rirv938-tune-mistral-gr_80586

developer_uid: rirv938

submission_id: rirv938-tune-mistral-gr_80586_v1

model_name: rirv938-tune-mistral-gr_80586_v1

model_group: rirv938/tune_mistral_grp

status: torndown

timestamp: 2025-04-29T20:11:27+00:00

num_battles: 7468

num_wins: 3717

celo_rating: 1297.98

family_friendly_score: 0.5594

family_friendly_standard_error: 0.007020991952708677

submission_type: basic

model_repo: rirv938/tune_mistral_grpo_cp62_92ff_v2_merged

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5522822413772509, 'latency_mean': 1.8106095170974732, 'latency_p50': 1.793840765953064, 'latency_p90': 2.0326895713806152}, {'batch_size': 3, 'throughput': 1.1842913305894156, 'latency_mean': 2.525027235746384, 'latency_p50': 2.524935007095337, 'latency_p90': 2.803319239616394}, {'batch_size': 5, 'throughput': 1.532834496553081, 'latency_mean': 3.232143596410751, 'latency_p50': 3.259382963180542, 'latency_p90': 3.5634287118911745}, {'batch_size': 6, 'throughput': 1.6629979845897531, 'latency_mean': 3.582821296453476, 'latency_p50': 3.6128753423690796, 'latency_p90': 4.01442699432373}, {'batch_size': 8, 'throughput': 1.8572097739663664, 'latency_mean': 4.276869331598282, 'latency_p50': 4.317027688026428, 'latency_p90': 4.777274155616761}, {'batch_size': 10, 'throughput': 1.973208304410685, 'latency_mean': 5.012942279577255, 'latency_p50': 5.002389192581177, 'latency_p90': 5.635736036300659}]

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

display_name: rirv938-tune-mistral-gr_80586_v1

is_internal_developer: True

language_model: rirv938/tune_mistral_grpo_cp62_92ff_v2_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.71

us_pacific_date: 2025-04-29

win_ratio: 0.4977236207820032

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': ['You:', '###', '\n', '</s>'], 'max_input_tokens': 768, '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-tune-mistral-gr-80586-v1-mkmlizer
Waiting for job on rirv938-tune-mistral-gr-80586-v1-mkmlizer to finish
rirv938-tune-mistral-gr-80586-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-tune-mistral-gr-80586-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-tune-mistral-gr-80586-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-tune-mistral-gr-80586-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-tune-mistral-gr-80586-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-tune-mistral-gr-80586-v1-mkmlizer: ║       /___/                                                         ║
rirv938-tune-mistral-gr-80586-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-80586-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-tune-mistral-gr-80586-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-tune-mistral-gr-80586-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-tune-mistral-gr-80586-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-80586-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-tune-mistral-gr-80586-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-tune-mistral-gr-80586-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-80586-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-tune-mistral-gr-80586-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-tune-mistral-gr-80586-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-tune-mistral-gr-80586-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-80586-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-tune-mistral-gr-80586-v1-mkmlizer: Downloaded to shared memory in 162.286s
rirv938-tune-mistral-gr-80586-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_8a77txt, device:0
rirv938-tune-mistral-gr-80586-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-tune-mistral-gr-80586-v1-mkmlizer: quantized model in 63.675s
rirv938-tune-mistral-gr-80586-v1-mkmlizer: Processed model rirv938/tune_mistral_grpo_cp62_92ff_v2_merged in 225.961s
rirv938-tune-mistral-gr-80586-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-tune-mistral-gr-80586-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-tune-mistral-gr-80586-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-tune-mistral-gr-80586-v1
rirv938-tune-mistral-gr-80586-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-80586-v1/config.json
rirv938-tune-mistral-gr-80586-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-80586-v1/special_tokens_map.json
rirv938-tune-mistral-gr-80586-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-80586-v1/tokenizer_config.json
rirv938-tune-mistral-gr-80586-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-80586-v1/tokenizer.json
rirv938-tune-mistral-gr-80586-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-80586-v1/flywheel_model.1.safetensors
rirv938-tune-mistral-gr-80586-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-80586-v1/flywheel_model.0.safetensors
rirv938-tune-mistral-gr-80586-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:17, 20.56it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:20, 17.49it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:15, 22.21it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:25, 13.63it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:26, 13.30it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 17.05it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:24, 13.62it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.66it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.79it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:20, 16.28it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:19, 16.85it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:24, 12.98it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 18.06it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.41it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:19, 15.76it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:19, 16.11it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:23, 12.72it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:17, 17.50it/s]
Loading 0:  19%|█▊        | 68/363 [00:03<00:14, 21.02it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:18, 15.49it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:17, 16.17it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:22, 12.61it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:15, 17.70it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.68it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:17, 15.31it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:17, 15.47it/s]
Loading 0:  26%|██▋       | 96/363 [00:05<00:13, 19.27it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:12, 21.55it/s]
Loading 0:  29%|██▊       | 104/363 [00:06<00:14, 17.76it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 13.98it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 13.48it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.33it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:20, 11.92it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 18.03it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.40it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.15it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 15.96it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:18, 12.76it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 18.04it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.75it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:13, 16.08it/s]
Loading 0:  40%|████      | 146/363 [00:08<00:13, 16.67it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:16, 13.07it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 18.42it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 22.05it/s]
Loading 0:  45%|████▍     | 162/363 [00:09<00:13, 14.51it/s]
Loading 0:  45%|████▌     | 165/363 [00:09<00:12, 16.37it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:14, 13.50it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:11, 16.52it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:09, 19.66it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:12, 14.71it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 15.36it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:13, 13.72it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:13, 13.22it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 17.47it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:07, 21.33it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 14.97it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 15.51it/s]
Loading 0:  56%|█████▌    | 202/363 [00:27<04:25,  1.65s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:53,  1.46s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:11,  1.19it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:30,  1.69it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:05,  2.29it/s]
Loading 0:  59%|█████▉    | 215/363 [00:28<00:53,  2.78it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:42,  3.43it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:33,  4.35it/s]
Loading 0:  61%|██████    | 221/363 [00:28<00:28,  4.93it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:15,  8.77it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:11, 12.07it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:11, 10.88it/s]
Loading 0:  65%|██████▌   | 236/363 [00:29<00:10, 12.25it/s]
Loading 0:  66%|██████▌   | 239/363 [00:29<00:11, 10.63it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:07, 15.55it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:06, 19.03it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:07, 14.55it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:07, 15.13it/s]
Loading 0:  71%|███████   | 257/363 [00:30<00:08, 12.21it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:05, 17.20it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 20.79it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 15.33it/s]
Loading 0:  75%|███████▍  | 272/363 [00:31<00:05, 15.96it/s]
Loading 0:  76%|███████▌  | 275/363 [00:32<00:06, 12.61it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 17.69it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 21.18it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:04, 15.53it/s]
Loading 0:  80%|███████▉  | 290/363 [00:32<00:04, 16.19it/s]
Loading 0:  81%|████████  | 293/363 [00:33<00:05, 12.71it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 17.39it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:02, 20.68it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:03, 15.47it/s]
Loading 0:  85%|████████▍ | 308/363 [00:33<00:03, 16.05it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:04, 12.58it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 17.53it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:02, 20.66it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 14.99it/s]
Loading 0:  90%|████████▉ | 326/363 [00:35<00:02, 15.72it/s]
Loading 0:  91%|█████████ | 329/363 [00:35<00:02, 12.55it/s]
Loading 0:  92%|█████████▏| 335/363 [00:35<00:01, 18.91it/s]
Loading 0:  93%|█████████▎| 339/363 [00:35<00:01, 17.92it/s]
Loading 0:  94%|█████████▍| 342/363 [00:36<00:01, 13.44it/s]
Loading 0:  95%|█████████▌| 345/363 [00:36<00:01, 15.42it/s]
Loading 0:  96%|█████████▌| 348/363 [00:36<00:01, 14.10it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 17.51it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 21.24it/s]
Loading 0:  99%|█████████▉| 359/363 [00:43<00:02,  1.55it/s]
Loading 0:  99%|█████████▉| 361/363 [00:44<00:01,  1.83it/s]
                                                            
Job rirv938-tune-mistral-gr-80586-v1-mkmlizer completed after 259.36s with status: succeeded
Stopping job with name rirv938-tune-mistral-gr-80586-v1-mkmlizer
Pipeline stage MKMLizer completed in 259.82s
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-tune-mistral-gr-80586-v1
Waiting for inference service rirv938-tune-mistral-gr-80586-v1 to be ready
Inference service rirv938-tune-mistral-gr-80586-v1 ready after 140.61713910102844s
Pipeline stage MKMLDeployer completed in 141.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4780592918395996s
Received healthy response to inference request in 1.8882322311401367s
Received healthy response to inference request in 1.9843730926513672s
Received healthy response to inference request in 1.8048055171966553s
Received healthy response to inference request in 2.2915151119232178s
5 requests
0 failed requests
5th percentile: 1.8214908599853517
10th percentile: 1.8381762027740478
20th percentile: 1.8715468883514403
30th percentile: 1.9074604034423828
40th percentile: 1.945916748046875
50th percentile: 1.9843730926513672
60th percentile: 2.1072299003601076
70th percentile: 2.2300867080688476
80th percentile: 2.328823947906494
90th percentile: 2.403441619873047
95th percentile: 2.4407504558563233
99th percentile: 2.4705975246429444
mean time: 2.0893970489501954
Pipeline stage StressChecker completed in 11.84s
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 0.64s
Shutdown handler de-registered
rirv938-tune-mistral-gr_80586_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-tune-mistral-gr-80586-v1-profiler
Waiting for inference service rirv938-tune-mistral-gr-80586-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 3148.95s
Shutdown handler de-registered
rirv938-tune-mistral-gr_80586_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-tune-mistral-gr_80586_v1 status is now torndown due to DeploymentManager action