| { |
| "architectures": [ |
| "BertForSequenceClassification" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "classifier_dropout": null, |
| "gradient_checkpointing": false, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "id2label": { |
| "0": "LABEL_0" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "label2id": { |
| "LABEL_0": 0 |
| }, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 512, |
| "model_type": "bert", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "pad_token_id": 0, |
| "position_embedding_type": "absolute", |
| "threshold_tau": 0.5254495143890381, |
| "torch_dtype": "float32", |
| "trained_epoch": 2, |
| "training_cfg": { |
| "batch_size": 16, |
| "checkpoint": "bert_aegis.pt", |
| "device": "cuda", |
| "lr_backbone": 2e-06, |
| "lr_head": 0.0001, |
| "max_length": 512, |
| "model_name": "bert-base-uncased", |
| "num_epochs": 2, |
| "num_workers": 4, |
| "seed": 42, |
| "val_split": 0.1, |
| "weight_decay": 0.01 |
| }, |
| "transformers_version": "4.52.4", |
| "type_vocab_size": 2, |
| "use_cache": true, |
| "val_metrics": { |
| "accuracy": 0.8198198198198198, |
| "f1": 0.856353591160221, |
| "fn": 213, |
| "fp": 47, |
| "precision": 0.9428223844282239, |
| "recall": 0.7844129554655871, |
| "roc_auc": 0.9164612715220003, |
| "tn": 408, |
| "tp": 775 |
| }, |
| "vocab_size": 30522 |
| } |
|
|
