Initial push

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+confusion_matrix.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,77 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: PKOBP/polish-roberta-8k
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: mwik-classifier-extended
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# mwik-classifier-extended
+
+This model is a fine-tuned version of [PKOBP/polish-roberta-8k](https://huggingface.co/PKOBP/polish-roberta-8k) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1518
+- Accuracy: 0.7348
+- Precision: 0.7235
+- Recall: 0.7348
+- F1: 0.7248
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 24
+- eval_batch_size: 48
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 96
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: polynomial
+- lr_scheduler_warmup_ratio: 0.06
+- num_epochs: 7
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 3.2781        | 1.0   | 64   | 1.8838          | 0.5812   | 0.4719    | 0.5812 | 0.5054 |
+| 1.766         | 2.0   | 128  | 1.4098          | 0.6593   | 0.6038    | 0.6593 | 0.6058 |
+| 1.3812        | 3.0   | 192  | 1.1837          | 0.7083   | 0.6701    | 0.7083 | 0.6749 |
+| 0.8668        | 4.0   | 256  | 1.1232          | 0.7289   | 0.7062    | 0.7289 | 0.7052 |
+| 0.6762        | 5.0   | 320  | 1.0806          | 0.7412   | 0.7268    | 0.7412 | 0.7247 |
+| 0.5221        | 6.0   | 384  | 1.0815          | 0.7358   | 0.7206    | 0.7358 | 0.7234 |
+| 0.4312        | 7.0   | 448  | 1.0919          | 0.7466   | 0.7281    | 0.7466 | 0.7320 |
+
+
+### Framework versions
+
+- Transformers 4.57.3
+- Pytorch 2.9.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.1

added_tokens.json

@@ -0,0 +1,66 @@
+{
+  "<mask>": 128000,
+  "<user_token_10>": 128010,
+  "<user_token_11>": 128011,
+  "<user_token_12>": 128012,
+  "<user_token_13>": 128013,
+  "<user_token_14>": 128014,
+  "<user_token_15>": 128015,
+  "<user_token_16>": 128016,
+  "<user_token_17>": 128017,
+  "<user_token_18>": 128018,
+  "<user_token_19>": 128019,
+  "<user_token_1>": 128001,
+  "<user_token_20>": 128020,
+  "<user_token_21>": 128021,
+  "<user_token_22>": 128022,
+  "<user_token_23>": 128023,
+  "<user_token_24>": 128024,
+  "<user_token_25>": 128025,
+  "<user_token_26>": 128026,
+  "<user_token_27>": 128027,
+  "<user_token_28>": 128028,
+  "<user_token_29>": 128029,
+  "<user_token_2>": 128002,
+  "<user_token_30>": 128030,
+  "<user_token_31>": 128031,
+  "<user_token_32>": 128032,
+  "<user_token_33>": 128033,
+  "<user_token_34>": 128034,
+  "<user_token_35>": 128035,
+  "<user_token_36>": 128036,
+  "<user_token_37>": 128037,
+  "<user_token_38>": 128038,
+  "<user_token_39>": 128039,
+  "<user_token_3>": 128003,
+  "<user_token_40>": 128040,
+  "<user_token_41>": 128041,
+  "<user_token_42>": 128042,
+  "<user_token_43>": 128043,
+  "<user_token_44>": 128044,
+  "<user_token_45>": 128045,
+  "<user_token_46>": 128046,
+  "<user_token_47>": 128047,
+  "<user_token_48>": 128048,
+  "<user_token_49>": 128049,
+  "<user_token_4>": 128004,
+  "<user_token_50>": 128050,
+  "<user_token_51>": 128051,
+  "<user_token_52>": 128052,
+  "<user_token_53>": 128053,
+  "<user_token_54>": 128054,
+  "<user_token_55>": 128055,
+  "<user_token_56>": 128056,
+  "<user_token_57>": 128057,
+  "<user_token_58>": 128058,
+  "<user_token_59>": 128059,
+  "<user_token_5>": 128005,
+  "<user_token_60>": 128060,
+  "<user_token_61>": 128061,
+  "<user_token_62>": 128062,
+  "<user_token_63>": 128063,
+  "<user_token_6>": 128006,
+  "<user_token_7>": 128007,
+  "<user_token_8>": 128008,
+  "<user_token_9>": 128009
+}

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.7348193697156034,
+    "eval_f1": 0.724775902380406,
+    "eval_loss": 1.1517707109451294,
+    "eval_precision": 0.723456161938857,
+    "eval_recall": 0.7348193697156034,
+    "eval_runtime": 6.6281,
+    "eval_samples_per_second": 196.285,
+    "eval_steps_per_second": 4.224,
+    "total_flos": 5.11047224331433e+16,
+    "train_loss": 1.151742445571082,
+    "train_runtime": 761.7181,
+    "train_samples_per_second": 55.883,
+    "train_steps_per_second": 0.588
+}

classification_report.txt

@@ -0,0 +1,91 @@
+
+================================================================================
+
+DETAILED CLASSIFICATION REPORT (Top-1)
+================================================================================
+              precision    recall  f1-score   support
+
+       BINFO     0.7083    0.9444    0.8095        18
+   DANE_ARCH     0.8000    0.6667    0.7273        18
+ DAN_DO_ROZL     0.5172    0.6250    0.5660        24
+DIERZ_ST_HYD     0.9074    0.9074    0.9074        54
+    DUZY_PRZ     1.0000    1.0000    1.0000         6
+    EBOK_ZGL     0.5000    0.4000    0.4444         5
+    EKSP_WOD     1.0000    0.8333    0.9091         6
+    GRVAT_ZM     0.0000    0.0000    0.0000         1
+     INFO_DW     0.6944    0.7353    0.7143        34
+        INSP     0.7250    0.7250    0.7250        40
+ INTERW_AW_K     0.6885    0.7500    0.7179        56
+ INTERW_AW_W     0.6875    0.6111    0.6471        54
+ INTERW_ODTW     0.6552    0.7600    0.7037        25
+  INTERW_ZAP     0.8462    0.8462    0.8462        13
+    KONT_WYM     1.0000    0.6667    0.8000         3
+    KOSZT_WP     0.0000    0.0000    0.0000         1
+LIK_PRZYL_WK     0.0000    0.0000    0.0000         2
+        MAPA     0.0000    0.0000    0.0000         0
+NEGOC_DESZCZ     0.8621    0.9091    0.8850        55
+    NOTA_KOR     0.8333    0.8333    0.8333         6
+ODPL_INSP_TV     0.8000    0.5000    0.6154         8
+ ODP_CZYSZ_K     0.0000    0.0000    0.0000         1
+   ODP_DOW_W     0.6667    0.8571    0.7500         7
+  ODP_LAB_WS     0.8462    0.8462    0.8462        13
+ ODP_LOK_WYC     0.5000    0.3333    0.4000         3
+ ODP_OPL_WOD     0.0000    0.0000    0.0000         2
+ ODP_POM_CIS     1.0000    0.5000    0.6667         2
+ ODP_WYM_ODL     0.5000    0.5000    0.5000         6
+ ODP_WYM_WOD     0.0000    0.0000    0.0000         1
+  ODP_ZAW_US     0.0000    0.0000    0.0000         1
+ ODP_ZO_ZASU     0.5000    0.6667    0.5714         3
+     ODSZKOD     0.5714    1.0000    0.7273         4
+    ODWOD_KD     0.0000    0.0000    0.0000         2
+    ODWOD_KS     0.5714    1.0000    0.7273         4
+OKR_WL_PRZEW     0.0000    0.0000    0.0000         1
+  OP_PRZY_WK     0.1818    0.1333    0.1538        15
+  OP_SIEC_WK     0.5588    0.6333    0.5938        30
+       OP_UM     0.9130    0.9130    0.9130        23
+       PENOM     0.4000    0.5000    0.4444         4
+     POMYLKA     0.0000    0.0000    0.0000         2
+  POTW_SALDA     0.3333    0.3333    0.3333         3
+   POTW_WPAT     0.7632    0.8286    0.7945        35
+     POZYTYW     0.6471    0.5500    0.5946        20
+POZ_SPR_WIND     0.6753    0.7647    0.7172        68
+     PROLONG     0.0000    0.0000    0.0000         2
+     PROMESA     1.0000    0.7500    0.8571         4
+        PRZE     0.8710    0.7826    0.8244        69
+   PRZEKSIEG     0.0000    0.0000    0.0000         4
+   PRZEN_WOD     0.7500    0.7500    0.7500         4
+ PRZYW_DOS_W     0.4000    0.6667    0.5000         3
+         PYT     0.3000    0.2571    0.2769        35
+  REKLAMACJA     0.7955    0.8434    0.8187        83
+        RODO     0.0000    0.0000    0.0000         1
+    ROW_EKSP     0.7692    0.7692    0.7692        13
+     ROW_WYC     0.0000    0.0000    0.0000         1
+ROZDZ_INSTAL     0.0000    0.0000    0.0000         2
+ROZL_PL_RATY     0.6000    1.0000    0.7500         3
+          SK     0.5185    0.4000    0.4516        35
+   SUZEBNOSC     1.0000    0.8182    0.9000        11
+    UDOST_WN     0.8889    0.8889    0.8889         9
+          UM     0.8866    0.8515    0.8687       101
+  UM_PARTYCY     0.9091    0.9524    0.9302        21
+  UZN_SCIEKI     0.7500    0.6000    0.6667         5
+  UZ_PRZY_WK     0.8684    0.9429    0.9041        35
+  UZ_SIEC_WK     0.9231    0.7500    0.8276        16
+  WAR_ODW_KS     1.0000    0.6667    0.8000         3
+WAR_PRZY_SIE     0.0000    0.0000    0.0000         5
+      WAR_WK     0.5294    0.6923    0.6000        13
+    WAR_WKKD     0.4375    0.4667    0.4516        15
+   WAR_WKROW     0.0000    0.0000    0.0000         2
+WOD_OGR_PRZY     0.7059    0.9231    0.8000        13
+   WPIN_SIEC     0.7778    0.8750    0.8235         8
+    WYJ_ROZL     0.0000    0.0000    0.0000         3
+ WYM_PRZY_WK     0.5556    0.6250    0.5882         8
+  ZAP_JAKOSC     1.0000    0.3333    0.5000         3
+   ZASW_KONC     0.6667    0.6667    0.6667         6
+     ZG_ODCZ     0.8723    0.9111    0.8913        45
+          ZM     0.6000    0.8750    0.7119        24
+    ZW_ANEKS     0.5000    0.6667    0.5714         3
+     ZW_NADP     1.0000    0.7857    0.8800        14
+
+    accuracy                         0.7348      1301
+   macro avg     0.5466    0.5448    0.5357      1301
+weighted avg     0.7235    0.7348    0.7248      1301

config.json

@@ -0,0 +1,207 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "auto_map": {
+    "AutoConfig": "configuration_roberta.RobertaConfig",
+    "AutoModel": "modeling_roberta.RobertaModel",
+    "AutoModelForCausalLM": "modeling_roberta.RobertaForCausalLM",
+    "AutoModelForMaskedLM": "modeling_roberta.RobertaForMaskedLM",
+    "AutoModelForMultipleChoice": "modeling_roberta.RobertaForMultipleChoice",
+    "AutoModelForQuestionAnswering": "modeling_roberta.RobertaForQuestionAnswering",
+    "AutoModelForSequenceClassification": "modeling_roberta.RobertaForSequenceClassification",
+    "AutoModelForTokenClassification": "modeling_roberta.RobertaForTokenClassification"
+  },
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "BINFO",
+    "1": "DANE_ARCH",
+    "2": "DAN_DO_ROZL",
+    "3": "DIERZ_ST_HYD",
+    "4": "DUZY_PRZ",
+    "5": "EBOK_ZGL",
+    "6": "EKSP_WOD",
+    "7": "GRVAT_ZM",
+    "8": "INFO_DW",
+    "9": "INSP",
+    "10": "INTERW_AW_K",
+    "11": "INTERW_AW_W",
+    "12": "INTERW_ODTW",
+    "13": "INTERW_ZAP",
+    "14": "KONT_WYM",
+    "15": "KOSZT_UM",
+    "16": "KOSZT_WP",
+    "17": "LIK_PRZYL_WK",
+    "18": "MAPA",
+    "19": "NEGOC_DESZCZ",
+    "20": "NOTA_KOR",
+    "21": "ODPL_INSP_TV",
+    "22": "ODP_CZYSZ_K",
+    "23": "ODP_DOW_W",
+    "24": "ODP_LAB_WS",
+    "25": "ODP_LOK_WYC",
+    "26": "ODP_OPL_WOD",
+    "27": "ODP_POM_CIS",
+    "28": "ODP_WYM_ODL",
+    "29": "ODP_WYM_WOD",
+    "30": "ODP_ZAW_US",
+    "31": "ODP_ZO_ZASU",
+    "32": "ODSZKOD",
+    "33": "ODWOD_KD",
+    "34": "ODWOD_KS",
+    "35": "OKR_WL_PRZEW",
+    "36": "OP_PRZY_WK",
+    "37": "OP_SIEC_WK",
+    "38": "OP_UM",
+    "39": "PENOM",
+    "40": "POMYLKA",
+    "41": "POTW_SALDA",
+    "42": "POTW_WPAT",
+    "43": "POZYTYW",
+    "44": "POZ_SPR_WIND",
+    "45": "PROLONG",
+    "46": "PROMESA",
+    "47": "PRZE",
+    "48": "PRZEKSIEG",
+    "49": "PRZEK_SIEC",
+    "50": "PRZEN_WOD",
+    "51": "PRZYW_DOS_W",
+    "52": "PYT",
+    "53": "REKLAMACJA",
+    "54": "RODO",
+    "55": "ROW_EKSP",
+    "56": "ROW_WYC",
+    "57": "ROZDZ_INSTAL",
+    "58": "ROZL_PL_RATY",
+    "59": "SK",
+    "60": "SPR_SPOS_ZAS",
+    "61": "SUZEBNOSC",
+    "62": "UDOST_WN",
+    "63": "UM",
+    "64": "UM_PARTYCY",
+    "65": "UZN_SCIEKI",
+    "66": "UZ_PRZY_WK",
+    "67": "UZ_SIEC_WK",
+    "68": "WAR_ODW_KS",
+    "69": "WAR_PRZY_SIE",
+    "70": "WAR_WK",
+    "71": "WAR_WKKD",
+    "72": "WAR_WKROW",
+    "73": "WOD_OGR_PRZY",
+    "74": "WPIN_SIEC",
+    "75": "WYJ_ROZL",
+    "76": "WYM_PRZY_WK",
+    "77": "ZAP_JAKOSC",
+    "78": "ZASW_KONC",
+    "79": "ZG_ODCZ",
+    "80": "ZM",
+    "81": "ZW_ANEKS",
+    "82": "ZW_NADP"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "BINFO": 0,
+    "DANE_ARCH": 1,
+    "DAN_DO_ROZL": 2,
+    "DIERZ_ST_HYD": 3,
+    "DUZY_PRZ": 4,
+    "EBOK_ZGL": 5,
+    "EKSP_WOD": 6,
+    "GRVAT_ZM": 7,
+    "INFO_DW": 8,
+    "INSP": 9,
+    "INTERW_AW_K": 10,
+    "INTERW_AW_W": 11,
+    "INTERW_ODTW": 12,
+    "INTERW_ZAP": 13,
+    "KONT_WYM": 14,
+    "KOSZT_UM": 15,
+    "KOSZT_WP": 16,
+    "LIK_PRZYL_WK": 17,
+    "MAPA": 18,
+    "NEGOC_DESZCZ": 19,
+    "NOTA_KOR": 20,
+    "ODPL_INSP_TV": 21,
+    "ODP_CZYSZ_K": 22,
+    "ODP_DOW_W": 23,
+    "ODP_LAB_WS": 24,
+    "ODP_LOK_WYC": 25,
+    "ODP_OPL_WOD": 26,
+    "ODP_POM_CIS": 27,
+    "ODP_WYM_ODL": 28,
+    "ODP_WYM_WOD": 29,
+    "ODP_ZAW_US": 30,
+    "ODP_ZO_ZASU": 31,
+    "ODSZKOD": 32,
+    "ODWOD_KD": 33,
+    "ODWOD_KS": 34,
+    "OKR_WL_PRZEW": 35,
+    "OP_PRZY_WK": 36,
+    "OP_SIEC_WK": 37,
+    "OP_UM": 38,
+    "PENOM": 39,
+    "POMYLKA": 40,
+    "POTW_SALDA": 41,
+    "POTW_WPAT": 42,
+    "POZYTYW": 43,
+    "POZ_SPR_WIND": 44,
+    "PROLONG": 45,
+    "PROMESA": 46,
+    "PRZE": 47,
+    "PRZEKSIEG": 48,
+    "PRZEK_SIEC": 49,
+    "PRZEN_WOD": 50,
+    "PRZYW_DOS_W": 51,
+    "PYT": 52,
+    "REKLAMACJA": 53,
+    "RODO": 54,
+    "ROW_EKSP": 55,
+    "ROW_WYC": 56,
+    "ROZDZ_INSTAL": 57,
+    "ROZL_PL_RATY": 58,
+    "SK": 59,
+    "SPR_SPOS_ZAS": 60,
+    "SUZEBNOSC": 61,
+    "UDOST_WN": 62,
+    "UM": 63,
+    "UM_PARTYCY": 64,
+    "UZN_SCIEKI": 65,
+    "UZ_PRZY_WK": 66,
+    "UZ_SIEC_WK": 67,
+    "WAR_ODW_KS": 68,
+    "WAR_PRZY_SIE": 69,
+    "WAR_WK": 70,
+    "WAR_WKKD": 71,
+    "WAR_WKROW": 72,
+    "WOD_OGR_PRZY": 73,
+    "WPIN_SIEC": 74,
+    "WYJ_ROZL": 75,
+    "WYM_PRZY_WK": 76,
+    "ZAP_JAKOSC": 77,
+    "ZASW_KONC": 78,
+    "ZG_ODCZ": 79,
+    "ZM": 80,
+    "ZW_ANEKS": 81,
+    "ZW_NADP": 82
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 128064
+}

configuration_roberta.py

@@ -0,0 +1,151 @@
+# coding=utf-8
+# Copyright 2018 The Google AI Language Team Authors and The HuggingFace Inc. team.
+# Copyright (c) 2018, NVIDIA CORPORATION.  All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+""" RoBERTa configuration"""
+from collections import OrderedDict
+from typing import Mapping
+
+from transformers import PretrainedConfig
+from transformers.onnx import OnnxConfig
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+
+class RobertaConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`RobertaModel`] or a [`TFRobertaModel`]. It is
+    used to instantiate a RoBERTa model according to the specified arguments, defining the model architecture.
+    Instantiating a configuration with the defaults will yield a similar configuration to that of the RoBERTa
+    [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) architecture.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 50265):
+            Vocabulary size of the RoBERTa model. Defines the number of different tokens that can be represented by the
+            `inputs_ids` passed when calling [`RobertaModel`] or [`TFRobertaModel`].
+        hidden_size (`int`, *optional*, defaults to 768):
+            Dimensionality of the encoder layers and the pooler layer.
+        num_hidden_layers (`int`, *optional*, defaults to 12):
+            Number of hidden layers in the Transformer encoder.
+        num_attention_heads (`int`, *optional*, defaults to 12):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        intermediate_size (`int`, *optional*, defaults to 3072):
+            Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
+        hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu"`):
+            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
+            `"relu"`, `"silu"` and `"gelu_new"` are supported.
+        hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
+        attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
+            The dropout ratio for the attention probabilities.
+        max_position_embeddings (`int`, *optional*, defaults to 512):
+            The maximum sequence length that this model might ever be used with. Typically set this to something large
+            just in case (e.g., 512 or 1024 or 2048).
+        type_vocab_size (`int`, *optional*, defaults to 2):
+            The vocabulary size of the `token_type_ids` passed when calling [`RobertaModel`] or [`TFRobertaModel`].
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        layer_norm_eps (`float`, *optional*, defaults to 1e-12):
+            The epsilon used by the layer normalization layers.
+        position_embedding_type (`str`, *optional*, defaults to `"absolute"`):
+            Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For
+            positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to
+            [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155).
+            For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models
+            with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658).
+        is_decoder (`bool`, *optional*, defaults to `False`):
+            Whether the model is used as a decoder or not. If `False`, the model is used as an encoder.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values attentions (not used by all models). Only
+            relevant if `config.is_decoder=True`.
+        classifier_dropout (`float`, *optional*):
+            The dropout ratio for the classification head.
+
+    Examples:
+
+    ```python
+    >>> from transformers import RobertaConfig, RobertaModel
+
+    >>> # Initializing a RoBERTa configuration
+    >>> configuration = RobertaConfig()
+
+    >>> # Initializing a model (with random weights) from the configuration
+    >>> model = RobertaModel(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "roberta"
+
+    def __init__(
+        self,
+        vocab_size=50265,
+        hidden_size=768,
+        num_hidden_layers=12,
+        num_attention_heads=12,
+        intermediate_size=3072,
+        hidden_act="gelu",
+        hidden_dropout_prob=0.1,
+        attention_probs_dropout_prob=0.1,
+        max_position_embeddings=512,
+        type_vocab_size=2,
+        initializer_range=0.02,
+        layer_norm_eps=1e-12,
+        pad_token_id=1,
+        bos_token_id=0,
+        eos_token_id=2,
+        position_embedding_type="absolute",
+        use_cache=True,
+        classifier_dropout=None,
+        **kwargs,
+    ):
+        super().__init__(pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
+
+        self.vocab_size = vocab_size
+        self.hidden_size = hidden_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.hidden_act = hidden_act
+        self.intermediate_size = intermediate_size
+        self.hidden_dropout_prob = hidden_dropout_prob
+        self.attention_probs_dropout_prob = attention_probs_dropout_prob
+        self.max_position_embeddings = max_position_embeddings
+        self.type_vocab_size = type_vocab_size
+        self.initializer_range = initializer_range
+        self.layer_norm_eps = layer_norm_eps
+        self.position_embedding_type = position_embedding_type
+        self.use_cache = use_cache
+        self.classifier_dropout = classifier_dropout
+
+
+class RobertaOnnxConfig(OnnxConfig):
+    @property
+    def inputs(self) -> Mapping[str, Mapping[int, str]]:
+        if self.task == "multiple-choice":
+            dynamic_axis = {0: "batch", 1: "choice", 2: "sequence"}
+        else:
+            dynamic_axis = {0: "batch", 1: "sequence"}
+        return OrderedDict(
+            [
+                ("input_ids", dynamic_axis),
+                ("attention_mask", dynamic_axis),
+            ]
+        )

label_info.json

@@ -0,0 +1,173 @@
+{
+  "label2id": {
+    "BINFO": 0,
+    "DANE_ARCH": 1,
+    "DAN_DO_ROZL": 2,
+    "DIERZ_ST_HYD": 3,
+    "DUZY_PRZ": 4,
+    "EBOK_ZGL": 5,
+    "EKSP_WOD": 6,
+    "GRVAT_ZM": 7,
+    "INFO_DW": 8,
+    "INSP": 9,
+    "INTERW_AW_K": 10,
+    "INTERW_AW_W": 11,
+    "INTERW_ODTW": 12,
+    "INTERW_ZAP": 13,
+    "KONT_WYM": 14,
+    "KOSZT_UM": 15,
+    "KOSZT_WP": 16,
+    "LIK_PRZYL_WK": 17,
+    "MAPA": 18,
+    "NEGOC_DESZCZ": 19,
+    "NOTA_KOR": 20,
+    "ODPL_INSP_TV": 21,
+    "ODP_CZYSZ_K": 22,
+    "ODP_DOW_W": 23,
+    "ODP_LAB_WS": 24,
+    "ODP_LOK_WYC": 25,
+    "ODP_OPL_WOD": 26,
+    "ODP_POM_CIS": 27,
+    "ODP_WYM_ODL": 28,
+    "ODP_WYM_WOD": 29,
+    "ODP_ZAW_US": 30,
+    "ODP_ZO_ZASU": 31,
+    "ODSZKOD": 32,
+    "ODWOD_KD": 33,
+    "ODWOD_KS": 34,
+    "OKR_WL_PRZEW": 35,
+    "OP_PRZY_WK": 36,
+    "OP_SIEC_WK": 37,
+    "OP_UM": 38,
+    "PENOM": 39,
+    "POMYLKA": 40,
+    "POTW_SALDA": 41,
+    "POTW_WPAT": 42,
+    "POZYTYW": 43,
+    "POZ_SPR_WIND": 44,
+    "PROLONG": 45,
+    "PROMESA": 46,
+    "PRZE": 47,
+    "PRZEKSIEG": 48,
+    "PRZEK_SIEC": 49,
+    "PRZEN_WOD": 50,
+    "PRZYW_DOS_W": 51,
+    "PYT": 52,
+    "REKLAMACJA": 53,
+    "RODO": 54,
+    "ROW_EKSP": 55,
+    "ROW_WYC": 56,
+    "ROZDZ_INSTAL": 57,
+    "ROZL_PL_RATY": 58,
+    "SK": 59,
+    "SPR_SPOS_ZAS": 60,
+    "SUZEBNOSC": 61,
+    "UDOST_WN": 62,
+    "UM": 63,
+    "UM_PARTYCY": 64,
+    "UZN_SCIEKI": 65,
+    "UZ_PRZY_WK": 66,
+    "UZ_SIEC_WK": 67,
+    "WAR_ODW_KS": 68,
+    "WAR_PRZY_SIE": 69,
+    "WAR_WK": 70,
+    "WAR_WKKD": 71,
+    "WAR_WKROW": 72,
+    "WOD_OGR_PRZY": 73,
+    "WPIN_SIEC": 74,
+    "WYJ_ROZL": 75,
+    "WYM_PRZY_WK": 76,
+    "ZAP_JAKOSC": 77,
+    "ZASW_KONC": 78,
+    "ZG_ODCZ": 79,
+    "ZM": 80,
+    "ZW_ANEKS": 81,
+    "ZW_NADP": 82
+  },
+  "id2label": {
+    "0": "BINFO",
+    "1": "DANE_ARCH",
+    "2": "DAN_DO_ROZL",
+    "3": "DIERZ_ST_HYD",
+    "4": "DUZY_PRZ",
+    "5": "EBOK_ZGL",
+    "6": "EKSP_WOD",
+    "7": "GRVAT_ZM",
+    "8": "INFO_DW",
+    "9": "INSP",
+    "10": "INTERW_AW_K",
+    "11": "INTERW_AW_W",
+    "12": "INTERW_ODTW",
+    "13": "INTERW_ZAP",
+    "14": "KONT_WYM",
+    "15": "KOSZT_UM",
+    "16": "KOSZT_WP",
+    "17": "LIK_PRZYL_WK",
+    "18": "MAPA",
+    "19": "NEGOC_DESZCZ",
+    "20": "NOTA_KOR",
+    "21": "ODPL_INSP_TV",
+    "22": "ODP_CZYSZ_K",
+    "23": "ODP_DOW_W",
+    "24": "ODP_LAB_WS",
+    "25": "ODP_LOK_WYC",
+    "26": "ODP_OPL_WOD",
+    "27": "ODP_POM_CIS",
+    "28": "ODP_WYM_ODL",
+    "29": "ODP_WYM_WOD",
+    "30": "ODP_ZAW_US",
+    "31": "ODP_ZO_ZASU",
+    "32": "ODSZKOD",
+    "33": "ODWOD_KD",
+    "34": "ODWOD_KS",
+    "35": "OKR_WL_PRZEW",
+    "36": "OP_PRZY_WK",
+    "37": "OP_SIEC_WK",
+    "38": "OP_UM",
+    "39": "PENOM",
+    "40": "POMYLKA",
+    "41": "POTW_SALDA",
+    "42": "POTW_WPAT",
+    "43": "POZYTYW",
+    "44": "POZ_SPR_WIND",
+    "45": "PROLONG",
+    "46": "PROMESA",
+    "47": "PRZE",
+    "48": "PRZEKSIEG",
+    "49": "PRZEK_SIEC",
+    "50": "PRZEN_WOD",
+    "51": "PRZYW_DOS_W",
+    "52": "PYT",
+    "53": "REKLAMACJA",
+    "54": "RODO",
+    "55": "ROW_EKSP",
+    "56": "ROW_WYC",
+    "57": "ROZDZ_INSTAL",
+    "58": "ROZL_PL_RATY",
+    "59": "SK",
+    "60": "SPR_SPOS_ZAS",
+    "61": "SUZEBNOSC",
+    "62": "UDOST_WN",
+    "63": "UM",
+    "64": "UM_PARTYCY",
+    "65": "UZN_SCIEKI",
+    "66": "UZ_PRZY_WK",
+    "67": "UZ_SIEC_WK",
+    "68": "WAR_ODW_KS",
+    "69": "WAR_PRZY_SIE",
+    "70": "WAR_WK",
+    "71": "WAR_WKKD",
+    "72": "WAR_WKROW",
+    "73": "WOD_OGR_PRZY",
+    "74": "WPIN_SIEC",
+    "75": "WYJ_ROZL",
+    "76": "WYM_PRZY_WK",
+    "77": "ZAP_JAKOSC",
+    "78": "ZASW_KONC",
+    "79": "ZG_ODCZ",
+    "80": "ZM",
+    "81": "ZW_ANEKS",
+    "82": "ZW_NADP"
+  },
+  "num_labels": 83
+}

logs/events.out.tfevents.1765909715.a68abee7a327.906.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:326d0fdc8691d325aa58bc4d798fd6b39c6d253b4384aa5e18ed5f8b1ed5d6f1
+size 14605

logs/events.out.tfevents.1765910484.a68abee7a327.906.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db97219afd49a5a42b0590f0a2c6e7f5e7a131bdb4afeb3863640396b6079142
+size 560

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bbc10888abc0cf1e6e0d33794129dd6d0d0bf83e6df293a9bfb68cc08965766
+size 1771949724

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

test_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.7348193697156034,
+    "eval_f1": 0.724775902380406,
+    "eval_loss": 1.1517707109451294,
+    "eval_precision": 0.723456161938857,
+    "eval_recall": 0.7348193697156034,
+    "eval_runtime": 6.6281,
+    "eval_samples_per_second": 196.285,
+    "eval_steps_per_second": 4.224
+}

tokenizer_config.json

@@ -0,0 +1,562 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<user_token_1>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128002": {
+      "content": "<user_token_2>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128003": {
+      "content": "<user_token_3>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128004": {
+      "content": "<user_token_4>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128005": {
+      "content": "<user_token_5>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128006": {
+      "content": "<user_token_6>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128007": {
+      "content": "<user_token_7>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128008": {
+      "content": "<user_token_8>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128009": {
+      "content": "<user_token_9>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128010": {
+      "content": "<user_token_10>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128011": {
+      "content": "<user_token_11>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128012": {
+      "content": "<user_token_12>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128013": {
+      "content": "<user_token_13>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128014": {
+      "content": "<user_token_14>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128015": {
+      "content": "<user_token_15>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128016": {
+      "content": "<user_token_16>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128017": {
+      "content": "<user_token_17>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128018": {
+      "content": "<user_token_18>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128019": {
+      "content": "<user_token_19>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128020": {
+      "content": "<user_token_20>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128021": {
+      "content": "<user_token_21>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128022": {
+      "content": "<user_token_22>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128023": {
+      "content": "<user_token_23>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128024": {
+      "content": "<user_token_24>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128025": {
+      "content": "<user_token_25>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128026": {
+      "content": "<user_token_26>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128027": {
+      "content": "<user_token_27>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128028": {
+      "content": "<user_token_28>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128029": {
+      "content": "<user_token_29>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128030": {
+      "content": "<user_token_30>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128031": {
+      "content": "<user_token_31>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128032": {
+      "content": "<user_token_32>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128033": {
+      "content": "<user_token_33>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128034": {
+      "content": "<user_token_34>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128035": {
+      "content": "<user_token_35>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128036": {
+      "content": "<user_token_36>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128037": {
+      "content": "<user_token_37>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128038": {
+      "content": "<user_token_38>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128039": {
+      "content": "<user_token_39>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128040": {
+      "content": "<user_token_40>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128041": {
+      "content": "<user_token_41>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128042": {
+      "content": "<user_token_42>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128043": {
+      "content": "<user_token_43>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128044": {
+      "content": "<user_token_44>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128045": {
+      "content": "<user_token_45>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128046": {
+      "content": "<user_token_46>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128047": {
+      "content": "<user_token_47>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128048": {
+      "content": "<user_token_48>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128049": {
+      "content": "<user_token_49>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128050": {
+      "content": "<user_token_50>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128051": {
+      "content": "<user_token_51>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128052": {
+      "content": "<user_token_52>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128053": {
+      "content": "<user_token_53>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128054": {
+      "content": "<user_token_54>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128055": {
+      "content": "<user_token_55>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128056": {
+      "content": "<user_token_56>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128057": {
+      "content": "<user_token_57>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128058": {
+      "content": "<user_token_58>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128059": {
+      "content": "<user_token_59>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128060": {
+      "content": "<user_token_60>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128061": {
+      "content": "<user_token_61>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128062": {
+      "content": "<user_token_62>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128063": {
+      "content": "<user_token_63>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "total_flos": 5.11047224331433e+16,
+    "train_loss": 1.151742445571082,
+    "train_runtime": 761.7181,
+    "train_samples_per_second": 55.883,
+    "train_steps_per_second": 0.588
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69aa8254a3525e98c4489875babf1dacaff8116ddc16e94e4f1d376257e65b4e
+size 5905