End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: distilbert-base-cased
+base_model: bert-base-cased
 tags:
 - generated_from_trainer
 metrics:
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # DIALOGUE_second_model
 
-This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset.
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3499
+- Loss: 0.3364
 - Precision: 0.9762
 - Recall: 0.9737
 - F1: 0.9736
@@ -55,20 +55,20 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 1.3735        | 0.31  | 15   | 1.3341          | 0.2562    | 0.4868 | 0.3323 | 0.4868   |
-| 1.2891        | 0.62  | 30   | 1.1793          | 0.8546    | 0.7368 | 0.6683 | 0.7368   |
-| 1.1           | 0.94  | 45   | 0.9372          | 0.9421    | 0.9342 | 0.9339 | 0.9342   |
-| 0.884         | 1.25  | 60   | 0.7268          | 0.9524    | 0.9474 | 0.9472 | 0.9474   |
-| 0.7087        | 1.56  | 75   | 0.5780          | 0.9762    | 0.9737 | 0.9736 | 0.9737   |
-| 0.6158        | 1.88  | 90   | 0.4773          | 0.9327    | 0.9211 | 0.9204 | 0.9211   |
-| 0.5052        | 2.19  | 105  | 0.4043          | 0.9762    | 0.9737 | 0.9736 | 0.9737   |
-| 0.4321        | 2.5   | 120  | 0.3652          | 0.9762    | 0.9737 | 0.9736 | 0.9737   |
-| 0.4412        | 2.81  | 135  | 0.3499          | 0.9762    | 0.9737 | 0.9736 | 0.9737   |
+| 1.3667        | 0.31  | 15   | 1.2505          | 0.2468    | 0.4868 | 0.3263 | 0.4868   |
+| 1.1649        | 0.62  | 30   | 1.0587          | 0.8659    | 0.7105 | 0.6935 | 0.7105   |
+| 1.0288        | 0.94  | 45   | 0.8905          | 0.9479    | 0.9342 | 0.9331 | 0.9342   |
+| 0.8541        | 1.25  | 60   | 0.7069          | 0.9762    | 0.9737 | 0.9736 | 0.9737   |
+| 0.6833        | 1.56  | 75   | 0.5616          | 0.9762    | 0.9737 | 0.9736 | 0.9737   |
+| 0.6072        | 1.88  | 90   | 0.4586          | 0.9762    | 0.9737 | 0.9736 | 0.9737   |
+| 0.4665        | 2.19  | 105  | 0.3944          | 0.9762    | 0.9737 | 0.9736 | 0.9737   |
+| 0.4274        | 2.5   | 120  | 0.3563          | 0.9762    | 0.9737 | 0.9736 | 0.9737   |
+| 0.4116        | 2.81  | 135  | 0.3364          | 0.9762    | 0.9737 | 0.9736 | 0.9737   |
 
 
 ### Framework versions
 
-- Transformers 4.36.2
+- Transformers 4.37.0
 - Pytorch 2.1.0+cu121
 - Datasets 2.16.1
 - Tokenizers 0.15.0

config.json

@@ -1,13 +1,14 @@
 {
-  "_name_or_path": "distilbert-base-cased",
-  "activation": "gelu",
+  "_name_or_path": "bert-base-cased",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "Hospital-Inform",
     "1": "Hospital-Request",
@@ -15,24 +16,24 @@
     "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": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "output_past": true,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "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",
+  "transformers_version": "4.37.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
   "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b804e2243b4315b37da4d96fb3ee9fe45c4445c1d3abb76a5685cbfee97c019
-size 263150840
+oid sha256:e4f2d81d6dfc25bb604e7bcd79acfaaf4d0aa9ca6609bad023110eaf142970c0
+size 433276920

runs/Jan23_14-28-05_b3ba10920348/events.out.tfevents.1706020108.b3ba10920348.178.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc73325b6b00bb5ebdc1b100b13de86ada85903007a41214e5f812512e6f9278
+size 10490

tokenizer_config.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:684b5c2816d28e5ce76d89aaf4cae488ad92b4164297b5eeaedc967d202fde47
-size 4728
+oid sha256:2e857c7c1121cf0c85367fdeef55d7d66fc8e32b927d83827544ee483bf7c529
+size 4664