Training in progress epoch 0

README.md

@@ -14,11 +14,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0736
-- Train Accuracy: 0.9581
-- Validation Loss: 0.1314
-- Validation Accuracy: 0.9410
-- Epoch: 7
+- Train Loss: 0.9485
+- Train Accuracy: 0.5543
+- Validation Loss: 0.8404
+- Validation Accuracy: 0.6870
+- Epoch: 0
 
 ## Model description
 
@@ -37,21 +37,14 @@ 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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 2000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, '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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 1250, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 0.2239     | 0.9102         | 0.2466          | 0.9250              | 0     |
-| 0.1442     | 0.9341         | 0.1783          | 0.9270              | 1     |
-| 0.1133     | 0.9440         | 0.1496          | 0.9360              | 2     |
-| 0.0986     | 0.9479         | 0.1336          | 0.9380              | 3     |
-| 0.0867     | 0.9510         | 0.1378          | 0.9360              | 4     |
-| 0.0782     | 0.9566         | 0.1314          | 0.9410              | 5     |
-| 0.0746     | 0.9581         | 0.1314          | 0.9410              | 6     |
-| 0.0736     | 0.9581         | 0.1314          | 0.9410              | 7     |
+| 0.9485     | 0.5543         | 0.8404          | 0.6870              | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9d69b2cfebd393bac06d9be1f25a73fd61bbe1e01fb0348d452e2ee7b54c501
+oid sha256:e755a7cc57d4cf9b09ca24a780ef895a96c7162b26c0090056583f71fa8af0a8
 size 133754512