Upload TFElectraForQuestionAnswering

README.md

@@ -0,0 +1,67 @@
+---
+license: apache-2.0
+base_model: google/electra-small-discriminator
+tags:
+- generated_from_keras_callback
+model-index:
+- name: textmining_proj02_electra
+  results: []
+---
+
+<!-- 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. -->
+
+# textmining_proj02_electra
+
+This model is a fine-tuned version of [google/electra-small-discriminator](https://huggingface.co/google/electra-small-discriminator) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 2.0145
+- Train End Logits Accuracy: 0.5186
+- Train Start Logits Accuracy: 0.4898
+- Validation Loss: 1.7837
+- Validation End Logits Accuracy: 0.5643
+- Validation Start Logits Accuracy: 0.5514
+- Epoch: 9
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+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': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 15630, '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 | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
+|:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
+| 3.5498     | 0.2455                    | 0.2154                      | 2.7762          | 0.3625                         | 0.3353                           | 0     |
+| 2.7913     | 0.3657                    | 0.3291                      | 2.5014          | 0.4105                         | 0.3950                           | 1     |
+| 2.5710     | 0.4032                    | 0.3725                      | 2.2847          | 0.4635                         | 0.4409                           | 2     |
+| 2.4125     | 0.4377                    | 0.4076                      | 2.1311          | 0.4904                         | 0.4761                           | 3     |
+| 2.2918     | 0.4641                    | 0.4348                      | 2.0155          | 0.5161                         | 0.5063                           | 4     |
+| 2.1978     | 0.4833                    | 0.4512                      | 1.9319          | 0.5343                         | 0.5214                           | 5     |
+| 2.1306     | 0.4960                    | 0.4664                      | 1.8634          | 0.5505                         | 0.5352                           | 6     |
+| 2.0801     | 0.5018                    | 0.4755                      | 1.8229          | 0.5568                         | 0.5457                           | 7     |
+| 2.0404     | 0.5139                    | 0.4837                      | 1.7963          | 0.5611                         | 0.5488                           | 8     |
+| 2.0145     | 0.5186                    | 0.4898                      | 1.7837          | 0.5643                         | 0.5514                           | 9     |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- TensorFlow 2.15.0
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "google/electra-small-discriminator",
+  "architectures": [
+    "ElectraForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6232c874e127f273a1e9f8bf21a5c3c59b170f5271cf52e23da03c22c0e07414
+size 54221088