Commit using trainer.push_to_hub()

.gitignore

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

README.md

@@ -0,0 +1,92 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- lener_br
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model_index:
+- name: bertimbau-base-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: 0.9692504609383333
+---
+
+<!-- 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-base-lener_br
+
+This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on the lener_br dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2298
+- Precision: 0.8501
+- Recall: 0.9138
+- F1: 0.8808
+- Accuracy: 0.9693
+
+## 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: 15
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0686        | 1.0   | 1957  | 0.1399          | 0.7759    | 0.8669 | 0.8189 | 0.9641   |
+| 0.0437        | 2.0   | 3914  | 0.1457          | 0.7997    | 0.8938 | 0.8441 | 0.9623   |
+| 0.0313        | 3.0   | 5871  | 0.1675          | 0.8466    | 0.8744 | 0.8603 | 0.9651   |
+| 0.0201        | 4.0   | 7828  | 0.1621          | 0.8713    | 0.8839 | 0.8775 | 0.9718   |
+| 0.0137        | 5.0   | 9785  | 0.1811          | 0.7783    | 0.9159 | 0.8415 | 0.9645   |
+| 0.0105        | 6.0   | 11742 | 0.1836          | 0.8568    | 0.9009 | 0.8783 | 0.9692   |
+| 0.0105        | 7.0   | 13699 | 0.1649          | 0.8339    | 0.9125 | 0.8714 | 0.9725   |
+| 0.0059        | 8.0   | 15656 | 0.2298          | 0.8501    | 0.9138 | 0.8808 | 0.9693   |
+| 0.0051        | 9.0   | 17613 | 0.2210          | 0.8437    | 0.9045 | 0.8731 | 0.9693   |
+| 0.0061        | 10.0  | 19570 | 0.2499          | 0.8627    | 0.8946 | 0.8784 | 0.9681   |
+| 0.0041        | 11.0  | 21527 | 0.1985          | 0.8560    | 0.9052 | 0.8799 | 0.9720   |
+| 0.003         | 12.0  | 23484 | 0.2204          | 0.8498    | 0.9065 | 0.8772 | 0.9699   |
+| 0.0014        | 13.0  | 25441 | 0.2152          | 0.8425    | 0.9067 | 0.8734 | 0.9709   |
+| 0.0005        | 14.0  | 27398 | 0.2317          | 0.8553    | 0.8987 | 0.8765 | 0.9705   |
+| 0.0015        | 15.0  | 29355 | 0.2436          | 0.8543    | 0.8989 | 0.8760 | 0.9700   |
+
+
+### 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-base-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": 768,
+  "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": 3072,
+  "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": 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",
+  "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:d488202ac3fe766f991ffb7f04eaf587b1bba28202705a4eeb6ae914f094e45e
+size 433453553

runs/Jul13_14-49-26_c88825540bf2/1626187774.517446/events.out.tfevents.1626187774.c88825540bf2.75.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa2dc3f10e0fd32f0e8b1bf8edf7ef2f59b00a95aac53625be8a5054aae32bdb
+size 4234

runs/Jul13_14-49-26_c88825540bf2/events.out.tfevents.1626187774.c88825540bf2.75.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e830b8154758dafb8e2b6fcb08a1260bb437e2992bfb35dfb8d0821b1e70e2b
+size 20488

runs/Jul13_14-49-26_c88825540bf2/events.out.tfevents.1626190101.c88825540bf2.75.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5f685ba276eb9b722da8af44c9d131c18c485af975410224c0257aa39cfbcbe
+size 521

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/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:bb08c5e56cd3860de724efd57330ca7d09377a26f5b04ce713c574a9abeb3cdb
+size 2671