trainer: training complete at 2024-02-10 17:34:36.971515.

README.md

@@ -0,0 +1,97 @@
+---
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+datasets:
+- essay_dataset
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: B001_cleaned
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: essay_dataset
+      type: essay_dataset
+      config: cleaned
+      split: test
+      args: cleaned
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value:
+        accuracy: 0.10526315789473684
+    - name: Precision
+      type: precision
+      value:
+        precision: 0.013157894736842105
+    - name: Recall
+      type: recall
+      value:
+        recall: 0.125
+    - name: F1
+      type: f1
+      value:
+        f1: 0.02380952380952381
+---
+
+<!-- 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. -->
+
+# B001_cleaned
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the essay_dataset dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.2117
+- Accuracy: {'accuracy': 0.10526315789473684}
+- Precision: {'precision': 0.013157894736842105}
+- Recall: {'recall': 0.125}
+- F1: {'f1': 0.02380952380952381}
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy                          | Precision                           | Recall            | F1                          |
+|:-------------:|:-----:|:----:|:---------------:|:---------------------------------:|:-----------------------------------:|:-----------------:|:---------------------------:|
+| No log        | 1.0   | 13   | 2.2061          | {'accuracy': 0.10526315789473684} | {'precision': 0.013157894736842105} | {'recall': 0.125} | {'f1': 0.02380952380952381} |
+| No log        | 2.0   | 26   | 2.2050          | {'accuracy': 0.10526315789473684} | {'precision': 0.013157894736842105} | {'recall': 0.125} | {'f1': 0.02380952380952381} |
+| No log        | 3.0   | 39   | 2.2045          | {'accuracy': 0.10526315789473684} | {'precision': 0.013157894736842105} | {'recall': 0.125} | {'f1': 0.02380952380952381} |
+| No log        | 4.0   | 52   | 2.2117          | {'accuracy': 0.10526315789473684} | {'precision': 0.013157894736842105} | {'recall': 0.125} | {'f1': 0.02380952380952381} |
+
+
+### Framework versions
+
+- Transformers 4.37.1
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "1": "1.0",
+    "2": "1.5",
+    "3": "2.0",
+    "4": "2.5",
+    "5": "3.0",
+    "6": "3.5",
+    "7": "4.0",
+    "8": "4.5",
+    "9": "5.0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "1.0": 1,
+    "1.5": 2,
+    "2.0": 3,
+    "2.5": 4,
+    "3.0": 5,
+    "3.5": 6,
+    "4.0": 7,
+    "4.5": 8,
+    "5.0": 9
+  },
+  "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": "4.37.1",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:838828830c73a2906883982a4337e5fa7db6586f1d6145d09f1339dc801defeb
+size 267854100

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 sha256:407414b3b4afc4e0ff2675dd8fbb2bd08941d4c4f102286ad4ed689a634d419d
+size 4664