apiche

Apiche's group workspace

Group: gpt_oss

1-1

of 1

Tags

Notes

Author

apiche

State

Crashed

Start time

August 8th, 2025 8:29:53 PM

Runtime

4d 4h 55m 35s

Tracked hours

1d 16h 28m 33s

Run path

apiche/pipeline-rl/gpt_oss_actor

Linux-5.15.0-1067-nvidia-x86_64-with-glibc2.39

Python version

CPython 3.11.11

Git repository

git clone git@github.com:ServiceNow/pipelinerl.git

Git state

git checkout -b "gpt_oss/actor" a634b394192af0d1b77b159c5e54a44140c47dfe

Command

-m pipelinerl.entrypoints.run_actor --config-dir results/gpt_oss/conf --config-name exp_config output_dir=results/gpt_oss hydra.run.dir=results/gpt_oss/actor +me.llm_urls=http://localhost:8080+http://localhost:8081+http://localhost:8082+http://localhost:8083

System Hardware

CPU count	112
Logical CPU count	224
GPU count	4
GPU type	NVIDIA H100 80GB HBM3

W&B CLI Version

0.19.11

Group

gpt_oss

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 172 keys
- accelerate_config:
  null
- actor.discount_factor:
  1
- actor.llm_max_rollouts:
  64
- actor.log_each_n_secs:
  0
- actor.problem_queue_size:
  64
- actor.result_queue_size:
  64
- actor.rollout_policy:
  "pipelinerl.domains.math.generate_math_rollout"
- actor.rollout_workers:
  1
- actor.shared_memory_entry_size:
  10,000,000
- actor.system_prompt:
  "Please reason step by step, and put your final answer within \boxed{}."
- actor.task_template:
  "{task}"
- actor.throughput_window_size:
  50
- attempts:
  1
- dataset_loader:
  "pipelinerl.domains.math.load_datasets"
- debug.mode:
  "actor"
- debug.place_inference_workers:
  true
- debug.streams_from:
  null
- debug.use_existing_llms:
  false
- deepspeed_config:
  "deepspeed_stage3_bf16"
- desired_num_gpus:
  128
- environment._target_:
  "pipelinerl.domains.math.MathEnvironment"
- eval_every_n_versions:
  78,000
- finetune.also_save_steps:[] 0 items
- finetune.attempts:
  1
- finetune.attn_implementation:
  "flash_attention_2"
- finetune.auto_device_map:
  false
- finetune.config_name:
  "/mnt/llmd/base_models/Qwen2.5-0.5B"
- finetune.cuda_empty_cache:
  true
- finetune.data:
  null
- finetune.desired_num_gpus:
  128
- finetune.eval_callback._target_:
  "tapeagents.finetune.eval.dummy_eval_callback"
- finetune.eval_callback.config_name:
  ""
- finetune.force_restart:
  true
- finetune.gradient_accumulation_passes:
  512
- finetune.gradient_checkpointing:
  true
- finetune.gradient_clipping_threshold:
  0.3
- finetune.input:
  "training_data"
- finetune.interrupt_train_steps:
  -1
- finetune.keep_intermediate_checkpoints:
  true
- finetune.learning_rate:
  0.000001
- finetune.load_as_bf16:
  true
- finetune.log_each_n_steps:
  1
- finetune.lora.alpha:
  16
- finetune.lora.base_model_4bit:
  false
- finetune.lora.base_model_8bit:
  false
- finetune.lora.bias:
  "none"
- world.environment_start_port:
  7,777
- world.finetune_fraction:
  0
- world.preprocessor_fraction:
  0
- world.replicas:
  1

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 45 keys
- actor/always_success:
  0
- actor/cumulative_time_for_current_num_llms:
  0
- actor/cumulative_time_for_desired_num_llms:
  0
- actor/cumulative_time_to_deduct:
  0
- actor/finished_groups:
  478
- actor/groups_in_progress:
  3
- actor/latency_mean:
  4.1094818115234375
- actor/model_version_mean:
  0
- actor/never_success:
  1
- actor/no_answer_mean:
  1
- actor/no_error_mean:
  1
- actor/num_turns_mean:
  1
- actor/open_reasoner_zero_57k/no_answer_mean:
  1
- actor/open_reasoner_zero_57k/no_error_mean:
  1
- actor/open_reasoner_zero_57k/num_turns_mean:
  1
- actor/open_reasoner_zero_57k/output_tokens_mean:
  1,329
- actor/open_reasoner_zero_57k/overflow_mean:
  0
- actor/open_reasoner_zero_57k/penalty_mean:
  0
- actor/open_reasoner_zero_57k/prompt_tokens_mean:
  532
- actor/open_reasoner_zero_57k/reward_mean:
  0
- actor/open_reasoner_zero_57k/success_mean:
  0
- actor/open_reasoner_zero_extended_72k/no_answer_mean:
  1
- actor/open_reasoner_zero_extended_72k/no_error_mean:
  1
- actor/open_reasoner_zero_extended_72k/num_turns_mean:
  1
- actor/open_reasoner_zero_extended_72k/output_tokens_mean:
  794
- actor/open_reasoner_zero_extended_72k/overflow_mean:
  0
- actor/open_reasoner_zero_extended_72k/penalty_mean:
  0
- actor/open_reasoner_zero_extended_72k/prompt_tokens_mean:
  80
- actor/open_reasoner_zero_extended_72k/reward_mean:
  0
- actor/open_reasoner_zero_extended_72k/success_mean:
  0
- actor/output_tokens_mean:
  1,329
- actor/output_tokens_per_second:
  1,116.456038770662
- actor/overflow_mean:
  0
- actor/penalty_mean:
  0
- actor/problem_queue_size:
  0
- actor/prompt_tokens_mean:
  532
- actor/prompt_tokens_per_second:
  128.4371061274513
- actor/published_samples:
  478
- actor/result_queue_size:
  0
- actor/reward_mean:
  0
- actor/samples_per_second:
  1.0710232332175724
- actor/sometimes_success:
  0
- actor/success_mean:
  0
- actor/time_since_start:
  532.8619978427887
- actor/total_tokens_per_second:
  1,244.8931448981132

This run produced these artifacts as outputs. Total: 1. Learn more

wandb-history

run-gpt_oss_actor-history:v1