End of training

README.md

@@ -0,0 +1,105 @@
+---
+license: cc-by-4.0
+base_model: NazaGara/NER-fine-tuned-BETO
+tags:
+- generated_from_trainer
+datasets:
+- conll2002
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: beto-finetuned-ner-cfv
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: conll2002
+      type: conll2002
+      config: es
+      split: validation
+      args: es
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.8614471581830633
+    - name: Recall
+      type: recall
+      value: 0.8671875
+    - name: F1
+      type: f1
+      value: 0.8643077980075576
+    - name: Accuracy
+      type: accuracy
+      value: 0.9790072369291234
+---
+
+<!-- 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. -->
+
+# beto-finetuned-ner-cfv
+
+This model is a fine-tuned version of [NazaGara/NER-fine-tuned-BETO](https://huggingface.co/NazaGara/NER-fine-tuned-BETO) on the conll2002 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1659
+- Precision: 0.8614
+- Recall: 0.8672
+- F1: 0.8643
+- Accuracy: 0.9790
+
+## 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: 4e-06
+- 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: 16
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0272        | 1.0   | 1041  | 0.1062          | 0.8549    | 0.8637 | 0.8593 | 0.9786   |
+| 0.0208        | 2.0   | 2082  | 0.1127          | 0.8443    | 0.8596 | 0.8519 | 0.9782   |
+| 0.0158        | 3.0   | 3123  | 0.1195          | 0.8545    | 0.8598 | 0.8572 | 0.9787   |
+| 0.0129        | 4.0   | 4164  | 0.1332          | 0.8629    | 0.8589 | 0.8609 | 0.9782   |
+| 0.0107        | 5.0   | 5205  | 0.1299          | 0.8555    | 0.8635 | 0.8595 | 0.9786   |
+| 0.0087        | 6.0   | 6246  | 0.1486          | 0.8564    | 0.8564 | 0.8564 | 0.9782   |
+| 0.0085        | 7.0   | 7287  | 0.1583          | 0.8618    | 0.8596 | 0.8607 | 0.9783   |
+| 0.0066        | 8.0   | 8328  | 0.1582          | 0.8604    | 0.8580 | 0.8592 | 0.9783   |
+| 0.0052        | 9.0   | 9369  | 0.1571          | 0.8554    | 0.8566 | 0.8560 | 0.9781   |
+| 0.0054        | 10.0  | 10410 | 0.1604          | 0.8628    | 0.8640 | 0.8634 | 0.9787   |
+| 0.004         | 11.0  | 11451 | 0.1584          | 0.8624    | 0.8670 | 0.8647 | 0.9791   |
+| 0.0036        | 12.0  | 12492 | 0.1633          | 0.8603    | 0.8658 | 0.8630 | 0.9786   |
+| 0.0036        | 13.0  | 13533 | 0.1620          | 0.8628    | 0.8658 | 0.8643 | 0.9790   |
+| 0.0032        | 14.0  | 14574 | 0.1645          | 0.8617    | 0.8676 | 0.8647 | 0.9793   |
+| 0.0028        | 15.0  | 15615 | 0.1645          | 0.8604    | 0.8670 | 0.8637 | 0.9792   |
+| 0.003         | 16.0  | 16656 | 0.1659          | 0.8614    | 0.8672 | 0.8643 | 0.9790   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "NazaGara/NER-fine-tuned-BETO",
+  "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-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "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": "4.41.2",
+  "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 sha256:9e45a586d0038e105e9034da8418b526bd1bfb6d4a4077d93ebdaae572bae265
+size 437092180

runs/Jun06_01-02-46_770262389be9/events.out.tfevents.1717635775.770262389be9.476.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab8f145769c2b3a85935962e1b210d43bbc402c107d038bcafe87169f11a48a0
+size 20119

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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "num_labels": 9,
+  "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 sha256:03f4a584f60c9423318871338ceca985209fde4893d92d3d8511037f0d537c6f
+size 5112