| { | |
| "architecture": "LlamaForCausalLM", | |
| "parameters": 35756544, | |
| "vocab_size": 16384, | |
| "hidden_size": 512, | |
| "intermediate_size": 1376, | |
| "num_hidden_layers": 6, | |
| "num_attention_heads": 8, | |
| "num_key_value_heads": 8, | |
| "max_position_embeddings": 1024, | |
| "epochs": 2, | |
| "batch_size": 16, | |
| "total_steps": 200, | |
| "learning_rate": 0.001, | |
| "weight_decay": 0.01, | |
| "random_seed": 42, | |
| "random_baseline_loss": 9.7041, | |
| "final_train_loss": 1.0608, | |
| "final_val_loss": 1.221, | |
| "total_training_time_seconds": 893.07, | |
| "hardware": { | |
| "platform": "Windows-10-10.0.26200-SP0", | |
| "processor": "Intel64 Family 6 Model 154 Stepping 4, GenuineIntel", | |
| "python_version": "3.11.15 (main, Mar 24 2026, 22:57:51) [MSC v.1944 64 bit (AMD64)]" | |
| } | |
| } |