Upload TFRobertaForSequenceClassification

README.md

@@ -0,0 +1,59 @@
+---
+license: mit
+tags:
+- generated_from_keras_callback
+model-index:
+- name: wine-reviews-roberta
+  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. -->
+
+# wine-reviews-roberta
+
+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: 0.2715
+- Train Acc: 0.8906
+- Validation Loss: 0.6536
+- Validation Acc: 0.7701
+- Epoch: 4
+
+## 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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 24455, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Train Acc | Validation Loss | Validation Acc | Epoch |
+|:----------:|:---------:|:---------------:|:--------------:|:-----:|
+| 0.6164     | 0.7297    | 0.5360          | 0.7665         | 0     |
+| 0.5040     | 0.7820    | 0.5145          | 0.7739         | 1     |
+| 0.4248     | 0.8206    | 0.5470          | 0.7744         | 2     |
+| 0.3413     | 0.8583    | 0.6132          | 0.7699         | 3     |
+| 0.2715     | 0.8906    | 0.6536          | 0.7701         | 4     |
+
+
+### Framework versions
+
+- Transformers 4.28.1
+- TensorFlow 2.11.0
+- Datasets 2.1.0
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,38 @@
+{
+  "_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",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "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",
+  "transformers_version": "4.28.1",
+  "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:d6c18d6d2d6830ff663a2c232a7455fedca348b1026be6e5ca62c98e1f60b06e
+size 498884416