metadata

base_model: sentence-transformers/all-mpnet-base-v2
library_name: sentence-transformers
metrics:
  - cosine_accuracy
  - dot_accuracy
  - manhattan_accuracy
  - euclidean_accuracy
  - max_accuracy
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:6462
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: gain successful RDP authentication
    sentences:
      - Creates or Schedules a task.
      - >-
        Execute processes on other systems complete with full interactivity for
        console applications without having to manually install client software.
      - >-
        allows users to execute commands remotely on target systems using
        various methods including WMI, SMB, SSH, RDP, and PowerShell
  - source_sentence: collect and stage the informaiton in AD
    sentences:
      - >-
        Displays the directory structure of a path or of the disk in a drive
        graphically.
      - >-
        Get user name and group information along with the respective security
        identifiers (SID) claims privileges logon identifier (logon ID) for the
        current user on the local system.
      - retrieve stored passwords from various software and operating systems
  - source_sentence: Download files or binary for further usage
    sentences:
      - >-
        allows users to extract sensitive credential information from the Local
        Security Authority (LSA) on Windows systems.
      - Transfer data from or to a server using URLs.
      - >-
        Displays and modifies entries in the Address Resolution Protocol (ARP)
        cache.
  - source_sentence: collect and stage the informaiton in AD
    sentences:
      - Adds displays or modifies global groups in domains.
      - Gets the local security groups.
      - >-
        Displays the directory structure of a path or of the disk in a drive
        graphically.
  - source_sentence: Modify Registry of Current User Profile
    sentences:
      - Stops one or more running services.
      - Allows users to manage local and domain user accounts.
      - >-
        Saves a copy of specified subkeys, entries,  and values of the registry
        in a specified file.
model-index:
  - name: SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
    results:
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: dev
          type: dev
        metrics:
          - type: cosine_accuracy
            value: 1
            name: Cosine Accuracy
          - type: dot_accuracy
            value: 0
            name: Dot Accuracy
          - type: manhattan_accuracy
            value: 1
            name: Manhattan Accuracy
          - type: euclidean_accuracy
            value: 1
            name: Euclidean Accuracy
          - type: max_accuracy
            value: 1
            name: Max Accuracy
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: test
          type: test
        metrics:
          - type: cosine_accuracy
            value: 1
            name: Cosine Accuracy
          - type: dot_accuracy
            value: 0
            name: Dot Accuracy
          - type: manhattan_accuracy
            value: 1
            name: Manhattan Accuracy
          - type: euclidean_accuracy
            value: 1
            name: Euclidean Accuracy
          - type: max_accuracy
            value: 1
            name: Max Accuracy

SentenceTransformer based on sentence-transformers/all-mpnet-base-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-mpnet-base-v2. 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: sentence-transformers/all-mpnet-base-v2
Maximum Sequence Length: 384 tokens
Output Dimensionality: 768 tokens
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': 384, 'do_lower_case': False}) with Transformer model: MPNetModel 
  (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})
  (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("brilan/procedure-tool-matching_3_epochs")
# Run inference
sentences = [
    'Modify Registry of Current User Profile',
    'Saves a copy of specified subkeys, entries,  and values of the registry in a specified file.',
    'Stops one or more running services.',
]
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]

Evaluation

Metrics

Triplet

Dataset: dev
Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	1.0
dot_accuracy	0.0
manhattan_accuracy	1.0
euclidean_accuracy	1.0
max_accuracy	1.0

Triplet

Dataset: test
Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	1.0
dot_accuracy	0.0
manhattan_accuracy	1.0
euclidean_accuracy	1.0
max_accuracy	1.0

Training Details

Training Dataset

Unnamed Dataset

Size: 6,462 training samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 5 tokens mean: 9.62 tokens max: 17 tokens	min: 5 tokens mean: 18.14 tokens max: 47 tokens	min: 5 tokens mean: 17.66 tokens max: 57 tokens

Samples:

anchor	positive	negative
`used compromised domain accounts to gain access to the target environment`	`allows users to execute commands remotely on target systems using various methods including WMI, SMB, SSH, RDP, and PowerShell`	`Displays information about user sessions on a Remote Desktop Session Host server.`
`use default credentials to connect to IPC$ shares on remote machines`	`Execute commands on remote targets via Remote Desktop Protocol (RDP) without requiring a graphical user interface (GUI).`	`It provides functionality to view create modify and delete user accounts directly from the command prompt.`
`gain access to the server via SSH`	`allow users to connect to RDP servers`	`allows administrators to manage and configure audit policies for the system and provides the ability to view, set, and modify the audit policies that control what events are logged by the Windows security auditing subsystem.`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Evaluation Dataset

Unnamed Dataset

Size: 2,770 evaluation samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 5 tokens mean: 9.48 tokens max: 17 tokens	min: 5 tokens mean: 18.31 tokens max: 47 tokens	min: 5 tokens mean: 18.21 tokens max: 57 tokens

Samples:

anchor	positive	negative
`Disable Windows Services related to security products`	`stop running service`	`Creates lists and deletes stored user names and passwords or credentials.`
`Get user information`	`Gets the local security groups.`	`Copy files from source to dest between local and remote machine skipping identical files.`
`used pass the hash for lateral movement`	`Execute processes on other systems complete with full interactivity for console applications without having to manually install client software.`	`Extracts passwords keys,pin,codes,tickets from the memory of lsass`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
warmup_ratio: 0.1
fp16: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
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: 1.0
num_train_epochs: 3
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
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
eval_use_gather_object: False
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	dev_cosine_accuracy	test_cosine_accuracy
0	0	-	-	0.8596	-
0.2475	100	2.0428	1.3753	0.9989	-
0.4950	200	1.5299	1.2361	1.0	-
0.7426	300	1.4871	1.1853	1.0	-
0.9901	400	1.4612	1.1707	1.0	-
1.2376	500	0.0287	1.2190	1.0	-
1.1584	600	0.9192	1.1738	1.0	-
1.4059	700	1.4131	1.1708	1.0	-
1.6535	800	1.4254	1.1428	1.0	-
1.9010	900	1.3977	1.1373	1.0	-
2.1485	1000	0.5379	1.1419	1.0	-
2.0693	1100	0.386	1.1306	1.0	-
2.3168	1200	1.3708	1.1260	1.0	-
2.3465	1212	-	-	-	1.0

Framework Versions

Python: 3.11.5
Sentence Transformers: 3.1.0
Transformers: 4.44.2
PyTorch: 2.4.1+cu121
Accelerate: 1.0.0
Datasets: 3.0.1
Tokenizers: 0.19.1

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",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}