Training in progress, epoch 1

README.md

@@ -0,0 +1,103 @@
+---
+license: mit
+base_model: neuralmind/bert-large-portuguese-cased
+tags:
+- generated_from_trainer
+datasets:
+- harem
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: NER_harem_bert-large-portuguese-cased
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: harem
+      type: harem
+      config: default
+      split: test
+      args: default
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.7077353867693384
+    - name: Recall
+      type: recall
+      value: 0.7553231228987672
+    - name: F1
+      type: f1
+      value: 0.7307553306830503
+    - name: Accuracy
+      type: accuracy
+      value: 0.9551379448220711
+---
+
+<!-- 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. -->
+
+# NER_harem_bert-large-portuguese-cased
+
+This model is a fine-tuned version of [neuralmind/bert-large-portuguese-cased](https://huggingface.co/neuralmind/bert-large-portuguese-cased) on the harem dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2487
+- Precision: 0.7077
+- Recall: 0.7553
+- F1: 0.7308
+- Accuracy: 0.9551
+
+## 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: 3e-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: 300
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 16   | 0.6334          | 0.0163    | 0.0078 | 0.0106 | 0.8468   |
+| No log        | 2.0   | 32   | 0.4537          | 0.2614    | 0.3112 | 0.2841 | 0.8826   |
+| No log        | 3.0   | 48   | 0.3117          | 0.5262    | 0.5671 | 0.5458 | 0.9231   |
+| No log        | 4.0   | 64   | 0.2421          | 0.5852    | 0.6631 | 0.6217 | 0.9385   |
+| No log        | 5.0   | 80   | 0.2099          | 0.5950    | 0.6855 | 0.6370 | 0.9479   |
+| No log        | 6.0   | 96   | 0.2153          | 0.6810    | 0.7464 | 0.7122 | 0.9551   |
+| No log        | 7.0   | 112  | 0.2270          | 0.6894    | 0.7198 | 0.7043 | 0.9546   |
+| No log        | 8.0   | 128  | 0.2213          | 0.6918    | 0.7437 | 0.7168 | 0.9554   |
+| No log        | 9.0   | 144  | 0.2299          | 0.7021    | 0.7564 | 0.7283 | 0.9545   |
+| No log        | 10.0  | 160  | 0.2256          | 0.7002    | 0.7591 | 0.7284 | 0.9562   |
+| No log        | 11.0  | 176  | 0.2169          | 0.7100    | 0.7736 | 0.7404 | 0.9568   |
+| No log        | 12.0  | 192  | 0.2266          | 0.6981    | 0.7740 | 0.7341 | 0.9571   |
+| No log        | 13.0  | 208  | 0.2322          | 0.7093    | 0.7620 | 0.7347 | 0.9570   |
+| No log        | 14.0  | 224  | 0.2487          | 0.7077    | 0.7553 | 0.7308 | 0.9551   |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,78 @@
+{
+  "_name_or_path": "PORTULAN/albertina-100m-portuguese-ptpt-encoder",
+  "architectures": [
+    "DebertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PESSOA",
+    "2": "I-PESSOA",
+    "3": "B-ORGANIZACAO",
+    "4": "I-ORGANIZACAO",
+    "5": "B-LOCAL",
+    "6": "I-LOCAL",
+    "7": "B-TEMPO",
+    "8": "I-TEMPO",
+    "9": "B-VALOR",
+    "10": "I-VALOR",
+    "11": "B-ABSTRACCAO",
+    "12": "I-ABSTRACCAO",
+    "13": "B-ACONTECIMENTO",
+    "14": "I-ACONTECIMENTO",
+    "15": "B-COISA",
+    "16": "I-COISA",
+    "17": "B-OBRA",
+    "18": "I-OBRA",
+    "19": "B-OUTRO",
+    "20": "I-OUTRO"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ABSTRACCAO": 11,
+    "B-ACONTECIMENTO": 13,
+    "B-COISA": 15,
+    "B-LOCAL": 5,
+    "B-OBRA": 17,
+    "B-ORGANIZACAO": 3,
+    "B-OUTRO": 19,
+    "B-PESSOA": 1,
+    "B-TEMPO": 7,
+    "B-VALOR": 9,
+    "I-ABSTRACCAO": 12,
+    "I-ACONTECIMENTO": 14,
+    "I-COISA": 16,
+    "I-LOCAL": 6,
+    "I-OBRA": 18,
+    "I-ORGANIZACAO": 4,
+    "I-OUTRO": 20,
+    "I-PESSOA": 2,
+    "I-TEMPO": 8,
+    "I-VALOR": 10,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "c2p",
+    "p2c"
+  ],
+  "position_biased_input": false,
+  "relative_attention": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 0,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69aff6dd40f2af49766291a469076fff8342b3a245c71b24bf2ae7dbe0baad6c
+size 554495468

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "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": "[SEP]",
+    "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 +1,59 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "errors": "replace",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "DebertaTokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "gpt2"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07e3cad1c2b4e99dece405c7b633d28012e66454a990462c0dc7b65b576ea3c0
+size 4984