google-play-sentiment-analysis

README.md

@@ -0,0 +1,62 @@
+---
+license: mit
+base_model: neuralmind/bert-base-portuguese-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: test_trainer
+  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. -->
+
+# test_trainer
+
+This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3183
+- Accuracy: 0.5193
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.4055        | 1.0   | 975  | 1.2549          | 0.4376   |
+| 1.1243        | 2.0   | 1950 | 1.2159          | 0.5067   |
+| 0.8642        | 3.0   | 2925 | 1.3183          | 0.5193   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "neuralmind/bert-base-portuguese-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Muito Negativo",
+    "1": "Negativo",
+    "2": "Neutro",
+    "3": "Positivo",
+    "4": "Muito Positivo"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Muito Negativo": 0,
+    "Muito Positivo": 4,
+    "Negativo": 1,
+    "Neutro": 2,
+    "Positivo": 3
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36aae8e34f16f7f79918e4615ebd7d8f48d334daed19dcef5c64dec07e8b38b4
+size 435731452

runs/Dec06_01-02-26_3580dc5ae611/events.out.tfevents.1701824557.3580dc5ae611.292.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86312606c06a503b4112d7c211c388a9104c9f59ae1fc241a33458b97df2c0e
+size 5967

runs/Dec06_01-04-13_3580dc5ae611/events.out.tfevents.1701824654.3580dc5ae611.292.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e21acad2c230a28ee41fa514f961aa8582d8ef5b99ee03ba9a18f3dddbdbd87d
+size 6807

runs/Dec06_01-21-17_3580dc5ae611/events.out.tfevents.1701825684.3580dc5ae611.6513.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f8980f1c2d40c3a44e48712ead6a69199fddaf8e3c420c1f147269f5a045666
+size 4184

runs/Dec06_01-22-20_3580dc5ae611/events.out.tfevents.1701825744.3580dc5ae611.6974.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bddabb85342687cfb95a07ac7af219c8c9806950b812fda231b584225d1c970
+size 6758

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 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "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 sha256:7e9c5ac15230789b21a5edaeb4295588f3ca16d6ffa24fea5076f2593bcc2e30
+size 4600