| { |
| "robovlm_name": "RoboKosMos", |
| "parent": null, |
| "task_name": "calvin_finetune", |
| "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-5, |
| "min_lr_scale": 1e-2, |
| "weight_decay": 0, |
| "warmup_epochs": 0.25, |
| "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", |
| "log_root": "runs/logs", |
| "cache_root": "runs/cache", |
| "model_load_path": null, |
| "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": "bf16", |
| "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": 1e-4, |
| "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": null, |
| "check_val_every_n_epoch": 1, |
| "max_steps": -1, |
| "accumulate_grad_batches": 1 |
| }, |
| "train_dataset": { |
| "type": "DiskCalvinDataset", |
| "data_dir": "datasets/calvin_data/task_ABCD_D/training", |
| "shift_first": false, |
| "model_name": "kosmos", |
| "rgb_pad": 10, |
| "gripper_pad": 4 |
| }, |
| "val_dataset": { |
| "type": "DiskCalvinDataset", |
| "data_dir": "datasets/calvin_data/task_ABCD_D/validation", |
| "model_name": "kosmos" |
| }, |
| "norm_action": true, |
| "norm_min": -0.65, |
| "norm_max": 0.65, |
| "raw_config_path": "configs/calvin_finetune/finetune_kosmos_cont-lstm-post_full-ft_text_vision_wd-0_ws-16_act-10.json", |
| "config": "configs/calvin_finetune/finetune_kosmos_cont-lstm-post_full-ft_text_vision_wd-0_ws-16_act-10.json", |
| "gpus": 8, |
| "num_nodes": 1, |
| "log_dir": "runs/logs/kosmos/calvin_finetune/2024-12-26/15-13", |
| "output_dir": "runs/checkpoints/kosmos/calvin_finetune/2024-12-26/15-13", |
| "data_dir": null, |
| "annotation_file": null, |
| "data_subfolder": null, |
| "task_num": null, |
| "exp_name": "15-13", |
| "use_multi_modal_emb": false, |
| "no_video_pretrained_model": false, |
| "finetune": false, |
| "llm": { |
| "type": null, |
| "n_embd": null, |
| "n_layer": null, |
| "n_head": null |
| } |
| } |