Training in progress epoch 8

README.md

@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.9746
-- Validation Loss: 3.3838
-- Epoch: 6
+- Train Loss: 2.8652
+- Validation Loss: 3.3984
+- Epoch: 8
 
 ## Model description
 
@@ -36,7 +36,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adafactor', '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': 6e-05, 'beta_2_decay': -0.8, 'epsilon_1': 1e-30, 'epsilon_2': 0.001, 'clip_threshold': 1.0, 'relative_step': True}
+- optimizer: {'name': 'Adafactor', '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': 6e-06, 'beta_2_decay': -0.8, 'epsilon_1': 1e-30, 'epsilon_2': 0.001, 'clip_threshold': 1.0, 'relative_step': True}
 - training_precision: mixed_float16
 
 ### Training results
@@ -50,6 +50,8 @@ The following hyperparameters were used during training:
 | 3.1830     | 3.3616          | 4     |
 | 3.0837     | 3.3737          | 5     |
 | 2.9746     | 3.3838          | 6     |
+| 2.8861     | 3.3932          | 7     |
+| 2.8652     | 3.3984          | 8     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06c344c8f1964f0edd417945dad54c301605d5e98c99c8d48192cd38861cca9e
+oid sha256:34ca0abe7efd0d3a2d893d7e1de8c9c0b201144cd607927724dca90f31cc2c9f
 size 1625921312