Version 1.0

Versión 1.0 del modelo de IA para PLN entrenado en español, para textos jurídicos!

config.json

@@ -0,0 +1,85 @@
+{
+  "_name_or_path": "BSC-TeMU/roberta-base-bne",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "fundamentación y motivación",
+    "1": "valoración de pruebas",
+    "2": "agravios infundados",
+    "3": "ninguno",
+    "4": "agravios inoperantes",
+    "5": "agravios fundados",
+    "6": "conceptos de invalidez fundados",
+    "7": "invalidez del acto impugnado.",
+    "8": "condena a autoridad",
+    "9": "interés jurídico o legítimo",
+    "10": "análisis de las causales de improcedencia y sobreseimiento",
+    "11": "omisión",
+    "12": "boleta de infracción",
+    "13": "derecho de petición",
+    "14": "negativa ficta",
+    "15": "dictamen de pensión",
+    "16": "congruencia y exhaustividad",
+    "17": "validez del acto impugnado",
+    "18": "conceptos de invalidez infundados",
+    "19": "excitativa de justicia",
+    "20": "sobreseimiento no tiene carácter de autoridad demandada",
+    "21": "actualización de causal de improcedencia",
+    "22": "sobreseimiento no existe el acto impugnado",
+    "23": "orden de visita de inspección y/o verificación",
+    "24": "oficio",
+    "25": "reposición de proceso"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "fundamentación y motivación": 0,
+    "valoración de pruebas": 1,
+    "análisis de las causales de improcedencia y sobreseimiento": 10,
+    "omisión": 11,
+    "boleta de infracción": 12,
+    "derecho de petición": 13,
+    "negativa ficta": 14,
+    "dictamen de pensión": 15,
+    "congruencia y exhaustividad": 16,
+    "validez del acto impugnado": 17,
+    "conceptos de invalidez infundados": 18,
+    "excitativa de justicia": 19,
+    "agravios infundados": 2,
+    "sobreseimiento no tiene carácter de autoridad demandada": 20,
+    "actualización de causal de improcedencia": 21,
+    "sobreseimiento no existe el acto impugnado": 22,
+    "orden de visita de inspección y/o verificación": 23,
+    "oficio": 24,
+    "reposición de proceso": 25,
+    "ninguno": 3,
+    "agravios inoperantes": 4,
+    "agravios fundados": 5,
+    "conceptos de invalidez fundados": 6,
+    "invalidez del acto impugnado.": 7,
+    "condena a autoridad": 8,
+    "interés jurídico o legítimo": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432e091a9309ee3aa8af0784ec2f91ad73f38b34ae8eae58211311472195eb8a
+size 997424389

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f89e7a118ef853dac1b00a3485a09097633ac98735331c40f716cf9e1256a8c
+size 498726645

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b8ed88fb58c297ec6dbf14dcb1a6e0465dec124ca66031459669d61bc43570a
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d652ba22cd679847c9ace1fe0f604ee188ec1802872614a15de20e7b775ed3d5
+size 627

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,292 @@
+{
+  "best_metric": 0.2851985559566787,
+  "best_model_checkpoint": "results/checkpoint-7944",
+  "epoch": 4.0,
+  "global_step": 7944,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.96012084592145e-05,
+      "loss": 2.8915,
+      "step": 198
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9202416918429007e-05,
+      "loss": 2.4239,
+      "step": 396
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.8803625377643506e-05,
+      "loss": 2.2481,
+      "step": 594
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.840483383685801e-05,
+      "loss": 2.1996,
+      "step": 792
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.800604229607251e-05,
+      "loss": 2.1824,
+      "step": 990
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.760725075528701e-05,
+      "loss": 2.0517,
+      "step": 1188
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.7208459214501513e-05,
+      "loss": 2.0375,
+      "step": 1386
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.6809667673716012e-05,
+      "loss": 2.0427,
+      "step": 1584
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6410876132930515e-05,
+      "loss": 1.967,
+      "step": 1782
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.6012084592145018e-05,
+      "loss": 1.982,
+      "step": 1980
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.2740715098165274,
+      "eval_loss": 2.498654365539551,
+      "eval_runtime": 49.553,
+      "eval_samples_per_second": 408.068,
+      "eval_steps_per_second": 40.825,
+      "step": 1986
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.5613293051359517e-05,
+      "loss": 1.8129,
+      "step": 2178
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.521450151057402e-05,
+      "loss": 1.7615,
+      "step": 2376
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.481570996978852e-05,
+      "loss": 1.82,
+      "step": 2574
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.4416918429003021e-05,
+      "loss": 1.7927,
+      "step": 2772
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.4018126888217525e-05,
+      "loss": 1.7828,
+      "step": 2970
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.3619335347432026e-05,
+      "loss": 1.7809,
+      "step": 3168
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.3220543806646526e-05,
+      "loss": 1.7006,
+      "step": 3366
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.2821752265861027e-05,
+      "loss": 1.7561,
+      "step": 3564
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.242296072507553e-05,
+      "loss": 1.7157,
+      "step": 3762
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.2024169184290032e-05,
+      "loss": 1.7302,
+      "step": 3960
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.27822560704218385,
+      "eval_loss": 2.486177444458008,
+      "eval_runtime": 49.6405,
+      "eval_samples_per_second": 407.349,
+      "eval_steps_per_second": 40.753,
+      "step": 3972
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 1.1625377643504531e-05,
+      "loss": 1.5066,
+      "step": 4158
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 1.1226586102719035e-05,
+      "loss": 1.5125,
+      "step": 4356
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 1.0827794561933536e-05,
+      "loss": 1.5064,
+      "step": 4554
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 1.0429003021148037e-05,
+      "loss": 1.5471,
+      "step": 4752
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.003021148036254e-05,
+      "loss": 1.5293,
+      "step": 4950
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 9.63141993957704e-06,
+      "loss": 1.5216,
+      "step": 5148
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 9.232628398791542e-06,
+      "loss": 1.6028,
+      "step": 5346
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 8.833836858006042e-06,
+      "loss": 1.5475,
+      "step": 5544
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 8.435045317220545e-06,
+      "loss": 1.506,
+      "step": 5742
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 8.036253776435046e-06,
+      "loss": 1.5518,
+      "step": 5940
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.2739231492013254,
+      "eval_loss": 2.57331919670105,
+      "eval_runtime": 49.6582,
+      "eval_samples_per_second": 407.204,
+      "eval_steps_per_second": 40.739,
+      "step": 5958
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 7.637462235649547e-06,
+      "loss": 1.3584,
+      "step": 6138
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 7.238670694864049e-06,
+      "loss": 1.3197,
+      "step": 6336
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 6.83987915407855e-06,
+      "loss": 1.3561,
+      "step": 6534
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 6.441087613293052e-06,
+      "loss": 1.3575,
+      "step": 6732
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 6.042296072507553e-06,
+      "loss": 1.3798,
+      "step": 6930
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 5.643504531722055e-06,
+      "loss": 1.355,
+      "step": 7128
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 5.2447129909365566e-06,
+      "loss": 1.3312,
+      "step": 7326
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 4.8459214501510575e-06,
+      "loss": 1.4011,
+      "step": 7524
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 4.447129909365559e-06,
+      "loss": 1.4124,
+      "step": 7722
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 4.048338368580061e-06,
+      "loss": 1.3597,
+      "step": 7920
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.2851985559566787,
+      "eval_loss": 2.571429491043091,
+      "eval_runtime": 49.4476,
+      "eval_samples_per_second": 408.938,
+      "eval_steps_per_second": 40.912,
+      "step": 7944
+    }
+  ],
+  "max_steps": 9930,
+  "num_train_epochs": 5,
+  "total_flos": 2302111312251120.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f49efcbeac67a2f541600dce7248cf28d04fd8307a53acc8881839659524b570
+size 3579