Skip to content

Instantly share code, notes, and snippets.

@FurkanGozukara

FurkanGozukara/adamW config.json

Created August 8, 2024 14:38
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save FurkanGozukara/5e9ee7d2b2070abb9a173dab342e1221 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save FurkanGozukara/5e9ee7d2b2070abb9a173dab342e1221 to your computer and use it in GitHub Desktop.
Download ZIP
adamW config.json
Raw
adamW config.json
{
"__version": 4,
"training_method": "FINE_TUNE",
"model_type": "STABLE_DIFFUSION_XL_10_BASE",
"debug_mode": false,
"debug_dir": "debug",
"workspace_dir": "/home/Ubuntu/apps/stable-diffusion-webui/models/Stable-diffusion",
"cache_dir": "/home/Ubuntu/apps/stable-diffusion-webui/OT_cacheworkspace-cache/run",
"tensorboard": false,
"tensorboard_expose": false,
"continue_last_backup": false,
"include_train_config": "ALL",
"base_model_name": "/home/Ubuntu/Downloads/RealVisXL_V4.0.safetensors",
"weight_dtype": "BFLOAT_16",
"output_dtype": "FLOAT_32",
"output_model_format": "SAFETENSORS",
"output_model_destination": "/home/Ubuntu/apps/stable-diffusion-webui/models/Stable-diffusion/adamw_v2.safetensors",
"gradient_checkpointing": true,
"force_circular_padding": false,
"concept_file_name": "training_concepts/concepts.json",
"concepts": null,
"aspect_ratio_bucketing": false,
"latent_caching": true,
"clear_cache_before_training": false,
"learning_rate_scheduler": "CONSTANT",
"custom_learning_rate_scheduler": null,
"scheduler_params": [],
"learning_rate": 3e-06,
"learning_rate_warmup_steps": 20,
"learning_rate_cycles": 1,
"epochs": 750,
"batch_size": 30,
"gradient_accumulation_steps": 1,
"ema": "OFF",
"ema_decay": 0.999,
"ema_update_step_interval": 5,
"dataloader_threads": 8,
"train_device": "cuda",
"temp_device": "cpu",
"train_dtype": "BFLOAT_16",
"fallback_train_dtype": "FLOAT_32",
"enable_autocast_cache": true,
"only_cache": false,
"resolution": "1024",
"attention_mechanism": "XFORMERS",
"align_prop": false,
"align_prop_probability": 0.1,
"align_prop_loss": "AESTHETIC",
"align_prop_weight": 0.01,
"align_prop_steps": 20,
"align_prop_truncate_steps": 0.5,
"align_prop_cfg_scale": 7.0,
"mse_strength": 1.0,
"mae_strength": 0.0,
"vb_loss_strength": 1.0,
"loss_weight_fn": "CONSTANT",
"loss_weight_strength": 5.0,
"dropout_probability": 0.0,
"loss_scaler": "NONE",
"learning_rate_scaler": "NONE",
"offset_noise_weight": 0.1,
"perturbation_noise_weight": 0.0,
"rescale_noise_scheduler_to_zero_terminal_snr": false,
"force_v_prediction": false,
"force_epsilon_prediction": false,
"min_noising_strength": 0.0,
"max_noising_strength": 1.0,
"timestep_distribution": "UNIFORM",
"noising_weight": 0.0,
"noising_bias": 0.0,
"unet": {
"__version": 0,
"model_name": "",
"include": true,
"train": true,
"stop_training_after": 0,
"stop_training_after_unit": "NEVER",
"learning_rate": 3e-06,
"weight_dtype": "BFLOAT_16",
"dropout_probability": 0.0,
"train_embedding": true,
"attention_mask": false
},
"prior": {
"__version": 0,
"model_name": "",
"include": true,
"train": true,
"stop_training_after": 0,
"stop_training_after_unit": "NEVER",
"learning_rate": null,
"weight_dtype": "NONE",
"dropout_probability": 0.0,
"train_embedding": true,
"attention_mask": false
},
"text_encoder": {
"__version": 0,
"model_name": "",
"include": true,
"train": false,
"stop_training_after": 500,
"stop_training_after_unit": "STEP",
"learning_rate": 0.0005,
"weight_dtype": "BFLOAT_16",
"dropout_probability": 0.0,
"train_embedding": false,
"attention_mask": false
},
"text_encoder_layer_skip": 1,
"text_encoder_2": {
"__version": 0,
"model_name": "",
"include": true,
"train": false,
"stop_training_after": 500,
"stop_training_after_unit": "STEP",
"learning_rate": 0.0005,
"weight_dtype": "BFLOAT_16",
"dropout_probability": 0.0,
"train_embedding": false,
"attention_mask": false
},
"text_encoder_2_layer_skip": 1,
"text_encoder_3": {
"__version": 0,
"model_name": "",
"include": true,
"train": true,
"stop_training_after": 30,
"stop_training_after_unit": "EPOCH",
"learning_rate": null,
"weight_dtype": "NONE",
"dropout_probability": 0.0,
"train_embedding": true,
"attention_mask": false
},
"text_encoder_3_layer_skip": 0,
"vae": {
"__version": 0,
"model_name": "stabilityai/sdxl-vae",
"include": true,
"train": true,
"stop_training_after": null,
"stop_training_after_unit": "NEVER",
"learning_rate": null,
"weight_dtype": "FLOAT_32",
"dropout_probability": 0.0,
"train_embedding": true,
"attention_mask": false
},
"effnet_encoder": {
"__version": 0,
"model_name": "",
"include": true,
"train": true,
"stop_training_after": null,
"stop_training_after_unit": "NEVER",
"learning_rate": null,
"weight_dtype": "NONE",
"dropout_probability": 0.0,
"train_embedding": true,
"attention_mask": false
},
"decoder": {
"__version": 0,
"model_name": "",
"include": true,
"train": true,
"stop_training_after": null,
"stop_training_after_unit": "NEVER",
"learning_rate": null,
"weight_dtype": "NONE",
"dropout_probability": 0.0,
"train_embedding": true,
"attention_mask": false
},
"decoder_text_encoder": {
"__version": 0,
"model_name": "",
"include": true,
"train": true,
"stop_training_after": null,
"stop_training_after_unit": "NEVER",
"learning_rate": null,
"weight_dtype": "NONE",
"dropout_probability": 0.0,
"train_embedding": true,
"attention_mask": false
},
"decoder_vqgan": {
"__version": 0,
"model_name": "",
"include": true,
"train": true,
"stop_training_after": null,
"stop_training_after_unit": "NEVER",
"learning_rate": null,
"weight_dtype": "NONE",
"dropout_probability": 0.0,
"train_embedding": true,
"attention_mask": false
},
"masked_training": false,
"unmasked_probability": 0.0,
"unmasked_weight": 0.0,
"normalize_masked_area_loss": false,
"embedding_learning_rate": null,
"preserve_embedding_norm": false,
"embedding": {
"__version": 0,
"uuid": "85e41034-3bbc-468d-8259-1ba360d685bc",
"model_name": "",
"placeholder": "<embedding>",
"train": true,
"stop_training_after": null,
"stop_training_after_unit": "NEVER",
"token_count": 1,
"initial_embedding_text": "*"
},
"additional_embeddings": [],
"embedding_weight_dtype": "FLOAT_32",
"peft_type": "LORA",
"lora_model_name": "",
"lora_rank": 64,
"lora_alpha": 1.0,
"lora_decompose": false,
"lora_decompose_norm_epsilon": true,
"lora_weight_dtype": "FLOAT_32",
"lora_layers": "attentions",
"lora_layer_preset": "attn-mlp",
"bundle_additional_embeddings": true,
"optimizer": {
"__version": 0,
"optimizer": "ADAMW",
"adam_w_mode": false,
"alpha": null,
"amsgrad": false,
"beta1": 0.9,
"beta2": 0.999,
"beta3": null,
"bias_correction": false,
"block_wise": false,
"capturable": false,
"centered": false,
"clip_threshold": null,
"d0": null,
"d_coef": null,
"dampening": null,
"decay_rate": null,
"decouple": false,
"differentiable": false,
"eps": 1e-08,
"eps2": null,
"foreach": false,
"fsdp_in_use": false,
"fused": false,
"fused_back_pass": true,
"growth_rate": null,
"initial_accumulator_value": null,
"is_paged": false,
"log_every": null,
"lr_decay": null,
"max_unorm": null,
"maximize": false,
"min_8bit_size": null,
"momentum": null,
"nesterov": false,
"no_prox": false,
"optim_bits": null,
"percentile_clipping": null,
"r": null,
"relative_step": false,
"safeguard_warmup": false,
"scale_parameter": false,
"stochastic_rounding": true,
"use_bias_correction": false,
"use_triton": false,
"warmup_init": false,
"weight_decay": 0.01,
"weight_lr_power": null,
"decoupled_decay": false,
"fixed_decay": false,
"rectify": false,
"degenerated_to_sgd": false,
"k": null,
"xi": null,
"n_sma_threshold": null,
"ams_bound": false,
"adanorm": false,
"adam_debias": false
},
"optimizer_defaults": {
"ADAMW": {
"__version": 0,
"optimizer": "ADAMW",
"adam_w_mode": false,
"alpha": null,
"amsgrad": false,
"beta1": 0.9,
"beta2": 0.999,
"beta3": null,
"bias_correction": false,
"block_wise": false,
"capturable": false,
"centered": false,
"clip_threshold": null,
"d0": null,
"d_coef": null,
"dampening": null,
"decay_rate": null,
"decouple": false,
"differentiable": false,
"eps": 1e-08,
"eps2": null,
"foreach": false,
"fsdp_in_use": false,
"fused": false,
"fused_back_pass": true,
"growth_rate": null,
"initial_accumulator_value": null,
"is_paged": false,
"log_every": null,
"lr_decay": null,
"max_unorm": null,
"maximize": false,
"min_8bit_size": null,
"momentum": null,
"nesterov": false,
"no_prox": false,
"optim_bits": null,
"percentile_clipping": null,
"r": null,
"relative_step": false,
"safeguard_warmup": false,
"scale_parameter": false,
"stochastic_rounding": true,
"use_bias_correction": false,
"use_triton": false,
"warmup_init": false,
"weight_decay": 0.01,
"weight_lr_power": null,
"decoupled_decay": false,
"fixed_decay": false,
"rectify": false,
"degenerated_to_sgd": false,
"k": null,
"xi": null,
"n_sma_threshold": null,
"ams_bound": false,
"adanorm": false,
"adam_debias": false
}
},
"sample_definition_file_name": "training_samples/samples.json",
"samples": null,
"sample_after": 1,
"sample_after_unit": "NEVER",
"sample_image_format": "JPG",
"samples_to_tensorboard": false,
"non_ema_sampling": false,
"backup_after": 30,
"backup_after_unit": "MINUTE",
"rolling_backup": false,
"rolling_backup_count": 1,
"backup_before_save": false,
"save_after": 150,
"save_after_unit": "EPOCH",
"save_filename_prefix": "adamw_v2"
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment