|
{ |
|
"_name_or_path": "/home/jovyan/work/code4me-analysis/notebooks/paper/results/13_jonberta/12_codeberta-biased-2e-05lr--0/model/-13_jonberta-biased-12_codeberta-biased-2e-05lr--0-(ATTN-208C_f-[0, 3]L)-2e-05lr-3", |
|
"add_feature_bias": true, |
|
"add_feature_embeddings": true, |
|
"add_self_attn": true, |
|
"architectures": [ |
|
"JonbertaForSequenceClassification" |
|
], |
|
"attention_probs_dropout_prob": 0.1, |
|
"bos_token_id": 0, |
|
"classifier_dropout": null, |
|
"eos_token_id": 2, |
|
"feature_dropout_prob": 0.1, |
|
"feature_hidden_size": 208, |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.1, |
|
"hidden_size": 768, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"layer_norm_eps": 1e-05, |
|
"max_position_embeddings": 514, |
|
"model_type": "roberta", |
|
"num_attention_heads": 12, |
|
"num_hidden_layers": 6, |
|
"num_telemetry_features": 26, |
|
"pad_token_id": 1, |
|
"position_embedding_type": "absolute", |
|
"problem_type": "single_label_classification", |
|
"self_attn_layers": [ |
|
0, |
|
3 |
|
], |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.37.2", |
|
"type_vocab_size": 1, |
|
"use_cache": true, |
|
"vocab_size": 52000 |
|
} |
|
|