add model

.gitignore

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

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model_index:
+- name: portuguese-archival-finding-aids
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 0.9617770479839446
+---
+
+<!-- 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. -->
+
+# portuguese-archival-finding-aids
+
+This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unkown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1812
+- Precision: 0.8624
+- Recall: 0.9557
+- F1: 0.9067
+- Accuracy: 0.9618
+
+## 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: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 192  | 0.1565          | 0.8511    | 0.9327 | 0.8900 | 0.9563   |
+| 0.1849        | 2.0   | 384  | 0.1594          | 0.8634    | 0.9543 | 0.9065 | 0.9619   |
+| 0.0454        | 3.0   | 576  | 0.1812          | 0.8624    | 0.9557 | 0.9067 | 0.9618   |
+
+
+### Framework versions
+
+- Transformers 4.10.0.dev0
+- Pytorch 1.9.0+cu111
+- Datasets 1.10.2
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "bert-base-multilingual-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": "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": 3072,
+  "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": 12,
+  "num_hidden_layers": 12,
+  "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": 119547
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f7d5c70b0d90d5a76ceb6b988b8400020be36c31d664e49229f89d89d82bead
+size 709168625

runs/Dec11_18-11-58_DESKTOP-GRC5L8E/1639246327.399495/events.out.tfevents.1639246327.DESKTOP-GRC5L8E.15736.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1c0e1c7d5fc6390b19d9ecf59a919b64f05240510bf7c85f7237ffafebe189a
+size 4395

runs/Dec11_18-11-58_DESKTOP-GRC5L8E/events.out.tfevents.1639246327.DESKTOP-GRC5L8E.15736.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7a0608407250626d95c94b7e848f2fe6d12004899880bf520ab5a2b42af1e3e
+size 5911

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": null, "name_or_path": "bert-base-multilingual-cased", "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b692d9495b713f0dc13e2653505ac14057a03549de04b9908bc31f2693c9dc
+size 2799