Training in progress epoch 0

README.md

@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.1170
-- Validation Loss: 0.5729
-- Train Accuracy: 0.8787
-- Epoch: 3
+- Train Loss: 3.5609
+- Validation Loss: 1.7191
+- Train Accuracy: 0.8982
+- Epoch: 0
 
 ## Model description
 
@@ -37,17 +37,14 @@ 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 14060, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, '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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 4424, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 2.8380     | 1.2684          | 0.8444         | 0     |
-| 0.6195     | 0.6499          | 0.8764         | 1     |
-| 0.2150     | 0.5704          | 0.8849         | 2     |
-| 0.1170     | 0.5729          | 0.8787         | 3     |
+| 3.5609     | 1.7191          | 0.8982         | 0     |
 
 
 ### Framework versions

config.json

@@ -5,7 +5,7 @@
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
-  "classifier_dropout": 0.2,
+  "classifier_dropout": 0.4,
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f83dcc997321be6ce653c33c8816fe1baf025e31818b40a1790a92d7f86f24b0
+oid sha256:d081e55bf3a98cb26171589295d2bcbbd63824460861c53116ae2fdcb207e0b2
 size 499332928