End of training

README.md

@@ -0,0 +1,69 @@
+---
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: bert_sql_classfication
+  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. -->
+
+# bert_sql_classfication
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3563
+- Accuracy: 0.95
+
+## 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: 16
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.7667        | 1.0   | 12   | 1.6574          | 0.45     |
+| 1.556         | 2.0   | 24   | 1.1844          | 0.9      |
+| 1.0991        | 3.0   | 36   | 0.8021          | 0.9      |
+| 0.8913        | 4.0   | 48   | 0.6070          | 0.95     |
+| 0.495         | 5.0   | 60   | 0.5021          | 0.9      |
+| 0.3888        | 6.0   | 72   | 0.4484          | 0.9      |
+| 0.2608        | 7.0   | 84   | 0.3813          | 0.9      |
+| 0.2031        | 8.0   | 96   | 0.3626          | 0.95     |
+| 0.1348        | 9.0   | 108  | 0.3812          | 0.9      |
+| 0.1166        | 10.0  | 120  | 0.3563          | 0.95     |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.0.0
+- Datasets 2.1.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "date_functions",
+    "1": "group_by",
+    "2": "order_by",
+    "3": "ratio",
+    "4": "table_join",
+    "5": "where"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "date_functions": 0,
+    "group_by": 1,
+    "order_by": 2,
+    "ratio": 3,
+    "table_join": 4,
+    "where": 5
+  },
+  "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": "4.36.2",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e71e1bfc15b876e62a5f3adb928068caca6e1cef44fa764f55290750c8ba8c6f
+size 267844872

runs/Jan18_05-02-42_08c5dd7ae1be/events.out.tfevents.1705554162.08c5dd7ae1be.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:639e0594003e4c5f077adaf601b1e722afa0a4ffc9d8d65ce80ea9607e55dee1
+size 11750

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 sha256:0234cb26bba5830bee72b802e4ded619ad2a7070956044d579eea32bec43fb0a
+size 4283