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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.0497
-- Validation Loss: 1.0375
-- Train Accuracy: 0.6875
-- Epoch: 3
+- Train Loss: 0.6915
+- Validation Loss: 0.6930
+- Train Accuracy: 0.7333
+- Epoch: 0
 
 ## Model description
 
@@ -37,22 +37,19 @@ 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': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0001, 'decay_steps': 25, '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': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0001, 'decay_steps': 20, '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 |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 1.0993     | 1.0980          | 0.4375         | 0     |
-| 1.1013     | 1.0968          | 0.375          | 1     |
-| 1.0860     | 1.0894          | 0.625          | 2     |
-| 1.0497     | 1.0375          | 0.6875         | 3     |
+| 0.6915     | 0.6930          | 0.7333         | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
+- Transformers 4.37.2
 - TensorFlow 2.15.0
-- Datasets 2.17.0
+- Datasets 2.17.1
 - Tokenizers 0.15.2

config.json

@@ -18,6 +18,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.37.2",
   "vocab_size": 30522
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55b26434a79e3959207d5829a7fda0272a83f0e362a0bcf4103304eb2512382e
+oid sha256:f0ac3699d54a0e01098156ee86771431e4f677918348e4a56dc261986266c7f0
 size 267948736