rirv938-tune-mistral-gr_30207

developer_uid: rirv938

submission_id: rirv938-tune-mistral-gr_30207_v1

model_name: rirv938-tune-mistral-gr_30207_v1

model_group: rirv938/tune_mistral_grp

status: torndown

timestamp: 2025-04-30T15:00:06+00:00

num_battles: 8607

num_wins: 4351

celo_rating: 1311.97

family_friendly_score: 0.5688

family_friendly_standard_error: 0.00700380696478708

submission_type: basic

model_repo: rirv938/tune_mistral_grpo_cp592_92ff_v3_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': 0.5577369425800446, 'latency_mean': 1.7929039204120636, 'latency_p50': 1.783364176750183, 'latency_p90': 1.9979043483734131}, {'batch_size': 4, 'throughput': 1.3809723620835095, 'latency_mean': 2.8852660596370696, 'latency_p50': 2.8553600311279297, 'latency_p90': 3.2118249893188477}, {'batch_size': 5, 'throughput': 1.5500320320430854, 'latency_mean': 3.2089654743671416, 'latency_p50': 3.204893469810486, 'latency_p90': 3.602805256843567}, {'batch_size': 8, 'throughput': 1.851660834173845, 'latency_mean': 4.277956889867783, 'latency_p50': 4.312609791755676, 'latency_p90': 4.8244893789291385}, {'batch_size': 10, 'throughput': 1.977065771388209, 'latency_mean': 4.995010174512863, 'latency_p50': 5.053108215332031, 'latency_p90': 5.656694078445435}, {'batch_size': 12, 'throughput': 2.067563563050979, 'latency_mean': 5.730267916917801, 'latency_p50': 5.7723305225372314, 'latency_p90': 6.473817658424378}, {'batch_size': 15, 'throughput': 2.1203498304435815, 'latency_mean': 6.97497849225998, 'latency_p50': 7.0085209608078, 'latency_p90': 7.993114185333251}]

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

display_name: rirv938-tune-mistral-gr_30207_v1

is_internal_developer: True

language_model: rirv938/tune_mistral_grpo_cp592_92ff_v3_run_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.72

us_pacific_date: 2025-04-30

win_ratio: 0.5055187637969095

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': ['</s>', '\n', 'You:', '###'], '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-30207-v1-mkmlizer
Waiting for job on rirv938-tune-mistral-gr-30207-v1-mkmlizer to finish
rirv938-tune-mistral-gr-30207-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-tune-mistral-gr-30207-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-tune-mistral-gr-30207-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-tune-mistral-gr-30207-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-tune-mistral-gr-30207-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-tune-mistral-gr-30207-v1-mkmlizer: ║       /___/                                                         ║
rirv938-tune-mistral-gr-30207-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-30207-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-tune-mistral-gr-30207-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-tune-mistral-gr-30207-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-tune-mistral-gr-30207-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-30207-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-tune-mistral-gr-30207-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-tune-mistral-gr-30207-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-30207-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-tune-mistral-gr-30207-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-tune-mistral-gr-30207-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-tune-mistral-gr-30207-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-30207-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-tune-mistral-gr-30207-v1-mkmlizer: Downloaded to shared memory in 147.419s
rirv938-tune-mistral-gr-30207-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvrrpkw2a, device:0
rirv938-tune-mistral-gr-30207-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-tune-mistral-gr-30207-v1-mkmlizer: quantized model in 63.675s
rirv938-tune-mistral-gr-30207-v1-mkmlizer: Processed model rirv938/tune_mistral_grpo_cp592_92ff_v3_run_merged in 211.094s
rirv938-tune-mistral-gr-30207-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-tune-mistral-gr-30207-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-tune-mistral-gr-30207-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-tune-mistral-gr-30207-v1
rirv938-tune-mistral-gr-30207-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-30207-v1/special_tokens_map.json
rirv938-tune-mistral-gr-30207-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-30207-v1/config.json
rirv938-tune-mistral-gr-30207-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-30207-v1/tokenizer_config.json
rirv938-tune-mistral-gr-30207-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-30207-v1/tokenizer.json
rirv938-tune-mistral-gr-30207-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-30207-v1/flywheel_model.1.safetensors
rirv938-tune-mistral-gr-30207-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-30207-v1/flywheel_model.0.safetensors
rirv938-tune-mistral-gr-30207-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.63it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:25, 14.14it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.73it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:26, 13.19it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:27, 12.66it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:21, 15.67it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:22, 14.83it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:24, 13.67it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 17.84it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.33it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:22, 14.47it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:23, 13.68it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:22, 14.44it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:27, 11.57it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 17.53it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 20.82it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.49it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:20, 14.86it/s]
Loading 0:  16%|█▌        | 58/363 [00:03<00:23, 13.20it/s]
Loading 0:  17%|█▋        | 60/363 [00:04<00:24, 12.54it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:17, 16.70it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 20.39it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:20, 14.47it/s]
Loading 0:  20%|██        | 73/363 [00:04<00:21, 13.78it/s]
Loading 0:  21%|██        | 75/363 [00:04<00:19, 14.48it/s]
Loading 0:  21%|██        | 77/363 [00:05<00:24, 11.54it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.24it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.97it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:17, 15.38it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:17, 15.83it/s]
Loading 0:  27%|██▋       | 97/363 [00:06<00:12, 21.24it/s]
Loading 0:  28%|██▊       | 101/363 [00:06<00:11, 22.33it/s]
Loading 0:  29%|██▊       | 104/363 [00:06<00:14, 18.21it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 13.99it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 13.67it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:17, 14.41it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:21, 11.45it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 17.16it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 20.35it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:16, 14.72it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:16, 14.13it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:15, 14.91it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:19, 11.97it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.71it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.17it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:14, 14.76it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:14, 15.27it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:15, 13.55it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:16, 12.85it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:12, 17.11it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 20.83it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:14, 14.29it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:14, 13.68it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:13, 14.40it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:16, 11.76it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:10, 17.49it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:08, 20.90it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 14.99it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 15.76it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:12, 13.83it/s]
Loading 0:  51%|█████     | 186/363 [00:12<00:13, 13.23it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:09, 17.40it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 21.01it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 14.80it/s]
Loading 0:  55%|█████▍    | 199/363 [00:12<00:11, 13.96it/s]
Loading 0:  55%|█████▌    | 201/363 [00:27<04:43,  1.75s/it]
Loading 0:  56%|█████▌    | 202/363 [00:27<04:04,  1.52s/it]
Loading 0:  56%|█████▌    | 204/363 [00:27<02:56,  1.11s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<01:48,  1.43it/s]
Loading 0:  58%|█████▊    | 210/363 [00:28<01:11,  2.13it/s]
Loading 0:  58%|█████▊    | 212/363 [00:28<00:55,  2.72it/s]
Loading 0:  59%|█████▉    | 214/363 [00:28<00:45,  3.30it/s]
Loading 0:  60%|█████▉    | 216/363 [00:28<00:38,  3.86it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:25,  5.66it/s]
Loading 0:  61%|██████    | 221/363 [00:29<00:23,  6.02it/s]
Loading 0:  62%|██████▏   | 226/363 [00:29<00:13, 10.33it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:09, 13.75it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:10, 11.92it/s]
Loading 0:  65%|██████▌   | 236/363 [00:29<00:09, 13.08it/s]
Loading 0:  66%|██████▌   | 239/363 [00:30<00:11, 11.13it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:07, 15.75it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:06, 18.94it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:07, 14.50it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:07, 15.25it/s]
Loading 0:  71%|███████   | 257/363 [00:31<00:08, 12.21it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:06, 16.82it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 19.91it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 15.25it/s]
Loading 0:  75%|███████▍  | 272/363 [00:32<00:05, 15.68it/s]
Loading 0:  75%|███████▌  | 274/363 [00:32<00:06, 14.14it/s]
Loading 0:  76%|███████▌  | 276/363 [00:32<00:06, 13.54it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 17.48it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 20.92it/s]
Loading 0:  79%|███████▉  | 287/363 [00:33<00:05, 14.95it/s]
Loading 0:  80%|███████▉  | 289/363 [00:33<00:05, 14.22it/s]
Loading 0:  80%|████████  | 291/363 [00:33<00:04, 15.05it/s]
Loading 0:  81%|████████  | 293/363 [00:33<00:05, 12.04it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 18.12it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:02, 21.52it/s]
Loading 0:  84%|████████▍ | 305/363 [00:34<00:03, 14.96it/s]
Loading 0:  85%|████████▍ | 308/363 [00:34<00:03, 15.39it/s]
Loading 0:  85%|████████▌ | 310/363 [00:34<00:03, 13.66it/s]
Loading 0:  86%|████████▌ | 312/363 [00:34<00:03, 13.06it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 17.14it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:02, 20.57it/s]
Loading 0:  89%|████████▉ | 323/363 [00:35<00:02, 14.46it/s]
Loading 0:  90%|████████▉ | 325/363 [00:35<00:02, 13.91it/s]
Loading 0:  90%|█████████ | 327/363 [00:35<00:02, 14.75it/s]
Loading 0:  91%|█████████ | 329/363 [00:35<00:02, 11.93it/s]
Loading 0:  92%|█████████▏| 334/363 [00:36<00:01, 18.39it/s]
Loading 0:  93%|█████████▎| 338/363 [00:36<00:01, 21.35it/s]
Loading 0:  94%|█████████▍| 341/363 [00:36<00:01, 14.45it/s]
Loading 0:  95%|█████████▍| 344/363 [00:36<00:01, 15.40it/s]
Loading 0:  95%|█████████▌| 346/363 [00:36<00:01, 13.91it/s]
Loading 0:  96%|█████████▌| 348/363 [00:37<00:01, 13.48it/s]
Loading 0:  97%|█████████▋| 352/363 [00:37<00:00, 18.28it/s]
Loading 0:  98%|█████████▊| 356/363 [00:37<00:00, 22.60it/s]
Loading 0:  99%|█████████▉| 359/363 [00:44<00:02,  1.45it/s]
Loading 0:  99%|█████████▉| 361/363 [00:44<00:01,  1.75it/s]
                                                            
Job rirv938-tune-mistral-gr-30207-v1-mkmlizer completed after 238.22s with status: succeeded
Stopping job with name rirv938-tune-mistral-gr-30207-v1-mkmlizer
Pipeline stage MKMLizer completed in 238.70s
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-30207-v1
Waiting for inference service rirv938-tune-mistral-gr-30207-v1 to be ready
Inference service rirv938-tune-mistral-gr-30207-v1 ready after 150.53103280067444s
Pipeline stage MKMLDeployer completed in 150.95s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.5694639682769775s
Received healthy response to inference request in 2.253662347793579s
Received healthy response to inference request in 2.170151710510254s
Received healthy response to inference request in 1.8277277946472168s
5 requests
1 failed requests
5th percentile: 1.8962125778198242
10th percentile: 1.9646973609924316
20th percentile: 2.1016669273376465
30th percentile: 2.186853837966919
40th percentile: 2.220258092880249
50th percentile: 2.253662347793579
60th percentile: 2.3799829959869383
70th percentile: 2.506303644180298
80th percentile: 6.080740833282474
90th percentile: 13.10329456329346
95th percentile: 16.614571428298948
99th percentile: 19.423592920303346
mean time: 5.789370822906494
%s, retrying in %s seconds...
Received healthy response to inference request in 2.0264461040496826s
Received healthy response to inference request in 2.188870668411255s
Received healthy response to inference request in 2.191347599029541s
Received healthy response to inference request in 2.145427703857422s
Received healthy response to inference request in 6.954962253570557s
5 requests
0 failed requests
5th percentile: 2.0502424240112305
10th percentile: 2.0740387439727783
20th percentile: 2.121631383895874
30th percentile: 2.1541162967681884
40th percentile: 2.171493482589722
50th percentile: 2.188870668411255
60th percentile: 2.1898614406585692
70th percentile: 2.1908522129058836
80th percentile: 3.144070529937745
90th percentile: 5.049516391754151
95th percentile: 6.002239322662353
99th percentile: 6.764417667388916
mean time: 3.1014108657836914
Pipeline stage StressChecker completed in 46.91s
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 0.71s
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 0.93s
Shutdown handler de-registered
rirv938-tune-mistral-gr_30207_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3237.74s
Shutdown handler de-registered
rirv938-tune-mistral-gr_30207_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-tune-mistral-gr_30207_v1 status is now torndown due to DeploymentManager action