developer_uid: rirv938
submission_id: rirv938-rinen-grpo-40k-_48409_v1
model_name: rirv938-rinen-grpo-40k-_48409_v1
model_group: rirv938/rinen_grpo_40k_c
status: torndown
timestamp: 2025-04-30T02:47:57+00:00
num_battles: 5660
num_wins: 3202
celo_rating: 1338.95
family_friendly_score: 0.577
family_friendly_standard_error: 0.006986715966747181
submission_type: basic
model_repo: rirv938/rinen_grpo_40k_cp1184_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': 0.6068069027094753, 'latency_mean': 1.6478908348083496, 'latency_p50': 1.6589349508285522, 'latency_p90': 1.7987816095352174}, {'batch_size': 3, 'throughput': 1.122156118979074, 'latency_mean': 2.669678633213043, 'latency_p50': 2.676032066345215, 'latency_p90': 2.904188346862793}, {'batch_size': 5, 'throughput': 1.3592392492012613, 'latency_mean': 3.663669821023941, 'latency_p50': 3.682749390602112, 'latency_p90': 4.127211570739746}, {'batch_size': 6, 'throughput': 1.4328377527036515, 'latency_mean': 4.156929148435593, 'latency_p50': 4.168431282043457, 'latency_p90': 4.700275087356568}, {'batch_size': 8, 'throughput': 1.4739725315502057, 'latency_mean': 5.39551335811615, 'latency_p50': 5.410411477088928, 'latency_p90': 5.952403235435486}, {'batch_size': 10, 'throughput': 1.5325009096281041, 'latency_mean': 6.4710078930854795, 'latency_p50': 6.482734322547913, 'latency_p90': 7.29113540649414}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-rinen-grpo-40k-_48409_v1
is_internal_developer: True
language_model: rirv938/rinen_grpo_40k_cp1184_95ff_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.37
us_pacific_date: 2025-04-29
win_ratio: 0.5657243816254417
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|im_end|>', '</s>', 'User:', '<|eot_id|>', 'You:', '####', 'Bot:', '\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
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-rinen-grpo-40k-48409-v1-mkmlizer
Waiting for job on rirv938-rinen-grpo-40k-48409-v1-mkmlizer to finish
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: ║ _____ __ __ ║
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: ║ /___/ ║
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: ║ ║
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: ║ Version: 0.12.8 ║
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: ║ ║
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: ║ belonging to: ║
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: ║ ║
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: ║ ║
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: Downloaded to shared memory in 85.418s
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpb5pmi1v5, device:0
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: quantized model in 45.780s
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: Processed model rirv938/rinen_grpo_40k_cp1184_95ff_merged in 131.199s
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-48409-v1
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-48409-v1/config.json
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-48409-v1/special_tokens_map.json
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-48409-v1/tokenizer_config.json
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-48409-v1/tokenizer.json
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-rinen-grpo-40k-48409-v1/flywheel_model.0.safetensors
rirv938-rinen-grpo-40k-48409-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:09, 38.78it/s] Loading 0: 2%|▏ | 8/363 [00:00<00:14, 23.80it/s] Loading 0: 3%|▎ | 11/363 [00:00<00:13, 25.48it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:17, 19.61it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:13, 26.24it/s] Loading 0: 6%|▌ | 22/363 [00:00<00:12, 27.14it/s] Loading 0: 7%|▋ | 25/363 [00:01<00:19, 17.24it/s] Loading 0: 8%|▊ | 28/363 [00:01<00:18, 18.16it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:18, 18.33it/s] Loading 0: 10%|█ | 37/363 [00:01<00:13, 23.56it/s] Loading 0: 11%|█▏ | 41/363 [00:01<00:14, 21.55it/s] Loading 0: 13%|█▎ | 46/363 [00:02<00:12, 25.80it/s] Loading 0: 14%|█▍ | 50/363 [00:02<00:13, 23.10it/s] Loading 0: 15%|█▌ | 55/363 [00:02<00:11, 26.89it/s] Loading 0: 17%|█▋ | 60/363 [00:02<00:10, 28.03it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:16, 18.38it/s] Loading 0: 19%|█▉ | 69/363 [00:03<00:13, 22.59it/s] Loading 0: 20%|█▉ | 72/363 [00:03<00:13, 21.20it/s] Loading 0: 21%|██ | 77/363 [00:03<00:13, 21.52it/s] Loading 0: 23%|██▎ | 82/363 [00:03<00:11, 25.15it/s] Loading 0: 23%|██▎ | 85/363 [00:03<00:10, 26.04it/s] Loading 0: 24%|██▍ | 88/363 [00:03<00:11, 24.68it/s] Loading 0: 25%|██▌ | 91/363 [00:03<00:10, 24.75it/s] Loading 0: 26%|██▌ | 95/363 [00:04<00:12, 21.94it/s] Loading 0: 28%|██▊ | 100/363 [00:04<00:10, 26.27it/s] Loading 0: 28%|██▊ | 103/363 [00:04<00:13, 18.73it/s] Loading 0: 29%|██▉ | 106/363 [00:04<00:13, 19.41it/s] Loading 0: 30%|███ | 109/363 [00:04<00:12, 20.77it/s] Loading 0: 31%|███ | 113/363 [00:05<00:12, 19.54it/s] Loading 0: 33%|███▎ | 118/363 [00:05<00:10, 24.09it/s] Loading 0: 33%|███▎ | 121/363 [00:05<00:09, 25.30it/s] Loading 0: 34%|███▍ | 124/363 [00:05<00:10, 23.60it/s] Loading 0: 35%|███▍ | 127/363 [00:05<00:09, 24.91it/s] Loading 0: 36%|███▌ | 131/363 [00:05<00:10, 22.87it/s] Loading 0: 37%|███▋ | 136/363 [00:05<00:08, 28.32it/s] Loading 0: 39%|███▉ | 141/363 [00:06<00:07, 30.10it/s] Loading 0: 40%|███▉ | 145/363 [00:06<00:10, 20.57it/s] Loading 0: 41%|████ | 149/363 [00:06<00:10, 20.28it/s] Loading 0: 42%|████▏ | 154/363 [00:06<00:08, 24.89it/s] Loading 0: 44%|████▎ | 158/363 [00:06<00:09, 22.72it/s] Loading 0: 45%|████▍ | 163/363 [00:07<00:07, 26.80it/s] Loading 0: 46%|████▌ | 167/363 [00:07<00:08, 24.08it/s] Loading 0: 47%|████▋ | 172/363 [00:07<00:06, 27.97it/s] Loading 0: 48%|████▊ | 176/363 [00:07<00:08, 23.34it/s] Loading 0: 50%|████▉ | 181/363 [00:07<00:06, 27.26it/s] Loading 0: 51%|█████ | 185/363 [00:08<00:10, 17.59it/s] Loading 0: 52%|█████▏ | 190/363 [00:08<00:07, 21.64it/s] Loading 0: 53%|█████▎ | 193/363 [00:08<00:07, 22.87it/s] Loading 0: 54%|█████▍ | 196/363 [00:08<00:07, 22.46it/s] Loading 0: 55%|█████▍ | 199/363 [00:08<00:07, 23.23it/s] Loading 0: 56%|█████▌ | 203/363 [00:08<00:07, 21.03it/s] Loading 0: 57%|█████▋ | 208/363 [00:08<00:06, 25.62it/s] Loading 0: 58%|█████▊ | 212/363 [00:09<00:06, 22.70it/s] Loading 0: 60%|█████▉ | 217/363 [00:09<00:05, 26.83it/s] Loading 0: 61%|██████ | 222/363 [00:09<00:05, 27.93it/s] Loading 0: 62%|██████▏ | 226/363 [00:09<00:07, 19.28it/s] Loading 0: 63%|██████▎ | 230/363 [00:10<00:06, 19.10it/s] Loading 0: 65%|██████▍ | 235/363 [00:10<00:05, 23.54it/s] Loading 0: 66%|██████▌ | 239/363 [00:10<00:05, 22.18it/s] Loading 0: 67%|██████▋ | 244/363 [00:10<00:04, 26.43it/s] Loading 0: 68%|██████▊ | 248/363 [00:10<00:04, 23.52it/s] Loading 0: 70%|██████▉ | 253/363 [00:10<00:04, 27.46it/s] Loading 0: 71%|███████ | 257/363 [00:11<00:04, 24.41it/s] Loading 0: 72%|███████▏ | 262/363 [00:11<00:03, 28.24it/s] Loading 0: 73%|███████▎ | 266/363 [00:11<00:05, 18.57it/s] Loading 0: 75%|███████▍ | 271/363 [00:11<00:04, 22.83it/s] Loading 0: 76%|███████▌ | 275/363 [00:11<00:04, 21.42it/s] Loading 0: 77%|███████▋ | 280/363 [00:12<00:03, 25.25it/s] Loading 0: 78%|███████▊ | 284/363 [00:12<00:03, 22.20it/s] Loading 0: 80%|███████▉ | 289/363 [00:12<00:02, 26.11it/s] Loading 0: 81%|████████ | 293/363 [00:12<00:03, 23.27it/s] Loading 0: 82%|████████▏ | 298/363 [00:12<00:02, 27.00it/s] Loading 0: 83%|████████▎ | 303/363 [00:12<00:02, 27.56it/s] Loading 0: 85%|████████▍ | 307/363 [00:13<00:02, 18.97it/s] Loading 0: 86%|████████▌ | 311/363 [00:13<00:02, 18.53it/s] Loading 0: 87%|████████▋ | 316/363 [00:13<00:02, 22.49it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:02, 20.72it/s] Loading 0: 90%|████████▉ | 325/363 [00:14<00:01, 24.91it/s] Loading 0: 91%|█████████ | 329/363 [00:14<00:01, 23.01it/s] Loading 0: 92%|█████████▏| 334/363 [00:14<00:01, 27.30it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 24.29it/s] Loading 0: 94%|█████████▍| 343/363 [00:14<00:00, 28.32it/s] Loading 0: 96%|█████████▌| 347/363 [00:22<00:08, 1.91it/s] Loading 0: 96%|█████████▋| 350/363 [00:22<00:05, 2.40it/s] Loading 0: 97%|█████████▋| 353/363 [00:22<00:03, 3.05it/s] Loading 0: 98%|█████████▊| 357/363 [00:22<00:01, 4.14it/s] Loading 0: 100%|█████████▉| 362/363 [00:22<00:00, 6.15it/s]
Job rirv938-rinen-grpo-40k-48409-v1-mkmlizer completed after 179.18s with status: succeeded
Stopping job with name rirv938-rinen-grpo-40k-48409-v1-mkmlizer
Pipeline stage MKMLizer completed in 179.65s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-rinen-grpo-40k-48409-v1
Waiting for inference service rirv938-rinen-grpo-40k-48409-v1 to be ready
Inference service rirv938-rinen-grpo-40k-48409-v1 ready after 140.451669216156s
Pipeline stage MKMLDeployer completed in 140.88s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.2245869636535645s
Received healthy response to inference request in 1.681028127670288s
Received healthy response to inference request in 1.8954617977142334s
Received healthy response to inference request in 1.588102102279663s
5 requests
1 failed requests
5th percentile: 1.606687307357788
10th percentile: 1.625272512435913
20th percentile: 1.662442922592163
30th percentile: 1.7239148616790771
40th percentile: 1.8096883296966553
50th percentile: 1.8954617977142334
60th percentile: 2.027111864089966
70th percentile: 2.158761930465698
80th percentile: 5.809118604660037
90th percentile: 12.978181886672974
95th percentile: 16.562713527679442
99th percentile: 19.43033884048462
mean time: 5.507284832000733
%s, retrying in %s seconds...
Received healthy response to inference request in 1.654071569442749s
Received healthy response to inference request in 1.6819565296173096s
Received healthy response to inference request in 1.901991844177246s
Received healthy response to inference request in 1.6243104934692383s
Received healthy response to inference request in 1.768735408782959s
5 requests
0 failed requests
5th percentile: 1.6302627086639405
10th percentile: 1.6362149238586425
20th percentile: 1.6481193542480468
30th percentile: 1.659648561477661
40th percentile: 1.6708025455474853
50th percentile: 1.6819565296173096
60th percentile: 1.7166680812835693
70th percentile: 1.751379632949829
80th percentile: 1.7953866958618163
90th percentile: 1.8486892700195312
95th percentile: 1.8753405570983888
99th percentile: 1.8966615867614747
mean time: 1.7262131690979003
Pipeline stage StressChecker completed in 39.15s
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 0.69s
Shutdown handler de-registered
rirv938-rinen-grpo-40k-_48409_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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-rinen-grpo-40k-48409-v1-profiler
Waiting for inference service rirv938-rinen-grpo-40k-48409-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 2961.04s
Shutdown handler de-registered
rirv938-rinen-grpo-40k-_48409_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-rinen-grpo-40k-_48409_v1 status is now torndown due to DeploymentManager action