Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: distilbert-base-cased-distilled-squad
+base_model: distilbert-base-uncased
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,10 +13,10 @@ probably proofread and complete it, then remove this comment. -->
 
 # vinay04111/bert-finetuned-squad
 
-This model is a fine-tuned version of [distilbert-base-cased-distilled-squad](https://huggingface.co/distilbert-base-cased-distilled-squad) on an unknown dataset.
+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: 0.3400
-- Epoch: 2
+- Train Loss: 1.4842
+- Epoch: 0
 
 ## Model description
 
@@ -35,21 +35,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 16635, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 16596, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
 - training_precision: mixed_float16
 
 ### Training results
 
 | Train Loss | Epoch |
 |:----------:|:-----:|
-| 0.6237     | 0     |
-| 0.4565     | 1     |
-| 0.3400     | 2     |
+| 1.4842     | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.34.0
-- TensorFlow 2.13.0
-- Datasets 2.14.5
+- Transformers 4.34.1
+- TensorFlow 2.14.0
+- Datasets 2.14.6
 - Tokenizers 0.14.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-cased-distilled-squad",
+  "_name_or_path": "distilbert-base-uncased",
   "activation": "gelu",
   "architectures": [
     "DistilBertForQuestionAnswering"
@@ -13,12 +13,11 @@
   "model_type": "distilbert",
   "n_heads": 12,
   "n_layers": 6,
-  "output_past": true,
   "pad_token_id": 0,
   "qa_dropout": 0.1,
   "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": true,
+  "sinusoidal_pos_embds": false,
   "tie_weights_": true,
-  "transformers_version": "4.34.0",
-  "vocab_size": 28996
+  "transformers_version": "4.34.1",
+  "vocab_size": 30522
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9946f102a3ecf7d941da8e7e96067332e0231e4b0817e4108610fe6f665f269
-size 260895720
+oid sha256:6d58e04a69b96abeb3bb67ffeda7c9d1a999b9ec2ebf309cdd34f4236af157bc
+size 265583592

tokenizer_config.json

@@ -41,10 +41,9 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": false,
+  "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",