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: 0.1498
+- Accuracy: 0.9713
+- F1: 0.8341
+- Precision: 0.8330
+- Recall: 0.8356
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 1.6252        | 0.11  | 50   | 1.7120          | 0.3451   | 0.1545 | 0.2382    | 0.1762 |
+| 0.7857        | 0.22  | 100  | 0.7296          | 0.8209   | 0.4973 | 0.4815    | 0.5166 |
+| 0.2986        | 0.33  | 150  | 0.5358          | 0.8830   | 0.6565 | 0.6402    | 0.6744 |
+| 0.2612        | 0.44  | 200  | 0.4678          | 0.9035   | 0.6704 | 0.6621    | 0.6795 |
+| 0.153         | 0.55  | 250  | 0.4325          | 0.9065   | 0.6648 | 0.6446    | 0.6879 |
+| 0.2274        | 0.66  | 300  | 0.3498          | 0.8969   | 0.6440 | 0.6237    | 0.6677 |
+| 0.1449        | 0.76  | 350  | 0.4254          | 0.8964   | 0.6885 | 0.8012    | 0.6895 |
+| 0.1695        | 0.87  | 400  | 0.3484          | 0.9248   | 0.7301 | 0.7857    | 0.7208 |
+| 0.1206        | 0.98  | 450  | 0.3075          | 0.9218   | 0.7351 | 0.7586    | 0.7279 |
+| 0.1142        | 1.09  | 500  | 0.2241          | 0.9467   | 0.8063 | 0.7964    | 0.8218 |
+| 0.0642        | 1.2   | 550  | 0.2527          | 0.9491   | 0.8159 | 0.8106    | 0.8239 |
+| 0.0935        | 1.31  | 600  | 0.1961          | 0.9601   | 0.8216 | 0.8270    | 0.8173 |
+| 0.0755        | 1.42  | 650  | 0.1290          | 0.9691   | 0.8272 | 0.8348    | 0.8201 |
+| 0.108         | 1.53  | 700  | 0.1712          | 0.9612   | 0.8215 | 0.8311    | 0.8130 |
+| 0.0667        | 1.64  | 750  | 0.1449          | 0.9716   | 0.8354 | 0.8371    | 0.8338 |
+| 0.0925        | 1.75  | 800  | 0.1193          | 0.9721   | 0.8345 | 0.8353    | 0.8337 |
+| 0.0769        | 1.86  | 850  | 0.1477          | 0.9675   | 0.8299 | 0.8270    | 0.8334 |
+| 0.0558        | 1.97  | 900  | 0.1988          | 0.9606   | 0.8239 | 0.8194    | 0.8299 |
+| 0.0379        | 2.07  | 950  | 0.1546          | 0.9694   | 0.8319 | 0.8300    | 0.8340 |
+| 0.0358        | 2.18  | 1000 | 0.1871          | 0.9655   | 0.8295 | 0.8283    | 0.8312 |
+| 0.0248        | 2.29  | 1050 | 0.1631          | 0.9661   | 0.8303 | 0.8278    | 0.8333 |
+| 0.0412        | 2.4   | 1100 | 0.1688          | 0.9658   | 0.8283 | 0.8235    | 0.8340 |
+| 0.0096        | 2.51  | 1150 | 0.1726          | 0.9661   | 0.8316 | 0.8297    | 0.8342 |
+| 0.0025        | 2.62  | 1200 | 0.1808          | 0.9653   | 0.8300 | 0.8261    | 0.8348 |
+| 0.0074        | 2.73  | 1250 | 0.1697          | 0.9677   | 0.8323 | 0.8291    | 0.8360 |
+| 0.028         | 2.84  | 1300 | 0.1630          | 0.9705   | 0.8359 | 0.8344    | 0.8377 |
+| 0.0292        | 2.95  | 1350 | 0.1743          | 0.9696   | 0.8352 | 0.8341    | 0.8366 |
+
+
+### 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 sha256:08ace5345b704ef67d0077b47f8c909614a113fbc4dca522dca900ef29b4037f
+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 sha256:1027cfa045ff361f8629fe3dfdb411af1d9ecd4de7bc0372c23d26eb6a2d632e
+size 4920