aisuko/encoder-L6-V2

1_Pooling/config.json

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

README.md

@@ -0,0 +1,761 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:4984
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/all-MiniLM-L6-v2
+widget:
+- source_sentence: '<think>
+
+    Let’s think through this step by step
+
+    rp = 500/month
+
+    fp = 10/day
+
+    lp = 60/lesson
+
+    lpw = 2 lessons/week
+
+    yp = 12 months/year
+
+    total = (500 × 12) + (10 × 365) + (60 × 2 × 52)
+
+    total = 6000 + 3650 + 6240
+
+    total = 15890
+
+    </think>
+
+    \boxed{15890}'
+  sentences:
+  - '<think>
+
+    Let’s think through this step by step
+
+    rp = 500/month
+
+    fp = 10/day
+
+    lp = 60/lesson
+
+    tp = (500 × 12) + (10 × 365) + (60 × 2 × 52)
+
+    tp = 6000 + 3650 + 6240
+
+    tp = 15890
+
+    </think>
+
+    \boxed{15890}'
+  - '<think>
+
+    Let’s think through this step by step
+
+    h1 = 500 ft
+
+    h2 = 2 * h1 = 2 * 500 = 1000 ft
+
+    Total height = h1 + h2 = 500 + 1000 = 1500 ft
+
+    </think>
+
+    \boxed{1500}'
+  - '<think>
+
+    Let’s think through this step by step
+
+    fc = 200
+
+    lc = 500
+
+    dc = 500 × 0.8 = 400
+
+    nc = 200 - 50 = 150
+
+    tc = 150 + 400 = 550
+
+    </think>
+
+    \boxed{550}'
+- source_sentence: '<think>
+
+    Let’s think through this step by step
+
+    s = 5 MB/song
+
+    m1 = 10 songs
+
+    m2 = 15 songs
+
+    m3 = 3 songs
+
+    total = (10 + 15 + 3) × 5
+
+    total = 28 × 5 = 140 MB
+
+    </think>
+
+    \boxed{140}'
+  sentences:
+  - '<think>
+
+    Let’s think through this step by step
+
+    s = 5 MB/song
+
+    m1 = 10 songs
+
+    m2 = 15 songs
+
+    m3 = 3 songs
+
+    Total memory = (10 + 15 + 3) × 5
+
+    Total memory = 28 × 5 = 140 MB
+
+    </think>
+
+    \boxed{140}'
+  - '<think>
+
+    Let’s think through this step by step
+
+    total_slices = 12
+
+    eaten_slices = 12 × (1/4) = 3
+
+    kept_slices = 12 - 3 = 9
+
+    </think>
+
+    \boxed{9}'
+  - '<think>
+
+    Let’s think through this step by step
+
+    Bald Mountain = 1.5 meters = 150 cm
+
+    Billy Mountain = 3.5 meters = 350 cm
+
+    Mount Pilot = 126 cm
+
+    Difference between Billy Mountain and Bald Mountain = 350 - 150 = 200 cm
+
+    Difference between Mount Pilot and Bald Mountain = 126 - 150 = -24 cm
+
+    </think>
+
+    \boxed{200}'
+- source_sentence: '<think>
+
+    Let’s think through this step by step
+
+    Strength training: 1 hour/session × 3 sessions/week = 3 hours/week
+
+    Boxing training: 1.5 hours/session × 4 sessions/week = 6 hours/week
+
+    Total training hours per week = 3 + 6 = 9 hours/week
+
+    </think>
+
+    \boxed{9}'
+  sentences:
+  - '<think>
+
+    Let’s think through this step by step
+
+    t = 5
+
+    p = 4
+
+    s = 6
+
+    r = 5 / 2 = 2.5
+
+    income = (2 × 5) + 4 + (4 × 6) + (6 × 2.5)
+
+    income = 10 + 4 + 24 + 15
+
+    income = 53
+
+    </think>
+
+    \boxed{53}'
+  - '<think>
+
+    Let’s think through this step by step
+
+    Strength training: 1 hour/session × 3 sessions/week = 3 hours/week
+
+    Boxing training: 1.5 hours/session × 4 sessions/week = 6 hours/week
+
+    Total training hours per week = 3 + 6 = 9 hours/week
+
+    </think>
+
+    \boxed{9}'
+  - '<think>
+
+    Let’s think through this step by step
+
+    Let d be the number of ducks sold
+
+    Earnings from selling chickens = 5 × 8 = 40
+
+    Earnings from selling ducks = 10d
+
+    Total earnings = 40 + 10d
+
+    Amount spent on wheelbarrow = (1/2)(40 + 10d)
+
+    Amount earned from selling wheelbarrow = 60
+
+    40 + 10d = 2(60)
+
+    10d = 80
+
+    d = 8
+
+    </think>
+
+    \boxed{8}'
+- source_sentence: '<think>
+
+    Let’s think through this step by step
+
+    up = 3 flights
+
+    down = 3 flights
+
+    total = (3 + 3) × 5 = 30 flights
+
+    </think>
+
+    \boxed{30}'
+  sentences:
+  - '<think>
+
+    Let’s think through this step by step
+
+    up = 3 flights
+
+    down = 3 flights
+
+    total = (3 + 3) × 5 = 30 flights
+
+    </think>
+
+    \boxed{30}'
+  - '<think>
+
+    Let’s think through this step by step
+
+    J = M + 10
+
+    J + 10 = 25
+
+    (M + 10) + 10 = 25
+
+    M + 20 = 25
+
+    M = 5
+
+    J = 5 + 10 = 15
+
+    Sum = 5 + 15 = 20
+
+    </think>
+
+    \boxed{20}'
+  - '<think>
+
+    Let’s think through this step by step
+
+    total_money = 7(1) + 4(5) + 2(10) + 1(20) = 7 + 20 + 20 + 20 = 67
+
+    cost = 67 - 4 = 63
+
+    pounds = 63 / 3 = 21
+
+    days = 7
+
+    average = 21 / 7 = 3
+
+    </think>
+
+    \boxed{3}'
+- source_sentence: '<think>
+
+    Let’s think through this step by step
+
+    n = 4
+
+    sp = 75
+
+    t = 36
+
+    spt = 36 / 4 = 9
+
+    op = 75 + 9 = 84
+
+    </think>
+
+    \boxed{84}'
+  sentences:
+  - '<think>
+
+    Let’s think through this step by step
+
+    Let B be Benedict''s house size
+
+    K = 10000 sq ft
+
+    K = 4B + 600
+
+    10000 = 4B + 600
+
+    4B = 9400
+
+    B = 2350 sq ft
+
+    </think>
+
+    \boxed{2350}'
+  - '<think>
+
+    Let’s think through this step by step
+
+    Total throws = 80
+
+    No pass thrown = 30% of 80 = 0.3 × 80 = 24
+
+    Sacked for a loss = 0.5 × 24 = 12
+
+    </think>
+
+    \boxed{12}'
+  - '<think>
+
+    Let’s think through this step by step
+
+    n = 4
+
+    sp = 75
+
+    t = 36
+
+    spt = t / n = 36 / 4 = 9
+
+    op = sp + spt = 75 + 9 = 84
+
+    </think>
+
+    \boxed{84}'
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev
+      type: sts-dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.8776143775032945
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8754887541943006
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test
+      type: sts-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.877613066248591
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.875487017524482
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) on the csv 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:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - csv
+<!-- - **Language:** Unknown -->
+<!-- - **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': 256, '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:
+
+```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("training")
+# Run inference
+sentences = [
+    '<think>\nLet’s think through this step by step\nn = 4\nsp = 75\nt = 36\nspt = 36 / 4 = 9\nop = 75 + 9 = 84\n</think>\n\\boxed{84}',
+    '<think>\nLet’s think through this step by step\nn = 4\nsp = 75\nt = 36\nspt = t / n = 36 / 4 = 9\nop = sp + spt = 75 + 9 = 84\n</think>\n\\boxed{84}',
+    "<think>\nLet’s think through this step by step\nLet B be Benedict's house size\nK = 10000 sq ft\nK = 4B + 600\n10000 = 4B + 600\n4B = 9400\nB = 2350 sq ft\n</think>\n\\boxed{2350}",
+]
+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]
+```
+
+<!--
+### 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
+
+* Datasets: `sts-dev` and `sts-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | sts-dev    | sts-test   |
+|:--------------------|:-----------|:-----------|
+| pearson_cosine      | 0.8776     | 0.8776     |
+| **spearman_cosine** | **0.8755** | **0.8755** |
+
+<!--
+## 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
+
+#### csv
+
+* Dataset: csv
+* Size: 4,984 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                              | positive                                                                            |
+  |:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                              |
+  | details | <ul><li>min: 34 tokens</li><li>mean: 66.41 tokens</li><li>max: 256 tokens</li></ul> | <ul><li>min: 36 tokens</li><li>mean: 67.03 tokens</li><li>max: 256 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                                                                                                                                                                                                                                                    | positive                                                                                                                                                                                                                                                                                                                                                                                                  |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code><think><br>Let’s think through this step by step<br>ht_hare = 14 inches<br>ht_camel = 24 × 14 = 336 inches<br>ht_camel_ft = 336 / 12 = 28 feet<br></think><br>\boxed{28}</code>                                                                                                                                                                                                                     | <code><think><br>Let’s think through this step by step<br>ht_hare = 14 inches<br>ht_camel = 24 * 14 = 336 inches<br>ht_camel_ft = 336 / 12 = 28 feet<br></think><br>\boxed{28}</code>                                                                                                                                                                                                                     |
+  | <code><think><br>Let’s think through this step by step<br>cpb = 5<br>sp = 90<br>pmpb = 2<br>tp = 5 × 5 = 25<br>tpmp = 5 × 2 = 10<br>profit = 90 - 25 - 10 = 55<br></think><br>\boxed{55}</code>                                                                                                                                                                                                           | <code><think><br>Let’s think through this step by step<br>cp = 5 × 5 = 25<br>sp = 90<br>p = sp - cp - (5 × 2) = 90 - 25 - 10 = 55<br></think><br>\boxed{55}</code>                                                                                                                                                                                                                                        |
+  | <code><think><br>Let’s think through this step by step<br>Time to iron a blouse = 15 minutes<br>Time to iron a dress = 20 minutes<br>Time spent on blouses = 2 hours = 120 minutes<br>Time spent on dresses = 3 hours = 180 minutes<br>Number of blouses ironed = 120 / 15 = 8<br>Number of dresses ironed = 180 / 20 = 9<br>Total pieces of clothes ironed = 8 + 9 = 17<br></think><br>\boxed{17}</code> | <code><think><br>Let’s think through this step by step<br>Time to iron 1 blouse = 15 minutes<br>Time to iron 1 dress = 20 minutes<br>Time spent on blouses = 2 hours = 120 minutes<br>Time spent on dresses = 3 hours = 180 minutes<br>Number of blouses ironed = 120 / 15 = 8<br>Number of dresses ironed = 180 / 20 = 9<br>Total pieces of clothes ironed = 8 + 9 = 17<br></think><br>\boxed{17}</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### csv
+
+* Dataset: csv
+* Size: 4,984 evaluation samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                              | positive                                                                            |
+  |:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                              |
+  | details | <ul><li>min: 33 tokens</li><li>mean: 66.68 tokens</li><li>max: 164 tokens</li></ul> | <ul><li>min: 33 tokens</li><li>mean: 66.71 tokens</li><li>max: 161 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                                                                                                                                | positive                                                                                                                                                                                                                                                                              |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code><think><br>Let’s think through this step by step<br>sg = 36<br>sc = 1/4<br>fl = 1/3<br>sg_left = sg - (sg × sc) - (sg × (1 - sc) × fl)<br>sg_left = 36 - (36 × 1/4) - (36 × (1 - 1/4) × 1/3)<br>sg_left = 36 - 9 - 6<br>sg_left = 21<br></think><br>\boxed{21}</code>           | <code><think><br>Let’s think through this step by step<br>sg = 36<br>sc = 1/4<br>fl = 1/3<br>sg_left = sg - (sg × sc) - (sg × (1 - sc) × fl)<br>sg_left = 36 - (36 × 1/4) - (36 × (1 - 1/4) × 1/3)<br>sg_left = 36 - 9 - 6<br>sg_left = 21<br></think><br>\boxed{21}</code>           |
+  | <code><think><br>Let’s think through this step by step<br>d1 = 125 miles<br>d2 = 223 miles<br>d3 = 493 - (125 + 223)<br>d3 = 145 miles<br></think><br>\boxed{145}</code>                                                                                                              | <code><think><br>Let’s think through this step by step<br>d1 = 125 miles<br>d2 = 223 miles<br>d3 = 493 - (125 + 223)<br>d3 = 145 miles<br></think><br>\boxed{145}</code>                                                                                                              |
+  | <code><think><br>Let’s think through this step by step<br>Total workdays = 2 weeks × 5 days/week = 10 days<br>Paid vacation days = 6 days<br>Unpaid vacation days = 10 - 6 = 4 days<br>Total pay = 15 × 8 = $120/day<br>Missed pay = 4 × 120 = $480<br></think><br>\boxed{480}</code> | <code><think><br>Let’s think through this step by step<br>Total workdays = 2 weeks × 5 days/week = 10 days<br>Paid vacation days = 6 days<br>Unpaid vacation days = 10 - 6 = 4 days<br>Total pay = 15 × 8 = $120/day<br>Missed pay = 4 × 120 = $480<br></think><br>\boxed{480}</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 2
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `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
+- `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`: 2
+- `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}
+- `tp_size`: 0
+- `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`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `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
+- `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
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | Validation Loss | sts-dev_spearman_cosine | sts-test_spearman_cosine |
+|:------:|:----:|:-------------:|:---------------:|:-----------------------:|:------------------------:|
+| -1     | -1   | -             | -               | 0.8671                  | -                        |
+| 0.3953 | 100  | 0.0204        | 0.0018          | 0.8743                  | -                        |
+| 0.7905 | 200  | 0.0046        | 0.0020          | 0.8752                  | -                        |
+| 1.1858 | 300  | 0.0021        | 0.0012          | 0.8752                  | -                        |
+| 1.5810 | 400  | 0.0008        | 0.0016          | 0.8757                  | -                        |
+| 1.9763 | 500  | 0.0027        | 0.0014          | 0.8755                  | -                        |
+| -1     | -1   | -             | -               | -                       | 0.8755                   |
+
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 3.4.1
+- Transformers: 4.51.1
+- PyTorch: 2.5.1+cu124
+- Accelerate: 1.3.0
+- Datasets: 3.5.0
+- Tokenizers: 0.21.0
+
+## 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",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@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}
+}
+```
+
+<!--
+## 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 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.51.1",
+    "pytorch": "2.5.1+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

eval/similarity_evaluation_sts-dev_results.csv

@@ -0,0 +1,6 @@
+epoch,steps,cosine_pearson,cosine_spearman
+0.3952569169960474,100,0.8768557369102674,0.874318253748564
+0.7905138339920948,200,0.8771717388441402,0.8751972862601562
+1.1857707509881423,300,0.8773181376919055,0.8752357555656901
+1.5810276679841897,400,0.8778527655445694,0.8756841473426699
+1.9762845849802373,500,0.8776143775032945,0.8754887541943006

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ece53c030bb3c7c5e8fe9a780d74d62c9bed62fa1d7ed2ce28cf4ad1086a7fff
+size 90864192

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

runs/Jul30_12-33-24_504bbaf3a637/events.out.tfevents.1753878821.504bbaf3a637.13.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d25fbfd64ed27f4f8d0a9edfdd4ce2705071859a1902b553481e0fe24b51272f
+size 7733

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 256,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 256,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72844a2c9869e8268360ecadfb2231093d1bedbfbe8460de39ede366a9e681cb
+size 5560