rirv938-anthropic-grpo-_74918

developer_uid: rirv938

submission_id: rirv938-anthropic-grpo-_74918_v3

model_name: rirv938-anthropic-grpo-_74918_v3

model_group: rirv938/anthropic_grpo_4

status: torndown

timestamp: 2025-05-14T00:12:36+00:00

num_battles: 7544

num_wins: 4042

celo_rating: 1299.72

family_friendly_score: 0.5472

family_friendly_standard_error: 0.0070394908906823645

submission_type: basic

model_repo: rirv938/anthropic_grpo_40k_cp1184_95ff_20ww_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': 0.6476541032004507, 'latency_mean': 1.543948302268982, 'latency_p50': 1.5411949157714844, 'latency_p90': 1.723906445503235}, {'batch_size': 3, 'throughput': 1.2360928415383476, 'latency_mean': 2.4151517176628112, 'latency_p50': 2.421067714691162, 'latency_p90': 2.6614611625671385}, {'batch_size': 5, 'throughput': 1.52927964017207, 'latency_mean': 3.2493306279182432, 'latency_p50': 3.221998453140259, 'latency_p90': 3.6790512561798097}, {'batch_size': 6, 'throughput': 1.6516774251271735, 'latency_mean': 3.6124659955501555, 'latency_p50': 3.601884961128235, 'latency_p90': 4.079231071472168}, {'batch_size': 8, 'throughput': 1.7359178788746834, 'latency_mean': 4.570684406757355, 'latency_p50': 4.57954740524292, 'latency_p90': 5.1453831672668455}, {'batch_size': 10, 'throughput': 1.7802274641103304, 'latency_mean': 5.573225737810135, 'latency_p50': 5.523741841316223, 'latency_p90': 6.288530588150024}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-anthropic-grpo-_74918_v3

is_internal_developer: True

language_model: rirv938/anthropic_grpo_40k_cp1184_95ff_20ww_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.67

us_pacific_date: 2025-05-13

win_ratio: 0.5357900318133616

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>', 'You:', '###', '\n'], '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-74918-v3-mkmlizer
Waiting for job on rirv938-anthropic-grpo-74918-v3-mkmlizer to finish
rirv938-anthropic-grpo-74918-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-74918-v3-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-74918-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-74918-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-74918-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-74918-v3-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-74918-v3-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74918-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-74918-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-74918-v3-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-74918-v3-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74918-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-74918-v3-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-74918-v3-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74918-v3-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-74918-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-74918-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-74918-v3-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74918-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-74918-v3-mkmlizer: Downloaded to shared memory in 136.321s
rirv938-anthropic-grpo-74918-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpz9utpmo1, device:0
rirv938-anthropic-grpo-74918-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-74918-v3-mkmlizer: quantized model in 41.023s
rirv938-anthropic-grpo-74918-v3-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp1184_95ff_20ww_merged in 177.345s
rirv938-anthropic-grpo-74918-v3-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-74918-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-74918-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-74918-v3
rirv938-anthropic-grpo-74918-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74918-v3/config.json
rirv938-anthropic-grpo-74918-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74918-v3/special_tokens_map.json
rirv938-anthropic-grpo-74918-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74918-v3/tokenizer_config.json
rirv938-anthropic-grpo-74918-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74918-v3/tokenizer.json
rirv938-anthropic-grpo-74918-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-74918-v3/flywheel_model.0.safetensors
rirv938-anthropic-grpo-74918-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.59it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.73it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.22it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 33.92it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:14, 23.82it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:14, 22.68it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 26.13it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 26.95it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.43it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 27.38it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.26it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.81it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 29.45it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:09, 31.86it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 20.79it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 27.65it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 27.17it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.52it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 29.19it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 27.99it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 30.82it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 29.46it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 24.56it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 21.77it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 29.28it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 29.02it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 31.93it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.94it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 32.32it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 30.59it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 31.16it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 27.93it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 25.70it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:08, 24.46it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 31.59it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 30.07it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.33it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.75it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 32.66it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 30.91it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 25.24it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 21.75it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 28.86it/s]
Loading 0:  54%|█████▍    | 196/363 [00:06<00:05, 28.34it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 31.22it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.83it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 32.53it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 31.01it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 31.06it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:05, 26.69it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 25.00it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.95it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 31.17it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 29.92it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 32.74it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 31.69it/s]
Loading 0:  70%|███████   | 255/363 [00:08<00:03, 33.70it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 31.73it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:03, 26.09it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 22.47it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 29.92it/s]
Loading 0:  76%|███████▋  | 277/363 [00:09<00:03, 28.45it/s]
Loading 0:  78%|███████▊  | 282/363 [00:09<00:02, 30.76it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 29.75it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 32.38it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 30.36it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 30.46it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 26.71it/s]
Loading 0:  85%|████████▍ | 307/363 [00:10<00:02, 24.84it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.27it/s]
Loading 0:  87%|████████▋ | 316/363 [00:11<00:01, 28.39it/s]
Loading 0:  88%|████████▊ | 320/363 [00:11<00:01, 25.57it/s]
Loading 0:  90%|████████▉ | 325/363 [00:11<00:01, 30.29it/s]
Loading 0:  91%|█████████ | 329/363 [00:11<00:01, 26.43it/s]
Loading 0:  93%|█████████▎| 336/363 [00:11<00:00, 32.67it/s]
Loading 0:  94%|█████████▎| 340/363 [00:11<00:00, 30.73it/s]
Loading 0:  95%|█████████▍| 344/363 [00:18<00:09,  2.06it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.74it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.93it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.07it/s]
                                                            
Job rirv938-anthropic-grpo-74918-v3-mkmlizer completed after 206.72s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-74918-v3-mkmlizer
Pipeline stage MKMLizer completed in 207.24s
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-74918-v3
Waiting for inference service rirv938-anthropic-grpo-74918-v3 to be ready
Inference service rirv938-anthropic-grpo-74918-v3 ready after 120.51285529136658s
Pipeline stage MKMLDeployer completed in 121.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2159624099731445s
Received healthy response to inference request in 1.6581029891967773s
Received healthy response to inference request in 1.7438018321990967s
Received healthy response to inference request in 1.6706478595733643s
Received healthy response to inference request in 1.6493403911590576s
5 requests
0 failed requests
5th percentile: 1.6510929107666015
10th percentile: 1.6528454303741456
20th percentile: 1.6563504695892335
30th percentile: 1.6606119632720948
40th percentile: 1.6656299114227295
50th percentile: 1.6706478595733643
60th percentile: 1.6999094486236572
70th percentile: 1.7291710376739502
80th percentile: 1.8382339477539062
90th percentile: 2.0270981788635254
95th percentile: 2.121530294418335
99th percentile: 2.1970759868621825
mean time: 1.787571096420288
Pipeline stage StressChecker completed in 10.25s
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 0.71s
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 0.83s
Shutdown handler de-registered
rirv938-anthropic-grpo-_74918_v3 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-74918-v3-profiler
Waiting for inference service rirv938-anthropic-grpo-74918-v3-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4773.12s
Shutdown handler de-registered
rirv938-anthropic-grpo-_74918_v3 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_74918_v3 status is now torndown due to DeploymentManager action