| { | |
| "dataset": { | |
| "total_examples": 24293, | |
| "training_examples": 21863, | |
| "validation_examples": 2430, | |
| "data_sources": { | |
| "synthetic_sql": "60%", | |
| "spider_dataset": "25%", | |
| "wikisql_dataset": "15%" | |
| }, | |
| "data_quality": "high", | |
| "mysql_specificity": "100%" | |
| }, | |
| "training_setup": { | |
| "training_type": "causal_language_modeling", | |
| "batch_size": 6, | |
| "sequence_length": 256, | |
| "learning_rate": 0.0003, | |
| "weight_decay": 0.1, | |
| "optimizer": "AdamW", | |
| "scheduler": "CosineAnnealingLR", | |
| "gradient_clipping": 1.0 | |
| }, | |
| "hardware_configuration": { | |
| "gpu": "RTX 5080 16GB", | |
| "memory_usage": "~2GB VRAM", | |
| "training_speed": "42.3 batches/second", | |
| "total_training_time": "12 minutes", | |
| "energy_efficiency": "excellent" | |
| }, | |
| "model_configuration": { | |
| "architecture": "GPT-style", | |
| "layers": 8, | |
| "heads": 8, | |
| "hidden_size": 512, | |
| "feedforward_size": 2048, | |
| "dropout": 0.1, | |
| "max_sequence": 512 | |
| } | |
| } |