Training in progress epoch 0

README.md

@@ -15,9 +15,9 @@ 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: 0.0027
-- Validation Loss: 0.0167
-- Epoch: 4
+- Train Loss: 0.2034
+- Validation Loss: 0.0864
+- Epoch: 0
 
 ## Model description
 
@@ -36,23 +36,19 @@ 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': 2e-05, 'decay_steps': 1390, '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': 2e-05, 'decay_steps': 1410, '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 | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.0938     | 0.0264          | 0     |
-| 0.0221     | 0.0245          | 1     |
-| 0.0122     | 0.0168          | 2     |
-| 0.0053     | 0.0166          | 3     |
-| 0.0027     | 0.0167          | 4     |
+| 0.2034     | 0.0864          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.42.3
+- Transformers 4.44.0
 - TensorFlow 2.16.2
 - Datasets 2.20.0
 - Tokenizers 0.19.1

config.json

@@ -9,13 +9,13 @@
   "dropout": 0.1,
   "hidden_dim": 3072,
   "id2label": {
-    "0": "NEGATIVE",
-    "1": "POSITIVE"
+    "0": "POSITIVE",
+    "1": "NEGATIVE"
   },
   "initializer_range": 0.02,
   "label2id": {
-    "NEGATIVE": 0,
-    "POSITIVE": 1
+    "NEGATIVE": 1,
+    "POSITIVE": 0
   },
   "max_position_embeddings": 512,
   "model_type": "distilbert",
@@ -26,6 +26,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "transformers_version": "4.42.3",
+  "transformers_version": "4.44.0",
   "vocab_size": 30522
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f6aac51d6aa7c7fe5c2f2f43889efd5123cb91750f5656252370a16d10a99c8
-size 267955144
+oid sha256:9ca9d2f5d87bed2f9ea6517ae6eddbbd4424c4f8c7734d0bf8f8c76e761a9b50
+size 267951808