developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_74918_v1
model_name: rirv938-anthropic-grpo-_74918_v1
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-05-13T16:36:46+00:00
num_battles: 8792
num_wins: 4515
celo_rating: 1293.1
family_friendly_score: 0.5564
family_friendly_standard_error: 0.007025938229161996
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': 0.6464866390495744, 'latency_mean': 1.5467547869682312, 'latency_p50': 1.5357632637023926, 'latency_p90': 1.714343285560608}, {'batch_size': 3, 'throughput': 1.233557704373271, 'latency_mean': 2.4224642515182495, 'latency_p50': 2.4412471055984497, 'latency_p90': 2.6830262660980226}, {'batch_size': 5, 'throughput': 1.5296448475526265, 'latency_mean': 3.252892107963562, 'latency_p50': 3.2517439126968384, 'latency_p90': 3.580849719047546}, {'batch_size': 6, 'throughput': 1.6327192118038103, 'latency_mean': 3.6472879743576048, 'latency_p50': 3.6510990858078003, 'latency_p90': 4.159001398086548}, {'batch_size': 8, 'throughput': 1.716516970825288, 'latency_mean': 4.628017309904099, 'latency_p50': 4.638809680938721, 'latency_p90': 5.252558779716492}, {'batch_size': 10, 'throughput': 1.7716743332069471, 'latency_mean': 5.597040694952011, 'latency_p50': 5.56649923324585, 'latency_p90': 6.268550276756287}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_74918_v1
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp1184_95ff_20ww_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.65
us_pacific_date: 2025-05-13
win_ratio: 0.5135350318471338
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-74918-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-74918-v1-mkmlizer to finish
rirv938-anthropic-grpo-74918-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-74918-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-74918-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-74918-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-74918-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-74918-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-74918-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74918-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-74918-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-74918-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-74918-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74918-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-74918-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-74918-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74918-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-74918-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-74918-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-74918-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-74918-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-74918-v1-mkmlizer: Downloaded to shared memory in 84.650s
rirv938-anthropic-grpo-74918-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpknxjk1nj, device:0
rirv938-anthropic-grpo-74918-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-74918-v1-mkmlizer: quantized model in 40.943s
rirv938-anthropic-grpo-74918-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp1184_95ff_20ww_merged in 125.594s
rirv938-anthropic-grpo-74918-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-74918-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-74918-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-74918-v1
rirv938-anthropic-grpo-74918-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74918-v1/config.json
rirv938-anthropic-grpo-74918-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74918-v1/special_tokens_map.json
rirv938-anthropic-grpo-74918-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74918-v1/tokenizer_config.json
rirv938-anthropic-grpo-74918-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-74918-v1/tokenizer.json
rirv938-anthropic-grpo-74918-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-74918-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-74918-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.04it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.73it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.73it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:09, 34.65it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:14, 24.12it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:13, 24.47it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:13, 23.75it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 30.48it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 29.07it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 31.12it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.81it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:10, 29.73it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 25.05it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.21it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 27.03it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:10, 26.46it/s]
Loading 0:  21%|██        | 77/363 [00:02<00:11, 24.69it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:08, 31.26it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 30.08it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 31.69it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.41it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 24.54it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 21.92it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 28.91it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 28.55it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 30.97it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.84it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 31.89it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 30.61it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 30.49it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.66it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 24.30it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.16it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 29.96it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 29.20it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.14it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 30.09it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 32.42it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.46it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.26it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 21.93it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 28.89it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:05, 27.98it/s]
Loading 0:  55%|█████▍    | 199/363 [00:07<00:05, 28.01it/s]
Loading 0:  56%|█████▌    | 203/363 [00:07<00:06, 25.45it/s]
Loading 0:  57%|█████▋    | 208/363 [00:07<00:05, 29.96it/s]
Loading 0:  58%|█████▊    | 212/363 [00:07<00:05, 26.92it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 31.52it/s]
Loading 0:  61%|██████▏   | 223/363 [00:08<00:05, 27.39it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 25.76it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 24.67it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 30.72it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 29.07it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 30.87it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:03, 29.69it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 31.63it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 29.66it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.43it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 21.90it/s]
Loading 0:  75%|███████▍  | 271/363 [00:09<00:03, 26.57it/s]
Loading 0:  76%|███████▌  | 275/363 [00:09<00:03, 24.75it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 31.33it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 30.01it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 32.26it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 30.90it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 30.51it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 26.17it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 24.77it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 23.65it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 30.57it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 29.79it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 32.00it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 30.64it/s]
Loading 0:  93%|█████████▎| 336/363 [00:11<00:00, 32.54it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 29.88it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.97it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.66it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.86it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.01it/s]
                                                            

Job rirv938-anthropic-grpo-74918-v1-mkmlizer completed after 146.73s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-74918-v1-mkmlizer
Pipeline stage MKMLizer completed in 147.27s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-74918-v1
Waiting for inference service rirv938-anthropic-grpo-74918-v1 to be ready
Inference service rirv938-anthropic-grpo-74918-v1 ready after 120.62780690193176s
Pipeline stage MKMLDeployer completed in 121.19s
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 2.3240530490875244s
Received healthy response to inference request in 1.8364112377166748s
Received healthy response to inference request in 1.8955612182617188s
Received healthy response to inference request in 1.6851913928985596s
5 requests
1 failed requests
5th percentile: 1.7154353618621827
10th percentile: 1.7456793308258056
20th percentile: 1.8061672687530517
30th percentile: 1.8482412338256835
40th percentile: 1.8719012260437011
50th percentile: 1.8955612182617188
60th percentile: 2.066957950592041
70th percentile: 2.2383546829223633
80th percentile: 5.887970876693728
90th percentile: 13.01580653190613
95th percentile: 16.579724359512326
99th percentile: 19.430858621597288
mean time: 5.576971817016601
%s, retrying in %s seconds...
Received healthy response to inference request in 1.7318081855773926s
Received healthy response to inference request in 1.8814146518707275s
Received healthy response to inference request in 1.5881679058074951s
Received healthy response to inference request in 1.6215448379516602s
Received healthy response to inference request in 1.8181328773498535s
5 requests
0 failed requests
5th percentile: 1.594843292236328
10th percentile: 1.6015186786651612
20th percentile: 1.6148694515228272
30th percentile: 1.6435975074768066
40th percentile: 1.6877028465270996
50th percentile: 1.7318081855773926
60th percentile: 1.766338062286377
70th percentile: 1.8008679389953612
80th percentile: 1.8307892322540282
90th percentile: 1.8561019420623779
95th percentile: 1.8687582969665528
99th percentile: 1.8788833808898926
mean time: 1.7282136917114257
Pipeline stage StressChecker completed in 39.39s
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 0.77s
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_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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-anthropic-grpo-74918-v1-profiler
Waiting for inference service rirv938-anthropic-grpo-74918-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5028.02s
Shutdown handler de-registered
rirv938-anthropic-grpo-_74918_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_74918_v1 status is now torndown due to DeploymentManager action