feat: Add model files

README.md

@@ -0,0 +1,70 @@
+---
+language:
+- pl
+license: mit 
+tags:
+- bert 
+- sentiment-classification 
+- clarinpl-embeddings
+- LEPISZCZE
+datasets:
+- clarin-pl/aspectemo
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+---
+
+# LEPISZCZE-aspectemo-allegro__herbert-base-cased-v1
+## Description
+Finetuned [allegro/herbert-base-cased](https://huggingface.co/allegro/herbert-base-cased) model on [clarin-pl/aspectemo](https://huggingface.co/datasets/clarin-pl/aspectemo) dataset. 
+
+Trained via [clarin-pl-embeddings](https://github.com/clarin-pl/embeddings) library, included in [LEPISZCZE](https://lepiszcze.ml/tasks/sentimentanalysis/) benchmark.
+
+## Results on clarin-pl/aspectemo
+|       |   accuracy |   f1_macro |   f1_micro |   f1_weighted |   recall_macro |   recall_micro |   recall_weighted |   precision_macro |   precision_micro |   precision_weighted |
+|:------|-----------:|-----------:|-----------:|--------------:|---------------:|---------------:|------------------:|------------------:|------------------:|---------------------:|
+| value |      0.952 |      0.368 |      0.585 |         0.586 |          0.371 |          0.566 |             0.566 |             0.392 |             0.606 |                0.617 |
+
+### Metrics per class
+|           |   precision |   recall |    f1 |   support |
+|:----------|------------:|---------:|------:|----------:|
+| a_amb     |       0.2   |    0.033 | 0.057 |        91 |
+| a_minus_m |       0.632 |    0.542 | 0.584 |      1033 |
+| a_minus_s |       0.156 |    0.209 | 0.178 |        67 |
+| a_plus_m  |       0.781 |    0.694 | 0.735 |      1015 |
+| a_plus_s  |       0.153 |    0.22  | 0.18  |        41 |
+| a_zero    |       0.431 |    0.529 | 0.475 |       501 |
+
+## Finetuning hyperparameters
+| Hyperparameter Name     | Value    |
+|:------------------------|:---------|
+| use_scheduler           | True     |
+| optimizer               | AdamW    |
+| warmup_steps            | 25       |
+| learning_rate           | 0.0005   |
+| adam_epsilon            | 1e-05    |
+| weight_decay            | 0        |
+| finetune_last_n_layers  | 4        |
+| classifier_dropout      | 0.2      |
+| max_seq_length          | 512      |
+| batch_size              | 64       |
+| max_epochs              | 20       |
+| early_stopping_monitor  | val/Loss |
+| early_stopping_mode     | min      |
+| early_stopping_patience | 3        |
+
+## Citation (BibTeX)
+```
+@article{augustyniak2022way,
+  title={This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish},
+  author={Augustyniak, Lukasz and Tagowski, Kamil and Sawczyn, Albert and Janiak, Denis and Bartusiak, Roman and Szymczak, Adrian and Janz, Arkadiusz and Szyma{'n}ski, Piotr and W{\k{a}}troba, Marcin and Morzy, Miko{\l}aj and others},
+  journal={Advances in Neural Information Processing Systems},
+  volume={35},
+  pages={21805--21818},
+  year={2022}
+}
+```
+
+

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "allegro/herbert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": 0.2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "a_minus_m",
+    "2": "a_minus_s",
+    "3": "a_zero",
+    "4": "a_plus_s",
+    "5": "a_plus_m",
+    "6": "a_amb"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "O": 0,
+    "a_amb": 6,
+    "a_minus_m": 1,
+    "a_minus_s": 2,
+    "a_plus_m": 5,
+    "a_plus_s": 4,
+    "a_zero": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "HerbertTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

hparams.json

@@ -0,0 +1,32 @@
+{
+  "optimizer":"AdamW",
+  "learning_rate":0.0005,
+  "adam_epsilon":0.00001,
+  "warmup_steps":25,
+  "weight_decay":0,
+  "train_batch_size":64,
+  "eval_batch_size":64,
+  "use_scheduler":true,
+  "metrics":null,
+  "model_name_or_path":"allegro/herbert-base-cased",
+  "num_classes":7,
+  "finetune_last_n_layers":4,
+  "config_kwargs":{
+    "classifier_dropout":0.2
+  },
+  "task_model_kwargs":{
+    "adam_epsilon":0.00001,
+    "eval_batch_size":64,
+    "learning_rate":0.0005,
+    "optimizer":"AdamW",
+    "train_batch_size":64,
+    "use_scheduler":true,
+    "warmup_steps":25,
+    "weight_decay":0
+  },
+  "model_compile_kwargs":null,
+  "evaluation_mode":"unit",
+  "tagging_scheme":null,
+  "ignore_index":-100,
+  "downstream_model_type":"AutoModelForTokenClassification"
+}

packages.json

@@ -0,0 +1,333 @@
+[
+  "absl-py==1.4.0",
+  "aiobotocore==2.5.0",
+  "aiohttp-retry==2.8.3",
+  "aiohttp==3.8.4",
+  "aioitertools==0.11.0",
+  "aiosignal==1.3.1",
+  "alembic==1.10.4",
+  "amqp==5.1.1",
+  "annoy==1.17.2",
+  "antlr4-python3-runtime==4.9.3",
+  "anyio==3.6.2",
+  "appdirs==1.4.4",
+  "argon2-cffi-bindings==21.2.0",
+  "argon2-cffi==21.3.0",
+  "arrow==1.2.3",
+  "asttokens==2.2.1",
+  "async-timeout==4.0.2",
+  "asyncssh==2.13.1",
+  "atpublic==3.1.1",
+  "attrs==23.1.0",
+  "backcall==0.2.0",
+  "beautifulsoup4==4.12.2",
+  "billiard==3.6.4.0",
+  "black==21.10b0",
+  "bleach==6.0.0",
+  "blessed==1.20.0",
+  "boto3==1.26.76",
+  "botocore==1.29.76",
+  "cachecontrol==0.12.11",
+  "cachetools==5.3.0",
+  "catalogue==2.0.8",
+  "celery==5.2.7",
+  "certifi==2022.12.7",
+  "cffi==1.15.1",
+  "charset-normalizer==3.1.0",
+  "clarinpl-embeddings==0.3.0",
+  "cleo==2.0.1",
+  "click-didyoumean==0.3.0",
+  "click-plugins==1.1.1",
+  "click-repl==0.2.0",
+  "click==8.0.4",
+  "cloudpickle==2.2.1",
+  "cmaes==0.9.1",
+  "cmake==3.26.3",
+  "colorama==0.4.6",
+  "coloredlogs==15.0.1",
+  "colorlog==6.7.0",
+  "comm==0.1.3",
+  "configobj==5.0.8",
+  "contourpy==1.0.7",
+  "coverage==6.5.0",
+  "crashtest==0.4.1",
+  "croniter==1.3.14",
+  "cryptography==40.0.2",
+  "cycler==0.11.0",
+  "databricks-cli==0.17.6",
+  "datasets==2.11.0",
+  "dateutils==0.6.12",
+  "debugpy==1.6.7",
+  "decorator==5.1.1",
+  "deepdiff==6.3.0",
+  "defusedxml==0.7.1",
+  "dictdiffer==0.9.0",
+  "dill==0.3.6",
+  "diskcache==5.6.1",
+  "distlib==0.3.6",
+  "distro==1.8.0",
+  "docker-pycreds==0.4.0",
+  "docker==6.0.1",
+  "dpath==2.1.5",
+  "dulwich==0.21.3",
+  "dvc-data==0.47.2",
+  "dvc-http==2.30.2",
+  "dvc-objects==0.21.2",
+  "dvc-render==0.3.1",
+  "dvc-s3==2.22.0",
+  "dvc-studio-client==0.8.0",
+  "dvc-task==0.2.1",
+  "dvc==2.55.0",
+  "entrypoints==0.4",
+  "evaluate==0.4.0",
+  "executing==1.2.0",
+  "fastapi==0.88.0",
+  "fastjsonschema==2.16.3",
+  "filelock==3.12.0",
+  "flask==2.2.4",
+  "flatbuffers==23.3.3",
+  "flatten-dict==0.4.2",
+  "flufl.lock==7.1.1",
+  "fonttools==4.39.3",
+  "fqdn==1.5.1",
+  "frozenlist==1.3.3",
+  "fsspec==2023.4.0",
+  "funcy==2.0",
+  "gitdb==4.0.10",
+  "gitpython==3.1.31",
+  "google-auth-oauthlib==1.0.0",
+  "google-auth==2.17.3",
+  "grandalf==0.8",
+  "greenlet==2.0.2",
+  "grpcio==1.54.0",
+  "gunicorn==20.1.0",
+  "h11==0.14.0",
+  "html5lib==1.1",
+  "huggingface-hub==0.14.1",
+  "humanfriendly==10.0",
+  "hydra-core==1.3.2",
+  "idna==3.4",
+  "importlib-metadata==6.6.0",
+  "importlib-resources==5.12.0",
+  "iniconfig==2.0.0",
+  "inquirer==3.1.3",
+  "ipykernel==6.22.0",
+  "ipython-genutils==0.2.0",
+  "ipython==8.12.0",
+  "ipywidgets==8.0.6",
+  "isoduration==20.11.0",
+  "isort==5.10.1",
+  "iterative-telemetry==0.0.8",
+  "itsdangerous==2.1.2",
+  "jaraco.classes==3.2.3",
+  "jedi==0.18.2",
+  "jeepney==0.8.0",
+  "jinja2==3.1.2",
+  "jmespath==1.0.1",
+  "joblib==1.2.0",
+  "jsonpointer==2.3",
+  "jsonschema==4.17.3",
+  "jupyter-client==8.2.0",
+  "jupyter-console==6.6.3",
+  "jupyter-core==5.3.0",
+  "jupyter-events==0.6.3",
+  "jupyter-server-terminals==0.4.4",
+  "jupyter-server==2.5.0",
+  "jupyter==1.0.0",
+  "jupyterlab-pygments==0.2.2",
+  "jupyterlab-widgets==3.0.7",
+  "keyring==23.13.1",
+  "kiwisolver==1.4.4",
+  "kombu==5.2.4",
+  "leaderboard==0.0.1",
+  "lightning-cloud==0.5.34",
+  "lightning-utilities==0.8.0",
+  "lightning==2.0.1",
+  "lit==16.0.2",
+  "lockfile==0.12.2",
+  "lz4==4.3.2",
+  "mako==1.2.4",
+  "markdown-it-py==2.2.0",
+  "markdown==3.4.3",
+  "markupsafe==2.1.2",
+  "matplotlib-inline==0.1.6",
+  "matplotlib==3.7.1",
+  "mdurl==0.1.2",
+  "mistune==2.0.5",
+  "mlflow==2.3.0",
+  "mpmath==1.3.0",
+  "msgpack==1.0.4",
+  "multidict==6.0.4",
+  "multiprocess==0.70.14",
+  "mypy-extensions==1.0.0",
+  "mypy==0.950",
+  "nanotime==0.5.2",
+  "nbclassic==0.5.6",
+  "nbclient==0.7.4",
+  "nbconvert==7.3.1",
+  "nbformat==5.8.0",
+  "nest-asyncio==1.5.6",
+  "networkx==3.1",
+  "notebook-shim==0.2.3",
+  "notebook==6.5.4",
+  "numpy==1.23.4",
+  "nvidia-cublas-cu11==11.10.3.66",
+  "nvidia-cuda-cupti-cu11==11.7.101",
+  "nvidia-cuda-nvrtc-cu11==11.7.99",
+  "nvidia-cuda-runtime-cu11==11.7.99",
+  "nvidia-cudnn-cu11==8.5.0.96",
+  "nvidia-cufft-cu11==10.9.0.58",
+  "nvidia-curand-cu11==10.2.10.91",
+  "nvidia-cusolver-cu11==11.4.0.1",
+  "nvidia-cusparse-cu11==11.7.4.91",
+  "nvidia-nccl-cu11==2.14.3",
+  "nvidia-nvtx-cu11==11.7.91",
+  "oauthlib==3.2.2",
+  "omegaconf==2.3.0",
+  "onnx==1.13.1",
+  "onnxconverter-common==1.13.0",
+  "onnxruntime-tools==1.7.0",
+  "onnxruntime==1.14.1",
+  "optuna==3.1.1",
+  "ordered-set==4.1.0",
+  "orjson==3.8.10",
+  "packaging==23.1",
+  "pandas==2.0.1",
+  "pandocfilters==1.5.0",
+  "parso==0.8.3",
+  "pastel==0.2.1",
+  "pathspec==0.11.1",
+  "pathtools==0.1.2",
+  "pexpect==4.8.0",
+  "pickleshare==0.7.5",
+  "pillow==9.5.0",
+  "pip==22.3.1",
+  "pkginfo==1.9.6",
+  "platformdirs==3.5.0",
+  "pluggy==1.0.0",
+  "poethepoet==0.11.0",
+  "poetry-core==1.4.0",
+  "poetry-plugin-export==1.3.0",
+  "poetry==1.3.2",
+  "prometheus-client==0.16.0",
+  "prompt-toolkit==3.0.38",
+  "protobuf==3.20.3",
+  "psutil==5.9.5",
+  "ptyprocess==0.7.0",
+  "pure-eval==0.2.2",
+  "py-cpuinfo==9.0.0",
+  "py3nvml==0.2.7",
+  "py==1.11.0",
+  "pyarrow==11.0.0",
+  "pyasn1-modules==0.3.0",
+  "pyasn1==0.5.0",
+  "pycparser==2.21",
+  "pydantic==1.10.7",
+  "pydot==1.4.2",
+  "pyflakes==2.4.0",
+  "pygit2==1.12.0",
+  "pygments==2.15.1",
+  "pygtrie==2.5.0",
+  "pyjwt==2.6.0",
+  "pyparsing==3.0.9",
+  "pyrsistent==0.19.3",
+  "pytest==6.2.5",
+  "python-dateutil==2.8.2",
+  "python-editor==1.0.4",
+  "python-json-logger==2.0.7",
+  "python-multipart==0.0.6",
+  "pytorch-lightning==2.0.1",
+  "pytz==2023.3",
+  "pyyaml==6.0",
+  "pyzmq==25.0.2",
+  "qtconsole==5.4.2",
+  "qtpy==2.3.1",
+  "querystring-parser==1.2.4",
+  "rapidfuzz==2.13.7",
+  "readchar==4.0.5",
+  "regex==2023.3.23",
+  "requests-oauthlib==1.3.1",
+  "requests-toolbelt==0.10.1",
+  "requests==2.29.0",
+  "responses==0.18.0",
+  "rfc3339-validator==0.1.4",
+  "rfc3986-validator==0.1.1",
+  "rich==13.3.5",
+  "rsa==4.9",
+  "ruamel.yaml.clib==0.2.7",
+  "ruamel.yaml==0.17.21",
+  "s3fs==2023.4.0",
+  "s3transfer==0.6.0",
+  "sacremoses==0.0.53",
+  "scikit-learn==1.2.2",
+  "scipy==1.10.1",
+  "scmrepo==1.0.2",
+  "secretstorage==3.3.3",
+  "send2trash==1.8.2",
+  "sentry-sdk==1.21.0",
+  "seqeval==1.2.2",
+  "setproctitle==1.3.2",
+  "setuptools==67.7.2",
+  "shellingham==1.5.0.post1",
+  "shortuuid==1.0.11",
+  "shtab==1.6.1",
+  "six==1.16.0",
+  "smmap==5.0.0",
+  "sniffio==1.3.0",
+  "soupsieve==2.4.1",
+  "sqlalchemy==2.0.11",
+  "sqlparse==0.4.4",
+  "sqltrie==0.3.1",
+  "srsly==2.4.6",
+  "stack-data==0.6.2",
+  "starlette==0.22.0",
+  "starsessions==1.3.0",
+  "sympy==1.11.1",
+  "tabulate==0.9.0",
+  "tensorboard-data-server==0.7.0",
+  "tensorboard-plugin-wit==1.8.1",
+  "tensorboard==2.12.2",
+  "terminado==0.17.1",
+  "tf2onnx==1.8.4",
+  "threadpoolctl==3.1.0",
+  "tinycss2==1.2.1",
+  "tokenizers==0.13.3",
+  "toml==0.10.2",
+  "tomli==1.2.3",
+  "tomlkit==0.11.8",
+  "torch==2.0.0",
+  "torchmetrics==0.11.4",
+  "tornado==6.3.1",
+  "tqdm==4.65.0",
+  "traitlets==5.9.0",
+  "transformers==4.28.1",
+  "triton==2.0.0",
+  "trove-classifiers==2023.1.20",
+  "typer==0.7.0",
+  "types-pyyaml==6.0.12.9",
+  "types-requests==2.26.1",
+  "types-setuptools==67.7.0.0",
+  "typing-extensions==4.5.0",
+  "tzdata==2023.3",
+  "uri-template==1.2.0",
+  "urllib3==1.26.15",
+  "uvicorn==0.21.1",
+  "vine==5.0.0",
+  "virtualenv==20.17.1",
+  "voluptuous==0.13.1",
+  "wandb==0.15.0",
+  "wcwidth==0.2.6",
+  "webcolors==1.13",
+  "webencodings==0.5.1",
+  "websocket-client==1.5.1",
+  "websockets==11.0.2",
+  "werkzeug==2.3.1",
+  "wheel==0.40.0",
+  "widgetsnbextension==4.0.7",
+  "wrapt==1.15.0",
+  "xmltodict==0.13.0",
+  "xxhash==3.2.0",
+  "yarl==1.9.2",
+  "zc.lockfile==3.0.post1",
+  "zipp==3.15.0"
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6022bffa030bf39ad8baeedc68e79b1129af909787fda758e4f7059b58967c0a
+size 495500013

special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lowercase_and_remove_accent": false,
+  "id2lang": null,
+  "lang2id": null,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "HerbertTokenizer",
+  "unk_token": "<unk>"
+}