Training in progress, step 500

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+base_model: bert-large-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: chatbot
+  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. -->
+
+# chatbot
+
+This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6024
+- Accuracy: 0.8958
+- F1: 0.8910
+- Precision: 0.8846
+- Recall: 0.9295
+
+## 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: 32
+- eval_batch_size: 16
+- 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: 50
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 2.9886        | 10.0  | 50   | 2.5714          | 0.2708   | 0.1833 | 0.1547    | 0.2949 |
+| 1.3584        | 20.0  | 100  | 1.1008          | 0.8542   | 0.8496 | 0.8622    | 0.9071 |
+| 0.1639        | 30.0  | 150  | 0.6093          | 0.8958   | 0.8897 | 0.8910    | 0.9295 |
+| 0.0136        | 40.0  | 200  | 0.6092          | 0.9167   | 0.9112 | 0.9071    | 0.9423 |
+| 0.007         | 50.0  | 250  | 0.6024          | 0.8958   | 0.8910 | 0.8846    | 0.9295 |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.2.0+cu121
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,85 @@
+{
+  "_name_or_path": "bert-large-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": 1024,
+  "id2label": {
+    "0": "greeting",
+    "1": "troubleshooting_indo",
+    "2": "troubleshooting",
+    "3": "account_indo",
+    "4": "account",
+    "5": "contact_indo",
+    "6": "contact",
+    "7": "privacy_indo",
+    "8": "privacy",
+    "9": "basic_info_indo",
+    "10": "basic_info",
+    "11": "features_indo",
+    "12": "features",
+    "13": "technical_issues_indo",
+    "14": "technical_issues",
+    "15": "founders_indo",
+    "16": "founders",
+    "17": "technology_indo",
+    "18": "technology",
+    "19": "accessible_indo",
+    "20": "accessible",
+    "21": "thanks_indo",
+    "22": "thanks",
+    "23": "location_indo",
+    "24": "location",
+    "25": "video_recording_indo",
+    "26": "video_recording"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "accessible": 20,
+    "accessible_indo": 19,
+    "account": 4,
+    "account_indo": 3,
+    "basic_info": 10,
+    "basic_info_indo": 9,
+    "contact": 6,
+    "contact_indo": 5,
+    "features": 12,
+    "features_indo": 11,
+    "founders": 16,
+    "founders_indo": 15,
+    "greeting": 0,
+    "location": 24,
+    "location_indo": 23,
+    "privacy": 8,
+    "privacy_indo": 7,
+    "technical_issues": 14,
+    "technical_issues_indo": 13,
+    "technology": 18,
+    "technology_indo": 17,
+    "thanks": 22,
+    "thanks_indo": 21,
+    "troubleshooting": 2,
+    "troubleshooting_indo": 1,
+    "video_recording": 26,
+    "video_recording_indo": 25
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "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 sha256:3320963c7303b6ee825a052642f64873b605723a684b35b7065d6b2d1c031ba8
+size 1340725268

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 +1,58 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 256,
+  "model_max_length": 512,
+  "never_split": null,
+  "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:e4269b9615f572f30b1c61cae82cc3a30678ecc64eea9ff7b99afb233c118937
+size 4600