apiche

Apiche's group workspace

Group: debug_actor_tir

1-1

of 1

Tags

Notes

Author

apiche

State

Crashed

Start time

August 14th, 2025 8:42:24 PM

Runtime

18h 47m 31s

Tracked hours

30m 20s

Run path

apiche/pipeline-rl/debug_actor_tir_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 "debug_actor_tir/actor" 30869fdf9aeab3bd84f1869f7c6f4b116c889bdd

Command

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

System Hardware

CPU count	112
Logical CPU count	224
GPU count	1
GPU type	NVIDIA H100 80GB HBM3

W&B CLI Version

0.19.11

Group

debug_actor_tir

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 178 keys
- accelerate_config:
  null
- actor.discount_factor:
  1
- actor.llm_max_rollouts:
  1
- actor.log_each_n_secs:
  0
- actor.max_reasoning_steps:
  8
- actor.problem_queue_size:
  64
- actor.result_queue_size:
  64
- actor.rollout_policy:
  "pipelinerl.domains.tir.rollouts.generate_tir_rollout"
- actor.rollout_workers:
  1
- actor.shared_memory_entry_size:
  10,000,000
- actor.system_prompt:
  ""
- actor.throughput_window_size:
  50
- agent._target_:
  "pipelinerl.domains.tir.agent.TIRMathAgent"
- agent.system_prompt:
  ""
- attempts:
  8
- dataset_loader:
  "pipelinerl.domains.tir.datasets.load_datasets"
- debug.mode:
  "actor"
- debug.place_inference_workers:
  true
- debug.streams_from:
  null
- debug.use_existing_llms:
  false
- deepspeed_config:
  "deepspeed_stage3_bf16"
- environment._target_:
  "pipelinerl.domains.tir.environment.AsyncMCPPythonEnvironment"
- 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/AI-MO-NuminaMath-7B-TIR"
- finetune.cuda_empty_cache:
  true
- finetune.data:
  null
- finetune.eval_callback._target_:
  "tapeagents.finetune.eval.dummy_eval_callback"
- finetune.eval_callback.config_name:
  ""
- finetune.force_restart:
  false
- finetune.gradient_accumulation_passes:
  1,024
- 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:
  4
- world.preprocessor_fraction:
  0
- world.replicas:
  1

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 76 keys
- actor/always_success:
  0
- actor/finished_groups:
  1
- actor/latency_max:
  1,415.6378955841064
- actor/latency_mean:
  1,359.4797143638134
- actor/latency_min:
  1,300.41970205307
- actor/latency_var:
  2,062.363833716937
- actor/model_version_mean:
  0
- actor/never_success:
  1
- actor/no_answer_mean:
  0
- actor/no_error_max:
  1
- actor/no_error_mean:
  0.875
- actor/no_error_min:
  0
- actor/no_error_var:
  0.109375
- actor/num_turns_max:
  3
- actor/num_turns_mean:
  2.375
- actor/num_turns_min:
  2
- actor/num_turns_var:
  0.234375
- actor/open_reasoner_zero_57k/no_answer_mean:
  0
- actor/open_reasoner_zero_57k/no_error_max:
  1
- actor/open_reasoner_zero_57k/no_error_mean:
  0.875
- actor/open_reasoner_zero_57k/no_error_min:
  0
- actor/open_reasoner_zero_57k/no_error_var:
  0.109375
- actor/open_reasoner_zero_57k/num_turns_max:
  3
- actor/open_reasoner_zero_57k/num_turns_mean:
  2.375
- actor/open_reasoner_zero_57k/num_turns_min:
  2
- actor/open_reasoner_zero_57k/num_turns_var:
  0.234375
- actor/open_reasoner_zero_57k/output_tokens_max:
  744
- actor/open_reasoner_zero_57k/output_tokens_mean:
  441.2631578947368
- actor/open_reasoner_zero_57k/output_tokens_min:
  96
- actor/open_reasoner_zero_57k/output_tokens_var:
  44,669.6675900277
- actor/open_reasoner_zero_57k/overflow_mean:
  0
- actor/open_reasoner_zero_57k/prompt_tokens_max:
  750
- actor/open_reasoner_zero_57k/prompt_tokens_mean:
  351.89473684210526
- actor/open_reasoner_zero_57k/prompt_tokens_min:
  200
- actor/open_reasoner_zero_57k/prompt_tokens_var:
  28,919.46260387812
- actor/open_reasoner_zero_57k/reward_max:
  0
- actor/open_reasoner_zero_57k/reward_mean:
  -0.00625
- actor/open_reasoner_zero_57k/reward_min:
  -0.05
- actor/open_reasoner_zero_57k/reward_var:
  0.0002734375000000001
- actor/open_reasoner_zero_57k/success_mean:
  0
- actor/open_reasoner_zero_57k/timeout_mean:
  0
- actor/open_reasoner_zero_extended_72k/no_answer_mean:
  0
- actor/open_reasoner_zero_extended_72k/no_error_mean:
  0
- actor/open_reasoner_zero_extended_72k/num_turns_mean:
  8
- actor/open_reasoner_zero_extended_72k/output_tokens_max:
  1,025
- actor/open_reasoner_zero_extended_72k/output_tokens_mean:
  677.875
- actor/sometimes_success:
  0
- actor/success_mean:
  0
- actor/time_since_start:
  1,416.71457529068
- actor/timeout_mean:
  0

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

wandb-history

run-debug_actor_tir_actor-history:v0