Model save

README.md

@@ -1,5 +1,6 @@
 ---
-license: mit
+library_name: transformers
+license: apache-2.0
 base_model: google-bert/bert-base-uncased
 tags:
 - generated_from_trainer
@@ -17,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6811
-- F1: 0.8046
+- Loss: 0.7055
+- F1: 0.7980
 
 ## Model description
 
@@ -37,27 +38,30 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- learning_rate: 1e-05
+- train_batch_size: 64
+- eval_batch_size: 64
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 600
-- num_epochs: 3.0
+- num_epochs: 5.0
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 1.5106        | 1.0   | 942  | 0.8143          | 0.7668 |
-| 0.7033        | 2.0   | 1884 | 0.6980          | 0.7985 |
-| 0.511         | 3.0   | 2826 | 0.6811          | 0.8046 |
+| 2.2299        | 1.0   | 538  | 1.0520          | 0.7118 |
+| 0.9383        | 2.0   | 1076 | 0.7800          | 0.7794 |
+| 0.7379        | 3.0   | 1614 | 0.7253          | 0.7947 |
+| 0.6362        | 4.0   | 2152 | 0.7107          | 0.7965 |
+| 0.5779        | 5.0   | 2690 | 0.7055          | 0.7980 |
 
 
 ### Framework versions
 
-- Transformers 4.42.4
-- Pytorch 2.3.1+cu121
-- Datasets 2.20.0
-- Tokenizers 0.19.1
+- Transformers 4.49.0.dev0
+- Pytorch 2.1.2.post304
+- Datasets 3.2.0
+- Tokenizers 0.21.0