Training in progress, step 30

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 +1,637 @@
+---
+language:
+- en
+license: apache-2.0
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_with_trainer
+- dataset_size:100K<n<1M
+- loss:SoftmaxLoss
+- loss:CosineSimilarityLoss
+base_model: microsoft/mpnet-base
+datasets:
+- nyu-mll/multi_nli
+- stanfordnlp/snli
+- mteb/stsbenchmark-sts
+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 taxi SUV drives past an urban construction site, as a man walks
+    down the street in the other direction.
+  sentences:
+  - The woman is walking down the street with high heels.
+  - A man is reading documents in a binder.
+  - A man is chasing an SUV that is going in the same direction as him.
+- source_sentence: Young man running towards a tennis court while another is waiting
+    in the other side of the net.
+  sentences:
+  - The person is cooking a hamburger.
+  - A young man is running to grab a tennis ball.
+  - A woman is dancing near a fire.
+- source_sentence: An asian woman sitting outside an outdoor market stall.
+  sentences:
+  - There are three workers
+  - A woman sits outdoors.
+  - Five women sit at a table.
+- source_sentence: All the same methods of analysis that are used with spoken languages
+    apply successfully to signed languages.
+  sentences:
+  - One idea that's been going around at least since the 80s is that you can distinguish
+    between Holds and Moves.
+  - You only need two-dimensional trigonometry if you know the distances to the two
+    stars and their angular separation.
+  - A woman driving a car is talking to the man seated beside her.
+- source_sentence: Rouen is the ancient center of Normandy's thriving textile industry,
+    and the place of Joan of Arc's martyrdom ' a national symbol of resistance to
+    tyranny.
+  sentences:
+  - The islands are part of France now instead of just colonies.
+  - Joan of Arc sacrificed her life at Rouen, which became an enduring symbol of opposition
+    to tyranny.
+  - I don't know how cold it got last night.
+pipeline_tag: sentence-similarity
+co2_eq_emissions:
+  emissions: 6.543912203095872
+  energy_consumed: 0.01683529336894555
+  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: 0.067
+  hardware_used: 1 x NVIDIA GeForce RTX 3090
+model-index:
+- name: SentenceTransformer based on microsoft/mpnet-base
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev
+      type: sts-dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.8625771940364872
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8606717551154308
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8638967614504363
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8633946128639698
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8611337271100419
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8606717551154308
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.862577202108671
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8606717551154308
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8638967614504363
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8633946128639698
+      name: Spearman Max
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test
+      type: sts-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.8121966861722953
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8064524624275264
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.8164566762295066
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.8087376581901532
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.8146700964672056
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.8064524624275264
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.8121966895185604
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.8064524624275264
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.8164566762295066
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.8087376581901532
+      name: Spearman Max
+---
+
+# SentenceTransformer based on microsoft/mpnet-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) on the [multi_nli](https://huggingface.co/datasets/nyu-mll/multi_nli), [snli](https://huggingface.co/datasets/stanfordnlp/snli) and [stsb](https://huggingface.co/datasets/mteb/stsbenchmark-sts) datasets. 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:** [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) <!-- at revision 6996ce1e91bd2a9c7d7f61daec37463394f73f09 -->
+- **Maximum Sequence Length:** 384 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Dot Product
+- **Training Datasets:**
+    - [multi_nli](https://huggingface.co/datasets/nyu-mll/multi_nli)
+    - [snli](https://huggingface.co/datasets/stanfordnlp/snli)
+    - [stsb](https://huggingface.co/datasets/mteb/stsbenchmark-sts)
+- **Language:** en
+- **License:** apache-2.0
+
+### 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': 384, 'do_lower_case': False}) with Transformer model: MPNetModel 
+  (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:
+
+```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/mpnet-base-allnli")
+# Run inference
+sentences = [
+    "Rouen is the ancient center of Normandy's thriving textile industry, and the place of Joan of Arc's martyrdom ' a national symbol of resistance to tyranny.",
+    'Joan of Arc sacrificed her life at Rouen, which became an enduring symbol of opposition to tyranny.',
+    'The islands are part of France now instead of just colonies.',
+]
+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]
+```
+
+<!--
+### 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-dev`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric             | Value      |
+|:-------------------|:-----------|
+| pearson_cosine     | 0.8626     |
+| spearman_cosine    | 0.8607     |
+| pearson_manhattan  | 0.8639     |
+| spearman_manhattan | 0.8634     |
+| pearson_euclidean  | 0.8611     |
+| spearman_euclidean | 0.8607     |
+| pearson_dot        | 0.8626     |
+| **spearman_dot**   | **0.8607** |
+| pearson_max        | 0.8639     |
+| spearman_max       | 0.8634     |
+
+#### Semantic Similarity
+* Dataset: `sts-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.8122     |
+| **spearman_cosine** | **0.8065** |
+| pearson_manhattan   | 0.8165     |
+| spearman_manhattan  | 0.8087     |
+| pearson_euclidean   | 0.8147     |
+| spearman_euclidean  | 0.8065     |
+| pearson_dot         | 0.8122     |
+| spearman_dot        | 0.8065     |
+| pearson_max         | 0.8165     |
+| spearman_max        | 0.8087     |
+
+<!--
+## 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 Datasets
+
+#### multi_nli
+
+* Dataset: [multi_nli](https://huggingface.co/datasets/nyu-mll/multi_nli) at [da70db2](https://huggingface.co/datasets/nyu-mll/multi_nli/tree/da70db2af9d09693783c3320c4249840212ee221)
+* Size: 392,702 training samples
+* Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | premise                                                                            | hypothesis                                                                        | label                                                              |
+  |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                            | int                                                                |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 26.95 tokens</li><li>max: 189 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 14.11 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>0: ~34.30%</li><li>1: ~28.20%</li><li>2: ~37.50%</li></ul> |
+* Samples:
+  | premise                                                                                                                                                                                                                                                                                              | hypothesis                                                                        | label          |
+  |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------|
+  | <code>Conceptually cream skimming has two basic dimensions - product and geography.</code>                                                                                                                                                                                                           | <code>Product and geography are what make cream skimming work. </code>            | <code>1</code> |
+  | <code>you know during the season and i guess at at your level uh you lose them to the next level if if they decide to recall the the parent team the Braves decide to call to recall a guy from triple A then a double A guy goes up to replace him and a single A guy goes up to replace him</code> | <code>You lose the things to the following level if the people recall.</code>     | <code>0</code> |
+  | <code>One of our number will carry out your instructions minutely.</code>                                                                                                                                                                                                                            | <code>A member of my team will execute your orders with immense precision.</code> | <code>0</code> |
+* Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
+
+#### snli
+
+* Dataset: [snli](https://huggingface.co/datasets/stanfordnlp/snli) at [cdb5c3d](https://huggingface.co/datasets/stanfordnlp/snli/tree/cdb5c3d5eed6ead6e5a341c8e56e669bb666725b)
+* Size: 549,367 training samples
+* Columns: <code>snli_premise</code>, <code>hypothesis</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | snli_premise                                                                      | hypothesis                                                                       | label                                                              |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:-------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                           | int                                                                |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 17.38 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 10.7 tokens</li><li>max: 31 tokens</li></ul> | <ul><li>0: ~33.40%</li><li>1: ~33.30%</li><li>2: ~33.30%</li></ul> |
+* Samples:
+  | snli_premise                                                        | hypothesis                                                     | label          |
+  |:--------------------------------------------------------------------|:---------------------------------------------------------------|:---------------|
+  | <code>A person on a horse jumps over a broken down airplane.</code> | <code>A person is training his horse for a competition.</code> | <code>1</code> |
+  | <code>A person on a horse jumps over a broken down airplane.</code> | <code>A person is at a diner, ordering an omelette.</code>     | <code>2</code> |
+  | <code>A person on a horse jumps over a broken down airplane.</code> | <code>A person is outdoors, on a horse.</code>                 | <code>0</code> |
+* Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
+
+#### stsb
+
+* Dataset: [stsb](https://huggingface.co/datasets/mteb/stsbenchmark-sts) at [8913289](https://huggingface.co/datasets/mteb/stsbenchmark-sts/tree/8913289635987208e6e7c72789e4be2fe94b6abd)
+* Size: 5,749 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                        | sentence2                                                                        | label                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | 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                                                             | label             |
+  |:-----------------------------------------------------------|:----------------------------------------------------------------------|:------------------|
+  | <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/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Evaluation Datasets
+
+#### multi_nli
+
+* Dataset: [multi_nli](https://huggingface.co/datasets/nyu-mll/multi_nli) at [da70db2](https://huggingface.co/datasets/nyu-mll/multi_nli/tree/da70db2af9d09693783c3320c4249840212ee221)
+* Size: 100 evaluation samples
+* Columns: <code>premise</code>, <code>hypothesis</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | premise                                                                            | hypothesis                                                                        | label                                                              |
+  |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                            | int                                                                |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 27.67 tokens</li><li>max: 138 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.48 tokens</li><li>max: 27 tokens</li></ul> | <ul><li>0: ~35.00%</li><li>1: ~31.00%</li><li>2: ~34.00%</li></ul> |
+* Samples:
+  | premise                                                                                                                                      | hypothesis                                                                                        | label          |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------|:---------------|
+  | <code>The new rights are nice enough</code>                                                                                                  | <code>Everyone really likes the newest benefits </code>                                           | <code>1</code> |
+  | <code>This site includes a list of all award winners and a searchable database of Government Executive articles.</code>                      | <code>The Government Executive articles housed on the website are not able to be searched.</code> | <code>2</code> |
+  | <code>uh i don't know i i have mixed emotions about him uh sometimes i like him but at the same times i love to see somebody beat him</code> | <code>I like him for the most part, but would still enjoy seeing someone beat him.</code>         | <code>0</code> |
+* Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
+
+#### snli
+
+* Dataset: [snli](https://huggingface.co/datasets/stanfordnlp/snli) at [cdb5c3d](https://huggingface.co/datasets/stanfordnlp/snli/tree/cdb5c3d5eed6ead6e5a341c8e56e669bb666725b)
+* Size: 9,842 evaluation samples
+* Columns: <code>snli_premise</code>, <code>hypothesis</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | snli_premise                                                                      | hypothesis                                                                        | label                                                              |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | int                                                                |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 18.44 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 10.57 tokens</li><li>max: 25 tokens</li></ul> | <ul><li>0: ~33.10%</li><li>1: ~33.30%</li><li>2: ~33.60%</li></ul> |
+* Samples:
+  | snli_premise                                                       | hypothesis                                                                                         | label          |
+  |:-------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------|:---------------|
+  | <code>Two women are embracing while holding to go packages.</code> | <code>The sisters are hugging goodbye while holding to go packages after just eating lunch.</code> | <code>1</code> |
+  | <code>Two women are embracing while holding to go packages.</code> | <code>Two woman are holding packages.</code>                                                       | <code>0</code> |
+  | <code>Two women are embracing while holding to go packages.</code> | <code>The men are fighting outside a deli.</code>                                                  | <code>2</code> |
+* Loss: [<code>SoftmaxLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss)
+
+#### stsb
+
+* Dataset: [stsb](https://huggingface.co/datasets/mteb/stsbenchmark-sts) at [8913289](https://huggingface.co/datasets/mteb/stsbenchmark-sts/tree/8913289635987208e6e7c72789e4be2fe94b6abd)
+* Size: 1,500 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                        | sentence2                                                                         | label                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | 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                                             | label             |
+  |:--------------------------------------------------|:------------------------------------------------------|:------------------|
+  | <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/sentence_transformer/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`: 64
+- `per_device_eval_batch_size`: 64
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `seed`: 33
+- `bf16`: True
+- `load_best_model_at_end`: True
+- `push_to_hub`: True
+- `hub_model_id`: tomaarsen/mpnet-base-allnli
+- `hub_private_repo`: True
+- `multi_dataset_batch_sampler`: round_robin
+
+#### 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`: 64
+- `per_device_eval_batch_size`: 64
+- `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`: 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
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 33
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: True
+- `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
+- `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`: True
+- `resume_from_checkpoint`: None
+- `hub_model_id`: tomaarsen/mpnet-base-allnli
+- `hub_strategy`: every_save
+- `hub_private_repo`: True
+- `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`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch      | Step    | Training Loss | stsb loss  | snli loss  | multi nli loss | sts-dev_spearman_dot | sts-test_spearman_cosine |
+|:----------:|:-------:|:-------------:|:----------:|:----------:|:--------------:|:--------------------:|:------------------------:|
+| 0.0370     | 10      | 0.8336        | -          | -          | -              | -                    | -                        |
+| 0.0741     | 20      | 0.8257        | -          | -          | -              | -                    | -                        |
+| 0.1111     | 30      | 0.6998        | 0.0736     | 1.0978     | 1.0961         | 0.6791               | -                        |
+| 0.1481     | 40      | 0.7878        | -          | -          | -              | -                    | -                        |
+| 0.1852     | 50      | 0.7868        | -          | -          | -              | -                    | -                        |
+| 0.2222     | 60      | 0.6761        | 0.0528     | 1.0958     | 1.0963         | 0.8035               | -                        |
+| 0.2593     | 70      | 0.7804        | -          | -          | -              | -                    | -                        |
+| 0.2963     | 80      | 0.7789        | -          | -          | -              | -                    | -                        |
+| 0.3333     | 90      | 0.6756        | 0.0390     | 1.0940     | 1.0962         | 0.8341               | -                        |
+| 0.3704     | 100     | 0.7811        | -          | -          | -              | -                    | -                        |
+| 0.4074     | 110     | 0.775         | -          | -          | -              | -                    | -                        |
+| 0.4444     | 120     | 0.6721        | 0.0351     | 1.0932     | 1.0981         | 0.8413               | -                        |
+| 0.4815     | 130     | 0.7794        | -          | -          | -              | -                    | -                        |
+| 0.5185     | 140     | 0.7764        | -          | -          | -              | -                    | -                        |
+| 0.5556     | 150     | 0.6705        | 0.0343     | 1.0906     | 1.0950         | 0.8485               | -                        |
+| 0.5926     | 160     | 0.776         | -          | -          | -              | -                    | -                        |
+| 0.6296     | 170     | 0.7742        | -          | -          | -              | -                    | -                        |
+| 0.6667     | 180     | 0.6643        | 0.0326     | 1.0887     | 1.0927         | 0.8547               | -                        |
+| 0.7037     | 190     | 0.7732        | -          | -          | -              | -                    | -                        |
+| 0.7407     | 200     | 0.7733        | -          | -          | -              | -                    | -                        |
+| 0.7778     | 210     | 0.6676        | 0.0318     | 1.0867     | 1.0912         | 0.8591               | -                        |
+| 0.8148     | 220     | 0.7706        | -          | -          | -              | -                    | -                        |
+| 0.8519     | 230     | 0.7716        | -          | -          | -              | -                    | -                        |
+| **0.8889** | **240** | **0.6633**    | **0.0302** | **1.0855** | **1.0889**     | **0.8607**           | **-**                    |
+| 0.9259     | 250     | 0.7711        | -          | -          | -              | -                    | -                        |
+| 0.9630     | 260     | 0.7716        | -          | -          | -              | -                    | -                        |
+| 1.0        | 270     | 0.6644        | 0.0316     | 1.0852     | 1.0890         | 0.8607               | 0.8065                   |
+
+* The bold row denotes the saved checkpoint.
+
+### Environmental Impact
+Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
+- **Energy Consumed**: 0.017 kWh
+- **Carbon Emitted**: 0.007 kg of CO2
+- **Hours Used**: 0.067 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: 3.1.0.dev0
+- Transformers: 4.41.2
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.30.1
+- Datasets: 2.19.1
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers and SoftmaxLoss
+```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 +1,24 @@
+{
+  "_name_or_path": "microsoft/mpnet-base",
+  "architectures": [
+    "MPNetModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "mpnet",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "vocab_size": 30527
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.1.0.dev0",
+    "transformers": "4.41.2",
+    "pytorch": "2.3.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "dot"
+}

emissions.csv

@@ -0,0 +1,3 @@
+timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
+2024-06-05T13:25:31,codecarbon,8f78a832-cb8b-4255-90f9-87291ab5a2c5,203.90490198135376,0.0066664767107362,3.269404828406667e-05,42.5,262.78315247135714,11.9164080619812,0.0024072106483909,0.0140688801439834,0.0006745199858985,0.0171506107782729,The Netherlands,NLD,utrecht,,,Windows-10-10.0.22631-SP0,3.11.6,2.3.4,24,13th Gen Intel(R) Core(TM) i7-13700K,1,1 x NVIDIA GeForce RTX 3090,5.0582,52.0756,31.777088165283203,machine,N,1.0
+2024-06-05T14:02:28,codecarbon,c19a4b76-5dda-443e-a1eb-73550f818127,200.78387594223022,0.006543912203095872,3.259182129235663e-05,42.5,248.66806443178965,11.916408061981201,0.002370365202095774,0.013800701318329445,0.0006642268485203281,0.01683529336894555,The Netherlands,NLD,utrecht,,,Windows-10-10.0.22631-SP0,3.11.6,2.3.4,24,13th Gen Intel(R) Core(TM) i7-13700K,1,1 x NVIDIA GeForce RTX 3090,5.0582,52.0756,31.777088165283203,machine,N,1.0

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a6c0ac72ffdd503c8ece4111263bf928521874978a5648a81f0ac725c47eb17
+size 437967672

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/Jun05_13-21-55_Tom/events.out.tfevents.1717586522.Tom.11064.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17b3f0ff9d4380d90fba6e4be100eceedadc23e5976d47f6be9b297671ab1427
+size 24190

runs/Jun05_13-58-55_Tom/events.out.tfevents.1717588742.Tom.10892.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a821f3e70c350339d6208d22f32d9df5640ff90dae6a51ab863190590d472a
+size 24190

runs/Jun05_14-24-25_Tom/events.out.tfevents.1717590271.Tom.22032.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70b8273416c93834129344714b7a0124744f27ef49d8a44501b38e7d1e77cfac
+size 6419

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 384,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "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": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 384,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa5f70e62daa8cfaaf203eb6f4ee8d4968199e089a94ed1ed8a30a5a3693181c
+size 5432