rirv938-snug-grpo-40k-cp_3986

developer_uid: rirv938

submission_id: rirv938-snug-grpo-40k-cp_3986_v1

model_name: rirv938-snug-grpo-40k-cp_3986_v1

model_group: rirv938/snug_grpo_40k_cp

status: torndown

timestamp: 2025-05-01T16:29:13+00:00

num_battles: 5451

num_wins: 2734

celo_rating: 1290.52

family_friendly_score: 0.5158

family_friendly_standard_error: 0.007067536487348332

submission_type: basic

model_repo: rirv938/snug_grpo_40k_cp592_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': 0.608709966188496, 'latency_mean': 1.6427553331851958, 'latency_p50': 1.6411008834838867, 'latency_p90': 1.838080644607544}, {'batch_size': 3, 'throughput': 1.1033014017191174, 'latency_mean': 2.715763362646103, 'latency_p50': 2.719874143600464, 'latency_p90': 2.969917726516724}, {'batch_size': 5, 'throughput': 1.3305475092142183, 'latency_mean': 3.75212771654129, 'latency_p50': 3.7411924600601196, 'latency_p90': 4.217423844337463}, {'batch_size': 6, 'throughput': 1.397854490868306, 'latency_mean': 4.266404660940171, 'latency_p50': 4.270278573036194, 'latency_p90': 4.7790132522583}, {'batch_size': 8, 'throughput': 1.457777422554762, 'latency_mean': 5.445956082344055, 'latency_p50': 5.443110942840576, 'latency_p90': 6.0892701864242555}, {'batch_size': 10, 'throughput': 1.502503177291645, 'latency_mean': 6.611993775367737, 'latency_p50': 6.681971549987793, 'latency_p90': 7.350427889823913}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rirv938-snug-grpo-40k-cp_3986_v1

is_internal_developer: True

language_model: rirv938/snug_grpo_40k_cp592_93ff_b_merged

model_size: 13B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2025-05-01

win_ratio: 0.5015593469088241

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': ['Bot:', 'User:', 'You:', '<|eot_id|>', '####', '</s>', '\n', '<|im_end|>'], '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-cp-3986-v1-mkmlizer
Waiting for job on rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer to finish
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: ║       /___/                                                         ║
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: ║                                                                     ║
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: ║                                                                     ║
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: ║                                                                     ║
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: ║                                                                     ║
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: Downloaded to shared memory in 83.861s
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpj1hjgnz7, device:0
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: quantized model in 41.337s
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: Processed model rirv938/snug_grpo_40k_cp592_93ff_b_merged in 125.199s
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-snug-grpo-40k-cp-3986-v1
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-snug-grpo-40k-cp-3986-v1/config.json
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-snug-grpo-40k-cp-3986-v1/special_tokens_map.json
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-snug-grpo-40k-cp-3986-v1/tokenizer_config.json
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-snug-grpo-40k-cp-3986-v1/flywheel_model.0.safetensors
rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 22.09it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 28.57it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.34it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 36.05it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:15, 21.29it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 25.91it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 27.29it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 29.04it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 28.07it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.51it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.57it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 27.92it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 24.59it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 21.50it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:10, 28.67it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:10, 28.58it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.49it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 30.23it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 29.40it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 32.05it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.05it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 24.65it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 21.67it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 28.78it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 28.03it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 30.47it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 29.47it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 32.31it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 30.80it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 30.68it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 26.70it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 24.76it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.41it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 30.58it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 29.10it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.88it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 30.60it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 33.06it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 31.31it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 25.53it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 22.02it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 29.19it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:05, 28.50it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 31.13it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.85it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 31.99it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 30.25it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 30.87it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:05, 26.97it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:05, 24.97it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:05, 23.98it/s]
Loading 0:  65%|██████▍   | 235/363 [00:08<00:04, 29.07it/s]
Loading 0:  66%|██████▌   | 239/363 [00:08<00:04, 25.27it/s]
Loading 0:  67%|██████▋   | 244/363 [00:08<00:03, 30.07it/s]
Loading 0:  68%|██████▊   | 248/363 [00:08<00:04, 26.10it/s]
Loading 0:  70%|██████▉   | 253/363 [00:09<00:03, 30.84it/s]
Loading 0:  71%|███████   | 257/363 [00:09<00:03, 26.67it/s]
Loading 0:  72%|███████▏  | 262/363 [00:09<00:03, 31.13it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 20.72it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 26.82it/s]
Loading 0:  76%|███████▋  | 277/363 [00:09<00:03, 26.65it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 29.40it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.04it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 30.08it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 28.58it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 29.00it/s]
Loading 0:  84%|████████▎ | 304/363 [00:10<00:02, 24.42it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 22.95it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 21.74it/s]
Loading 0:  88%|████████▊ | 318/363 [00:11<00:01, 28.39it/s]
Loading 0:  89%|████████▊ | 322/363 [00:11<00:01, 27.16it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 28.64it/s]
Loading 0:  91%|█████████ | 330/363 [00:11<00:01, 25.92it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 29.87it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 28.16it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.98it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.64it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.83it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  4.94it/s]
                                                            
Job rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer completed after 145.61s with status: succeeded
Stopping job with name rirv938-snug-grpo-40k-cp-3986-v1-mkmlizer
Pipeline stage MKMLizer completed in 146.06s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-snug-grpo-40k-cp-3986-v1
Waiting for inference service rirv938-snug-grpo-40k-cp-3986-v1 to be ready
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)
Inference service rirv938-snug-grpo-40k-cp-3986-v1 ready after 150.5257031917572s
Pipeline stage MKMLDeployer completed in 150.99s
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 2.380525588989258s
Received healthy response to inference request in 1.7352352142333984s
Received healthy response to inference request in 1.6046063899993896s
Received healthy response to inference request in 1.6091604232788086s
5 requests
1 failed requests
5th percentile: 1.6055171966552735
10th percentile: 1.6064280033111573
20th percentile: 1.6082496166229248
30th percentile: 1.6343753814697266
40th percentile: 1.6848052978515624
50th percentile: 1.7352352142333984
60th percentile: 1.993351364135742
70th percentile: 2.2514675140380858
80th percentile: 5.929718923568728
90th percentile: 13.028105592727663
95th percentile: 16.577298927307126
99th percentile: 19.416653594970704
mean time: 5.49120397567749
%s, retrying in %s seconds...
Received healthy response to inference request in 1.5834786891937256s
Received healthy response to inference request in 1.8219490051269531s
Received healthy response to inference request in 1.7211856842041016s
Received healthy response to inference request in 1.7335317134857178s
Received healthy response to inference request in 1.7249994277954102s
5 requests
0 failed requests
5th percentile: 1.6110200881958008
10th percentile: 1.638561487197876
20th percentile: 1.6936442852020264
30th percentile: 1.7219484329223633
40th percentile: 1.7234739303588866
50th percentile: 1.7249994277954102
60th percentile: 1.7284123420715332
70th percentile: 1.7318252563476562
80th percentile: 1.7512151718139648
90th percentile: 1.786582088470459
95th percentile: 1.804265546798706
99th percentile: 1.8184123134613037
mean time: 1.7170289039611817
Pipeline stage StressChecker completed in 38.67s
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 0.65s
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 0.63s
Shutdown handler de-registered
rirv938-snug-grpo-40k-cp_3986_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 2991.02s
Shutdown handler de-registered
rirv938-snug-grpo-40k-cp_3986_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-snug-grpo-40k-cp_3986_v1 status is now torndown due to DeploymentManager action