end

README.md

@@ -15,11 +15,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.6930
-- Train Accuracy: 0.4992
-- Validation Loss: 0.6942
-- Validation Accuracy: 0.5634
-- Epoch: 4
+- Train Loss: 0.0530
+- Train Accuracy: 0.9818
+- Validation Loss: 0.3083
+- Validation Accuracy: 0.8876
+- Epoch: 1
 
 ## Model description
 
@@ -38,18 +38,15 @@ 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': 5e-05, 'decay_steps': 400, 'end_learning_rate': 0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 16838, 'end_learning_rate': 0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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 |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 0.7052     | 0.4661         | 0.6890          | 0.5634              | 0     |
-| 0.6937     | 0.5323         | 0.7109          | 0.4366              | 1     |
-| 0.6962     | 0.4976         | 0.6910          | 0.5634              | 2     |
-| 0.6941     | 0.4929         | 0.6920          | 0.5634              | 3     |
-| 0.6930     | 0.4992         | 0.6942          | 0.5634              | 4     |
+| 0.1150     | 0.9609         | 0.3167          | 0.8888              | 0     |
+| 0.0530     | 0.9818         | 0.3083          | 0.8876              | 1     |
 
 
 ### Framework versions

config.json

@@ -10,13 +10,13 @@
   "finetuning_task": "sst-2",
   "hidden_dim": 3072,
   "id2label": {
-    "0": "not_entailment",
-    "1": "entailment"
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
   },
   "initializer_range": 0.02,
   "label2id": {
-    "entailment": "1",
-    "not_entailment": "0"
+    "NEGATIVE": 0,
+    "POSITIVE": 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:b23875741c9694e4e7daea095671c6415e9a351b7ce87bf23de424eabf9a648d
-size 267951808
+oid sha256:1f651b5961a1b91f59b5fde3325c19c84d85f13fa455c6ae84e4b857514e247c
+size 267955144