Upload TFFlaubertForSequenceClassification

README.md

@@ -1,6 +1,4 @@
 ---
-license: mit
-base_model: flaubert/flaubert_base_cased
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,12 +11,9 @@ probably proofread and complete it, then remove this comment. -->
 
 # complexity_80_model
 
-This model is a fine-tuned version of [flaubert/flaubert_base_cased](https://huggingface.co/flaubert/flaubert_base_cased) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.1458
-- Validation Loss: 0.1550
-- Train Accuracy: 0.9328
-- Epoch: 2
+
 
 ## Model description
 
@@ -37,16 +32,11 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 196040, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- optimizer: None
 - training_precision: float32
 
 ### Training results
 
-| Train Loss | Validation Loss | Train Accuracy | Epoch |
-|:----------:|:---------------:|:--------------:|:-----:|
-| 0.1899     | 0.1728          | 0.9235         | 0     |
-| 0.1619     | 0.1627          | 0.9315         | 1     |
-| 0.1458     | 0.1550          | 0.9328         | 2     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "flaubert/flaubert_base_cased",
+  "_name_or_path": "complexity_80_model",
   "amp": 1,
   "architectures": [
     "FlaubertForSequenceClassification"