AmirlyPhd/final_V1-bert-text-classification-model

README.md

@@ -0,0 +1,94 @@
+---
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: final_V1-bert-text-classification-model
+  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. -->
+
+# final_V1-bert-text-classification-model
+
+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: 0.1649
+- Accuracy: 0.9713
+- F1: 0.8328
+- Precision: 0.8290
+- Recall: 0.8375
+
+## 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: 16
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 1.7173        | 0.11  | 50   | 1.7812          | 0.3445   | 0.1475 | 0.1755    | 0.1881 |
+| 0.9537        | 0.22  | 100  | 0.9779          | 0.7416   | 0.4399 | 0.4301    | 0.4701 |
+| 0.373         | 0.33  | 150  | 0.6741          | 0.8321   | 0.6187 | 0.6018    | 0.6423 |
+| 0.2625        | 0.44  | 200  | 0.3897          | 0.9070   | 0.6684 | 0.6503    | 0.6892 |
+| 0.2216        | 0.55  | 250  | 0.3971          | 0.9089   | 0.6670 | 0.6465    | 0.6920 |
+| 0.1583        | 0.66  | 300  | 0.3601          | 0.9029   | 0.6816 | 0.7957    | 0.6757 |
+| 0.1661        | 0.76  | 350  | 0.2266          | 0.9180   | 0.6950 | 0.7317    | 0.7019 |
+| 0.112         | 0.87  | 400  | 0.2525          | 0.9494   | 0.8020 | 0.7955    | 0.8132 |
+| 0.0857        | 0.98  | 450  | 0.2701          | 0.9459   | 0.8124 | 0.8060    | 0.8232 |
+| 0.1223        | 1.09  | 500  | 0.1781          | 0.9631   | 0.8281 | 0.8251    | 0.8319 |
+| 0.0641        | 1.2   | 550  | 0.2162          | 0.9552   | 0.8236 | 0.8229    | 0.8258 |
+| 0.0907        | 1.31  | 600  | 0.1486          | 0.9705   | 0.8351 | 0.8357    | 0.8346 |
+| 0.0738        | 1.42  | 650  | 0.1380          | 0.9696   | 0.8300 | 0.8276    | 0.8331 |
+| 0.0946        | 1.53  | 700  | 0.1577          | 0.9705   | 0.8357 | 0.8370    | 0.8345 |
+| 0.0476        | 1.64  | 750  | 0.1497          | 0.9707   | 0.8349 | 0.8337    | 0.8363 |
+| 0.0873        | 1.75  | 800  | 0.1722          | 0.9655   | 0.8318 | 0.8288    | 0.8353 |
+| 0.0487        | 1.86  | 850  | 0.1782          | 0.9647   | 0.8312 | 0.8283    | 0.8345 |
+| 0.0548        | 1.97  | 900  | 0.1610          | 0.9666   | 0.8336 | 0.8329    | 0.8346 |
+| 0.0492        | 2.07  | 950  | 0.1423          | 0.9688   | 0.8338 | 0.8287    | 0.8393 |
+| 0.0279        | 2.18  | 1000 | 0.1707          | 0.9669   | 0.8325 | 0.8287    | 0.8371 |
+| 0.0401        | 2.29  | 1050 | 0.1583          | 0.9688   | 0.8337 | 0.8300    | 0.8382 |
+| 0.0313        | 2.4   | 1100 | 0.1799          | 0.9647   | 0.8306 | 0.8274    | 0.8348 |
+| 0.025         | 2.51  | 1150 | 0.1661          | 0.9669   | 0.8320 | 0.8311    | 0.8335 |
+| 0.0043        | 2.62  | 1200 | 0.1933          | 0.9647   | 0.8305 | 0.8280    | 0.8339 |
+| 0.0115        | 2.73  | 1250 | 0.1570          | 0.9696   | 0.8328 | 0.8308    | 0.8352 |
+| 0.0198        | 2.84  | 1300 | 0.1538          | 0.9702   | 0.8340 | 0.8328    | 0.8355 |
+| 0.0085        | 2.95  | 1350 | 0.1591          | 0.9694   | 0.8337 | 0.8327    | 0.8351 |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "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:e72649d61ebfbcf7b1d384e6c65d2183ea949b9985b36262cc3a5df255719db4
+size 437974028

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:e78bf5e7f8b1ba1d7c3e4e02614d71e07f8682ca40db55eb24ad560f0a6c9d73
+size 4920