Upload TFDebertaV2ForSequenceClassification

README.md

@@ -0,0 +1,69 @@
+---
+license: mit
+tags:
+- generated_from_keras_callback
+model-index:
+- name: quynh_deberta-v3-Base-finetuned-AI_req_3
+  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. -->
+
+# quynh_deberta-v3-Base-finetuned-AI_req_3
+
+This model is a fine-tuned version of [microsoft/deberta-v3-Base](https://huggingface.co/microsoft/deberta-v3-Base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.0121
+- Train Accuracy: 0.9986
+- Validation Loss: 1.0930
+- Validation Accuracy: 0.8190
+- Epoch: 14
+
+## 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', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2730, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
+|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
+| 0.8969     | 0.6099         | 0.7640          | 0.7048              | 0     |
+| 0.7508     | 0.6951         | 0.7178          | 0.7048              | 1     |
+| 0.6149     | 0.7404         | 0.5981          | 0.7714              | 2     |
+| 0.5077     | 0.7720         | 0.5059          | 0.8095              | 3     |
+| 0.4357     | 0.8036         | 0.4621          | 0.8095              | 4     |
+| 0.3671     | 0.8407         | 0.4859          | 0.8190              | 5     |
+| 0.2844     | 0.8777         | 0.6214          | 0.8000              | 6     |
+| 0.2789     | 0.8860         | 0.5499          | 0.8190              | 7     |
+| 0.1938     | 0.9107         | 0.8163          | 0.7810              | 8     |
+| 0.1773     | 0.9231         | 0.8831          | 0.7905              | 9     |
+| 0.1308     | 0.9547         | 0.6316          | 0.8095              | 10    |
+| 0.0803     | 0.9712         | 0.8531          | 0.8286              | 11    |
+| 0.0544     | 0.9849         | 0.7941          | 0.7810              | 12    |
+| 0.0285     | 0.9931         | 0.9530          | 0.8190              | 13    |
+| 0.0121     | 0.9986         | 1.0930          | 0.8190              | 14    |
+
+
+### Framework versions
+
+- Transformers 4.28.0
+- TensorFlow 2.9.1
+- Datasets 2.16.1
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-Base",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "y",
+    "1": "p",
+    "2": "n"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "n": 2,
+    "p": 1,
+    "y": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "transformers_version": "4.28.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0895a3eda24196d88d22cd1d801abcd15cd28537284393528520e515e9bfe6de
+size 737989928