Training in progress epoch 0

README.md

@@ -15,13 +15,13 @@ 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: 1.4037
-- Train End Logits Accuracy: 0.6311
-- Train Start Logits Accuracy: 0.6080
-- Validation Loss: 1.5702
-- Validation End Logits Accuracy: 0.5961
-- Validation Start Logits Accuracy: 0.5822
-- Epoch: 1
+- Train Loss: 2.6112
+- Train End Logits Accuracy: 0.3765
+- Train Start Logits Accuracy: 0.3608
+- Validation Loss: 1.7039
+- Validation End Logits Accuracy: 0.5682
+- Validation Start Logits Accuracy: 0.5274
+- Epoch: 0
 
 ## Model description
 
@@ -40,15 +40,14 @@ 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': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1112, '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': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1112, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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 End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
 |:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
-| 2.6794     | 0.3520                    | 0.3436                      | 1.6794          | 0.5794                         | 0.5645                           | 0     |
-| 1.4037     | 0.6311                    | 0.6080                      | 1.5702          | 0.5961                         | 0.5822                           | 1     |
+| 2.6112     | 0.3765                    | 0.3608                      | 1.7039          | 0.5682                         | 0.5274                           | 0     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1705315795.9f1809461959.495.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77238219a0790cf5194382c4b0579c8f495ee86b28ce26c6417ff550b1678207
+size 1205493

logs/validation/events.out.tfevents.1705316157.9f1809461959.495.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e5aa636fdea8d564fb2bde2a057d57fab84648ae2f13ab493ab81e04dd5f1b8
+size 604

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1566e8c1ee00899ca983a455e1c808477fcf23dfc01c8c97a3cdc7837a5550a
+oid sha256:df6912782e17bc44d6bc3c9a3424d24eee0cad1ebd13ffc5a11b874693ce095f
 size 265583592