Function save_opt_context_gguf

common/train.cpp:596–661

}

void save_opt_context_gguf(struct gguf_context * fctx, struct ggml_opt_context * opt) {
    gguf_set_val_u32(fctx, LLM_KV_OPTIMIZER_FILE_VERSION, 0);
    gguf_set_val_u32(fctx, LLM_KV_OPTIMIZER_CONVERGENCE_PAST_COUNT, opt->params.past);
    gguf_set_val_u64(fctx, LLM_KV_OPTIMIZER_PARAMETER_COUNT, (uint64_t) opt->nx);
    gguf_set_val_u32(fctx, LLM_KV_OPTIMIZER_ITERATION_COUNT, opt->iter);
    gguf_set_val_bool(fctx, LLM_KV_OPTIMIZER_JUST_INITIALIZED, opt->just_initialized);

    switch (opt->params.type) {
        case GGML_OPT_ADAM:
            {
                gguf_set_val_str(fctx, LLM_KV_OPTIMIZER_TYPE, LLM_KV_OPTIMIZER_TYPE_ADAM);
                gguf_set_val_f32(fctx, LLM_KV_OPTIMIZER_ADAM_BEST_LOSS,            opt->adam.fx_best);
                gguf_set_val_f32(fctx, LLM_KV_OPTIMIZER_ADAM_PREVIOUS_LOSS,        opt->adam.fx_prev);
                gguf_set_val_u32(fctx, LLM_KV_OPTIMIZER_ADAM_NO_IMPROVEMENT_COUNT, opt->adam.n_no_improvement);

                ggml_set_name(opt->adam.m, LLM_TENSOR_OPTIMIZER_ADAM_FIRST_MOMENTS);
                ggml_set_name(opt->adam.v, LLM_TENSOR_OPTIMIZER_ADAM_SECOND_MOMENTS);
                if (opt->adam.pf) {
                    ggml_set_name(opt->adam.pf, LLM_TENSOR_OPTIMIZER_ADAM_PAST_LOSS_VALUES);
                }

                gguf_add_tensor(fctx, opt->adam.m);
                gguf_add_tensor(fctx, opt->adam.v);
                if (opt->adam.pf) {
                    gguf_add_tensor(fctx, opt->adam.pf);
                }
            } break;
        case GGML_OPT_LBFGS:
            {
                gguf_set_val_str(fctx, LLM_KV_OPTIMIZER_TYPE, LLM_KV_OPTIMIZER_TYPE_LBFGS);
                gguf_set_val_u32(fctx, LLM_KV_OPTIMIZER_LBFGS_APPROX_HESSIAN_COUNT, opt->params.lbfgs.m);
                gguf_set_val_f32(fctx, LLM_KV_OPTIMIZER_LBFGS_BEST_LOSS,            opt->lbfgs.fx_best);
                gguf_set_val_f32(fctx, LLM_KV_OPTIMIZER_LBFGS_LINE_SEARCH_STEP,     opt->lbfgs.step);
                gguf_set_val_i32(fctx, LLM_KV_OPTIMIZER_LBFGS_LINE_SEARCH_J,        opt->lbfgs.j);
                gguf_set_val_i32(fctx, LLM_KV_OPTIMIZER_LBFGS_LINE_SEARCH_K,        opt->lbfgs.k);
                gguf_set_val_i32(fctx, LLM_KV_OPTIMIZER_LBFGS_LINE_SEARCH_END,      opt->lbfgs.end);
                gguf_set_val_u32(fctx, LLM_KV_OPTIMIZER_LBFGS_NO_IMPROVEMENT_COUNT, opt->lbfgs.n_no_improvement);

                ggml_set_name(opt->lbfgs.x,    LLM_TENSOR_OPTIMIZER_LBFGS_CURRENT_PARAMETERS);
                ggml_set_name(opt->lbfgs.xp,   LLM_TENSOR_OPTIMIZER_LBFGS_PREVIOUS_PARAMETERS);
                ggml_set_name(opt->lbfgs.g,    LLM_TENSOR_OPTIMIZER_LBFGS_CURRENT_GRADIENTS);
                ggml_set_name(opt->lbfgs.gp,   LLM_TENSOR_OPTIMIZER_LBFGS_PREVIOUS_GRADIENTS);
                ggml_set_name(opt->lbfgs.d,    LLM_TENSOR_OPTIMIZER_LBFGS_SEARCH_DIRECTION);
                if (opt->lbfgs.pf) {
                    ggml_set_name(opt->lbfgs.pf, LLM_TENSOR_OPTIMIZER_LBFGS_PAST_LOSS_VALUES);
                }
                ggml_set_name(opt->lbfgs.lmal, LLM_TENSOR_OPTIMIZER_LBFGS_MEMORY_ALPHA);
                ggml_set_name(opt->lbfgs.lmys, LLM_TENSOR_OPTIMIZER_LBFGS_MEMORY_YS);
                ggml_set_name(opt->lbfgs.lms,  LLM_TENSOR_OPTIMIZER_LBFGS_MEMORY_S);
                ggml_set_name(opt->lbfgs.lmy,  LLM_TENSOR_OPTIMIZER_LBFGS_MEMORY_Y);

                gguf_add_tensor(fctx, opt->lbfgs.x);
                gguf_add_tensor(fctx, opt->lbfgs.xp);
                gguf_add_tensor(fctx, opt->lbfgs.g);
                gguf_add_tensor(fctx, opt->lbfgs.gp);
                gguf_add_tensor(fctx, opt->lbfgs.d);
                if (opt->lbfgs.pf) {
                    gguf_add_tensor(fctx, opt->lbfgs.pf);