35 lines
1022 B
JSON
35 lines
1022 B
JSON
{
|
||
"title": "Отчёт об оценке модели Code_analyze.1.0",
|
||
"model": "Code_analyze.1.0",
|
||
"hf_model": "Vilyam888/Code_analyze.1.0",
|
||
"base_model": "Qwen/Qwen2.5-Coder-3B-Instruct",
|
||
"finetuning_method": "LoRA",
|
||
"base_model_quantization": "none",
|
||
"inference_dtype": "bfloat16",
|
||
"evaluation_date": "2026-06-11",
|
||
"evaluation_sample": "test.jsonl, N = 100",
|
||
"reference_split": "hold-out test",
|
||
"generation": {
|
||
"temperature": 0.2,
|
||
"max_new_tokens": 2048
|
||
},
|
||
"training": {
|
||
"train_loss_final": 0.241,
|
||
"eval_loss_final": 0.2776,
|
||
"eval_mean_token_accuracy": 0.925,
|
||
"perplexity_validation": 1.32,
|
||
"num_train_epochs": 2,
|
||
"global_step": 222
|
||
},
|
||
"generation_metrics": {
|
||
"valid_json_rate": 0.93,
|
||
"required_fields_rate": 0.9,
|
||
"tag_name_match_rate": 0.88,
|
||
"bleu4_corpus": 0.7,
|
||
"bleu4_summary": 0.72,
|
||
"rouge1_f1": 0.71,
|
||
"rouge2_f1": 0.56,
|
||
"rougeL_f1": 0.69,
|
||
"codebleu_status": "not_applicable"
|
||
}
|
||
} |