Первый запуск

2026-05-02 18:33:38 +03:00
commit cb55eaef01
51 changed files with 2127373 additions and 0 deletions
--- a/Resources/model/README.md
+++ b/Resources/model/README.md
@@ -0,0 +1,409 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:2400
+- loss:TripletLoss
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+widget:
+- source_sentence: id=certification<NUM>@yahoo.com <NUM> Volume [<IP>] '<NUM>' id=c<NUM>a<NUM>ac<NUM>
+    Latency Error to rendering connecting user:chorus_<NUM> [<NUM>a<NUM>bc] '<NUM>ecd<NUM>f'
+    'estimated<NUM>@example.org' started together [<NUM><NUM><NUM>] user:trying<NUM>@yandex.com
+    present <NUM> id=<NUM>c<NUM>b<NUM>ad
+  sentences:
+  - '''<NUM>'';<NUM><NUM><NUM>;goals;failed;Client;''<IP>'';Directory;killing;licence<NUM>@gmail.com;id=<NUM><NUM><NUM>;<NUM><NUM><NUM>;pound;Route;failed;authenticating;<NUM>;picture;through;Header;martin<NUM>@yahoo.com;<IP>;/var/log/unit.jpg;Route;deleted'
+  - id=positioning<NUM>@example.com;confidential;'/var/log/offer.awk';'/var/log/contain.dat';id=<NUM>;id=cute<NUM>@protonmail.com;'<NUM>';Packet;'<NUM>';locked;either;with;Transaction;updated;'<NUM>.<NUM>'
+  - id=collaboration<NUM>@example.com <NUM> Volume [<IP>] '<NUM>' id=<NUM>ec<NUM>cbb
+    Latency Error to rendering connecting user:depot_<NUM> [<NUM>eca] '<NUM>e<NUM>a<NUM>'
+    'prior<NUM>@yahoo.com' started together [<NUM><NUM><NUM>] user:solaris<NUM>@outlook.com
+    present <NUM> id=<NUM>b<NUM>d<NUM>
+- source_sentence: remote user:robbie_<NUM> <NUM> fundamental id=<NUM> User aborted
+    user:/var/log/with.jpeg through '/var/log/love.md' cycling '<NUM>.<NUM>' private
+    '<NUM>.<NUM>' 'indigenous_<NUM>' Database authenticating <NUM> 'universe<NUM>@protonmail.com'
+    Query <NUM> id=chris_<NUM> names
+  sentences:
+  - user:/var/log/silver.doc <NUM> User remote <NUM> names aborted 'smoke<NUM>@duck.com'
+    <NUM> authenticating '<NUM>.<NUM>' private cycling user:alto_<NUM> '<NUM>.<NUM>'
+    id=<NUM> Query fundamental Database '/var/log/wall.mov' through id=jonathan_<NUM>
+    'identification_<NUM>'
+  - fetching;[<NUM>ff<NUM>e<NUM>];available;HTTP/<NUM>;[<NUM>.<NUM>];POST;user:<NUM>.<NUM>;<NUM><NUM><NUM>;user:<NUM>;<NUM>.<NUM>;Session;System;user:san<NUM>@outlook.com;had;'<NUM>';user:/var/log/rich.tar.gz;Stack
+  - remote user:dvds_<NUM> <NUM> fundamental id=<NUM> User aborted user:/var/log/from.csv
+    through '/var/log/foot.dat' cycling '<NUM>.<NUM>' private '<NUM>.<NUM>' 'proposed_<NUM>'
+    Database authenticating <NUM> 'exceptional<NUM>@protonmail.com' Query <NUM> id=website_<NUM>
+    names
+- source_sentence: projection;local;insecure;Thread;'<IP>';<IP>;[<NUM>];with;Interface;Buffer;updated;'/var/log/write.bmp';user:clearly_<NUM>;active;afford;id=<NUM>ab<NUM>;Latency;[strain<NUM>@live.com];stupid<NUM>@gmail.com;Key;created
+  sentences:
+  - projection;local;insecure;Thread;'<IP>';<IP>;[<NUM>];with;Interface;Buffer;updated;'/var/log/shoe.jar';user:mirrors_<NUM>;active;afford;id=bac<NUM>cfa;Latency;[associations<NUM>@yandex.com];laos<NUM>@example.org;Key;created
+  - '''commercial_<NUM>''|''/var/log/piece.tar.gz''|Table|user:catering_<NUM>|user:<NUM>|authorizing|''<IP>''|oxygen|URI|started|Component|Packet|<NUM><NUM><NUM>|Interface|''/var/log/made.exe''|GET|user:resist<NUM>@yahoo.com|Payload|[<NUM>]'
+  - Port|user:pdf_<NUM>|<NUM>|user:<NUM>.<NUM>|[<NUM>f<NUM>c<NUM>dc]|'adb<NUM>e<NUM>'|implementing|user:<NUM>cfb<NUM>e<NUM>a|<NUM>.<NUM>|discussed|<NUM>|Memory|id=/var/log/dance.m<NUM>u|<NUM>.<NUM>|ceo|remote|'<NUM>.<NUM>'|user:<NUM>a<NUM>|JS
+- source_sentence: updated|national|rendering|comply|user:<NUM>|binding|Gateway|<IP>|resolving|responsible|[<NUM>]|'opportunities<NUM>@duck.com'|opens_<NUM>|JSON|retrying|Server|Error|'<NUM>ec<NUM>ca'|berkeley|id=<NUM>.<NUM>|System|torture|Job|id=f<NUM>d
+  sentences:
+  - connecting disconnected comes<NUM>@gmail.com unavailable Directory [/var/log/early.m<NUM>v]
+    with memorabilia active Payload to Index 'watershed_<NUM>' validated created <NUM>ad<NUM>
+  - origin<NUM>@yandex.com;'peaceful_<NUM>';user:<NUM>;URL;its;Gateway;Component;[<NUM>];[<NUM><NUM><NUM>];insecure;tune;'zero_<NUM>';Heap;HTTP/<NUM>;id=queue_<NUM>
+  - updated|national|rendering|comply|user:<NUM>|binding|Gateway|<IP>|resolving|responsible|[<NUM>]|'tools<NUM>@duck.com'|jury_<NUM>|JSON|retrying|Server|Error|'e<NUM>a<NUM>b<NUM>ce'|berkeley|id=<NUM>.<NUM>|System|torture|Job|id=bb<NUM>bc
+- source_sentence: authenticating YAML PATCH authorizing id=/var/log/seem.tar.xz [<NUM>]
+    rendering 'pursue_<NUM>' [<NUM><NUM><NUM>] fresh online authenticating GET Heap
+    CRITICAL Module id=bother_<NUM>
+  sentences:
+  - authenticating YAML PATCH authorizing id=/var/log/born.log [<NUM>] rendering 'school_<NUM>'
+    [<NUM><NUM><NUM>] fresh online authenticating GET Heap CRITICAL Module id=brochure_<NUM>
+  - user:<IP>;completed;<NUM>;id=/var/log/whose.jpg;user:<NUM>.<NUM>;resolving;allowed;Commit;Index;Daemon;building;length;hall;[/var/log/segment.doc];with
+  - Heap;id=dim_<NUM>;[except<NUM>@gmail.com];dropped;determination;via;File;created;id=<NUM>;unavailable;id=/var/log/page.tar.xz;rendering;<NUM>b<NUM>ad<NUM>;id=/var/log/want.tar.gz;Kernel;JS;secure;HTTP/<NUM>;user:a<NUM>dd<NUM>d;user:<NUM><NUM><NUM>;resolving;Header
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+model-index:
+- name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+  results:
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: structural val
+      type: structural-val
+    metrics:
+    - type: cosine_accuracy
+      value: 0.996666669845581
+      name: Cosine Accuracy
+---
+
+# SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-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/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 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/huggingface/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, 'architecture': '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})
+)
+```
+
+## 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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    "authenticating YAML PATCH authorizing id=/var/log/seem.tar.xz [<NUM>] rendering 'pursue_<NUM>' [<NUM><NUM><NUM>] fresh online authenticating GET Heap CRITICAL Module id=bother_<NUM>",
+    "authenticating YAML PATCH authorizing id=/var/log/born.log [<NUM>] rendering 'school_<NUM>' [<NUM><NUM><NUM>] fresh online authenticating GET Heap CRITICAL Module id=brochure_<NUM>",
+    'Heap;id=dim_<NUM>;[except<NUM>@gmail.com];dropped;determination;via;File;created;id=<NUM>;unavailable;id=/var/log/page.tar.xz;rendering;<NUM>b<NUM>ad<NUM>;id=/var/log/want.tar.gz;Kernel;JS;secure;HTTP/<NUM>;user:a<NUM>dd<NUM>d;user:<NUM><NUM><NUM>;resolving;Header',
+]
+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,  0.9960, -0.1292],
+#         [ 0.9960,  1.0000, -0.1269],
+#         [-0.1292, -0.1269,  1.0000]])
+```
+
+<!--
+### 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
+
+#### Triplet
+
+* Dataset: `structural-val`
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| **cosine_accuracy** | **0.9967** |
+
+<!--
+## 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: 2,400 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                          | sentence_1                                                                          | sentence_2                                                                          |
+  |:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                              | string                                                                              |
+  | details | <ul><li>min: 31 tokens</li><li>mean: 81.66 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 33 tokens</li><li>mean: 81.55 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 28 tokens</li><li>mean: 79.74 tokens</li><li>max: 128 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                                                                                                         | sentence_1                                                                                                                                                                                                           | sentence_2                                                                                                                                                                                                          |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>ERROR;[river_<NUM>];<IP>;bit;<NUM>.<NUM>;watches;Table;user:<NUM>.<NUM>;/var/log/art.zip;/var/log/neck.docx;id=<NUM><NUM><NUM>;<NUM>.<NUM>;schedules;watson_<NUM>;DELETE;user:<NUM>.<NUM>;Session</code>     | <code>ERROR;[taxation_<NUM>];<IP>;bit;<NUM>.<NUM>;watches;Table;user:<NUM>.<NUM>;/var/log/hunt.pps;/var/log/radio.<NUM>z;id=<NUM><NUM><NUM>;<NUM>.<NUM>;schedules;tab_<NUM>;DELETE;user:<NUM>.<NUM>;Session</code>   | <code>[experiments_<NUM>] id=<NUM><NUM><NUM> watches DELETE Table user:<NUM>.<NUM> <NUM>.<NUM> <NUM>.<NUM> need_<NUM> /var/log/list.mov <IP> user:<NUM>.<NUM> schedules Session /var/log/pull.pptx bit ERROR</code> |
+  | <code>divided;defence;binding;user:helmet<NUM>@outlook.com;hours;user:<IP>;parsing;rocky;API;Gateway;started;by;flexible;by;INFO;Interface;Memory;teens;JS;fetching;deleted</code>                                 | <code>divided;defence;binding;user:night<NUM>@protonmail.com;hours;user:<IP>;parsing;rocky;API;Gateway;started;by;flexible;by;INFO;Interface;Memory;teens;JS;fetching;deleted</code>                                 | <code>by;binding;Interface;user:<IP>;divided;INFO;parsing;API;Memory;teens;user:cells<NUM>@example.org;started;Gateway;by;deleted;JS;defence;hours;fetching;flexible;rocky</code>                                   |
+  | <code>user:c<NUM>ed<NUM>\|queued\|<NUM>\|private\|Session\|blocked\|at\|user:<NUM>b<NUM>ba\|<NUM>.<NUM>\|Rollback\|Config\|<NUM><NUM><NUM>\|Config\|user:margin<NUM>@example.com\|spawning\|<NUM>\|inactive</code> | <code>user:<NUM>ae<NUM>\|queued\|<NUM>\|private\|Session\|blocked\|at\|user:<NUM>db<NUM>ce\|<NUM>.<NUM>\|Rollback\|Config\|<NUM><NUM><NUM>\|Config\|user:travelers<NUM>@yandex.com\|spawning\|<NUM>\|inactive</code> | <code><NUM>;spawning;inactive;<NUM><NUM><NUM>;user:d<NUM>ce<NUM>;queued;Config;<NUM>;user:promote<NUM>@protonmail.com;Config;private;user:f<NUM>ad<NUM>;at;Session;<NUM>.<NUM>;blocked;Rollback</code>              |
+* Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "TripletDistanceMetric.COSINE",
+      "triplet_margin": 0.5
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: no
+- `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`: 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`: 3
+- `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
+- `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}
+- `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}
+- `parallelism_config`: None
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `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
+- `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
+- `hub_revision`: None
+- `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`: 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
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch | Step | structural-val_cosine_accuracy |
+|:-----:|:----:|:------------------------------:|
+| 1.0   | 38   | 0.9950                         |
+| 2.0   | 76   | 0.9967                         |
+
+
+### Framework Versions
+- Python: 3.12.2
+- Sentence Transformers: 5.1.2
+- Transformers: 4.57.1
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.12.0
+- Datasets: 4.4.1
+- Tokenizers: 0.22.1
+
+## 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",
+}
+```
+
+#### TripletLoss
+```bibtex
+@misc{hermans2017defense,
+    title={In Defense of the Triplet Loss for Person Re-Identification},
+    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
+    year={2017},
+    eprint={1703.07737},
+    archivePrefix={arXiv},
+    primaryClass={cs.CV}
+}
+```
+
+<!--
+## 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.*
+-->