configs/kosmos_ph_post_train_google_robot.json

{
    "robovlm_name": "RoboKosMos",
    "parent": null,
    "model": "kosmos",
    "model_url": "https://huggingface.co/microsoft/kosmos-2-patch14-224",
    "seq_len": 1,
    "image_size": 224,
    "image_mean": [
        0.48145466,
        0.4578275,
        0.40821073
    ],
    "image_std": [
        0.26862954,
        0.26130258,
        0.27577711
    ],
    "window_size": 16,
    "fwd_pred_next_n": 10,
    "arm_gripper_loss_ratio": 0.01,
    "cap_loss_ratio": 0.05,
    "fwd_loss_ratio": 0,
    "seed": 123,
    "batch_size": 4,
    "num_workers": 16,
    "data_scale": 1,
    "optimizer": "adam",
    "learning_rate": 2e-05,
    "min_lr_scale": 0.01,
    "weight_decay": 0,
    "warmup_epochs": 0,
    "warmup_steps": 0,
    "warmup_ratio": null,
    "use_hand_rgb": true,
    "use_time_causal_attn": false,
    "use_mim_obs_loss": false,
    "use_pixel_loss": true,
    "use_obs_queries": true,
    "use_vision_resampler": false,
    "vision_masked_ratio": 0.9,
    "use_tube_mask": false,
    "output_root": "runs/checkpoints/oxe_post_train",
    "log_root": "runs/logs/oxe_post_train",
    "cache_root": "runs/cache/oxe_post_train",
    "model_load_path": "runs/checkpoints/oxe_pretrain/kosmos/2024-11-21/01-16/epoch=0-step=50000.pt",
    "model_load_source": "torch",
    "resume": null,
    "model_path": ".vlms/kosmos-2-patch14-224",
    "model_config": ".vlms/kosmos-2-patch14-224/config.json",
    "train_setup": {
        "precision": "16",
        "predict_action": true,
        "predict_forward": false,
        "predict_forward_hand": false,
        "predict_caption": false,
        "train_vision": true,
        "bits": -1,
        "freeze_mm_mlp_adapter": false,
        "freeze_backbone": false,
        "freeze_resampler": false,
        "tune_mm_mlp_adapter": false,
        "mm_use_im_start_end": false,
        "mm_use_im_patch_token": false,
        "gradient_checkpointing": false,
        "lora_enable": false,
        "mm_projector_lr": 0.0001,
        "lora_r": 64,
        "lora_alpha": 16,
        "lora_dropout": 0.05,
        "lora_bias": "none",
        "train_text_embedding": true
    },
    "vision_resampler": {
        "vis_dim": 1024,
        "depth": 8,
        "dim_head": 64,
        "heads": 8,
        "num_latents": 64
    },
    "act_encoder": null,
    "act_head": {
        "type": "LSTMDecoder",
        "hidden_size": 1024,
        "action_dim": 7,
        "down_sample": "none",
        "latent": 1,
        "fwd_pred_next_n": 1,
        "window_size": 1,
        "action_space": "continuous",
        "with_history": true,
        "history_type": "post"
    },
    "fwd_head": null,
    "tokenizer": {
        "type": "AutoProcessor",
        "pretrained_model_name_or_path": ".vlms/kosmos-2-patch14-224",
        "tokenizer_type": "kosmos",
        "max_text_len": 256,
        "additional_special_tokens": null
    },
    "vlm": {
        "type": "AutoModelForVision2Seq",
        "name": "kosmos",
        "pretrained_model_name_or_path": ".vlms/kosmos-2-patch14-224"
    },
    "trainer": {
        "accelerator": "gpu",
        "strategy": "deepspeed_stage_2",
        "precision": "16",
        "logger": [
            "tensorboard"
        ],
        "gradient_clip_val": 1.0,
        "use_distributed_sampler": false,
        "log_every_n_steps": 10,
        "max_epochs": 5,
        "val_check_interval": 10000,
        "check_val_every_n_epoch": null,
        "max_steps": 50000,
        "accumulate_grad_batches": 1,
        "limit_val_batches": 100
    },
    "train_dataset": {
        "type": "OpenVLADataset",
        "data_root_dir": "datasets/open-x-embodiment",
        "model_name": "kosmos",
        "image_aug": true,
        "mode": "train",
        "data_mix": "rt_1",
        "window_sample": "sliding",
        "organize_type": "interleave",
        "shuffle_buffer_size": 51200,
        "train": true
    },
    "val_dataset": {
        "type": "OpenVLADataset",
        "data_root_dir": "datasets/open-x-embodiment",
        "model_name": "kosmos",
        "mode": "train",
        "data_mix": "rt_1",
        "window_sample": "sliding",
        "organize_type": "interleave",
        "shuffle_buffer_size": 1000,
        "train": false,
        "filter_langs": true
    },
    "raw_config_path": "configs/kosmos/oxe_post_train/finetune_kosmos_cont-lstm-post_full-ft_text_vision_wd=0_hist=16_act=10_use-hand_aug-shift_act-norm_lr-1e-5_bs-128_warm-0_oxe-pre_rt.json",
    "config": "configs/kosmos/oxe_post_train/finetune_kosmos_cont-lstm-post_full-ft_text_vision_wd=0_hist=16_act=10_use-hand_aug-shift_act-norm_lr-1e-5_bs-128_warm-0_oxe-pre_rt.json",
    "gpus": 8,
    "num_nodes": 4,
    "log_dir": "runs/logs/oxe_post_train/kosmos/calvin_finetune/2024-11-24/16-11",
    "output_dir": "runs/logs/oxe_post_train/kosmos/calvin_finetune/2024-11-24/16-11",
    "data_dir": null,
    "annotation_file": null,
    "data_subfolder": null,
    "task_num": null,
    "exp_name": "16-11",
    "use_multi_modal_emb": false,
    "no_video_pretrained_model": false,
    "finetune": false,
    "llm": {
        "type": null,
        "n_embd": null,
        "n_layer": null,
        "n_head": null
    }
}