Upload folder using huggingface_hub

pretrained_model/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+tags:
+- base_model:adapter:/fsx/caroline_pascal/models/so101
+- 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 0.21.0

pretrained_model/adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Flux3Policy",
+    "parent_library": "lerobot.policies.flux3.modeling_flux3"
+  },
+  "base_model_name_or_path": "/fsx/caroline_pascal/models/so101",
+  "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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "dit.emb_in.action",
+    "dit.emb_in.action_cond",
+    "dit.final_layer.action",
+    "dit.final_layer.action_cond"
+  ],
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": ".*\\.(q_proj|k_proj|v_proj|attn_out|mlp_in|mlp_out)",
+  "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
+}

pretrained_model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b2864bbe5c195833e219c054ac237c8ea241780df4e181403f285cd4eb786b
+size 471701520

pretrained_model/config.json

@@ -0,0 +1,142 @@
+{
+    "type": "flux3",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.images.scene": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                256,
+                256
+            ]
+        },
+        "observation.images.wrist": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                256,
+                256
+            ]
+        },
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                6
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                6
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "use_peft": true,
+    "push_to_hub": false,
+    "repo_id": null,
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": "/fsx/caroline_pascal/models/so101",
+    "pretrained_revision": null,
+    "conditioning": "history",
+    "packer": null,
+    "condition_on_past_actions": false,
+    "action_representation": "delta",
+    "delta_absolute_dims": [
+        -1
+    ],
+    "text_fixed_length": 320,
+    "video_position_fps": 24.0,
+    "history_snapshots": 1,
+    "normalization_stats": null,
+    "normalization_clip": 6.0,
+    "separate_timesteps": true,
+    "video_logit_mean": 1.08,
+    "video_logit_std": 1.0,
+    "conditioning_noise_max": 0.2,
+    "loss_reduction": "modalities",
+    "action_channel_weights": [
+        1.0,
+        1.0,
+        1.0,
+        1.0,
+        1.0,
+        2.0
+    ],
+    "gradient_checkpointing": true,
+    "chunk_size": 32,
+    "n_action_steps": 30,
+    "fps": 30.0,
+    "camera_layout": "side_by_side",
+    "camera_keys": [
+        "observation.images.scene",
+        "observation.images.wrist"
+    ],
+    "canvas_hw": [
+        256,
+        512
+    ],
+    "action_modality": "action",
+    "action_scale": 2.0,
+    "gripper_flip_dims": [],
+    "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"
+    ],
+    "normalization_mapping": {
+        "VISUAL": "IDENTITY",
+        "STATE": "IDENTITY",
+        "ACTION": "IDENTITY"
+    },
+    "trunk_weights": null,
+    "video_vae_id": "/fsx/caroline_pascal/models/so101/components/video_vae.safetensors",
+    "text_encoder_id": "/fsx/caroline_pascal/models/so101/components/text_encoder",
+    "dit_config": null,
+    "content_streams": [
+        "video",
+        "video_cond"
+    ],
+    "attn_mode": "torch",
+    "dtype": "bfloat16",
+    "compile_model": false,
+    "sampler": "cosmos_unipc",
+    "num_inference_steps": 4,
+    "guidance_scale": 3.0,
+    "guidance_scale_action": null,
+    "sampler_shift": 5.0,
+    "inference_seed": 0,
+    "head_init_seed": 0,
+    "train_timestep_width": 0.75,
+    "train_timestep_shift": 42.0,
+    "action_loss_weight": 0.5,
+    "video_loss_weight": 1.0,
+    "caption_dropout": 0.1,
+    "augment": false,
+    "optimizer_lr": 0.0001,
+    "optimizer_lr_heads_multiplier": 5.0,
+    "optimizer_betas": [
+        0.9,
+        0.999
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 0.0,
+    "optimizer_grad_clip_norm": 1.0,
+    "scheduler_freeze_backbone_steps": 0,
+    "scheduler_warmup_steps": 0,
+    "scheduler_warmup_steps_heads": 0,
+    "scheduler_decay_steps": 0,
+    "scheduler_cooldown_steps": 0
+}

pretrained_model/policy_postprocessor.json

@@ -0,0 +1,24 @@
+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "flux3_action_history_unnormalizer",
+      "config": {
+        "action_dim": 6,
+        "action_representation": "delta",
+        "absolute_dims": [
+          -1
+        ],
+        "normalization_clip": 6.0
+      },
+      "state_file": "policy_postprocessor_step_0_flux3_action_history_unnormalizer.safetensors"
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cpu",
+        "float_dtype": null
+      }
+    }
+  ]
+}

pretrained_model/policy_postprocessor_step_0_flux3_action_history_unnormalizer.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96a5f8de8c33db904ba2cfadeac7a4477f64bca1e0a5bba8da6f4ed576ff4331
+size 184

pretrained_model/policy_preprocessor.json

@@ -0,0 +1,44 @@
+{
+  "name": "policy_preprocessor",
+  "steps": [
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {
+          "observation.images.on_top": "observation.images.scene",
+          "observation.images.camera_on_follower": "observation.images.wrist"
+        }
+      }
+    },
+    {
+      "registry_name": "to_batch_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cuda",
+        "float_dtype": null
+      }
+    },
+    {
+      "registry_name": "flux3_action_history_normalizer",
+      "config": {
+        "action_dim": 6,
+        "action_representation": "delta",
+        "absolute_dims": [
+          -1
+        ],
+        "normalization_clip": 6.0,
+        "n_obs_steps": 1,
+        "chunk_size": 32,
+        "camera_keys": [
+          "observation.images.scene",
+          "observation.images.wrist"
+        ],
+        "condition_on_past_actions": false
+      },
+      "state_file": "policy_preprocessor_step_3_flux3_action_history_normalizer.safetensors"
+    }
+  ]
+}

pretrained_model/policy_preprocessor_step_3_flux3_action_history_normalizer.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb0b16f0b7909cb2604c089e1fdda2caf34d7ea168574594a5f5cf673d326d97
+size 360

pretrained_model/train_config.json

@@ -0,0 +1,356 @@
+{
+    "dataset": {
+        "repo_id": "cetiennec/yellow_on_purple_super",
+        "repo_type": "dataset",
+        "root": null,
+        "episodes": null,
+        "exclude_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": "torchcodec",
+        "return_uint8": false,
+        "depth_output_unit": "mm",
+        "streaming": false,
+        "eval_split": 0.2
+    },
+    "env": null,
+    "policy": {
+        "type": "flux3",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.images.scene": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    256,
+                    256
+                ]
+            },
+            "observation.images.wrist": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    256,
+                    256
+                ]
+            },
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    6
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    6
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "use_peft": true,
+        "push_to_hub": false,
+        "repo_id": null,
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": "/fsx/caroline_pascal/models/so101",
+        "pretrained_revision": null,
+        "conditioning": "history",
+        "packer": null,
+        "condition_on_past_actions": false,
+        "action_representation": "delta",
+        "delta_absolute_dims": [
+            -1
+        ],
+        "text_fixed_length": 320,
+        "video_position_fps": 24.0,
+        "history_snapshots": 1,
+        "normalization_stats": null,
+        "normalization_clip": 6.0,
+        "separate_timesteps": true,
+        "video_logit_mean": 1.08,
+        "video_logit_std": 1.0,
+        "conditioning_noise_max": 0.2,
+        "loss_reduction": "modalities",
+        "action_channel_weights": [
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            2.0
+        ],
+        "gradient_checkpointing": true,
+        "chunk_size": 32,
+        "n_action_steps": 30,
+        "fps": 30.0,
+        "camera_layout": "side_by_side",
+        "camera_keys": [
+            "observation.images.scene",
+            "observation.images.wrist"
+        ],
+        "canvas_hw": [
+            256,
+            512
+        ],
+        "action_modality": "action",
+        "action_scale": 2.0,
+        "gripper_flip_dims": [],
+        "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"
+        ],
+        "normalization_mapping": {
+            "VISUAL": "IDENTITY",
+            "STATE": "IDENTITY",
+            "ACTION": "IDENTITY"
+        },
+        "trunk_weights": null,
+        "video_vae_id": "/fsx/caroline_pascal/models/so101/components/video_vae.safetensors",
+        "text_encoder_id": "/fsx/caroline_pascal/models/so101/components/text_encoder",
+        "dit_config": null,
+        "content_streams": [
+            "video",
+            "video_cond"
+        ],
+        "attn_mode": "torch",
+        "dtype": "bfloat16",
+        "compile_model": false,
+        "sampler": "cosmos_unipc",
+        "num_inference_steps": 4,
+        "guidance_scale": 3.0,
+        "guidance_scale_action": null,
+        "sampler_shift": 5.0,
+        "inference_seed": 0,
+        "head_init_seed": 0,
+        "train_timestep_width": 0.75,
+        "train_timestep_shift": 42.0,
+        "action_loss_weight": 0.5,
+        "video_loss_weight": 1.0,
+        "caption_dropout": 0.1,
+        "augment": false,
+        "optimizer_lr": 0.0001,
+        "optimizer_lr_heads_multiplier": 5.0,
+        "optimizer_betas": [
+            0.9,
+            0.999
+        ],
+        "optimizer_eps": 1e-08,
+        "optimizer_weight_decay": 0.0,
+        "optimizer_grad_clip_norm": 1.0,
+        "scheduler_freeze_backbone_steps": 0,
+        "scheduler_warmup_steps": 0,
+        "scheduler_warmup_steps_heads": 0,
+        "scheduler_decay_steps": 0,
+        "scheduler_cooldown_steps": 0
+    },
+    "reward_model": null,
+    "output_dir": "/fsx/caroline_pascal/outputs/yellow_on_purple_lora_4gpu",
+    "job_name": "flux3",
+    "resume": false,
+    "seed": 42,
+    "cudnn_deterministic": false,
+    "num_workers": 8,
+    "batch_size": 2,
+    "prefetch_factor": 4,
+    "persistent_workers": true,
+    "dataloader_multiprocessing_context": "spawn",
+    "steps": 10000,
+    "env_eval_freq": 0,
+    "log_freq": 20,
+    "eval_steps": 500,
+    "max_eval_samples": 0,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 500,
+    "checkpoint_format": "safetensors",
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 0.0001,
+        "weight_decay": 0.0,
+        "grad_clip_norm": 1.0,
+        "betas": [
+            0.9,
+            0.999
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": {
+        "type": "frozen_warmup_constant",
+        "num_warmup_steps": 0,
+        "freeze_steps": 0,
+        "warmup_steps_heads": 0,
+        "decay_steps": 0,
+        "cooldown_steps": 0
+    },
+    "parallelism": {
+        "dp_replicate": 4,
+        "dp_shard": 1,
+        "context_parallel": {
+            "ring_degree": 1,
+            "ulysses_degree": 1
+        },
+        "cfg_parallel": 1
+    },
+    "accelerator": {
+        "mixed_precision": "bf16",
+        "gradient_accumulation": {
+            "steps": 1
+        },
+        "fsdp": {
+            "reshard_after_forward": true,
+            "wrap_modules": null,
+            "min_num_params": null,
+            "cpu_offload": false,
+            "ignored_modules": null
+        },
+        "ddp": {
+            "find_unused_parameters": true,
+            "gradient_as_bucket_view": false,
+            "static_graph": false
+        },
+        "compile": {
+            "enabled": false,
+            "backend": "inductor",
+            "mode": null,
+            "regional": true
+        },
+        "activation_checkpointing": {
+            "mode": "none"
+        }
+    },
+    "eval": {
+        "n_episodes": 50,
+        "batch_size": 50,
+        "use_async_envs": true,
+        "recording": false,
+        "recording_repo_id": null,
+        "recording_private": false
+    },
+    "ema": {
+        "enable": true,
+        "decay": 0.999,
+        "update_after_step": 0,
+        "inv_gamma": 1.0,
+        "power": 0.75,
+        "min_decay": 0.0,
+        "max_decay": 0.9999,
+        "use_for_eval": true
+    },
+    "wandb": {
+        "enable": true,
+        "disable_artifact": false,
+        "project": "flux3-so101",
+        "entity": null,
+        "notes": null,
+        "run_id": "yrahmxpq",
+        "mode": null,
+        "add_tags": true
+    },
+    "peft": {
+        "target_modules": null,
+        "full_training_modules": null,
+        "method_type": "LORA",
+        "init_type": null,
+        "r": 32,
+        "lora_alpha": 32
+    },
+    "job": {
+        "target": null,
+        "image": "huggingface/lerobot-gpu:latest",
+        "timeout": "2d",
+        "detach": false,
+        "tags": []
+    },
+    "save_checkpoint_to_hub": false,
+    "sample_weighting": null,
+    "rename_map": {
+        "observation.images.on_top": "observation.images.scene",
+        "observation.images.camera_on_follower": "observation.images.wrist"
+    },
+    "checkpoint_path": null
+}

pretrained_model_ema/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+tags:
+- base_model:adapter:/fsx/caroline_pascal/models/so101
+- 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 0.21.0

pretrained_model_ema/adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Flux3Policy",
+    "parent_library": "lerobot.policies.flux3.modeling_flux3"
+  },
+  "base_model_name_or_path": "/fsx/caroline_pascal/models/so101",
+  "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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "dit.emb_in.action",
+    "dit.emb_in.action_cond",
+    "dit.final_layer.action",
+    "dit.final_layer.action_cond"
+  ],
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": ".*\\.(q_proj|k_proj|v_proj|attn_out|mlp_in|mlp_out)",
+  "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
+}

pretrained_model_ema/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9851a2cd8a7a877eca2c123af18e25cba7a9a469b9333d566cc2d58c99bac559
+size 471701520

pretrained_model_ema/config.json

@@ -0,0 +1,142 @@
+{
+    "type": "flux3",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.images.scene": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                256,
+                256
+            ]
+        },
+        "observation.images.wrist": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                256,
+                256
+            ]
+        },
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                6
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                6
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "use_peft": true,
+    "push_to_hub": false,
+    "repo_id": null,
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": "/fsx/caroline_pascal/models/so101",
+    "pretrained_revision": null,
+    "conditioning": "history",
+    "packer": null,
+    "condition_on_past_actions": false,
+    "action_representation": "delta",
+    "delta_absolute_dims": [
+        -1
+    ],
+    "text_fixed_length": 320,
+    "video_position_fps": 24.0,
+    "history_snapshots": 1,
+    "normalization_stats": null,
+    "normalization_clip": 6.0,
+    "separate_timesteps": true,
+    "video_logit_mean": 1.08,
+    "video_logit_std": 1.0,
+    "conditioning_noise_max": 0.2,
+    "loss_reduction": "modalities",
+    "action_channel_weights": [
+        1.0,
+        1.0,
+        1.0,
+        1.0,
+        1.0,
+        2.0
+    ],
+    "gradient_checkpointing": true,
+    "chunk_size": 32,
+    "n_action_steps": 30,
+    "fps": 30.0,
+    "camera_layout": "side_by_side",
+    "camera_keys": [
+        "observation.images.scene",
+        "observation.images.wrist"
+    ],
+    "canvas_hw": [
+        256,
+        512
+    ],
+    "action_modality": "action",
+    "action_scale": 2.0,
+    "gripper_flip_dims": [],
+    "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"
+    ],
+    "normalization_mapping": {
+        "VISUAL": "IDENTITY",
+        "STATE": "IDENTITY",
+        "ACTION": "IDENTITY"
+    },
+    "trunk_weights": null,
+    "video_vae_id": "/fsx/caroline_pascal/models/so101/components/video_vae.safetensors",
+    "text_encoder_id": "/fsx/caroline_pascal/models/so101/components/text_encoder",
+    "dit_config": null,
+    "content_streams": [
+        "video",
+        "video_cond"
+    ],
+    "attn_mode": "torch",
+    "dtype": "bfloat16",
+    "compile_model": false,
+    "sampler": "cosmos_unipc",
+    "num_inference_steps": 4,
+    "guidance_scale": 3.0,
+    "guidance_scale_action": null,
+    "sampler_shift": 5.0,
+    "inference_seed": 0,
+    "head_init_seed": 0,
+    "train_timestep_width": 0.75,
+    "train_timestep_shift": 42.0,
+    "action_loss_weight": 0.5,
+    "video_loss_weight": 1.0,
+    "caption_dropout": 0.1,
+    "augment": false,
+    "optimizer_lr": 0.0001,
+    "optimizer_lr_heads_multiplier": 5.0,
+    "optimizer_betas": [
+        0.9,
+        0.999
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 0.0,
+    "optimizer_grad_clip_norm": 1.0,
+    "scheduler_freeze_backbone_steps": 0,
+    "scheduler_warmup_steps": 0,
+    "scheduler_warmup_steps_heads": 0,
+    "scheduler_decay_steps": 0,
+    "scheduler_cooldown_steps": 0
+}

pretrained_model_ema/policy_postprocessor.json

@@ -0,0 +1,24 @@
+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "flux3_action_history_unnormalizer",
+      "config": {
+        "action_dim": 6,
+        "action_representation": "delta",
+        "absolute_dims": [
+          -1
+        ],
+        "normalization_clip": 6.0
+      },
+      "state_file": "policy_postprocessor_step_0_flux3_action_history_unnormalizer.safetensors"
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cpu",
+        "float_dtype": null
+      }
+    }
+  ]
+}

pretrained_model_ema/policy_postprocessor_step_0_flux3_action_history_unnormalizer.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96a5f8de8c33db904ba2cfadeac7a4477f64bca1e0a5bba8da6f4ed576ff4331
+size 184

pretrained_model_ema/policy_preprocessor.json

@@ -0,0 +1,44 @@
+{
+  "name": "policy_preprocessor",
+  "steps": [
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {
+          "observation.images.on_top": "observation.images.scene",
+          "observation.images.camera_on_follower": "observation.images.wrist"
+        }
+      }
+    },
+    {
+      "registry_name": "to_batch_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cuda",
+        "float_dtype": null
+      }
+    },
+    {
+      "registry_name": "flux3_action_history_normalizer",
+      "config": {
+        "action_dim": 6,
+        "action_representation": "delta",
+        "absolute_dims": [
+          -1
+        ],
+        "normalization_clip": 6.0,
+        "n_obs_steps": 1,
+        "chunk_size": 32,
+        "camera_keys": [
+          "observation.images.scene",
+          "observation.images.wrist"
+        ],
+        "condition_on_past_actions": false
+      },
+      "state_file": "policy_preprocessor_step_3_flux3_action_history_normalizer.safetensors"
+    }
+  ]
+}

pretrained_model_ema/policy_preprocessor_step_3_flux3_action_history_normalizer.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb0b16f0b7909cb2604c089e1fdda2caf34d7ea168574594a5f5cf673d326d97
+size 360

pretrained_model_ema/train_config.json

@@ -0,0 +1,356 @@
+{
+    "dataset": {
+        "repo_id": "cetiennec/yellow_on_purple_super",
+        "repo_type": "dataset",
+        "root": null,
+        "episodes": null,
+        "exclude_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": "torchcodec",
+        "return_uint8": false,
+        "depth_output_unit": "mm",
+        "streaming": false,
+        "eval_split": 0.2
+    },
+    "env": null,
+    "policy": {
+        "type": "flux3",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.images.scene": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    256,
+                    256
+                ]
+            },
+            "observation.images.wrist": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    256,
+                    256
+                ]
+            },
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    6
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    6
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "use_peft": true,
+        "push_to_hub": false,
+        "repo_id": null,
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": "/fsx/caroline_pascal/models/so101",
+        "pretrained_revision": null,
+        "conditioning": "history",
+        "packer": null,
+        "condition_on_past_actions": false,
+        "action_representation": "delta",
+        "delta_absolute_dims": [
+            -1
+        ],
+        "text_fixed_length": 320,
+        "video_position_fps": 24.0,
+        "history_snapshots": 1,
+        "normalization_stats": null,
+        "normalization_clip": 6.0,
+        "separate_timesteps": true,
+        "video_logit_mean": 1.08,
+        "video_logit_std": 1.0,
+        "conditioning_noise_max": 0.2,
+        "loss_reduction": "modalities",
+        "action_channel_weights": [
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            2.0
+        ],
+        "gradient_checkpointing": true,
+        "chunk_size": 32,
+        "n_action_steps": 30,
+        "fps": 30.0,
+        "camera_layout": "side_by_side",
+        "camera_keys": [
+            "observation.images.scene",
+            "observation.images.wrist"
+        ],
+        "canvas_hw": [
+            256,
+            512
+        ],
+        "action_modality": "action",
+        "action_scale": 2.0,
+        "gripper_flip_dims": [],
+        "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"
+        ],
+        "normalization_mapping": {
+            "VISUAL": "IDENTITY",
+            "STATE": "IDENTITY",
+            "ACTION": "IDENTITY"
+        },
+        "trunk_weights": null,
+        "video_vae_id": "/fsx/caroline_pascal/models/so101/components/video_vae.safetensors",
+        "text_encoder_id": "/fsx/caroline_pascal/models/so101/components/text_encoder",
+        "dit_config": null,
+        "content_streams": [
+            "video",
+            "video_cond"
+        ],
+        "attn_mode": "torch",
+        "dtype": "bfloat16",
+        "compile_model": false,
+        "sampler": "cosmos_unipc",
+        "num_inference_steps": 4,
+        "guidance_scale": 3.0,
+        "guidance_scale_action": null,
+        "sampler_shift": 5.0,
+        "inference_seed": 0,
+        "head_init_seed": 0,
+        "train_timestep_width": 0.75,
+        "train_timestep_shift": 42.0,
+        "action_loss_weight": 0.5,
+        "video_loss_weight": 1.0,
+        "caption_dropout": 0.1,
+        "augment": false,
+        "optimizer_lr": 0.0001,
+        "optimizer_lr_heads_multiplier": 5.0,
+        "optimizer_betas": [
+            0.9,
+            0.999
+        ],
+        "optimizer_eps": 1e-08,
+        "optimizer_weight_decay": 0.0,
+        "optimizer_grad_clip_norm": 1.0,
+        "scheduler_freeze_backbone_steps": 0,
+        "scheduler_warmup_steps": 0,
+        "scheduler_warmup_steps_heads": 0,
+        "scheduler_decay_steps": 0,
+        "scheduler_cooldown_steps": 0
+    },
+    "reward_model": null,
+    "output_dir": "/fsx/caroline_pascal/outputs/yellow_on_purple_lora_4gpu",
+    "job_name": "flux3",
+    "resume": false,
+    "seed": 42,
+    "cudnn_deterministic": false,
+    "num_workers": 8,
+    "batch_size": 2,
+    "prefetch_factor": 4,
+    "persistent_workers": true,
+    "dataloader_multiprocessing_context": "spawn",
+    "steps": 10000,
+    "env_eval_freq": 0,
+    "log_freq": 20,
+    "eval_steps": 500,
+    "max_eval_samples": 0,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 500,
+    "checkpoint_format": "safetensors",
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 0.0001,
+        "weight_decay": 0.0,
+        "grad_clip_norm": 1.0,
+        "betas": [
+            0.9,
+            0.999
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": {
+        "type": "frozen_warmup_constant",
+        "num_warmup_steps": 0,
+        "freeze_steps": 0,
+        "warmup_steps_heads": 0,
+        "decay_steps": 0,
+        "cooldown_steps": 0
+    },
+    "parallelism": {
+        "dp_replicate": 4,
+        "dp_shard": 1,
+        "context_parallel": {
+            "ring_degree": 1,
+            "ulysses_degree": 1
+        },
+        "cfg_parallel": 1
+    },
+    "accelerator": {
+        "mixed_precision": "bf16",
+        "gradient_accumulation": {
+            "steps": 1
+        },
+        "fsdp": {
+            "reshard_after_forward": true,
+            "wrap_modules": null,
+            "min_num_params": null,
+            "cpu_offload": false,
+            "ignored_modules": null
+        },
+        "ddp": {
+            "find_unused_parameters": true,
+            "gradient_as_bucket_view": false,
+            "static_graph": false
+        },
+        "compile": {
+            "enabled": false,
+            "backend": "inductor",
+            "mode": null,
+            "regional": true
+        },
+        "activation_checkpointing": {
+            "mode": "none"
+        }
+    },
+    "eval": {
+        "n_episodes": 50,
+        "batch_size": 50,
+        "use_async_envs": true,
+        "recording": false,
+        "recording_repo_id": null,
+        "recording_private": false
+    },
+    "ema": {
+        "enable": true,
+        "decay": 0.999,
+        "update_after_step": 0,
+        "inv_gamma": 1.0,
+        "power": 0.75,
+        "min_decay": 0.0,
+        "max_decay": 0.9999,
+        "use_for_eval": true
+    },
+    "wandb": {
+        "enable": true,
+        "disable_artifact": false,
+        "project": "flux3-so101",
+        "entity": null,
+        "notes": null,
+        "run_id": "yrahmxpq",
+        "mode": null,
+        "add_tags": true
+    },
+    "peft": {
+        "target_modules": null,
+        "full_training_modules": null,
+        "method_type": "LORA",
+        "init_type": null,
+        "r": 32,
+        "lora_alpha": 32
+    },
+    "job": {
+        "target": null,
+        "image": "huggingface/lerobot-gpu:latest",
+        "timeout": "2d",
+        "detach": false,
+        "tags": []
+    },
+    "save_checkpoint_to_hub": false,
+    "sample_weighting": null,
+    "rename_map": {
+        "observation.images.on_top": "observation.images.scene",
+        "observation.images.camera_on_follower": "observation.images.wrist"
+    },
+    "checkpoint_path": null
+}

training_state/ema_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da5c64d177af0aa512b05b41af22f72a6ba56443deb694e029ed7d09dc463d0
+size 547442891

training_state/optimizer_param_groups.json

@@ -0,0 +1,682 @@
+[
+    {
+        "lr": 0.0001,
+        "betas": [
+            0.9,
+            0.999
+        ],
+        "eps": 1e-08,
+        "weight_decay": 0.0,
+        "amsgrad": false,
+        "maximize": false,
+        "foreach": null,
+        "capturable": false,
+        "differentiable": false,
+        "fused": null,
+        "decoupled_weight_decay": true,
+        "initial_lr": 0.0001,
+        "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,
+            240,
+            241,
+            242,
+            243,
+            244,
+            245,
+            246,
+            247,
+            248,
+            249,
+            250,
+            251,
+            252,
+            253,
+            254,
+            255,
+            256,
+            257,
+            258,
+            259,
+            260,
+            261,
+            262,
+            263,
+            264,
+            265,
+            266,
+            267,
+            268,
+            269,
+            270,
+            271,
+            272,
+            273,
+            274,
+            275,
+            276,
+            277,
+            278,
+            279,
+            280,
+            281,
+            282,
+            283,
+            284,
+            285,
+            286,
+            287,
+            288,
+            289,
+            290,
+            291,
+            292,
+            293,
+            294,
+            295,
+            296,
+            297,
+            298,
+            299,
+            300,
+            301,
+            302,
+            303,
+            304,
+            305,
+            306,
+            307,
+            308,
+            309,
+            310,
+            311,
+            312,
+            313,
+            314,
+            315,
+            316,
+            317,
+            318,
+            319,
+            320,
+            321,
+            322,
+            323,
+            324,
+            325,
+            326,
+            327,
+            328,
+            329,
+            330,
+            331,
+            332,
+            333,
+            334,
+            335,
+            336,
+            337,
+            338,
+            339,
+            340,
+            341,
+            342,
+            343,
+            344,
+            345,
+            346,
+            347,
+            348,
+            349,
+            350,
+            351,
+            352,
+            353,
+            354,
+            355,
+            356,
+            357,
+            358,
+            359,
+            360,
+            361,
+            362,
+            363,
+            364,
+            365,
+            366,
+            367,
+            368,
+            369,
+            370,
+            371,
+            372,
+            373,
+            374,
+            375,
+            376,
+            377,
+            378,
+            379,
+            380,
+            381,
+            382,
+            383,
+            384,
+            385,
+            386,
+            387,
+            388,
+            389,
+            390,
+            391,
+            392,
+            393,
+            394,
+            395,
+            396,
+            397,
+            398,
+            399,
+            400,
+            401,
+            402,
+            403,
+            404,
+            405,
+            406,
+            407,
+            408,
+            409,
+            410,
+            411,
+            412,
+            413,
+            414,
+            415,
+            416,
+            417,
+            418,
+            419,
+            420,
+            421,
+            422,
+            423,
+            424,
+            425,
+            426,
+            427,
+            428,
+            429,
+            430,
+            431,
+            432,
+            433,
+            434,
+            435,
+            436,
+            437,
+            438,
+            439,
+            440,
+            441,
+            442,
+            443,
+            444,
+            445,
+            446,
+            447,
+            448,
+            449,
+            450,
+            451,
+            452,
+            453,
+            454,
+            455,
+            456,
+            457,
+            458,
+            459,
+            460,
+            461,
+            462,
+            463,
+            464,
+            465,
+            466,
+            467,
+            468,
+            469,
+            470,
+            471,
+            472,
+            473,
+            474,
+            475,
+            476,
+            477,
+            478,
+            479,
+            480,
+            481,
+            482,
+            483,
+            484,
+            485,
+            486,
+            487,
+            488,
+            489,
+            490,
+            491,
+            492,
+            493,
+            494,
+            495,
+            496,
+            497,
+            498,
+            499,
+            500,
+            501,
+            502,
+            503,
+            504,
+            505,
+            506,
+            507,
+            508,
+            509,
+            510,
+            511,
+            512,
+            513,
+            514,
+            515,
+            516,
+            517,
+            518,
+            519,
+            520,
+            521,
+            522,
+            523,
+            524,
+            525,
+            526,
+            527,
+            528,
+            529,
+            530,
+            531,
+            532,
+            533,
+            534,
+            535,
+            536,
+            537,
+            538,
+            539,
+            540,
+            541,
+            542,
+            543,
+            544,
+            545,
+            546,
+            547,
+            548,
+            549,
+            550,
+            551,
+            552,
+            553,
+            554,
+            555,
+            556,
+            557,
+            558,
+            559,
+            560,
+            561,
+            562,
+            563,
+            564,
+            565,
+            566,
+            567,
+            568,
+            569,
+            570,
+            571,
+            572,
+            573,
+            574,
+            575,
+            576,
+            577,
+            578,
+            579,
+            580,
+            581,
+            582,
+            583,
+            584,
+            585,
+            586,
+            587,
+            588,
+            589,
+            590,
+            591,
+            592,
+            593,
+            594,
+            595,
+            596,
+            597,
+            598,
+            599,
+            600,
+            601,
+            602,
+            603,
+            604,
+            605,
+            606,
+            607,
+            608,
+            609,
+            610,
+            611,
+            612,
+            613,
+            614,
+            615,
+            616,
+            617,
+            618,
+            619,
+            620,
+            621,
+            622,
+            623,
+            624,
+            625,
+            626,
+            627,
+            628,
+            629,
+            630,
+            631,
+            632,
+            633,
+            634,
+            635
+        ]
+    },
+    {
+        "lr": 0.0005,
+        "betas": [
+            0.9,
+            0.999
+        ],
+        "eps": 1e-08,
+        "weight_decay": 0.0,
+        "amsgrad": false,
+        "maximize": false,
+        "foreach": null,
+        "capturable": false,
+        "differentiable": false,
+        "fused": null,
+        "decoupled_weight_decay": true,
+        "initial_lr": 0.0005,
+        "params": [
+            636,
+            637,
+            638,
+            639,
+            640,
+            641
+        ]
+    }
+]

training_state/optimizer_state.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89eda11cf42a76e0612883a045c333f4f1575b336d48d4df0959b8133f910649
+size 867827728

training_state/rng_state.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51172596e3acf80eeb60a0fd69cef8acefa7d746e0d6617d755dcff382548f8e
+size 15708

training_state/scheduler_state.json

@@ -0,0 +1,18 @@
+{
+    "base_lrs": [
+        0.0001,
+        0.0005
+    ],
+    "last_epoch": 10000,
+    "_step_count": 10001,
+    "_is_initial": false,
+    "_get_lr_called_within_step": false,
+    "_last_lr": [
+        0.0001,
+        0.0005
+    ],
+    "lr_lambdas": [
+        null,
+        null
+    ]
+}

training_state/training_step.json

@@ -0,0 +1,12 @@
+{
+    "step": 10000,
+    "dp_world_size": 4,
+    "batch_size": 2,
+    "grad_accum_steps": 1,
+    "parallelism": {
+        "dp_replicate": 4,
+        "dp_shard": 1,
+        "ring_degree": 1,
+        "ulysses_degree": 1
+    }
+}