developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_26753_v1
model_name: rirv938-anthropic-grpo-_26753_v1
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-05-18T15:18:27+00:00
num_battles: 7933
num_wins: 3933
celo_rating: 1287.39
family_friendly_score: 0.5147999999999999
family_friendly_standard_error: 0.007067969439662285
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp124_98ff_g4b15_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': 0.647036024599153, 'latency_mean': 1.5454127764701844, 'latency_p50': 1.535514235496521, 'latency_p90': 1.7316355228424072}, {'batch_size': 3, 'throughput': 1.2046827391989283, 'latency_mean': 2.48469703912735, 'latency_p50': 2.5043755769729614, 'latency_p90': 2.7187718868255617}, {'batch_size': 5, 'throughput': 1.5025944161365583, 'latency_mean': 3.313098895549774, 'latency_p50': 3.286884069442749, 'latency_p90': 3.6608466148376464}, {'batch_size': 6, 'throughput': 1.5686312407541518, 'latency_mean': 3.808224585056305, 'latency_p50': 3.8433785438537598, 'latency_p90': 4.240277552604676}, {'batch_size': 8, 'throughput': 1.6665811681899552, 'latency_mean': 4.7761056578159335, 'latency_p50': 4.7759668827056885, 'latency_p90': 5.323833680152893}, {'batch_size': 10, 'throughput': 1.7142766886816523, 'latency_mean': 5.776667997837067, 'latency_p50': 5.799308180809021, 'latency_p90': 6.51994297504425}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_26753_v1
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp124_98ff_g4b15_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.56
us_pacific_date: 2025-05-18
win_ratio: 0.4957771334930039
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': 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-26753-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-26753-v1-mkmlizer to finish
rirv938-anthropic-grpo-26753-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-26753-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-26753-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-26753-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-26753-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-26753-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-26753-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-26753-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-26753-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-26753-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-26753-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-26753-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-26753-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-26753-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-26753-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-26753-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-26753-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-26753-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-26753-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-26753-v1-mkmlizer: Downloaded to shared memory in 87.942s
rirv938-anthropic-grpo-26753-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgyog44m0, device:0
rirv938-anthropic-grpo-26753-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-26753-v1-mkmlizer: quantized model in 41.995s
rirv938-anthropic-grpo-26753-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp124_98ff_g4b15_merged in 129.938s
rirv938-anthropic-grpo-26753-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-26753-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-26753-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-26753-v1
rirv938-anthropic-grpo-26753-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-26753-v1/config.json
rirv938-anthropic-grpo-26753-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-26753-v1/special_tokens_map.json
rirv938-anthropic-grpo-26753-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-26753-v1/tokenizer_config.json
rirv938-anthropic-grpo-26753-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-26753-v1/tokenizer.json
rirv938-anthropic-grpo-26753-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-26753-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-26753-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<00:12, 27.36it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 23.89it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 30.56it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:15, 21.94it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:17, 19.63it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 25.10it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 26.04it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 27.40it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:12, 26.55it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 29.52it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:11, 28.01it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:11, 27.79it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:13, 23.20it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 20.72it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 27.36it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:10, 27.36it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 23.00it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 29.63it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 27.64it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:09, 29.71it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 28.51it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 22.64it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:12, 20.52it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 27.19it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:09, 25.63it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 30.17it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.09it/s]
Loading 0:  35%|███▌      | 128/363 [00:04<00:07, 31.21it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:08, 27.28it/s]
Loading 0:  38%|███▊      | 137/363 [00:05<00:07, 29.38it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 31.30it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:10, 21.69it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 21.42it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:07, 27.85it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:07, 27.03it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:06, 29.06it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 27.81it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.14it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 29.02it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 22.92it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 20.88it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:06, 25.59it/s]
Loading 0:  53%|█████▎    | 194/363 [00:07<00:07, 23.31it/s]
Loading 0:  55%|█████▍    | 199/363 [00:07<00:05, 28.35it/s]
Loading 0:  56%|█████▌    | 203/363 [00:07<00:06, 25.57it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 31.60it/s]
Loading 0:  59%|█████▉    | 214/363 [00:08<00:04, 29.94it/s]
Loading 0:  60%|██████    | 218/363 [00:08<00:04, 30.01it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 24.87it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 23.48it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 22.55it/s]
Loading 0:  65%|██████▍   | 235/363 [00:08<00:04, 27.60it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:04, 25.13it/s]
Loading 0:  68%|██████▊   | 246/363 [00:09<00:03, 31.32it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 29.16it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 30.50it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 28.45it/s]
Loading 0:  72%|███████▏  | 263/363 [00:10<00:04, 22.03it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 20.07it/s]
Loading 0:  75%|███████▍  | 271/363 [00:10<00:03, 25.34it/s]
Loading 0:  76%|███████▌  | 275/363 [00:10<00:03, 23.69it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 30.02it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.88it/s]
Loading 0:  80%|████████  | 291/363 [00:11<00:02, 30.64it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 29.33it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 29.52it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 24.85it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 23.79it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 22.85it/s]
Loading 0:  88%|████████▊ | 318/363 [00:12<00:01, 29.49it/s]
Loading 0:  89%|████████▊ | 322/363 [00:12<00:01, 28.69it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 30.64it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 29.51it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 31.43it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.88it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.99it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.68it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.89it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  5.01it/s]
                                                            

Job rirv938-anthropic-grpo-26753-v1-mkmlizer completed after 155.72s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-26753-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.22s
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-26753-v1
Waiting for inference service rirv938-anthropic-grpo-26753-v1 to be ready
Inference service rirv938-anthropic-grpo-26753-v1 ready after 140.59780311584473s
Pipeline stage MKMLDeployer completed in 141.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4320859909057617s
Received healthy response to inference request in 1.7626357078552246s
Received healthy response to inference request in 1.8096599578857422s
Received healthy response to inference request in 1.5304970741271973s
Received healthy response to inference request in 1.6101467609405518s
5 requests
0 failed requests
5th percentile: 1.5464270114898682
10th percentile: 1.562356948852539
20th percentile: 1.5942168235778809
30th percentile: 1.6406445503234863
40th percentile: 1.7016401290893555
50th percentile: 1.7626357078552246
60th percentile: 1.7814454078674316
70th percentile: 1.8002551078796387
80th percentile: 1.9341451644897463
90th percentile: 2.183115577697754
95th percentile: 2.3076007843017576
99th percentile: 2.407188949584961
mean time: 1.8290050983428956
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 0.74s
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 0.65s
Shutdown handler de-registered
rirv938-anthropic-grpo-_26753_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-anthropic-grpo-26753-v1-profiler
Waiting for inference service rirv938-anthropic-grpo-26753-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 3067.54s
Shutdown handler de-registered
rirv938-anthropic-grpo-_26753_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_26753_v1 status is now torndown due to DeploymentManager action