Upload TFBertForSequenceClassification

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: Regression_bert_1
+  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. -->
+
+# Regression_bert_1
+
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.3594
+- Train Mae: 0.2822
+- Train Mse: 0.1206
+- Train R2-score: 0.6163
+- Train Accuracy: 0.5308
+- Validation Loss: 0.3503
+- Validation Mae: 0.3488
+- Validation Mse: 0.1574
+- Validation R2-score: 0.8718
+- Validation Accuracy: 0.2703
+- 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': 2e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Train Mae | Train Mse | Train R2-score | Train Accuracy | Validation Loss | Validation Mae | Validation Mse | Validation R2-score | Validation Accuracy | Epoch |
+|:----------:|:---------:|:---------:|:--------------:|:--------------:|:---------------:|:--------------:|:--------------:|:-------------------:|:-------------------:|:-----:|
+| 0.4941     | 0.2941    | 0.1183    | -0.5444        | 0.5769         | 0.3126          | 0.3108         | 0.1099         | 0.8865              | 0.2703              | 0     |
+| 0.4660     | 0.3256    | 0.1546    | 0.0002         | 0.5231         | 0.3682          | 0.3669         | 0.1835         | 0.8572              | 0.2703              | 1     |
+| 0.4110     | 0.3178    | 0.1552    | 0.6834         | 0.5            | 0.4381          | 0.4369         | 0.2390         | 0.8207              | 0.2703              | 2     |
+| 0.3886     | 0.3112    | 0.1560    | 0.7184         | 0.5231         | 0.3566          | 0.3552         | 0.1672         | 0.8661              | 0.2703              | 3     |
+| 0.4055     | 0.2890    | 0.1248    | 0.7655         | 0.6077         | 0.4364          | 0.4353         | 0.2376         | 0.8218              | 0.2703              | 4     |
+| 0.3955     | 0.2930    | 0.1272    | 0.7685         | 0.5538         | 0.3868          | 0.3855         | 0.1971         | 0.8489              | 0.2703              | 5     |
+| 0.3949     | 0.3003    | 0.1386    | 0.3857         | 0.5154         | 0.3614          | 0.3600         | 0.1751         | 0.8620              | 0.2703              | 6     |
+| 0.3390     | 0.2874    | 0.1306    | 0.7121         | 0.5231         | 0.3766          | 0.3753         | 0.1894         | 0.8542              | 0.2703              | 7     |
+| 0.3556     | 0.2775    | 0.1190    | 0.7890         | 0.5231         | 0.3561          | 0.3547         | 0.1664         | 0.8667              | 0.2703              | 8     |
+| 0.3594     | 0.2822    | 0.1206    | 0.6163         | 0.5308         | 0.3503          | 0.3488         | 0.1574         | 0.8718              | 0.2703              | 9     |
+
+
+### Framework versions
+
+- Transformers 4.27.2
+- TensorFlow 2.11.0
+- Datasets 2.10.1
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "transformers_version": "4.27.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8a35631d786f0744012b2d5b183757de70a48fb8c9592a2e13782b81c345b6b
+size 433532180