Upload TFDistilBertForSequenceClassification

README.md

@@ -0,0 +1,60 @@
+---
+license: apache-2.0
+base_model: distilbert/distilbert-base-uncased
+tags:
+- generated_from_keras_callback
+model-index:
+- name: my-awesome-model_1104
+  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. -->
+
+# my-awesome-model_1104
+
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.1542
+- Validation Loss: 0.2705
+- Train Accuracy: 0.8859
+- Train F1: 0.7612
+- Train Precision: 0.7567
+- Train Recall: 0.7658
+- Epoch: 2
+
+## 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': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 440, '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 | Validation Loss | Train Accuracy | Train F1 | Train Precision | Train Recall | Epoch |
+|:----------:|:---------------:|:--------------:|:--------:|:---------------:|:------------:|:-----:|
+| 0.4339     | 0.3796          | 0.8310         | 0.4791   | 0.8934          | 0.3273       | 0     |
+| 0.2672     | 0.3265          | 0.8680         | 0.6606   | 0.8491          | 0.5405       | 1     |
+| 0.1542     | 0.2705          | 0.8859         | 0.7612   | 0.7567          | 0.7658       | 2     |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- TensorFlow 2.17.0
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "NotHarm",
+    "1": "Harm"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Harm": 1,
+    "NotHarm": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.41.1",
+  "vocab_size": 30522
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d0c540cdd47cd24febd914417772ae7bc1dfecf74ce89b17369b12fb9474d10
+size 267951808