First version

.gitattributes

@@ -30,3 +30,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,72 @@
 ---
 license: apache-2.0
+language: br
+library_name: transformers
+tags:
+- question-answering
+datasets:
+- eraldoluis/faquad
+metrics:
+- squad
+
+model-index:
+- name: faquad-bert-base-portuguese-cased
+  results:
+  - task:
+      type: extractive-qa
+      name: Extractive Question-Answering
+    dataset:
+      type: eraldoluis/faquad
+      name: FaQuAD
+      split: eval
+    metrics:
+      - type: squad
+        value: 
+        - f1: 83.0912959832023
+          exact_match: 74.53169347209082
+        name: Eval F1 and ExactMatch
+        verified: false
 ---
+
+<!-- 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. -->
+
+# tmp_exs_faquad
+
+This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on the [FaQuAD dataset](https://huggingface.co/datasets/eraldoluis/faquad).
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+The model was trained on the `train` split and evaluated on the `eval` split.
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 64
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.21.3
+- Pytorch 1.12.1+cu113
+- Datasets 2.4.0
+- Tokenizers 0.12.1

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_exact_match": 74.53169347209082,
+    "eval_f1": 83.0912959832023,
+    "eval_samples": 12198,
+    "train_loss": 1.1721088012826149,
+    "train_runtime": 6793.9155,
+    "train_samples": 99470,
+    "train_samples_per_second": 43.923,
+    "train_steps_per_second": 0.687
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "neuralmind/bert-base-portuguese-cased",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.21.3",
+  "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:d7caff164835d55e8d5cab822d83e6832ad27cc30ccb2bda330ee09da011bda4
+size 433406769

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "name_or_path": "neuralmind/bert-base-portuguese-cased",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/home/eraldo/.cache/huggingface/transformers/eecc45187d085a1169eed91017d358cc0e9cbdd5dc236bcd710059dbf0a2f816.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.1721088012826149,
+    "train_runtime": 6793.9155,
+    "train_samples": 99470,
+    "train_samples_per_second": 43.923,
+    "train_steps_per_second": 0.687
+}

trainer_state.json

@@ -0,0 +1,133 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 4665,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.6784565916398713e-05,
+      "loss": 2.1905,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "eval_exact_match": 61.28666035950804,
+      "eval_f1": 71.363458978244,
+      "step": 500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2.356913183279743e-05,
+      "loss": 1.4634,
+      "step": 1000
+    },
+    {
+      "epoch": 0.64,
+      "eval_exact_match": 67.86187322611164,
+      "eval_f1": 77.44564129629615,
+      "step": 1000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.0353697749196142e-05,
+      "loss": 1.2925,
+      "step": 1500
+    },
+    {
+      "epoch": 0.96,
+      "eval_exact_match": 70.5771050141911,
+      "eval_f1": 79.53930047182527,
+      "step": 1500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.7138263665594855e-05,
+      "loss": 1.0802,
+      "step": 2000
+    },
+    {
+      "epoch": 1.29,
+      "eval_exact_match": 72.1286660359508,
+      "eval_f1": 80.97163819236762,
+      "step": 2000
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.392282958199357e-05,
+      "loss": 1.0438,
+      "step": 2500
+    },
+    {
+      "epoch": 1.61,
+      "eval_exact_match": 73.28287606433302,
+      "eval_f1": 81.68746817914159,
+      "step": 2500
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.0707395498392284e-05,
+      "loss": 1.0276,
+      "step": 3000
+    },
+    {
+      "epoch": 1.93,
+      "eval_exact_match": 72.99905392620624,
+      "eval_f1": 81.97780926342594,
+      "step": 3000
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 7.491961414790997e-06,
+      "loss": 0.8789,
+      "step": 3500
+    },
+    {
+      "epoch": 2.25,
+      "eval_exact_match": 74.03973509933775,
+      "eval_f1": 82.60781680674411,
+      "step": 3500
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 4.276527331189711e-06,
+      "loss": 0.8502,
+      "step": 4000
+    },
+    {
+      "epoch": 2.57,
+      "eval_exact_match": 74.33301797540209,
+      "eval_f1": 82.95704498318004,
+      "step": 4000
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.0610932475884245e-06,
+      "loss": 0.8325,
+      "step": 4500
+    },
+    {
+      "epoch": 2.89,
+      "eval_exact_match": 74.5600756859035,
+      "eval_f1": 83.17536432572425,
+      "step": 4500
+    },
+    {
+      "epoch": 3.0,
+      "step": 4665,
+      "total_flos": 5.848017388319232e+16,
+      "train_loss": 1.1721088012826149,
+      "train_runtime": 6793.9155,
+      "train_samples_per_second": 43.923,
+      "train_steps_per_second": 0.687
+    }
+  ],
+  "max_steps": 4665,
+  "num_train_epochs": 3,
+  "total_flos": 5.848017388319232e+16,
+  "trial_name": null,
+  "trial_params": null
+}