rirv938-anthropic-grpo-4_2727

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-4_2727_v1

model_name: rirv938-anthropic-grpo-4_2727_v1

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-15T02:56:07+00:00

num_battles: 6926

num_wins: 3564

celo_rating: 1298.31

family_friendly_score: 0.5486

family_friendly_standard_error: 0.007037585381364833

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp888_95ff_20ww2_merged

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.645931495904715, 'latency_mean': 1.5480721855163575, 'latency_p50': 1.5473994016647339, 'latency_p90': 1.7150819301605225}, {'batch_size': 3, 'throughput': 1.2420604821164376, 'latency_mean': 2.4067869448661803, 'latency_p50': 2.3924823999404907, 'latency_p90': 2.682633137702942}, {'batch_size': 5, 'throughput': 1.52264105056578, 'latency_mean': 3.270918273925781, 'latency_p50': 3.269237756729126, 'latency_p90': 3.6808242559432984}, {'batch_size': 6, 'throughput': 1.61063054003884, 'latency_mean': 3.710351641178131, 'latency_p50': 3.705280900001526, 'latency_p90': 4.180702590942383}, {'batch_size': 8, 'throughput': 1.7003991156392486, 'latency_mean': 4.672051575183868, 'latency_p50': 4.643439412117004, 'latency_p90': 5.28389036655426}, {'batch_size': 10, 'throughput': 1.729609590213557, 'latency_mean': 5.732265038490295, 'latency_p50': 5.754863977432251, 'latency_p90': 6.470412850379944}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-4_2727_v1

ineligible_reason: num_battles<10000

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp888_95ff_20ww2_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.62

us_pacific_date: 2025-05-14

win_ratio: 0.5145827317354894

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': ['</s>', '\n', 'You:', '###'], 'max_input_tokens': 768, '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-4-2727-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-4-2727-v1-mkmlizer to finish
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: Downloaded to shared memory in 86.488s
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp69vrn4_s, device:0
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: quantized model in 42.101s
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp888_95ff_20ww2_merged in 128.590s
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-2727-v1
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-2727-v1/config.json
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-2727-v1/special_tokens_map.json
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-2727-v1/tokenizer_config.json
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-4-2727-v1/tokenizer.json
rirv938-anthropic-grpo-4-2727-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.41it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.26it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.68it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 30.88it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:14, 22.68it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:16, 20.32it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 26.11it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:11, 27.40it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.77it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 28.10it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.29it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.97it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 27.89it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 30.15it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 20.28it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 26.62it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 26.54it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:11, 24.80it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 27.53it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.86it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 31.37it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 28.84it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.66it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 21.05it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:09, 26.05it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:10, 23.94it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 30.35it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.14it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.38it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 28.92it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 29.19it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 24.96it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:09, 23.67it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 22.60it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:07, 29.24it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 28.48it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 30.20it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 28.74it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.47it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.69it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 22.81it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 20.49it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:06, 25.87it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:07, 23.10it/s]
Loading 0:  55%|█████▍    | 199/363 [00:07<00:05, 27.70it/s]
Loading 0:  56%|█████▌    | 203/363 [00:07<00:06, 24.77it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 30.79it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:05, 29.12it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:05, 28.93it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 24.95it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 23.63it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 22.17it/s]
Loading 0:  65%|██████▍   | 235/363 [00:08<00:04, 27.22it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:04, 24.88it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 30.90it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 29.17it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 30.87it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 29.55it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 23.96it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 21.17it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 27.90it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 27.32it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 29.45it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.57it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 30.30it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 28.80it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 28.82it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 24.50it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 23.15it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 22.00it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 28.52it/s]
Loading 0:  89%|████████▊ | 322/363 [00:12<00:01, 27.78it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 29.91it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 29.04it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 31.15it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.81it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.96it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.63it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:02,  3.81it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.92it/s]
Loading 0: 100%|█████████▉| 362/363 [00:20<00:00,  7.02it/s]
                                                            
Job rirv938-anthropic-grpo-4-2727-v1-mkmlizer completed after 155.2s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-4-2727-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.85s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-4-2727-v1
Waiting for inference service rirv938-anthropic-grpo-4-2727-v1 to be ready
Inference service rirv938-anthropic-grpo-4-2727-v1 ready after 130.76373100280762s
Pipeline stage MKMLDeployer completed in 131.37s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3152565956115723s
Received healthy response to inference request in 1.660691738128662s
Received healthy response to inference request in 1.6716818809509277s
Received healthy response to inference request in 1.6008391380310059s
Received healthy response to inference request in 1.7410972118377686s
5 requests
0 failed requests
5th percentile: 1.612809658050537
10th percentile: 1.6247801780700684
20th percentile: 1.6487212181091309
30th percentile: 1.6628897666931153
40th percentile: 1.6672858238220214
50th percentile: 1.6716818809509277
60th percentile: 1.699448013305664
70th percentile: 1.7272141456604004
80th percentile: 1.8559290885925295
90th percentile: 2.085592842102051
95th percentile: 2.2004247188568113
99th percentile: 2.29229022026062
mean time: 1.7979133129119873
Pipeline stage StressChecker completed in 10.50s
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 0.68s
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 0.69s
Shutdown handler de-registered
rirv938-anthropic-grpo-4_2727_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-anthropic-grpo-4-2727-v1-profiler
Waiting for inference service rirv938-anthropic-grpo-4-2727-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2706.15s
Shutdown handler de-registered
rirv938-anthropic-grpo-4_2727_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-4_2727_v1 status is now torndown due to DeploymentManager action