test_model #13
|
@ -1,25 +0,0 @@
|
|||
{
|
||||
"architectures": [
|
||||
"BertForSequenceClassification"
|
||||
],
|
||||
"attention_probs_dropout_prob": 0.1,
|
||||
"classifier_dropout": null,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_dropout_prob": 0.1,
|
||||
"hidden_size": 384,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 1536,
|
||||
"layer_norm_eps": 1e-12,
|
||||
"max_position_embeddings": 512,
|
||||
"model_type": "bert",
|
||||
"num_attention_heads": 6,
|
||||
"num_hidden_layers": 6,
|
||||
"pad_token_id": 0,
|
||||
"position_embedding_type": "absolute",
|
||||
"problem_type": "single_label_classification",
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.44.0",
|
||||
"type_vocab_size": 2,
|
||||
"use_cache": true,
|
||||
"vocab_size": 119547
|
||||
}
|
|
@ -114,7 +114,7 @@ if __name__ == '__main__':
|
|||
train_df, val_df = train_test_split(df, test_size=0.35, random_state=42)
|
||||
|
||||
# Initialize and train the model
|
||||
trainer = FakeNewsModelTrainer(size_factor=0.25)
|
||||
trainer = FakeNewsModelTrainer(size_factor=0.5)
|
||||
train_data = trainer.prepare_data(train_df)
|
||||
val_data = trainer.prepare_data(val_df)
|
||||
trainer.train(train_data, val_data)
|
||||
|
|
Reference in New Issue