bert-base-uncased finetune 3 epoch

README.md

@@ -1,8 +1,10 @@
 ---
 license: apache-2.0
-base_model: bert-base-uncased
+base_model: zhuchi76/bert-finetuned-sst2
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: bert-finetuned-sst2
   results: []
@@ -13,7 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-finetuned-sst2
 
-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 [zhuchi76/bert-finetuned-sst2](https://huggingface.co/zhuchi76/bert-finetuned-sst2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4948
+- Accuracy: 0.77
 
 ## Model description
 
@@ -40,6 +45,15 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 3.0
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 13   | 0.6412          | 0.57     |
+| No log        | 2.0   | 26   | 0.5484          | 0.76     |
+| No log        | 3.0   | 39   | 0.4948          | 0.77     |
+
+
 ### Framework versions
 
 - Transformers 4.38.2

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "zhuchi76/bert-finetuned-sst2",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -18,6 +18,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
   "type_vocab_size": 2,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c2bcc9c784b1eeef67b868b192e218a837e399f6fa8e404bf6af7c7a003f377
+oid sha256:d68ad8898308ab35cd494482447172df0d09fcec03ed0f09b3d6a17cc375aeae
 size 437958648

runs/Mar22_18-30-48_arg10/events.out.tfevents.1711103458.arg10.654.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ac688a3ec2b164a8f900479d45c26d40e5a67231aa64ee2041a8f0d5c96b7a7
-size 5990
+oid sha256:58d4678254f63679b764d36323671c47e265ba654a0619d016c79dc64ef53a0d
+size 129

runs/Mar22_18-30-48_arg10/events.out.tfevents.1711103540.arg10.654.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58dda2bcd4e52bef692da44a38ff6959a906214911f87028e6f261373438cb32
-size 6081
+oid sha256:80c9743a041fb1ea907b0d1ae5e141381b1514d7d60c6e916104283698a09eed
+size 129

runs/Mar22_18-45-31_arg10/events.out.tfevents.1711104337.arg10.654.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2da386250ed2b9442e78dea5a5e7544509b52e06a2e37061a1446673cbeb0feb
-size 6114
+oid sha256:1e4ddf3b9a348a4e28e24518215ac7cb8904d733d22bea8778d2624e3321897c
+size 129

runs/Mar22_18-46-25_arg10/events.out.tfevents.1711104401.arg10.654.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e98f211c241fe9fd434716b28bcfb7da0c55a82a5bb81947ba9a3f766d3df64
-size 6023
+oid sha256:807eaa0d067a681b68e9f41caedf616845a833a4431ad1de5c0ef701e93230c8
+size 129

runs/Mar23_16-51-42_arg10/events.out.tfevents.1711183904.arg10.44500.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dc5aea3910632490dd4ffd4dba7a8ed1bb45e85a795a51aae9b800d0558873d
-size 6023
+oid sha256:a7b0aea8ceb97d24ef7920fcd876fdfaf0f7a3bf60cbc4a9292c1a1ce971a1c9
+size 129

runs/Mar23_17-08-45_arg10/events.out.tfevents.1711184931.arg10.44500.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df6470d8936a7b8da54244103aa202bce0a88fb45a54bd0c34aff7ea83fa12ac
-size 6081
+oid sha256:0e7c82ee0b4ad4d5aa4f921428f1b341222d9a7397877ff82445eb94c667fe11
+size 129

runs/Mar23_18-37-39_arg10/events.out.tfevents.1711190262.arg10.48308.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c00b091165bcd81cf79c29e8bc5c588794962526db118c86e3c6ef316e8bd501
+size 5908

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef90cb7dbb00bc46d099462ce14848784860114f9dfc35a4dd57683c84a4b940
+oid sha256:bb1ab82f8e222852fe47687e5a738a4f6b4ab5cebec0f0fdb3fbef2290b4f9f1
 size 4920