ft_bert_base_cased

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.593
+      value: 0.583
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the yelp_review_full dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2113
-- Accuracy: 0.593
+- Loss: 0.9880
+- Accuracy: 0.583
 
 ## Model description
 
@@ -53,20 +53,19 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 125  | 1.0822          | 0.568    |
-| No log        | 2.0   | 250  | 1.0701          | 0.595    |
-| No log        | 3.0   | 375  | 1.2113          | 0.593    |
+| No log        | 1.0   | 63   | 1.2632          | 0.459    |
+| No log        | 2.0   | 126  | 0.9880          | 0.583    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67507328fc97acea4f20df31503c292a33d807fe6cfb754d7020f42c7dede8b7
+oid sha256:38872ac0559838392c909cd2975d379a877b7f6ed7a6e617c317abc60480c8c1
 size 433279996

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c8c6fc060b6c928c667479da1378bb30625e67fd5bf08a9679d7772adaa2318
+oid sha256:06e73ceeb93dca53d439e7b74eb476ccb08f10adcf01056f25a029b286187568
 size 4155