tranhuudan-fullstack-ai-engineer/final_model_main

SentenceTransformer based on huudan123/model_stage2

This is a sentence-transformers model finetuned from huudan123/model_stage2. 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: huudan123/model_stage2
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 tokens
• 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': 512, '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})
)

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("huudan123/final_model_main")
# Run inference
sentences = [
    'Thật nực cười khi tôi thấy các hãng hàng không đôi khi yêu cầu tắt những thứ này.',
    'Tôi rất tiếc khi nghe điều này Kelly.',
    'Hàng loạt các cuộc tấn công Iraq giết chết ít nhất sáu người',
]
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-evaluator
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.0529
spearman_cosine	0.3363
pearson_manhattan	0.1549
spearman_manhattan	0.3374
pearson_euclidean	0.1553
spearman_euclidean	0.3361
pearson_dot	0.055
spearman_dot	0.0579
pearson_max	0.1553
spearman_max	0.3374

Training Details

Training Hyperparameters

Non-Default Hyperparameters

• overwrite_output_dir: True
• eval_strategy: epoch
• per_device_train_batch_size: 128
• per_device_eval_batch_size: 128
• learning_rate: 2e-05
• num_train_epochs: 30
• warmup_ratio: 0.1
• fp16: True
• load_best_model_at_end: True
• gradient_checkpointing: True

All Hyperparameters

Click to expand

• overwrite_output_dir: True
• do_predict: False
• eval_strategy: epoch
• 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
• 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: 30
• 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: 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
• 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: True
• 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
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	sts-evaluator_spearman_max
0	0	-	-	0.6240
0.6234	500	0.0186	-	-
1.0	802	-	0.0215	0.7037
1.2469	1000	0.0071	-	-
1.8703	1500	0.0063	-	-
2.0	1604	-	0.0216	0.7184
2.4938	2000	0.0057	-	-
3.0	2406	-	0.0200	0.7298
3.1172	2500	0.0055	-	-
3.7406	3000	0.0052	-	-
4.0	3208	-	0.0175	0.7733
4.3641	3500	0.005	-	-
4.9875	4000	0.005	-	-
5.0	4010	-	0.0144	0.7820
5.6110	4500	0.0046	-	-
6.0	4812	-	0.0135	0.7839
6.2344	5000	0.0045	-	-
6.8579	5500	0.0043	-	-
7.0	5614	-	0.0132	0.7867
7.4813	6000	0.0041	-	-
8.0	6416	-	0.0113	0.7894
8.1047	6500	0.004	-	-
8.7282	7000	0.0037	-	-
9.0	7218	-	0.0105	0.7845
9.3516	7500	0.0036	-	-
9.9751	8000	0.0037	-	-
10.0	8020	-	0.0096	0.7963
10.5985	8500	0.0074	-	-
11.0	8822	-	0.2441	0.3470
11.2219	9000	0.0065	-	-
11.8454	9500	0.0063	-	-
12.0	9624	-	0.2443	0.2869
12.4688	10000	0.0062	-	-
13.0	10426	-	0.2446	0.2917
13.0923	10500	0.0061	-	-
13.7157	11000	0.006	-	-
14.0	11228	-	0.2446	0.3374

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.0.1
• Transformers: 4.42.4
• PyTorch: 2.3.1+cu121
• Accelerate: 0.33.0
• Datasets: 2.20.0
• 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",
}