rirv938-anthropic-grpo-4_3092

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-4_3092_v1

model_name: rirv938-anthropic-grpo-4_3092_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-04-29T18:35:57+00:00

num_battles: 6855

num_wins: 3717

celo_rating: 1334.27

family_friendly_score: 0.5626

family_friendly_standard_error: 0.0070154292812343285

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp888_95ff_merged

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6083273990660307, 'latency_mean': 1.6437728381156922, 'latency_p50': 1.6397936344146729, 'latency_p90': 1.832322120666504}, {'batch_size': 3, 'throughput': 1.1179559091142721, 'latency_mean': 2.677144411802292, 'latency_p50': 2.706753969192505, 'latency_p90': 2.9179177284240723}, {'batch_size': 5, 'throughput': 1.3597598736962166, 'latency_mean': 3.6644118309020994, 'latency_p50': 3.685734510421753, 'latency_p90': 4.100092887878418}, {'batch_size': 6, 'throughput': 1.4238431913548117, 'latency_mean': 4.187776904106141, 'latency_p50': 4.197495818138123, 'latency_p90': 4.744076538085937}, {'batch_size': 8, 'throughput': 1.4869905529995173, 'latency_mean': 5.340777730941772, 'latency_p50': 5.293694019317627, 'latency_p90': 6.082207417488098}, {'batch_size': 10, 'throughput': 1.526030677418754, 'latency_mean': 6.502855379581451, 'latency_p50': 6.518772840499878, 'latency_p90': 7.264240384101868}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-4_3092_v1

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp888_95ff_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.37

us_pacific_date: 2025-04-29

win_ratio: 0.5422319474835886

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['###', '\n', '</s>', 'You:'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name rirv938-anthropic-grpo-4-3092-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-4-3092-v1-mkmlizer to finish
rirv938-anthropic-grpo-4-3092-v1-mkmlizer: Downloaded to shared memory in 84.676s
rirv938-anthropic-grpo-4-3092-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpui4ng9r9, device:0
rirv938-anthropic-grpo-4-3092-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-4-3092-v1-mkmlizer: quantized model in 43.283s
rirv938-anthropic-grpo-4-3092-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp888_95ff_merged in 127.960s
rirv938-anthropic-grpo-4-3092-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-4-3092-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-4-3092-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-3092-v1
rirv938-anthropic-grpo-4-3092-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-3092-v1/config.json
rirv938-anthropic-grpo-4-3092-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-3092-v1/special_tokens_map.json
rirv938-anthropic-grpo-4-3092-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-3092-v1/tokenizer_config.json
rirv938-anthropic-grpo-4-3092-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-3092-v1/tokenizer.json
rirv938-anthropic-grpo-4-3092-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-3092-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-4-3092-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.67it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 26.28it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:15, 23.26it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 29.06it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:15, 21.32it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:17, 19.03it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 24.83it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 25.82it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:12, 26.58it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:13, 24.04it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 26.84it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:13, 23.35it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:10, 28.13it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 29.47it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 19.50it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:12, 24.04it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:12, 23.97it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 22.27it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.67it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 23.76it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 28.13it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:10, 24.77it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:09, 28.91it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 19.27it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 23.83it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 22.29it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 26.17it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 23.18it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 27.45it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 24.30it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 28.55it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 29.28it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:10, 20.63it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 20.15it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 24.60it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:09, 22.72it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 27.11it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:08, 23.89it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 28.21it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 24.88it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 28.78it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 19.25it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.56it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:07, 22.19it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 26.52it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 24.02it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 28.31it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:06, 24.99it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:05, 29.15it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 29.90it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 21.14it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 20.45it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 24.86it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 22.97it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 27.15it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:04, 24.44it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:03, 28.63it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 25.20it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 29.28it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:05, 19.37it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:03, 23.63it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:03, 22.02it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 26.58it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 24.16it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:02, 28.68it/s]
Loading 0:  81%|████████  | 293/363 [00:11<00:02, 25.44it/s]
Loading 0:  82%|████████▏ | 298/363 [00:12<00:02, 28.52it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:02, 28.59it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 20.76it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 20.54it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 25.15it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 23.52it/s]
Loading 0:  90%|████████▉ | 325/363 [00:13<00:01, 28.16it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 25.15it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:00, 29.69it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:00, 26.07it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 30.55it/s]
Loading 0:  96%|█████████▌| 347/363 [00:20<00:08,  1.99it/s]
Loading 0:  96%|█████████▋| 350/363 [00:20<00:05,  2.51it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:03,  3.19it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.35it/s]
Loading 0: 100%|█████████▉| 362/363 [00:21<00:00,  6.46it/s]
                                                            
Job rirv938-anthropic-grpo-4-3092-v1-mkmlizer completed after 155.2s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-4-3092-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.70s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-4-3092-v1
Waiting for inference service rirv938-anthropic-grpo-4-3092-v1 to be ready
Inference service rirv938-anthropic-grpo-4-3092-v1 ready after 140.6309313774109s
Pipeline stage MKMLDeployer completed in 141.17s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.29219126701355s
Received healthy response to inference request in 1.7513933181762695s
Received healthy response to inference request in 1.687009572982788s
Received healthy response to inference request in 1.6817424297332764s
Received healthy response to inference request in 1.645042896270752s
5 requests
0 failed requests
5th percentile: 1.6523828029632568
10th percentile: 1.6597227096557616
20th percentile: 1.6744025230407715
30th percentile: 1.6827958583831788
40th percentile: 1.6849027156829834
50th percentile: 1.687009572982788
60th percentile: 1.7127630710601807
70th percentile: 1.7385165691375732
80th percentile: 1.8595529079437256
90th percentile: 2.0758720874786376
95th percentile: 2.1840316772460935
99th percentile: 2.2705593490600586
mean time: 1.811475896835327
Pipeline stage StressChecker completed in 10.38s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.67s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.66s
Shutdown handler de-registered
rirv938-anthropic-grpo-4_3092_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5811.54s
Shutdown handler de-registered
rirv938-anthropic-grpo-4_3092_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-4_3092_v1 status is now torndown due to DeploymentManager action