rhaymison/bert-squad-portuguese

README.md

@@ -0,0 +1,92 @@
+---
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+model-index:
+- name: finetune-BERT-squad
+  results: []
+---
+
+<!-- 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. -->
+
+# finetune-BERT-squad
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5641
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 2.7626        | 0.08  | 500   | 2.5754          |
+| 2.5464        | 0.16  | 1000  | 2.3808          |
+| 2.4107        | 0.24  | 1500  | 2.2688          |
+| 2.2761        | 0.32  | 2000  | 2.1665          |
+| 2.2131        | 0.41  | 2500  | 2.0738          |
+| 2.1205        | 0.49  | 3000  | 1.9971          |
+| 2.0377        | 0.57  | 3500  | 1.9840          |
+| 2.0069        | 0.65  | 4000  | 1.8964          |
+| 1.9743        | 0.73  | 4500  | 1.8704          |
+| 1.9438        | 0.81  | 5000  | 1.8286          |
+| 1.9039        | 0.89  | 5500  | 1.8021          |
+| 1.8537        | 0.97  | 6000  | 1.7742          |
+| 1.6983        | 1.06  | 6500  | 1.7601          |
+| 1.6149        | 1.14  | 7000  | 1.7156          |
+| 1.5687        | 1.22  | 7500  | 1.7334          |
+| 1.6083        | 1.3   | 8000  | 1.6960          |
+| 1.6093        | 1.38  | 8500  | 1.6979          |
+| 1.6001        | 1.46  | 9000  | 1.6654          |
+| 1.5706        | 1.54  | 9500  | 1.6478          |
+| 1.5379        | 1.62  | 10000 | 1.6440          |
+| 1.5143        | 1.7   | 10500 | 1.6111          |
+| 1.4894        | 1.79  | 11000 | 1.6249          |
+| 1.5061        | 1.87  | 11500 | 1.5881          |
+| 1.4999        | 1.95  | 12000 | 1.5907          |
+| 1.3902        | 2.03  | 12500 | 1.5939          |
+| 1.2689        | 2.11  | 13000 | 1.6066          |
+| 1.2791        | 2.19  | 13500 | 1.5989          |
+| 1.2811        | 2.27  | 14000 | 1.6070          |
+| 1.2999        | 2.35  | 14500 | 1.5910          |
+| 1.248         | 2.44  | 15000 | 1.6142          |
+| 1.2373        | 2.52  | 15500 | 1.5919          |
+| 1.2767        | 2.6   | 16000 | 1.5836          |
+| 1.2809        | 2.68  | 16500 | 1.5665          |
+| 1.267         | 2.76  | 17000 | 1.5690          |
+| 1.2798        | 2.84  | 17500 | 1.5629          |
+| 1.26          | 2.92  | 18000 | 1.5641          |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "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,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51646d96c89d938829ea65ac9778511b50f2e7a6bbde549421f2ac54170cfd1e
+size 435596088

runs/Mar21_13-27-16_60dd32125665/events.out.tfevents.1711027677.60dd32125665.4249.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26c0a3c10cb352c983436d73483d4956ca9b121710a0b4672fbc16717eec42b0
+size 4563

runs/Mar21_13-29-41_60dd32125665/events.out.tfevents.1711027789.60dd32125665.4249.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bc82c4f365f49e5e115fe2f5e698fd6e8f249b48b547c5f1cd98144dc267b64
+size 22309

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 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be0af72b66ab726ffbf9d140a20b31ae5efebdff236f0cca3533941ce559917d
+size 4856