rirv938-grpo-to-compare_72853

developer_uid: rirv938

submission_id: rirv938-grpo-to-compare_72853_v1

model_name: rirv938-grpo-to-compare_72853_v1

model_group: rirv938/grpo_to_compare_

status: torndown

timestamp: 2025-04-26T01:00:37+00:00

num_battles: 10217

num_wins: 5882

celo_rating: 1353.66

family_friendly_score: 0.5352

family_friendly_standard_error: 0.007053523374881521

submission_type: basic

model_repo: rirv938/grpo_to_compare_to_dpo_10k_cp312_lr6_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': 0.5285129440358431, 'latency_mean': 1.892034866809845, 'latency_p50': 1.8989059925079346, 'latency_p90': 2.0804808378219604}, {'batch_size': 3, 'throughput': 1.0861872666351653, 'latency_mean': 2.7473985040187836, 'latency_p50': 2.7497209310531616, 'latency_p90': 3.0121180772781373}, {'batch_size': 5, 'throughput': 1.38961618635768, 'latency_mean': 3.5752477180957793, 'latency_p50': 3.5662312507629395, 'latency_p90': 3.9957581996917724}, {'batch_size': 6, 'throughput': 1.5198068283627673, 'latency_mean': 3.9234118926525117, 'latency_p50': 3.8779430389404297, 'latency_p90': 4.369994878768921}, {'batch_size': 8, 'throughput': 1.657334342437441, 'latency_mean': 4.791726404428482, 'latency_p50': 4.784364938735962, 'latency_p90': 5.409114146232605}, {'batch_size': 10, 'throughput': 1.738967708822944, 'latency_mean': 5.7176777946949, 'latency_p50': 5.716552972793579, 'latency_p90': 6.505326437950134}]

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

display_name: rirv938-grpo-to-compare_72853_v1

is_internal_developer: True

language_model: rirv938/grpo_to_compare_to_dpo_10k_cp312_lr6_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.45

us_pacific_date: 2025-04-25

win_ratio: 0.5757071547420965

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-72853-v1-mkmlizer
Waiting for job on rirv938-grpo-to-compare-72853-v1-mkmlizer to finish
rirv938-grpo-to-compare-72853-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-grpo-to-compare-72853-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-grpo-to-compare-72853-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-grpo-to-compare-72853-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-grpo-to-compare-72853-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-grpo-to-compare-72853-v1-mkmlizer: ║       /___/                                                         ║
rirv938-grpo-to-compare-72853-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-72853-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-grpo-to-compare-72853-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-grpo-to-compare-72853-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-grpo-to-compare-72853-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-72853-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-grpo-to-compare-72853-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-grpo-to-compare-72853-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-72853-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-grpo-to-compare-72853-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-grpo-to-compare-72853-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-grpo-to-compare-72853-v1-mkmlizer: ║                                                                     ║
rirv938-grpo-to-compare-72853-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-grpo-to-compare-72853-v1-mkmlizer: Downloaded to shared memory in 196.709s
rirv938-grpo-to-compare-72853-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfaj98omh, device:0
rirv938-grpo-to-compare-72853-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-grpo-to-compare-72853-v1-mkmlizer: quantized model in 61.135s
rirv938-grpo-to-compare-72853-v1-mkmlizer: Processed model rirv938/grpo_to_compare_to_dpo_10k_cp312_lr6_merged in 257.845s
rirv938-grpo-to-compare-72853-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-grpo-to-compare-72853-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-grpo-to-compare-72853-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-grpo-to-compare-72853-v1
rirv938-grpo-to-compare-72853-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-72853-v1/config.json
rirv938-grpo-to-compare-72853-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-72853-v1/special_tokens_map.json
rirv938-grpo-to-compare-72853-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-grpo-to-compare-72853-v1/tokenizer.json
rirv938-grpo-to-compare-72853-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-72853-v1/flywheel_model.1.safetensors
rirv938-grpo-to-compare-72853-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-grpo-to-compare-72853-v1/flywheel_model.0.safetensors
rirv938-grpo-to-compare-72853-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:17, 20.88it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:20, 17.54it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.70it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:26, 13.32it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:26, 13.22it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.91it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:24, 13.71it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.67it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 23.19it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:20, 15.89it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:19, 16.50it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:25, 12.84it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 18.00it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.51it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:19, 15.76it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:18, 16.54it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:23, 13.06it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 18.23it/s]
Loading 0:  19%|█▊        | 68/363 [00:03<00:13, 21.53it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:18, 15.70it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:17, 16.28it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:21, 13.04it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:15, 18.25it/s]
Loading 0:  24%|██▎       | 86/363 [00:04<00:12, 21.74it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:17, 15.80it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:16, 16.42it/s]
Loading 0:  27%|██▋       | 97/363 [00:05<00:12, 21.40it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:11, 22.37it/s]
Loading 0:  29%|██▊       | 104/363 [00:06<00:14, 18.36it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:17, 14.46it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:17, 14.17it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:16, 14.94it/s]
Loading 0:  31%|███       | 113/363 [00:06<00:20, 12.49it/s]
Loading 0:  33%|███▎      | 118/363 [00:06<00:13, 18.76it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:10, 22.33it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.56it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 16.52it/s]
Loading 0:  36%|███▌      | 131/363 [00:07<00:17, 13.19it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 18.56it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 22.11it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:13, 16.07it/s]
Loading 0:  40%|████      | 146/363 [00:08<00:12, 16.91it/s]
Loading 0:  41%|████      | 149/363 [00:08<00:15, 13.38it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 18.69it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 22.10it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:12, 15.94it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:12, 16.56it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:14, 13.35it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 18.59it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.87it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:11, 16.15it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:10, 16.65it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:13, 13.33it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 18.41it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:07, 21.85it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:10, 16.03it/s]
Loading 0:  55%|█████▌    | 200/363 [00:11<00:09, 16.53it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:09, 16.53it/s]
Loading 0:  55%|█████▌    | 201/363 [00:25<04:19,  1.60s/it]
Loading 0:  56%|█████▌    | 203/363 [00:25<03:19,  1.25s/it]
Loading 0:  57%|█████▋    | 207/363 [00:26<01:56,  1.34it/s]
Loading 0:  58%|█████▊    | 210/363 [00:26<01:21,  1.87it/s]
Loading 0:  59%|█████▊    | 213/363 [00:26<00:59,  2.51it/s]
Loading 0:  59%|█████▉    | 215/363 [00:26<00:48,  3.03it/s]
Loading 0:  60%|█████▉    | 217/363 [00:26<00:39,  3.71it/s]
Loading 0:  61%|██████    | 220/363 [00:27<00:28,  5.02it/s]
Loading 0:  61%|██████    | 222/363 [00:27<00:23,  5.88it/s]
Loading 0:  62%|██████▏   | 226/363 [00:27<00:15,  9.02it/s]
Loading 0:  63%|██████▎   | 230/363 [00:27<00:10, 12.55it/s]
Loading 0:  64%|██████▍   | 233/363 [00:27<00:11, 11.32it/s]
Loading 0:  65%|██████▌   | 236/363 [00:27<00:09, 12.90it/s]
Loading 0:  66%|██████▌   | 239/363 [00:28<00:10, 11.29it/s]
Loading 0:  67%|██████▋   | 244/363 [00:28<00:07, 16.42it/s]
Loading 0:  68%|██████▊   | 248/363 [00:28<00:05, 19.91it/s]
Loading 0:  69%|██████▉   | 251/363 [00:28<00:07, 15.10it/s]
Loading 0:  70%|██████▉   | 254/363 [00:28<00:06, 15.95it/s]
Loading 0:  71%|███████   | 257/363 [00:29<00:08, 12.85it/s]
Loading 0:  72%|███████▏  | 262/363 [00:29<00:05, 17.84it/s]
Loading 0:  73%|███████▎  | 266/363 [00:29<00:04, 20.92it/s]
Loading 0:  74%|███████▍  | 269/363 [00:29<00:06, 15.65it/s]
Loading 0:  75%|███████▍  | 272/363 [00:30<00:05, 16.49it/s]
Loading 0:  76%|███████▌  | 275/363 [00:30<00:06, 13.18it/s]
Loading 0:  77%|███████▋  | 280/363 [00:30<00:04, 18.15it/s]
Loading 0:  78%|███████▊  | 284/363 [00:30<00:03, 21.71it/s]
Loading 0:  79%|███████▉  | 287/363 [00:30<00:04, 16.29it/s]
Loading 0:  80%|███████▉  | 290/363 [00:31<00:04, 17.08it/s]
Loading 0:  81%|████████  | 293/363 [00:31<00:05, 13.35it/s]
Loading 0:  82%|████████▏ | 298/363 [00:31<00:03, 18.48it/s]
Loading 0:  83%|████████▎ | 302/363 [00:31<00:02, 21.46it/s]
Loading 0:  84%|████████▍ | 305/363 [00:31<00:03, 15.74it/s]
Loading 0:  85%|████████▍ | 308/363 [00:32<00:03, 16.54it/s]
Loading 0:  86%|████████▌ | 311/363 [00:32<00:03, 13.25it/s]
Loading 0:  87%|████████▋ | 316/363 [00:32<00:02, 18.26it/s]
Loading 0:  88%|████████▊ | 320/363 [00:32<00:01, 21.54it/s]
Loading 0:  89%|████████▉ | 323/363 [00:33<00:02, 15.96it/s]
Loading 0:  90%|████████▉ | 326/363 [00:33<00:02, 16.53it/s]
Loading 0:  91%|█████████ | 329/363 [00:33<00:02, 13.26it/s]
Loading 0:  92%|█████████▏| 334/363 [00:33<00:01, 18.53it/s]
Loading 0:  93%|█████████▎| 338/363 [00:33<00:01, 22.02it/s]
Loading 0:  94%|█████████▍| 341/363 [00:34<00:01, 16.16it/s]
Loading 0:  95%|█████████▍| 344/363 [00:34<00:01, 16.95it/s]
Loading 0:  96%|█████████▌| 347/363 [00:34<00:01, 13.54it/s]
Loading 0:  97%|█████████▋| 352/363 [00:34<00:00, 18.74it/s]
Loading 0:  98%|█████████▊| 356/363 [00:34<00:00, 22.26it/s]
Loading 0:  99%|█████████▉| 360/363 [00:41<00:01,  1.75it/s]
Loading 0: 100%|██████████| 363/363 [00:42<00:00,  2.25it/s]
                                                            
Job rirv938-grpo-to-compare-72853-v1-mkmlizer completed after 288.62s with status: succeeded
Stopping job with name rirv938-grpo-to-compare-72853-v1-mkmlizer
Pipeline stage MKMLizer completed in 289.10s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-grpo-to-compare-72853-v1
Waiting for inference service rirv938-grpo-to-compare-72853-v1 to be ready
Inference service rirv938-grpo-to-compare-72853-v1 ready after 130.66085147857666s
Pipeline stage MKMLDeployer completed in 131.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9737672805786133s
Received healthy response to inference request in 2.1818108558654785s
Received healthy response to inference request in 2.101560354232788s
Received healthy response to inference request in 2.1332204341888428s
Received healthy response to inference request in 1.9358360767364502s
5 requests
0 failed requests
5th percentile: 1.9689809322357177
10th percentile: 2.002125787734985
20th percentile: 2.0684154987335206
30th percentile: 2.107892370223999
40th percentile: 2.1205564022064207
50th percentile: 2.1332204341888428
60th percentile: 2.152656602859497
70th percentile: 2.1720927715301515
80th percentile: 2.3402021408081057
90th percentile: 2.6569847106933593
95th percentile: 2.815375995635986
99th percentile: 2.942089023590088
mean time: 2.2652390003204346
Pipeline stage StressChecker completed in 12.56s
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 0.76s
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 0.80s
Shutdown handler de-registered
rirv938-grpo-to-compare_72853_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
Pipeline stage MKMLProfilerDeleter completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-grpo-to-compare-72853-v1-profiler
Waiting for inference service rirv938-grpo-to-compare-72853-v1-profiler to be ready
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 2793.08s
Shutdown handler de-registered
rirv938-grpo-to-compare_72853_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-grpo-to-compare_72853_v1 status is now torndown due to DeploymentManager action