End of training

README.md

@@ -1,10 +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_four_model
   results: []
@@ -15,10 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # DIALOGUE_four_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:
-- Loss: 0.0457
-- Accuracy: 0.9902
+- Loss: 0.1237
+- Accuracy: 0.9737
+- Precision: 0.9762
+- Recall: 0.9737
+- F1: 0.9736
 
 ## Model description
 
@@ -47,17 +53,17 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.083         | 0.31  | 15   | 0.0933          | 0.9706   |
-| 0.0508        | 0.62  | 30   | 0.0409          | 0.9902   |
-| 0.0158        | 0.94  | 45   | 0.0600          | 0.9902   |
-| 0.013         | 1.25  | 60   | 0.0626          | 0.9902   |
-| 0.0052        | 1.56  | 75   | 0.0451          | 0.9804   |
-| 0.0045        | 1.88  | 90   | 0.0422          | 0.9902   |
-| 0.0035        | 2.19  | 105  | 0.0446          | 0.9902   |
-| 0.0031        | 2.5   | 120  | 0.0457          | 0.9902   |
-| 0.0034        | 2.81  | 135  | 0.0457          | 0.9902   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 1.2597        | 0.31  | 15   | 1.0370          | 0.7105   | 0.6143    | 0.7105 | 0.6481 |
+| 0.857         | 0.62  | 30   | 0.5686          | 0.9474   | 0.9565    | 0.9474 | 0.9468 |
+| 0.5836        | 0.94  | 45   | 0.3401          | 0.9737   | 0.9762    | 0.9737 | 0.9736 |
+| 0.317         | 1.25  | 60   | 0.2230          | 0.9737   | 0.9762    | 0.9737 | 0.9736 |
+| 0.2482        | 1.56  | 75   | 0.1819          | 0.9737   | 0.9762    | 0.9737 | 0.9736 |
+| 0.1655        | 1.88  | 90   | 0.1573          | 0.9737   | 0.9762    | 0.9737 | 0.9736 |
+| 0.0814        | 2.19  | 105  | 0.1175          | 0.9737   | 0.9762    | 0.9737 | 0.9736 |
+| 0.1098        | 2.5   | 120  | 0.1131          | 0.9737   | 0.9762    | 0.9737 | 0.9736 |
+| 0.0862        | 2.81  | 135  | 0.1237          | 0.9737   | 0.9762    | 0.9737 | 0.9736 |
 
 
 ### Framework versions

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:ce3d990347a3a3b76974b4a5ecff762ff7d74d6a31074464047477bddef4b140
-size 437964800
+oid sha256:97bc6eaa84364625f9a016297d4e47d705a9a4f10b0f4207ca4004a216b1895e
+size 267838720

runs/Jan16_10-40-30_745092e66db7/events.out.tfevents.1705401659.745092e66db7.965.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:305c1476400cd2b718d59e38ac5df69ad6421848568da2605212760470752134
+size 10387

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:dcb8880fed2ed269f7a447835df2416331cecaa81f998f2b9229b2b7340067bd
+oid sha256:6899d300faa8743b4a2db69a82f724ab41309451bbe52accba9e4002c63cb129
 size 4728