{ "active_parameters_per_token": 50512000, "architecture": { "hidden_size": 896, "intermediate_size": 1024, "max_position_embeddings": 4096, "num_attention_heads": 14, "num_experts_per_tok": 1, "num_hidden_layers": 6, "num_key_value_heads": 14, "num_local_experts": 7, "vocab_size": 16384 }, "assistant_target_tokens": 100023805, "completed_budget": true, "context_window": 4096, "dataset": "mookiezi/Discord-Dialogues", "elapsed_seconds": 659.3014483451843, "finished_at": "2026-08-26T07:22:26Z", "precision": "bf16 autocast with fp32 master weights", "qat": true, "qat_scheme": "symmetric per-output-channel INT8 weight fake quantization", "sequence_length_trained": 1024, "stage": "sft", "steps": 2197, "tokens_trained": 215973888, "total_parameters": 149602432 }