rirv938-grpo-to-compare_36740

developer_uid: rirv938

submission_id: rirv938-grpo-to-compare_36740_v1

model_name: rirv938-grpo-to-compare_36740_v1

model_group: rirv938/grpo_to_compare_

status: torndown

timestamp: 2025-04-26T07:12:46+00:00

num_battles: 10568

num_wins: 5354

celo_rating: 1293.33

family_friendly_score: 0.5584

family_friendly_standard_error: 0.007022669577874214

submission_type: basic

model_repo: rirv938/grpo_to_compare_to_dpo_10k_cp156_lr8_merged

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5363682386715386, 'latency_mean': 1.8643359434604645, 'latency_p50': 1.8677101135253906, 'latency_p90': 2.0742234230041503}, {'batch_size': 3, 'throughput': 1.0991063266252137, 'latency_mean': 2.7270774984359742, 'latency_p50': 2.7403966188430786, 'latency_p90': 3.013353776931763}, {'batch_size': 5, 'throughput': 1.4123967017526005, 'latency_mean': 3.5238074481487276, 'latency_p50': 3.5225019454956055, 'latency_p90': 3.987139678001404}, {'batch_size': 6, 'throughput': 1.5232856873766993, 'latency_mean': 3.908952808380127, 'latency_p50': 3.935786724090576, 'latency_p90': 4.356730246543885}, {'batch_size': 8, 'throughput': 1.6673556797513878, 'latency_mean': 4.7521879565715786, 'latency_p50': 4.737238049507141, 'latency_p90': 5.302754664421081}, {'batch_size': 10, 'throughput': 1.7465459986073033, 'latency_mean': 5.656450771093368, 'latency_p50': 5.667009353637695, 'latency_p90': 6.340462851524353}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: rirv938-grpo-to-compare_36740_v1

is_internal_developer: True

language_model: rirv938/grpo_to_compare_to_dpo_10k_cp156_lr8_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.47

us_pacific_date: 2025-04-26

win_ratio: 0.5066237698713096

generation_params: {'temperature': 0.9, 'top_p': 0.9, 'min_p': 0.2, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['###', '</s>', 'You:', '\n'], 'max_input_tokens': 1024, '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-grpo-to-compare-36740-v1-mkmlizer
Waiting for job on rirv938-grpo-to-compare-36740-v1-mkmlizer to finish
rirv938-grpo-to-compare-36740-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-grpo-to-compare-36740-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-grpo-to-compare-36740-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-grpo-to-compare-36740-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-grpo-to-compare-36740-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-grpo-to-compare-36740-v1-mkmlizer: ║       /___/                                                         ║
rirv938-grpo-to-compare-36740-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-36740-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-grpo-to-compare-36740-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-grpo-to-compare-36740-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-grpo-to-compare-36740-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-36740-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-grpo-to-compare-36740-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-grpo-to-compare-36740-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-36740-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-grpo-to-compare-36740-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-grpo-to-compare-36740-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-grpo-to-compare-36740-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-36740-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-grpo-to-compare-36740-v1-mkmlizer: Downloaded to shared memory in 173.893s
rirv938-grpo-to-compare-36740-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcmaihm_y, device:0
rirv938-grpo-to-compare-36740-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-grpo-to-compare-36740-v1-mkmlizer: quantized model in 61.780s
rirv938-grpo-to-compare-36740-v1-mkmlizer: Processed model rirv938/grpo_to_compare_to_dpo_10k_cp156_lr8_merged in 235.674s
rirv938-grpo-to-compare-36740-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-grpo-to-compare-36740-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-grpo-to-compare-36740-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-grpo-to-compare-36740-v1
rirv938-grpo-to-compare-36740-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-36740-v1/config.json
rirv938-grpo-to-compare-36740-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-36740-v1/special_tokens_map.json
rirv938-grpo-to-compare-36740-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-36740-v1/tokenizer_config.json
rirv938-grpo-to-compare-36740-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-36740-v1/flywheel_model.1.safetensors
rirv938-grpo-to-compare-36740-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-36740-v1/flywheel_model.0.safetensors
rirv938-grpo-to-compare-36740-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:17, 20.89it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:20, 17.66it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:15, 22.57it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:25, 13.83it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:25, 13.46it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:19, 17.37it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:24, 13.79it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:16, 20.01it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:16, 19.83it/s]
Loading 0:  10%|▉         | 36/363 [00:02<00:21, 15.05it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:18, 17.14it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:21, 15.25it/s]
Loading 0:  13%|█▎        | 47/363 [00:02<00:15, 20.62it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:16, 19.20it/s]
Loading 0:  15%|█▍        | 54/363 [00:03<00:21, 14.50it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:18, 16.49it/s]
Loading 0:  17%|█▋        | 60/363 [00:03<00:20, 14.83it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:15, 18.78it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:15, 19.35it/s]
Loading 0:  20%|█▉        | 72/363 [00:04<00:19, 14.86it/s]
Loading 0:  21%|██        | 75/363 [00:04<00:16, 17.02it/s]
Loading 0:  21%|██▏       | 78/363 [00:04<00:18, 15.17it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:14, 19.20it/s]
Loading 0:  24%|██▎       | 86/363 [00:04<00:11, 23.11it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:16, 16.28it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:16, 16.58it/s]
Loading 0:  27%|██▋       | 97/363 [00:05<00:12, 21.94it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:11, 22.88it/s]
Loading 0:  29%|██▊       | 104/363 [00:05<00:13, 18.77it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:17, 14.44it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 14.06it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.80it/s]
Loading 0:  31%|███       | 113/363 [00:06<00:20, 12.35it/s]
Loading 0:  33%|███▎      | 118/363 [00:06<00:13, 18.54it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.89it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.14it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 16.09it/s]
Loading 0:  36%|███▌      | 131/363 [00:07<00:18, 12.71it/s]
Loading 0:  37%|███▋      | 136/363 [00:07<00:12, 18.11it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.87it/s]
Loading 0:  40%|███▉      | 144/363 [00:08<00:15, 14.01it/s]
Loading 0:  40%|████      | 147/363 [00:08<00:13, 16.08it/s]
Loading 0:  41%|████▏     | 150/363 [00:08<00:14, 14.69it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 18.40it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 22.23it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:12, 15.81it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:12, 16.33it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:15, 12.98it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 18.22it/s]
Loading 0:  49%|████▉     | 177/363 [00:10<00:09, 19.05it/s]
Loading 0:  50%|████▉     | 180/363 [00:10<00:12, 14.73it/s]
Loading 0:  50%|█████     | 183/363 [00:10<00:10, 16.76it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:11, 15.16it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 19.01it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:07, 22.76it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:10, 15.84it/s]
Loading 0:  55%|█████▌    | 200/363 [00:11<00:09, 16.44it/s]
Loading 0:  56%|█████▌    | 203/363 [00:26<03:45,  1.41s/it]
Loading 0:  57%|█████▋    | 207/363 [00:26<02:25,  1.07it/s]
Loading 0:  58%|█████▊    | 210/363 [00:26<01:45,  1.45it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:18,  1.91it/s]
Loading 0:  60%|█████▉    | 216/363 [00:27<00:59,  2.45it/s]
Loading 0:  60%|██████    | 219/363 [00:27<00:43,  3.34it/s]
Loading 0:  61%|██████    | 222/363 [00:27<00:33,  4.20it/s]
Loading 0:  62%|██████▏   | 226/363 [00:27<00:22,  6.14it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:15,  8.56it/s]
Loading 0:  64%|██████▍   | 233/363 [00:28<00:14,  8.71it/s]
Loading 0:  65%|██████▌   | 236/363 [00:28<00:12, 10.16it/s]
Loading 0:  66%|██████▌   | 239/363 [00:28<00:12,  9.56it/s]
Loading 0:  67%|██████▋   | 244/363 [00:28<00:08, 14.07it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:06, 17.64it/s]
Loading 0:  69%|██████▉   | 252/363 [00:29<00:08, 12.94it/s]
Loading 0:  70%|███████   | 255/363 [00:29<00:07, 14.98it/s]
Loading 0:  71%|███████   | 258/363 [00:29<00:07, 13.87it/s]
Loading 0:  72%|███████▏  | 263/363 [00:30<00:05, 18.93it/s]
Loading 0:  74%|███████▎  | 267/363 [00:30<00:05, 18.05it/s]
Loading 0:  74%|███████▍  | 270/363 [00:30<00:06, 14.13it/s]
Loading 0:  75%|███████▌  | 273/363 [00:30<00:05, 16.27it/s]
Loading 0:  76%|███████▌  | 276/363 [00:31<00:05, 14.83it/s]
Loading 0:  77%|███████▋  | 281/363 [00:31<00:04, 20.22it/s]
Loading 0:  79%|███████▊  | 285/363 [00:31<00:04, 19.21it/s]
Loading 0:  79%|███████▉  | 288/363 [00:31<00:05, 14.68it/s]
Loading 0:  80%|████████  | 291/363 [00:31<00:04, 16.80it/s]
Loading 0:  81%|████████  | 294/363 [00:32<00:04, 15.16it/s]
Loading 0:  82%|████████▏ | 299/363 [00:32<00:03, 20.60it/s]
Loading 0:  83%|████████▎ | 303/363 [00:32<00:03, 19.35it/s]
Loading 0:  84%|████████▍ | 306/363 [00:32<00:03, 14.76it/s]
Loading 0:  85%|████████▌ | 309/363 [00:32<00:03, 16.83it/s]
Loading 0:  86%|████████▌ | 312/363 [00:33<00:03, 15.31it/s]
Loading 0:  87%|████████▋ | 317/363 [00:33<00:02, 20.77it/s]
Loading 0:  88%|████████▊ | 321/363 [00:33<00:02, 19.50it/s]
Loading 0:  89%|████████▉ | 324/363 [00:33<00:02, 14.85it/s]
Loading 0:  90%|█████████ | 327/363 [00:33<00:02, 17.06it/s]
Loading 0:  91%|█████████ | 330/363 [00:34<00:02, 15.36it/s]
Loading 0:  92%|█████████▏| 334/363 [00:34<00:01, 19.27it/s]
Loading 0:  93%|█████████▎| 338/363 [00:34<00:01, 23.16it/s]
Loading 0:  94%|█████████▍| 341/363 [00:34<00:01, 16.53it/s]
Loading 0:  95%|█████████▍| 344/363 [00:34<00:01, 17.05it/s]
Loading 0:  96%|█████████▌| 347/363 [00:35<00:01, 13.36it/s]
Loading 0:  97%|█████████▋| 352/363 [00:35<00:00, 18.85it/s]
Loading 0:  98%|█████████▊| 357/363 [00:42<00:03,  1.83it/s]
Loading 0:  99%|█████████▉| 360/363 [00:42<00:01,  2.32it/s]
Loading 0: 100%|█████████▉| 362/363 [00:42<00:00,  2.73it/s]
                                                            
Job rirv938-grpo-to-compare-36740-v1-mkmlizer completed after 269.39s with status: succeeded
Stopping job with name rirv938-grpo-to-compare-36740-v1-mkmlizer
Pipeline stage MKMLizer completed in 269.97s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-grpo-to-compare-36740-v1
Waiting for inference service rirv938-grpo-to-compare-36740-v1 to be ready
Inference service rirv938-grpo-to-compare-36740-v1 ready after 140.73571872711182s
Pipeline stage MKMLDeployer completed in 141.18s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.764348268508911s
Received healthy response to inference request in 1.8979778289794922s
Received healthy response to inference request in 2.0692155361175537s
Received healthy response to inference request in 2.2231078147888184s
Received healthy response to inference request in 2.028695583343506s
5 requests
0 failed requests
5th percentile: 1.924121379852295
10th percentile: 1.9502649307250977
20th percentile: 2.002552032470703
30th percentile: 2.0367995738983153
40th percentile: 2.0530075550079347
50th percentile: 2.0692155361175537
60th percentile: 2.1307724475860597
70th percentile: 2.1923293590545656
80th percentile: 2.331355905532837
90th percentile: 2.547852087020874
95th percentile: 2.6561001777648925
99th percentile: 2.7426986503601074
mean time: 2.196669006347656
Pipeline stage StressChecker completed in 12.33s
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 0.68s
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-grpo-to-compare_36740_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
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 4250.57s
Shutdown handler de-registered
rirv938-grpo-to-compare_36740_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-grpo-to-compare_36740_v1 status is now torndown due to DeploymentManager action