aiformes-models / README.md

eyaferjani

Upload 8 files

9920fce verified 2 days ago

preview code

Raw

History Blame Contribute Delete

14.7 kB

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:4500
  - loss:CosineSimilarityLoss
base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
widget:
  - source_sentence: Honnêtement, mon stress est modéré, je gère globalement bien
    sentences:
      - Je suis passionné par mes missions
      - Très élevé, épuisé
      - Je suis bien dans mon poste mais les perspectives d'évolution manquent
  - source_sentence: Franchement, incertain, à voir selon l'évolution de l'entreprise
    sentences:
      - Je suis serein, aucune pression excessive
      - Honnêtement, je ne sais pas encore, peut-être rester ou explorer
      - Franchement, je me vois évoluer ici, obtenir une promotion
  - source_sentence: Franchement, je construis mon avenir ici, pas question de partir
    sentences:
      - Je suis mécontent de la façon dont je suis traité
      - Je passe des entretiens pour explorer d'autres opportunités
      - Je suis fidèle à cette entreprise, elle me correspond
  - source_sentence: Correct, sans plus
    sentences:
      - Franchement, bien, pas de pression
      - Franchement, les valeurs correspondent à peu près
      - Franchement, pas du tout motivé
  - source_sentence: Franchement, je ne cherche pas du tout à partir, je suis épanoui ici
    sentences:
      - Cette entreprise est une étape, pas une destination finale
      - Cette expérience est temporaire dans mon parcours
      - Franchement, les valeurs de l'entreprise correspondent aux miennes
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - pearson_cosine
  - spearman_cosine
model-index:
  - name: >-
      SentenceTransformer based on
      sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: val rh
          type: val_rh
        metrics:
          - type: pearson_cosine
            value: 0.995510812995037
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.9788444539668885
            name: Spearman Cosine

SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

This is a sentence-transformers model finetuned from sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
Maximum Sequence Length: 128 tokens
Output Dimensionality: 384 dimensions
Similarity Function: Cosine Similarity
Supported Modality: Text

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
  (1): Pooling({'embedding_dimension': 384, 'pooling_mode': 'mean', 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    'Franchement, je ne cherche pas du tout à partir, je suis épanoui ici',
    'Cette expérience est temporaire dans mon parcours',
    "Franchement, les valeurs de l'entreprise correspondent aux miennes",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.2799, 0.9658],
#         [0.2799, 1.0000, 0.3024],
#         [0.9658, 0.3024, 1.0000]])

Evaluation

Metrics

Semantic Similarity

Dataset: val_rh
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.9955
spearman_cosine	0.9788

Training Details

Training Dataset

Unnamed Dataset

Size: 4,500 training samples
Columns: sentence_0, sentence_1, and label

Approximate statistics based on the first 100 samples:

	sentence_0	sentence_1	label
type	string	string	float
modality	text	text
details	min: 8 tokens mean: 15.15 tokens max: 24 tokens	min: 4 tokens mean: 14.33 tokens max: 26 tokens	min: 0.13 mean: 0.62 max: 1.0

Samples:

sentence_0	sentence_1	label
`Honnêtement, je postule à d'autres offres régulièrement`	`Je veux partir le plus tôt possible`	`0.96`
`Honnêtement, mon avenir est ici, je ne cherche pas ailleurs`	`Je suis ici pour apprendre puis je verrai la suite ailleurs`	`0.35`
`Honnêtement, je suis très satisfait de mon poste`	`Franchement, je suis mécontent de la façon dont je suis traité`	`0.17999999999999994`

Loss: CosineSimilarityLoss with these parameters:

{
    "loss_fct": "torch.nn.modules.loss.MSELoss",
    "cos_score_transformation": "torch.nn.modules.linear.Identity"
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 10
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

do_predict: False
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_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
num_train_epochs: 10
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_ratio: None
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
enable_jit_checkpoint: False
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
use_cpu: False
seed: 42
data_seed: None
bf16: False
fp16: False
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: -1
ddp_backend: None
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
parallelism_config: None
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch_fused
optim_args: None
group_by_length: False
length_column_name: length
project: huggingface
trackio_space_id: trackio
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
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
hub_revision: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_for_metrics: []
eval_do_concat_batches: True
auto_find_batch_size: False
full_determinism: False
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_num_input_tokens_seen: no
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: True
use_cache: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	val_rh_spearman_cosine
0.7092	200	-	0.9140
1.0	282	-	0.9358
1.4184	400	-	0.9261
1.7730	500	0.0233	-
2.0	564	-	0.9569
2.1277	600	-	0.9572
2.8369	800	-	0.9600
3.0	846	-	0.9636
3.5461	1000	0.0020	0.9642
4.0	1128	-	0.9698
4.2553	1200	-	0.9690
4.9645	1400	-	0.9738
5.0	1410	-	0.9736
5.3191	1500	0.0013	-
5.6738	1600	-	0.9717
6.0	1692	-	0.9723
6.3830	1800	-	0.9733
7.0	1974	-	0.9766
7.0922	2000	0.0010	0.9764
7.8014	2200	-	0.9781
8.0	2256	-	0.9774
8.5106	2400	-	0.9776
8.8652	2500	0.0008	-
9.0	2538	-	0.9781
9.2199	2600	-	0.9785
9.9291	2800	-	0.9788
10.0	2820	-	0.9788

Training Time

Training: 6.6 minutes

Framework Versions

Python: 3.12.13
Sentence Transformers: 5.5.1
Transformers: 5.0.0
PyTorch: 2.11.0+cu128
Accelerate: 1.13.0
Datasets: 4.0.0
Tokenizers: 0.22.2

Citation

BibTeX

Sentence Transformers

@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",
}