Upload TFDistilBertForQuestionAnswering

README.md

@@ -2,20 +2,22 @@
 license: apache-2.0
 base_model: distilbert-base-uncased
 tags:
-- generated_from_trainer
+- generated_from_keras_callback
 model-index:
 - name: my_awesome_qa_model
   results: []
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
 
 # my_awesome_qa_model
 
 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:
-- Loss: 1.6865
+- Train Loss: 1.5477
+- Validation Loss: 1.7788
+- Epoch: 2
 
 ## Model description
 
@@ -34,26 +36,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 3
+- 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': 500, '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
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 250  | 2.3057          |
-| 2.5561        | 2.0   | 500  | 1.7411          |
-| 2.5561        | 3.0   | 750  | 1.6865          |
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 3.4904     | 2.2145          | 0     |
+| 1.8153     | 1.7788          | 1     |
+| 1.5477     | 1.7788          | 2     |
 
 
 ### Framework versions
 
 - Transformers 4.41.2
-- Pytorch 2.3.0+cu121
+- TensorFlow 2.15.0
 - Datasets 2.20.0
 - Tokenizers 0.19.1

config.json

@@ -18,7 +18,6 @@
   "seq_classif_dropout": 0.2,
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "torch_dtype": "float32",
   "transformers_version": "4.41.2",
   "vocab_size": 30522
 }

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71c21f4de8c72d837449a1025d6ddc61fb6c0df63ae9f91b94200cc7b86d00b8
+size 265583592