	2298	-	nan
3.0026	2300	0.4228	-
3.0679	2350	0.3294	-
3.1332	2400	0.3256	-
3.1984	2450	0.3555	-
3.2637	2500	0.3770	-
3.3290	2550	0.3339	-
3.3943	2600	0.3764	-
3.4595	2650	0.3544	-
3.5248	2700	0.3567	-
3.5901	2750	0.3539	-
3.6554	2800	0.3585	-
3.7206	2850	0.3224	-
3.7859	2900	0.3383	-
3.8512	2950	0.3584	-
3.9164	3000	0.3584	-
3.9817	3050	0.3108	-
4.0	3064	-	nan
4.0470	3100	0.3361	-
4.1123	3150	0.3048	-
4.1775	3200	0.3154	-
4.2428	3250	0.2866	-
4.3081	3300	0.2981	-
4.3734	3350	0.3149	-
4.4386	3400	0.3128	-
4.5039	3450	0.3237	-
4.5692	3500	0.3054	-
4.6345	3550	0.3015	-
4.6997	3600	0.2885	-
4.7650	3650	0.2745	-
4.8303	3700	0.3062	-
4.8956	3750	0.2996	-
4.9608	3800	0.3058	-
5.0	3830	-	nan

Framework Versions

• Python: 3.12.12
• Sentence Transformers: 5.2.3
• Transformers: 5.0.0
• PyTorch: 2.10.0+cu128
• Accelerate: 1.12.0
• Datasets: 4.0.0
• Tokenizers: 0.22.2

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}
}