|
--- |
|
tags: |
|
- sentence-transformers |
|
- sentence-similarity |
|
- feature-extraction |
|
- generated_from_trainer |
|
- dataset_size:234000 |
|
- loss:MSELoss |
|
base_model: google-bert/bert-base-multilingual-uncased |
|
widget: |
|
- source_sentence: who sings in spite of ourselves with john prine |
|
sentences: |
|
- es |
|
- når ble michael jordan draftet til nba |
|
- quien canta en spite of ourselves con john prine |
|
- source_sentence: who wrote when you look me in the eyes |
|
sentences: |
|
- متى بدأت الفتاة الكشفية في بيع ملفات تعريف الارتباط |
|
- A écrit when you look me in the eyes |
|
- fr |
|
- source_sentence: when was fathers day made a national holiday |
|
sentences: |
|
- wann wurde der Vatertag zum nationalen Feiertag |
|
- de |
|
- ' អ្នកណាច្រៀង i want to sing you a love song' |
|
- source_sentence: what is the density of the continental crust |
|
sentences: |
|
- cuál es la densidad de la corteza continental |
|
- wie zingt i want to sing you a love song |
|
- es |
|
- source_sentence: who wrote the song i shot the sheriff |
|
sentences: |
|
- Quel est l'âge légal pour consommer du vin au Canada? |
|
- i shot the sheriff şarkısını kim besteledi |
|
- tr |
|
pipeline_tag: sentence-similarity |
|
library_name: sentence-transformers |
|
metrics: |
|
- negative_mse |
|
model-index: |
|
- name: SentenceTransformer based on google-bert/bert-base-multilingual-uncased |
|
results: |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to ar |
|
type: MSE-val-en-to-ar |
|
metrics: |
|
- type: negative_mse |
|
value: -20.37721574306488 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to da |
|
type: MSE-val-en-to-da |
|
metrics: |
|
- type: negative_mse |
|
value: -17.167489230632782 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to de |
|
type: MSE-val-en-to-de |
|
metrics: |
|
- type: negative_mse |
|
value: -17.10948944091797 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to en |
|
type: MSE-val-en-to-en |
|
metrics: |
|
- type: negative_mse |
|
value: -15.333698689937592 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to es |
|
type: MSE-val-en-to-es |
|
metrics: |
|
- type: negative_mse |
|
value: -16.898061335086823 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to fi |
|
type: MSE-val-en-to-fi |
|
metrics: |
|
- type: negative_mse |
|
value: -18.428558111190796 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to fr |
|
type: MSE-val-en-to-fr |
|
metrics: |
|
- type: negative_mse |
|
value: -17.04207956790924 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to he |
|
type: MSE-val-en-to-he |
|
metrics: |
|
- type: negative_mse |
|
value: -19.942057132720947 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to hu |
|
type: MSE-val-en-to-hu |
|
metrics: |
|
- type: negative_mse |
|
value: -18.757066130638123 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to it |
|
type: MSE-val-en-to-it |
|
metrics: |
|
- type: negative_mse |
|
value: -17.18708872795105 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to ja |
|
type: MSE-val-en-to-ja |
|
metrics: |
|
- type: negative_mse |
|
value: -19.915536046028137 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to ko |
|
type: MSE-val-en-to-ko |
|
metrics: |
|
- type: negative_mse |
|
value: -21.39919400215149 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to km |
|
type: MSE-val-en-to-km |
|
metrics: |
|
- type: negative_mse |
|
value: -28.658682107925415 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to ms |
|
type: MSE-val-en-to-ms |
|
metrics: |
|
- type: negative_mse |
|
value: -17.25209951400757 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to nl |
|
type: MSE-val-en-to-nl |
|
metrics: |
|
- type: negative_mse |
|
value: -16.605134308338165 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to no |
|
type: MSE-val-en-to-no |
|
metrics: |
|
- type: negative_mse |
|
value: -17.149969935417175 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to pl |
|
type: MSE-val-en-to-pl |
|
metrics: |
|
- type: negative_mse |
|
value: -17.846450209617615 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to pt |
|
type: MSE-val-en-to-pt |
|
metrics: |
|
- type: negative_mse |
|
value: -17.19353199005127 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to ru |
|
type: MSE-val-en-to-ru |
|
metrics: |
|
- type: negative_mse |
|
value: -18.13419610261917 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to sv |
|
type: MSE-val-en-to-sv |
|
metrics: |
|
- type: negative_mse |
|
value: -17.13200956583023 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to th |
|
type: MSE-val-en-to-th |
|
metrics: |
|
- type: negative_mse |
|
value: -26.43084228038788 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to tr |
|
type: MSE-val-en-to-tr |
|
metrics: |
|
- type: negative_mse |
|
value: -18.183308839797974 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to vi |
|
type: MSE-val-en-to-vi |
|
metrics: |
|
- type: negative_mse |
|
value: -18.749597668647766 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to zh cn |
|
type: MSE-val-en-to-zh_cn |
|
metrics: |
|
- type: negative_mse |
|
value: -18.811793625354767 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to zh hk |
|
type: MSE-val-en-to-zh_hk |
|
metrics: |
|
- type: negative_mse |
|
value: -18.54081153869629 |
|
name: Negative Mse |
|
- task: |
|
type: knowledge-distillation |
|
name: Knowledge Distillation |
|
dataset: |
|
name: MSE val en to zh tw |
|
type: MSE-val-en-to-zh_tw |
|
metrics: |
|
- type: negative_mse |
|
value: -19.14038509130478 |
|
name: Negative Mse |
|
--- |
|
|
|
# SentenceTransformer based on google-bert/bert-base-multilingual-uncased |
|
|
|
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [google-bert/bert-base-multilingual-uncased](https://huggingface.co/google-bert/bert-base-multilingual-uncased). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
- **Model Type:** Sentence Transformer |
|
- **Base model:** [google-bert/bert-base-multilingual-uncased](https://huggingface.co/google-bert/bert-base-multilingual-uncased) <!-- at revision 7cbf9a625e29989f6b9c6c2fa68234c304f7e38f --> |
|
- **Maximum Sequence Length:** 128 tokens |
|
- **Output Dimensionality:** 768 dimensions |
|
- **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': 128, 'do_lower_case': False}) with Transformer model: BertModel |
|
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) |
|
) |
|
``` |
|
|
|
## Usage |
|
|
|
### Direct Usage (Sentence Transformers) |
|
|
|
First install the Sentence Transformers library: |
|
|
|
```bash |
|
pip install -U sentence-transformers |
|
``` |
|
|
|
Then you can load this model and run inference. |
|
```python |
|
from sentence_transformers import SentenceTransformer |
|
|
|
# Download from the 🤗 Hub |
|
model = SentenceTransformer("luanafelbarros/bert-base-multilingual-uncased-matryoshka-mkqa") |
|
# Run inference |
|
sentences = [ |
|
'who wrote the song i shot the sheriff', |
|
'i shot the sheriff şarkısını kim besteledi', |
|
'tr', |
|
] |
|
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 |
|
|
|
#### Knowledge Distillation |
|
|
|
* Datasets: `MSE-val-en-to-ar`, `MSE-val-en-to-da`, `MSE-val-en-to-de`, `MSE-val-en-to-en`, `MSE-val-en-to-es`, `MSE-val-en-to-fi`, `MSE-val-en-to-fr`, `MSE-val-en-to-he`, `MSE-val-en-to-hu`, `MSE-val-en-to-it`, `MSE-val-en-to-ja`, `MSE-val-en-to-ko`, `MSE-val-en-to-km`, `MSE-val-en-to-ms`, `MSE-val-en-to-nl`, `MSE-val-en-to-no`, `MSE-val-en-to-pl`, `MSE-val-en-to-pt`, `MSE-val-en-to-ru`, `MSE-val-en-to-sv`, `MSE-val-en-to-th`, `MSE-val-en-to-tr`, `MSE-val-en-to-vi`, `MSE-val-en-to-zh_cn`, `MSE-val-en-to-zh_hk` and `MSE-val-en-to-zh_tw` |
|
* Evaluated with [<code>MSEEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.MSEEvaluator) |
|
|
|
| Metric | MSE-val-en-to-ar | MSE-val-en-to-da | MSE-val-en-to-de | MSE-val-en-to-en | MSE-val-en-to-es | MSE-val-en-to-fi | MSE-val-en-to-fr | MSE-val-en-to-he | MSE-val-en-to-hu | MSE-val-en-to-it | MSE-val-en-to-ja | MSE-val-en-to-ko | MSE-val-en-to-km | MSE-val-en-to-ms | MSE-val-en-to-nl | MSE-val-en-to-no | MSE-val-en-to-pl | MSE-val-en-to-pt | MSE-val-en-to-ru | MSE-val-en-to-sv | MSE-val-en-to-th | MSE-val-en-to-tr | MSE-val-en-to-vi | MSE-val-en-to-zh_cn | MSE-val-en-to-zh_hk | MSE-val-en-to-zh_tw | |
|
|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:-----------------|:--------------------|:--------------------|:--------------------| |
|
| **negative_mse** | **-20.3772** | **-17.1675** | **-17.1095** | **-15.3337** | **-16.8981** | **-18.4286** | **-17.0421** | **-19.9421** | **-18.7571** | **-17.1871** | **-19.9155** | **-21.3992** | **-28.6587** | **-17.2521** | **-16.6051** | **-17.15** | **-17.8465** | **-17.1935** | **-18.1342** | **-17.132** | **-26.4308** | **-18.1833** | **-18.7496** | **-18.8118** | **-18.5408** | **-19.1404** | |
|
|
|
<!-- |
|
## 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: 234,000 training samples |
|
* Columns: <code>english</code>, <code>non-english</code>, <code>target</code>, and <code>label</code> |
|
* Approximate statistics based on the first 1000 samples: |
|
| | english | non-english | target | label | |
|
|:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:-------------------------------------| |
|
| type | string | string | string | list | |
|
| details | <ul><li>min: 10 tokens</li><li>mean: 11.48 tokens</li><li>max: 16 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 13.27 tokens</li><li>max: 33 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.38 tokens</li><li>max: 7 tokens</li></ul> | <ul><li>size: 768 elements</li></ul> | |
|
* Samples: |
|
| english | non-english | target | label | |
|
|:-------------------------------------------------|:--------------------------------------------------------|:----------------|:------------------------------------------------------------------------------------------------------------------------| |
|
| <code>who plays hope on days of our lives</code> | <code>من الذي يلعب الأمل في أيام حياتنا</code> | <code>ar</code> | <code>[0.2171212136745453, 0.5138550996780396, 0.5517176389694214, -1.0655105113983154, 1.5853567123413086, ...]</code> | |
|
| <code>who plays hope on days of our lives</code> | <code>hvem spiller hope i Horton-sagaen</code> | <code>da</code> | <code>[0.2171212136745453, 0.5138550996780396, 0.5517176389694214, -1.0655105113983154, 1.5853567123413086, ...]</code> | |
|
| <code>who plays hope on days of our lives</code> | <code>Wer spielt die Hope in Zeit der Sehnsucht?</code> | <code>de</code> | <code>[0.2171212136745453, 0.5138550996780396, 0.5517176389694214, -1.0655105113983154, 1.5853567123413086, ...]</code> | |
|
* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#mseloss) |
|
|
|
### Evaluation Dataset |
|
|
|
#### Unnamed Dataset |
|
|
|
|
|
* Size: 13,000 evaluation samples |
|
* Columns: <code>english</code>, <code>non-english</code>, <code>target</code>, and <code>label</code> |
|
* Approximate statistics based on the first 1000 samples: |
|
| | english | non-english | target | label | |
|
|:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:-------------------------------------| |
|
| type | string | string | string | list | |
|
| details | <ul><li>min: 10 tokens</li><li>mean: 11.53 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 13.37 tokens</li><li>max: 50 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.38 tokens</li><li>max: 7 tokens</li></ul> | <ul><li>size: 768 elements</li></ul> | |
|
* Samples: |
|
| english | non-english | target | label | |
|
|:------------------------------------------------------------|:----------------------------------------------------------------|:----------------|:-----------------------------------------------------------------------------------------------------------------------------| |
|
| <code>who played prudence on nanny and the professor</code> | <code>من لعب دور "prudence" فى "nanny and the professor"</code> | <code>ar</code> | <code>[-0.2837616801261902, -0.4943353235721588, 0.020107418298721313, 0.7796109318733215, -0.47365888953208923, ...]</code> | |
|
| <code>who played prudence on nanny and the professor</code> | <code>hvem spiller prudence på nanny and the professor</code> | <code>da</code> | <code>[-0.2837616801261902, -0.4943353235721588, 0.020107418298721313, 0.7796109318733215, -0.47365888953208923, ...]</code> | |
|
| <code>who played prudence on nanny and the professor</code> | <code>Wer spielte Prudence in Nanny and the Professor</code> | <code>de</code> | <code>[-0.2837616801261902, -0.4943353235721588, 0.020107418298721313, 0.7796109318733215, -0.47365888953208923, ...]</code> | |
|
* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#mseloss) |
|
|
|
### Training Hyperparameters |
|
#### Non-Default Hyperparameters |
|
|
|
- `eval_strategy`: steps |
|
- `per_device_train_batch_size`: 64 |
|
- `per_device_eval_batch_size`: 64 |
|
- `learning_rate`: 1e-05 |
|
- `num_train_epochs`: 1 |
|
- `warmup_ratio`: 0.1 |
|
- `fp16`: True |
|
|
|
#### All Hyperparameters |
|
<details><summary>Click to expand</summary> |
|
|
|
- `overwrite_output_dir`: False |
|
- `do_predict`: False |
|
- `eval_strategy`: steps |
|
- `prediction_loss_only`: 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 |
|
- `torch_empty_cache_steps`: None |
|
- `learning_rate`: 1e-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`: 42 |
|
- `data_seed`: None |
|
- `jit_mode_eval`: False |
|
- `use_ipex`: False |
|
- `bf16`: False |
|
- `fp16`: True |
|
- `fp16_opt_level`: O1 |
|
- `half_precision_backend`: auto |
|
- `bf16_full_eval`: False |
|
- `fp16_full_eval`: False |
|
- `tf32`: None |
|
- `local_rank`: 0 |
|
- `ddp_backend`: None |
|
- `tpu_num_cores`: None |
|
- `tpu_metrics_debug`: False |
|
- `debug`: [] |
|
- `dataloader_drop_last`: False |
|
- `dataloader_num_workers`: 0 |
|
- `dataloader_prefetch_factor`: None |
|
- `past_index`: -1 |
|
- `disable_tqdm`: False |
|
- `remove_unused_columns`: True |
|
- `label_names`: None |
|
- `load_best_model_at_end`: False |
|
- `ignore_data_skip`: False |
|
- `fsdp`: [] |
|
- `fsdp_min_num_params`: 0 |
|
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} |
|
- `fsdp_transformer_layer_cls_to_wrap`: None |
|
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} |
|
- `deepspeed`: None |
|
- `label_smoothing_factor`: 0.0 |
|
- `optim`: adamw_torch |
|
- `optim_args`: None |
|
- `adafactor`: False |
|
- `group_by_length`: False |
|
- `length_column_name`: length |
|
- `ddp_find_unused_parameters`: None |
|
- `ddp_bucket_cap_mb`: None |
|
- `ddp_broadcast_buffers`: 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 |
|
- `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 |
|
- `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 |
|
- `eval_on_start`: False |
|
- `use_liger_kernel`: False |
|
- `eval_use_gather_object`: False |
|
- `average_tokens_across_devices`: False |
|
- `prompts`: None |
|
- `batch_sampler`: batch_sampler |
|
- `multi_dataset_batch_sampler`: proportional |
|
|
|
</details> |
|
|
|
### Training Logs |
|
| Epoch | Step | Training Loss | Validation Loss | MSE-val-en-to-ar_negative_mse | MSE-val-en-to-da_negative_mse | MSE-val-en-to-de_negative_mse | MSE-val-en-to-en_negative_mse | MSE-val-en-to-es_negative_mse | MSE-val-en-to-fi_negative_mse | MSE-val-en-to-fr_negative_mse | MSE-val-en-to-he_negative_mse | MSE-val-en-to-hu_negative_mse | MSE-val-en-to-it_negative_mse | MSE-val-en-to-ja_negative_mse | MSE-val-en-to-ko_negative_mse | MSE-val-en-to-km_negative_mse | MSE-val-en-to-ms_negative_mse | MSE-val-en-to-nl_negative_mse | MSE-val-en-to-no_negative_mse | MSE-val-en-to-pl_negative_mse | MSE-val-en-to-pt_negative_mse | MSE-val-en-to-ru_negative_mse | MSE-val-en-to-sv_negative_mse | MSE-val-en-to-th_negative_mse | MSE-val-en-to-tr_negative_mse | MSE-val-en-to-vi_negative_mse | MSE-val-en-to-zh_cn_negative_mse | MSE-val-en-to-zh_hk_negative_mse | MSE-val-en-to-zh_tw_negative_mse | |
|
|:------:|:----:|:-------------:|:---------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:--------------------------------:|:--------------------------------:|:--------------------------------:| |
|
| 0.1367 | 500 | 0.3588 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |
|
| 0.2734 | 1000 | 0.3078 | 0.2868 | -27.3597 | -26.5326 | -26.5313 | -26.0601 | -26.4280 | -26.8319 | -26.4885 | -27.1627 | -26.9695 | -26.5628 | -27.2583 | -27.7239 | -31.2177 | -26.6501 | -26.4197 | -26.4809 | -26.6655 | -26.4345 | -26.6570 | -26.5526 | -30.4823 | -26.9554 | -27.1040 | -27.0230 | -26.9012 | -27.0515 | |
|
| 0.4102 | 1500 | 0.2846 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |
|
| 0.5469 | 2000 | 0.2707 | 0.2617 | -24.6096 | -22.8821 | -22.8752 | -21.8660 | -22.7026 | -23.6128 | -22.7468 | -24.2281 | -23.6469 | -22.9147 | -24.3616 | -25.2999 | -30.4061 | -23.0865 | -22.5916 | -22.8392 | -23.1451 | -22.7741 | -23.2652 | -22.9440 | -29.2747 | -23.5285 | -23.8786 | -23.6384 | -23.5170 | -23.8081 | |
|
| 0.6836 | 2500 | 0.2613 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |
|
| 0.8203 | 3000 | 0.2542 | 0.2491 | -23.2261 | -21.0314 | -20.9970 | -19.7599 | -20.8388 | -21.9791 | -20.8374 | -22.8299 | -22.0605 | -21.0367 | -22.9281 | -24.1290 | -29.9238 | -21.2195 | -20.6506 | -20.9939 | -21.4204 | -20.9651 | -21.5594 | -21.0815 | -28.3947 | -21.8046 | -22.2153 | -21.9866 | -21.8474 | -22.1930 | |
|
| 0.9571 | 3500 | 0.248 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |
|
| 1.0938 | 4000 | 0.2438 | 0.2420 | -22.4435 | -19.9880 | -19.9588 | -18.5856 | -19.7880 | -20.9892 | -19.8194 | -21.9951 | -21.1703 | -19.9940 | -22.1052 | -23.3569 | -29.5927 | -20.1685 | -19.5862 | -19.9676 | -20.4346 | -19.9623 | -20.6201 | -20.0273 | -27.9725 | -20.8061 | -21.2406 | -21.0913 | -20.9345 | -21.3353 | |
|
| 1.2305 | 4500 | 0.2401 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |
|
| 1.3672 | 5000 | 0.2371 | 0.2373 | -21.9444 | -19.3005 | -19.2441 | -17.7989 | -19.0868 | -20.3950 | -19.1305 | -21.5127 | -20.6068 | -19.3250 | -21.5673 | -22.8791 | -29.3793 | -19.4702 | -18.8669 | -19.2886 | -19.8258 | -19.3057 | -20.0101 | -19.3345 | -27.5779 | -20.1899 | -20.6284 | -20.5167 | -20.3229 | -20.7721 | |
|
| 1.5040 | 5500 | 0.2349 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |
|
| 1.6407 | 6000 | 0.2336 | 0.2346 | -21.6615 | -18.9016 | -18.8657 | -17.3452 | -18.6869 | -20.0105 | -18.7528 | -21.1990 | -20.2645 | -18.9266 | -21.2386 | -22.6295 | -29.2204 | -19.0695 | -18.4641 | -18.9026 | -19.4506 | -18.9074 | -19.6659 | -18.9515 | -27.3466 | -19.8162 | -20.2736 | -20.1841 | -19.9848 | -20.4531 | |
|
| 1.7774 | 6500 | 0.2319 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |
|
| 1.9141 | 7000 | 0.2309 | 0.2332 | -21.5220 | -18.7091 | -18.6632 | -17.1205 | -18.4809 | -19.8342 | -18.5557 | -21.0604 | -20.0990 | -18.7323 | -21.0808 | -22.4971 | -29.1680 | -18.8630 | -18.2583 | -18.6989 | -19.2859 | -18.7163 | -19.4929 | -18.7442 | -27.2443 | -19.6327 | -20.1037 | -20.0234 | -19.8106 | -20.3017 | |
|
| 0.1367 | 500 | 0.2302 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |
|
| 0.2734 | 1000 | 0.2261 | 0.2290 | -21.1100 | -18.0936 | -18.0277 | -16.4059 | -17.8516 | -19.2687 | -17.9684 | -20.6744 | -19.5689 | -18.1063 | -20.6725 | -22.0790 | -28.9503 | -18.2049 | -17.5842 | -18.0814 | -18.7115 | -18.1111 | -18.9581 | -18.1032 | -26.8510 | -19.0325 | -19.5538 | -19.6006 | -19.3362 | -19.8807 | |
|
| 0.4102 | 1500 | 0.222 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |
|
| 0.5469 | 2000 | 0.2188 | 0.2246 | -20.5835 | -17.4530 | -17.3853 | -15.6663 | -17.1929 | -18.6930 | -17.3208 | -20.1688 | -19.0165 | -17.4784 | -20.1460 | -21.6056 | -28.7345 | -17.5632 | -16.9100 | -17.4263 | -18.0993 | -17.4835 | -18.3902 | -17.4462 | -26.5854 | -18.4647 | -19.0091 | -19.0492 | -18.7904 | -19.3776 | |
|
| 0.6836 | 2500 | 0.2166 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |
|
| 0.8203 | 3000 | 0.2148 | 0.2226 | -20.3772 | -17.1675 | -17.1095 | -15.3337 | -16.8981 | -18.4286 | -17.0421 | -19.9421 | -18.7571 | -17.1871 | -19.9155 | -21.3992 | -28.6587 | -17.2521 | -16.6051 | -17.1500 | -17.8465 | -17.1935 | -18.1342 | -17.1320 | -26.4308 | -18.1833 | -18.7496 | -18.8118 | -18.5408 | -19.1404 | |
|
| 0.9571 | 3500 | 0.2133 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |
|
|
|
|
|
### Framework Versions |
|
- Python: 3.10.12 |
|
- Sentence Transformers: 3.3.1 |
|
- Transformers: 4.46.3 |
|
- PyTorch: 2.5.1+cu121 |
|
- Accelerate: 1.1.1 |
|
- Datasets: 3.1.0 |
|
- Tokenizers: 0.20.3 |
|
|
|
## 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", |
|
} |
|
``` |
|
|
|
#### MSELoss |
|
```bibtex |
|
@inproceedings{reimers-2020-multilingual-sentence-bert, |
|
title = "Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation", |
|
author = "Reimers, Nils and Gurevych, Iryna", |
|
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing", |
|
month = "11", |
|
year = "2020", |
|
publisher = "Association for Computational Linguistics", |
|
url = "https://arxiv.org/abs/2004.09813", |
|
} |
|
``` |
|
|
|
<!-- |
|
## 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.* |
|
--> |
