Upload TFBartForConditionalGeneration

README.md

@@ -14,8 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [philschmid/tf-distilbart-cnn-12-6](https://huggingface.co/philschmid/tf-distilbart-cnn-12-6) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0884
-- Epoch: 9
+- Train Loss: 0.1445
+- Validation Loss: 0.4524
+- Epoch: 4
 
 ## Model description
 
@@ -34,23 +35,18 @@ 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': 5e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
-| Train Loss | Epoch |
-|:----------:|:-----:|
-| 1.1636     | 0     |
-| 0.4195     | 1     |
-| 0.2564     | 2     |
-| 0.1826     | 3     |
-| 0.1501     | 4     |
-| 0.1312     | 5     |
-| 0.1404     | 6     |
-| 0.0992     | 7     |
-| 0.0944     | 8     |
-| 0.0884     | 9     |
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 0.7265     | 0.4665          | 0     |
+| 0.3192     | 0.4480          | 1     |
+| 0.2154     | 0.4395          | 2     |
+| 0.1587     | 0.4668          | 3     |
+| 0.1445     | 0.4524          | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4ff5ee2f5a70abf790eae374bde3dd18bd2efbbaa15664d9f44f11770d0f66f
+oid sha256:1e74ca0f5295c41851706ea75d0650303b7eefa26be6b96e922ff8092cdcdd05
 size 1222622640