Upload TFRobertaForSequenceClassification

README.md

@@ -0,0 +1,61 @@
+---
+license: mit
+tags:
+- generated_from_keras_callback
+model-index:
+- name: roberta-blm-tweets
+  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. -->
+
+# roberta-blm-tweets
+
+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: 0.3333
+- Train Accuracy: 0.8964
+- Validation Loss: 1.5482
+- Validation Accuracy: 0.6106
+- Epoch: 7
+
+## 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': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
+|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
+| 1.4279     | 0.4908         | 1.3684          | 0.5442              | 0     |
+| 1.1474     | 0.6375         | 1.2189          | 0.5796              | 1     |
+| 0.9645     | 0.7016         | 1.1257          | 0.6106              | 2     |
+| 0.7404     | 0.7534         | 1.2809          | 0.6239              | 3     |
+| 0.6608     | 0.7965         | 1.4192          | 0.5973              | 4     |
+| 0.5460     | 0.8187         | 1.3828          | 0.5354              | 5     |
+| 0.4058     | 0.8668         | 1.5394          | 0.5929              | 6     |
+| 0.3333     | 0.8964         | 1.5482          | 0.6106              | 7     |
+
+
+### Framework versions
+
+- Transformers 4.25.1
+- TensorFlow 2.9.2
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,48 @@
+{
+  "_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",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "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": "4.25.1",
+  "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 sha256:05007451dc0170b475e486b58f3ba502ea14b9ebf2e819717445346dfc3581ec
+size 498899840