Training in progress epoch 0

README.md

@@ -13,9 +13,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 5.6501
-- Validation Loss: 5.9263
-- Epoch: 3
+- Train Loss: 8.0106
+- Validation Loss: 8.1104
+- Epoch: 0
 
 ## Model description
 
@@ -34,17 +34,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 0.0006, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0006, 'decay_steps': 28440, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 700, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
+- optimizer: {'inner_optimizer': {'class_name': 'Addons>AdamW', 'config': {'name': 'AdamW', 'learning_rate': {'class_name': 'ExponentialDecay', 'config': {'initial_learning_rate': 0.0005, 'decay_steps': 100000, 'decay_rate': 0.96, 'staircase': True, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay': 0.01, 'exclude_from_weight_decay': None}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
 - training_precision: mixed_float16
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 6.9370     | 6.3016          | 0     |
-| 6.1151     | 6.0404          | 1     |
-| 5.8246     | 5.9557          | 2     |
-| 5.6501     | 5.9263          | 3     |
+| 8.0106     | 8.1104          | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36f9dc692d32736d9fc66e39124c98eb31296940616cdcf9573534851c4d6110
+oid sha256:41582e56a407b1d4a0a6d75eb1b83cd5b9f706423ead1f57a2458716533a8ea5
 size 451065960