add model

.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-large-pt-archive
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 0.9766762474673703
+---
+
+<!-- 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-large-pt-archive
+
+This model is a fine-tuned version of [neuralmind/bert-large-portuguese-cased](https://huggingface.co/neuralmind/bert-large-portuguese-cased) on an unkown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0869
+- Precision: 0.9280
+- Recall: 0.9541
+- F1: 0.9409
+- Accuracy: 0.9767
+
+## 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: 4
+- eval_batch_size: 4
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0665        | 1.0   | 765  | 0.1020          | 0.8928    | 0.9566 | 0.9236 | 0.9696   |
+| 0.0392        | 2.0   | 1530 | 0.0781          | 0.9229    | 0.9586 | 0.9404 | 0.9757   |
+| 0.0201        | 3.0   | 2295 | 0.0809          | 0.9278    | 0.9550 | 0.9412 | 0.9767   |
+| 0.0152        | 4.0   | 3060 | 0.0869          | 0.9280    | 0.9541 | 0.9409 | 0.9767   |
+
+
+### 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-large-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": 1024,
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_2": 2,
+    "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": 16,
+  "num_hidden_layers": 24,
+  "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:ad14b81794963f0f15a95605b017bf827cf25ca1dfbee60edb73f252b4ada31e
+size 1333593265

runs/Dec11_18-36-15_DESKTOP-GRC5L8E/1639247785.6670897/events.out.tfevents.1639247785.DESKTOP-GRC5L8E.5028.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be8de5770c3b110272b6bf5e2de1b299d6bac47df665f84ba2a0fee198965bd
+size 4351

runs/Dec11_18-36-15_DESKTOP-GRC5L8E/events.out.tfevents.1639247785.DESKTOP-GRC5L8E.5028.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c69c0978c16ab32cab832da4d87e5881486c0beea4209c9adb9d923515435c8
+size 7940

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\\d5b721c156180bbbcc4a1017e8c72a18f8f96cdc178acec5ddcd45905712b4cf.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "neuralmind/bert-large-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 sha256:7a8d1228ec72d442319ac8f90acb57b6f66c53584fd51a642e40cb23819c41e7
+size 2799