rirv938-tune-mistral-gr_58521

developer_uid: rirv938

submission_id: rirv938-tune-mistral-gr_58521_v1

model_name: rirv938-tune-mistral-gr_58521_v1

model_group: rirv938/tune_mistral_grp

status: torndown

timestamp: 2025-05-01T16:32:19+00:00

num_battles: 6092

num_wins: 3572

celo_rating: 1345.5

family_friendly_score: 0.597

family_friendly_standard_error: 0.006936728335461898

submission_type: basic

model_repo: rirv938/tune_mistral_grpo_cp1184_92ff_new_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': 0.550000842939119, 'latency_mean': 1.8181105744838715, 'latency_p50': 1.818008303642273, 'latency_p90': 2.0231704473495484}, {'batch_size': 3, 'throughput': 1.159978399968866, 'latency_mean': 2.5808839094638825, 'latency_p50': 2.5719186067581177, 'latency_p90': 2.8849044322967528}, {'batch_size': 5, 'throughput': 1.5224097923331286, 'latency_mean': 3.253735067844391, 'latency_p50': 3.204201579093933, 'latency_p90': 3.697920560836792}, {'batch_size': 6, 'throughput': 1.6622969767979998, 'latency_mean': 3.5875390326976775, 'latency_p50': 3.571089744567871, 'latency_p90': 4.029027032852173}, {'batch_size': 8, 'throughput': 1.8311566472490233, 'latency_mean': 4.335883492231369, 'latency_p50': 4.377238869667053, 'latency_p90': 4.847524547576905}, {'batch_size': 10, 'throughput': 1.9628336724560524, 'latency_mean': 5.063341798782349, 'latency_p50': 5.054078817367554, 'latency_p90': 5.721257758140564}]

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

display_name: rirv938-tune-mistral-gr_58521_v1

is_internal_developer: True

language_model: rirv938/tune_mistral_grpo_cp1184_92ff_new_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.7

us_pacific_date: 2025-05-01

win_ratio: 0.5863427445830598

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>', 'You:', '\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-58521-v1-mkmlizer
Waiting for job on rirv938-tune-mistral-gr-58521-v1-mkmlizer to finish
rirv938-tune-mistral-gr-58521-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-tune-mistral-gr-58521-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-tune-mistral-gr-58521-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-tune-mistral-gr-58521-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-tune-mistral-gr-58521-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-tune-mistral-gr-58521-v1-mkmlizer: ║       /___/                                                         ║
rirv938-tune-mistral-gr-58521-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-58521-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-tune-mistral-gr-58521-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-tune-mistral-gr-58521-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-tune-mistral-gr-58521-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-58521-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-tune-mistral-gr-58521-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-tune-mistral-gr-58521-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-58521-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-tune-mistral-gr-58521-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-tune-mistral-gr-58521-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-tune-mistral-gr-58521-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-58521-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-tune-mistral-gr-58521-v1-mkmlizer: Downloaded to shared memory in 173.418s
rirv938-tune-mistral-gr-58521-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpktfyyg1_, device:0
rirv938-tune-mistral-gr-58521-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission bogoconic1-nemo-280k-s6_46455_v1: HTTPConnectionPool(host='bogoconic1-nemo-280k-s6-46455-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-tune-mistral-gr-58521-v1-mkmlizer: quantized model in 62.069s
rirv938-tune-mistral-gr-58521-v1-mkmlizer: Processed model rirv938/tune_mistral_grpo_cp1184_92ff_new_merged in 235.488s
rirv938-tune-mistral-gr-58521-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-tune-mistral-gr-58521-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-tune-mistral-gr-58521-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-tune-mistral-gr-58521-v1
rirv938-tune-mistral-gr-58521-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-58521-v1/config.json
rirv938-tune-mistral-gr-58521-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-58521-v1/special_tokens_map.json
rirv938-tune-mistral-gr-58521-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-58521-v1/tokenizer_config.json
rirv938-tune-mistral-gr-58521-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-58521-v1/tokenizer.json
rirv938-tune-mistral-gr-58521-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-58521-v1/flywheel_model.1.safetensors
rirv938-tune-mistral-gr-58521-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-58521-v1/flywheel_model.0.safetensors
rirv938-tune-mistral-gr-58521-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.09it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:25, 14.04it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.86it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:25, 13.65it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:26, 13.26it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.92it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.35it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.12it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 23.02it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:20, 16.04it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:19, 16.63it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:24, 13.08it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 18.48it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 22.12it/s]
Loading 0:  15%|█▍        | 54/363 [00:03<00:21, 14.28it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:18, 16.25it/s]
Loading 0:  17%|█▋        | 60/363 [00:03<00:20, 14.70it/s]
Loading 0:  18%|█▊        | 65/363 [00:03<00:14, 19.87it/s]
Loading 0:  19%|█▉        | 69/363 [00:04<00:15, 18.71it/s]
Loading 0:  20%|█▉        | 72/363 [00:04<00:20, 14.34it/s]
Loading 0:  21%|██        | 75/363 [00:04<00:17, 16.30it/s]
Loading 0:  21%|██▏       | 78/363 [00:04<00:19, 14.88it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:14, 18.78it/s]
Loading 0:  24%|██▎       | 86/363 [00:04<00:12, 21.96it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:17, 15.73it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:16, 16.17it/s]
Loading 0:  27%|██▋       | 97/363 [00:05<00:12, 21.46it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:11, 22.39it/s]
Loading 0:  29%|██▊       | 104/363 [00:06<00:14, 18.46it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:17, 14.25it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 13.82it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.63it/s]
Loading 0:  31%|███       | 113/363 [00:06<00:20, 12.26it/s]
Loading 0:  33%|███▎      | 119/363 [00:07<00:12, 20.19it/s]
Loading 0:  34%|███▍      | 123/363 [00:07<00:12, 19.55it/s]
Loading 0:  35%|███▍      | 126/363 [00:07<00:16, 14.57it/s]
Loading 0:  36%|███▌      | 129/363 [00:07<00:13, 16.73it/s]
Loading 0:  36%|███▋      | 132/363 [00:07<00:15, 14.95it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 18.88it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:09, 22.82it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:13, 16.16it/s]
Loading 0:  40%|████      | 146/363 [00:08<00:13, 16.69it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:16, 12.99it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 18.43it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 22.08it/s]
Loading 0:  45%|████▍     | 162/363 [00:09<00:14, 14.31it/s]
Loading 0:  45%|████▌     | 165/363 [00:09<00:12, 16.31it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:13, 14.74it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 18.67it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 22.39it/s]
Loading 0:  50%|████▉     | 180/363 [00:10<00:12, 14.18it/s]
Loading 0:  50%|█████     | 183/363 [00:10<00:11, 16.13it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:12, 14.53it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 18.41it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:07, 22.11it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:10, 15.84it/s]
Loading 0:  55%|█████▌    | 200/363 [00:11<00:09, 16.55it/s]
Loading 0:  56%|█████▌    | 203/363 [00:26<03:45,  1.41s/it]
Loading 0:  57%|█████▋    | 207/363 [00:26<02:25,  1.07it/s]
Loading 0:  58%|█████▊    | 210/363 [00:26<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,  2.46it/s]
Loading 0:  60%|██████    | 219/363 [00:27<00:43,  3.34it/s]
Loading 0:  61%|██████    | 222/363 [00:27<00:33,  4.22it/s]
Loading 0:  62%|██████▏   | 226/363 [00:27<00:22,  6.19it/s]
Loading 0:  64%|██████▎   | 231/363 [00:28<00:15,  8.54it/s]
Loading 0:  64%|██████▍   | 234/363 [00:28<00:15,  8.52it/s]
Loading 0:  65%|██████▌   | 237/363 [00:28<00:12, 10.42it/s]
Loading 0:  66%|██████▌   | 240/363 [00:28<00:11, 10.76it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:08, 14.26it/s]
Loading 0:  69%|██████▊   | 249/363 [00:29<00:07, 16.07it/s]
Loading 0:  69%|██████▉   | 252/363 [00:29<00:08, 13.25it/s]
Loading 0:  70%|███████   | 255/363 [00:29<00:07, 15.38it/s]
Loading 0:  71%|███████   | 258/363 [00:29<00:07, 14.25it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 18.19it/s]
Loading 0:  74%|███████▎  | 267/363 [00:30<00:04, 19.20it/s]
Loading 0:  74%|███████▍  | 270/363 [00:30<00:06, 14.65it/s]
Loading 0:  75%|███████▌  | 273/363 [00:30<00:05, 16.77it/s]
Loading 0:  76%|███████▌  | 276/363 [00:31<00:05, 15.09it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 18.64it/s]
Loading 0:  78%|███████▊  | 284/363 [00:31<00:03, 22.14it/s]
Loading 0:  79%|███████▉  | 287/363 [00:31<00:04, 16.17it/s]
Loading 0:  80%|███████▉  | 290/363 [00:31<00:04, 16.57it/s]
Loading 0:  81%|████████  | 293/363 [00:32<00:05, 12.77it/s]
Loading 0:  82%|████████▏ | 298/363 [00:32<00:03, 17.82it/s]
Loading 0:  83%|████████▎ | 302/363 [00:32<00:02, 21.36it/s]
Loading 0:  84%|████████▍ | 305/363 [00:32<00:03, 15.66it/s]
Loading 0:  85%|████████▍ | 308/363 [00:32<00:03, 16.32it/s]
Loading 0:  86%|████████▌ | 311/363 [00:33<00:04, 12.75it/s]
Loading 0:  87%|████████▋ | 316/363 [00:33<00:02, 17.91it/s]
Loading 0:  88%|████████▊ | 320/363 [00:33<00:02, 21.46it/s]
Loading 0:  89%|████████▉ | 323/363 [00:33<00:02, 15.80it/s]
Loading 0:  90%|████████▉ | 326/363 [00:33<00:02, 16.47it/s]
Loading 0:  91%|█████████ | 329/363 [00:34<00:02, 12.95it/s]
Loading 0:  92%|█████████▏| 334/363 [00:34<00:01, 18.19it/s]
Loading 0:  93%|█████████▎| 339/363 [00:34<00:01, 18.95it/s]
Loading 0:  94%|█████████▍| 342/363 [00:34<00:01, 14.75it/s]
Loading 0:  95%|█████████▌| 345/363 [00:35<00:01, 16.78it/s]
Loading 0:  96%|█████████▌| 348/363 [00:35<00:01, 14.97it/s]
Loading 0:  97%|█████████▋| 353/363 [00:35<00:00, 20.29it/s]
Loading 0:  98%|█████████▊| 357/363 [00:42<00:03,  1.75it/s]
Loading 0:  99%|█████████▉| 360/363 [00:42<00:01,  2.24it/s]
Loading 0: 100%|█████████▉| 362/363 [00:42<00:00,  2.65it/s]
                                                            
Job rirv938-tune-mistral-gr-58521-v1-mkmlizer completed after 258.86s with status: succeeded
Stopping job with name rirv938-tune-mistral-gr-58521-v1-mkmlizer
Pipeline stage MKMLizer completed in 259.50s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-tune-mistral-gr-58521-v1
Waiting for inference service rirv938-tune-mistral-gr-58521-v1 to be ready
Inference service rirv938-tune-mistral-gr-58521-v1 ready after 140.59407258033752s
Pipeline stage MKMLDeployer completed in 141.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.668208599090576s
Received healthy response to inference request in 2.1830873489379883s
Received healthy response to inference request in 2.2337052822113037s
Received healthy response to inference request in 1.921924352645874s
Received healthy response to inference request in 2.1508963108062744s
5 requests
0 failed requests
5th percentile: 1.967718744277954
10th percentile: 2.013513135910034
20th percentile: 2.1051019191741944
30th percentile: 2.1573345184326174
40th percentile: 2.170210933685303
50th percentile: 2.1830873489379883
60th percentile: 2.2033345222473146
70th percentile: 2.2235816955566405
80th percentile: 2.3206059455871584
90th percentile: 2.4944072723388673
95th percentile: 2.5813079357147215
99th percentile: 2.650828466415405
mean time: 2.2315643787384034
Pipeline stage StressChecker completed in 12.62s
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 0.70s
Shutdown handler de-registered
rirv938-tune-mistral-gr_58521_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-tune-mistral-gr-58521-v1-profiler
Waiting for inference service rirv938-tune-mistral-gr-58521-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 3115.79s
Shutdown handler de-registered
rirv938-tune-mistral-gr_58521_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-tune-mistral-gr_58521_v1 status is now torndown due to DeploymentManager action