{ "step": 715, "val_loss": 1.1147265434265137, "mmlu_acc": 0.2919921875, "arc_easy_acc": 0.27734375, "model_config": { "sequence_len": 2048, "vocab_size": 65536, "n_layer": 20, "n_head": 10, "n_kv_head": 10, "n_embd": 1280 } }