End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: bert-base-uncased
+base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
 model-index:
@@ -13,13 +13,16 @@ should probably proofread and complete it, then remove this comment. -->
 
 # DIALOGUE_second_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: 0.0993
+- eval_loss: 0.1403
 - eval_accuracy: 0.9737
-- eval_runtime: 0.7905
-- eval_samples_per_second: 96.139
-- eval_steps_per_second: 12.65
+- eval_precision: 0.9762
+- eval_recall: 0.9737
+- eval_f1: 0.9736
+- eval_runtime: 0.311
+- eval_samples_per_second: 244.401
+- eval_steps_per_second: 32.158
 - epoch: 2.5
 - step: 120
 

config.json

@@ -1,14 +1,13 @@
 {
-  "_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": "Hospital-Inform",
     "1": "Hospital-Request",
@@ -16,24 +15,23 @@
     "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 sha256:6f2838a205d53b7548429ae4b402e8a1ef907a0bbcac914cf907fd072aae5d0c
-size 437964800
+oid sha256:020ceb60207a3751f91777bfeea9fa6550a58a96d4b12e2b5742710207946a4f
+size 267838720

runs/Jan16_08-15-40_c40909a81e72/events.out.tfevents.1705392945.c40909a81e72.357.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ce3752cacb6bb2abfdc9f2a46ffe31336fea2b36b5bbdcc26bc40c279e16e8
+size 8794

runs/Jan16_08-16-13_c40909a81e72/events.out.tfevents.1705392977.c40909a81e72.357.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cd267eec44e670c8808bbc8b00a4c4e0e87d193bd7423e015efd7326558077a
+size 6943

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 sha256:07ed8fd2d021f8e28d50d81fb5dedfbf9421d9e9bd75e11e89d04d0e022e3998
-size 4664
+oid sha256:8c154c4a903115b051293c3b3d0a7c2670a012e5b737ddd09f10adf5be7d5376
+size 4728