End of training

README.md

@@ -1,8 +1,13 @@
 ---
 license: apache-2.0
-base_model: bert-base-uncased
+base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
 model-index:
 - name: DIALOGUE_five_model
   results: []
@@ -13,15 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # DIALOGUE_five_model
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
+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:
-- eval_loss: 0.1106
-- eval_accuracy: 0.9902
-- eval_runtime: 1.2371
-- eval_samples_per_second: 82.453
-- eval_steps_per_second: 10.509
-- epoch: 1.88
-- step: 90
+- Loss: 0.4632
+- Accuracy: 0.9342
+- Precision: 0.9421
+- Recall: 0.9342
+- F1: 0.9313
 
 ## Model description
 
@@ -40,7 +43,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
+- learning_rate: 0.00012
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -48,6 +51,21 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 3
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.1351        | 0.31  | 15   | 0.1519          | 0.9737   | 0.9762    | 0.9737 | 0.9736 |
+| 0.0519        | 0.62  | 30   | 0.2044          | 0.9737   | 0.9762    | 0.9737 | 0.9736 |
+| 0.0728        | 0.94  | 45   | 0.1813          | 0.9737   | 0.9762    | 0.9737 | 0.9736 |
+| 0.0017        | 1.25  | 60   | 0.0108          | 1.0      | 1.0       | 1.0    | 1.0    |
+| 0.0492        | 1.56  | 75   | 0.3072          | 0.9342   | 0.9421    | 0.9342 | 0.9313 |
+| 0.0881        | 1.88  | 90   | 0.1682          | 0.9737   | 0.9762    | 0.9737 | 0.9736 |
+| 0.0018        | 2.19  | 105  | 0.3500          | 0.9342   | 0.9421    | 0.9342 | 0.9313 |
+| 0.0008        | 2.5   | 120  | 0.4114          | 0.9342   | 0.9421    | 0.9342 | 0.9313 |
+| 0.0011        | 2.81  | 135  | 0.4632          | 0.9342   | 0.9421    | 0.9342 | 0.9313 |
+
+
 ### Framework versions
 
 - Transformers 4.36.2

config.json

@@ -1,39 +1,37 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "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"
+    "0": "Hospital-Inform",
+    "1": "Hospital-Request",
+    "2": "general-bye",
+    "3": "general-thank"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
     "LABEL_2": 2,
     "LABEL_3": 3
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
   "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",
-  "type_vocab_size": 2,
-  "use_cache": true,
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf1b9d9bcd8bec5ca7b82c25c94976d1c495d55eac2a823e832d9689b4620256
-size 437964800
+oid sha256:03296576272917aad8f08c5cec875124527920671c9cd56fdefdc11b0b9a7633
+size 267838720

runs/Jan16_10-57-54_745092e66db7/events.out.tfevents.1705402688.745092e66db7.965.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e9bfb90b2fade6818c470b34566c995f26c42a609b6ab42ae1b9489598b6674
+size 10480

tokenizer_config.json

@@ -52,6 +52,6 @@
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ffd96bd074c020111a8f26f6fb5eaa5709f99dec8ba0d2e84b3f8e4508ad7fc
+oid sha256:c00aed96eab2e103b39781b96d424bc72a596207866310fd884d8a175a71bdee
 size 4728