rirv938-tune-mistral-gr_99159

developer_uid: rirv938

submission_id: rirv938-tune-mistral-gr_99159_v1

model_name: rirv938-tune-mistral-gr_99159_v1

model_group: rirv938/tune_mistral_grp

status: torndown

timestamp: 2025-04-30T02:51:10+00:00

num_battles: 5294

num_wins: 2875

celo_rating: 1321.82

family_friendly_score: 0.563

family_friendly_standard_error: 0.007014713108887633

submission_type: basic

model_repo: rirv938/tune_mistral_grpo_cp592_92ff_run_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': 0.5581164039225279, 'latency_mean': 1.791685903072357, 'latency_p50': 1.7685880661010742, 'latency_p90': 1.9960702657699585}, {'batch_size': 4, 'throughput': 1.378510749584069, 'latency_mean': 2.8900166726112366, 'latency_p50': 2.8967230319976807, 'latency_p90': 3.227799034118652}, {'batch_size': 5, 'throughput': 1.5413101974525878, 'latency_mean': 3.2169305872917175, 'latency_p50': 3.2150261402130127, 'latency_p90': 3.61655216217041}, {'batch_size': 8, 'throughput': 1.8654078291287168, 'latency_mean': 4.245919467210769, 'latency_p50': 4.221869349479675, 'latency_p90': 4.76494288444519}, {'batch_size': 10, 'throughput': 1.9768709570728604, 'latency_mean': 4.999403009414673, 'latency_p50': 5.0147788524627686, 'latency_p90': 5.522320556640625}, {'batch_size': 12, 'throughput': 2.0685694740636182, 'latency_mean': 5.725011285543442, 'latency_p50': 5.666885137557983, 'latency_p90': 6.555214810371399}, {'batch_size': 15, 'throughput': 2.1397004352867777, 'latency_mean': 6.9479429411888125, 'latency_p50': 6.9891417026519775, 'latency_p90': 7.888692331314087}]

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

display_name: rirv938-tune-mistral-gr_99159_v1

is_internal_developer: True

language_model: rirv938/tune_mistral_grpo_cp592_92ff_run_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.73

us_pacific_date: 2025-04-29

win_ratio: 0.5430676237249716

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:', '</s>', '###', '\n'], '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-99159-v1-mkmlizer
Waiting for job on rirv938-tune-mistral-gr-99159-v1-mkmlizer to finish
rirv938-tune-mistral-gr-99159-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-tune-mistral-gr-99159-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-tune-mistral-gr-99159-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-tune-mistral-gr-99159-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-tune-mistral-gr-99159-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-tune-mistral-gr-99159-v1-mkmlizer: ║       /___/                                                         ║
rirv938-tune-mistral-gr-99159-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-99159-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-tune-mistral-gr-99159-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-tune-mistral-gr-99159-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-tune-mistral-gr-99159-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-99159-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-tune-mistral-gr-99159-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-tune-mistral-gr-99159-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-99159-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-tune-mistral-gr-99159-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-tune-mistral-gr-99159-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-tune-mistral-gr-99159-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-99159-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-tune-mistral-gr-99159-v1-mkmlizer: Downloaded to shared memory in 158.507s
rirv938-tune-mistral-gr-99159-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0ql6tp8c, device:0
rirv938-tune-mistral-gr-99159-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-tune-mistral-gr-99159-v1-mkmlizer: quantized model in 62.660s
rirv938-tune-mistral-gr-99159-v1-mkmlizer: Processed model rirv938/tune_mistral_grpo_cp592_92ff_run_merged in 221.168s
rirv938-tune-mistral-gr-99159-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-tune-mistral-gr-99159-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-tune-mistral-gr-99159-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-tune-mistral-gr-99159-v1
rirv938-tune-mistral-gr-99159-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-99159-v1/config.json
rirv938-tune-mistral-gr-99159-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-99159-v1/special_tokens_map.json
rirv938-tune-mistral-gr-99159-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-99159-v1/tokenizer_config.json
rirv938-tune-mistral-gr-99159-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-99159-v1/tokenizer.json
rirv938-tune-mistral-gr-99159-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-99159-v1/flywheel_model.1.safetensors
rirv938-tune-mistral-gr-99159-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-99159-v1/flywheel_model.0.safetensors
rirv938-tune-mistral-gr-99159-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:17, 20.94it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:19, 18.05it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:15, 22.56it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:26, 13.02it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:27, 12.83it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.48it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.20it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 18.86it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.45it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:22, 14.81it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:21, 15.24it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:23, 13.68it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:24, 13.24it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 17.23it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 20.92it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.63it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:21, 14.28it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:20, 15.06it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:25, 12.16it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 18.44it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:13, 22.05it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 15.27it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.93it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:22, 12.56it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:15, 17.66it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 21.05it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:18, 15.00it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:17, 15.39it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:15, 17.33it/s]
Loading 0:  27%|██▋       | 99/363 [00:05<00:12, 21.02it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 19.49it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:17, 14.83it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 13.60it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:19, 13.31it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.24it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:21, 11.66it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 18.08it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.84it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.17it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 16.15it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:18, 12.81it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.69it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.02it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:14, 15.50it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:13, 16.33it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:16, 13.03it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 18.14it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 21.14it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:13, 15.41it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:12, 16.25it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:14, 13.12it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 18.19it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.28it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:11, 15.49it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 16.41it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:13, 13.21it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 18.38it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:07, 21.94it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:10, 16.00it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:09, 16.74it/s]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:42,  1.39s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:24,  1.08it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:45,  1.45it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:18,  1.92it/s]
Loading 0:  60%|█████▉    | 216/363 [00:27<00:59,  2.47it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:42,  3.35it/s]
Loading 0:  61%|██████    | 222/363 [00:28<00:33,  4.22it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:22,  6.16it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:15,  8.58it/s]
Loading 0:  64%|██████▍   | 233/363 [00:28<00:15,  8.64it/s]
Loading 0:  65%|██████▌   | 236/363 [00:29<00:12, 10.20it/s]
Loading 0:  66%|██████▌   | 239/363 [00:29<00:12,  9.76it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:08, 14.35it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:06, 17.54it/s]
Loading 0:  69%|██████▉   | 251/363 [00:29<00:07, 14.37it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:07, 15.50it/s]
Loading 0:  71%|███████   | 257/363 [00:30<00:08, 12.87it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 17.99it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:04, 21.62it/s]
Loading 0:  74%|███████▍  | 270/363 [00:31<00:06, 14.46it/s]
Loading 0:  75%|███████▌  | 273/363 [00:31<00:05, 16.59it/s]
Loading 0:  76%|███████▌  | 276/363 [00:31<00:05, 15.04it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 18.83it/s]
Loading 0:  78%|███████▊  | 284/363 [00:31<00:03, 22.54it/s]
Loading 0:  79%|███████▉  | 288/363 [00:32<00:05, 14.12it/s]
Loading 0:  80%|████████  | 291/363 [00:32<00:04, 15.93it/s]
Loading 0:  81%|████████  | 294/363 [00:32<00:04, 14.22it/s]
Loading 0:  82%|████████▏ | 298/363 [00:32<00:03, 17.85it/s]
Loading 0:  83%|████████▎ | 302/363 [00:32<00:02, 21.45it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:04, 14.43it/s]
Loading 0:  85%|████████▍ | 308/363 [00:33<00:03, 15.29it/s]
Loading 0:  86%|████████▌ | 311/363 [00:33<00:04, 12.34it/s]
Loading 0:  87%|████████▋ | 316/363 [00:33<00:02, 16.98it/s]
Loading 0:  88%|████████▊ | 320/363 [00:33<00:02, 20.28it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 14.59it/s]
Loading 0:  90%|████████▉ | 326/363 [00:34<00:02, 15.69it/s]
Loading 0:  91%|█████████ | 329/363 [00:34<00:02, 12.84it/s]
Loading 0:  92%|█████████▏| 334/363 [00:34<00:01, 18.06it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 21.33it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:01, 15.35it/s]
Loading 0:  95%|█████████▍| 344/363 [00:35<00:01, 16.13it/s]
Loading 0:  96%|█████████▌| 347/363 [00:35<00:01, 12.95it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 18.08it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 21.42it/s]
Loading 0:  99%|█████████▉| 359/363 [00:43<00:02,  1.60it/s]
Loading 0: 100%|█████████▉| 362/363 [00:43<00:00,  2.08it/s]
                                                            
Job rirv938-tune-mistral-gr-99159-v1-mkmlizer completed after 247.54s with status: succeeded
Stopping job with name rirv938-tune-mistral-gr-99159-v1-mkmlizer
Pipeline stage MKMLizer completed in 247.99s
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-99159-v1
Waiting for inference service rirv938-tune-mistral-gr-99159-v1 to be ready
Inference service rirv938-tune-mistral-gr-99159-v1 ready after 150.48388171195984s
Pipeline stage MKMLDeployer completed in 150.90s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5432276725769043s
Received healthy response to inference request in 1.9089977741241455s
Received healthy response to inference request in 1.915647268295288s
Received healthy response to inference request in 1.949300765991211s
Received healthy response to inference request in 1.8276348114013672s
5 requests
0 failed requests
5th percentile: 1.843907403945923
10th percentile: 1.8601799964904786
20th percentile: 1.8927251815795898
30th percentile: 1.910327672958374
40th percentile: 1.912987470626831
50th percentile: 1.915647268295288
60th percentile: 1.9291086673736573
70th percentile: 1.9425700664520265
80th percentile: 2.0680861473083496
90th percentile: 2.305656909942627
95th percentile: 2.4244422912597656
99th percentile: 2.5194705963134765
mean time: 2.028961658477783
Pipeline stage StressChecker completed in 11.37s
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 0.61s
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 0.61s
Shutdown handler de-registered
rirv938-tune-mistral-gr_99159_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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-tune-mistral-gr-99159-v1-profiler
Waiting for inference service rirv938-tune-mistral-gr-99159-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 2862.71s
Shutdown handler de-registered
rirv938-tune-mistral-gr_99159_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-tune-mistral-gr_99159_v1 status is now torndown due to DeploymentManager action