rirv938-tune-mistral-gr_89879

developer_uid: rirv938

submission_id: rirv938-tune-mistral-gr_89879_v1

model_name: rirv938-tune-mistral-gr_89879_v1

model_group: rirv938/tune_mistral_grp

status: torndown

timestamp: 2025-04-29T20:11:36+00:00

num_battles: 7426

num_wins: 3573

celo_rating: 1285.75

family_friendly_score: 0.5644

family_friendly_standard_error: 0.007012169992234929

submission_type: basic

model_repo: rirv938/tune_mistral_grpo_cp62_92ff_v4_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': 0.5507421100387057, 'latency_mean': 1.8156742811203004, 'latency_p50': 1.8112553358078003, 'latency_p90': 2.0295488119125364}, {'batch_size': 4, 'throughput': 1.3855873961464125, 'latency_mean': 2.8715607678890227, 'latency_p50': 2.8533815145492554, 'latency_p90': 3.1843713045120237}, {'batch_size': 5, 'throughput': 1.5570827984512954, 'latency_mean': 3.1906217908859253, 'latency_p50': 3.1998223066329956, 'latency_p90': 3.5808925867080688}, {'batch_size': 8, 'throughput': 1.8787805394213295, 'latency_mean': 4.226921563148498, 'latency_p50': 4.214297771453857, 'latency_p90': 4.778739380836487}, {'batch_size': 10, 'throughput': 1.9970804647439833, 'latency_mean': 4.946826771497727, 'latency_p50': 4.974287271499634, 'latency_p90': 5.543766736984253}, {'batch_size': 12, 'throughput': 2.0769766486529897, 'latency_mean': 5.719297189712524, 'latency_p50': 5.715914368629456, 'latency_p90': 6.386674523353577}, {'batch_size': 15, 'throughput': 2.1636472240918265, 'latency_mean': 6.864899026155472, 'latency_p50': 6.868232607841492, 'latency_p90': 7.757526969909668}]

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

display_name: rirv938-tune-mistral-gr_89879_v1

is_internal_developer: True

language_model: rirv938/tune_mistral_grpo_cp62_92ff_v4_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.75

us_pacific_date: 2025-04-29

win_ratio: 0.48114732022623213

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': 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-89879-v1-mkmlizer
Waiting for job on rirv938-tune-mistral-gr-89879-v1-mkmlizer to finish
rirv938-tune-mistral-gr-89879-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-tune-mistral-gr-89879-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-tune-mistral-gr-89879-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-tune-mistral-gr-89879-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-tune-mistral-gr-89879-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-tune-mistral-gr-89879-v1-mkmlizer: ║       /___/                                                         ║
rirv938-tune-mistral-gr-89879-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-89879-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-tune-mistral-gr-89879-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-tune-mistral-gr-89879-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-tune-mistral-gr-89879-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-89879-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-tune-mistral-gr-89879-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-tune-mistral-gr-89879-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-89879-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-tune-mistral-gr-89879-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-tune-mistral-gr-89879-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-tune-mistral-gr-89879-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-89879-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-tune-mistral-gr-89879-v1-mkmlizer: Downloaded to shared memory in 174.422s
rirv938-tune-mistral-gr-89879-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjw7a5wxn, device:0
rirv938-tune-mistral-gr-89879-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-tune-mistral-gr-89879-v1-mkmlizer: quantized model in 65.987s
rirv938-tune-mistral-gr-89879-v1-mkmlizer: Processed model rirv938/tune_mistral_grpo_cp62_92ff_v4_merged in 240.410s
rirv938-tune-mistral-gr-89879-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-tune-mistral-gr-89879-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-tune-mistral-gr-89879-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-tune-mistral-gr-89879-v1
rirv938-tune-mistral-gr-89879-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-89879-v1/config.json
rirv938-tune-mistral-gr-89879-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-89879-v1/special_tokens_map.json
rirv938-tune-mistral-gr-89879-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-89879-v1/tokenizer_config.json
rirv938-tune-mistral-gr-89879-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-89879-v1/tokenizer.json
rirv938-tune-mistral-gr-89879-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-89879-v1/flywheel_model.1.safetensors
rirv938-tune-mistral-gr-89879-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-89879-v1/flywheel_model.0.safetensors
rirv938-tune-mistral-gr-89879-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:17, 21.01it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:21, 16.94it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:17, 20.31it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:26, 12.97it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:32, 10.83it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:22, 15.63it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:22, 14.98it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:25, 13.25it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:19, 17.58it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.14it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:22, 14.44it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:23, 13.82it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:22, 14.72it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:26, 11.93it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 17.56it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:14, 21.09it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:20, 14.92it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:19, 15.72it/s]
Loading 0:  16%|█▌        | 58/363 [00:03<00:21, 14.18it/s]
Loading 0:  17%|█▋        | 60/363 [00:03<00:21, 13.79it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:16, 18.27it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:13, 22.22it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:18, 15.51it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.86it/s]
Loading 0:  21%|██        | 76/363 [00:04<00:20, 14.12it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:20, 13.68it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:15, 18.03it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:12, 22.02it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:17, 15.26it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:17, 15.81it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:14, 18.17it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 21.79it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 19.79it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:18, 14.04it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:19, 13.12it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:20, 12.68it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.54it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:22, 11.20it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 17.36it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 20.81it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:16, 14.59it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:17, 13.54it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:16, 14.38it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:19, 11.84it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.82it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.14it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:14, 14.79it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:14, 15.28it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:15, 13.63it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:16, 13.21it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:12, 17.35it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 20.82it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:13, 14.53it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:14, 13.80it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:13, 14.76it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:16, 11.76it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 17.81it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:08, 20.89it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 14.68it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 15.46it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:12, 13.94it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:13, 13.21it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:09, 17.53it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 21.06it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 14.81it/s]
Loading 0:  55%|█████▍    | 199/363 [00:12<00:11, 14.10it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:11, 14.10it/s]
Loading 0:  55%|█████▌    | 201/363 [00:27<04:47,  1.78s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:39,  1.37s/it]
Loading 0:  57%|█████▋    | 207/363 [00:28<02:07,  1.22it/s]
Loading 0:  58%|█████▊    | 209/363 [00:28<01:38,  1.56it/s]
Loading 0:  58%|█████▊    | 212/363 [00:28<01:08,  2.22it/s]
Loading 0:  59%|█████▉    | 214/363 [00:28<00:56,  2.66it/s]
Loading 0:  60%|█████▉    | 216/363 [00:28<00:45,  3.21it/s]
Loading 0:  60%|██████    | 219/363 [00:29<00:30,  4.66it/s]
Loading 0:  61%|██████    | 221/363 [00:29<00:27,  5.12it/s]
Loading 0:  62%|██████▏   | 226/363 [00:29<00:16,  8.49it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:11, 11.45it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:12, 10.52it/s]
Loading 0:  65%|██████▍   | 235/363 [00:30<00:11, 10.80it/s]
Loading 0:  65%|██████▌   | 237/363 [00:30<00:10, 11.89it/s]
Loading 0:  66%|██████▌   | 239/363 [00:30<00:11, 10.39it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:07, 16.02it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:05, 19.60it/s]
Loading 0:  69%|██████▉   | 251/363 [00:31<00:07, 14.06it/s]
Loading 0:  70%|██████▉   | 254/363 [00:31<00:07, 14.88it/s]
Loading 0:  71%|███████   | 256/363 [00:31<00:07, 13.47it/s]
Loading 0:  71%|███████   | 258/363 [00:31<00:08, 13.04it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:05, 16.98it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 20.40it/s]
Loading 0:  74%|███████▍  | 269/363 [00:32<00:06, 14.30it/s]
Loading 0:  75%|███████▍  | 271/363 [00:32<00:06, 13.47it/s]
Loading 0:  75%|███████▌  | 273/363 [00:32<00:06, 14.50it/s]
Loading 0:  76%|███████▌  | 275/363 [00:32<00:07, 11.83it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 17.72it/s]
Loading 0:  78%|███████▊  | 284/363 [00:33<00:03, 20.96it/s]
Loading 0:  79%|███████▉  | 287/363 [00:33<00:05, 14.87it/s]
Loading 0:  80%|███████▉  | 290/363 [00:33<00:04, 15.80it/s]
Loading 0:  80%|████████  | 292/363 [00:33<00:04, 14.21it/s]
Loading 0:  81%|████████  | 294/363 [00:33<00:05, 13.49it/s]
Loading 0:  82%|████████▏ | 298/363 [00:34<00:03, 17.41it/s]
Loading 0:  83%|████████▎ | 302/363 [00:34<00:03, 20.09it/s]
Loading 0:  84%|████████▍ | 305/363 [00:34<00:04, 14.08it/s]
Loading 0:  85%|████████▍ | 307/363 [00:34<00:04, 13.41it/s]
Loading 0:  85%|████████▌ | 309/363 [00:34<00:03, 14.38it/s]
Loading 0:  86%|████████▌ | 311/363 [00:35<00:04, 11.84it/s]
Loading 0:  87%|████████▋ | 316/363 [00:35<00:02, 17.58it/s]
Loading 0:  88%|████████▊ | 320/363 [00:35<00:02, 20.78it/s]
Loading 0:  89%|████████▉ | 323/363 [00:35<00:02, 14.75it/s]
Loading 0:  90%|████████▉ | 325/363 [00:35<00:02, 13.97it/s]
Loading 0:  90%|█████████ | 327/363 [00:36<00:02, 14.76it/s]
Loading 0:  91%|█████████ | 329/363 [00:36<00:02, 12.05it/s]
Loading 0:  92%|█████████▏| 334/363 [00:36<00:01, 17.60it/s]
Loading 0:  93%|█████████▎| 338/363 [00:36<00:01, 21.01it/s]
Loading 0:  94%|█████████▍| 341/363 [00:36<00:01, 14.99it/s]
Loading 0:  94%|█████████▍| 343/363 [00:37<00:01, 14.11it/s]
Loading 0:  95%|█████████▌| 345/363 [00:37<00:01, 14.86it/s]
Loading 0:  96%|█████████▌| 347/363 [00:37<00:01, 12.12it/s]
Loading 0:  97%|█████████▋| 352/363 [00:37<00:00, 17.95it/s]
Loading 0:  98%|█████████▊| 356/363 [00:37<00:00, 21.30it/s]
Loading 0:  99%|█████████▉| 359/363 [00:44<00:02,  1.46it/s]
Loading 0:  99%|█████████▉| 361/363 [00:45<00:01,  1.75it/s]
                                                            
Job rirv938-tune-mistral-gr-89879-v1-mkmlizer completed after 271.27s with status: succeeded
Stopping job with name rirv938-tune-mistral-gr-89879-v1-mkmlizer
Pipeline stage MKMLizer completed in 271.72s
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-tune-mistral-gr-89879-v1
Waiting for inference service rirv938-tune-mistral-gr-89879-v1 to be ready
Inference service rirv938-tune-mistral-gr-89879-v1 ready after 140.5265257358551s
Pipeline stage MKMLDeployer completed in 141.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.963975429534912s
Received healthy response to inference request in 1.9563395977020264s
Received healthy response to inference request in 2.1272637844085693s
Received healthy response to inference request in 1.598174810409546s
Received healthy response to inference request in 2.2234318256378174s
5 requests
0 failed requests
5th percentile: 1.669807767868042
10th percentile: 1.741440725326538
20th percentile: 1.8847066402435302
30th percentile: 1.9578667640686036
40th percentile: 1.9609210968017579
50th percentile: 1.963975429534912
60th percentile: 2.029290771484375
70th percentile: 2.094606113433838
80th percentile: 2.146497392654419
90th percentile: 2.1849646091461183
95th percentile: 2.204198217391968
99th percentile: 2.2195851039886474
mean time: 1.9738370895385742
Pipeline stage StressChecker completed in 11.18s
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 0.64s
Shutdown handler de-registered
rirv938-tune-mistral-gr_89879_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.22s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-tune-mistral-gr-89879-v1-profiler
Waiting for inference service rirv938-tune-mistral-gr-89879-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 3171.92s
Shutdown handler de-registered
rirv938-tune-mistral-gr_89879_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-tune-mistral-gr_89879_v1 status is now torndown due to DeploymentManager action