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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.5161
-- Validation Loss: 0.5053
+- Train Loss: 0.6748
+- Validation Loss: 0.6426
 - Train Accuracy: 0.6692
-- Epoch: 10
+- Epoch: 0
 
 ## Model description
 
@@ -36,24 +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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 40, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 80, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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 |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.6577     | 0.6166          | 0.6692         | 0     |
-| 0.6098     | 0.5816          | 0.6692         | 1     |
-| 0.5679     | 0.5477          | 0.6692         | 2     |
-| 0.5500     | 0.5217          | 0.6692         | 3     |
-| 0.5239     | 0.5053          | 0.6692         | 4     |
-| 0.5178     | 0.5053          | 0.6692         | 5     |
-| 0.5196     | 0.5053          | 0.6692         | 6     |
-| 0.5152     | 0.5053          | 0.6692         | 7     |
-| 0.5142     | 0.5053          | 0.6692         | 8     |
-| 0.5189     | 0.5053          | 0.6692         | 9     |
-| 0.5161     | 0.5053          | 0.6692         | 10    |
+| 0.6748     | 0.6426          | 0.6692         | 0     |
 
 
 ### Framework versions

config.json

@@ -10,12 +10,12 @@
   "hidden_dim": 3072,
   "id2label": {
     "0": "CRITICISM",
-    "1": "NOT"
+    "1": "OTHER"
   },
   "initializer_range": 0.02,
   "label2id": {
     "CRITICISM": 0,
-    "NOT": 1
+    "OTHER": 1
   },
   "max_position_embeddings": 512,
   "model_type": "distilbert",

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e76516a6e5ad684b88b038fb448c5120d6d80612c39a2fa62a681e5ff49659e
+oid sha256:f5ad5a276341eb21c409db041dd9de4f652d0b3fe5a476598e3963f533c0b489
 size 267951808