Training in progress, step 500

README.md

@@ -0,0 +1,99 @@
+---
+library_name: transformers
+base_model: dccuchile/bert-base-spanish-wwm-uncased
+tags:
+- generated_from_trainer
+datasets:
+- biobert_json
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: bert-biobert
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: biobert_json
+      type: biobert_json
+      config: Biobert_json
+      split: validation
+      args: Biobert_json
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.9479839607930497
+    - name: Recall
+      type: recall
+      value: 0.9641461342395922
+    - name: F1
+      type: f1
+      value: 0.95599674257954
+    - name: Accuracy
+      type: accuracy
+      value: 0.9768617183218656
+---
+
+<!-- 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-biobert
+
+This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-uncased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-uncased) on the biobert_json dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1154
+- Precision: 0.9480
+- Recall: 0.9641
+- F1: 0.9560
+- Accuracy: 0.9769
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.364         | 1.0   | 612  | 0.1155          | 0.9302    | 0.9525 | 0.9412 | 0.9686   |
+| 0.117         | 2.0   | 1224 | 0.1034          | 0.9405    | 0.9640 | 0.9521 | 0.9749   |
+| 0.0837        | 3.0   | 1836 | 0.0980          | 0.9469    | 0.9682 | 0.9574 | 0.9772   |
+| 0.066         | 4.0   | 2448 | 0.0975          | 0.9474    | 0.9678 | 0.9575 | 0.9775   |
+| 0.0451        | 5.0   | 3060 | 0.0982          | 0.9498    | 0.9648 | 0.9572 | 0.9770   |
+| 0.0405        | 6.0   | 3672 | 0.1074          | 0.9469    | 0.9643 | 0.9555 | 0.9761   |
+| 0.0318        | 7.0   | 4284 | 0.1104          | 0.9478    | 0.9663 | 0.9570 | 0.9771   |
+| 0.031         | 8.0   | 4896 | 0.1145          | 0.9495    | 0.9654 | 0.9574 | 0.9772   |
+| 0.0235        | 9.0   | 5508 | 0.1137          | 0.9495    | 0.9639 | 0.9566 | 0.9767   |
+| 0.0209        | 10.0  | 6120 | 0.1154          | 0.9480    | 0.9641 | 0.9560 | 0.9769   |
+
+
+### Framework versions
+
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,91 @@
+{
+  "_name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
+  "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": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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": "4.46.2",
+  "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 sha256:7ee90216f8835cd7f59ca58c0b19ec20c88d4878d91785602275c892ba846bab
+size 437156776

runs/Dec05_09-17-01_0ce4b59191ac/events.out.tfevents.1733390231.0ce4b59191ac.5946.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68870fa38e4f4580268dea556f0a607ac70e2906b2805b3937cf6a02263d45ea
+size 14050

runs/Dec05_09-17-01_0ce4b59191ac/events.out.tfevents.1733390718.0ce4b59191ac.5946.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f82906dc84c3e9f86fd2002a5b1d008955d24c423b8a7fcb1dfd0688b8a3e1b1
+size 560

runs/Dec05_09-27-05_0ce4b59191ac/events.out.tfevents.1733390830.0ce4b59191ac.9325.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:157c0667f7813b1d6217ed0268cf5eaf948ae9f3d265a9932137e1746b8df0cc
+size 14050

runs/Dec05_09-27-05_0ce4b59191ac/events.out.tfevents.1733391318.0ce4b59191ac.9325.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8098ba096d34871564226e543d068b8c5ff6dcdf9d4cec976d5c408f306aeb5
+size 560

runs/Dec05_09-45-28_0ce4b59191ac/events.out.tfevents.1733391950.0ce4b59191ac.9325.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5c7089726940ca6ac7d52827e49f9476207c688b7ec7e06cf25cbd08c061390
+size 6644

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 @@
+{
+  "add_prefix_space": true,
+  "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": true,
+  "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 sha256:0224b3d0b04611ec7aa499c12311e2756cdc450ee8b1fdc9c7e8db08481e2813
+size 5368