Upload TFDistilBertForSequenceClassification

README.md

@@ -15,8 +15,8 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [thomasavare/distilbert-ft-test3](https://huggingface.co/thomasavare/distilbert-ft-test3) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.4653
-- Train Accuracy: 0.6860
+- Train Loss: 1.2268
+- Train Accuracy: 0.7180
 - Epoch: 2
 
 ## Model description
@@ -36,16 +36,16 @@ 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': 1e-05, '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': True, 'is_legacy_optimizer': False, 'learning_rate': 5e-07, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Train Accuracy | Epoch |
 |:----------:|:--------------:|:-----:|
-| 2.8597     | 0.5860         | 0     |
-| 1.7989     | 0.6440         | 1     |
-| 1.4653     | 0.6860         | 2     |
+| 1.2639     | 0.7020         | 0     |
+| 1.2616     | 0.6940         | 1     |
+| 1.2268     | 0.7180         | 2     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aacd065962fba25c1018acab42c2ca5ea6d11b66a26c955efb6aed600203eede
+oid sha256:8d0b4ae8ae838ed3dac54ff86d5d3564c62b77c1ae45a9ee6d0873a6281dea95
 size 268102600