adediu25/distilbert-base-uncased-binary-classification

README.md

@@ -0,0 +1,69 @@
+---
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: 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. -->
+
+# trainer
+
+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: 0.6671
+- Accuracy: {'accuracy': 0.6136936111747194}
+
+## 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: 0.001
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy                         |
+|:-------------:|:-----:|:-----:|:---------------:|:--------------------------------:|
+| 0.6652        | 1.0   | 5096  | 0.6672          | {'accuracy': 0.6136936111747194} |
+| 0.6621        | 2.0   | 10192 | 0.6675          | {'accuracy': 0.6136936111747194} |
+| 0.6702        | 3.0   | 15288 | 0.6711          | {'accuracy': 0.6136936111747194} |
+| 0.6748        | 4.0   | 20384 | 0.6705          | {'accuracy': 0.6136936111747194} |
+| 0.6693        | 5.0   | 25480 | 0.6674          | {'accuracy': 0.6136936111747194} |
+| 0.6594        | 6.0   | 30576 | 0.6672          | {'accuracy': 0.6136936111747194} |
+| 0.6663        | 7.0   | 35672 | 0.6682          | {'accuracy': 0.6136936111747194} |
+| 0.6738        | 8.0   | 40768 | 0.6671          | {'accuracy': 0.6136936111747194} |
+| 0.6669        | 9.0   | 45864 | 0.6671          | {'accuracy': 0.6136936111747194} |
+| 0.6654        | 10.0  | 50960 | 0.6671          | {'accuracy': 0.6136936111747194} |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Non-HS",
+    "1": "HS"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "HS": 1,
+    "Non-HS": 0
+  },
+  "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": "4.38.2",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97219368b07aa31839d4c96f6a57e98683fec34373954ae12bd5b9e287c63f37
+size 267832560

runs/Apr12_02-23-05_25fee827e415/events.out.tfevents.1712888587.25fee827e415.1118.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93ef8296e3bfda154753eab380585219c5b44ff449fa557401bdde5185969362
+size 4522

runs/Apr12_03-02-44_25fee827e415/events.out.tfevents.1712890966.25fee827e415.1118.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e17c5fc6db676e5a41f9ee10110fb88edfd1fb61f03bf8be08c4d264ac73d572
+size 29214

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 +1,56 @@
+{
+  "add_prefix_space": true,
+  "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 sha256:20f45f383e3b1da361a15121b490e02caa99a2b967bb73ff04564be82e106b11
+size 4856