Training in progress epoch 0

README.md

@@ -15,11 +15,11 @@ 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: 0.1332
-- Validation Loss: 0.8350
-- Train Accuracy: 0.7975
-- Train F1: 0.8249
-- Epoch: 5
+- Train Loss: 2.0102
+- Validation Loss: 1.8738
+- Train Accuracy: 0.3011
+- Train F1: 0.0518
+- Epoch: 0
 
 ## Model description
 
@@ -38,19 +38,14 @@ 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': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 13248, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 120, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, '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': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-06, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-06, 'decay_steps': 8812, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 100, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Train Accuracy | Train F1 | Epoch |
 |:----------:|:---------------:|:--------------:|:--------:|:-----:|
-| 1.5262     | 0.8842          | 0.7330         | 0.7218   | 0     |
-| 0.7051     | 0.7528          | 0.7599         | 0.7698   | 1     |
-| 0.4812     | 0.6969          | 0.7921         | 0.8120   | 2     |
-| 0.3259     | 0.6595          | 0.7939         | 0.8153   | 3     |
-| 0.2134     | 0.7854          | 0.7867         | 0.8077   | 4     |
-| 0.1332     | 0.8350          | 0.7975         | 0.8249   | 5     |
+| 2.0102     | 1.8738          | 0.3011         | 0.0518   | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3531b5d6136d7d03b78b53f146229bb08623b1b7118d36c9389184e0221f902b
-size 267976648
+oid sha256:9fa38d90f40abe32fda4a697ebc16b8cce35eb96b65e3269cc6f0ba9323ccdc2
+size 267973312