rirv938-grpo-to-compare_44163

developer_uid: rirv938

submission_id: rirv938-grpo-to-compare_44163_v1

model_name: rirv938-grpo-to-compare_44163_v1

model_group: rirv938/grpo_to_compare_

status: torndown

timestamp: 2025-04-26T20:04:31+00:00

num_battles: 10350

num_wins: 5406

celo_rating: 1309.24

family_friendly_score: 0.5574

family_friendly_standard_error: 0.0070243183299164335

submission_type: basic

model_repo: rirv938/grpo_to_compare_to_dpo_10k_cp156_lr9_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': 0.5263696878283668, 'latency_mean': 1.8997320854663848, 'latency_p50': 1.913628101348877, 'latency_p90': 2.0917819499969483}, {'batch_size': 3, 'throughput': 1.0754692182236503, 'latency_mean': 2.769152407646179, 'latency_p50': 2.787690043449402, 'latency_p90': 3.090382957458496}, {'batch_size': 5, 'throughput': 1.385127245800278, 'latency_mean': 3.5970700073242186, 'latency_p50': 3.5782328844070435, 'latency_p90': 3.9983840465545653}, {'batch_size': 6, 'throughput': 1.4910913252980404, 'latency_mean': 4.003192771673202, 'latency_p50': 4.007423043251038, 'latency_p90': 4.458620476722717}, {'batch_size': 8, 'throughput': 1.6392065792811161, 'latency_mean': 4.833820939064026, 'latency_p50': 4.829054355621338, 'latency_p90': 5.475266146659851}, {'batch_size': 10, 'throughput': 1.7342822427887923, 'latency_mean': 5.714170492887497, 'latency_p50': 5.755215287208557, 'latency_p90': 6.492615723609925}]

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

display_name: rirv938-grpo-to-compare_44163_v1

is_internal_developer: True

language_model: rirv938/grpo_to_compare_to_dpo_10k_cp156_lr9_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.42

us_pacific_date: 2025-04-26

win_ratio: 0.5223188405797101

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', 'You:', '</s>'], '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-44163-v1-mkmlizer
Waiting for job on rirv938-grpo-to-compare-44163-v1-mkmlizer to finish
rirv938-grpo-to-compare-44163-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-grpo-to-compare-44163-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-grpo-to-compare-44163-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-grpo-to-compare-44163-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-grpo-to-compare-44163-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-grpo-to-compare-44163-v1-mkmlizer: ║       /___/                                                         ║
rirv938-grpo-to-compare-44163-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-44163-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-grpo-to-compare-44163-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-grpo-to-compare-44163-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-grpo-to-compare-44163-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-44163-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-grpo-to-compare-44163-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-grpo-to-compare-44163-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-44163-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-grpo-to-compare-44163-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-grpo-to-compare-44163-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-grpo-to-compare-44163-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-44163-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-grpo-to-compare-44163-v1-mkmlizer: Downloaded to shared memory in 168.323s
rirv938-grpo-to-compare-44163-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpylp3qhqs, device:0
rirv938-grpo-to-compare-44163-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-grpo-to-compare-44163-v1-mkmlizer: quantized model in 64.101s
rirv938-grpo-to-compare-44163-v1-mkmlizer: Processed model rirv938/grpo_to_compare_to_dpo_10k_cp156_lr9_merged in 232.425s
rirv938-grpo-to-compare-44163-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-grpo-to-compare-44163-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-grpo-to-compare-44163-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-grpo-to-compare-44163-v1
rirv938-grpo-to-compare-44163-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-44163-v1/config.json
rirv938-grpo-to-compare-44163-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-44163-v1/special_tokens_map.json
rirv938-grpo-to-compare-44163-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-44163-v1/tokenizer_config.json
rirv938-grpo-to-compare-44163-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-44163-v1/tokenizer.json
rirv938-grpo-to-compare-44163-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-44163-v1/flywheel_model.1.safetensors
rirv938-grpo-to-compare-44163-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-44163-v1/flywheel_model.0.safetensors
rirv938-grpo-to-compare-44163-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:17, 20.58it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:20, 17.14it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 20.90it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:27, 12.70it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:28, 12.33it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:22, 15.49it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:21, 15.86it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:27, 12.26it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.08it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.81it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:21, 15.44it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:20, 15.82it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:26, 12.36it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 17.77it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.44it/s]
Loading 0:  15%|█▍        | 54/363 [00:03<00:22, 13.91it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:19, 15.90it/s]
Loading 0:  17%|█▋        | 60/363 [00:03<00:20, 14.51it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:17, 17.59it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 20.56it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 15.01it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.67it/s]
Loading 0:  21%|██        | 76/363 [00:04<00:20, 14.01it/s]
Loading 0:  21%|██▏       | 78/363 [00:04<00:21, 13.55it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:15, 17.76it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:12, 21.65it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:17, 15.47it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:17, 15.83it/s]
Loading 0:  26%|██▋       | 96/363 [00:05<00:13, 19.98it/s]
Loading 0:  28%|██▊       | 101/363 [00:06<00:12, 21.68it/s]
Loading 0:  29%|██▊       | 104/363 [00:06<00:14, 17.61it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 14.01it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 13.57it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.24it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:20, 11.94it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 17.85it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.10it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.17it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 15.94it/s]
Loading 0:  36%|███▌      | 130/363 [00:08<00:16, 14.20it/s]
Loading 0:  36%|███▋      | 132/363 [00:08<00:16, 13.72it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 18.30it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:09, 22.61it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:14, 15.69it/s]
Loading 0:  40%|████      | 146/363 [00:08<00:13, 16.43it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:16, 12.82it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 18.26it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 22.00it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:14, 14.07it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:12, 16.08it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:13, 14.48it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 17.89it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.26it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:11, 15.50it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 16.05it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:14, 12.50it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:10, 17.11it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:08, 20.07it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:10, 15.16it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 15.69it/s]
Loading 0:  56%|█████▌    | 202/363 [00:27<04:09,  1.55s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:41,  1.38s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:07,  1.23it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:28,  1.73it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:03,  2.35it/s]
Loading 0:  59%|█████▉    | 215/363 [00:28<00:51,  2.85it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:41,  3.51it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:32,  4.44it/s]
Loading 0:  61%|██████    | 221/363 [00:28<00:28,  5.01it/s]
Loading 0:  63%|██████▎   | 227/363 [00:28<00:13,  9.75it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:11, 11.99it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:11, 10.95it/s]
Loading 0:  65%|██████▌   | 236/363 [00:29<00:10, 12.32it/s]
Loading 0:  66%|██████▌   | 239/363 [00:29<00:12, 10.31it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:07, 14.99it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:06, 18.50it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:07, 14.40it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:07, 15.21it/s]
Loading 0:  71%|███████   | 257/363 [00:30<00:09, 11.71it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:06, 16.28it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:05, 19.26it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 14.76it/s]
Loading 0:  75%|███████▍  | 272/363 [00:31<00:05, 15.49it/s]
Loading 0:  76%|███████▌  | 275/363 [00:32<00:07, 12.29it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 17.12it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 20.61it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:05, 15.16it/s]
Loading 0:  80%|███████▉  | 290/363 [00:32<00:04, 15.54it/s]
Loading 0:  81%|████████  | 293/363 [00:33<00:05, 12.06it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 16.89it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:03, 20.04it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:03, 14.83it/s]
Loading 0:  85%|████████▍ | 308/363 [00:33<00:03, 15.35it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:04, 12.02it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 16.71it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:02, 19.69it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 14.78it/s]
Loading 0:  90%|████████▉ | 326/363 [00:35<00:02, 15.33it/s]
Loading 0:  90%|█████████ | 328/363 [00:35<00:02, 13.77it/s]
Loading 0:  91%|█████████ | 330/363 [00:35<00:02, 13.52it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 18.04it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 22.08it/s]
Loading 0:  94%|█████████▍| 341/363 [00:36<00:01, 14.76it/s]
Loading 0:  95%|█████████▍| 344/363 [00:36<00:01, 15.43it/s]
Loading 0:  96%|█████████▌| 347/363 [00:36<00:01, 12.32it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 17.56it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 20.93it/s]
Loading 0:  99%|█████████▉| 359/363 [00:43<00:02,  1.58it/s]
Loading 0: 100%|█████████▉| 362/363 [00:44<00:00,  2.04it/s]
                                                            
Job rirv938-grpo-to-compare-44163-v1-mkmlizer completed after 268.5s with status: succeeded
Stopping job with name rirv938-grpo-to-compare-44163-v1-mkmlizer
Pipeline stage MKMLizer completed in 268.98s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-grpo-to-compare-44163-v1
Waiting for inference service rirv938-grpo-to-compare-44163-v1 to be ready
Inference service rirv938-grpo-to-compare-44163-v1 ready after 140.5788915157318s
Pipeline stage MKMLDeployer completed in 141.13s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.421964406967163s
Received healthy response to inference request in 1.9868550300598145s
Received healthy response to inference request in 2.028939962387085s
Received healthy response to inference request in 2.089683771133423s
Received healthy response to inference request in 1.888185977935791s
5 requests
0 failed requests
5th percentile: 1.9079197883605956
10th percentile: 1.9276535987854004
20th percentile: 1.9671212196350099
30th percentile: 1.9952720165252686
40th percentile: 2.0121059894561766
50th percentile: 2.028939962387085
60th percentile: 2.05323748588562
70th percentile: 2.0775350093841554
80th percentile: 2.156139898300171
90th percentile: 2.289052152633667
95th percentile: 2.3555082798004148
99th percentile: 2.4086731815338136
mean time: 2.0831258296966553
Pipeline stage StressChecker completed in 11.80s
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 0.64s
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 0.66s
Shutdown handler de-registered
rirv938-grpo-to-compare_44163_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4596.74s
Shutdown handler de-registered
rirv938-grpo-to-compare_44163_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-grpo-to-compare_44163_v1 status is now torndown due to DeploymentManager action