jmroth's picture
HPO best: cross-encoder/ms-marco-MiniLM-L-6-v2 | {'num_train_epochs': 1, 'learning_rate': 1.4319807550234704e-06, 'per_device_train_batch_size': 16} | threshold=0.85
0a41a2e verified
{
"add_cross_attention": false,
"architectures": [
"BertForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": null,
"classifier_dropout": null,
"dtype": "float32",
"eos_token_id": null,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 384,
"id2label": {
"0": "LABEL_0"
},
"initializer_range": 0.02,
"intermediate_size": 1536,
"is_decoder": false,
"label2id": {
"LABEL_0": 0
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 6,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"sbert_ce_default_activation_function": "torch.nn.modules.linear.Identity",
"tie_word_embeddings": true,
"transformers_version": "5.0.0",
"type_vocab_size": 2,
"use_cache": false,
"vocab_size": 30522
}