|
--- |
|
base_model: intfloat/multilingual-e5-small |
|
datasets: [] |
|
language: [] |
|
library_name: sentence-transformers |
|
metrics: |
|
- cosine_accuracy |
|
- cosine_accuracy_threshold |
|
- cosine_f1 |
|
- cosine_f1_threshold |
|
- cosine_precision |
|
- cosine_recall |
|
- cosine_ap |
|
- dot_accuracy |
|
- dot_accuracy_threshold |
|
- dot_f1 |
|
- dot_f1_threshold |
|
- dot_precision |
|
- dot_recall |
|
- dot_ap |
|
- manhattan_accuracy |
|
- manhattan_accuracy_threshold |
|
- manhattan_f1 |
|
- manhattan_f1_threshold |
|
- manhattan_precision |
|
- manhattan_recall |
|
- manhattan_ap |
|
- euclidean_accuracy |
|
- euclidean_accuracy_threshold |
|
- euclidean_f1 |
|
- euclidean_f1_threshold |
|
- euclidean_precision |
|
- euclidean_recall |
|
- euclidean_ap |
|
- max_accuracy |
|
- max_accuracy_threshold |
|
- max_f1 |
|
- max_f1_threshold |
|
- max_precision |
|
- max_recall |
|
- max_ap |
|
pipeline_tag: sentence-similarity |
|
tags: |
|
- sentence-transformers |
|
- sentence-similarity |
|
- feature-extraction |
|
- generated_from_trainer |
|
- dataset_size:916 |
|
- loss:OnlineContrastiveLoss |
|
widget: |
|
- source_sentence: Ways to enhance memory retention |
|
sentences: |
|
- How to improve memory? |
|
- What is the currency of China? |
|
- How do I replace a flat tire? |
|
- source_sentence: Why it's essential to maintain a balanced diet |
|
sentences: |
|
- What is the importance of a balanced diet? |
|
- What is the population of Canada? |
|
- How to create a website from scratch? |
|
- source_sentence: What is the chemical formula for methanol? |
|
sentences: |
|
- What is the highest mountain in North America? |
|
- What are the advantages of electric cars over gasoline vehicles? |
|
- What is the chemical formula for ethanol? |
|
- source_sentence: How is photosynthesis carried out? |
|
sentences: |
|
- What is the currency of the United States? |
|
- What is the capital of Norway? |
|
- How does photosynthesis work? |
|
- source_sentence: How is the weather today? |
|
sentences: |
|
- Who invented the airplane? |
|
- What is the weather like today? |
|
- Who was the first female Prime Minister of the UK? |
|
model-index: |
|
- name: SentenceTransformer based on intfloat/multilingual-e5-small |
|
results: |
|
- task: |
|
type: binary-classification |
|
name: Binary Classification |
|
dataset: |
|
name: pair class dev |
|
type: pair-class-dev |
|
metrics: |
|
- type: cosine_accuracy |
|
value: 0.9388646288209607 |
|
name: Cosine Accuracy |
|
- type: cosine_accuracy_threshold |
|
value: 0.7886800765991211 |
|
name: Cosine Accuracy Threshold |
|
- type: cosine_f1 |
|
value: 0.9411764705882353 |
|
name: Cosine F1 |
|
- type: cosine_f1_threshold |
|
value: 0.7886800765991211 |
|
name: Cosine F1 Threshold |
|
- type: cosine_precision |
|
value: 0.9572649572649573 |
|
name: Cosine Precision |
|
- type: cosine_recall |
|
value: 0.9256198347107438 |
|
name: Cosine Recall |
|
- type: cosine_ap |
|
value: 0.973954773457217 |
|
name: Cosine Ap |
|
- type: dot_accuracy |
|
value: 0.9388646288209607 |
|
name: Dot Accuracy |
|
- type: dot_accuracy_threshold |
|
value: 0.7886800765991211 |
|
name: Dot Accuracy Threshold |
|
- type: dot_f1 |
|
value: 0.9411764705882353 |
|
name: Dot F1 |
|
- type: dot_f1_threshold |
|
value: 0.7886800765991211 |
|
name: Dot F1 Threshold |
|
- type: dot_precision |
|
value: 0.9572649572649573 |
|
name: Dot Precision |
|
- type: dot_recall |
|
value: 0.9256198347107438 |
|
name: Dot Recall |
|
- type: dot_ap |
|
value: 0.973954773457217 |
|
name: Dot Ap |
|
- type: manhattan_accuracy |
|
value: 0.9388646288209607 |
|
name: Manhattan Accuracy |
|
- type: manhattan_accuracy_threshold |
|
value: 10.132380485534668 |
|
name: Manhattan Accuracy Threshold |
|
- type: manhattan_f1 |
|
value: 0.9411764705882353 |
|
name: Manhattan F1 |
|
- type: manhattan_f1_threshold |
|
value: 10.132380485534668 |
|
name: Manhattan F1 Threshold |
|
- type: manhattan_precision |
|
value: 0.9572649572649573 |
|
name: Manhattan Precision |
|
- type: manhattan_recall |
|
value: 0.9256198347107438 |
|
name: Manhattan Recall |
|
- type: manhattan_ap |
|
value: 0.9728889947842537 |
|
name: Manhattan Ap |
|
- type: euclidean_accuracy |
|
value: 0.9388646288209607 |
|
name: Euclidean Accuracy |
|
- type: euclidean_accuracy_threshold |
|
value: 0.6500871777534485 |
|
name: Euclidean Accuracy Threshold |
|
- type: euclidean_f1 |
|
value: 0.9411764705882353 |
|
name: Euclidean F1 |
|
- type: euclidean_f1_threshold |
|
value: 0.6500871777534485 |
|
name: Euclidean F1 Threshold |
|
- type: euclidean_precision |
|
value: 0.9572649572649573 |
|
name: Euclidean Precision |
|
- type: euclidean_recall |
|
value: 0.9256198347107438 |
|
name: Euclidean Recall |
|
- type: euclidean_ap |
|
value: 0.973954773457217 |
|
name: Euclidean Ap |
|
- type: max_accuracy |
|
value: 0.9388646288209607 |
|
name: Max Accuracy |
|
- type: max_accuracy_threshold |
|
value: 10.132380485534668 |
|
name: Max Accuracy Threshold |
|
- type: max_f1 |
|
value: 0.9411764705882353 |
|
name: Max F1 |
|
- type: max_f1_threshold |
|
value: 10.132380485534668 |
|
name: Max F1 Threshold |
|
- type: max_precision |
|
value: 0.9572649572649573 |
|
name: Max Precision |
|
- type: max_recall |
|
value: 0.9256198347107438 |
|
name: Max Recall |
|
- type: max_ap |
|
value: 0.973954773457217 |
|
name: Max Ap |
|
- task: |
|
type: binary-classification |
|
name: Binary Classification |
|
dataset: |
|
name: pair class test |
|
type: pair-class-test |
|
metrics: |
|
- type: cosine_accuracy |
|
value: 0.9388646288209607 |
|
name: Cosine Accuracy |
|
- type: cosine_accuracy_threshold |
|
value: 0.8207830190658569 |
|
name: Cosine Accuracy Threshold |
|
- type: cosine_f1 |
|
value: 0.9421487603305785 |
|
name: Cosine F1 |
|
- type: cosine_f1_threshold |
|
value: 0.8207830190658569 |
|
name: Cosine F1 Threshold |
|
- type: cosine_precision |
|
value: 0.9421487603305785 |
|
name: Cosine Precision |
|
- type: cosine_recall |
|
value: 0.9421487603305785 |
|
name: Cosine Recall |
|
- type: cosine_ap |
|
value: 0.9731728800864022 |
|
name: Cosine Ap |
|
- type: dot_accuracy |
|
value: 0.9388646288209607 |
|
name: Dot Accuracy |
|
- type: dot_accuracy_threshold |
|
value: 0.8207829594612122 |
|
name: Dot Accuracy Threshold |
|
- type: dot_f1 |
|
value: 0.9421487603305785 |
|
name: Dot F1 |
|
- type: dot_f1_threshold |
|
value: 0.8207829594612122 |
|
name: Dot F1 Threshold |
|
- type: dot_precision |
|
value: 0.9421487603305785 |
|
name: Dot Precision |
|
- type: dot_recall |
|
value: 0.9421487603305785 |
|
name: Dot Recall |
|
- type: dot_ap |
|
value: 0.9731728800864022 |
|
name: Dot Ap |
|
- type: manhattan_accuracy |
|
value: 0.9344978165938864 |
|
name: Manhattan Accuracy |
|
- type: manhattan_accuracy_threshold |
|
value: 9.387104988098145 |
|
name: Manhattan Accuracy Threshold |
|
- type: manhattan_f1 |
|
value: 0.9382716049382717 |
|
name: Manhattan F1 |
|
- type: manhattan_f1_threshold |
|
value: 9.516077041625977 |
|
name: Manhattan F1 Threshold |
|
- type: manhattan_precision |
|
value: 0.9344262295081968 |
|
name: Manhattan Precision |
|
- type: manhattan_recall |
|
value: 0.9421487603305785 |
|
name: Manhattan Recall |
|
- type: manhattan_ap |
|
value: 0.9720713665843098 |
|
name: Manhattan Ap |
|
- type: euclidean_accuracy |
|
value: 0.9388646288209607 |
|
name: Euclidean Accuracy |
|
- type: euclidean_accuracy_threshold |
|
value: 0.5986893177032471 |
|
name: Euclidean Accuracy Threshold |
|
- type: euclidean_f1 |
|
value: 0.9421487603305785 |
|
name: Euclidean F1 |
|
- type: euclidean_f1_threshold |
|
value: 0.5986893177032471 |
|
name: Euclidean F1 Threshold |
|
- type: euclidean_precision |
|
value: 0.9421487603305785 |
|
name: Euclidean Precision |
|
- type: euclidean_recall |
|
value: 0.9421487603305785 |
|
name: Euclidean Recall |
|
- type: euclidean_ap |
|
value: 0.9731728800864022 |
|
name: Euclidean Ap |
|
- type: max_accuracy |
|
value: 0.9388646288209607 |
|
name: Max Accuracy |
|
- type: max_accuracy_threshold |
|
value: 9.387104988098145 |
|
name: Max Accuracy Threshold |
|
- type: max_f1 |
|
value: 0.9421487603305785 |
|
name: Max F1 |
|
- type: max_f1_threshold |
|
value: 9.516077041625977 |
|
name: Max F1 Threshold |
|
- type: max_precision |
|
value: 0.9421487603305785 |
|
name: Max Precision |
|
- type: max_recall |
|
value: 0.9421487603305785 |
|
name: Max Recall |
|
- type: max_ap |
|
value: 0.9731728800864022 |
|
name: Max Ap |
|
--- |
|
|
|
# SentenceTransformer based on intfloat/multilingual-e5-small |
|
|
|
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small). 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:** [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) <!-- at revision fd1525a9fd15316a2d503bf26ab031a61d056e98 --> |
|
- **Maximum Sequence Length:** 512 tokens |
|
- **Output Dimensionality:** 384 tokens |
|
- **Similarity Function:** Cosine Similarity |
|
<!-- - **Training Dataset:** Unknown --> |
|
<!-- - **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': 512, '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("srikarvar/fine_tuned_model_1") |
|
# Run inference |
|
sentences = [ |
|
'How is the weather today?', |
|
'What is the weather like today?', |
|
'Who was the first female Prime Minister of the UK?', |
|
] |
|
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 |
|
|
|
#### Binary Classification |
|
* Dataset: `pair-class-dev` |
|
* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator) |
|
|
|
| Metric | Value | |
|
|:-----------------------------|:----------| |
|
| cosine_accuracy | 0.9389 | |
|
| cosine_accuracy_threshold | 0.7887 | |
|
| cosine_f1 | 0.9412 | |
|
| cosine_f1_threshold | 0.7887 | |
|
| cosine_precision | 0.9573 | |
|
| cosine_recall | 0.9256 | |
|
| cosine_ap | 0.974 | |
|
| dot_accuracy | 0.9389 | |
|
| dot_accuracy_threshold | 0.7887 | |
|
| dot_f1 | 0.9412 | |
|
| dot_f1_threshold | 0.7887 | |
|
| dot_precision | 0.9573 | |
|
| dot_recall | 0.9256 | |
|
| dot_ap | 0.974 | |
|
| manhattan_accuracy | 0.9389 | |
|
| manhattan_accuracy_threshold | 10.1324 | |
|
| manhattan_f1 | 0.9412 | |
|
| manhattan_f1_threshold | 10.1324 | |
|
| manhattan_precision | 0.9573 | |
|
| manhattan_recall | 0.9256 | |
|
| manhattan_ap | 0.9729 | |
|
| euclidean_accuracy | 0.9389 | |
|
| euclidean_accuracy_threshold | 0.6501 | |
|
| euclidean_f1 | 0.9412 | |
|
| euclidean_f1_threshold | 0.6501 | |
|
| euclidean_precision | 0.9573 | |
|
| euclidean_recall | 0.9256 | |
|
| euclidean_ap | 0.974 | |
|
| max_accuracy | 0.9389 | |
|
| max_accuracy_threshold | 10.1324 | |
|
| max_f1 | 0.9412 | |
|
| max_f1_threshold | 10.1324 | |
|
| max_precision | 0.9573 | |
|
| max_recall | 0.9256 | |
|
| **max_ap** | **0.974** | |
|
|
|
#### Binary Classification |
|
* Dataset: `pair-class-test` |
|
* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator) |
|
|
|
| Metric | Value | |
|
|:-----------------------------|:-----------| |
|
| cosine_accuracy | 0.9389 | |
|
| cosine_accuracy_threshold | 0.8208 | |
|
| cosine_f1 | 0.9421 | |
|
| cosine_f1_threshold | 0.8208 | |
|
| cosine_precision | 0.9421 | |
|
| cosine_recall | 0.9421 | |
|
| cosine_ap | 0.9732 | |
|
| dot_accuracy | 0.9389 | |
|
| dot_accuracy_threshold | 0.8208 | |
|
| dot_f1 | 0.9421 | |
|
| dot_f1_threshold | 0.8208 | |
|
| dot_precision | 0.9421 | |
|
| dot_recall | 0.9421 | |
|
| dot_ap | 0.9732 | |
|
| manhattan_accuracy | 0.9345 | |
|
| manhattan_accuracy_threshold | 9.3871 | |
|
| manhattan_f1 | 0.9383 | |
|
| manhattan_f1_threshold | 9.5161 | |
|
| manhattan_precision | 0.9344 | |
|
| manhattan_recall | 0.9421 | |
|
| manhattan_ap | 0.9721 | |
|
| euclidean_accuracy | 0.9389 | |
|
| euclidean_accuracy_threshold | 0.5987 | |
|
| euclidean_f1 | 0.9421 | |
|
| euclidean_f1_threshold | 0.5987 | |
|
| euclidean_precision | 0.9421 | |
|
| euclidean_recall | 0.9421 | |
|
| euclidean_ap | 0.9732 | |
|
| max_accuracy | 0.9389 | |
|
| max_accuracy_threshold | 9.3871 | |
|
| max_f1 | 0.9421 | |
|
| max_f1_threshold | 9.5161 | |
|
| max_precision | 0.9421 | |
|
| max_recall | 0.9421 | |
|
| **max_ap** | **0.9732** | |
|
|
|
<!-- |
|
## 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 |
|
|
|
#### Unnamed Dataset |
|
|
|
|
|
* Size: 916 training samples |
|
* Columns: <code>label</code>, <code>sentence2</code>, and <code>sentence1</code> |
|
* Approximate statistics based on the first 1000 samples: |
|
| | label | sentence2 | sentence1 | |
|
|:--------|:------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| |
|
| type | int | string | string | |
|
| details | <ul><li>0: ~49.56%</li><li>1: ~50.44%</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 10.32 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 10.92 tokens</li><li>max: 22 tokens</li></ul> | |
|
* Samples: |
|
| label | sentence2 | sentence1 | |
|
|:---------------|:---------------------------------------------------------------------|:-----------------------------------------------------| |
|
| <code>1</code> | <code>What are the potential side effects of this medication?</code> | <code>What are the side effects of this drug?</code> | |
|
| <code>0</code> | <code>How to fix a torn pocket?</code> | <code>How to fix a broken zipper?</code> | |
|
| <code>0</code> | <code>How to make a chocolate chip cookie dough?</code> | <code>How to bake a chocolate chip cookie?</code> | |
|
* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss) |
|
|
|
### Evaluation Dataset |
|
|
|
#### Unnamed Dataset |
|
|
|
|
|
* Size: 229 evaluation samples |
|
* Columns: <code>label</code>, <code>sentence2</code>, and <code>sentence1</code> |
|
* Approximate statistics based on the first 1000 samples: |
|
| | label | sentence2 | sentence1 | |
|
|:--------|:------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| |
|
| type | int | string | string | |
|
| details | <ul><li>0: ~47.16%</li><li>1: ~52.84%</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.95 tokens</li><li>max: 16 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 10.81 tokens</li><li>max: 20 tokens</li></ul> | |
|
* Samples: |
|
| label | sentence2 | sentence1 | |
|
|:---------------|:--------------------------------------------------------------|:---------------------------------------------------| |
|
| <code>0</code> | <code>What methods are used to measure a nation's GDP?</code> | <code>How is the GDP of a country measured?</code> | |
|
| <code>0</code> | <code>What is the currency of Japan?</code> | <code>What is the currency of China?</code> | |
|
| <code>1</code> | <code>Steps to cultivate tomatoes at home</code> | <code>How to grow tomatoes in a garden?</code> | |
|
* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss) |
|
|
|
### Training Hyperparameters |
|
#### Non-Default Hyperparameters |
|
|
|
- `eval_strategy`: epoch |
|
- `per_device_train_batch_size`: 32 |
|
- `per_device_eval_batch_size`: 32 |
|
- `gradient_accumulation_steps`: 2 |
|
- `weight_decay`: 0.01 |
|
- `num_train_epochs`: 8 |
|
- `warmup_ratio`: 0.1 |
|
- `load_best_model_at_end`: True |
|
- `optim`: adamw_torch_fused |
|
- `batch_sampler`: no_duplicates |
|
|
|
#### All Hyperparameters |
|
<details><summary>Click to expand</summary> |
|
|
|
- `overwrite_output_dir`: False |
|
- `do_predict`: False |
|
- `eval_strategy`: epoch |
|
- `prediction_loss_only`: True |
|
- `per_device_train_batch_size`: 32 |
|
- `per_device_eval_batch_size`: 32 |
|
- `per_gpu_train_batch_size`: None |
|
- `per_gpu_eval_batch_size`: None |
|
- `gradient_accumulation_steps`: 2 |
|
- `eval_accumulation_steps`: None |
|
- `learning_rate`: 5e-05 |
|
- `weight_decay`: 0.01 |
|
- `adam_beta1`: 0.9 |
|
- `adam_beta2`: 0.999 |
|
- `adam_epsilon`: 1e-08 |
|
- `max_grad_norm`: 1.0 |
|
- `num_train_epochs`: 8 |
|
- `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`: 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_fused |
|
- `optim_args`: None |
|
- `adafactor`: False |
|
- `group_by_length`: False |
|
- `length_column_name`: length |
|
- `ddp_find_unused_parameters`: None |
|
- `ddp_bucket_cap_mb`: None |
|
- `ddp_broadcast_buffers`: False |
|
- `dataloader_pin_memory`: True |
|
- `dataloader_persistent_workers`: False |
|
- `skip_memory_metrics`: True |
|
- `use_legacy_prediction_loop`: False |
|
- `push_to_hub`: False |
|
- `resume_from_checkpoint`: None |
|
- `hub_model_id`: None |
|
- `hub_strategy`: every_save |
|
- `hub_private_repo`: False |
|
- `hub_always_push`: False |
|
- `gradient_checkpointing`: 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`: no_duplicates |
|
- `multi_dataset_batch_sampler`: proportional |
|
|
|
</details> |
|
|
|
### Training Logs |
|
| Epoch | Step | Training Loss | loss | pair-class-dev_max_ap | pair-class-test_max_ap | |
|
|:----------:|:------:|:-------------:|:----------:|:---------------------:|:----------------------:| |
|
| 0 | 0 | - | - | 0.7130 | - | |
|
| 0.6897 | 10 | 3.0972 | - | - | - | |
|
| 1.0345 | 15 | - | 0.8033 | 0.9272 | - | |
|
| 1.3448 | 20 | 1.0451 | - | - | - | |
|
| 2.0345 | 30 | 0.5786 | 0.4910 | 0.9680 | - | |
|
| 2.6897 | 40 | 0.2996 | - | - | - | |
|
| 3.0345 | 45 | - | 0.4487 | 0.9731 | - | |
|
| 3.3448 | 50 | 0.0901 | - | - | - | |
|
| **4.0345** | **60** | **0.067** | **0.4115** | **0.9732** | **-** | |
|
| 4.6897 | 70 | 0.0729 | - | - | - | |
|
| 5.0345 | 75 | - | 0.4543 | 0.9727 | - | |
|
| 5.3448 | 80 | 0.0453 | - | - | - | |
|
| 6.0345 | 90 | 0.0637 | 0.4249 | 0.9736 | - | |
|
| 6.6897 | 100 | 0.0388 | - | - | - | |
|
| 7.0345 | 105 | - | 0.4223 | 0.9740 | - | |
|
| 7.3448 | 110 | 0.0382 | - | - | - | |
|
| 7.4828 | 112 | - | 0.4226 | 0.9740 | 0.9732 | |
|
|
|
* The bold row denotes the saved checkpoint. |
|
|
|
### Framework Versions |
|
- Python: 3.10.12 |
|
- Sentence Transformers: 3.0.1 |
|
- Transformers: 4.41.2 |
|
- PyTorch: 2.1.2+cu121 |
|
- Accelerate: 0.32.1 |
|
- Datasets: 2.19.1 |
|
- 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.* |
|
--> |
