Upload TFDistilBertForSequenceClassification

README.md

@@ -16,9 +16,9 @@ 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: 0.1058
-- Validation Loss: 0.0557
-- Train Accuracy: 0.988
+- Train Loss: 0.1103
+- Validation Loss: 0.0741
+- Train Accuracy: 0.978
 - Epoch: 2
 
 ## Model description
@@ -38,21 +38,21 @@ 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': 625, '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': 375, '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 |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.4628     | 0.2186          | 0.926          | 0     |
-| 0.2093     | 0.0990          | 0.974          | 1     |
-| 0.1058     | 0.0557          | 0.988          | 2     |
+| 0.4268     | 0.1951          | 0.928          | 0     |
+| 0.1921     | 0.1166          | 0.964          | 1     |
+| 0.1103     | 0.0741          | 0.978          | 2     |
 
 
 ### Framework versions
 
-- Transformers 4.48.3
+- Transformers 4.51.3
 - TensorFlow 2.18.0
-- Datasets 3.4.1
+- Datasets 3.5.1
 - Tokenizers 0.21.1

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"
@@ -26,6 +25,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "transformers_version": "4.48.3",
+  "transformers_version": "4.51.3",
   "vocab_size": 30522
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b302d08e59559beb41da01b1a057e6a9a4e3589871ad44d2d5eeb9e6b5089f
-size 267951808
+oid sha256:d6c66b4e52dfb34629e5072d089182404dfa7586ab4dee43a3c6c15d72849a5c
+size 267955144