rirv938-grpo-to-compare-_9822

developer_uid: rirv938

submission_id: rirv938-grpo-to-compare-_9822_v1

model_name: rirv938-grpo-to-compare-_9822_v1

model_group: rirv938/grpo_to_compare_

status: torndown

timestamp: 2025-04-28T20:16:00+00:00

num_battles: 7403

num_wins: 4048

celo_rating: 1318.3

family_friendly_score: 0.573

family_friendly_standard_error: 0.006995298421082549

submission_type: basic

model_repo: rirv938/grpo_to_compare_to_dpo_10k_cp312_with_ff_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': 0.5374168367041426, 'latency_mean': 1.8606873595714568, 'latency_p50': 1.850577473640442, 'latency_p90': 2.0570324897766112}, {'batch_size': 3, 'throughput': 1.0965590327755674, 'latency_mean': 2.7181528639793395, 'latency_p50': 2.7129944562911987, 'latency_p90': 3.0285006523132325}, {'batch_size': 5, 'throughput': 1.3880544402950652, 'latency_mean': 3.581050487756729, 'latency_p50': 3.6236143112182617, 'latency_p90': 4.008985948562622}, {'batch_size': 6, 'throughput': 1.5043203448751257, 'latency_mean': 3.956702573299408, 'latency_p50': 4.0121248960494995, 'latency_p90': 4.4452176809310915}, {'batch_size': 8, 'throughput': 1.6494976851150973, 'latency_mean': 4.823189563751221, 'latency_p50': 4.789173722267151, 'latency_p90': 5.436080431938171}, {'batch_size': 10, 'throughput': 1.7560004989292417, 'latency_mean': 5.641765928268432, 'latency_p50': 5.628641724586487, 'latency_p90': 6.344260764122009}]

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

display_name: rirv938-grpo-to-compare-_9822_v1

is_internal_developer: True

language_model: rirv938/grpo_to_compare_to_dpo_10k_cp312_with_ff_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.44

us_pacific_date: 2025-04-28

win_ratio: 0.5468053491827637

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': ['\n', '</s>', '###', 'You:'], '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-9822-v1-mkmlizer
Waiting for job on rirv938-grpo-to-compare-9822-v1-mkmlizer to finish
rirv938-grpo-to-compare-9822-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-grpo-to-compare-9822-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-grpo-to-compare-9822-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-grpo-to-compare-9822-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-grpo-to-compare-9822-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-grpo-to-compare-9822-v1-mkmlizer: ║       /___/                                                         ║
rirv938-grpo-to-compare-9822-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-9822-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-grpo-to-compare-9822-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-grpo-to-compare-9822-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-grpo-to-compare-9822-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-9822-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-grpo-to-compare-9822-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-grpo-to-compare-9822-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-9822-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-grpo-to-compare-9822-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-grpo-to-compare-9822-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-grpo-to-compare-9822-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-9822-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-damien-mafia-bos_79245_v2: HTTPConnectionPool(host='chaiml-damien-mafia-bos-79245-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-damien-mafia-bos_79245_v2: HTTPConnectionPool(host='chaiml-damien-mafia-bos-79245-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-damien-mafia-bos_79245_v2: HTTPConnectionPool(host='chaiml-damien-mafia-bos-79245-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-grpo-to-compare-9822-v1-mkmlizer: Downloaded to shared memory in 164.633s
rirv938-grpo-to-compare-9822-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9_phmr2y, device:0
rirv938-grpo-to-compare-9822-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-grpo-to-compare-9822-v1-mkmlizer: quantized model in 62.143s
rirv938-grpo-to-compare-9822-v1-mkmlizer: Processed model rirv938/grpo_to_compare_to_dpo_10k_cp312_with_ff_merged in 226.777s
rirv938-grpo-to-compare-9822-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-grpo-to-compare-9822-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-grpo-to-compare-9822-v1
rirv938-grpo-to-compare-9822-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-9822-v1/config.json
rirv938-grpo-to-compare-9822-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-9822-v1/special_tokens_map.json
rirv938-grpo-to-compare-9822-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-9822-v1/tokenizer_config.json
rirv938-grpo-to-compare-9822-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-9822-v1/tokenizer.json
rirv938-grpo-to-compare-9822-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-9822-v1/flywheel_model.1.safetensors
rirv938-grpo-to-compare-9822-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-9822-v1/flywheel_model.0.safetensors
rirv938-grpo-to-compare-9822-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:17, 20.71it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:20, 17.65it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:15, 22.11it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:25, 13.83it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:26, 13.04it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.56it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.29it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.42it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 23.03it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:20, 15.86it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:19, 16.27it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:25, 12.70it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 18.05it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.44it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:19, 15.55it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:18, 16.18it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:23, 12.83it/s]
Loading 0:  18%|█▊        | 65/363 [00:03<00:15, 19.37it/s]
Loading 0:  19%|█▉        | 69/363 [00:04<00:15, 18.56it/s]
Loading 0:  20%|█▉        | 72/363 [00:04<00:20, 14.51it/s]
Loading 0:  21%|██        | 75/363 [00:04<00:17, 16.45it/s]
Loading 0:  21%|██▏       | 78/363 [00:04<00:19, 14.86it/s]
Loading 0:  23%|██▎       | 83/363 [00:04<00:13, 20.18it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:12, 21.83it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:17, 15.65it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:16, 16.08it/s]
Loading 0:  27%|██▋       | 97/363 [00:05<00:12, 21.32it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:11, 22.08it/s]
Loading 0:  29%|██▊       | 104/363 [00:06<00:14, 18.22it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:17, 14.28it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 13.61it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.33it/s]
Loading 0:  31%|███       | 113/363 [00:06<00:21, 11.90it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 18.01it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.38it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.23it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 15.89it/s]
Loading 0:  36%|███▌      | 130/363 [00:07<00:16, 14.06it/s]
Loading 0:  36%|███▋      | 132/363 [00:08<00:17, 13.55it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 18.24it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:09, 22.64it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:14, 15.71it/s]
Loading 0:  40%|████      | 146/363 [00:08<00:13, 16.36it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:16, 12.59it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 17.95it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 21.70it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:12, 15.89it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:12, 16.14it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:15, 12.66it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 17.69it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.40it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:11, 15.83it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:10, 16.50it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:14, 12.70it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 17.79it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:08, 20.93it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:10, 15.25it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 16.01it/s]
Loading 0:  55%|█████▌    | 200/363 [00:26<00:10, 16.01it/s]
Loading 0:  55%|█████▌    | 201/363 [00:26<04:32,  1.68s/it]
Loading 0:  56%|█████▌    | 203/363 [00:26<03:29,  1.31s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:02,  1.27it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:25,  1.79it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:02,  2.41it/s]
Loading 0:  60%|█████▉    | 216/363 [00:27<00:48,  3.06it/s]
Loading 0:  60%|██████    | 219/363 [00:27<00:34,  4.17it/s]
Loading 0:  61%|██████    | 221/363 [00:28<00:30,  4.62it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:17,  7.65it/s]
Loading 0:  64%|██████▎   | 231/363 [00:28<00:13,  9.81it/s]
Loading 0:  64%|██████▍   | 234/363 [00:28<00:13,  9.39it/s]
Loading 0:  65%|██████▌   | 237/363 [00:29<00:11, 11.34it/s]
Loading 0:  66%|██████▌   | 240/363 [00:29<00:10, 11.44it/s]
Loading 0:  67%|██████▋   | 245/363 [00:29<00:07, 16.25it/s]
Loading 0:  69%|██████▊   | 249/363 [00:29<00:06, 16.29it/s]
Loading 0:  69%|██████▉   | 252/363 [00:30<00:08, 13.25it/s]
Loading 0:  70%|███████   | 255/363 [00:30<00:07, 15.36it/s]
Loading 0:  71%|███████   | 258/363 [00:30<00:07, 14.43it/s]
Loading 0:  72%|███████▏  | 263/363 [00:30<00:05, 19.83it/s]
Loading 0:  74%|███████▎  | 267/363 [00:30<00:05, 19.04it/s]
Loading 0:  74%|███████▍  | 270/363 [00:31<00:06, 14.53it/s]
Loading 0:  75%|███████▌  | 273/363 [00:31<00:05, 16.49it/s]
Loading 0:  76%|███████▌  | 276/363 [00:31<00:05, 14.86it/s]
Loading 0:  77%|███████▋  | 281/363 [00:31<00:04, 20.18it/s]
Loading 0:  79%|███████▊  | 285/363 [00:31<00:04, 19.17it/s]
Loading 0:  79%|███████▉  | 288/363 [00:32<00:05, 14.53it/s]
Loading 0:  80%|████████  | 291/363 [00:32<00:04, 16.61it/s]
Loading 0:  81%|████████  | 294/363 [00:32<00:04, 14.82it/s]
Loading 0:  82%|████████▏ | 298/363 [00:32<00:03, 18.61it/s]
Loading 0:  83%|████████▎ | 302/363 [00:32<00:02, 21.88it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:03, 15.52it/s]
Loading 0:  85%|████████▍ | 308/363 [00:33<00:03, 16.14it/s]
Loading 0:  86%|████████▌ | 311/363 [00:33<00:04, 12.64it/s]
Loading 0:  87%|████████▋ | 316/363 [00:33<00:02, 17.70it/s]
Loading 0:  88%|████████▊ | 320/363 [00:33<00:02, 21.22it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 15.53it/s]
Loading 0:  90%|████████▉ | 326/363 [00:34<00:02, 16.33it/s]
Loading 0:  91%|█████████ | 329/363 [00:34<00:02, 12.92it/s]
Loading 0:  92%|█████████▏| 335/363 [00:34<00:01, 19.47it/s]
Loading 0:  93%|█████████▎| 339/363 [00:35<00:01, 18.72it/s]
Loading 0:  94%|█████████▍| 342/363 [00:35<00:01, 14.55it/s]
Loading 0:  95%|█████████▌| 345/363 [00:35<00:01, 16.56it/s]
Loading 0:  96%|█████████▌| 348/363 [00:35<00:00, 15.06it/s]
Loading 0:  97%|█████████▋| 352/363 [00:35<00:00, 18.68it/s]
Loading 0:  98%|█████████▊| 357/363 [00:42<00:03,  1.77it/s]
Loading 0:  99%|█████████▉| 360/363 [00:43<00:01,  2.26it/s]
Loading 0: 100%|█████████▉| 362/363 [00:43<00:00,  2.66it/s]
                                                            
Job rirv938-grpo-to-compare-9822-v1-mkmlizer completed after 258.19s with status: succeeded
Stopping job with name rirv938-grpo-to-compare-9822-v1-mkmlizer
Pipeline stage MKMLizer completed in 258.71s
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-grpo-to-compare-9822-v1
Waiting for inference service rirv938-grpo-to-compare-9822-v1 to be ready
Inference service rirv938-grpo-to-compare-9822-v1 ready after 130.44663667678833s
Pipeline stage MKMLDeployer completed in 131.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9070966243743896s
Received healthy response to inference request in 1.9632916450500488s
Received healthy response to inference request in 2.2780187129974365s
Received healthy response to inference request in 1.8063781261444092s
Received healthy response to inference request in 1.8324294090270996s
5 requests
0 failed requests
5th percentile: 1.8115883827209474
10th percentile: 1.8167986392974853
20th percentile: 1.8272191524505614
30th percentile: 1.8586018562316895
40th percentile: 1.910946750640869
50th percentile: 1.9632916450500488
60th percentile: 2.089182472229004
70th percentile: 2.2150732994079587
80th percentile: 2.4038342952728273
90th percentile: 2.6554654598236085
95th percentile: 2.781281042098999
99th percentile: 2.8819335079193116
mean time: 2.157442903518677
Pipeline stage StressChecker completed in 12.31s
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 0.81s
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 0.75s
Shutdown handler de-registered
rirv938-grpo-to-compare-_9822_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
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 2856.71s
Shutdown handler de-registered
rirv938-grpo-to-compare-_9822_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-grpo-to-compare-_9822_v1 status is now torndown due to DeploymentManager action