claudiaMartinez1982/bert-base-spanish-wwm-cased_bs32

README.md

@@ -0,0 +1,52 @@
+---
+library_name: transformers
+base_model: dccuchile/bert-base-spanish-wwm-cased
+tags:
+- generated_from_trainer
+model-index:
+- name: bert-base-spanish-wwm-cased_bs32
+  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. -->
+
+# bert-base-spanish-wwm-cased_bs32
+
+This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on the None dataset.
+
+## 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- 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: linear
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.6.0+cu124
+- Datasets 2.14.4
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,76 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": ",",
+    "1": "0",
+    "2": "B-BIOMARCADOR",
+    "3": "B-CANCER",
+    "4": "B-CIRUGIA",
+    "5": "B-DOSIS",
+    "6": "B-EDAD",
+    "7": "B-FECHA",
+    "8": "B-GLEASON",
+    "9": "B-MEDICAMENTO",
+    "10": "B-TNM",
+    "11": "B-TRATAMIENTO",
+    "12": "I-BIOMARCADOR",
+    "13": "I-CANCER",
+    "14": "I-CIRUGIA",
+    "15": "I-DOSIS",
+    "16": "I-EDAD",
+    "17": "I-FECHA",
+    "18": "I-GLEASON",
+    "19": "I-MEDICAMENTO",
+    "20": "I-TNM",
+    "21": "I-TRATAMIENTO",
+    "22": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    ",": 0,
+    "0": 1,
+    "B-BIOMARCADOR": 2,
+    "B-CANCER": 3,
+    "B-CIRUGIA": 4,
+    "B-DOSIS": 5,
+    "B-EDAD": 6,
+    "B-FECHA": 7,
+    "B-GLEASON": 8,
+    "B-MEDICAMENTO": 9,
+    "B-TNM": 10,
+    "B-TRATAMIENTO": 11,
+    "I-BIOMARCADOR": 12,
+    "I-CANCER": 13,
+    "I-CIRUGIA": 14,
+    "I-DOSIS": 15,
+    "I-EDAD": 16,
+    "I-FECHA": 17,
+    "I-GLEASON": 18,
+    "I-MEDICAMENTO": 19,
+    "I-TNM": 20,
+    "I-TRATAMIENTO": 21,
+    "O": 22
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fcd30c7b0c28cb8c129cbb0c4b34832cbff874440bb5bd09500113812a7329b
+size 437135244

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "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 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[MASK]",
+      "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
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46e1764ca4bec45f5a445e9e44126dadd7c4389c33f5a58b84f7cf122f9b2117
+size 5304