lfcc/bert-base-pt-archive

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,75 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model_index:
+- name: bert-base-pt-archive
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 0.9700325118974698
+---
+
+<!-- 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-pt-archive
+
+This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on an unkown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1140
+- Precision: 0.9147
+- Recall: 0.9483
+- F1: 0.9312
+- Accuracy: 0.9700
+
+## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 192  | 0.1438          | 0.8917    | 0.9392 | 0.9148 | 0.9633   |
+| 0.2454        | 2.0   | 384  | 0.1222          | 0.8985    | 0.9417 | 0.9196 | 0.9671   |
+| 0.0526        | 3.0   | 576  | 0.1098          | 0.9150    | 0.9481 | 0.9312 | 0.9698   |
+| 0.0372        | 4.0   | 768  | 0.1140          | 0.9147    | 0.9483 | 0.9312 | 0.9700   |
+
+
+### Framework versions
+
+- Transformers 4.10.0.dev0
+- Pytorch 1.9.0+cu111
+- Datasets 1.10.2
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "neuralmind/bert-base-portuguese-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-Organizacao",
+    "2": "I-Local",
+    "3": "B-Local",
+    "4": "B-Pessoa",
+    "5": "I-Profissao",
+    "6": "B-Profissao",
+    "7": "B-Data",
+    "8": "I-Data",
+    "9": "I-Pessoa",
+    "10": "I-Organizacao"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Data": 7,
+    "B-Local": 3,
+    "B-Organizacao": 1,
+    "B-Pessoa": 4,
+    "B-Profissao": 6,
+    "I-Data": 8,
+    "I-Local": 2,
+    "I-Organizacao": 10,
+    "I-Pessoa": 9,
+    "I-Profissao": 5,
+    "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": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db77fd2e0944d4d4f78241ca7d0265f355d62c2ae72164f668934fe50320748
+size 433447409

runs/Jan18_17-09-47_DESKTOP-GRC5L8E/1642526051.624885/events.out.tfevents.1642526051.DESKTOP-GRC5L8E.7444.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04b17c4616519e11832848fdc715baf0978e1b5708b33af129489f8cfb96c7b9
+size 4347

runs/Jan18_17-09-47_DESKTOP-GRC5L8E/events.out.tfevents.1642526051.DESKTOP-GRC5L8E.7444.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47829cbffa3ed8350c13e71cf6495d7db1b5e2ab0616af5881abc7630f577c80
+size 6549

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "C:\\Users\\Filip/.cache\\huggingface\\transformers\\eecc45187d085a1169eed91017d358cc0e9cbdd5dc236bcd710059dbf0a2f816.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "neuralmind/bert-base-portuguese-cased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:690bcf693caaa432b8e3305ed624e181db634da3e6892fbf0bb83ed1c531599c
+size 2799