Training in progress epoch 0

README.md

@@ -15,10 +15,8 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: nan
-- Train Accuracy: 0.2234
-- Validation Loss: nan
-- Validation Accuracy: 0.2530
+- Train Loss: 0.2325
+- Validation Loss: 0.1100
 - Epoch: 0
 
 ## Model description
@@ -38,19 +36,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 4680, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
 - training_precision: float32
 
 ### Training results
 
-| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
-|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| nan        | 0.2234         | nan             | 0.2530              | 0     |
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 0.2325     | 0.1100          | 0     |
 
 
 ### Framework versions
 
 - Transformers 4.31.0
-- TensorFlow 2.13.0
+- TensorFlow 2.12.0
 - Datasets 2.14.0
 - Tokenizers 0.13.3

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a54be72b451fbd8e6a3701a17175a53ec7a4306e458109bf0da05e1bbf2223c6
+oid sha256:c86e58e798c90b6ba64c1403aad81e63cad6d1db3ea04619a125065a3817df49
 size 261004560