checkpoint 010000

checkpoints/010000/pretrained_model/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+tags:
+- base_model:adapter:lerobot/lingbot_va_libero_long
+- lora
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.20.0

checkpoints/010000/pretrained_model/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "LingBotVAPolicy",
+    "parent_library": "lerobot.policies.lingbot_va.modeling_lingbot_va"
+  },
+  "base_model_name_or_path": "lerobot/lingbot_va_libero_long",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "to_q",
+    "to_v"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

checkpoints/010000/pretrained_model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2139792b1599c18980e450d34cbab3c2130b5ca361f49f0b390e6a29c2afa817
+size 47218168

checkpoints/010000/pretrained_model/config.json

@@ -0,0 +1,100 @@
+{
+    "type": "lingbot_va",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.images.image": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                256,
+                256
+            ]
+        },
+        "observation.images.image2": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                256,
+                256
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                4
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "use_peft": true,
+    "push_to_hub": true,
+    "repo_id": "Grigorij/Tello_multifruit_sum_lingbot",
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": "lerobot/lingbot_va_libero_long",
+    "pretrained_revision": null,
+    "patch_size": [
+        1,
+        2,
+        2
+    ],
+    "num_attention_heads": 24,
+    "attention_head_dim": 128,
+    "in_channels": 48,
+    "out_channels": 48,
+    "action_dim": 30,
+    "text_dim": 4096,
+    "freq_dim": 256,
+    "ffn_dim": 14336,
+    "num_layers": 30,
+    "cross_attn_norm": true,
+    "eps": 1e-06,
+    "rope_max_seq_len": 1024,
+    "attn_mode": "flex",
+    "wan_pretrained_path": "robbyant/lingbot-va-posttrain-libero-long",
+    "dtype": "bfloat16",
+    "text_encoder_device": "cpu",
+    "obs_cam_keys": [
+        "observation.images.camera_front"
+    ],
+    "image_hflip": true,
+    "camera_layout": "width_concat",
+    "height": 128,
+    "width": 128,
+    "action_per_frame": 4,
+    "frame_chunk_size": 4,
+    "attn_window": 30,
+    "num_inference_steps": 20,
+    "video_exec_step": -1,
+    "action_num_inference_steps": 50,
+    "guidance_scale": 5.0,
+    "action_guidance_scale": 1.0,
+    "snr_shift": 5.0,
+    "action_snr_shift": 0.05,
+    "max_sequence_length": 512,
+    "used_action_channel_ids": [
+        0,
+        1,
+        2,
+        3
+    ],
+    "save_predicted_video": false,
+    "normalization_mapping": {
+        "VISUAL": "IDENTITY",
+        "STATE": "IDENTITY",
+        "ACTION": "IDENTITY"
+    },
+    "optimizer_lr": 1e-05,
+    "optimizer_betas": [
+        0.9,
+        0.95
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 0.0001,
+    "optimizer_grad_clip_norm": 1.0,
+    "scheduler_warmup_steps": 1000
+}

checkpoints/010000/pretrained_model/policy_postprocessor.json

@@ -0,0 +1,32 @@
+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "unnormalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              4
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "IDENTITY",
+          "STATE": "IDENTITY",
+          "ACTION": "IDENTITY"
+        }
+      },
+      "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cpu",
+        "float_dtype": null
+      }
+    }
+  ]
+}

checkpoints/010000/pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a30ca67d452ece489554004dfaa59926d9fb507c8e843ae0cae763e3dfa4e257
+size 6380

checkpoints/010000/pretrained_model/policy_preprocessor.json

@@ -0,0 +1,60 @@
+{
+  "name": "policy_preprocessor",
+  "steps": [
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {
+          "observation.images.image": "observation.images.camera_front"
+        }
+      }
+    },
+    {
+      "registry_name": "to_batch_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "normalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "observation.images.image": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              256,
+              256
+            ]
+          },
+          "observation.images.image2": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              256,
+              256
+            ]
+          },
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              4
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "IDENTITY",
+          "STATE": "IDENTITY",
+          "ACTION": "IDENTITY"
+        }
+      },
+      "state_file": "policy_preprocessor_step_2_normalizer_processor.safetensors"
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cuda",
+        "float_dtype": null
+      }
+    }
+  ]
+}

checkpoints/010000/pretrained_model/policy_preprocessor_step_2_normalizer_processor.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a30ca67d452ece489554004dfaa59926d9fb507c8e843ae0cae763e3dfa4e257
+size 6380

checkpoints/010000/pretrained_model/train_config.json

@@ -0,0 +1,264 @@
+{
+    "dataset": {
+        "repo_id": "Grigorij/Tello_multifruit_sum",
+        "repo_type": "dataset",
+        "root": null,
+        "episodes": null,
+        "image_transforms": {
+            "enable": false,
+            "max_num_transforms": 3,
+            "random_order": false,
+            "tfs": {
+                "brightness": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "brightness": [
+                            0.8,
+                            1.2
+                        ]
+                    }
+                },
+                "contrast": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "contrast": [
+                            0.8,
+                            1.2
+                        ]
+                    }
+                },
+                "saturation": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "saturation": [
+                            0.5,
+                            1.5
+                        ]
+                    }
+                },
+                "hue": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "hue": [
+                            -0.05,
+                            0.05
+                        ]
+                    }
+                },
+                "sharpness": {
+                    "weight": 1.0,
+                    "type": "SharpnessJitter",
+                    "kwargs": {
+                        "sharpness": [
+                            0.5,
+                            1.5
+                        ]
+                    }
+                },
+                "affine": {
+                    "weight": 1.0,
+                    "type": "RandomAffine",
+                    "kwargs": {
+                        "degrees": [
+                            -5.0,
+                            5.0
+                        ],
+                        "translate": [
+                            0.05,
+                            0.05
+                        ]
+                    }
+                }
+            }
+        },
+        "revision": null,
+        "use_imagenet_stats": true,
+        "video_backend": "pyav",
+        "return_uint8": false,
+        "depth_output_unit": "mm",
+        "streaming": false,
+        "eval_split": 0.0
+    },
+    "env": null,
+    "policy": {
+        "type": "lingbot_va",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.images.image": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    256,
+                    256
+                ]
+            },
+            "observation.images.image2": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    256,
+                    256
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    4
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "use_peft": true,
+        "push_to_hub": true,
+        "repo_id": "Grigorij/Tello_multifruit_sum_lingbot",
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": "lerobot/lingbot_va_libero_long",
+        "pretrained_revision": null,
+        "patch_size": [
+            1,
+            2,
+            2
+        ],
+        "num_attention_heads": 24,
+        "attention_head_dim": 128,
+        "in_channels": 48,
+        "out_channels": 48,
+        "action_dim": 30,
+        "text_dim": 4096,
+        "freq_dim": 256,
+        "ffn_dim": 14336,
+        "num_layers": 30,
+        "cross_attn_norm": true,
+        "eps": 1e-06,
+        "rope_max_seq_len": 1024,
+        "attn_mode": "flex",
+        "wan_pretrained_path": "robbyant/lingbot-va-posttrain-libero-long",
+        "dtype": "bfloat16",
+        "text_encoder_device": "cpu",
+        "obs_cam_keys": [
+            "observation.images.camera_front"
+        ],
+        "image_hflip": true,
+        "camera_layout": "width_concat",
+        "height": 128,
+        "width": 128,
+        "action_per_frame": 4,
+        "frame_chunk_size": 4,
+        "attn_window": 30,
+        "num_inference_steps": 20,
+        "video_exec_step": -1,
+        "action_num_inference_steps": 50,
+        "guidance_scale": 5.0,
+        "action_guidance_scale": 1.0,
+        "snr_shift": 5.0,
+        "action_snr_shift": 0.05,
+        "max_sequence_length": 512,
+        "used_action_channel_ids": [
+            0,
+            1,
+            2,
+            3
+        ],
+        "save_predicted_video": false,
+        "normalization_mapping": {
+            "VISUAL": "IDENTITY",
+            "STATE": "IDENTITY",
+            "ACTION": "IDENTITY"
+        },
+        "optimizer_lr": 1e-05,
+        "optimizer_betas": [
+            0.9,
+            0.95
+        ],
+        "optimizer_eps": 1e-08,
+        "optimizer_weight_decay": 0.0001,
+        "optimizer_grad_clip_norm": 1.0,
+        "scheduler_warmup_steps": 1000
+    },
+    "reward_model": null,
+    "output_dir": "outputs/train/2026-08-10/13-53-01_lingbot_va",
+    "job_name": "lingbot_va",
+    "resume": false,
+    "seed": 1000,
+    "cudnn_deterministic": false,
+    "num_workers": 4,
+    "batch_size": 1,
+    "prefetch_factor": 4,
+    "persistent_workers": true,
+    "dataloader_multiprocessing_context": "spawn",
+    "steps": 25000,
+    "env_eval_freq": 20000,
+    "log_freq": 200,
+    "eval_steps": 0,
+    "max_eval_samples": 0,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 5000,
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 1e-05,
+        "weight_decay": 0.0001,
+        "grad_clip_norm": 1.0,
+        "betas": [
+            0.9,
+            0.95
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": {
+        "type": "constant_with_warmup",
+        "num_warmup_steps": 1000
+    },
+    "eval": {
+        "n_episodes": 50,
+        "batch_size": 16,
+        "use_async_envs": true,
+        "recording": false,
+        "recording_repo_id": null,
+        "recording_private": false
+    },
+    "wandb": {
+        "enable": true,
+        "disable_artifact": false,
+        "project": "lerobot",
+        "entity": null,
+        "notes": null,
+        "run_id": "sklwrhjy",
+        "mode": null,
+        "add_tags": true
+    },
+    "peft": {
+        "target_modules": [
+            "to_q",
+            "to_v"
+        ],
+        "full_training_modules": null,
+        "method_type": "LORA",
+        "init_type": null,
+        "r": 16,
+        "lora_alpha": 16
+    },
+    "job": {
+        "target": null,
+        "image": "huggingface/lerobot-gpu:latest",
+        "timeout": "2d",
+        "detach": false,
+        "tags": []
+    },
+    "save_checkpoint_to_hub": true,
+    "sample_weighting": null,
+    "rename_map": {
+        "observation.images.image": "observation.images.camera_front"
+    },
+    "checkpoint_path": null
+}

checkpoints/010000/training_state/optimizer_param_groups.json

@@ -0,0 +1,261 @@
+[
+    {
+        "lr": 1e-05,
+        "betas": [
+            0.9,
+            0.95
+        ],
+        "eps": 1e-08,
+        "weight_decay": 0.0001,
+        "amsgrad": false,
+        "maximize": false,
+        "foreach": null,
+        "capturable": false,
+        "differentiable": false,
+        "fused": null,
+        "decoupled_weight_decay": true,
+        "initial_lr": 1e-05,
+        "params": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15,
+            16,
+            17,
+            18,
+            19,
+            20,
+            21,
+            22,
+            23,
+            24,
+            25,
+            26,
+            27,
+            28,
+            29,
+            30,
+            31,
+            32,
+            33,
+            34,
+            35,
+            36,
+            37,
+            38,
+            39,
+            40,
+            41,
+            42,
+            43,
+            44,
+            45,
+            46,
+            47,
+            48,
+            49,
+            50,
+            51,
+            52,
+            53,
+            54,
+            55,
+            56,
+            57,
+            58,
+            59,
+            60,
+            61,
+            62,
+            63,
+            64,
+            65,
+            66,
+            67,
+            68,
+            69,
+            70,
+            71,
+            72,
+            73,
+            74,
+            75,
+            76,
+            77,
+            78,
+            79,
+            80,
+            81,
+            82,
+            83,
+            84,
+            85,
+            86,
+            87,
+            88,
+            89,
+            90,
+            91,
+            92,
+            93,
+            94,
+            95,
+            96,
+            97,
+            98,
+            99,
+            100,
+            101,
+            102,
+            103,
+            104,
+            105,
+            106,
+            107,
+            108,
+            109,
+            110,
+            111,
+            112,
+            113,
+            114,
+            115,
+            116,
+            117,
+            118,
+            119,
+            120,
+            121,
+            122,
+            123,
+            124,
+            125,
+            126,
+            127,
+            128,
+            129,
+            130,
+            131,
+            132,
+            133,
+            134,
+            135,
+            136,
+            137,
+            138,
+            139,
+            140,
+            141,
+            142,
+            143,
+            144,
+            145,
+            146,
+            147,
+            148,
+            149,
+            150,
+            151,
+            152,
+            153,
+            154,
+            155,
+            156,
+            157,
+            158,
+            159,
+            160,
+            161,
+            162,
+            163,
+            164,
+            165,
+            166,
+            167,
+            168,
+            169,
+            170,
+            171,
+            172,
+            173,
+            174,
+            175,
+            176,
+            177,
+            178,
+            179,
+            180,
+            181,
+            182,
+            183,
+            184,
+            185,
+            186,
+            187,
+            188,
+            189,
+            190,
+            191,
+            192,
+            193,
+            194,
+            195,
+            196,
+            197,
+            198,
+            199,
+            200,
+            201,
+            202,
+            203,
+            204,
+            205,
+            206,
+            207,
+            208,
+            209,
+            210,
+            211,
+            212,
+            213,
+            214,
+            215,
+            216,
+            217,
+            218,
+            219,
+            220,
+            221,
+            222,
+            223,
+            224,
+            225,
+            226,
+            227,
+            228,
+            229,
+            230,
+            231,
+            232,
+            233,
+            234,
+            235,
+            236,
+            237,
+            238,
+            239
+        ]
+    }
+]

checkpoints/010000/training_state/optimizer_state.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7696c4d49e194bf58c53a484efee51240387ea91c1d2cc5e3198714a7162e083
+size 94434712

checkpoints/010000/training_state/rng_state.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:647934b55588a1b458e7c31fd2a4d8002f2891b9352a677ddfabf29e751d8bb4
+size 15708

checkpoints/010000/training_state/scheduler_state.json

@@ -0,0 +1,15 @@
+{
+    "base_lrs": [
+        1e-05
+    ],
+    "last_epoch": 10000,
+    "_step_count": 10001,
+    "_is_initial": false,
+    "_get_lr_called_within_step": false,
+    "_last_lr": [
+        1e-05
+    ],
+    "lr_lambdas": [
+        null
+    ]
+}

checkpoints/010000/training_state/training_step.json

@@ -0,0 +1,5 @@
+{
+    "step": 10000,
+    "num_processes": 1,
+    "batch_size": 1
+}