21 lines
728 B
JSON
21 lines
728 B
JSON
{
|
|
"metric_group": "training_perplexity",
|
|
"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",
|
|
"checkpoint": "outputs/code-analyze-qlora/checkpoint-222",
|
|
"source": "outputs/code-analyze-qlora/checkpoint-222/trainer_state.json",
|
|
"validation_file": "prepared_data/code_analyze/val.jsonl",
|
|
"evaluation_date": "2026-06-11",
|
|
"metrics": {
|
|
"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
|
|
}
|
|
} |