sync step-5000 checkpoint to main (Pi0.5 + ObjectVLA LoRA, 5000 steps)

ema_shadow.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99edb451c12367e530664e90bdd8fa6cca34339b25b86f32128f0adea51abf81
+size 231701035

pretrained_model/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+tags:
+- base_model:adapter:/home/shadeform/ckpts/warm_pg_v2_patched
+- 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 0.19.1

pretrained_model/adapter_config.json

@@ -0,0 +1,178 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "PI05Policy",
+    "parent_library": "lerobot.policies.pi05.modeling_pi05"
+  },
+  "base_model_name_or_path": "/home/shadeform/ckpts/warm_pg_v2_patched",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {
+    ".*language_model\\.layers\\.0\\..*\\.down_proj$": 16,
+    ".*language_model\\.layers\\.0\\..*\\.gate_proj$": 16,
+    ".*language_model\\.layers\\.0\\..*\\.k_proj$": 16,
+    ".*language_model\\.layers\\.0\\..*\\.o_proj$": 16,
+    ".*language_model\\.layers\\.0\\..*\\.q_proj$": 16,
+    ".*language_model\\.layers\\.0\\..*\\.up_proj$": 16,
+    ".*language_model\\.layers\\.0\\..*\\.v_proj$": 16,
+    ".*language_model\\.layers\\.10\\..*\\.down_proj$": 64,
+    ".*language_model\\.layers\\.10\\..*\\.gate_proj$": 64,
+    ".*language_model\\.layers\\.10\\..*\\.k_proj$": 64,
+    ".*language_model\\.layers\\.10\\..*\\.o_proj$": 64,
+    ".*language_model\\.layers\\.10\\..*\\.q_proj$": 64,
+    ".*language_model\\.layers\\.10\\..*\\.up_proj$": 64,
+    ".*language_model\\.layers\\.10\\..*\\.v_proj$": 64,
+    ".*language_model\\.layers\\.11\\..*\\.down_proj$": 64,
+    ".*language_model\\.layers\\.11\\..*\\.gate_proj$": 64,
+    ".*language_model\\.layers\\.11\\..*\\.k_proj$": 64,
+    ".*language_model\\.layers\\.11\\..*\\.o_proj$": 64,
+    ".*language_model\\.layers\\.11\\..*\\.q_proj$": 64,
+    ".*language_model\\.layers\\.11\\..*\\.up_proj$": 64,
+    ".*language_model\\.layers\\.11\\..*\\.v_proj$": 64,
+    ".*language_model\\.layers\\.12\\..*\\.down_proj$": 64,
+    ".*language_model\\.layers\\.12\\..*\\.gate_proj$": 64,
+    ".*language_model\\.layers\\.12\\..*\\.k_proj$": 64,
+    ".*language_model\\.layers\\.12\\..*\\.o_proj$": 64,
+    ".*language_model\\.layers\\.12\\..*\\.q_proj$": 64,
+    ".*language_model\\.layers\\.12\\..*\\.up_proj$": 64,
+    ".*language_model\\.layers\\.12\\..*\\.v_proj$": 64,
+    ".*language_model\\.layers\\.13\\..*\\.down_proj$": 32,
+    ".*language_model\\.layers\\.13\\..*\\.gate_proj$": 32,
+    ".*language_model\\.layers\\.13\\..*\\.k_proj$": 32,
+    ".*language_model\\.layers\\.13\\..*\\.o_proj$": 32,
+    ".*language_model\\.layers\\.13\\..*\\.q_proj$": 32,
+    ".*language_model\\.layers\\.13\\..*\\.up_proj$": 32,
+    ".*language_model\\.layers\\.13\\..*\\.v_proj$": 32,
+    ".*language_model\\.layers\\.14\\..*\\.down_proj$": 32,
+    ".*language_model\\.layers\\.14\\..*\\.gate_proj$": 32,
+    ".*language_model\\.layers\\.14\\..*\\.k_proj$": 32,
+    ".*language_model\\.layers\\.14\\..*\\.o_proj$": 32,
+    ".*language_model\\.layers\\.14\\..*\\.q_proj$": 32,
+    ".*language_model\\.layers\\.14\\..*\\.up_proj$": 32,
+    ".*language_model\\.layers\\.14\\..*\\.v_proj$": 32,
+    ".*language_model\\.layers\\.15\\..*\\.down_proj$": 48,
+    ".*language_model\\.layers\\.15\\..*\\.gate_proj$": 48,
+    ".*language_model\\.layers\\.15\\..*\\.k_proj$": 48,
+    ".*language_model\\.layers\\.15\\..*\\.o_proj$": 48,
+    ".*language_model\\.layers\\.15\\..*\\.q_proj$": 48,
+    ".*language_model\\.layers\\.15\\..*\\.up_proj$": 48,
+    ".*language_model\\.layers\\.15\\..*\\.v_proj$": 48,
+    ".*language_model\\.layers\\.16\\..*\\.down_proj$": 48,
+    ".*language_model\\.layers\\.16\\..*\\.gate_proj$": 48,
+    ".*language_model\\.layers\\.16\\..*\\.k_proj$": 48,
+    ".*language_model\\.layers\\.16\\..*\\.o_proj$": 48,
+    ".*language_model\\.layers\\.16\\..*\\.q_proj$": 48,
+    ".*language_model\\.layers\\.16\\..*\\.up_proj$": 48,
+    ".*language_model\\.layers\\.16\\..*\\.v_proj$": 48,
+    ".*language_model\\.layers\\.17\\..*\\.down_proj$": 48,
+    ".*language_model\\.layers\\.17\\..*\\.gate_proj$": 48,
+    ".*language_model\\.layers\\.17\\..*\\.k_proj$": 48,
+    ".*language_model\\.layers\\.17\\..*\\.o_proj$": 48,
+    ".*language_model\\.layers\\.17\\..*\\.q_proj$": 48,
+    ".*language_model\\.layers\\.17\\..*\\.up_proj$": 48,
+    ".*language_model\\.layers\\.17\\..*\\.v_proj$": 48,
+    ".*language_model\\.layers\\.1\\..*\\.down_proj$": 16,
+    ".*language_model\\.layers\\.1\\..*\\.gate_proj$": 16,
+    ".*language_model\\.layers\\.1\\..*\\.k_proj$": 16,
+    ".*language_model\\.layers\\.1\\..*\\.o_proj$": 16,
+    ".*language_model\\.layers\\.1\\..*\\.q_proj$": 16,
+    ".*language_model\\.layers\\.1\\..*\\.up_proj$": 16,
+    ".*language_model\\.layers\\.1\\..*\\.v_proj$": 16,
+    ".*language_model\\.layers\\.2\\..*\\.down_proj$": 16,
+    ".*language_model\\.layers\\.2\\..*\\.gate_proj$": 16,
+    ".*language_model\\.layers\\.2\\..*\\.k_proj$": 16,
+    ".*language_model\\.layers\\.2\\..*\\.o_proj$": 16,
+    ".*language_model\\.layers\\.2\\..*\\.q_proj$": 16,
+    ".*language_model\\.layers\\.2\\..*\\.up_proj$": 16,
+    ".*language_model\\.layers\\.2\\..*\\.v_proj$": 16,
+    ".*language_model\\.layers\\.3\\..*\\.down_proj$": 16,
+    ".*language_model\\.layers\\.3\\..*\\.gate_proj$": 16,
+    ".*language_model\\.layers\\.3\\..*\\.k_proj$": 16,
+    ".*language_model\\.layers\\.3\\..*\\.o_proj$": 16,
+    ".*language_model\\.layers\\.3\\..*\\.q_proj$": 16,
+    ".*language_model\\.layers\\.3\\..*\\.up_proj$": 16,
+    ".*language_model\\.layers\\.3\\..*\\.v_proj$": 16,
+    ".*language_model\\.layers\\.4\\..*\\.down_proj$": 16,
+    ".*language_model\\.layers\\.4\\..*\\.gate_proj$": 16,
+    ".*language_model\\.layers\\.4\\..*\\.k_proj$": 16,
+    ".*language_model\\.layers\\.4\\..*\\.o_proj$": 16,
+    ".*language_model\\.layers\\.4\\..*\\.q_proj$": 16,
+    ".*language_model\\.layers\\.4\\..*\\.up_proj$": 16,
+    ".*language_model\\.layers\\.4\\..*\\.v_proj$": 16,
+    ".*language_model\\.layers\\.5\\..*\\.down_proj$": 32,
+    ".*language_model\\.layers\\.5\\..*\\.gate_proj$": 32,
+    ".*language_model\\.layers\\.5\\..*\\.k_proj$": 32,
+    ".*language_model\\.layers\\.5\\..*\\.o_proj$": 32,
+    ".*language_model\\.layers\\.5\\..*\\.q_proj$": 32,
+    ".*language_model\\.layers\\.5\\..*\\.up_proj$": 32,
+    ".*language_model\\.layers\\.5\\..*\\.v_proj$": 32,
+    ".*language_model\\.layers\\.6\\..*\\.down_proj$": 32,
+    ".*language_model\\.layers\\.6\\..*\\.gate_proj$": 32,
+    ".*language_model\\.layers\\.6\\..*\\.k_proj$": 32,
+    ".*language_model\\.layers\\.6\\..*\\.o_proj$": 32,
+    ".*language_model\\.layers\\.6\\..*\\.q_proj$": 32,
+    ".*language_model\\.layers\\.6\\..*\\.up_proj$": 32,
+    ".*language_model\\.layers\\.6\\..*\\.v_proj$": 32,
+    ".*language_model\\.layers\\.7\\..*\\.down_proj$": 32,
+    ".*language_model\\.layers\\.7\\..*\\.gate_proj$": 32,
+    ".*language_model\\.layers\\.7\\..*\\.k_proj$": 32,
+    ".*language_model\\.layers\\.7\\..*\\.o_proj$": 32,
+    ".*language_model\\.layers\\.7\\..*\\.q_proj$": 32,
+    ".*language_model\\.layers\\.7\\..*\\.up_proj$": 32,
+    ".*language_model\\.layers\\.7\\..*\\.v_proj$": 32,
+    ".*language_model\\.layers\\.8\\..*\\.down_proj$": 64,
+    ".*language_model\\.layers\\.8\\..*\\.gate_proj$": 64,
+    ".*language_model\\.layers\\.8\\..*\\.k_proj$": 64,
+    ".*language_model\\.layers\\.8\\..*\\.o_proj$": 64,
+    ".*language_model\\.layers\\.8\\..*\\.q_proj$": 64,
+    ".*language_model\\.layers\\.8\\..*\\.up_proj$": 64,
+    ".*language_model\\.layers\\.8\\..*\\.v_proj$": 64,
+    ".*language_model\\.layers\\.9\\..*\\.down_proj$": 64,
+    ".*language_model\\.layers\\.9\\..*\\.gate_proj$": 64,
+    ".*language_model\\.layers\\.9\\..*\\.k_proj$": 64,
+    ".*language_model\\.layers\\.9\\..*\\.o_proj$": 64,
+    ".*language_model\\.layers\\.9\\..*\\.q_proj$": 64,
+    ".*language_model\\.layers\\.9\\..*\\.up_proj$": 64,
+    ".*language_model\\.layers\\.9\\..*\\.v_proj$": 64
+  },
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

pretrained_model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7efb2171b7aab204ef535093e4e87a372d530217b4671a7dd872ae903a29283
+size 231546504

pretrained_model/config.json

@@ -0,0 +1,115 @@
+{
+    "type": "pi05",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                6
+            ]
+        },
+        "observation.images.camera1": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        },
+        "observation.images.reference": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                480
+            ]
+        },
+        "observation.images.empty_camera_0": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                224,
+                224
+            ]
+        },
+        "observation.images.empty_camera_1": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                224,
+                224
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                6
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "use_peft": true,
+    "push_to_hub": true,
+    "repo_id": "HBOrtiz/pi05_eval3_objectvla",
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": "/home/shadeform/ckpts/warm_pg_v2_patched",
+    "paligemma_variant": "gemma_2b",
+    "action_expert_variant": "gemma_300m",
+    "dtype": "bfloat16",
+    "chunk_size": 50,
+    "n_action_steps": 50,
+    "max_state_dim": 32,
+    "max_action_dim": 32,
+    "num_inference_steps": 10,
+    "time_sampling_beta_alpha": 1.5,
+    "time_sampling_beta_beta": 1.0,
+    "time_sampling_scale": 0.999,
+    "time_sampling_offset": 0.001,
+    "min_period": 0.004,
+    "max_period": 4.0,
+    "use_relative_actions": false,
+    "relative_exclude_joints": [
+        "gripper"
+    ],
+    "action_feature_names": [
+        "shoulder_pan.pos",
+        "shoulder_lift.pos",
+        "elbow_flex.pos",
+        "wrist_flex.pos",
+        "wrist_roll.pos",
+        "gripper.pos"
+    ],
+    "rtc_config": null,
+    "image_resolution": [
+        224,
+        224
+    ],
+    "empty_cameras": 2,
+    "tokenizer_max_length": 200,
+    "normalization_mapping": {
+        "VISUAL": "IDENTITY",
+        "STATE": "QUANTILES",
+        "ACTION": "QUANTILES"
+    },
+    "gradient_checkpointing": true,
+    "compile_model": false,
+    "compile_mode": "max-autotune",
+    "freeze_vision_encoder": true,
+    "train_expert_only": false,
+    "optimizer_lr": 1e-05,
+    "optimizer_betas": [
+        0.9,
+        0.95
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 0.01,
+    "optimizer_grad_clip_norm": 1.0,
+    "scheduler_warmup_steps": 1000,
+    "scheduler_decay_steps": 30000,
+    "scheduler_decay_lr": 2.5e-06
+}

pretrained_model/policy_postprocessor.json

@@ -0,0 +1,38 @@
+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "unnormalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              6
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "IDENTITY",
+          "STATE": "QUANTILES",
+          "ACTION": "QUANTILES"
+        }
+      },
+      "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
+    },
+    {
+      "registry_name": "absolute_actions_processor",
+      "config": {
+        "enabled": false
+      }
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cpu",
+        "float_dtype": null
+      }
+    }
+  ]
+}

pretrained_model/policy_postprocessor_step_0_unnormalizer_processor.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1542e0f5f54eb21e9d354b5040f8ec941b32f7cc3ea19c3ccb4f5a14333858f8
+size 7608

pretrained_model/policy_preprocessor.json

@@ -0,0 +1,112 @@
+{
+  "name": "policy_preprocessor",
+  "steps": [
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {}
+      }
+    },
+    {
+      "registry_name": "to_batch_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "delta_actions_processor",
+      "config": {
+        "enabled": false,
+        "exclude_joints": [
+          "gripper"
+        ],
+        "action_names": [
+          "shoulder_pan.pos",
+          "shoulder_lift.pos",
+          "elbow_flex.pos",
+          "wrist_flex.pos",
+          "wrist_roll.pos",
+          "gripper.pos"
+        ]
+      }
+    },
+    {
+      "registry_name": "normalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "observation.state": {
+            "type": "STATE",
+            "shape": [
+              6
+            ]
+          },
+          "observation.images.camera1": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              480,
+              640
+            ]
+          },
+          "observation.images.reference": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              480,
+              480
+            ]
+          },
+          "observation.images.empty_camera_0": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              224,
+              224
+            ]
+          },
+          "observation.images.empty_camera_1": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              224,
+              224
+            ]
+          },
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              6
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "IDENTITY",
+          "STATE": "QUANTILES",
+          "ACTION": "QUANTILES"
+        }
+      },
+      "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
+    },
+    {
+      "registry_name": "pi05_prepare_state_tokenizer_processor_step",
+      "config": {}
+    },
+    {
+      "registry_name": "tokenizer_processor",
+      "config": {
+        "max_length": 200,
+        "task_key": "task",
+        "padding_side": "right",
+        "padding": "max_length",
+        "truncation": true,
+        "tokenizer_name": "google/paligemma-3b-pt-224"
+      }
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cuda",
+        "float_dtype": null
+      }
+    }
+  ]
+}

pretrained_model/policy_preprocessor_step_3_normalizer_processor.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1542e0f5f54eb21e9d354b5040f8ec941b32f7cc3ea19c3ccb4f5a14333858f8
+size 7608

pretrained_model/train_config.json

@@ -0,0 +1,270 @@
+{
+    "dataset": {
+        "repo_id": "HBOrtiz/so101_eval3_aug_v3_200celebs",
+        "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,
+        "streaming": false
+    },
+    "env": null,
+    "policy": {
+        "type": "pi05",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    6
+                ]
+            },
+            "observation.images.camera1": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            },
+            "observation.images.reference": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    480
+                ]
+            },
+            "observation.images.empty_camera_0": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    224,
+                    224
+                ]
+            },
+            "observation.images.empty_camera_1": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    224,
+                    224
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    6
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "use_peft": true,
+        "push_to_hub": true,
+        "repo_id": "HBOrtiz/pi05_eval3_objectvla",
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": "/home/shadeform/ckpts/warm_pg_v2_patched",
+        "paligemma_variant": "gemma_2b",
+        "action_expert_variant": "gemma_300m",
+        "dtype": "bfloat16",
+        "chunk_size": 50,
+        "n_action_steps": 50,
+        "max_state_dim": 32,
+        "max_action_dim": 32,
+        "num_inference_steps": 10,
+        "time_sampling_beta_alpha": 1.5,
+        "time_sampling_beta_beta": 1.0,
+        "time_sampling_scale": 0.999,
+        "time_sampling_offset": 0.001,
+        "min_period": 0.004,
+        "max_period": 4.0,
+        "use_relative_actions": false,
+        "relative_exclude_joints": [
+            "gripper"
+        ],
+        "action_feature_names": [
+            "shoulder_pan.pos",
+            "shoulder_lift.pos",
+            "elbow_flex.pos",
+            "wrist_flex.pos",
+            "wrist_roll.pos",
+            "gripper.pos"
+        ],
+        "rtc_config": null,
+        "image_resolution": [
+            224,
+            224
+        ],
+        "empty_cameras": 2,
+        "tokenizer_max_length": 200,
+        "normalization_mapping": {
+            "VISUAL": "IDENTITY",
+            "STATE": "QUANTILES",
+            "ACTION": "QUANTILES"
+        },
+        "gradient_checkpointing": true,
+        "compile_model": false,
+        "compile_mode": "max-autotune",
+        "freeze_vision_encoder": true,
+        "train_expert_only": false,
+        "optimizer_lr": 1e-05,
+        "optimizer_betas": [
+            0.9,
+            0.95
+        ],
+        "optimizer_eps": 1e-08,
+        "optimizer_weight_decay": 0.01,
+        "optimizer_grad_clip_norm": 1.0,
+        "scheduler_warmup_steps": 1000,
+        "scheduler_decay_steps": 30000,
+        "scheduler_decay_lr": 2.5e-06
+    },
+    "reward_model": null,
+    "output_dir": "outputs/pi05_track_2_objectvla",
+    "job_name": "pi05",
+    "resume": false,
+    "seed": 1000,
+    "cudnn_deterministic": false,
+    "num_workers": 24,
+    "batch_size": 24,
+    "prefetch_factor": 4,
+    "persistent_workers": true,
+    "steps": 30000,
+    "eval_freq": 20000,
+    "log_freq": 200,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 5000,
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 1e-05,
+        "weight_decay": 0.01,
+        "grad_clip_norm": 1.0,
+        "betas": [
+            0.9,
+            0.95
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": {
+        "type": "cosine_decay_with_warmup",
+        "num_warmup_steps": 1000,
+        "num_decay_steps": 30000,
+        "peak_lr": 1e-05,
+        "decay_lr": 2.5e-06
+    },
+    "eval": {
+        "n_episodes": 50,
+        "batch_size": 19,
+        "use_async_envs": true
+    },
+    "wandb": {
+        "enable": false,
+        "disable_artifact": false,
+        "project": "lerobot",
+        "entity": null,
+        "notes": null,
+        "run_id": null,
+        "mode": null,
+        "add_tags": true
+    },
+    "peft": {
+        "target_modules": [
+            "q_proj",
+            "k_proj",
+            "v_proj",
+            "o_proj",
+            "gate_proj",
+            "up_proj",
+            "down_proj"
+        ],
+        "full_training_modules": null,
+        "method_type": "LORA",
+        "init_type": null,
+        "r": 16,
+        "lora_alpha": 64
+    },
+    "sample_weighting": null,
+    "rename_map": {
+        "observation.images.camera1": "observation.images.right_wrist_0_rgb"
+    },
+    "checkpoint_path": null
+}