Commit using trainer.push_to_hub()

.gitignore

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

README.md

@@ -0,0 +1,78 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- lener_br
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model_index:
+- name: bertimbau-large-lener_br
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: lener_br
+      type: lener_br
+      args: lener_br
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 0.9680466881009341
+---
+
+<!-- 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. -->
+
+# bertimbau-large-lener_br
+
+This model is a fine-tuned version of [neuralmind/bert-large-portuguese-cased](https://huggingface.co/neuralmind/bert-large-portuguese-cased) on the lener_br dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1212
+- Precision: 0.8574
+- Recall: 0.8925
+- F1: 0.8746
+- Accuracy: 0.9680
+
+## 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: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0569        | 1.0   | 1957 | 0.1212          | 0.8574    | 0.8925 | 0.8746 | 0.9680   |
+
+
+### Framework versions
+
+- Transformers 4.8.2
+- Pytorch 1.9.0+cu102
+- Datasets 1.9.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "neuralmind/bert-large-portuguese-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "B-ORGANIZACAO",
+    "2": "I-ORGANIZACAO",
+    "3": "B-PESSOA",
+    "4": "I-PESSOA",
+    "5": "B-TEMPO",
+    "6": "I-TEMPO",
+    "7": "B-LOCAL",
+    "8": "I-LOCAL",
+    "9": "B-LEGISLACAO",
+    "10": "I-LEGISLACAO",
+    "11": "B-JURISPRUDENCIA",
+    "12": "I-JURISPRUDENCIA"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-JURISPRUDENCIA": 11,
+    "B-LEGISLACAO": 9,
+    "B-LOCAL": 7,
+    "B-ORGANIZACAO": 1,
+    "B-PESSOA": 3,
+    "B-TEMPO": 5,
+    "I-JURISPRUDENCIA": 12,
+    "I-LEGISLACAO": 10,
+    "I-LOCAL": 8,
+    "I-ORGANIZACAO": 2,
+    "I-PESSOA": 4,
+    "I-TEMPO": 6,
+    "O": 0
+  },
+  "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",
+  "transformers_version": "4.8.2",
+  "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 sha256:494ecc3959bc3c092d27448c08e3e8174592e942cc58b3fa94d2416ca3299187
+size 1333601457

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, "model_max_length": 512, "special_tokens_map_file": "/root/.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:ab4bb7f1cd452930d28253762e8e5de81589166907b08df5ce774141cea76b0c
+size 2671