mirror of https://github.com/bmaltais/kohya_ss
Add pytorch_optimizer.CAME to optimizer list.
bmaltais
parent
1c7ab4d4f3
commit
8f2476115e
|
|
@ -213,6 +213,7 @@ class BasicTraining:
|
||||||
"PagedLion8bit",
|
"PagedLion8bit",
|
||||||
"Prodigy",
|
"Prodigy",
|
||||||
"prodigyplus.ProdigyPlusScheduleFree",
|
"prodigyplus.ProdigyPlusScheduleFree",
|
||||||
|
"pytorch_optimizer.CAME",
|
||||||
"RAdamScheduleFree",
|
"RAdamScheduleFree",
|
||||||
"SGDNesterov",
|
"SGDNesterov",
|
||||||
"SGDNesterov8bit",
|
"SGDNesterov8bit",
|
||||||
|
|
|
||||||
|
|
@ -0,0 +1,123 @@
|
||||||
|
{
|
||||||
|
"LoRA_type": "Standard",
|
||||||
|
"LyCORIS_preset": "full",
|
||||||
|
"adaptive_noise_scale": 0,
|
||||||
|
"additional_parameters": " --optimizer_args \"weight_decay=0.01\" \"d_coef=1\" \"use_bias_correction=True\" \"safeguard_warmup=False\" \"betas=0.9,0.99\"",
|
||||||
|
"block_alphas": "",
|
||||||
|
"block_dims": "",
|
||||||
|
"block_lr_zero_threshold": "",
|
||||||
|
"bucket_no_upscale": true,
|
||||||
|
"bucket_reso_steps": 256,
|
||||||
|
"cache_latents": true,
|
||||||
|
"cache_latents_to_disk": true,
|
||||||
|
"caption_dropout_every_n_epochs": 0.0,
|
||||||
|
"caption_dropout_rate": 0,
|
||||||
|
"caption_extension": ".txt",
|
||||||
|
"clip_skip": 2,
|
||||||
|
"color_aug": false,
|
||||||
|
"constrain": 0.0,
|
||||||
|
"conv_alpha": 1,
|
||||||
|
"conv_block_alphas": "",
|
||||||
|
"conv_block_dims": "",
|
||||||
|
"conv_dim": 1,
|
||||||
|
"debiased_estimation_loss": false,
|
||||||
|
"decompose_both": false,
|
||||||
|
"dim_from_weights": false,
|
||||||
|
"down_lr_weight": "",
|
||||||
|
"enable_bucket": true,
|
||||||
|
"epoch": 50,
|
||||||
|
"factor": -1,
|
||||||
|
"flip_aug": false,
|
||||||
|
"fp8_base": false,
|
||||||
|
"full_bf16": true,
|
||||||
|
"full_fp16": false,
|
||||||
|
"gradient_accumulation_steps": "1",
|
||||||
|
"gradient_checkpointing": true,
|
||||||
|
"keep_tokens": 4,
|
||||||
|
"learning_rate": 1.0,
|
||||||
|
"logging_dir": "E:/work/LoRa_work/logging",
|
||||||
|
"lora_network_weights": "",
|
||||||
|
"lr_scheduler": "cosine",
|
||||||
|
"lr_scheduler_args": "",
|
||||||
|
"lr_scheduler_num_cycles": "",
|
||||||
|
"lr_scheduler_power": "",
|
||||||
|
"lr_warmup": 0,
|
||||||
|
"max_bucket_reso": 2048,
|
||||||
|
"max_data_loader_n_workers": "0",
|
||||||
|
"max_grad_norm": 1,
|
||||||
|
"max_resolution": "1024,1024",
|
||||||
|
"max_timestep": 1000,
|
||||||
|
"max_token_length": "75",
|
||||||
|
"max_train_epochs": "50",
|
||||||
|
"max_train_steps": "",
|
||||||
|
"mem_eff_attn": false,
|
||||||
|
"mid_lr_weight": "",
|
||||||
|
"min_bucket_reso": 512,
|
||||||
|
"min_snr_gamma": 0,
|
||||||
|
"min_timestep": 0,
|
||||||
|
"mixed_precision": "bf16",
|
||||||
|
"model_list": "custom",
|
||||||
|
"module_dropout": 0,
|
||||||
|
"multires_noise_discount": 0,
|
||||||
|
"multires_noise_iterations": 0,
|
||||||
|
"network_alpha": 2,
|
||||||
|
"network_dim": 16,
|
||||||
|
"network_dropout": 0,
|
||||||
|
"no_token_padding": false,
|
||||||
|
"noise_offset": 0,
|
||||||
|
"noise_offset_type": "Original",
|
||||||
|
"num_cpu_threads_per_process": 2,
|
||||||
|
"optimizer": "Prodigy",
|
||||||
|
"optimizer_args": "",
|
||||||
|
"output_dir": "E:/work/output",
|
||||||
|
"output_name": "zunko_pony_v1",
|
||||||
|
"persistent_data_loader_workers": false,
|
||||||
|
"pretrained_model_name_or_path": "E:/models/ponyDiffusionV6XL_v6StartWithThisOne.safetensors",
|
||||||
|
"prior_loss_weight": 1.0,
|
||||||
|
"random_crop": false,
|
||||||
|
"rank_dropout": 0,
|
||||||
|
"rank_dropout_scale": false,
|
||||||
|
"reg_data_dir": "",
|
||||||
|
"rescaled": false,
|
||||||
|
"resume": "",
|
||||||
|
"sample_every_n_epochs": 0,
|
||||||
|
"sample_every_n_steps": 0,
|
||||||
|
"sample_prompts": "",
|
||||||
|
"sample_sampler": "euler_a",
|
||||||
|
"save_every_n_epochs": 10,
|
||||||
|
"save_every_n_steps": 0,
|
||||||
|
"save_last_n_steps": 0,
|
||||||
|
"save_last_n_steps_state": 0,
|
||||||
|
"save_model_as": "safetensors",
|
||||||
|
"save_precision": "bf16",
|
||||||
|
"save_state": false,
|
||||||
|
"scale_v_pred_loss_like_noise_pred": false,
|
||||||
|
"scale_weight_norms": 0,
|
||||||
|
"sdxl": true,
|
||||||
|
"sdxl_cache_text_encoder_outputs": false,
|
||||||
|
"sdxl_no_half_vae": true,
|
||||||
|
"seed": "1055217506",
|
||||||
|
"shuffle_caption": true,
|
||||||
|
"stop_text_encoder_training": 0,
|
||||||
|
"text_encoder_lr": 0.0,
|
||||||
|
"train_batch_size": 3,
|
||||||
|
"train_data_dir": "E:/work/input/zunko_dataset",
|
||||||
|
"train_norm": false,
|
||||||
|
"train_on_input": true,
|
||||||
|
"training_comment": "",
|
||||||
|
"unet_lr": 0.0,
|
||||||
|
"unit": 1,
|
||||||
|
"up_lr_weight": "",
|
||||||
|
"use_cp": false,
|
||||||
|
"use_scalar": false,
|
||||||
|
"use_tucker": false,
|
||||||
|
"use_wandb": false,
|
||||||
|
"v2": false,
|
||||||
|
"v_parameterization": false,
|
||||||
|
"v_pred_like_loss": 0,
|
||||||
|
"vae": "",
|
||||||
|
"vae_batch_size": 0,
|
||||||
|
"wandb_api_key": "",
|
||||||
|
"weighted_captions": false,
|
||||||
|
"xformers": "xformers"
|
||||||
|
}
|
||||||
Loading…
Reference in New Issue