Model save

.gitattributes

@@ -0,0 +1 @@
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,63 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-base
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: boe_classifier
+  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. -->
+
+# boe_classifier
+
+This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- F1: 0.3068
+- Loss: 7.9021
+
+## 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: 3e-05
+- train_batch_size: 1
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 10
+- total_train_batch_size: 10
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | F1     | Validation Loss |
+|:-------------:|:------:|:----:|:------:|:---------------:|
+| No log        | 0.9195 | 8    | 0.2727 | 9.3126          |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 9.275862068965518,
+    "eval_f1": 0.31034482758620696,
+    "eval_loss": 7.982325553894043,
+    "eval_runtime": 0.1803,
+    "eval_samples": 10,
+    "eval_samples_per_second": 55.472,
+    "eval_steps_per_second": 27.736,
+    "total_flos": 202609940734866.0,
+    "train_loss": 0.0,
+    "train_runtime": 0.2425,
+    "train_samples": 87,
+    "train_samples_per_second": 358.716,
+    "train_steps_per_second": 32.985
+}

config.json

@@ -0,0 +1,121 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Leyes Organicas",
+    "1": "Reales Decretos y Reales Decretos-Leyes",
+    "2": "Tratados y Convenios Internacionales",
+    "3": "Leyes de Comunidades Autonomas",
+    "4": "Reglamentos y Normativas Generales",
+    "5": "Nombramientos y Ceses",
+    "6": "Promociones y Situaciones Especiales",
+    "7": "Convocatorias y Resultados de Oposiciones",
+    "8": "Anuncios de Concursos y Adjudicaciones de Plazas",
+    "9": "Ayudas",
+    "10": "Subvenciones y Becas",
+    "11": "Convenios Colectivos y Cartas de Servicio",
+    "12": "Planes de Estudio y Normativas Educativas",
+    "13": "Convenios Internacionales y Medidas Especiales",
+    "14": "Edictos y Notificaciones Judiciales",
+    "15": "Procedimientos y Citaciones Judiciales",
+    "16": "Licitaciones y Adjudicaciones Publicas",
+    "17": "Avisos y Notificaciones Oficiales",
+    "18": "Anuncios Comerciales y Convocatorias Privadas",
+    "19": "Sentencias y Autos del Tribunal Constitucional",
+    "20": "Orden de Publicaciones y Sumarios",
+    "21": "Publicaciones por Organo Emisor",
+    "22": "Jerarquia y Autenticidad de Normativas",
+    "23": "Publicaciones en Lenguas Cooficiales",
+    "24": "Interpretaciones y Documentos Oficiales",
+    "25": "Informes y Comunicaciones de Interes General",
+    "26": "Documentos y Estrategias Nacionales",
+    "27": "Medidas de Emergencia y Seguridad Nacional",
+    "28": "Anuncios de Regulaciones Especificas",
+    "29": "Normativas Temporales y Urgentes",
+    "30": "Medidas y Politicas Sectoriales",
+    "31": "Todos los Tipos de Leyes (Nacionales y Autonomicas)",
+    "32": "Todos los Tipos de Decretos (Legislativos y no Legislativos)",
+    "33": "Convocatorias y Resultados Generales (Empleo y Educacion)",
+    "34": "Anuncios y Avisos (Oficiales y Privados)",
+    "35": "Judicial y Procedimientos Legales",
+    "36": "Sentencias y Declaraciones Judiciales",
+    "37": "Publicaciones Multilingues y Cooficiales",
+    "38": "Informes y Estrategias de Politica",
+    "39": "Emergencias Nacionales y Medidas Excepcionales",
+    "40": "Documentos y Comunicaciones Especificas"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Anuncios Comerciales y Convocatorias Privadas": 18,
+    "Anuncios de Concursos y Adjudicaciones de Plazas": 8,
+    "Anuncios de Regulaciones Especificas": 28,
+    "Anuncios y Avisos (Oficiales y Privados)": 34,
+    "Avisos y Notificaciones Oficiales": 17,
+    "Ayudas": 9,
+    "Convenios Colectivos y Cartas de Servicio": 11,
+    "Convenios Internacionales y Medidas Especiales": 13,
+    "Convocatorias y Resultados Generales (Empleo y Educacion)": 33,
+    "Convocatorias y Resultados de Oposiciones": 7,
+    "Documentos y Comunicaciones Especificas": 40,
+    "Documentos y Estrategias Nacionales": 26,
+    "Edictos y Notificaciones Judiciales": 14,
+    "Emergencias Nacionales y Medidas Excepcionales": 39,
+    "Informes y Comunicaciones de Interes General": 25,
+    "Informes y Estrategias de Politica": 38,
+    "Interpretaciones y Documentos Oficiales": 24,
+    "Jerarquia y Autenticidad de Normativas": 22,
+    "Judicial y Procedimientos Legales": 35,
+    "Leyes Organicas": 0,
+    "Leyes de Comunidades Autonomas": 3,
+    "Licitaciones y Adjudicaciones Publicas": 16,
+    "Medidas de Emergencia y Seguridad Nacional": 27,
+    "Medidas y Politicas Sectoriales": 30,
+    "Nombramientos y Ceses": 5,
+    "Normativas Temporales y Urgentes": 29,
+    "Orden de Publicaciones y Sumarios": 20,
+    "Planes de Estudio y Normativas Educativas": 12,
+    "Procedimientos y Citaciones Judiciales": 15,
+    "Promociones y Situaciones Especiales": 6,
+    "Publicaciones Multilingues y Cooficiales": 37,
+    "Publicaciones en Lenguas Cooficiales": 23,
+    "Publicaciones por Organo Emisor": 21,
+    "Reales Decretos y Reales Decretos-Leyes": 1,
+    "Reglamentos y Normativas Generales": 4,
+    "Sentencias y Autos del Tribunal Constitucional": 19,
+    "Sentencias y Declaraciones Judiciales": 36,
+    "Subvenciones y Becas": 10,
+    "Todos los Tipos de Decretos (Legislativos y no Legislativos)": 32,
+    "Todos los Tipos de Leyes (Nacionales y Autonomicas)": 31,
+    "Tratados y Convenios Internacionales": 2
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.275862068965518,
+    "eval_f1": 0.31034482758620696,
+    "eval_loss": 7.982325553894043,
+    "eval_runtime": 0.1803,
+    "eval_samples": 10,
+    "eval_samples_per_second": 55.472,
+    "eval_steps_per_second": 27.736
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2951b0da7a268fe762a4a2af8a10d266416f85b51beecae72d5326be7773f0d3
+size 737839252

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "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
+    },
+    "50264": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "errors": "replace",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "DebertaTokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "gpt2"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.275862068965518,
+    "total_flos": 202609940734866.0,
+    "train_loss": 0.0,
+    "train_runtime": 0.2425,
+    "train_samples": 87,
+    "train_samples_per_second": 358.716,
+    "train_steps_per_second": 32.985
+}

trainer_state.json

@@ -0,0 +1,186 @@
+{
+  "best_metric": 0.31034482758620696,
+  "best_model_checkpoint": "./models/checkpoint/checkpoint-68",
+  "epoch": 9.275862068965518,
+  "eval_steps": 500,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9195402298850575,
+      "eval_f1": 0.2727272727272727,
+      "eval_loss": 9.31263256072998,
+      "eval_runtime": 0.1958,
+      "eval_samples_per_second": 51.067,
+      "eval_steps_per_second": 25.534,
+      "step": 8
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "step": 8,
+      "total_flos": 20939936811486.0,
+      "train_loss": 9.918171882629395,
+      "train_runtime": 21.4307,
+      "train_samples_per_second": 4.06,
+      "train_steps_per_second": 0.373
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "step": 8,
+      "total_flos": 20939936811486.0,
+      "train_loss": 0.0,
+      "train_runtime": 0.5294,
+      "train_samples_per_second": 164.352,
+      "train_steps_per_second": 15.113
+    },
+    {
+      "epoch": 1.9195402298850575,
+      "eval_f1": 0.2530120481927711,
+      "eval_loss": 9.20499038696289,
+      "eval_runtime": 0.1794,
+      "eval_samples_per_second": 55.739,
+      "eval_steps_per_second": 27.87,
+      "step": 16
+    },
+    {
+      "epoch": 2.954022988505747,
+      "eval_f1": 0.25842696629213485,
+      "eval_loss": 8.635601997375488,
+      "eval_runtime": 0.1743,
+      "eval_samples_per_second": 57.382,
+      "eval_steps_per_second": 28.691,
+      "step": 25
+    },
+    {
+      "epoch": 3.9885057471264367,
+      "eval_f1": 0.30409356725146197,
+      "eval_loss": 8.560417175292969,
+      "eval_runtime": 0.1737,
+      "eval_samples_per_second": 57.572,
+      "eval_steps_per_second": 28.786,
+      "step": 34
+    },
+    {
+      "epoch": 4.908045977011494,
+      "eval_f1": 0.3076923076923077,
+      "eval_loss": 8.47392463684082,
+      "eval_runtime": 0.1856,
+      "eval_samples_per_second": 53.876,
+      "eval_steps_per_second": 26.938,
+      "step": 42
+    },
+    {
+      "epoch": 5.942528735632184,
+      "eval_f1": 0.30857142857142855,
+      "eval_loss": 8.22740364074707,
+      "eval_runtime": 0.1773,
+      "eval_samples_per_second": 56.411,
+      "eval_steps_per_second": 28.205,
+      "step": 51
+    },
+    {
+      "epoch": 6.977011494252873,
+      "eval_f1": 0.3,
+      "eval_loss": 8.102139472961426,
+      "eval_runtime": 0.1819,
+      "eval_samples_per_second": 54.979,
+      "eval_steps_per_second": 27.49,
+      "step": 60
+    },
+    {
+      "epoch": 7.896551724137931,
+      "eval_f1": 0.31034482758620696,
+      "eval_loss": 7.982325553894043,
+      "eval_runtime": 0.1721,
+      "eval_samples_per_second": 58.115,
+      "eval_steps_per_second": 29.057,
+      "step": 68
+    },
+    {
+      "epoch": 8.931034482758621,
+      "eval_f1": 0.30681818181818177,
+      "eval_loss": 7.987342834472656,
+      "eval_runtime": 0.1737,
+      "eval_samples_per_second": 57.583,
+      "eval_steps_per_second": 28.792,
+      "step": 77
+    },
+    {
+      "epoch": 9.275862068965518,
+      "eval_f1": 0.30681818181818177,
+      "eval_loss": 7.902113437652588,
+      "eval_runtime": 0.1822,
+      "eval_samples_per_second": 54.889,
+      "eval_steps_per_second": 27.444,
+      "step": 80
+    },
+    {
+      "epoch": 9.275862068965518,
+      "step": 80,
+      "total_flos": 202609940734866.0,
+      "train_loss": 7.418544769287109,
+      "train_runtime": 132.4614,
+      "train_samples_per_second": 6.568,
+      "train_steps_per_second": 0.604
+    },
+    {
+      "epoch": 9.275862068965518,
+      "step": 80,
+      "total_flos": 202609940734866.0,
+      "train_loss": 0.0,
+      "train_runtime": 0.245,
+      "train_samples_per_second": 355.061,
+      "train_steps_per_second": 32.649
+    },
+    {
+      "epoch": 9.275862068965518,
+      "step": 80,
+      "total_flos": 202609940734866.0,
+      "train_loss": 0.0,
+      "train_runtime": 0.244,
+      "train_samples_per_second": 356.519,
+      "train_steps_per_second": 32.783
+    },
+    {
+      "epoch": 9.275862068965518,
+      "step": 80,
+      "total_flos": 202609940734866.0,
+      "train_loss": 0.0,
+      "train_runtime": 0.2425,
+      "train_samples_per_second": 358.716,
+      "train_steps_per_second": 32.985
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 202609940734866.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}