rirv938-tune-mistral-gr_98214

developer_uid: rirv938

submission_id: rirv938-tune-mistral-gr_98214_v1

model_name: rirv938-tune-mistral-gr_98214_v1

model_group: rirv938/tune_mistral_grp

status: torndown

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

num_battles: 6158

num_wins: 3364

celo_rating: 1319.93

family_friendly_score: 0.5822

family_friendly_standard_error: 0.006974857131153297

submission_type: basic

model_repo: rirv938/tune_mistral_grpo_cp296_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': 0.551463075682296, 'latency_mean': 1.8132963478565216, 'latency_p50': 1.826865315437317, 'latency_p90': 2.0255215406417846}, {'batch_size': 4, 'throughput': 1.3815892031945423, 'latency_mean': 2.8793024265766145, 'latency_p50': 2.87765634059906, 'latency_p90': 3.168198895454407}, {'batch_size': 5, 'throughput': 1.5596142609797665, 'latency_mean': 3.1915717220306394, 'latency_p50': 3.1644290685653687, 'latency_p90': 3.5936017990112306}, {'batch_size': 8, 'throughput': 1.8873063173031406, 'latency_mean': 4.207486947774887, 'latency_p50': 4.128833651542664, 'latency_p90': 4.791885495185852}, {'batch_size': 10, 'throughput': 1.981575110803489, 'latency_mean': 4.9972831308841705, 'latency_p50': 5.014037013053894, 'latency_p90': 5.677111339569092}, {'batch_size': 12, 'throughput': 2.07156120174488, 'latency_mean': 5.732963339090348, 'latency_p50': 5.7556174993515015, 'latency_p90': 6.455275440216064}, {'batch_size': 15, 'throughput': 2.162473708147402, 'latency_mean': 6.8551533472537995, 'latency_p50': 6.844102621078491, 'latency_p90': 7.855447244644164}]

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

display_name: rirv938-tune-mistral-gr_98214_v1

is_internal_developer: True

language_model: rirv938/tune_mistral_grpo_cp296_92ff_new_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.76

us_pacific_date: 2025-05-01

win_ratio: 0.5462812601493992

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-98214-v1-mkmlizer
Waiting for job on rirv938-tune-mistral-gr-98214-v1-mkmlizer to finish
rirv938-tune-mistral-gr-98214-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-tune-mistral-gr-98214-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-tune-mistral-gr-98214-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-tune-mistral-gr-98214-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-tune-mistral-gr-98214-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-tune-mistral-gr-98214-v1-mkmlizer: ║       /___/                                                         ║
rirv938-tune-mistral-gr-98214-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-98214-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-tune-mistral-gr-98214-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-tune-mistral-gr-98214-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-tune-mistral-gr-98214-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-98214-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-tune-mistral-gr-98214-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-tune-mistral-gr-98214-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-98214-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-tune-mistral-gr-98214-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-tune-mistral-gr-98214-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-tune-mistral-gr-98214-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-98214-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
rirv938-tune-mistral-gr-98214-v1-mkmlizer: Downloaded to shared memory in 164.140s
rirv938-tune-mistral-gr-98214-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzwuoth4k, device:0
rirv938-tune-mistral-gr-98214-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-tune-mistral-gr-98214-v1-mkmlizer: quantized model in 62.655s
rirv938-tune-mistral-gr-98214-v1-mkmlizer: Processed model rirv938/tune_mistral_grpo_cp296_92ff_new_merged in 226.796s
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-98214-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-tune-mistral-gr-98214-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-tune-mistral-gr-98214-v1
rirv938-tune-mistral-gr-98214-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-98214-v1/config.json
rirv938-tune-mistral-gr-98214-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-98214-v1/special_tokens_map.json
rirv938-tune-mistral-gr-98214-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-98214-v1/tokenizer_config.json
rirv938-tune-mistral-gr-98214-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-98214-v1/tokenizer.json
rirv938-tune-mistral-gr-98214-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-98214-v1/flywheel_model.1.safetensors
rirv938-tune-mistral-gr-98214-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-98214-v1/flywheel_model.0.safetensors
rirv938-tune-mistral-gr-98214-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:17, 20.85it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:19, 17.93it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:15, 23.01it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:24, 14.28it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:26, 13.30it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.75it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.47it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.63it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:16, 19.72it/s]
Loading 0:  10%|▉         | 36/363 [00:02<00:22, 14.76it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:19, 16.75it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:21, 14.77it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:16, 18.74it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:13, 22.69it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:19, 15.98it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:18, 16.64it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:23, 13.06it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 18.35it/s]
Loading 0:  19%|█▉        | 69/363 [00:04<00:15, 19.05it/s]
Loading 0:  20%|█▉        | 72/363 [00:04<00:19, 14.74it/s]
Loading 0:  21%|██        | 75/363 [00:04<00:17, 16.69it/s]
Loading 0:  21%|██▏       | 78/363 [00:04<00:18, 15.12it/s]
Loading 0:  23%|██▎       | 83/363 [00:04<00:13, 20.39it/s]
Loading 0:  24%|██▍       | 87/363 [00:05<00:14, 19.28it/s]
Loading 0:  25%|██▍       | 90/363 [00:05<00:18, 14.59it/s]
Loading 0:  26%|██▋       | 96/363 [00:05<00:12, 21.17it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:11, 22.84it/s]
Loading 0:  29%|██▊       | 104/363 [00:05<00:13, 18.81it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:17, 14.75it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 13.77it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.28it/s]
Loading 0:  31%|███       | 113/363 [00:06<00:20, 11.98it/s]
Loading 0:  33%|███▎      | 118/363 [00:06<00:13, 18.21it/s]
Loading 0:  34%|███▍      | 123/363 [00:07<00:12, 18.89it/s]
Loading 0:  35%|███▍      | 126/363 [00:07<00:16, 14.19it/s]
Loading 0:  36%|███▌      | 129/363 [00:07<00:14, 16.22it/s]
Loading 0:  36%|███▋      | 132/363 [00:07<00:15, 14.48it/s]
Loading 0:  38%|███▊      | 137/363 [00:08<00:11, 19.78it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.21it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:14, 14.89it/s]
Loading 0:  40%|████      | 146/363 [00:08<00:14, 15.42it/s]
Loading 0:  41%|████      | 148/363 [00:08<00:15, 13.62it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:15, 13.36it/s]
Loading 0:  43%|████▎     | 155/363 [00:09<00:10, 19.60it/s]
Loading 0:  44%|████▍     | 159/363 [00:09<00:10, 18.77it/s]
Loading 0:  45%|████▍     | 162/363 [00:09<00:14, 13.90it/s]
Loading 0:  45%|████▌     | 165/363 [00:09<00:12, 15.88it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:13, 14.37it/s]
Loading 0:  48%|████▊     | 173/363 [00:10<00:09, 19.89it/s]
Loading 0:  49%|████▉     | 177/363 [00:10<00:09, 18.93it/s]
Loading 0:  50%|████▉     | 180/363 [00:10<00:12, 14.61it/s]
Loading 0:  50%|█████     | 183/363 [00:10<00:10, 16.79it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:11, 15.37it/s]
Loading 0:  53%|█████▎    | 191/363 [00:11<00:08, 20.91it/s]
Loading 0:  54%|█████▎    | 195/363 [00:11<00:08, 20.01it/s]
Loading 0:  55%|█████▍    | 198/363 [00:11<00:11, 14.91it/s]
Loading 0:  55%|█████▌    | 200/363 [00:26<00:10, 14.91it/s]
Loading 0:  55%|█████▌    | 201/363 [00:26<03:35,  1.33s/it]
Loading 0:  56%|█████▌    | 203/363 [00:26<02:55,  1.10s/it]
Loading 0:  57%|█████▋    | 207/363 [00:26<01:50,  1.41it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:20,  1.91it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<00:59,  2.53it/s]
Loading 0:  59%|█████▉    | 215/363 [00:27<00:49,  3.02it/s]
Loading 0:  60%|█████▉    | 217/363 [00:27<00:39,  3.66it/s]
Loading 0:  60%|██████    | 219/363 [00:27<00:31,  4.59it/s]
Loading 0:  61%|██████    | 221/363 [00:28<00:27,  5.17it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:15,  9.00it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:10, 12.13it/s]
Loading 0:  64%|██████▍   | 233/363 [00:28<00:12, 10.73it/s]
Loading 0:  65%|██████▌   | 236/363 [00:28<00:10, 12.18it/s]
Loading 0:  66%|██████▌   | 238/363 [00:29<00:10, 11.58it/s]
Loading 0:  66%|██████▌   | 240/363 [00:29<00:10, 11.56it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:07, 15.47it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:06, 18.57it/s]
Loading 0:  69%|██████▉   | 251/363 [00:29<00:08, 13.42it/s]
Loading 0:  70%|██████▉   | 253/363 [00:30<00:08, 13.13it/s]
Loading 0:  70%|███████   | 255/363 [00:30<00:07, 14.10it/s]
Loading 0:  71%|███████   | 257/363 [00:30<00:09, 11.69it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 18.09it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:04, 22.29it/s]
Loading 0:  74%|███████▍  | 269/363 [00:30<00:05, 15.79it/s]
Loading 0:  75%|███████▍  | 272/363 [00:31<00:05, 16.46it/s]
Loading 0:  76%|███████▌  | 275/363 [00:31<00:06, 12.90it/s]
Loading 0:  77%|███████▋  | 281/363 [00:31<00:04, 19.67it/s]
Loading 0:  79%|███████▊  | 285/363 [00:31<00:04, 18.90it/s]
Loading 0:  79%|███████▉  | 288/363 [00:32<00:05, 14.37it/s]
Loading 0:  80%|████████  | 291/363 [00:32<00:04, 16.36it/s]
Loading 0:  81%|████████  | 294/363 [00:32<00:04, 14.98it/s]
Loading 0:  82%|████████▏ | 299/363 [00:32<00:03, 20.38it/s]
Loading 0:  83%|████████▎ | 303/363 [00:32<00:03, 19.06it/s]
Loading 0:  84%|████████▍ | 306/363 [00:33<00:03, 14.46it/s]
Loading 0:  85%|████████▌ | 309/363 [00:33<00:03, 16.29it/s]
Loading 0:  86%|████████▌ | 312/363 [00:33<00:03, 14.81it/s]
Loading 0:  87%|████████▋ | 317/363 [00:33<00:02, 20.25it/s]
Loading 0:  88%|████████▊ | 321/363 [00:33<00:02, 19.10it/s]
Loading 0:  89%|████████▉ | 324/363 [00:34<00:02, 14.62it/s]
Loading 0:  90%|█████████ | 327/363 [00:34<00:02, 16.72it/s]
Loading 0:  91%|█████████ | 330/363 [00:34<00:02, 14.92it/s]
Loading 0:  92%|█████████▏| 334/363 [00:34<00:01, 18.92it/s]
Loading 0:  93%|█████████▎| 338/363 [00:34<00:01, 22.74it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:01, 16.14it/s]
Loading 0:  95%|█████████▍| 344/363 [00:35<00:01, 16.75it/s]
Loading 0:  96%|█████████▌| 347/363 [00:35<00:01, 12.85it/s]
Loading 0:  97%|█████████▋| 352/363 [00:35<00:00, 17.77it/s]
Loading 0:  98%|█████████▊| 356/363 [00:35<00:00, 21.41it/s]
Loading 0:  99%|█████████▉| 359/363 [00:43<00:02,  1.60it/s]
Loading 0: 100%|█████████▉| 362/363 [00:43<00:00,  2.06it/s]
                                                            
Job rirv938-tune-mistral-gr-98214-v1-mkmlizer completed after 258.2s with status: succeeded
Stopping job with name rirv938-tune-mistral-gr-98214-v1-mkmlizer
Pipeline stage MKMLizer completed in 258.71s
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-98214-v1
Waiting for inference service rirv938-tune-mistral-gr-98214-v1 to be ready
Inference service rirv938-tune-mistral-gr-98214-v1 ready after 150.536301612854s
Pipeline stage MKMLDeployer completed in 151.04s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5177996158599854s
Received healthy response to inference request in 1.9127693176269531s
Received healthy response to inference request in 2.1266376972198486s
Received healthy response to inference request in 2.026067018508911s
Received healthy response to inference request in 1.9763998985290527s
5 requests
0 failed requests
5th percentile: 1.925495433807373
10th percentile: 1.938221549987793
20th percentile: 1.9636737823486328
30th percentile: 1.9863333225250244
40th percentile: 2.006200170516968
50th percentile: 2.026067018508911
60th percentile: 2.066295289993286
70th percentile: 2.106523561477661
80th percentile: 2.204870080947876
90th percentile: 2.3613348484039305
95th percentile: 2.439567232131958
99th percentile: 2.50215313911438
mean time: 2.11193470954895
Pipeline stage StressChecker completed in 11.89s
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 0.89s
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 0.66s
Shutdown handler de-registered
rirv938-tune-mistral-gr_98214_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-tune-mistral-gr-98214-v1-profiler
Waiting for inference service rirv938-tune-mistral-gr-98214-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 3136.43s
Shutdown handler de-registered
rirv938-tune-mistral-gr_98214_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-tune-mistral-gr_98214_v1 status is now torndown due to DeploymentManager action