fyp / README.md

scr17

Upload fine-tuned model

6986cfa 9 months ago

preview code

raw

history blame contribute delete

16.9 kB

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:5000
  - loss:CosineSimilarityLoss
base_model: sentence-transformers/all-MiniLM-L6-v2
widget:
  - source_sentence: >-
      looking Product Manager expertise AWS Cybersecurity JavaScript Cloud
      Architecture candidate responsible designing implementing maintaining
      solutions using modern technologies
    sentences:
      - >-
        Emily Barry professional skilled JavaScript Machine Learning Kubernetes
        Computer Vision Experienced working multiple projects involving cloud
        technologies modern software development practices
      - >-
        Stephen Baker professional skilled React AWS Node.js NLP Experienced
        working multiple projects involving cloud technologies modern software
        development practices
      - >-
        James Jackson professional skilled Node.js Cybersecurity Kubernetes
        Docker Experienced working multiple projects involving cloud
        technologies modern software development practices
  - source_sentence: >-
      looking Software Engineer expertise AWS TensorFlow NLP Node.js candidate
      responsible designing implementing maintaining solutions using modern
      technologies
    sentences:
      - >-
        Jennifer Thompson professional skilled JavaScript TensorFlow Computer
        Vision Django Experienced working multiple projects involving cloud
        technologies modern software development practices
      - >-
        Lisa Bell professional skilled Python TensorFlow Computer Vision Machine
        Learning Experienced working multiple projects involving cloud
        technologies modern software development practices
      - >-
        Susan Rogers professional skilled Docker Cybersecurity Machine Learning
        Python Experienced working multiple projects involving cloud
        technologies modern software development practices
  - source_sentence: >-
      looking DevOps Engineer expertise Cybersecurity Machine Learning SQL
      TensorFlow candidate responsible designing implementing maintaining
      solutions using modern technologies
    sentences:
      - >-
        Kenneth Jones professional skilled NLP Node.js Cybersecurity Cloud
        Architecture Experienced working multiple projects involving cloud
        technologies modern software development practices
      - >-
        Matthew Mcintyre professional skilled NoSQL Kubernetes React Docker
        Experienced working multiple projects involving cloud technologies
        modern software development practices
      - >-
        William Wilson professional skilled SQL Kubernetes CI/CD Security
        Analysis Experienced working multiple projects involving cloud
        technologies modern software development practices
  - source_sentence: >-
      looking Software Engineer expertise Cybersecurity NLP SQL Django candidate
      responsible designing implementing maintaining solutions using modern
      technologies
    sentences:
      - >-
        Daniel Stewart professional skilled JavaScript Python Cybersecurity
        TensorFlow Experienced working multiple projects involving cloud
        technologies modern software development practices
      - >-
        Kristy Massey MD professional skilled Django Security Analysis
        JavaScript Cybersecurity Experienced working multiple projects involving
        cloud technologies modern software development practices
      - >-
        Melanie Sutton professional skilled Django CI/CD JavaScript SQL
        Experienced working multiple projects involving cloud technologies
        modern software development practices
  - source_sentence: >-
      looking AI Researcher expertise CI/CD Docker TensorFlow JavaScript
      candidate responsible designing implementing maintaining solutions using
      modern technologies
    sentences:
      - >-
        Dr. William Ramirez professional skilled NoSQL React CI/CD Cloud
        Architecture Experienced working multiple projects involving cloud
        technologies modern software development practices
      - >-
        Rebecca Wiley professional skilled Python Kubernetes Node.js JavaScript
        Experienced working multiple projects involving cloud technologies
        modern software development practices
      - >-
        Roberta Graham professional skilled Flask Machine Learning Node.js
        Docker Experienced working multiple projects involving cloud
        technologies modern software development practices
pipeline_tag: sentence-similarity
library_name: sentence-transformers

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. 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: sentence-transformers/all-MiniLM-L6-v2
Maximum Sequence Length: 256 tokens
Output Dimensionality: 384 dimensions
Similarity Function: Cosine Similarity

Model Sources

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

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 256, '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:

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 = [
    'looking AI Researcher expertise CI/CD Docker TensorFlow JavaScript candidate responsible designing implementing maintaining solutions using modern technologies',
    'Roberta Graham professional skilled Flask Machine Learning Node.js Docker Experienced working multiple projects involving cloud technologies modern software development practices',
    'Rebecca Wiley professional skilled Python Kubernetes Node.js JavaScript Experienced working multiple projects involving cloud technologies modern software development practices',
]
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]

Training Details

Training Dataset

Unnamed Dataset

Size: 5,000 training samples
Columns: sentence_0, sentence_1, and label
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label
type string string float
details
min: 20 tokens
mean: 24.72 tokens
max: 32 tokens

min: 22 tokens
mean: 26.26 tokens
max: 34 tokens

min: 0.4
mean: 0.71
max: 1.0

	sentence_0	sentence_1	label
type	string	string	float
details	min: 20 tokens mean: 24.72 tokens max: 32 tokens	min: 22 tokens mean: 26.26 tokens max: 34 tokens	min: 0.4 mean: 0.71 max: 1.0

Samples:

sentence_0	sentence_1	label
`looking AI Researcher expertise CI/CD Python Computer Vision Flask candidate responsible designing implementing maintaining solutions using modern technologies`	`Deanna Gibson professional skilled Security Analysis Node.js Machine Learning Kubernetes Experienced working multiple projects involving cloud technologies modern software development practices`	`0.481`
`looking Machine Learning Engineer expertise AWS Kubernetes Python Django candidate responsible designing implementing maintaining solutions using modern technologies`	`Amanda Johnson professional skilled AWS NLP Node.js Security Analysis Experienced working multiple projects involving cloud technologies modern software development practices`	`0.982`
`looking Cybersecurity Analyst expertise JavaScript Python Node.js NoSQL candidate responsible designing implementing maintaining solutions using modern technologies`	`Alicia Patton professional skilled Node.js TensorFlow SQL NoSQL Experienced working multiple projects involving cloud technologies modern software development practices`	`0.597`

Loss: CosineSimilarityLoss with these parameters:

{
    "loss_fct": "torch.nn.modules.loss.MSELoss"
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 30
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: no
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
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: 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: 30
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
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: 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}
tp_size: 0
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: None
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
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: round_robin

Training Logs

Epoch	Step	Training Loss
1.5974	500	0.0324
3.1949	1000	0.0298
4.7923	1500	0.028
6.3898	2000	0.025
7.9872	2500	0.0229
9.5847	3000	0.0198
11.1821	3500	0.0179
12.7796	4000	0.0156
14.3770	4500	0.014
15.9744	5000	0.0127
17.5719	5500	0.0115
19.1693	6000	0.0104
20.7668	6500	0.0098
22.3642	7000	0.009
23.9617	7500	0.0086
25.5591	8000	0.0082
27.1565	8500	0.0078
28.7540	9000	0.0076

Framework Versions

Python: 3.11.12
Sentence Transformers: 3.4.1
Transformers: 4.51.3
PyTorch: 2.6.0+cu124
Accelerate: 1.5.2
Datasets: 3.5.0
Tokenizers: 0.21.1

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",
}