Upload folder using huggingface_hub

.gitattributes

@@ -44,3 +44,5 @@ deadly_corridor_fix_latency_6_1000ep_7k2steps_single_baseline/wandb/wandb/run-20
 deadly_corridor_fix_latency_6_1000ep_7k2steps_single_baseline/wandb/wandb/run-20260726_123335-0b3r9ly8/run-0b3r9ly8.wandb filter=lfs diff=lfs merge=lfs -text
 demon_attack_fix_latency_6_200ep_7k2steps_single_baseline/wandb/wandb/run-20260726_024003-61qjyp27/run-61qjyp27.wandb filter=lfs diff=lfs merge=lfs -text
 demon_attack_fix_latency_6_200ep_7k2steps_single_baseline/wandb/wandb/run-20260726_123618-3aeecfjc/run-3aeecfjc.wandb filter=lfs diff=lfs merge=lfs -text
+flappy_fix_latency_3_200ep_7k2steps_stitch/wandb/wandb/run-20260726_075412-klqpptni/run-klqpptni.wandb filter=lfs diff=lfs merge=lfs -text
+flappy_fix_latency_3_200ep_7k2steps_stitch/wandb/wandb/run-20260726_161939-az1orhy4/run-az1orhy4.wandb filter=lfs diff=lfs merge=lfs -text

flappy_fix_latency_3_200ep_7k2steps_stitch/checkpoints/steps_4000_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e67f12ecb33b6c95262f0bdc9bda384c1f2fe6068c1dfbf4b3be48c0b852ba6f
+size 9784896838

flappy_fix_latency_3_200ep_7k2steps_stitch/checkpoints/steps_4000_state/latest

@@ -0,0 +1 @@
+pytorch_model

flappy_fix_latency_3_200ep_7k2steps_stitch/checkpoints/steps_4000_state/pytorch_model/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ee0260eb9e2f3dc51c0bf4db388b35181f99da08ca44de9e1f5b2c58f5a43ff
+size 9007152504

flappy_fix_latency_3_200ep_7k2steps_stitch/checkpoints/steps_4000_state/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fa3dd57147994c7e97d01d958f099b9f86df9990a1b6696c7f3f2cff6f8f624
+size 14604

flappy_fix_latency_3_200ep_7k2steps_stitch/checkpoints/steps_4000_state/random_states_1.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c820e726a7197487f0858f22258b17303f76fe2b582b67702973facfaf8e27ef
+size 14604

flappy_fix_latency_3_200ep_7k2steps_stitch/checkpoints/steps_4000_state/zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

flappy_fix_latency_3_200ep_7k2steps_stitch/config.full.yaml

@@ -0,0 +1,254 @@
+framework:
+  name: QwenOFT
+  qwenvl:
+    base_vlm: /lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/playground/Pretrained_models/Qwen3-VL-4B-Instruct
+    attn_implementation: flash_attention_2
+    flex_backend: triton
+    enable_gradient_checkpointing: true
+  action_model:
+    action_model_type: MLP
+    action_dim: 7
+    action_hidden_dim: 2560
+    future_action_window_size: 0
+    past_action_window_size: 0
+    loss_type: discrete_ce
+    state_dim: 7
+    action_horizon: 1
+    action_env_dim: 2
+  kv_memory:
+    enabled: false
+    window: 4
+    rollout_len: 8
+    packed_train: false
+    rebased_sink: true
+datasets:
+  vla_data:
+    dataset_py: lerobot_datasets
+    include_state: true
+    data_root_dir: /lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/data/memory/flappy_fix_latency_3_200ep_7k2steps
+    data_mix: flappy_train__bridge
+    eval_data_mix: flappy_train__bridge__val
+    custom_mixtures_path: null
+    action_type: discrete
+    sequential_step_sampling: false
+    eval_sequential_step_sampling: null
+    num_workers: 8
+    eval_num_workers: 8
+    prefetch_factor: 4
+    persistent_workers: true
+    pin_memory: true
+    shuffle: true
+    action_balance:
+      enabled: false
+      strategy: balanced_epoch
+      action_key: action_id
+      target_flap_fraction: 0.3
+      noop_id: 0
+      flap_id: 1
+    latency_curriculum:
+      enabled: false
+      strategy: exclusive
+      latencies: null
+      phase_steps: null
+      phase_distributions: null
+      new_latency_passes: 1.0
+      replay_passes: 0.25
+      target_total_passes: 2.0
+      final_equalization: true
+      step_budget_mode: auto
+      eval_at_phase_end: false
+      save_at_phase_end: false
+      computed_plan: null
+    per_device_batch_size: 8
+    load_all_data_for_training: true
+    num_obs_frames: 4
+    image_mode: stitch
+    prompt_mode: raw
+    stitch_grid:
+    - 2
+    - 2
+    obs_image_size: null
+    video_backend: torchvision_av
+dataset:
+  source_hf: ''
+  config_name: null
+  source_subdir: null
+  converted_name: flappy_train
+  single_source_hf: ''
+  mixed_source_hf: ''
+  single_converted_name: flappy_train
+  mixed_converted_name: flappy_mixed_latency_train
+  single_latency_filter: null
+  mixed_latency_filter: null
+  force_download: false
+  setup_force: false
+  skip_verification: false
+  target_latency_unit: raw_frames
+  verify_rows: 200
+  max_episodes: null
+  episodes_per_latency: null
+  latency_filter: null
+  debug_subset:
+    enabled: false
+    max_episodes: 5
+    suffix: debug
+base_model:
+  repo_id: Qwen/Qwen3-VL-4B-Instruct
+initialization:
+  checkpoint_local_dir: playground/Pretrained_models/Qwen3VL-OFT-Bridge-RT-1
+  checkpoint_hf_repo_id: StarVLA/Qwen3VL-OFT-Bridge-RT-1
+  checkpoint_filename: checkpoints/steps_5000_pytorch_model.pt
+trainer:
+  max_train_steps: 4000
+  num_warmup_steps: 100
+  save_interval: 500
+  eval_interval: 250
+  eval_num_batches: 50
+  per_latency_eval_num_batches: null
+  eval_action_classification: false
+  eval_action_classification_interval: null
+  cc_f1_tolerance: 1
+  learning_rate:
+    base: 2.0e-05
+    qwen_vl_interface: 1.0e-05
+    action_model: 0.0001
+  lr_scheduler_type: cosine_with_min_lr
+  scheduler_specific_kwargs:
+    min_lr: 1.0e-06
+  freeze_modules: ''
+  freeze_vit: false
+  freeze_tied_embedding: false
+  freeze_llm_layers: []
+  loss_scale:
+    vla: 1.0
+    vlm: 0.1
+  max_grad_norm: 1.0
+  weight_decay: 0.0
+  logging_frequency: 1
+  profile_timing:
+    enabled: false
+    log_interval: 10
+  gradient_clipping: 1.0
+  gradient_accumulation_steps: 16
+  distributed_backend: deepspeed
+  is_resume: true
+  pretrained_checkpoint: /lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/checkpoints/steps_2000_state
+  resume_step: 2000
+  reload_modules: null
+  optimizer:
+    name: AdamW
+    betas:
+    - 0.9
+    - 0.95
+    eps: 1.0e-08
+    weight_decay: 1.0e-08
+    fused: true
+  save_format: pt
+workspace_dir: WORKSPACE_DIR
+run_root_dir: /lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints
+seed: 42
+wandb_entity: zihanwang-ai-northwestern-university
+wandb_project: starVLA_rl_games
+auth:
+  env_file: null
+  hf_token_env: HF_TOKEN
+  wandb_api_key_env: WANDB_API_KEY
+paths:
+  run_root_dir: results/Checkpoints
+  dataset_local_dir: data/memory/flappy_fix_latency_3_200ep_7k2steps
+  dataset_cache_dir: null
+  base_model_dir: playground/Pretrained_models/Qwen3-VL-4B-Instruct
+  accelerate_config: starVLA/config/deepseeds/deepspeed_zero2.yaml
+launch:
+  use_accelerate: true
+  gpus: null
+  num_processes: 1
+  dry_run: false
+conda:
+  enabled: true
+  env_name: null
+rl_games:
+  model_alias: openvla
+  env_eval:
+    image_size: 224
+    frameskip: 1
+    image_transform: raw_rgb
+    prompt_mode: raw
+    ghost_trail:
+      history_frames: 5
+      gamma: 1.3
+      min_alpha: 35
+      scroll_px_per_step: 4.0
+      ground_fraction: 0.22
+    seed: 42
+    fixed_episode_seeds: true
+    latency_seed_stride: 0
+    task_seed_stride: 0
+    task_description: ''
+    eval_parallel_envs: 5
+    action_chunk_execution:
+      enabled: false
+      chunk_size: null
+    enabled: true
+    eval_backend: latency_bench
+    distributed_mode: rank_sharded
+    vectorized:
+      enabled: false
+      batch_size: 1
+    latency:
+      prompt_map_path: /lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/data/memory/flappy_fix_latency_3_200ep_7k2steps/flappy_train__bridge/latency_prompt_map.json
+      mode: single
+      values:
+      - 0
+    mid_train:
+      enabled: true
+      interval_steps: 250
+      latencies:
+      - 3
+      num_episodes: 20
+      max_steps_per_episode: 3600
+    post_train:
+      enabled: true
+      latencies:
+      - 3
+      num_episodes: 50
+      max_steps_per_episode: 3600
+  task: flappy
+  initialization_mode: bridge
+  action_carrier: bridge
+model: openvla
+env: flappy
+init: bridge
+bridge_base_model:
+  repo_id:
+    openvla: Qwen/Qwen3-VL-4B-Instruct
+    pi0: StarVLA/Qwen2.5-VL-3B-Instruct-Action
+    pi05: Qwen/Qwen3-VL-4B-Instruct
+    gr00t: Qwen/Qwen3-VL-4B-Instruct
+  local_dir:
+    openvla: playground/Pretrained_models/Qwen3-VL-4B-Instruct
+    pi0: playground/Pretrained_models/Qwen2.5-VL-3B-Instruct-Action
+    pi05: playground/Pretrained_models/Qwen3-VL-4B-Instruct
+    gr00t: playground/Pretrained_models/Qwen3-VL-4B-Instruct
+mode: single
+checkpoint:
+  load: auto
+  hf_repo_id: null
+  save_best_model: false
+  save_final_model: true
+  save_pt_file: false
+  save_training_state: true
+  save_safetensors_file: true
+  local:
+    keep_last_n: 1
+  sync:
+    enabled: false
+    repo_id: null
+    keep_last_n: 0
+    sync_every_n_checkpoints: 1
+    resume_policy: local_latest
+run_id: flappy_fix_latency_3_200ep_7k2steps_stitch
+output_dir: /lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch
+config_yaml: null
+is_debug: false
+version_id: '0.21'

flappy_fix_latency_3_200ep_7k2steps_stitch/config.yaml

@@ -0,0 +1,103 @@
+checkpoint:
+  local:
+    keep_last_n: 1
+  save_best_model: false
+  save_final_model: true
+  save_pt_file: false
+  save_safetensors_file: true
+  save_training_state: true
+  sync:
+    enabled: false
+    keep_last_n: 0
+    repo_id: null
+datasets:
+  vla_data:
+    data_mix: flappy_train__bridge
+    dataset_py: lerobot_datasets
+    eval_data_mix: flappy_train__bridge__val
+    latency_curriculum:
+      enabled: false
+    obs_image_size: null
+    per_device_batch_size: 8
+framework:
+  action_model:
+    action_dim: 7
+    action_env_dim: 2
+    action_hidden_dim: 2560
+    action_horizon: 1
+    action_model_type: MLP
+    loss_type: discrete_ce
+  kv_memory:
+    enabled: false
+    packed_train: false
+    rebased_sink: true
+    rollout_len: 8
+    window: 4
+  name: QwenOFT
+  qwenvl:
+    attn_implementation: flash_attention_2
+    base_vlm: /lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/playground/Pretrained_models/Qwen3-VL-4B-Instruct
+    enable_gradient_checkpointing: true
+output_dir: /lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch
+rl_games:
+  env_eval:
+    distributed_mode: rank_sharded
+    enabled: true
+    eval_backend: latency_bench
+    eval_parallel_envs: 5
+    fixed_episode_seeds: true
+    image_size: 224
+    image_transform: raw_rgb
+    latency:
+      prompt_map_path: /lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/data/memory/flappy_fix_latency_3_200ep_7k2steps/flappy_train__bridge/latency_prompt_map.json
+    mid_train:
+      enabled: true
+      interval_steps: 250
+      latencies:
+      - 3
+      max_steps_per_episode: 3600
+      num_episodes: 20
+    prompt_mode: raw
+    seed: 42
+  model_alias: openvla
+  task: flappy
+run_id: flappy_fix_latency_3_200ep_7k2steps_stitch
+run_root_dir: /lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints
+seed: 42
+trainer:
+  distributed_backend: deepspeed
+  eval_action_classification: false
+  eval_action_classification_interval: null
+  eval_interval: 250
+  eval_num_batches: 50
+  freeze_llm_layers: []
+  freeze_modules: ''
+  freeze_tied_embedding: false
+  freeze_vit: false
+  gradient_accumulation_steps: 16
+  is_resume: true
+  learning_rate:
+    action_model: 0.0001
+    base: 2.0e-05
+    qwen_vl_interface: 1.0e-05
+  logging_frequency: 1
+  lr_scheduler_type: cosine_with_min_lr
+  max_train_steps: 4000
+  num_warmup_steps: 100
+  optimizer:
+    betas:
+    - 0.9
+    - 0.95
+    eps: 1.0e-08
+    fused: true
+    weight_decay: 1.0e-08
+  per_latency_eval_num_batches: null
+  pretrained_checkpoint: /lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/checkpoints/steps_2000_state
+  profile_timing:
+    enabled: false
+  resume_step: 2000
+  save_interval: 500
+  scheduler_specific_kwargs:
+    min_lr: 1.0e-06
+wandb_entity: zihanwang-ai-northwestern-university
+wandb_project: starVLA_rl_games

flappy_fix_latency_3_200ep_7k2steps_stitch/dataset_statistics.json

@@ -0,0 +1,127 @@
+{
+  "new_embodiment": {
+    "action": {
+      "mean": [
+        0.8235060572624207,
+        0.17649392783641815,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "std": [
+        0.3809901773929596,
+        0.3809901773929596,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "max": [
+        1.0,
+        1.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "min": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q01": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q99": [
+        1.0,
+        1.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "mask": [
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        true
+      ]
+    },
+    "state": {
+      "mean": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "std": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "max": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "min": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q01": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q99": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ]
+    },
+    "num_transitions": 1393742,
+    "num_trajectories": 198
+  }
+}

flappy_fix_latency_3_200ep_7k2steps_stitch/dataset_statistics_eval.json

@@ -0,0 +1,127 @@
+{
+  "new_embodiment": {
+    "action": {
+      "mean": [
+        0.8237500190734863,
+        0.17624999582767487,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "std": [
+        0.3810042142868042,
+        0.3810042142868042,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "max": [
+        1.0,
+        1.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "min": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q01": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q99": [
+        1.0,
+        1.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "mask": [
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        true
+      ]
+    },
+    "state": {
+      "mean": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "std": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "max": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "min": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q01": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "q99": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ]
+    },
+    "num_transitions": 14400,
+    "num_trajectories": 2
+  }
+}

flappy_fix_latency_3_200ep_7k2steps_stitch/eval/mid_train/step_1000.json

@@ -0,0 +1,120 @@
+{
+  "per_latency": {
+    "flappy/latency_3": {
+      "latency": 3,
+      "num_episodes": 20,
+      "mean_reward": 2.0000000447034836,
+      "mean_length": 31.0,
+      "std_reward": 0.0,
+      "std_length": 0.0,
+      "episode_rewards": [
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836
+      ],
+      "episode_lengths": [
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31
+      ],
+      "decoded_action_hist": {},
+      "fixed_episode_seeds": true,
+      "eval_seed": 42,
+      "episode_seeds": [
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null
+      ],
+      "episode_indices": [
+        0,
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19
+      ]
+    }
+  },
+  "aggregate": {
+    "stage": "mid_train",
+    "step": 1000,
+    "task": "flappy",
+    "model_alias": "openvla",
+    "fixed_episode_seeds": true,
+    "eval_seed": 42,
+    "total_episodes": 20,
+    "mean_reward": 2.0000000447034836,
+    "mean_length": 31.0,
+    "std_reward": 0.0,
+    "std_length": 0.0,
+    "task_count": 1,
+    "macro_mean_reward": 2.0000000447034836,
+    "macro_mean_length": 31.0,
+    "distributed_eval": true
+  }
+}

flappy_fix_latency_3_200ep_7k2steps_stitch/eval/mid_train/step_1250.json

@@ -0,0 +1,120 @@
+{
+  "per_latency": {
+    "flappy/latency_3": {
+      "latency": 3,
+      "num_episodes": 20,
+      "mean_reward": 2.0000000447034836,
+      "mean_length": 31.0,
+      "std_reward": 0.0,
+      "std_length": 0.0,
+      "episode_rewards": [
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836
+      ],
+      "episode_lengths": [
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31
+      ],
+      "decoded_action_hist": {},
+      "fixed_episode_seeds": true,
+      "eval_seed": 42,
+      "episode_seeds": [
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null
+      ],
+      "episode_indices": [
+        0,
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19
+      ]
+    }
+  },
+  "aggregate": {
+    "stage": "mid_train",
+    "step": 1250,
+    "task": "flappy",
+    "model_alias": "openvla",
+    "fixed_episode_seeds": true,
+    "eval_seed": 42,
+    "total_episodes": 20,
+    "mean_reward": 2.0000000447034836,
+    "mean_length": 31.0,
+    "std_reward": 0.0,
+    "std_length": 0.0,
+    "task_count": 1,
+    "macro_mean_reward": 2.0000000447034836,
+    "macro_mean_length": 31.0,
+    "distributed_eval": true
+  }
+}

flappy_fix_latency_3_200ep_7k2steps_stitch/eval/mid_train/step_1500.json

@@ -0,0 +1,120 @@
+{
+  "per_latency": {
+    "flappy/latency_3": {
+      "latency": 3,
+      "num_episodes": 20,
+      "mean_reward": 2.0000000447034836,
+      "mean_length": 31.0,
+      "std_reward": 0.0,
+      "std_length": 0.0,
+      "episode_rewards": [
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836
+      ],
+      "episode_lengths": [
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31
+      ],
+      "decoded_action_hist": {},
+      "fixed_episode_seeds": true,
+      "eval_seed": 42,
+      "episode_seeds": [
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null
+      ],
+      "episode_indices": [
+        0,
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19
+      ]
+    }
+  },
+  "aggregate": {
+    "stage": "mid_train",
+    "step": 1500,
+    "task": "flappy",
+    "model_alias": "openvla",
+    "fixed_episode_seeds": true,
+    "eval_seed": 42,
+    "total_episodes": 20,
+    "mean_reward": 2.0000000447034836,
+    "mean_length": 31.0,
+    "std_reward": 0.0,
+    "std_length": 0.0,
+    "task_count": 1,
+    "macro_mean_reward": 2.0000000447034836,
+    "macro_mean_length": 31.0,
+    "distributed_eval": true
+  }
+}

flappy_fix_latency_3_200ep_7k2steps_stitch/eval/mid_train/step_1750.json

@@ -0,0 +1,120 @@
+{
+  "per_latency": {
+    "flappy/latency_3": {
+      "latency": 3,
+      "num_episodes": 20,
+      "mean_reward": 2.0000000447034836,
+      "mean_length": 31.0,
+      "std_reward": 0.0,
+      "std_length": 0.0,
+      "episode_rewards": [
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836
+      ],
+      "episode_lengths": [
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31
+      ],
+      "decoded_action_hist": {},
+      "fixed_episode_seeds": true,
+      "eval_seed": 42,
+      "episode_seeds": [
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null
+      ],
+      "episode_indices": [
+        0,
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19
+      ]
+    }
+  },
+  "aggregate": {
+    "stage": "mid_train",
+    "step": 1750,
+    "task": "flappy",
+    "model_alias": "openvla",
+    "fixed_episode_seeds": true,
+    "eval_seed": 42,
+    "total_episodes": 20,
+    "mean_reward": 2.0000000447034836,
+    "mean_length": 31.0,
+    "std_reward": 0.0,
+    "std_length": 0.0,
+    "task_count": 1,
+    "macro_mean_reward": 2.0000000447034836,
+    "macro_mean_length": 31.0,
+    "distributed_eval": true
+  }
+}

flappy_fix_latency_3_200ep_7k2steps_stitch/eval/mid_train/step_2000.json

@@ -0,0 +1,120 @@
+{
+  "per_latency": {
+    "flappy/latency_3": {
+      "latency": 3,
+      "num_episodes": 20,
+      "mean_reward": 2.0000000447034836,
+      "mean_length": 31.0,
+      "std_reward": 0.0,
+      "std_length": 0.0,
+      "episode_rewards": [
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836
+      ],
+      "episode_lengths": [
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31
+      ],
+      "decoded_action_hist": {},
+      "fixed_episode_seeds": true,
+      "eval_seed": 42,
+      "episode_seeds": [
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null
+      ],
+      "episode_indices": [
+        0,
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19
+      ]
+    }
+  },
+  "aggregate": {
+    "stage": "mid_train",
+    "step": 2000,
+    "task": "flappy",
+    "model_alias": "openvla",
+    "fixed_episode_seeds": true,
+    "eval_seed": 42,
+    "total_episodes": 20,
+    "mean_reward": 2.0000000447034836,
+    "mean_length": 31.0,
+    "std_reward": 0.0,
+    "std_length": 0.0,
+    "task_count": 1,
+    "macro_mean_reward": 2.0000000447034836,
+    "macro_mean_length": 31.0,
+    "distributed_eval": true
+  }
+}

flappy_fix_latency_3_200ep_7k2steps_stitch/eval/mid_train/step_2250.json

@@ -0,0 +1,120 @@
+{
+  "per_latency": {
+    "flappy/latency_3": {
+      "latency": 3,
+      "num_episodes": 20,
+      "mean_reward": 2.0000000447034836,
+      "mean_length": 31.0,
+      "std_reward": 0.0,
+      "std_length": 0.0,
+      "episode_rewards": [
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836
+      ],
+      "episode_lengths": [
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31
+      ],
+      "decoded_action_hist": {},
+      "fixed_episode_seeds": true,
+      "eval_seed": 42,
+      "episode_seeds": [
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null
+      ],
+      "episode_indices": [
+        0,
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19
+      ]
+    }
+  },
+  "aggregate": {
+    "stage": "mid_train",
+    "step": 2250,
+    "task": "flappy",
+    "model_alias": "openvla",
+    "fixed_episode_seeds": true,
+    "eval_seed": 42,
+    "total_episodes": 20,
+    "mean_reward": 2.0000000447034836,
+    "mean_length": 31.0,
+    "std_reward": 0.0,
+    "std_length": 0.0,
+    "task_count": 1,
+    "macro_mean_reward": 2.0000000447034836,
+    "macro_mean_length": 31.0,
+    "distributed_eval": true
+  }
+}

flappy_fix_latency_3_200ep_7k2steps_stitch/eval/mid_train/step_250.json

@@ -0,0 +1,120 @@
+{
+  "per_latency": {
+    "flappy/latency_3": {
+      "latency": 3,
+      "num_episodes": 20,
+      "mean_reward": 2.0000000447034836,
+      "mean_length": 31.0,
+      "std_reward": 0.0,
+      "std_length": 0.0,
+      "episode_rewards": [
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836
+      ],
+      "episode_lengths": [
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31
+      ],
+      "decoded_action_hist": {},
+      "fixed_episode_seeds": true,
+      "eval_seed": 42,
+      "episode_seeds": [
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null
+      ],
+      "episode_indices": [
+        0,
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19
+      ]
+    }
+  },
+  "aggregate": {
+    "stage": "mid_train",
+    "step": 250,
+    "task": "flappy",
+    "model_alias": "openvla",
+    "fixed_episode_seeds": true,
+    "eval_seed": 42,
+    "total_episodes": 20,
+    "mean_reward": 2.0000000447034836,
+    "mean_length": 31.0,
+    "std_reward": 0.0,
+    "std_length": 0.0,
+    "task_count": 1,
+    "macro_mean_reward": 2.0000000447034836,
+    "macro_mean_length": 31.0,
+    "distributed_eval": true
+  }
+}

flappy_fix_latency_3_200ep_7k2steps_stitch/eval/mid_train/step_2500.json

@@ -0,0 +1,120 @@
+{
+  "per_latency": {
+    "flappy/latency_3": {
+      "latency": 3,
+      "num_episodes": 20,
+      "mean_reward": 2.0000000447034836,
+      "mean_length": 31.0,
+      "std_reward": 0.0,
+      "std_length": 0.0,
+      "episode_rewards": [
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836
+      ],
+      "episode_lengths": [
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31
+      ],
+      "decoded_action_hist": {},
+      "fixed_episode_seeds": true,
+      "eval_seed": 42,
+      "episode_seeds": [
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null
+      ],
+      "episode_indices": [
+        0,
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19
+      ]
+    }
+  },
+  "aggregate": {
+    "stage": "mid_train",
+    "step": 2500,
+    "task": "flappy",
+    "model_alias": "openvla",
+    "fixed_episode_seeds": true,
+    "eval_seed": 42,
+    "total_episodes": 20,
+    "mean_reward": 2.0000000447034836,
+    "mean_length": 31.0,
+    "std_reward": 0.0,
+    "std_length": 0.0,
+    "task_count": 1,
+    "macro_mean_reward": 2.0000000447034836,
+    "macro_mean_length": 31.0,
+    "distributed_eval": true
+  }
+}

flappy_fix_latency_3_200ep_7k2steps_stitch/eval/mid_train/step_2750.json

@@ -0,0 +1,120 @@
+{
+  "per_latency": {
+    "flappy/latency_3": {
+      "latency": 3,
+      "num_episodes": 20,
+      "mean_reward": 2.0000000447034836,
+      "mean_length": 31.0,
+      "std_reward": 0.0,
+      "std_length": 0.0,
+      "episode_rewards": [
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836
+      ],
+      "episode_lengths": [
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31
+      ],
+      "decoded_action_hist": {},
+      "fixed_episode_seeds": true,
+      "eval_seed": 42,
+      "episode_seeds": [
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null
+      ],
+      "episode_indices": [
+        0,
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19
+      ]
+    }
+  },
+  "aggregate": {
+    "stage": "mid_train",
+    "step": 2750,
+    "task": "flappy",
+    "model_alias": "openvla",
+    "fixed_episode_seeds": true,
+    "eval_seed": 42,
+    "total_episodes": 20,
+    "mean_reward": 2.0000000447034836,
+    "mean_length": 31.0,
+    "std_reward": 0.0,
+    "std_length": 0.0,
+    "task_count": 1,
+    "macro_mean_reward": 2.0000000447034836,
+    "macro_mean_length": 31.0,
+    "distributed_eval": true
+  }
+}

flappy_fix_latency_3_200ep_7k2steps_stitch/eval/mid_train/step_3000.json

@@ -0,0 +1,120 @@
+{
+  "per_latency": {
+    "flappy/latency_3": {
+      "latency": 3,
+      "num_episodes": 20,
+      "mean_reward": 2.0000000447034836,
+      "mean_length": 31.0,
+      "std_reward": 0.0,
+      "std_length": 0.0,
+      "episode_rewards": [
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836
+      ],
+      "episode_lengths": [
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31
+      ],
+      "decoded_action_hist": {},
+      "fixed_episode_seeds": true,
+      "eval_seed": 42,
+      "episode_seeds": [
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null
+      ],
+      "episode_indices": [
+        0,
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19
+      ]
+    }
+  },
+  "aggregate": {
+    "stage": "mid_train",
+    "step": 3000,
+    "task": "flappy",
+    "model_alias": "openvla",
+    "fixed_episode_seeds": true,
+    "eval_seed": 42,
+    "total_episodes": 20,
+    "mean_reward": 2.0000000447034836,
+    "mean_length": 31.0,
+    "std_reward": 0.0,
+    "std_length": 0.0,
+    "task_count": 1,
+    "macro_mean_reward": 2.0000000447034836,
+    "macro_mean_length": 31.0,
+    "distributed_eval": true
+  }
+}

flappy_fix_latency_3_200ep_7k2steps_stitch/eval/mid_train/step_3250.json

@@ -0,0 +1,120 @@
+{
+  "per_latency": {
+    "flappy/latency_3": {
+      "latency": 3,
+      "num_episodes": 20,
+      "mean_reward": 2.0000000447034836,
+      "mean_length": 31.0,
+      "std_reward": 0.0,
+      "std_length": 0.0,
+      "episode_rewards": [
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836
+      ],
+      "episode_lengths": [
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31
+      ],
+      "decoded_action_hist": {},
+      "fixed_episode_seeds": true,
+      "eval_seed": 42,
+      "episode_seeds": [
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null
+      ],
+      "episode_indices": [
+        0,
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19
+      ]
+    }
+  },
+  "aggregate": {
+    "stage": "mid_train",
+    "step": 3250,
+    "task": "flappy",
+    "model_alias": "openvla",
+    "fixed_episode_seeds": true,
+    "eval_seed": 42,
+    "total_episodes": 20,
+    "mean_reward": 2.0000000447034836,
+    "mean_length": 31.0,
+    "std_reward": 0.0,
+    "std_length": 0.0,
+    "task_count": 1,
+    "macro_mean_reward": 2.0000000447034836,
+    "macro_mean_length": 31.0,
+    "distributed_eval": true
+  }
+}

flappy_fix_latency_3_200ep_7k2steps_stitch/eval/mid_train/step_3500.json

@@ -0,0 +1,120 @@
+{
+  "per_latency": {
+    "flappy/latency_3": {
+      "latency": 3,
+      "num_episodes": 20,
+      "mean_reward": 2.0000000447034836,
+      "mean_length": 31.0,
+      "std_reward": 0.0,
+      "std_length": 0.0,
+      "episode_rewards": [
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836
+      ],
+      "episode_lengths": [
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31
+      ],
+      "decoded_action_hist": {},
+      "fixed_episode_seeds": true,
+      "eval_seed": 42,
+      "episode_seeds": [
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null
+      ],
+      "episode_indices": [
+        0,
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19
+      ]
+    }
+  },
+  "aggregate": {
+    "stage": "mid_train",
+    "step": 3500,
+    "task": "flappy",
+    "model_alias": "openvla",
+    "fixed_episode_seeds": true,
+    "eval_seed": 42,
+    "total_episodes": 20,
+    "mean_reward": 2.0000000447034836,
+    "mean_length": 31.0,
+    "std_reward": 0.0,
+    "std_length": 0.0,
+    "task_count": 1,
+    "macro_mean_reward": 2.0000000447034836,
+    "macro_mean_length": 31.0,
+    "distributed_eval": true
+  }
+}

flappy_fix_latency_3_200ep_7k2steps_stitch/eval/mid_train/step_3750.json

@@ -0,0 +1,120 @@
+{
+  "per_latency": {
+    "flappy/latency_3": {
+      "latency": 3,
+      "num_episodes": 20,
+      "mean_reward": 2.0000000447034836,
+      "mean_length": 31.0,
+      "std_reward": 0.0,
+      "std_length": 0.0,
+      "episode_rewards": [
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836
+      ],
+      "episode_lengths": [
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31
+      ],
+      "decoded_action_hist": {},
+      "fixed_episode_seeds": true,
+      "eval_seed": 42,
+      "episode_seeds": [
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null
+      ],
+      "episode_indices": [
+        0,
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19
+      ]
+    }
+  },
+  "aggregate": {
+    "stage": "mid_train",
+    "step": 3750,
+    "task": "flappy",
+    "model_alias": "openvla",
+    "fixed_episode_seeds": true,
+    "eval_seed": 42,
+    "total_episodes": 20,
+    "mean_reward": 2.0000000447034836,
+    "mean_length": 31.0,
+    "std_reward": 0.0,
+    "std_length": 0.0,
+    "task_count": 1,
+    "macro_mean_reward": 2.0000000447034836,
+    "macro_mean_length": 31.0,
+    "distributed_eval": true
+  }
+}

flappy_fix_latency_3_200ep_7k2steps_stitch/eval/mid_train/step_4000.json

@@ -0,0 +1,120 @@
+{
+  "per_latency": {
+    "flappy/latency_3": {
+      "latency": 3,
+      "num_episodes": 20,
+      "mean_reward": 2.0000000447034836,
+      "mean_length": 31.0,
+      "std_reward": 0.0,
+      "std_length": 0.0,
+      "episode_rewards": [
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836
+      ],
+      "episode_lengths": [
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31
+      ],
+      "decoded_action_hist": {},
+      "fixed_episode_seeds": true,
+      "eval_seed": 42,
+      "episode_seeds": [
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null
+      ],
+      "episode_indices": [
+        0,
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19
+      ]
+    }
+  },
+  "aggregate": {
+    "stage": "mid_train",
+    "step": 4000,
+    "task": "flappy",
+    "model_alias": "openvla",
+    "fixed_episode_seeds": true,
+    "eval_seed": 42,
+    "total_episodes": 20,
+    "mean_reward": 2.0000000447034836,
+    "mean_length": 31.0,
+    "std_reward": 0.0,
+    "std_length": 0.0,
+    "task_count": 1,
+    "macro_mean_reward": 2.0000000447034836,
+    "macro_mean_length": 31.0,
+    "distributed_eval": true
+  }
+}

flappy_fix_latency_3_200ep_7k2steps_stitch/eval/mid_train/step_500.json

@@ -0,0 +1,120 @@
+{
+  "per_latency": {
+    "flappy/latency_3": {
+      "latency": 3,
+      "num_episodes": 20,
+      "mean_reward": 2.0000000447034836,
+      "mean_length": 31.0,
+      "std_reward": 0.0,
+      "std_length": 0.0,
+      "episode_rewards": [
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836
+      ],
+      "episode_lengths": [
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31
+      ],
+      "decoded_action_hist": {},
+      "fixed_episode_seeds": true,
+      "eval_seed": 42,
+      "episode_seeds": [
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null
+      ],
+      "episode_indices": [
+        0,
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19
+      ]
+    }
+  },
+  "aggregate": {
+    "stage": "mid_train",
+    "step": 500,
+    "task": "flappy",
+    "model_alias": "openvla",
+    "fixed_episode_seeds": true,
+    "eval_seed": 42,
+    "total_episodes": 20,
+    "mean_reward": 2.0000000447034836,
+    "mean_length": 31.0,
+    "std_reward": 0.0,
+    "std_length": 0.0,
+    "task_count": 1,
+    "macro_mean_reward": 2.0000000447034836,
+    "macro_mean_length": 31.0,
+    "distributed_eval": true
+  }
+}

flappy_fix_latency_3_200ep_7k2steps_stitch/eval/mid_train/step_750.json

@@ -0,0 +1,120 @@
+{
+  "per_latency": {
+    "flappy/latency_3": {
+      "latency": 3,
+      "num_episodes": 20,
+      "mean_reward": 2.0000000447034836,
+      "mean_length": 31.0,
+      "std_reward": 0.0,
+      "std_length": 0.0,
+      "episode_rewards": [
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836
+      ],
+      "episode_lengths": [
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31
+      ],
+      "decoded_action_hist": {},
+      "fixed_episode_seeds": true,
+      "eval_seed": 42,
+      "episode_seeds": [
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null
+      ],
+      "episode_indices": [
+        0,
+        1,
+        2,
+        3,
+        4,
+        5,
+        6,
+        7,
+        8,
+        9,
+        10,
+        11,
+        12,
+        13,
+        14,
+        15,
+        16,
+        17,
+        18,
+        19
+      ]
+    }
+  },
+  "aggregate": {
+    "stage": "mid_train",
+    "step": 750,
+    "task": "flappy",
+    "model_alias": "openvla",
+    "fixed_episode_seeds": true,
+    "eval_seed": 42,
+    "total_episodes": 20,
+    "mean_reward": 2.0000000447034836,
+    "mean_length": 31.0,
+    "std_reward": 0.0,
+    "std_length": 0.0,
+    "task_count": 1,
+    "macro_mean_reward": 2.0000000447034836,
+    "macro_mean_length": 31.0,
+    "distributed_eval": true
+  }
+}

flappy_fix_latency_3_200ep_7k2steps_stitch/eval/post_train/step_4000.json

@@ -0,0 +1,240 @@
+{
+  "per_latency": {
+    "flappy/latency_3": {
+      "latency": 3,
+      "num_episodes": 50,
+      "mean_reward": 2.0000000447034836,
+      "mean_length": 31.0,
+      "std_reward": 0.0,
+      "std_length": 0.0,
+      "episode_rewards": [
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836,
+        2.0000000447034836
+      ],
+      "episode_lengths": [
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31,
+        31
+      ],
+      "decoded_action_hist": {},
+      "fixed_episode_seeds": true,
+      "eval_seed": 42,
+      "episode_seeds": [
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null,
+        null
+      ],
+      "episode_indices": [
+        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
+      ]
+    }
+  },
+  "aggregate": {
+    "stage": "post_train",
+    "step": 4000,
+    "task": "flappy",
+    "model_alias": "openvla",
+    "fixed_episode_seeds": true,
+    "eval_seed": 42,
+    "total_episodes": 50,
+    "mean_reward": 2.0000000447034836,
+    "mean_length": 31.0,
+    "std_reward": 0.0,
+    "std_length": 0.0,
+    "task_count": 1,
+    "macro_mean_reward": 2.0000000447034836,
+    "macro_mean_length": 31.0,
+    "distributed_eval": true
+  }
+}

flappy_fix_latency_3_200ep_7k2steps_stitch/hydra/.hydra/config.yaml

@@ -0,0 +1,252 @@
+framework:
+  qwenvl:
+    base_vlm: /lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/playground/Pretrained_models/Qwen3-VL-4B-Instruct
+    attn_implementation: flash_attention_2
+    flex_backend: triton
+    enable_gradient_checkpointing: true
+  action_model:
+    state_dim: 7
+    loss_type: discrete_ce
+    action_horizon: 1
+    future_action_window_size: 0
+    past_action_window_size: 0
+    action_dim: 7
+    action_env_dim: 2
+  kv_memory:
+    enabled: false
+    window: 4
+    rollout_len: 8
+    packed_train: false
+    rebased_sink: true
+  name: QwenOFT
+datasets:
+  vla_data:
+    dataset_py: lerobot_datasets
+    include_state: true
+    data_root_dir: /lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/data/memory/flappy_fix_latency_3_200ep_7k2steps
+    data_mix: flappy_train__bridge
+    eval_data_mix: flappy_train__bridge__val
+    custom_mixtures_path: null
+    action_type: discrete
+    sequential_step_sampling: false
+    eval_sequential_step_sampling: null
+    num_workers: 8
+    eval_num_workers: 8
+    prefetch_factor: 4
+    persistent_workers: true
+    pin_memory: true
+    shuffle: true
+    action_balance:
+      enabled: false
+      strategy: balanced_epoch
+      action_key: action_id
+      target_flap_fraction: 0.3
+      noop_id: 0
+      flap_id: 1
+    latency_curriculum:
+      enabled: false
+      strategy: exclusive
+      latencies: null
+      phase_steps: null
+      phase_distributions: null
+      new_latency_passes: 1.0
+      replay_passes: 0.25
+      target_total_passes: 2.0
+      final_equalization: true
+      step_budget_mode: auto
+      eval_at_phase_end: false
+      save_at_phase_end: false
+      computed_plan: null
+    per_device_batch_size: 8
+    load_all_data_for_training: true
+    num_obs_frames: 4
+    image_mode: stitch
+    prompt_mode: raw
+    stitch_grid:
+    - 2
+    - 2
+    obs_image_size: null
+    video_backend: torchvision_av
+dataset:
+  source_hf: ''
+  config_name: null
+  source_subdir: null
+  converted_name: flappy_train
+  single_source_hf: ''
+  mixed_source_hf: ''
+  single_converted_name: flappy_train
+  mixed_converted_name: flappy_mixed_latency_train
+  single_latency_filter: null
+  mixed_latency_filter: null
+  force_download: false
+  setup_force: false
+  skip_verification: false
+  target_latency_unit: raw_frames
+  verify_rows: 200
+  max_episodes: null
+  episodes_per_latency: null
+  latency_filter: null
+  debug_subset:
+    enabled: false
+    max_episodes: 5
+    suffix: debug
+base_model:
+  repo_id: Qwen/Qwen3-VL-4B-Instruct
+initialization:
+  checkpoint_local_dir: playground/Pretrained_models/Qwen3VL-OFT-Bridge-RT-1
+  checkpoint_hf_repo_id: StarVLA/Qwen3VL-OFT-Bridge-RT-1
+  checkpoint_filename: checkpoints/steps_5000_pytorch_model.pt
+trainer:
+  max_train_steps: 4000
+  num_warmup_steps: 100
+  save_interval: 500
+  eval_interval: 250
+  eval_num_batches: 50
+  per_latency_eval_num_batches: null
+  eval_action_classification: false
+  eval_action_classification_interval: null
+  cc_f1_tolerance: 1
+  learning_rate:
+    base: 2.0e-05
+    qwen_vl_interface: 1.0e-05
+    action_model: 0.0001
+  lr_scheduler_type: cosine_with_min_lr
+  scheduler_specific_kwargs:
+    min_lr: 1.0e-06
+  freeze_modules: ''
+  freeze_vit: false
+  freeze_tied_embedding: false
+  freeze_llm_layers: []
+  loss_scale:
+    vla: 1.0
+    vlm: 0.1
+  max_grad_norm: 1.0
+  weight_decay: 0.0
+  logging_frequency: 1
+  profile_timing:
+    enabled: false
+    log_interval: 10
+  gradient_clipping: 1.0
+  gradient_accumulation_steps: 16
+  distributed_backend: deepspeed
+  is_resume: true
+  pretrained_checkpoint: /lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/checkpoints/steps_2000_state
+  resume_step: 2000
+  reload_modules: null
+  optimizer:
+    name: AdamW
+    betas:
+    - 0.9
+    - 0.95
+    eps: 1.0e-08
+    weight_decay: 1.0e-08
+    fused: true
+  save_format: pt
+workspace_dir: WORKSPACE_DIR
+run_root_dir: /lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints
+seed: 42
+wandb_entity: ${oc.env:WANDB_ENTITY}
+wandb_project: ${oc.env:WANDB_PROJECT,starVLA_rl_games}
+auth:
+  env_file: null
+  hf_token_env: HF_TOKEN
+  wandb_api_key_env: WANDB_API_KEY
+paths:
+  run_root_dir: results/Checkpoints
+  dataset_local_dir: data/memory/flappy_fix_latency_3_200ep_7k2steps
+  dataset_cache_dir: null
+  base_model_dir: playground/Pretrained_models/Qwen3-VL-4B-Instruct
+  accelerate_config: starVLA/config/deepseeds/deepspeed_zero2.yaml
+launch:
+  use_accelerate: true
+  gpus: null
+  num_processes: 1
+  dry_run: false
+conda:
+  enabled: true
+  env_name: null
+rl_games:
+  model_alias: openvla
+  env_eval:
+    image_size: 224
+    frameskip: 1
+    image_transform: raw_rgb
+    prompt_mode: raw
+    ghost_trail:
+      history_frames: 5
+      gamma: 1.3
+      min_alpha: 35
+      scroll_px_per_step: 4.0
+      ground_fraction: 0.22
+    seed: 42
+    fixed_episode_seeds: true
+    latency_seed_stride: 0
+    task_seed_stride: 0
+    task_description: ''
+    eval_parallel_envs: 5
+    action_chunk_execution:
+      enabled: false
+      chunk_size: null
+    enabled: true
+    eval_backend: latency_bench
+    distributed_mode: rank_sharded
+    vectorized:
+      enabled: false
+      batch_size: 1
+    latency:
+      prompt_map_path: /lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/data/memory/flappy_fix_latency_3_200ep_7k2steps/flappy_train__bridge/latency_prompt_map.json
+      mode: single
+      values:
+      - 0
+    mid_train:
+      enabled: true
+      interval_steps: 250
+      latencies:
+      - 3
+      num_episodes: 20
+      max_steps_per_episode: 3600
+    post_train:
+      enabled: true
+      latencies:
+      - 3
+      num_episodes: 50
+      max_steps_per_episode: 3600
+  task: flappy
+  initialization_mode: bridge
+  action_carrier: bridge
+model: openvla
+env: flappy
+init: bridge
+bridge_base_model:
+  repo_id:
+    openvla: Qwen/Qwen3-VL-4B-Instruct
+    pi0: StarVLA/Qwen2.5-VL-3B-Instruct-Action
+    pi05: Qwen/Qwen3-VL-4B-Instruct
+    gr00t: Qwen/Qwen3-VL-4B-Instruct
+  local_dir:
+    openvla: playground/Pretrained_models/Qwen3-VL-4B-Instruct
+    pi0: playground/Pretrained_models/Qwen2.5-VL-3B-Instruct-Action
+    pi05: playground/Pretrained_models/Qwen3-VL-4B-Instruct
+    gr00t: playground/Pretrained_models/Qwen3-VL-4B-Instruct
+mode: single
+checkpoint:
+  load: auto
+  hf_repo_id: null
+  save_best_model: false
+  save_final_model: true
+  save_pt_file: false
+  save_training_state: true
+  save_safetensors_file: true
+  local:
+    keep_last_n: 1
+  sync:
+    enabled: false
+    repo_id: null
+    keep_last_n: 0
+    sync_every_n_checkpoints: 1
+    resume_policy: local_latest
+run_id: flappy_fix_latency_3_200ep_7k2steps_stitch
+output_dir: null
+config_yaml: null
+is_debug: false
+version_id: 0.21

flappy_fix_latency_3_200ep_7k2steps_stitch/hydra/.hydra/hydra.yaml

@@ -0,0 +1,370 @@
+hydra:
+  run:
+    dir: ${run_root_dir}/${run_id}/hydra
+  sweep:
+    dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S}
+    subdir: ${hydra.job.num}
+  launcher:
+    _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
+  sweeper:
+    _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
+    max_batch_size: null
+    params: null
+  help:
+    app_name: ${hydra.job.name}
+    header: '${hydra.help.app_name} is powered by Hydra.
+
+      '
+    footer: 'Powered by Hydra (https://hydra.cc)
+
+      Use --hydra-help to view Hydra specific help
+
+      '
+    template: '${hydra.help.header}
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (group=option)
+
+
+      $APP_CONFIG_GROUPS
+
+
+      == Config ==
+
+      Override anything in the config (foo.bar=value)
+
+
+      $CONFIG
+
+
+      ${hydra.help.footer}
+
+      '
+  hydra_help:
+    template: 'Hydra (${hydra.runtime.version})
+
+      See https://hydra.cc for more info.
+
+
+      == Flags ==
+
+      $FLAGS_HELP
+
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (For example, append hydra/job_logging=disabled
+      to command line)
+
+
+      $HYDRA_CONFIG_GROUPS
+
+
+      Use ''--cfg hydra'' to Show the Hydra config.
+
+      '
+    hydra_help: ???
+  hydra_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][HYDRA] %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+    root:
+      level: INFO
+      handlers:
+      - console
+    loggers:
+      logging_example:
+        level: DEBUG
+    disable_existing_loggers: false
+  job_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+      file:
+        class: logging.FileHandler
+        formatter: simple
+        filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log
+    root:
+      level: INFO
+      handlers:
+      - console
+      - file
+    disable_existing_loggers: false
+  env: {}
+  mode: RUN
+  searchpath: []
+  callbacks: {}
+  output_subdir: .hydra
+  overrides:
+    hydra:
+    - hydra.mode=RUN
+    task:
+    - model=openvla
+    - env=flappy
+    - init=bridge
+    - mode=single
+    - ++framework.qwenvl.base_vlm=playground/Pretrained_models/Qwen3-VL-4B-Instruct
+    - ++framework.qwenvl.attn_implementation=flash_attention_2
+    - ++framework.qwenvl.flex_backend=triton
+    - ++framework.qwenvl.enable_gradient_checkpointing=true
+    - ++framework.action_model.state_dim=7
+    - ++framework.action_model.loss_type=discrete_ce
+    - ++framework.action_model.action_horizon=1
+    - ++framework.action_model.future_action_window_size=0
+    - ++framework.action_model.past_action_window_size=0
+    - ++framework.action_model.action_dim=7
+    - ++framework.action_model.action_env_dim=2
+    - ++framework.kv_memory.enabled=false
+    - ++framework.kv_memory.window=4
+    - ++framework.kv_memory.rollout_len=8
+    - ++framework.kv_memory.packed_train=false
+    - ++framework.kv_memory.rebased_sink=true
+    - ++framework.name=QwenOFT
+    - ++datasets.vla_data.dataset_py=lerobot_datasets
+    - ++datasets.vla_data.include_state=true
+    - ++datasets.vla_data.data_root_dir=playground/Datasets/rl_games
+    - ++datasets.vla_data.data_mix=flappy_train
+    - ++datasets.vla_data.eval_data_mix=null
+    - ++datasets.vla_data.custom_mixtures_path=null
+    - ++datasets.vla_data.action_type=discrete
+    - ++datasets.vla_data.sequential_step_sampling=false
+    - ++datasets.vla_data.eval_sequential_step_sampling=null
+    - ++datasets.vla_data.num_workers=8
+    - ++datasets.vla_data.eval_num_workers=8
+    - ++datasets.vla_data.prefetch_factor=4
+    - ++datasets.vla_data.persistent_workers=true
+    - ++datasets.vla_data.pin_memory=true
+    - ++datasets.vla_data.shuffle=true
+    - ++datasets.vla_data.action_balance.enabled=false
+    - ++datasets.vla_data.action_balance.strategy=balanced_epoch
+    - ++datasets.vla_data.action_balance.action_key=action_id
+    - ++datasets.vla_data.action_balance.target_flap_fraction=0.3
+    - ++datasets.vla_data.action_balance.noop_id=0
+    - ++datasets.vla_data.action_balance.flap_id=1
+    - ++datasets.vla_data.latency_curriculum.enabled=false
+    - ++datasets.vla_data.latency_curriculum.strategy=exclusive
+    - ++datasets.vla_data.latency_curriculum.latencies=null
+    - ++datasets.vla_data.latency_curriculum.phase_steps=null
+    - ++datasets.vla_data.latency_curriculum.phase_distributions=null
+    - ++datasets.vla_data.latency_curriculum.new_latency_passes=1.0
+    - ++datasets.vla_data.latency_curriculum.replay_passes=0.25
+    - ++datasets.vla_data.latency_curriculum.target_total_passes=2.0
+    - ++datasets.vla_data.latency_curriculum.final_equalization=true
+    - ++datasets.vla_data.latency_curriculum.step_budget_mode=auto
+    - ++datasets.vla_data.latency_curriculum.eval_at_phase_end=false
+    - ++datasets.vla_data.latency_curriculum.save_at_phase_end=false
+    - ++datasets.vla_data.latency_curriculum.computed_plan=null
+    - ++datasets.vla_data.per_device_batch_size=8
+    - ++datasets.vla_data.load_all_data_for_training=true
+    - ++datasets.vla_data.num_obs_frames=4
+    - ++datasets.vla_data.image_mode=stitch
+    - ++datasets.vla_data.prompt_mode=raw
+    - ++datasets.vla_data.stitch_grid=[2,2]
+    - ++datasets.vla_data.obs_image_size=null
+    - ++datasets.vla_data.video_backend=torchvision_av
+    - ++dataset.source_hf=
+    - ++dataset.config_name=null
+    - ++dataset.source_subdir=null
+    - ++dataset.converted_name=flappy_train
+    - ++dataset.single_source_hf=
+    - ++dataset.mixed_source_hf=
+    - ++dataset.single_converted_name=flappy_train
+    - ++dataset.mixed_converted_name=flappy_mixed_latency_train
+    - ++dataset.single_latency_filter=null
+    - ++dataset.mixed_latency_filter=null
+    - ++dataset.force_download=false
+    - ++dataset.setup_force=false
+    - ++dataset.skip_verification=false
+    - ++dataset.target_latency_unit=raw_frames
+    - ++dataset.verify_rows=200
+    - ++dataset.max_episodes=null
+    - ++dataset.episodes_per_latency=null
+    - ++dataset.latency_filter=null
+    - ++dataset.debug_subset.enabled=false
+    - ++dataset.debug_subset.max_episodes=5
+    - ++dataset.debug_subset.suffix=debug
+    - ++base_model.repo_id=Qwen/Qwen3-VL-4B-Instruct
+    - ++initialization.checkpoint_local_dir=playground/Pretrained_models/Qwen3VL-OFT-Bridge-RT-1
+    - ++initialization.checkpoint_hf_repo_id=StarVLA/Qwen3VL-OFT-Bridge-RT-1
+    - ++initialization.checkpoint_filename=checkpoints/steps_5000_pytorch_model.pt
+    - ++trainer.max_train_steps=4000
+    - ++trainer.num_warmup_steps=100
+    - ++trainer.save_interval=500
+    - ++trainer.eval_interval=250
+    - ++trainer.eval_num_batches=50
+    - ++trainer.per_latency_eval_num_batches=null
+    - ++trainer.eval_action_classification=false
+    - ++trainer.eval_action_classification_interval=null
+    - ++trainer.cc_f1_tolerance=1
+    - ++trainer.learning_rate.base=2e-05
+    - ++trainer.learning_rate.qwen_vl_interface=1e-05
+    - ++trainer.learning_rate.action_model=0.0001
+    - ++trainer.lr_scheduler_type=cosine_with_min_lr
+    - ++trainer.scheduler_specific_kwargs.min_lr=1e-06
+    - ++trainer.freeze_modules=
+    - ++trainer.freeze_vit=false
+    - ++trainer.freeze_tied_embedding=false
+    - ++trainer.freeze_llm_layers=[]
+    - ++trainer.loss_scale.vla=1.0
+    - ++trainer.loss_scale.vlm=0.1
+    - ++trainer.max_grad_norm=1.0
+    - ++trainer.weight_decay=0.0
+    - ++trainer.logging_frequency=1
+    - ++trainer.profile_timing.enabled=false
+    - ++trainer.profile_timing.log_interval=10
+    - ++trainer.gradient_clipping=1.0
+    - ++trainer.gradient_accumulation_steps=16
+    - ++trainer.distributed_backend=deepspeed
+    - ++trainer.is_resume=false
+    - ++trainer.pretrained_checkpoint=null
+    - ++trainer.resume_step=0
+    - ++trainer.reload_modules=null
+    - ++trainer.optimizer.name=AdamW
+    - ++trainer.optimizer.betas=[0.9,0.95]
+    - ++trainer.optimizer.eps=1e-08
+    - ++trainer.optimizer.weight_decay=1e-08
+    - ++trainer.optimizer.fused=true
+    - ++trainer.save_format=pt
+    - ++workspace_dir=WORKSPACE_DIR
+    - ++run_root_dir=results/Checkpoints
+    - ++seed=42
+    - ++auth.env_file=null
+    - ++auth.hf_token_env=HF_TOKEN
+    - ++auth.wandb_api_key_env=WANDB_API_KEY
+    - ++paths.run_root_dir=results/Checkpoints
+    - ++paths.dataset_local_dir=data/memory/flappy_fix_latency_3_200ep_7k2steps
+    - ++paths.dataset_cache_dir=null
+    - ++paths.base_model_dir=playground/Pretrained_models/Qwen3-VL-4B-Instruct
+    - ++paths.accelerate_config=starVLA/config/deepseeds/deepspeed_zero2.yaml
+    - ++rl_games.model_alias=openvla
+    - ++rl_games.env_eval.image_size=224
+    - ++rl_games.env_eval.frameskip=1
+    - ++rl_games.env_eval.image_transform=raw_rgb
+    - ++rl_games.env_eval.prompt_mode=raw
+    - ++rl_games.env_eval.ghost_trail.history_frames=5
+    - ++rl_games.env_eval.ghost_trail.gamma=1.3
+    - ++rl_games.env_eval.ghost_trail.min_alpha=35
+    - ++rl_games.env_eval.ghost_trail.scroll_px_per_step=4.0
+    - ++rl_games.env_eval.ghost_trail.ground_fraction=0.22
+    - ++rl_games.env_eval.seed=42
+    - ++rl_games.env_eval.fixed_episode_seeds=true
+    - ++rl_games.env_eval.latency_seed_stride=0
+    - ++rl_games.env_eval.task_seed_stride=0
+    - ++rl_games.env_eval.task_description=
+    - ++rl_games.env_eval.eval_parallel_envs=5
+    - ++rl_games.env_eval.action_chunk_execution.enabled=false
+    - ++rl_games.env_eval.action_chunk_execution.chunk_size=null
+    - ++rl_games.env_eval.enabled=true
+    - ++rl_games.env_eval.eval_backend=latency_bench
+    - ++rl_games.env_eval.distributed_mode=rank_sharded
+    - ++rl_games.env_eval.vectorized.enabled=false
+    - ++rl_games.env_eval.vectorized.batch_size=1
+    - ++rl_games.env_eval.latency.prompt_map_path=null
+    - ++rl_games.env_eval.latency.mode=single
+    - ++rl_games.env_eval.latency.values=[0]
+    - ++rl_games.env_eval.mid_train.enabled=true
+    - ++rl_games.env_eval.mid_train.interval_steps=250
+    - ++rl_games.env_eval.mid_train.latencies=[3]
+    - ++rl_games.env_eval.mid_train.num_episodes=20
+    - ++rl_games.env_eval.mid_train.max_steps_per_episode=3600
+    - ++rl_games.env_eval.post_train.enabled=true
+    - ++rl_games.env_eval.post_train.latencies=[3]
+    - ++rl_games.env_eval.post_train.num_episodes=50
+    - ++rl_games.env_eval.post_train.max_steps_per_episode=3600
+    - ++rl_games.task=flappy
+    - ++rl_games.initialization_mode=bridge
+    - ++rl_games.action_carrier=bridge
+    - ++bridge_base_model.repo_id.openvla=Qwen/Qwen3-VL-4B-Instruct
+    - ++bridge_base_model.repo_id.pi0=StarVLA/Qwen2.5-VL-3B-Instruct-Action
+    - ++bridge_base_model.repo_id.pi05=Qwen/Qwen3-VL-4B-Instruct
+    - ++bridge_base_model.repo_id.gr00t=Qwen/Qwen3-VL-4B-Instruct
+    - ++bridge_base_model.local_dir.openvla=playground/Pretrained_models/Qwen3-VL-4B-Instruct
+    - ++bridge_base_model.local_dir.pi0=playground/Pretrained_models/Qwen2.5-VL-3B-Instruct-Action
+    - ++bridge_base_model.local_dir.pi05=playground/Pretrained_models/Qwen3-VL-4B-Instruct
+    - ++bridge_base_model.local_dir.gr00t=playground/Pretrained_models/Qwen3-VL-4B-Instruct
+    - ++checkpoint.load=auto
+    - ++checkpoint.hf_repo_id=null
+    - ++checkpoint.save_best_model=false
+    - ++checkpoint.save_final_model=true
+    - ++checkpoint.save_pt_file=false
+    - ++checkpoint.save_training_state=true
+    - ++checkpoint.save_safetensors_file=true
+    - ++checkpoint.local.keep_last_n=1
+    - ++checkpoint.sync.enabled=false
+    - ++checkpoint.sync.repo_id=null
+    - ++checkpoint.sync.keep_last_n=0
+    - ++checkpoint.sync.sync_every_n_checkpoints=1
+    - ++checkpoint.sync.resume_policy=local_latest
+    - ++run_id=flappy_fix_latency_3_200ep_7k2steps_stitch
+    - ++output_dir=null
+    - ++config_yaml=null
+    - ++is_debug=false
+    - ++version_id=0.21
+    - ++run_root_dir=/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints
+    - ++trainer.is_resume=true
+    - ++trainer.pretrained_checkpoint=/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/checkpoints/steps_2000_state
+    - ++trainer.resume_step=2000
+    - ++datasets.vla_data.data_root_dir=/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/data/memory/flappy_fix_latency_3_200ep_7k2steps
+    - ++datasets.vla_data.data_mix=flappy_train__bridge
+    - ++datasets.vla_data.eval_data_mix=flappy_train__bridge__val
+    - ++framework.qwenvl.base_vlm=/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/playground/Pretrained_models/Qwen3-VL-4B-Instruct
+    - ++rl_games.env_eval.latency.prompt_map_path=/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/data/memory/flappy_fix_latency_3_200ep_7k2steps/flappy_train__bridge/latency_prompt_map.json
+  job:
+    name: train_starvla_hydra
+    chdir: false
+    override_dirname: ++auth.env_file=null,++auth.hf_token_env=HF_TOKEN,++auth.wandb_api_key_env=WANDB_API_KEY,++base_model.repo_id=Qwen/Qwen3-VL-4B-Instruct,++bridge_base_model.local_dir.gr00t=playground/Pretrained_models/Qwen3-VL-4B-Instruct,++bridge_base_model.local_dir.openvla=playground/Pretrained_models/Qwen3-VL-4B-Instruct,++bridge_base_model.local_dir.pi05=playground/Pretrained_models/Qwen3-VL-4B-Instruct,++bridge_base_model.local_dir.pi0=playground/Pretrained_models/Qwen2.5-VL-3B-Instruct-Action,++bridge_base_model.repo_id.gr00t=Qwen/Qwen3-VL-4B-Instruct,++bridge_base_model.repo_id.openvla=Qwen/Qwen3-VL-4B-Instruct,++bridge_base_model.repo_id.pi05=Qwen/Qwen3-VL-4B-Instruct,++bridge_base_model.repo_id.pi0=StarVLA/Qwen2.5-VL-3B-Instruct-Action,++checkpoint.hf_repo_id=null,++checkpoint.load=auto,++checkpoint.local.keep_last_n=1,++checkpoint.save_best_model=false,++checkpoint.save_final_model=true,++checkpoint.save_pt_file=false,++checkpoint.save_safetensors_file=true,++checkpoint.save_training_state=true,++checkpoint.sync.enabled=false,++checkpoint.sync.keep_last_n=0,++checkpoint.sync.repo_id=null,++checkpoint.sync.resume_policy=local_latest,++checkpoint.sync.sync_every_n_checkpoints=1,++config_yaml=null,++dataset.config_name=null,++dataset.converted_name=flappy_train,++dataset.debug_subset.enabled=false,++dataset.debug_subset.max_episodes=5,++dataset.debug_subset.suffix=debug,++dataset.episodes_per_latency=null,++dataset.force_download=false,++dataset.latency_filter=null,++dataset.max_episodes=null,++dataset.mixed_converted_name=flappy_mixed_latency_train,++dataset.mixed_latency_filter=null,++dataset.mixed_source_hf=,++dataset.setup_force=false,++dataset.single_converted_name=flappy_train,++dataset.single_latency_filter=null,++dataset.single_source_hf=,++dataset.skip_verification=false,++dataset.source_hf=,++dataset.source_subdir=null,++dataset.target_latency_unit=raw_frames,++dataset.verify_rows=200,++datasets.vla_data.action_balance.action_key=action_id,++datasets.vla_data.action_balance.enabled=false,++datasets.vla_data.action_balance.flap_id=1,++datasets.vla_data.action_balance.noop_id=0,++datasets.vla_data.action_balance.strategy=balanced_epoch,++datasets.vla_data.action_balance.target_flap_fraction=0.3,++datasets.vla_data.action_type=discrete,++datasets.vla_data.custom_mixtures_path=null,++datasets.vla_data.data_mix=flappy_train,++datasets.vla_data.data_mix=flappy_train__bridge,++datasets.vla_data.data_root_dir=/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/data/memory/flappy_fix_latency_3_200ep_7k2steps,++datasets.vla_data.data_root_dir=playground/Datasets/rl_games,++datasets.vla_data.dataset_py=lerobot_datasets,++datasets.vla_data.eval_data_mix=flappy_train__bridge__val,++datasets.vla_data.eval_data_mix=null,++datasets.vla_data.eval_num_workers=8,++datasets.vla_data.eval_sequential_step_sampling=null,++datasets.vla_data.image_mode=stitch,++datasets.vla_data.include_state=true,++datasets.vla_data.latency_curriculum.computed_plan=null,++datasets.vla_data.latency_curriculum.enabled=false,++datasets.vla_data.latency_curriculum.eval_at_phase_end=false,++datasets.vla_data.latency_curriculum.final_equalization=true,++datasets.vla_data.latency_curriculum.latencies=null,++datasets.vla_data.latency_curriculum.new_latency_passes=1.0,++datasets.vla_data.latency_curriculum.phase_distributions=null,++datasets.vla_data.latency_curriculum.phase_steps=null,++datasets.vla_data.latency_curriculum.replay_passes=0.25,++datasets.vla_data.latency_curriculum.save_at_phase_end=false,++datasets.vla_data.latency_curriculum.step_budget_mode=auto,++datasets.vla_data.latency_curriculum.strategy=exclusive,++datasets.vla_data.latency_curriculum.target_total_passes=2.0,++datasets.vla_data.load_all_data_for_training=true,++datasets.vla_data.num_obs_frames=4,++datasets.vla_data.num_workers=8,++datasets.vla_data.obs_image_size=null,++datasets.vla_data.per_device_batch_size=8,++datasets.vla_data.persistent_workers=true,++datasets.vla_data.pin_memory=true,++datasets.vla_data.prefetch_factor=4,++datasets.vla_data.prompt_mode=raw,++datasets.vla_data.sequential_step_sampling=false,++datasets.vla_data.shuffle=true,++datasets.vla_data.stitch_grid=[2,2],++datasets.vla_data.video_backend=torchvision_av,++framework.action_model.action_dim=7,++framework.action_model.action_env_dim=2,++framework.action_model.action_horizon=1,++framework.action_model.future_action_window_size=0,++framework.action_model.loss_type=discrete_ce,++framework.action_model.past_action_window_size=0,++framework.action_model.state_dim=7,++framework.kv_memory.enabled=false,++framework.kv_memory.packed_train=false,++framework.kv_memory.rebased_sink=true,++framework.kv_memory.rollout_len=8,++framework.kv_memory.window=4,++framework.name=QwenOFT,++framework.qwenvl.attn_implementation=flash_attention_2,++framework.qwenvl.base_vlm=/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/playground/Pretrained_models/Qwen3-VL-4B-Instruct,++framework.qwenvl.base_vlm=playground/Pretrained_models/Qwen3-VL-4B-Instruct,++framework.qwenvl.enable_gradient_checkpointing=true,++framework.qwenvl.flex_backend=triton,++initialization.checkpoint_filename=checkpoints/steps_5000_pytorch_model.pt,++initialization.checkpoint_hf_repo_id=StarVLA/Qwen3VL-OFT-Bridge-RT-1,++initialization.checkpoint_local_dir=playground/Pretrained_models/Qwen3VL-OFT-Bridge-RT-1,++is_debug=false,++output_dir=null,++paths.accelerate_config=starVLA/config/deepseeds/deepspeed_zero2.yaml,++paths.base_model_dir=playground/Pretrained_models/Qwen3-VL-4B-Instruct,++paths.dataset_cache_dir=null,++paths.dataset_local_dir=data/memory/flappy_fix_latency_3_200ep_7k2steps,++paths.run_root_dir=results/Checkpoints,++rl_games.action_carrier=bridge,++rl_games.env_eval.action_chunk_execution.chunk_size=null,++rl_games.env_eval.action_chunk_execution.enabled=false,++rl_games.env_eval.distributed_mode=rank_sharded,++rl_games.env_eval.enabled=true,++rl_games.env_eval.eval_backend=latency_bench,++rl_games.env_eval.eval_parallel_envs=5,++rl_games.env_eval.fixed_episode_seeds=true,++rl_games.env_eval.frameskip=1,++rl_games.env_eval.ghost_trail.gamma=1.3,++rl_games.env_eval.ghost_trail.ground_fraction=0.22,++rl_games.env_eval.ghost_trail.history_frames=5,++rl_games.env_eval.ghost_trail.min_alpha=35,++rl_games.env_eval.ghost_trail.scroll_px_per_step=4.0,++rl_games.env_eval.image_size=224,++rl_games.env_eval.image_transform=raw_rgb,++rl_games.env_eval.latency.mode=single,++rl_games.env_eval.latency.prompt_map_path=/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/data/memory/flappy_fix_latency_3_200ep_7k2steps/flappy_train__bridge/latency_prompt_map.json,++rl_games.env_eval.latency.prompt_map_path=null,++rl_games.env_eval.latency.values=[0],++rl_games.env_eval.latency_seed_stride=0,++rl_games.env_eval.mid_train.enabled=true,++rl_games.env_eval.mid_train.interval_steps=250,++rl_games.env_eval.mid_train.latencies=[3],++rl_games.env_eval.mid_train.max_steps_per_episode=3600,++rl_games.env_eval.mid_train.num_episodes=20,++rl_games.env_eval.post_train.enabled=true,++rl_games.env_eval.post_train.latencies=[3],++rl_games.env_eval.post_train.max_steps_per_episode=3600,++rl_games.env_eval.post_train.num_episodes=50,++rl_games.env_eval.prompt_mode=raw,++rl_games.env_eval.seed=42,++rl_games.env_eval.task_description=,++rl_games.env_eval.task_seed_stride=0,++rl_games.env_eval.vectorized.batch_size=1,++rl_games.env_eval.vectorized.enabled=false,++rl_games.initialization_mode=bridge,++rl_games.model_alias=openvla,++rl_games.task=flappy,++run_id=flappy_fix_latency_3_200ep_7k2steps_stitch,++run_root_dir=/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints,++run_root_dir=results/Checkpoints,++seed=42,++trainer.cc_f1_tolerance=1,++trainer.distributed_backend=deepspeed,++trainer.eval_action_classification=false,++trainer.eval_action_classification_interval=null,++trainer.eval_interval=250,++trainer.eval_num_batches=50,++trainer.freeze_llm_layers=[],++trainer.freeze_modules=,++trainer.freeze_tied_embedding=false,++trainer.freeze_vit=false,++trainer.gradient_accumulation_steps=16,++trainer.gradient_clipping=1.0,++trainer.is_resume=false,++trainer.is_resume=true,++trainer.learning_rate.action_model=0.0001,++trainer.learning_rate.base=2e-05,++trainer.learning_rate.qwen_vl_interface=1e-05,++trainer.logging_frequency=1,++trainer.loss_scale.vla=1.0,++trainer.loss_scale.vlm=0.1,++trainer.lr_scheduler_type=cosine_with_min_lr,++trainer.max_grad_norm=1.0,++trainer.max_train_steps=4000,++trainer.num_warmup_steps=100,++trainer.optimizer.betas=[0.9,0.95],++trainer.optimizer.eps=1e-08,++trainer.optimizer.fused=true,++trainer.optimizer.name=AdamW,++trainer.optimizer.weight_decay=1e-08,++trainer.per_latency_eval_num_batches=null,++trainer.pretrained_checkpoint=/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/checkpoints/steps_2000_state,++trainer.pretrained_checkpoint=null,++trainer.profile_timing.enabled=false,++trainer.profile_timing.log_interval=10,++trainer.reload_modules=null,++trainer.resume_step=0,++trainer.resume_step=2000,++trainer.save_format=pt,++trainer.save_interval=500,++trainer.scheduler_specific_kwargs.min_lr=1e-06,++trainer.weight_decay=0.0,++version_id=0.21,++workspace_dir=WORKSPACE_DIR,env=flappy,init=bridge,mode=single,model=openvla
+    id: ???
+    num: ???
+    config_name: train
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.3.4
+    version_base: '1.1'
+    cwd: /lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/examples/rl_games/config
+      schema: file
+      provider: main
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/hydra
+    choices:
+      cross_task_setup: null
+      checkpoint: default
+      mode: single
+      init: bridge
+      env: flappy
+      model: openvla
+      hydra/env: default
+      hydra/callbacks: null
+      hydra/job_logging: default
+      hydra/hydra_logging: default
+      hydra/hydra_help: default
+      hydra/help: default
+      hydra/sweeper: basic
+      hydra/launcher: basic
+      hydra/output: default
+  verbose: false

flappy_fix_latency_3_200ep_7k2steps_stitch/hydra/.hydra/overrides.yaml

@@ -0,0 +1,210 @@
+- model=openvla
+- env=flappy
+- init=bridge
+- mode=single
+- ++framework.qwenvl.base_vlm=playground/Pretrained_models/Qwen3-VL-4B-Instruct
+- ++framework.qwenvl.attn_implementation=flash_attention_2
+- ++framework.qwenvl.flex_backend=triton
+- ++framework.qwenvl.enable_gradient_checkpointing=true
+- ++framework.action_model.state_dim=7
+- ++framework.action_model.loss_type=discrete_ce
+- ++framework.action_model.action_horizon=1
+- ++framework.action_model.future_action_window_size=0
+- ++framework.action_model.past_action_window_size=0
+- ++framework.action_model.action_dim=7
+- ++framework.action_model.action_env_dim=2
+- ++framework.kv_memory.enabled=false
+- ++framework.kv_memory.window=4
+- ++framework.kv_memory.rollout_len=8
+- ++framework.kv_memory.packed_train=false
+- ++framework.kv_memory.rebased_sink=true
+- ++framework.name=QwenOFT
+- ++datasets.vla_data.dataset_py=lerobot_datasets
+- ++datasets.vla_data.include_state=true
+- ++datasets.vla_data.data_root_dir=playground/Datasets/rl_games
+- ++datasets.vla_data.data_mix=flappy_train
+- ++datasets.vla_data.eval_data_mix=null
+- ++datasets.vla_data.custom_mixtures_path=null
+- ++datasets.vla_data.action_type=discrete
+- ++datasets.vla_data.sequential_step_sampling=false
+- ++datasets.vla_data.eval_sequential_step_sampling=null
+- ++datasets.vla_data.num_workers=8
+- ++datasets.vla_data.eval_num_workers=8
+- ++datasets.vla_data.prefetch_factor=4
+- ++datasets.vla_data.persistent_workers=true
+- ++datasets.vla_data.pin_memory=true
+- ++datasets.vla_data.shuffle=true
+- ++datasets.vla_data.action_balance.enabled=false
+- ++datasets.vla_data.action_balance.strategy=balanced_epoch
+- ++datasets.vla_data.action_balance.action_key=action_id
+- ++datasets.vla_data.action_balance.target_flap_fraction=0.3
+- ++datasets.vla_data.action_balance.noop_id=0
+- ++datasets.vla_data.action_balance.flap_id=1
+- ++datasets.vla_data.latency_curriculum.enabled=false
+- ++datasets.vla_data.latency_curriculum.strategy=exclusive
+- ++datasets.vla_data.latency_curriculum.latencies=null
+- ++datasets.vla_data.latency_curriculum.phase_steps=null
+- ++datasets.vla_data.latency_curriculum.phase_distributions=null
+- ++datasets.vla_data.latency_curriculum.new_latency_passes=1.0
+- ++datasets.vla_data.latency_curriculum.replay_passes=0.25
+- ++datasets.vla_data.latency_curriculum.target_total_passes=2.0
+- ++datasets.vla_data.latency_curriculum.final_equalization=true
+- ++datasets.vla_data.latency_curriculum.step_budget_mode=auto
+- ++datasets.vla_data.latency_curriculum.eval_at_phase_end=false
+- ++datasets.vla_data.latency_curriculum.save_at_phase_end=false
+- ++datasets.vla_data.latency_curriculum.computed_plan=null
+- ++datasets.vla_data.per_device_batch_size=8
+- ++datasets.vla_data.load_all_data_for_training=true
+- ++datasets.vla_data.num_obs_frames=4
+- ++datasets.vla_data.image_mode=stitch
+- ++datasets.vla_data.prompt_mode=raw
+- ++datasets.vla_data.stitch_grid=[2,2]
+- ++datasets.vla_data.obs_image_size=null
+- ++datasets.vla_data.video_backend=torchvision_av
+- ++dataset.source_hf=
+- ++dataset.config_name=null
+- ++dataset.source_subdir=null
+- ++dataset.converted_name=flappy_train
+- ++dataset.single_source_hf=
+- ++dataset.mixed_source_hf=
+- ++dataset.single_converted_name=flappy_train
+- ++dataset.mixed_converted_name=flappy_mixed_latency_train
+- ++dataset.single_latency_filter=null
+- ++dataset.mixed_latency_filter=null
+- ++dataset.force_download=false
+- ++dataset.setup_force=false
+- ++dataset.skip_verification=false
+- ++dataset.target_latency_unit=raw_frames
+- ++dataset.verify_rows=200
+- ++dataset.max_episodes=null
+- ++dataset.episodes_per_latency=null
+- ++dataset.latency_filter=null
+- ++dataset.debug_subset.enabled=false
+- ++dataset.debug_subset.max_episodes=5
+- ++dataset.debug_subset.suffix=debug
+- ++base_model.repo_id=Qwen/Qwen3-VL-4B-Instruct
+- ++initialization.checkpoint_local_dir=playground/Pretrained_models/Qwen3VL-OFT-Bridge-RT-1
+- ++initialization.checkpoint_hf_repo_id=StarVLA/Qwen3VL-OFT-Bridge-RT-1
+- ++initialization.checkpoint_filename=checkpoints/steps_5000_pytorch_model.pt
+- ++trainer.max_train_steps=4000
+- ++trainer.num_warmup_steps=100
+- ++trainer.save_interval=500
+- ++trainer.eval_interval=250
+- ++trainer.eval_num_batches=50
+- ++trainer.per_latency_eval_num_batches=null
+- ++trainer.eval_action_classification=false
+- ++trainer.eval_action_classification_interval=null
+- ++trainer.cc_f1_tolerance=1
+- ++trainer.learning_rate.base=2e-05
+- ++trainer.learning_rate.qwen_vl_interface=1e-05
+- ++trainer.learning_rate.action_model=0.0001
+- ++trainer.lr_scheduler_type=cosine_with_min_lr
+- ++trainer.scheduler_specific_kwargs.min_lr=1e-06
+- ++trainer.freeze_modules=
+- ++trainer.freeze_vit=false
+- ++trainer.freeze_tied_embedding=false
+- ++trainer.freeze_llm_layers=[]
+- ++trainer.loss_scale.vla=1.0
+- ++trainer.loss_scale.vlm=0.1
+- ++trainer.max_grad_norm=1.0
+- ++trainer.weight_decay=0.0
+- ++trainer.logging_frequency=1
+- ++trainer.profile_timing.enabled=false
+- ++trainer.profile_timing.log_interval=10
+- ++trainer.gradient_clipping=1.0
+- ++trainer.gradient_accumulation_steps=16
+- ++trainer.distributed_backend=deepspeed
+- ++trainer.is_resume=false
+- ++trainer.pretrained_checkpoint=null
+- ++trainer.resume_step=0
+- ++trainer.reload_modules=null
+- ++trainer.optimizer.name=AdamW
+- ++trainer.optimizer.betas=[0.9,0.95]
+- ++trainer.optimizer.eps=1e-08
+- ++trainer.optimizer.weight_decay=1e-08
+- ++trainer.optimizer.fused=true
+- ++trainer.save_format=pt
+- ++workspace_dir=WORKSPACE_DIR
+- ++run_root_dir=results/Checkpoints
+- ++seed=42
+- ++auth.env_file=null
+- ++auth.hf_token_env=HF_TOKEN
+- ++auth.wandb_api_key_env=WANDB_API_KEY
+- ++paths.run_root_dir=results/Checkpoints
+- ++paths.dataset_local_dir=data/memory/flappy_fix_latency_3_200ep_7k2steps
+- ++paths.dataset_cache_dir=null
+- ++paths.base_model_dir=playground/Pretrained_models/Qwen3-VL-4B-Instruct
+- ++paths.accelerate_config=starVLA/config/deepseeds/deepspeed_zero2.yaml
+- ++rl_games.model_alias=openvla
+- ++rl_games.env_eval.image_size=224
+- ++rl_games.env_eval.frameskip=1
+- ++rl_games.env_eval.image_transform=raw_rgb
+- ++rl_games.env_eval.prompt_mode=raw
+- ++rl_games.env_eval.ghost_trail.history_frames=5
+- ++rl_games.env_eval.ghost_trail.gamma=1.3
+- ++rl_games.env_eval.ghost_trail.min_alpha=35
+- ++rl_games.env_eval.ghost_trail.scroll_px_per_step=4.0
+- ++rl_games.env_eval.ghost_trail.ground_fraction=0.22
+- ++rl_games.env_eval.seed=42
+- ++rl_games.env_eval.fixed_episode_seeds=true
+- ++rl_games.env_eval.latency_seed_stride=0
+- ++rl_games.env_eval.task_seed_stride=0
+- ++rl_games.env_eval.task_description=
+- ++rl_games.env_eval.eval_parallel_envs=5
+- ++rl_games.env_eval.action_chunk_execution.enabled=false
+- ++rl_games.env_eval.action_chunk_execution.chunk_size=null
+- ++rl_games.env_eval.enabled=true
+- ++rl_games.env_eval.eval_backend=latency_bench
+- ++rl_games.env_eval.distributed_mode=rank_sharded
+- ++rl_games.env_eval.vectorized.enabled=false
+- ++rl_games.env_eval.vectorized.batch_size=1
+- ++rl_games.env_eval.latency.prompt_map_path=null
+- ++rl_games.env_eval.latency.mode=single
+- ++rl_games.env_eval.latency.values=[0]
+- ++rl_games.env_eval.mid_train.enabled=true
+- ++rl_games.env_eval.mid_train.interval_steps=250
+- ++rl_games.env_eval.mid_train.latencies=[3]
+- ++rl_games.env_eval.mid_train.num_episodes=20
+- ++rl_games.env_eval.mid_train.max_steps_per_episode=3600
+- ++rl_games.env_eval.post_train.enabled=true
+- ++rl_games.env_eval.post_train.latencies=[3]
+- ++rl_games.env_eval.post_train.num_episodes=50
+- ++rl_games.env_eval.post_train.max_steps_per_episode=3600
+- ++rl_games.task=flappy
+- ++rl_games.initialization_mode=bridge
+- ++rl_games.action_carrier=bridge
+- ++bridge_base_model.repo_id.openvla=Qwen/Qwen3-VL-4B-Instruct
+- ++bridge_base_model.repo_id.pi0=StarVLA/Qwen2.5-VL-3B-Instruct-Action
+- ++bridge_base_model.repo_id.pi05=Qwen/Qwen3-VL-4B-Instruct
+- ++bridge_base_model.repo_id.gr00t=Qwen/Qwen3-VL-4B-Instruct
+- ++bridge_base_model.local_dir.openvla=playground/Pretrained_models/Qwen3-VL-4B-Instruct
+- ++bridge_base_model.local_dir.pi0=playground/Pretrained_models/Qwen2.5-VL-3B-Instruct-Action
+- ++bridge_base_model.local_dir.pi05=playground/Pretrained_models/Qwen3-VL-4B-Instruct
+- ++bridge_base_model.local_dir.gr00t=playground/Pretrained_models/Qwen3-VL-4B-Instruct
+- ++checkpoint.load=auto
+- ++checkpoint.hf_repo_id=null
+- ++checkpoint.save_best_model=false
+- ++checkpoint.save_final_model=true
+- ++checkpoint.save_pt_file=false
+- ++checkpoint.save_training_state=true
+- ++checkpoint.save_safetensors_file=true
+- ++checkpoint.local.keep_last_n=1
+- ++checkpoint.sync.enabled=false
+- ++checkpoint.sync.repo_id=null
+- ++checkpoint.sync.keep_last_n=0
+- ++checkpoint.sync.sync_every_n_checkpoints=1
+- ++checkpoint.sync.resume_policy=local_latest
+- ++run_id=flappy_fix_latency_3_200ep_7k2steps_stitch
+- ++output_dir=null
+- ++config_yaml=null
+- ++is_debug=false
+- ++version_id=0.21
+- ++run_root_dir=/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints
+- ++trainer.is_resume=true
+- ++trainer.pretrained_checkpoint=/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/checkpoints/steps_2000_state
+- ++trainer.resume_step=2000
+- ++datasets.vla_data.data_root_dir=/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/data/memory/flappy_fix_latency_3_200ep_7k2steps
+- ++datasets.vla_data.data_mix=flappy_train__bridge
+- ++datasets.vla_data.eval_data_mix=flappy_train__bridge__val
+- ++framework.qwenvl.base_vlm=/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/playground/Pretrained_models/Qwen3-VL-4B-Instruct
+- ++rl_games.env_eval.latency.prompt_map_path=/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/data/memory/flappy_fix_latency_3_200ep_7k2steps/flappy_train__bridge/latency_prompt_map.json

flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/_progress/rank_0.json

@@ -0,0 +1 @@
+{"completed": 10}

flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/_progress/rank_1.json

@@ -0,0 +1 @@
+{"completed": 10}

flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3/episode_metrics.jsonl

@@ -0,0 +1,10 @@
+{"episode_id": 1, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 43, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 3, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 45, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 5, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 47, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 7, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 49, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 9, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 51, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 11, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 53, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 13, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 55, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 15, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 57, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 17, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 59, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 19, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 61, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}

flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/_progress/rank_0.json

@@ -0,0 +1 @@
+{"completed": 10}

flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/_progress/rank_1.json

@@ -0,0 +1 @@
+{"completed": 10}

flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3/episode_metrics.jsonl

@@ -0,0 +1,10 @@
+{"episode_id": 0, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 42, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 2, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 44, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 4, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 46, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 6, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 48, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 8, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 50, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 10, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 52, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 12, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 54, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 14, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 56, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 16, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 58, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 18, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 60, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}

flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/_progress/rank_0.json

@@ -0,0 +1 @@
+{"completed": 10}

flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/_progress/rank_1.json

@@ -0,0 +1 @@
+{"completed": 10}

flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3/episode_metrics.jsonl

@@ -0,0 +1,10 @@
+{"episode_id": 0, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 42, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 2, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 44, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 4, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 46, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 6, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 48, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 8, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 50, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 10, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 52, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 12, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 54, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 14, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 56, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 16, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 58, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 18, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 60, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1500/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}

flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/_progress/rank_0.json

@@ -0,0 +1 @@
+{"completed": 10}

flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/_progress/rank_1.json

@@ -0,0 +1 @@
+{"completed": 10}

flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3/episode_metrics.jsonl

@@ -0,0 +1,10 @@
+{"episode_id": 0, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 42, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 2, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 44, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 4, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 46, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 6, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 48, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 8, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 50, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 10, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 52, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 12, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 54, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 14, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 56, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 16, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 58, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 18, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 60, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_1750/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}

flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/_progress/rank_0.json

@@ -0,0 +1 @@
+{"completed": 10}

flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/_progress/rank_1.json

@@ -0,0 +1 @@
+{"completed": 10}

flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3/episode_metrics.jsonl

@@ -0,0 +1,10 @@
+{"episode_id": 0, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 42, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 2, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 44, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 4, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 46, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 6, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 48, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 8, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 50, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 10, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 52, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 12, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 54, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 14, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 56, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 16, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 58, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 18, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 60, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2000/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}

flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/_progress/rank_0.json

@@ -0,0 +1 @@
+{"completed": 10}

flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/_progress/rank_1.json

@@ -0,0 +1 @@
+{"completed": 10}

flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3/episode_metrics.jsonl

@@ -0,0 +1,10 @@
+{"episode_id": 1, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 43, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 3, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 45, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 5, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 47, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 7, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 49, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 9, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 51, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 11, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 53, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 13, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 55, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 15, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 57, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 17, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 59, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}
+{"episode_id": 19, "episode_return": 2.0000000447034836, "episode_return_env": 2.0000000447034836, "game_score": 0.0, "mean_latency_ms": 100.0, "metadata": {"checkpoint_path": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "config_name": "starvla_flappy_train_eval", "env_fps": 30.0, "env_id": "flappy", "episode_seed": 61, "frame_ms": 33.333333333333336, "instance_id": null, "instance_origin": null, "latency_type": "fixed", "mode": "simulated", "obs_fps": 30.0, "output_dir": "/lustre/fsw/portfolios/nvr/projects/nvr_lacr_llm/users/zihwang/latency-sensitive-bench/third_party/starVLA/results/Checkpoints/flappy_fix_latency_3_200ep_7k2steps_stitch/latency_bench_eval/mid_train/step_2250/flappy/latency_3", "policy_id": "starvla", "profile_id": null, "profile_path": null, "replay_host": null, "run_name": "starvla_flappy_train_eval", "target_device": null}, "num_actions": 31, "num_dropped_actions": 2, "num_invalid_actions": 0, "p90_latency_ms": 100.0, "p99_latency_ms": 100.0, "return_raw": null, "survival_steps": 31}