Training in progress epoch 0

README.md

@@ -14,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [almanach/camembert-bio-base](https://huggingface.co/almanach/camembert-bio-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.4020
+- Train Loss: 1.3892
 - Validation Loss: 1.3863
-- Train Accuracy: 0.2378
-- Epoch: 5
+- Train Accuracy: 0.2805
+- Epoch: 0
 
 ## Model description
 
@@ -36,19 +36,14 @@ 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': 0.001, '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': 0.0002, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 1.3939     | 1.3863          | 0.2195         | 0     |
-| 1.3959     | 1.3863          | 0.1646         | 1     |
-| 1.3884     | 1.3863          | 0.2195         | 2     |
-| 1.3859     | 1.3863          | 0.2561         | 3     |
-| 1.4083     | 1.3863          | 0.1951         | 4     |
-| 1.4020     | 1.3863          | 0.2378         | 5     |
+| 1.3892     | 1.3863          | 0.2805         | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f98670ae361b777b2d34114d09c4ff446d184a16710d83acb8aa032d93b462a
+oid sha256:cf3e9fda91aa4f6095e5ff9bdfe6eeee3674471ba970d16789a33fbc09e988ea
 size 442780888