rirv938-snug-grpo-40k-c_63788

developer_uid: rirv938

submission_id: rirv938-snug-grpo-40k-c_63788_v1

model_name: rirv938-snug-grpo-40k-c_63788_v1

model_group: rirv938/snug_grpo_40k_cp

status: torndown

timestamp: 2025-05-01T16:29:04+00:00

num_battles: 5582

num_wins: 2832

celo_rating: 1292.8

family_friendly_score: 0.5236000000000001

family_friendly_standard_error: 0.007063186816161669

submission_type: basic

model_repo: rirv938/snug_grpo_40k_cp1184_93ff_b_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': 0.6041223615397281, 'latency_mean': 1.6551966083049774, 'latency_p50': 1.6593151092529297, 'latency_p90': 1.8225970268249512}, {'batch_size': 3, 'throughput': 1.1152663530406375, 'latency_mean': 2.684038836956024, 'latency_p50': 2.6786367893218994, 'latency_p90': 2.953613042831421}, {'batch_size': 5, 'throughput': 1.3283390644444335, 'latency_mean': 3.745614368915558, 'latency_p50': 3.7138198614120483, 'latency_p90': 4.181739926338196}, {'batch_size': 6, 'throughput': 1.39770101312716, 'latency_mean': 4.27405750989914, 'latency_p50': 4.269163608551025, 'latency_p90': 4.774715805053711}, {'batch_size': 8, 'throughput': 1.457338089859618, 'latency_mean': 5.454902219772339, 'latency_p50': 5.47579550743103, 'latency_p90': 6.120744228363036}, {'batch_size': 10, 'throughput': 1.496100584462445, 'latency_mean': 6.6344742846488955, 'latency_p50': 6.671125650405884, 'latency_p90': 7.513554906845092}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-snug-grpo-40k-c_63788_v1

is_internal_developer: True

language_model: rirv938/snug_grpo_40k_cp1184_93ff_b_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.33

us_pacific_date: 2025-05-01

win_ratio: 0.5073450376209244

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': ['\n', 'User:', 'Bot:', '</s>', 'You:', '<|im_end|>', '<|eot_id|>', '####'], '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-snug-grpo-40k-c-63788-v1-mkmlizer
Waiting for job on rirv938-snug-grpo-40k-c-63788-v1-mkmlizer to finish
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: ║       /___/                                                         ║
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: ║                                                                     ║
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: ║                                                                     ║
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: ║                                                                     ║
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: ║                                                                     ║
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission bogoconic1-nemo-280k-s6_46455_v1: HTTPConnectionPool(host='bogoconic1-nemo-280k-s6-46455-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: Downloaded to shared memory in 70.957s
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzvxhn733, device:0
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: quantized model in 44.003s
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: Processed model rirv938/snug_grpo_40k_cp1184_93ff_b_merged in 114.961s
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-snug-grpo-40k-c-63788-v1
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-snug-grpo-40k-c-63788-v1/config.json
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-snug-grpo-40k-c-63788-v1/special_tokens_map.json
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-snug-grpo-40k-c-63788-v1/tokenizer_config.json
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-snug-grpo-40k-c-63788-v1/tokenizer.json
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-snug-grpo-40k-c-63788-v1/flywheel_model.0.safetensors
rirv938-snug-grpo-40k-c-63788-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.69it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:15, 23.40it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:14, 24.74it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:18, 19.03it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:13, 25.35it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:13, 26.17it/s]
Loading 0:   7%|▋         | 25/363 [00:01<00:19, 17.11it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 17.84it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:17, 18.61it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.38it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 22.39it/s]
Loading 0:  13%|█▎        | 48/363 [00:02<00:10, 29.09it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:11, 27.49it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:11, 27.76it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 23.62it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:14, 21.26it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 27.53it/s]
Loading 0:  20%|██        | 74/363 [00:03<00:10, 27.72it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:12, 23.04it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 29.64it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:10, 27.04it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:10, 26.75it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:11, 23.80it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:09, 28.16it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:14, 18.25it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:11, 22.44it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:12, 20.81it/s]
Loading 0:  33%|███▎      | 118/363 [00:04<00:09, 25.01it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 22.68it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 26.42it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 23.80it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 28.13it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 28.44it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:11, 19.57it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:11, 18.86it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 22.58it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:09, 20.74it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:08, 24.85it/s]
Loading 0:  46%|████▌     | 167/363 [00:07<00:08, 22.54it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:07, 26.60it/s]
Loading 0:  48%|████▊     | 176/363 [00:07<00:07, 23.44it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 27.12it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:10, 17.50it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:08, 21.46it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:07, 22.65it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 22.16it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:07, 23.00it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:07, 20.66it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:06, 25.12it/s]
Loading 0:  58%|█████▊    | 211/363 [00:08<00:05, 26.13it/s]
Loading 0:  59%|█████▉    | 214/363 [00:09<00:06, 24.68it/s]
Loading 0:  60%|█████▉    | 217/363 [00:09<00:05, 25.03it/s]
Loading 0:  61%|██████    | 222/363 [00:09<00:05, 26.52it/s]
Loading 0:  62%|██████▏   | 225/363 [00:09<00:08, 16.95it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 19.35it/s]
Loading 0:  65%|██████▍   | 235/363 [00:10<00:05, 24.59it/s]
Loading 0:  66%|██████▌   | 239/363 [00:10<00:05, 23.00it/s]
Loading 0:  68%|██████▊   | 246/363 [00:10<00:04, 29.22it/s]
Loading 0:  69%|██████▉   | 250/363 [00:10<00:04, 27.84it/s]
Loading 0:  70%|███████   | 255/363 [00:10<00:03, 29.87it/s]
Loading 0:  71%|███████▏  | 259/363 [00:10<00:03, 28.71it/s]
Loading 0:  72%|███████▏  | 263/363 [00:11<00:04, 22.34it/s]
Loading 0:  73%|███████▎  | 266/363 [00:11<00:04, 20.03it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:03, 25.24it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:03, 23.14it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 27.47it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 24.02it/s]
Loading 0:  80%|███████▉  | 289/363 [00:12<00:02, 28.39it/s]
Loading 0:  81%|████████  | 293/363 [00:12<00:02, 24.48it/s]
Loading 0:  82%|████████▏ | 298/363 [00:12<00:02, 28.92it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:02, 29.99it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 21.26it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:02, 19.87it/s]
Loading 0:  87%|████████▋ | 316/363 [00:13<00:01, 24.01it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 22.78it/s]
Loading 0:  90%|████████▉ | 325/363 [00:13<00:01, 27.67it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 24.78it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:00, 29.66it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 26.11it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 30.70it/s]
Loading 0:  96%|█████████▌| 347/363 [00:21<00:07,  2.01it/s]
Loading 0:  96%|█████████▋| 350/363 [00:21<00:05,  2.52it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:03,  3.20it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.36it/s]
Loading 0: 100%|█████████▉| 362/363 [00:21<00:00,  6.49it/s]
                                                            
Job rirv938-snug-grpo-40k-c-63788-v1-mkmlizer completed after 145.61s with status: succeeded
Stopping job with name rirv938-snug-grpo-40k-c-63788-v1-mkmlizer
Pipeline stage MKMLizer completed in 146.33s
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-snug-grpo-40k-c-63788-v1
Waiting for inference service rirv938-snug-grpo-40k-c-63788-v1 to be ready
Inference service rirv938-snug-grpo-40k-c-63788-v1 ready after 150.6743984222412s
Pipeline stage MKMLDeployer completed in 151.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3043723106384277s
Received healthy response to inference request in 1.8918688297271729s
Received healthy response to inference request in 1.7132604122161865s
Received healthy response to inference request in 1.6369147300720215s
Received healthy response to inference request in 1.5380773544311523s
5 requests
0 failed requests
5th percentile: 1.5578448295593261
10th percentile: 1.5776123046875
20th percentile: 1.6171472549438477
30th percentile: 1.6521838665008546
40th percentile: 1.6827221393585206
50th percentile: 1.7132604122161865
60th percentile: 1.784703779220581
70th percentile: 1.8561471462249755
80th percentile: 1.9743695259094238
90th percentile: 2.139370918273926
95th percentile: 2.2218716144561768
99th percentile: 2.2878721714019776
mean time: 1.816898727416992
Pipeline stage StressChecker completed in 10.32s
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 0.62s
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 0.68s
Shutdown handler de-registered
rirv938-snug-grpo-40k-c_63788_v1 status is now deployed due to DeploymentManager action
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 3251.06s
Shutdown handler de-registered
rirv938-snug-grpo-40k-c_63788_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-snug-grpo-40k-c_63788_v1 status is now torndown due to DeploymentManager action