Upload TFDistilBertForQuestionAnswering

README.md

@@ -15,8 +15,8 @@ probably proofread and complete it, then remove this comment. -->
 
 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:
-- Train Loss: 0.6592
-- Epoch: 4
+- Train Loss: 0.2897
+- Epoch: 5
 
 ## Model description
 
@@ -35,18 +35,19 @@ 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': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 60, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- 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': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 186, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Epoch |
 |:----------:|:-----:|
-| 3.2451     | 0     |
-| 0.9100     | 1     |
-| 0.6492     | 2     |
-| 0.6482     | 3     |
-| 0.6592     | 4     |
+| 1.5140     | 0     |
+| 0.3420     | 1     |
+| 0.2925     | 2     |
+| 0.2936     | 3     |
+| 0.2972     | 4     |
+| 0.2897     | 5     |
 
 
 ### Framework versions
@@ -54,4 +55,4 @@ The following hyperparameters were used during training:
 - Transformers 4.35.2
 - TensorFlow 2.15.0
 - Datasets 2.16.1
-- Tokenizers 0.15.0
+- Tokenizers 0.15.1

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e21ad1e2e957a118554717f14dad2cc50dee6403c50a10079d76074f750c9f0
+oid sha256:c10c418e52b10f5e6328e6f7d3873041dc6c0b522c975097f2aa4f6efac9171f
 size 265583592