|
--- |
|
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:2332 |
|
- loss:OnlineContrastiveLoss |
|
widget: |
|
- source_sentence: Who discovered the structure of DNA? |
|
sentences: |
|
- Who discovered the structure of RNA? |
|
- Steps to apply for a scholarship |
|
- First human to set foot on the moon |
|
- source_sentence: Who directed 'Schindler's List'? |
|
sentences: |
|
- Who directed 'The Pianist'? |
|
- What are some high paying jobs for a fresher with an M.Tech in biotechnology? |
|
- Where can I find gluten-free restaurants? |
|
- source_sentence: Which is the best shares to purchase and sale daily trading? |
|
sentences: |
|
- In Sydney, which company would be the best to get advice for Business Sales & |
|
Purchases? |
|
- Steps to adjust phone settings |
|
- Is a 3.8 GPA sufficient to get into a top school? |
|
- source_sentence: Nd she is always sad? |
|
sentences: |
|
- Where to purchase organic produce |
|
- Aerodynamically what happens when propellor rotates? |
|
- How is unsupervised learning used for data insights? |
|
- source_sentence: How to bake a pie? |
|
sentences: |
|
- What is the population of Chicago? |
|
- Steps to bake a pie |
|
- 'What is the distribution of traffic between Google organic search results? e.g. |
|
#1 vs. #2 in rankings, first page vs. second page' |
|
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: 0.8653846153846154 |
|
name: Cosine Accuracy |
|
- type: cosine_accuracy_threshold |
|
value: 0.872760534286499 |
|
name: Cosine Accuracy Threshold |
|
- type: cosine_f1 |
|
value: 0.8656716417910447 |
|
name: Cosine F1 |
|
- type: cosine_f1_threshold |
|
value: 0.8200240135192871 |
|
name: Cosine F1 Threshold |
|
- type: cosine_precision |
|
value: 0.8285714285714286 |
|
name: Cosine Precision |
|
- type: cosine_recall |
|
value: 0.90625 |
|
name: Cosine Recall |
|
- type: cosine_ap |
|
value: 0.9322624848213654 |
|
name: Cosine Ap |
|
- type: dot_accuracy |
|
value: 0.8653846153846154 |
|
name: Dot Accuracy |
|
- type: dot_accuracy_threshold |
|
value: 0.872760534286499 |
|
name: Dot Accuracy Threshold |
|
- type: dot_f1 |
|
value: 0.8656716417910447 |
|
name: Dot F1 |
|
- type: dot_f1_threshold |
|
value: 0.8200240135192871 |
|
name: Dot F1 Threshold |
|
- type: dot_precision |
|
value: 0.8285714285714286 |
|
name: Dot Precision |
|
- type: dot_recall |
|
value: 0.90625 |
|
name: Dot Recall |
|
- type: dot_ap |
|
value: 0.9322624848213654 |
|
name: Dot Ap |
|
- type: manhattan_accuracy |
|
value: 0.8692307692307693 |
|
name: Manhattan Accuracy |
|
- type: manhattan_accuracy_threshold |
|
value: 9.252302169799805 |
|
name: Manhattan Accuracy Threshold |
|
- type: manhattan_f1 |
|
value: 0.8721804511278196 |
|
name: Manhattan F1 |
|
- type: manhattan_f1_threshold |
|
value: 9.252302169799805 |
|
name: Manhattan F1 Threshold |
|
- type: manhattan_precision |
|
value: 0.8405797101449275 |
|
name: Manhattan Precision |
|
- type: manhattan_recall |
|
value: 0.90625 |
|
name: Manhattan Recall |
|
- type: manhattan_ap |
|
value: 0.9322911488571455 |
|
name: Manhattan Ap |
|
- type: euclidean_accuracy |
|
value: 0.8653846153846154 |
|
name: Euclidean Accuracy |
|
- type: euclidean_accuracy_threshold |
|
value: 0.5044240355491638 |
|
name: Euclidean Accuracy Threshold |
|
- type: euclidean_f1 |
|
value: 0.8656716417910447 |
|
name: Euclidean F1 |
|
- type: euclidean_f1_threshold |
|
value: 0.5999571084976196 |
|
name: Euclidean F1 Threshold |
|
- type: euclidean_precision |
|
value: 0.8285714285714286 |
|
name: Euclidean Precision |
|
- type: euclidean_recall |
|
value: 0.90625 |
|
name: Euclidean Recall |
|
- type: euclidean_ap |
|
value: 0.9322624848213654 |
|
name: Euclidean Ap |
|
- type: max_accuracy |
|
value: 0.8692307692307693 |
|
name: Max Accuracy |
|
- type: max_accuracy_threshold |
|
value: 9.252302169799805 |
|
name: Max Accuracy Threshold |
|
- type: max_f1 |
|
value: 0.8721804511278196 |
|
name: Max F1 |
|
- type: max_f1_threshold |
|
value: 9.252302169799805 |
|
name: Max F1 Threshold |
|
- type: max_precision |
|
value: 0.8405797101449275 |
|
name: Max Precision |
|
- type: max_recall |
|
value: 0.90625 |
|
name: Max Recall |
|
- type: max_ap |
|
value: 0.9322911488571455 |
|
name: Max Ap |
|
- task: |
|
type: binary-classification |
|
name: Binary Classification |
|
dataset: |
|
name: pair class test |
|
type: pair-class-test |
|
metrics: |
|
- type: cosine_accuracy |
|
value: 0.916 |
|
name: Cosine Accuracy |
|
- type: cosine_accuracy_threshold |
|
value: 0.844039261341095 |
|
name: Cosine Accuracy Threshold |
|
- type: cosine_f1 |
|
value: 0.907488986784141 |
|
name: Cosine F1 |
|
- type: cosine_f1_threshold |
|
value: 0.8230063319206238 |
|
name: Cosine F1 Threshold |
|
- type: cosine_precision |
|
value: 0.8728813559322034 |
|
name: Cosine Precision |
|
- type: cosine_recall |
|
value: 0.944954128440367 |
|
name: Cosine Recall |
|
- type: cosine_ap |
|
value: 0.96095333014952 |
|
name: Cosine Ap |
|
- type: dot_accuracy |
|
value: 0.916 |
|
name: Dot Accuracy |
|
- type: dot_accuracy_threshold |
|
value: 0.8440393209457397 |
|
name: Dot Accuracy Threshold |
|
- type: dot_f1 |
|
value: 0.907488986784141 |
|
name: Dot F1 |
|
- type: dot_f1_threshold |
|
value: 0.8230063319206238 |
|
name: Dot F1 Threshold |
|
- type: dot_precision |
|
value: 0.8728813559322034 |
|
name: Dot Precision |
|
- type: dot_recall |
|
value: 0.944954128440367 |
|
name: Dot Recall |
|
- type: dot_ap |
|
value: 0.96095333014952 |
|
name: Dot Ap |
|
- type: manhattan_accuracy |
|
value: 0.916 |
|
name: Manhattan Accuracy |
|
- type: manhattan_accuracy_threshold |
|
value: 8.581160545349121 |
|
name: Manhattan Accuracy Threshold |
|
- type: manhattan_f1 |
|
value: 0.907488986784141 |
|
name: Manhattan F1 |
|
- type: manhattan_f1_threshold |
|
value: 9.327116012573242 |
|
name: Manhattan F1 Threshold |
|
- type: manhattan_precision |
|
value: 0.8728813559322034 |
|
name: Manhattan Precision |
|
- type: manhattan_recall |
|
value: 0.944954128440367 |
|
name: Manhattan Recall |
|
- type: manhattan_ap |
|
value: 0.9612698712458685 |
|
name: Manhattan Ap |
|
- type: euclidean_accuracy |
|
value: 0.916 |
|
name: Euclidean Accuracy |
|
- type: euclidean_accuracy_threshold |
|
value: 0.5584936141967773 |
|
name: Euclidean Accuracy Threshold |
|
- type: euclidean_f1 |
|
value: 0.907488986784141 |
|
name: Euclidean F1 |
|
- type: euclidean_f1_threshold |
|
value: 0.594968318939209 |
|
name: Euclidean F1 Threshold |
|
- type: euclidean_precision |
|
value: 0.8728813559322034 |
|
name: Euclidean Precision |
|
- type: euclidean_recall |
|
value: 0.944954128440367 |
|
name: Euclidean Recall |
|
- type: euclidean_ap |
|
value: 0.96095333014952 |
|
name: Euclidean Ap |
|
- type: max_accuracy |
|
value: 0.916 |
|
name: Max Accuracy |
|
- type: max_accuracy_threshold |
|
value: 8.581160545349121 |
|
name: Max Accuracy Threshold |
|
- type: max_f1 |
|
value: 0.907488986784141 |
|
name: Max F1 |
|
- type: max_f1_threshold |
|
value: 9.327116012573242 |
|
name: Max F1 Threshold |
|
- type: max_precision |
|
value: 0.8728813559322034 |
|
name: Max Precision |
|
- type: max_recall |
|
value: 0.944954128440367 |
|
name: Max Recall |
|
- type: max_ap |
|
value: 0.9612698712458685 |
|
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_5") |
|
# Run inference |
|
sentences = [ |
|
'How to bake a pie?', |
|
'Steps to bake a pie', |
|
'What is the population of Chicago?', |
|
] |
|
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 | 0.8654 | |
|
| cosine_accuracy_threshold | 0.8728 | |
|
| cosine_f1 | 0.8657 | |
|
| cosine_f1_threshold | 0.82 | |
|
| cosine_precision | 0.8286 | |
|
| cosine_recall | 0.9062 | |
|
| cosine_ap | 0.9323 | |
|
| dot_accuracy | 0.8654 | |
|
| dot_accuracy_threshold | 0.8728 | |
|
| dot_f1 | 0.8657 | |
|
| dot_f1_threshold | 0.82 | |
|
| dot_precision | 0.8286 | |
|
| dot_recall | 0.9062 | |
|
| dot_ap | 0.9323 | |
|
| manhattan_accuracy | 0.8692 | |
|
| manhattan_accuracy_threshold | 9.2523 | |
|
| manhattan_f1 | 0.8722 | |
|
| manhattan_f1_threshold | 9.2523 | |
|
| manhattan_precision | 0.8406 | |
|
| manhattan_recall | 0.9062 | |
|
| manhattan_ap | 0.9323 | |
|
| euclidean_accuracy | 0.8654 | |
|
| euclidean_accuracy_threshold | 0.5044 | |
|
| euclidean_f1 | 0.8657 | |
|
| euclidean_f1_threshold | 0.6 | |
|
| euclidean_precision | 0.8286 | |
|
| euclidean_recall | 0.9062 | |
|
| euclidean_ap | 0.9323 | |
|
| max_accuracy | 0.8692 | |
|
| max_accuracy_threshold | 9.2523 | |
|
| max_f1 | 0.8722 | |
|
| max_f1_threshold | 9.2523 | |
|
| max_precision | 0.8406 | |
|
| max_recall | 0.9062 | |
|
| **max_ap** | **0.9323** | |
|
|
|
#### 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 | 0.916 | |
|
| cosine_accuracy_threshold | 0.844 | |
|
| cosine_f1 | 0.9075 | |
|
| cosine_f1_threshold | 0.823 | |
|
| cosine_precision | 0.8729 | |
|
| cosine_recall | 0.945 | |
|
| cosine_ap | 0.961 | |
|
| dot_accuracy | 0.916 | |
|
| dot_accuracy_threshold | 0.844 | |
|
| dot_f1 | 0.9075 | |
|
| dot_f1_threshold | 0.823 | |
|
| dot_precision | 0.8729 | |
|
| dot_recall | 0.945 | |
|
| dot_ap | 0.961 | |
|
| manhattan_accuracy | 0.916 | |
|
| manhattan_accuracy_threshold | 8.5812 | |
|
| manhattan_f1 | 0.9075 | |
|
| manhattan_f1_threshold | 9.3271 | |
|
| manhattan_precision | 0.8729 | |
|
| manhattan_recall | 0.945 | |
|
| manhattan_ap | 0.9613 | |
|
| euclidean_accuracy | 0.916 | |
|
| euclidean_accuracy_threshold | 0.5585 | |
|
| euclidean_f1 | 0.9075 | |
|
| euclidean_f1_threshold | 0.595 | |
|
| euclidean_precision | 0.8729 | |
|
| euclidean_recall | 0.945 | |
|
| euclidean_ap | 0.961 | |
|
| max_accuracy | 0.916 | |
|
| max_accuracy_threshold | 8.5812 | |
|
| max_f1 | 0.9075 | |
|
| max_f1_threshold | 9.3271 | |
|
| max_precision | 0.8729 | |
|
| max_recall | 0.945 | |
|
| **max_ap** | **0.9613** | |
|
|
|
<!-- |
|
## 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: 2,332 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 | int | |
|
| details | <ul><li>min: 6 tokens</li><li>mean: 12.96 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 12.67 tokens</li><li>max: 55 tokens</li></ul> | <ul><li>0: ~52.80%</li><li>1: ~47.20%</li></ul> | |
|
* Samples: |
|
| sentence1 | sentence2 | label | |
|
|:-----------------------------------------------------------------------|:---------------------------------------------------------|:---------------| |
|
| <code>How to bake a chocolate cake?</code> | <code>Recipe for baking a chocolate cake</code> | <code>1</code> | |
|
| <code>Why do girls want to be friends with the guy they reject?</code> | <code>How do guys feel after rejecting a girl?</code> | <code>0</code> | |
|
| <code>How can I stop being afraid of working?</code> | <code>How do you stop being afraid of everything?</code> | <code>0</code> | |
|
* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss) |
|
|
|
### Evaluation Dataset |
|
|
|
#### Unnamed Dataset |
|
|
|
|
|
* Size: 260 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 | int | |
|
| details | <ul><li>min: 6 tokens</li><li>mean: 13.44 tokens</li><li>max: 39 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 12.99 tokens</li><li>max: 50 tokens</li></ul> | <ul><li>0: ~50.77%</li><li>1: ~49.23%</li></ul> | |
|
* Samples: |
|
| sentence1 | sentence2 | label | |
|
|:-----------------------------------------|:--------------------------------------------------|:---------------| |
|
| <code>How to cook spaghetti?</code> | <code>Steps to cook spaghetti</code> | <code>1</code> | |
|
| <code>How to create a mobile app?</code> | <code>How to create a desktop application?</code> | <code>0</code> | |
|
| <code>How can I update my resume?</code> | <code>Steps to revise and update a resume</code> | <code>1</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 |
|
- `num_train_epochs`: 4 |
|
- `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`: 0.0 |
|
- `adam_beta1`: 0.9 |
|
- `adam_beta2`: 0.999 |
|
- `adam_epsilon`: 1e-08 |
|
- `max_grad_norm`: 1.0 |
|
- `num_train_epochs`: 4 |
|
- `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 | - | - | 0.6979 | - | |
|
| 0.2740 | 10 | 1.9007 | - | - | - | |
|
| 0.5479 | 20 | 1.1616 | - | - | - | |
|
| 0.8219 | 30 | 0.9094 | - | - | - | |
|
| 0.9863 | 36 | - | 0.7692 | 0.9117 | - | |
|
| 1.0959 | 40 | 0.9105 | - | - | - | |
|
| 1.3699 | 50 | 0.6629 | - | - | - | |
|
| 1.6438 | 60 | 0.4243 | - | - | - | |
|
| 1.9178 | 70 | 0.4729 | - | - | - | |
|
| **2.0** | **73** | **-** | **0.7294** | **0.9306** | **-** | |
|
| 2.1918 | 80 | 0.4897 | - | - | - | |
|
| 2.4658 | 90 | 0.3103 | - | - | - | |
|
| 2.7397 | 100 | 0.2316 | - | - | - | |
|
| 2.9863 | 109 | - | 0.7807 | 0.9311 | - | |
|
| 3.0137 | 110 | 0.3179 | - | - | - | |
|
| 3.2877 | 120 | 0.1975 | - | - | - | |
|
| 3.5616 | 130 | 0.1477 | - | - | - | |
|
| 3.8356 | 140 | 0.1034 | - | - | - | |
|
| 3.9452 | 144 | - | 0.8132 | 0.9323 | 0.9613 | |
|
|
|
* 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.* |
|
--> |
