End of training

README.md

@@ -0,0 +1,79 @@
+---
+base_model: dccuchile/bert-base-spanish-wwm-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: bert-base-spanish-wwm-cased-ner
+  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-ner
+
+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.
+It achieves the following results on the evaluation set:
+- Loss: 0.3695
+- Precision: 0.8640
+- Recall: 0.9126
+- F1: 0.8876
+- Accuracy: 0.9378
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 280  | 0.3016          | 0.7779    | 0.8252 | 0.8009 | 0.9052   |
+| 0.4113        | 2.0   | 560  | 0.2671          | 0.8150    | 0.8681 | 0.8407 | 0.9248   |
+| 0.4113        | 3.0   | 840  | 0.2747          | 0.8181    | 0.8593 | 0.8382 | 0.9268   |
+| 0.1179        | 4.0   | 1120 | 0.2875          | 0.8336    | 0.8978 | 0.8645 | 0.9312   |
+| 0.1179        | 5.0   | 1400 | 0.3087          | 0.8529    | 0.9022 | 0.8769 | 0.9361   |
+| 0.0608        | 6.0   | 1680 | 0.3449          | 0.8645    | 0.8978 | 0.8808 | 0.9351   |
+| 0.0608        | 7.0   | 1960 | 0.3478          | 0.8539    | 0.8919 | 0.8725 | 0.9337   |
+| 0.0306        | 8.0   | 2240 | 0.3495          | 0.8426    | 0.8963 | 0.8686 | 0.9337   |
+| 0.0231        | 9.0   | 2520 | 0.3812          | 0.8660    | 0.9096 | 0.8873 | 0.9366   |
+| 0.0231        | 10.0  | 2800 | 0.3346          | 0.8473    | 0.8963 | 0.8711 | 0.9386   |
+| 0.0174        | 11.0  | 3080 | 0.3721          | 0.8583    | 0.9067 | 0.8818 | 0.9373   |
+| 0.0174        | 12.0  | 3360 | 0.3778          | 0.8632    | 0.9067 | 0.8844 | 0.9371   |
+| 0.014         | 13.0  | 3640 | 0.3733          | 0.8624    | 0.9096 | 0.8854 | 0.9366   |
+| 0.014         | 14.0  | 3920 | 0.3709          | 0.8652    | 0.9126 | 0.8882 | 0.9398   |
+| 0.013         | 15.0  | 4200 | 0.3695          | 0.8640    | 0.9126 | 0.8876 | 0.9378   |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
+  "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": "O",
+    "1": "B-Anatomical_Entity",
+    "10": "I-Location",
+    "11": "B-Type_of_measure",
+    "12": "I-Type_of_measure",
+    "13": "B-Measure",
+    "14": "I-Measure",
+    "15": "B-Degree",
+    "16": "I-Degree",
+    "17": "B-ConditionalTemporal",
+    "18": "I-ConditionalTemporal",
+    "2": "I-Anatomical_Entity",
+    "3": "B-Finding",
+    "4": "I-Finding",
+    "5": "B-Uncertainty",
+    "6": "I-Uncertainty",
+    "7": "B-Negation",
+    "8": "I-Negation",
+    "9": "B-Location"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Anatomical_Entity": "1",
+    "B-ConditionalTemporal": "17",
+    "B-Degree": "15",
+    "B-Finding": "3",
+    "B-Location": "9",
+    "B-Measure": "13",
+    "B-Negation": "7",
+    "B-Type_of_measure": "11",
+    "B-Uncertainty": "5",
+    "I-Anatomical_Entity": "2",
+    "I-ConditionalTemporal": "18",
+    "I-Degree": "16",
+    "I-Finding": "4",
+    "I-Location": "10",
+    "I-Measure": "14",
+    "I-Negation": "8",
+    "I-Type_of_measure": "12",
+    "I-Uncertainty": "6",
+    "O": "0"
+  },
+  "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": "4.41.1",
+  "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 sha256:8a64b94cf69f90be4ce90d441fb003d43cecda511656720ca1dd4293f743ce58
+size 437122940

runs/Jun02_16-16-42_50a0327f41e4/events.out.tfevents.1717345003.50a0327f41e4.22857.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25d8d5ff36b002ac79a1c2314207f012fa3d03bc3435e1d8b148c681bd0fe05d
+size 15030

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 +1,57 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "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 sha256:9e8521ad117e9c68e71ce26ea61bd0197a5f3d8585f5dfe22895c6e414ea793c
+size 5112