Upload TFAlbertForSequenceClassification

README.md

@@ -1,6 +1,49 @@
 ---
-license: mit
-language:
-- en
-pipeline_tag: text-classification
----
+license: apache-2.0
+base_model: albert-base-v2
+tags:
+- generated_from_keras_callback
+model-index:
+- name: albert-spam-filter
+  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. -->
+
+# albert-spam-filter
+
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+
+
+## 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1290, '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
+
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- TensorFlow 2.13.0
+- Datasets 2.14.5
+- Tokenizers 0.14.1

config.json

@@ -1,12 +1,40 @@
 {
-  "_name_or_path": "albert-spam-filter",
+  "_name_or_path": "albert-base-v2",
   "architectures": [
-    "AlbertForUnmaskedLM"
+    "AlbertForSequenceClassification"
   ],
-  "id2label": {0: "Not Spam", 1: "Spam"},
-  "label2id": {"Not Spam": 0, "Spam": 1},
-  "problem_type": "binary_classification",
-  "torch_dtype": "float32",
-  "transformers_version": "4.21.3",
-  "use_cache": true,
-}
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Not Spam",
+    "1": "Spam"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Not Spam": 0,
+    "Spam": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.34.0",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f623ecbe03d69817ea8b2d860c2b3441073370a90f82b43e2a4624245e054aa5
+size 46781688