developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_82907_v1
model_name: rirv938-anthropic-grpo-_82907_v1
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-05-17T17:37:22+00:00
num_battles: 10081
num_wins: 5334
celo_rating: 1304.67
family_friendly_score: 0.5534
family_friendly_standard_error: 0.007030625007778469
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp1776_95ff_beta6_3_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': 0.6375668505811615, 'latency_mean': 1.5683995604515075, 'latency_p50': 1.568625569343567, 'latency_p90': 1.7388498067855835}, {'batch_size': 3, 'throughput': 1.2034634194045, 'latency_mean': 2.4813468515872956, 'latency_p50': 2.4613322019577026, 'latency_p90': 2.722324824333191}, {'batch_size': 5, 'throughput': 1.5079651903377478, 'latency_mean': 3.303269112110138, 'latency_p50': 3.298801064491272, 'latency_p90': 3.6667718648910523}, {'batch_size': 6, 'throughput': 1.5782988068365158, 'latency_mean': 3.7854882001876833, 'latency_p50': 3.8187557458877563, 'latency_p90': 4.200376677513122}, {'batch_size': 8, 'throughput': 1.6654805709565164, 'latency_mean': 4.755905656814575, 'latency_p50': 4.756083846092224, 'latency_p90': 5.351236581802368}, {'batch_size': 10, 'throughput': 1.7318611056645696, 'latency_mean': 5.725932395458221, 'latency_p50': 5.736968159675598, 'latency_p90': 6.4818476915359495}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-anthropic-grpo-_82907_v1
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp1776_95ff_beta6_3_merged
model_size: 13B
ranking_group: single
throughput_3p7s: 1.57
us_pacific_date: 2025-05-17
win_ratio: 0.5291141751810337
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': ['You:', '###', '</s>', '\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-82907-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-82907-v1-mkmlizer to finish
rirv938-anthropic-grpo-82907-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-82907-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-82907-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-82907-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-82907-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-82907-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-82907-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-82907-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-82907-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-82907-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-82907-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-82907-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-82907-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-82907-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-82907-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-82907-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-82907-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-82907-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-82907-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-82907-v1-mkmlizer: Downloaded to shared memory in 77.228s
rirv938-anthropic-grpo-82907-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpad4w423a, device:0
rirv938-anthropic-grpo-82907-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-82907-v1-mkmlizer: quantized model in 43.469s
rirv938-anthropic-grpo-82907-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp1776_95ff_beta6_3_merged in 120.698s
rirv938-anthropic-grpo-82907-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-82907-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-82907-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-82907-v1
rirv938-anthropic-grpo-82907-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-82907-v1/config.json
rirv938-anthropic-grpo-82907-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-82907-v1/special_tokens_map.json
rirv938-anthropic-grpo-82907-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-82907-v1/tokenizer_config.json
rirv938-anthropic-grpo-82907-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-82907-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-82907-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.38it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:13, 26.17it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:15, 23.18it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:11, 29.47it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:14, 22.84it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:16, 20.07it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 25.64it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 26.76it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 27.55it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:12, 26.44it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 28.76it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:11, 27.47it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 27.65it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 29.65it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 19.24it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:11, 25.73it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:11, 24.85it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:12, 22.36it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.99it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:12, 22.47it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:10, 27.08it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:11, 23.93it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:09, 27.91it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 18.80it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 23.40it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:11, 21.85it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 26.27it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:10, 23.55it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 27.43it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 24.00it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 28.46it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 29.05it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:10, 20.85it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 20.36it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 24.95it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:09, 22.59it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 26.92it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:08, 23.71it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:06, 28.12it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 24.22it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 28.19it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:09, 18.83it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.09it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:07, 21.34it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 25.80it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 23.12it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 27.75it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:06, 24.87it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:04, 29.63it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 30.33it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 20.83it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 20.28it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 25.20it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 23.24it/s]
Loading 0:  67%|██████▋   | 244/363 [00:09<00:04, 28.19it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:04, 25.34it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:03, 29.80it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 26.31it/s]
Loading 0:  72%|███████▏  | 263/363 [00:10<00:03, 25.54it/s]
Loading 0:  73%|███████▎  | 266/363 [00:10<00:04, 22.36it/s]
Loading 0:  75%|███████▌  | 273/363 [00:10<00:03, 28.55it/s]
Loading 0:  76%|███████▋  | 277/363 [00:11<00:03, 27.22it/s]
Loading 0:  78%|███████▊  | 282/363 [00:11<00:02, 28.96it/s]
Loading 0:  79%|███████▉  | 286/363 [00:11<00:02, 27.53it/s]
Loading 0:  80%|████████  | 291/363 [00:11<00:02, 29.32it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:02, 27.77it/s]
Loading 0:  82%|████████▏ | 299/363 [00:11<00:02, 27.45it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:02, 29.89it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 21.30it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 20.64it/s]
Loading 0:  87%|████████▋ | 316/363 [00:12<00:01, 25.63it/s]
Loading 0:  88%|████████▊ | 320/363 [00:12<00:01, 23.39it/s]
Loading 0:  90%|████████▉ | 325/363 [00:12<00:01, 28.03it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 24.89it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:00, 29.56it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:00, 25.49it/s]
Loading 0:  94%|█████████▍| 343/363 [00:13<00:00, 29.71it/s]
Loading 0:  96%|█████████▌| 347/363 [00:20<00:08,  1.96it/s]
Loading 0:  96%|█████████▋| 350/363 [00:20<00:05,  2.47it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:03,  3.16it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.31it/s]
                                                            

Job rirv938-anthropic-grpo-82907-v1-mkmlizer completed after 145.36s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-82907-v1-mkmlizer
Pipeline stage MKMLizer completed in 145.86s
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-82907-v1
Waiting for inference service rirv938-anthropic-grpo-82907-v1 to be ready
Inference service rirv938-anthropic-grpo-82907-v1 ready after 140.75610828399658s
Pipeline stage MKMLDeployer completed in 141.30s
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 2.0551531314849854s
Received healthy response to inference request in 1.6960129737854004s
Received healthy response to inference request in 1.7108345031738281s
Received healthy response to inference request in 1.561401605606079s
5 requests
1 failed requests
5th percentile: 1.5883238792419434
10th percentile: 1.6152461528778077
20th percentile: 1.669090700149536
30th percentile: 1.698977279663086
40th percentile: 1.704905891418457
50th percentile: 1.7108345031738281
60th percentile: 1.848561954498291
70th percentile: 1.9862894058227538
80th percentile: 5.68144340515137
90th percentile: 12.934023952484132
95th percentile: 16.56031422615051
99th percentile: 19.461346445083617
mean time: 5.4420013427734375
%s, retrying in %s seconds...
Received healthy response to inference request in 1.7371461391448975s
Received healthy response to inference request in 1.579667329788208s
Received healthy response to inference request in 1.6159577369689941s
Received healthy response to inference request in 1.834717035293579s
Received healthy response to inference request in 1.4865326881408691s
5 requests
0 failed requests
5th percentile: 1.505159616470337
10th percentile: 1.5237865447998047
20th percentile: 1.5610404014587402
30th percentile: 1.5869254112243651
40th percentile: 1.6014415740966796
50th percentile: 1.6159577369689941
60th percentile: 1.6644330978393556
70th percentile: 1.7129084587097168
80th percentile: 1.7566603183746339
90th percentile: 1.7956886768341065
95th percentile: 1.8152028560638427
99th percentile: 1.830814199447632
mean time: 1.6508041858673095
Pipeline stage StressChecker completed in 37.99s
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 0.89s
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 0.73s
Shutdown handler de-registered
rirv938-anthropic-grpo-_82907_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 0.14s
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-82907-v1-profiler
Waiting for inference service rirv938-anthropic-grpo-82907-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 4782.47s
Shutdown handler de-registered
rirv938-anthropic-grpo-_82907_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_82907_v1 status is now torndown due to DeploymentManager action