Training in progress epoch 0

README.md

@@ -1,5 +1,6 @@
 ---
 license: apache-2.0
+base_model: bert-base-uncased
 tags:
 - generated_from_keras_callback
 model-index:
@@ -12,49 +13,43 @@ probably proofread and complete it, then remove this comment. -->
 
 # athrado/bert-finetuned-nli
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the [sick](https://huggingface.co/datasets/sick) dataset for natural language inference.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0671
-- Train Accuracy: 0.9806
-- Validation Loss: 0.5285
-- Validation Accuracy: 0.8424
-- Epoch: 4
+- Train Loss: 0.5542
+- Train Accuracy: 0.7587
+- Validation Loss: 0.4403
+- Validation Accuracy: 0.8343
+- Epoch: 0
 
 ## Model description
 
-Example model for educational purposes: fine-tuning the bert-base-uncased model for natural language inference. 
+More information needed
 
 ## Intended uses & limitations
 
-- Learning about transformer model and fine-tuning
-- Natural language inference fine-tuned on small dataset
+More information needed
 
 ## Training and evaluation data
 
-The model is evaluated using the sick validation. We report accuracy, and in addition we computed a weighted F1-score of 0.842.
+More information needed
 
 ## Training procedure
 
 ### 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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 2775, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 2775, '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-07, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 0.5345     | 0.7810         | 0.4586          | 0.8283              | 0     |
-| 0.3253     | 0.8797         | 0.3890          | 0.8404              | 1     |
-| 0.2070     | 0.9290         | 0.4210          | 0.8303              | 2     |
-| 0.1171     | 0.9610         | 0.5200          | 0.8424              | 3     |
-| 0.0671     | 0.9806         | 0.5285          | 0.8424              | 4     |
+| 0.5542     | 0.7587         | 0.4403          | 0.8343              | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.30.2
-- TensorFlow 2.12.0
-- Datasets 2.13.1
+- Transformers 4.31.0
+- TensorFlow 2.13.0
 - Tokenizers 0.13.3

config.json

@@ -28,7 +28,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.30.2",
+  "transformers_version": "4.31.0",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9570b1bc29b01b3af2aade89d8cd5bc73e6b45afa3ea4d70b2df37ed8a5474ce
+oid sha256:b9114f23b29209780a9fe54eb5847b459a6cc473406b1dc93f9db43bc2aefe91
 size 438226204