Training in progress epoch 0

README.md

@@ -15,13 +15,13 @@ 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: 0.2967
-- Validation Loss: 0.5395
-- Train Accuracy: 0.8097
-- Train Precision: 0.8082
-- Train Recall: 0.8097
-- Train F1: 0.8050
-- Epoch: 2
+- Train Loss: 0.5499
+- Validation Loss: 0.5859
+- Train Accuracy: 0.7608
+- Train Precision: 0.7579
+- Train Recall: 0.7608
+- Train F1: 0.7578
+- Epoch: 0
 
 ## Model description
 
@@ -40,21 +40,19 @@ 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': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 18780, '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': 90930, '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 | Train Precision | Train Recall | Train F1 | Epoch |
 |:----------:|:---------------:|:--------------:|:---------------:|:------------:|:--------:|:-----:|
-| 0.6998     | 0.5708          | 0.7604         | 0.7585          | 0.7604       | 0.7569   | 0     |
-| 0.4521     | 0.5249          | 0.7986         | 0.7959          | 0.7986       | 0.7947   | 1     |
-| 0.2967     | 0.5395          | 0.8097         | 0.8082          | 0.8097       | 0.8050   | 2     |
+| 0.5499     | 0.5859          | 0.7608         | 0.7579          | 0.7608       | 0.7578   | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.40.2
+- Transformers 4.41.0
 - TensorFlow 2.15.0
 - Datasets 2.19.1
 - Tokenizers 0.19.1

config.json

@@ -9,15 +9,15 @@
   "dropout": 0.1,
   "hidden_dim": 3072,
   "id2label": {
-    "0": "NOT ENOUGH INFO",
-    "1": "SUPPORTS",
-    "2": "REFUTES"
+    "0": "SUPPORTS",
+    "1": "REFUTES",
+    "2": "NOT ENOUGH INFO"
   },
   "initializer_range": 0.02,
   "label2id": {
-    "NOT ENOUGH INFO": 0,
-    "REFUTES": 2,
-    "SUPPORTS": 1
+    "NOT ENOUGH INFO": 2,
+    "REFUTES": 1,
+    "SUPPORTS": 0
   },
   "max_position_embeddings": 512,
   "model_type": "distilbert",
@@ -29,6 +29,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "transformers_version": "4.40.2",
+  "transformers_version": "4.41.0",
   "vocab_size": 30522
 }

logs/train/events.out.tfevents.1716365651.f6a4bbb2972d.324.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a801398516cb6cecce47f53c9ee1950241fbb8f66ac4f77f5d759d264135248f
+size 1924279

logs/validation/events.out.tfevents.1716366035.f6a4bbb2972d.324.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7c3fbe8e9113a1817c9003525e61c3f16ed23f2be34990620dc29f6f88fe6d1
+size 232

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0374c08f0d1fba05b8c7cc7629b1b191e7dfba8b9215a4aedcac919834becc28
-size 267954880
+oid sha256:4f63b8447d0785a0a4d8e56c4dcf3dd7d05dd74c2a0978969e652f0eaa1a454d
+size 267958216