Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "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
+}

README.md

@@ -0,0 +1,510 @@
+---
+language:
+- en
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- loss:CosineSimilarityLoss
+base_model: google-bert/bert-base-uncased
+metrics:
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+widget:
+- source_sentence: A woman is dancing.
+  sentences:
+  - An audience watches a girl dance.
+  - A man is outside on a July day.
+  - A man is cutting up carrots.
+- source_sentence: A man shoots a man.
+  sentences:
+  - The man is aiming a gun.
+  - A helicopter flies over water.
+  - a dog trots through the grass.
+- source_sentence: A man is spitting.
+  sentences:
+  - A man is crying.
+  - A helicopter flies over water.
+  - A slow loris hanging on a cord.
+- source_sentence: A boy is vacuuming.
+  sentences:
+  - A little boy is vacuuming the floor.
+  - A guy is playing an instrument.
+  - A woman equestrian riding a horse.
+- source_sentence: A woman is reading.
+  sentences:
+  - A woman is writing something.
+  - A man is standing in the rain.
+  - A man slices an onion.
+pipeline_tag: sentence-similarity
+co2_eq_emissions:
+  emissions: 4.738044659547021
+  energy_consumed: 0.012189401288254294
+  source: codecarbon
+  training_type: fine-tuning
+  on_cloud: false
+  cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
+  ram_total_size: 31.777088165283203
+  hours_used: 0.058
+  hardware_used: 1 x NVIDIA GeForce RTX 3090
+model-index:
+- name: SentenceTransformer based on google-bert/bert-base-uncased
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test
+      type: sts-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.8682431647858876
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8703313606188837
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8385159885167599
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8435007318066774
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8391102057706885
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8441165556372876
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8140605796498762
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8174591525223206
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8682431647858876
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8703313606188837
+      name: Spearman Max
+    - type: pearson_cosine
+      value: 0.8418519780467144
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8363102079867478
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8282641539296681
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8261442750405601
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8279900369159026
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8258841934048688
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.7681509901549408
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.757455580460212
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8418519780467144
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8363102079867478
+      name: Spearman Max
+---
+
+# SentenceTransformer based on google-bert/bert-base-uncased
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) 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:** [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) <!-- at revision 86b5e0934494bd15c9632b12f734a8a67f723594 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb)
+- **Language:** en
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (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:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("tomaarsen/bert-base-uncased-augmentation-indomain-nlpaug-sts")
+# Run inference
+sentences = [
+    'A woman is reading.',
+    'A woman is writing something.',
+    'A man is standing in the rain.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+* Dataset: `sts-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8682     |
+| **spearman_cosine** | **0.8703** |
+| pearson_manhattan   | 0.8385     |
+| spearman_manhattan  | 0.8435     |
+| pearson_euclidean   | 0.8391     |
+| spearman_euclidean  | 0.8441     |
+| pearson_dot         | 0.8141     |
+| spearman_dot        | 0.8175     |
+| pearson_max         | 0.8682     |
+| spearman_max        | 0.8703     |
+
+#### Semantic Similarity
+* Dataset: `sts-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8419     |
+| **spearman_cosine** | **0.8363** |
+| pearson_manhattan   | 0.8283     |
+| spearman_manhattan  | 0.8261     |
+| pearson_euclidean   | 0.828      |
+| spearman_euclidean  | 0.8259     |
+| pearson_dot         | 0.7682     |
+| spearman_dot        | 0.7575     |
+| pearson_max         | 0.8419     |
+| spearman_max        | 0.8363     |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### sentence-transformers/stsb
+
+* Dataset: [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [d999f12](https://huggingface.co/datasets/sentence-transformers/stsb/tree/d999f12281623b0925506817d9bd85e88289218a)
+* Size: 11,498 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                        | sentence2                                                                        | score                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           | float                                                          |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 10.0 tokens</li><li>max: 28 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 9.95 tokens</li><li>max: 25 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.54</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                  | sentence2                                                             | score             |
+  |:-----------------------------------------------------------|:----------------------------------------------------------------------|:------------------|
+  | <code>A plane is taking off.</code>                        | <code>An air plane is taking off.</code>                              | <code>1.0</code>  |
+  | <code>A man is playing a large flute.</code>               | <code>A man is playing a flute.</code>                                | <code>0.76</code> |
+  | <code>A man is spreading shreded cheese on a pizza.</code> | <code>A man is spreading shredded cheese on an uncooked pizza.</code> | <code>0.76</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### sentence-transformers/stsb
+
+* Dataset: [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [d999f12](https://huggingface.co/datasets/sentence-transformers/stsb/tree/d999f12281623b0925506817d9bd85e88289218a)
+* Size: 1,500 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                        | sentence2                                                                         | score                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                            | float                                                          |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 15.1 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.11 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.47</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                         | sentence2                                             | score             |
+  |:--------------------------------------------------|:------------------------------------------------------|:------------------|
+  | <code>A man with a hard hat is dancing.</code>    | <code>A man wearing a hard hat is dancing.</code>     | <code>1.0</code>  |
+  | <code>A young child is riding a horse.</code>     | <code>A child is riding a horse.</code>               | <code>0.95</code> |
+  | <code>A man is feeding a mouse to a snake.</code> | <code>The man is feeding a mouse to the snake.</code> | <code>1.0</code>  |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `fp16`: True
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: False
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `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`: 1
+- `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
+- `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`: None
+- `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_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | loss   | sts-test_spearman_cosine |
+|:------:|:----:|:-------------:|:------:|:------------------------:|
+| 0.1391 | 100  | 0.0572        | 0.0427 | 0.8222                   |
+| 0.2782 | 200  | 0.0316        | 0.0342 | 0.8450                   |
+| 0.4172 | 300  | 0.0276        | 0.0324 | 0.8621                   |
+| 0.5563 | 400  | 0.0246        | 0.0300 | 0.8661                   |
+| 0.6954 | 500  | 0.0206        | 0.0288 | 0.8650                   |
+| 0.8345 | 600  | 0.0186        | 0.0301 | 0.8696                   |
+| 0.9736 | 700  | 0.0185        | 0.0286 | 0.8703                   |
+| 1.0    | 719  | -             | -      | 0.8363                   |
+
+
+### Environmental Impact
+Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
+- **Energy Consumed**: 0.012 kWh
+- **Carbon Emitted**: 0.005 kg of CO2
+- **Hours Used**: 0.058 hours
+
+### Training Hardware
+- **On Cloud**: No
+- **GPU Model**: 1 x NVIDIA GeForce RTX 3090
+- **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
+- **RAM Size**: 31.78 GB
+
+### Framework Versions
+- Python: 3.11.6
+- Sentence Transformers: 3.0.0.dev0
+- Transformers: 4.41.0.dev0
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.26.1
+- Datasets: 2.18.0
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@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",
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.0.dev0",
+    "transformers": "4.41.0.dev0",
+    "pytorch": "2.3.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d908ab1874e2824ea4024b9e8f1fb0622a1f5304869a9e44e4039b09c90ff27b
+size 437951328

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}