Datasets:

weixu-zhang
/

visrl-resume-checkpoints

Error code:   StreamingRowsError
Exception:    CastError
Message:      Couldn't cast
</tool_call>: int64
<tool_call>: int64
<|box_end|>: int64
<|box_start|>: int64
<|endoftext|>: int64
<|file_sep|>: int64
<|fim_middle|>: int64
<|fim_pad|>: int64
<|fim_prefix|>: int64
<|fim_suffix|>: int64
<|im_end|>: int64
<|im_start|>: int64
<|image_pad|>: int64
<|object_ref_end|>: int64
<|object_ref_start|>: int64
<|quad_end|>: int64
<|quad_start|>: int64
<|repo_name|>: int64
<|video_pad|>: int64
<|vision_end|>: int64
<|vision_pad|>: int64
<|vision_start|>: int64
FSDP_version: int64
world_size: int64
to
{'FSDP_version': Value('int64'), 'world_size': Value('int64')}
because column names don't match
Traceback:    Traceback (most recent call last):
                File "/src/services/worker/src/worker/utils.py", line 99, in get_rows_or_raise
                  return get_rows(
                         ^^^^^^^^^
                File "/src/libs/libcommon/src/libcommon/utils.py", line 272, in decorator
                  return func(*args, **kwargs)
                         ^^^^^^^^^^^^^^^^^^^^^
                File "/src/services/worker/src/worker/utils.py", line 77, in get_rows
                  rows_plus_one = list(itertools.islice(ds, rows_max_number + 1))
                                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/iterable_dataset.py", line 2690, in __iter__
                  for key, example in ex_iterable:
                                      ^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/iterable_dataset.py", line 2227, in __iter__
                  for key, pa_table in self._iter_arrow():
                                       ^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/iterable_dataset.py", line 2251, in _iter_arrow
                  for key, pa_table in self.ex_iterable._iter_arrow():
                                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/iterable_dataset.py", line 494, in _iter_arrow
                  for key, pa_table in iterator:
                                       ^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/iterable_dataset.py", line 384, in _iter_arrow
                  for key, pa_table in self.generate_tables_fn(**gen_kwags):
                                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 299, in _generate_tables
                  self._cast_table(pa_table, json_field_paths=json_field_paths),
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 128, in _cast_table
                  pa_table = table_cast(pa_table, self.info.features.arrow_schema)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2321, in table_cast
                  return cast_table_to_schema(table, schema)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2249, in cast_table_to_schema
                  raise CastError(
              datasets.table.CastError: Couldn't cast
              </tool_call>: int64
              <tool_call>: int64
              <|box_end|>: int64
              <|box_start|>: int64
              <|endoftext|>: int64
              <|file_sep|>: int64
              <|fim_middle|>: int64
              <|fim_pad|>: int64
              <|fim_prefix|>: int64
              <|fim_suffix|>: int64
              <|im_end|>: int64
              <|im_start|>: int64
              <|image_pad|>: int64
              <|object_ref_end|>: int64
              <|object_ref_start|>: int64
              <|quad_end|>: int64
              <|quad_start|>: int64
              <|repo_name|>: int64
              <|video_pad|>: int64
              <|vision_end|>: int64
              <|vision_pad|>: int64
              <|vision_start|>: int64
              FSDP_version: int64
              world_size: int64
              to
              {'FSDP_version': Value('int64'), 'world_size': Value('int64')}
              because column names don't match

Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.

VisRL raw resume checkpoints

This dataset stores raw FSDP training checkpoints intended for resuming training on another server, not for direct inference.

Current contents

path	use
`latest_checkpointed_iteration.txt`	root-level tracker for the current best 7B LoRA resume snapshot (`global_step_300`)
`global_step_300/`	raw single-H200 7B LoRA low-LR resume checkpoint corresponding to the current best merged model
`global_step_200/`	earlier single-H200 7B LoRA low-LR resume checkpoint kept for comparison / fallback
`phase3d_7lang_recovery_20260502_1712/latest_checkpointed_iteration.txt`	tracker for the Phase 3d 7-language mirror
`phase3d_7lang_recovery_20260502_1712/global_step_1500/`	raw H200 Phase 3d 7-language resume checkpoint

Use this repo when

you want to continue GRPO training from an existing H200 run;
you need optimizer / extra state, not just model weights;
you are migrating to another server and want a resume point without rsync.

Prefer these repos for eval / inference

weixu-zhang/viscoder2-7b-grpo-phase3b-fixedrubric-lora-lowlr-step300
weixu-zhang/viscoder2-3b-grpo-phase3d-7lang-step1500

Downloads last month: 138

Total file size:

109 GB