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
 metrics:
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # training-1
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0188
-- Accuracy: 0.9957
-- Precision: 0.9979
-- Recall: 0.9936
-- F1: 0.9957
+- Loss: 0.0292
+- Accuracy: 0.9940
+- Precision: 0.9982
+- Recall: 0.9893
+- F1: 0.9937
 
 ## Model description
 
@@ -43,9 +43,9 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -55,11 +55,25 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| No log        | 0.99  | 175  | 0.0323          | 0.9925   | 1.0       | 0.9850 | 0.9925 |
-| 0.1307        | 1.99  | 350  | 0.0291          | 0.9936   | 1.0       | 0.9872 | 0.9935 |
-| 0.0299        | 2.98  | 525  | 0.0201          | 0.9957   | 0.9979    | 0.9936 | 0.9957 |
-| 0.024         | 3.98  | 700  | 0.0188          | 0.9957   | 0.9979    | 0.9936 | 0.9957 |
-| 0.0183        | 4.97  | 875  | 0.0188          | 0.9957   | 0.9979    | 0.9936 | 0.9957 |
+| No log        | 0.25  | 85   | 0.0345          | 0.9931   | 0.9982    | 0.9875 | 0.9928 |
+| No log        | 0.5   | 170  | 0.0428          | 0.9905   | 1.0       | 0.9804 | 0.9901 |
+| No log        | 0.75  | 255  | 0.0295          | 0.9940   | 0.9982    | 0.9893 | 0.9937 |
+| 0.0811        | 1.0   | 340  | 0.0237          | 0.9957   | 1.0       | 0.9911 | 0.9955 |
+| 0.0811        | 1.25  | 425  | 0.0618          | 0.9897   | 1.0       | 0.9786 | 0.9892 |
+| 0.0811        | 1.5   | 510  | 0.0338          | 0.9940   | 1.0       | 0.9875 | 0.9937 |
+| 0.0811        | 1.76  | 595  | 0.0373          | 0.9931   | 1.0       | 0.9857 | 0.9928 |
+| 0.0267        | 2.01  | 680  | 0.0382          | 0.9923   | 0.9982    | 0.9857 | 0.9919 |
+| 0.0267        | 2.26  | 765  | 0.0271          | 0.9948   | 1.0       | 0.9893 | 0.9946 |
+| 0.0267        | 2.51  | 850  | 0.0355          | 0.9940   | 1.0       | 0.9875 | 0.9937 |
+| 0.0267        | 2.76  | 935  | 0.0397          | 0.9940   | 1.0       | 0.9875 | 0.9937 |
+| 0.0187        | 3.01  | 1020 | 0.0270          | 0.9940   | 0.9982    | 0.9893 | 0.9937 |
+| 0.0187        | 3.26  | 1105 | 0.0246          | 0.9948   | 0.9982    | 0.9911 | 0.9946 |
+| 0.0187        | 3.51  | 1190 | 0.0340          | 0.9940   | 1.0       | 0.9875 | 0.9937 |
+| 0.0187        | 3.76  | 1275 | 0.0242          | 0.9957   | 1.0       | 0.9911 | 0.9955 |
+| 0.0093        | 4.01  | 1360 | 0.0224          | 0.9948   | 0.9982    | 0.9911 | 0.9946 |
+| 0.0093        | 4.26  | 1445 | 0.0275          | 0.9940   | 0.9982    | 0.9893 | 0.9937 |
+| 0.0093        | 4.51  | 1530 | 0.0285          | 0.9940   | 0.9982    | 0.9893 | 0.9937 |
+| 0.0093        | 4.76  | 1615 | 0.0292          | 0.9940   | 0.9982    | 0.9893 | 0.9937 |
 
 
 ### Framework versions

config.json

@@ -1,27 +1,25 @@
 {
-  "_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,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "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": "4.33.1",
-  "type_vocab_size": 2,
-  "use_cache": true,
   "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43d4a406737e3075bd00408e59822a99d9c784d163df09c314bd5bcd1b39a6f6
-size 438003950
+oid sha256:7acd063f486d2307b8db8225437c8fba5d71f6c8b7dc261b5ffad01be0373b61
+size 267855978

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4f2bf76be559a9f4817c4ba074097d33e500a4c024e88e150b3cbc4d18010b1
+oid sha256:6805874f93e682a9cec9dc0ea8f1e836bb07d9630cff35857cf4f9d1163e2f2d
 size 4472