Upload TFRobertaForSequenceClassification

README.md

@@ -0,0 +1,70 @@
+---
+license: mit
+tags:
+- generated_from_keras_callback
+model-index:
+- name: Regression_roberta_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_roberta_1
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.3891
+- Train Mae: 0.3117
+- Train Mse: 0.1477
+- Train R2-score: 0.7113
+- Train Accuracy: 0.7077
+- Validation Loss: 0.3272
+- Validation Mae: 0.3256
+- Validation Mse: 0.1253
+- Validation R2-score: 0.8839
+- Validation Accuracy: 0.9459
+- 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 |
+|:----------:|:---------:|:---------:|:--------------:|:--------------:|:---------------:|:--------------:|:--------------:|:-------------------:|:-------------------:|:-----:|
+| 0.4486     | 0.2939    | 0.1319    | 0.7250         | 0.7769         | 0.4177          | 0.4165         | 0.2221         | 0.8321              | 0.3243              | 0     |
+| 0.3684     | 0.2898    | 0.1342    | 0.5541         | 0.7462         | 0.4019          | 0.4006         | 0.2091         | 0.8409              | 0.3243              | 1     |
+| 0.3423     | 0.2854    | 0.1299    | 0.7355         | 0.7462         | 0.3971          | 0.3958         | 0.2050         | 0.8438              | 0.3243              | 2     |
+| 0.3514     | 0.2890    | 0.1324    | 0.7935         | 0.7538         | 0.3552          | 0.3538         | 0.1640         | 0.8681              | 0.9459              | 3     |
+| 0.3722     | 0.3107    | 0.1525    | 0.5604         | 0.7000         | 0.3448          | 0.3432         | 0.1484         | 0.8750              | 0.9459              | 4     |
+| 0.3996     | 0.2949    | 0.1305    | 0.7869         | 0.8231         | 0.3692          | 0.3677         | 0.1794         | 0.8514              | 0.4865              | 5     |
+| 0.3441     | 0.2895    | 0.1322    | 0.7546         | 0.7538         | 0.3186          | 0.3169         | 0.1159         | 0.8860              | 0.9459              | 6     |
+| 0.3898     | 0.2921    | 0.1255    | 0.5919         | 0.7692         | 0.4107          | 0.4095         | 0.2160         | 0.8366              | 0.3243              | 7     |
+| 0.3552     | 0.2868    | 0.1297    | 0.7113         | 0.7538         | 0.4426          | 0.4415         | 0.2434         | 0.8179              | 0.3243              | 8     |
+| 0.3891     | 0.3117    | 0.1477    | 0.7113         | 0.7077         | 0.3272          | 0.3256         | 0.1253         | 0.8839              | 0.9459              | 9     |
+
+
+### Framework versions
+
+- Transformers 4.27.2
+- TensorFlow 2.11.0
+- Datasets 2.10.1
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "transformers_version": "4.27.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fc4577c35e54d7af3ff1b2fb1481441c456d64d62773d4e5ec9432a0b1f76d5
+size 498875200