AmirlyPhd/final_V1-distilbert-text-classification-model

README.md

@@ -0,0 +1,94 @@
+---
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: final_V1-distilbert-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-distilbert-text-classification-model
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1232
+- Accuracy: 0.9743
+- F1: 0.8372
+- Precision: 0.8341
+- Recall: 0.8408
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 1.7299        | 0.11  | 50   | 1.8504          | 0.2773   | 0.0874 | 0.1995    | 0.1296 |
+| 0.7996        | 0.22  | 100  | 0.7195          | 0.8242   | 0.5075 | 0.5040    | 0.5175 |
+| 0.3009        | 0.33  | 150  | 0.4573          | 0.8991   | 0.6736 | 0.6652    | 0.6833 |
+| 0.2559        | 0.44  | 200  | 0.5667          | 0.8701   | 0.6478 | 0.6293    | 0.6709 |
+| 0.1636        | 0.55  | 250  | 0.4599          | 0.9040   | 0.6752 | 0.6662    | 0.6864 |
+| 0.1813        | 0.66  | 300  | 0.3651          | 0.9103   | 0.6823 | 0.8187    | 0.6881 |
+| 0.1695        | 0.76  | 350  | 0.3603          | 0.9114   | 0.6969 | 0.8090    | 0.7002 |
+| 0.128         | 0.87  | 400  | 0.3779          | 0.9191   | 0.7197 | 0.7975    | 0.7165 |
+| 0.0976        | 0.98  | 450  | 0.3244          | 0.9095   | 0.7308 | 0.7394    | 0.7275 |
+| 0.0867        | 1.09  | 500  | 0.1825          | 0.9617   | 0.8283 | 0.8278    | 0.8294 |
+| 0.059         | 1.2   | 550  | 0.1847          | 0.9614   | 0.8258 | 0.8234    | 0.8291 |
+| 0.0719        | 1.31  | 600  | 0.1783          | 0.9590   | 0.8273 | 0.8263    | 0.8287 |
+| 0.0504        | 1.42  | 650  | 0.1311          | 0.9702   | 0.8325 | 0.8337    | 0.8315 |
+| 0.0525        | 1.53  | 700  | 0.1531          | 0.9694   | 0.8325 | 0.8355    | 0.8295 |
+| 0.0193        | 1.64  | 750  | 0.1675          | 0.9666   | 0.8311 | 0.8291    | 0.8334 |
+| 0.081         | 1.75  | 800  | 0.1531          | 0.9705   | 0.8329 | 0.8306    | 0.8354 |
+| 0.0453        | 1.86  | 850  | 0.2261          | 0.9295   | 0.7451 | 0.8081    | 0.7321 |
+| 0.0401        | 1.97  | 900  | 0.2015          | 0.9601   | 0.8283 | 0.8263    | 0.8315 |
+| 0.0686        | 2.07  | 950  | 0.1674          | 0.9642   | 0.8291 | 0.8255    | 0.8337 |
+| 0.0353        | 2.18  | 1000 | 0.1639          | 0.9664   | 0.8303 | 0.8264    | 0.8350 |
+| 0.0345        | 2.29  | 1050 | 0.1830          | 0.9639   | 0.8295 | 0.8264    | 0.8335 |
+| 0.0212        | 2.4   | 1100 | 0.1978          | 0.9634   | 0.8291 | 0.8258    | 0.8336 |
+| 0.0028        | 2.51  | 1150 | 0.1864          | 0.9653   | 0.8305 | 0.8273    | 0.8344 |
+| 0.0023        | 2.62  | 1200 | 0.1906          | 0.9661   | 0.8309 | 0.8277    | 0.8348 |
+| 0.0076        | 2.73  | 1250 | 0.1826          | 0.9669   | 0.8307 | 0.8278    | 0.8341 |
+| 0.0272        | 2.84  | 1300 | 0.1830          | 0.9666   | 0.8306 | 0.8283    | 0.8335 |
+| 0.0065        | 2.95  | 1350 | 0.1908          | 0.9661   | 0.8303 | 0.8278    | 0.8333 |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "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,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11067cf9602fe4d98f8eab27e32cbf7a5a921d2ae224d5e7a5f2d8cb8277252c
+size 267847948

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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4159371078fc0cb67b01d0fbe93abcad1c7e1fd36a553ae65b2d1949713c562
+size 4920