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 [camembert-base](https://huggingface.co/camembert-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0542
-- Train Accuracy: 0.9844
-- Validation Loss: 0.5073
-- Validation Accuracy: 0.8436
-- Epoch: 4
+- Train Loss: 0.5259
+- Train Accuracy: 0.7349
+- Validation Loss: 0.4369
+- Validation Accuracy: 0.8017
+- Epoch: 0
 
 ## Model description
 
@@ -37,23 +37,19 @@ 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': 1005, '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': 2838, '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 |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 0.4753     | 0.7890         | 0.3616          | 0.8547              | 0     |
-| 0.3120     | 0.8799         | 0.3702          | 0.8492              | 1     |
-| 0.1824     | 0.9340         | 0.3928          | 0.8547              | 2     |
-| 0.0972     | 0.9714         | 0.4849          | 0.8436              | 3     |
-| 0.0542     | 0.9844         | 0.5073          | 0.8436              | 4     |
+| 0.5259     | 0.7349         | 0.4369          | 0.8017              | 0     |
 
 
 ### Framework versions
 
 - Transformers 4.26.1
 - TensorFlow 2.11.0
-- Datasets 2.9.0
+- Datasets 2.10.1
 - Tokenizers 0.13.2

logs/train/events.out.tfevents.1678826736.f95d79dc82d3.2369.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf01391fb9d34355560e01da437cdb6ca43fe6bfa00f5f2ffa65c6d1e8928ad5
+size 3918412

logs/validation/events.out.tfevents.1678826975.f95d79dc82d3.2369.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ea5415ff7b836785fd6013768f774a56a411b9a8ca4cce431ba6c7e43b02304
+size 356

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0004c1fccae98e3743f05ed8490df31d3d7c0688279683c08e98c0e662373d69
+oid sha256:c19b3967ecf2321f8f5936131ef33a3e95516e1b362e7539cb8e8b4f4d121617
 size 442783616