rirv938-tune-mistral-gr_51403

developer_uid: rirv938

submission_id: rirv938-tune-mistral-gr_51403_v1

model_name: rirv938-tune-mistral-gr_51403_v1

model_group: rirv938/tune_mistral_grp

status: torndown

timestamp: 2025-04-30T23:58:42+00:00

num_battles: 6324

num_wins: 3292

celo_rating: 1304.09

family_friendly_score: 0.5562

family_friendly_standard_error: 0.007026258748437891

submission_type: basic

model_repo: rirv938/tune_mistral_grpo_cp592_92ff_v3_run3_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': 0.557223008616424, 'latency_mean': 1.7945466840267181, 'latency_p50': 1.8120332956314087, 'latency_p90': 1.9983741521835328}, {'batch_size': 4, 'throughput': 1.3808179298795231, 'latency_mean': 2.8790260410308837, 'latency_p50': 2.8775447607040405, 'latency_p90': 3.2044829368591308}, {'batch_size': 5, 'throughput': 1.549339238732302, 'latency_mean': 3.2174955868721007, 'latency_p50': 3.216069459915161, 'latency_p90': 3.6503391981124875}, {'batch_size': 8, 'throughput': 1.8933399214740692, 'latency_mean': 4.213166184425354, 'latency_p50': 4.2043997049331665, 'latency_p90': 4.777025127410888}, {'batch_size': 10, 'throughput': 1.9865971908842468, 'latency_mean': 4.980484048128128, 'latency_p50': 5.044927597045898, 'latency_p90': 5.627157664299011}, {'batch_size': 12, 'throughput': 2.0864722509466525, 'latency_mean': 5.686320195198059, 'latency_p50': 5.736629962921143, 'latency_p90': 6.591671204566955}, {'batch_size': 15, 'throughput': 2.130459102273198, 'latency_mean': 6.952828440666199, 'latency_p50': 6.9354599714279175, 'latency_p90': 7.9846714496612545}]

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

display_name: rirv938-tune-mistral-gr_51403_v1

is_internal_developer: True

language_model: rirv938/tune_mistral_grpo_cp592_92ff_v3_run3_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.74

us_pacific_date: 2025-04-30

win_ratio: 0.5205566097406704

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', '</s>', '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-51403-v1-mkmlizer
Waiting for job on rirv938-tune-mistral-gr-51403-v1-mkmlizer to finish
rirv938-tune-mistral-gr-51403-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-tune-mistral-gr-51403-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-tune-mistral-gr-51403-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-tune-mistral-gr-51403-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-tune-mistral-gr-51403-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-tune-mistral-gr-51403-v1-mkmlizer: ║       /___/                                                         ║
rirv938-tune-mistral-gr-51403-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-51403-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-tune-mistral-gr-51403-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-tune-mistral-gr-51403-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-tune-mistral-gr-51403-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-51403-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-tune-mistral-gr-51403-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-tune-mistral-gr-51403-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-51403-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-tune-mistral-gr-51403-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-tune-mistral-gr-51403-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-tune-mistral-gr-51403-v1-mkmlizer: ║                                                                     ║
rirv938-tune-mistral-gr-51403-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-tune-mistral-gr-51403-v1-mkmlizer: Downloaded to shared memory in 184.429s
rirv938-tune-mistral-gr-51403-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0gqc3jdj, device:0
rirv938-tune-mistral-gr-51403-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-tune-mistral-gr-51403-v1-mkmlizer: quantized model in 66.704s
rirv938-tune-mistral-gr-51403-v1-mkmlizer: Processed model rirv938/tune_mistral_grpo_cp592_92ff_v3_run3_merged in 251.135s
rirv938-tune-mistral-gr-51403-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-tune-mistral-gr-51403-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-tune-mistral-gr-51403-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-tune-mistral-gr-51403-v1
rirv938-tune-mistral-gr-51403-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-51403-v1/config.json
rirv938-tune-mistral-gr-51403-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-51403-v1/special_tokens_map.json
rirv938-tune-mistral-gr-51403-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-51403-v1/tokenizer_config.json
rirv938-tune-mistral-gr-51403-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-tune-mistral-gr-51403-v1/tokenizer.json
rirv938-tune-mistral-gr-51403-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-51403-v1/flywheel_model.1.safetensors
rirv938-tune-mistral-gr-51403-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-tune-mistral-gr-51403-v1/flywheel_model.0.safetensors
rirv938-tune-mistral-gr-51403-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:13, 25.87it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:29, 12.14it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:19, 18.36it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:29, 11.89it/s]
Loading 0:   4%|▍         | 15/363 [00:01<00:36,  9.63it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:25, 13.70it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:24, 14.02it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:31, 10.83it/s]
Loading 0:   8%|▊         | 28/363 [00:02<00:20, 16.14it/s]
Loading 0:   9%|▉         | 32/363 [00:02<00:17, 19.07it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:25, 12.80it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:26, 12.23it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:25, 12.88it/s]
Loading 0:  11%|█▏        | 41/363 [00:03<00:31, 10.34it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:20, 15.62it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:16, 18.97it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:22, 13.65it/s]
Loading 0:  15%|█▌        | 55/363 [00:04<00:23, 13.05it/s]
Loading 0:  16%|█▌        | 57/363 [00:04<00:22, 13.77it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:27, 11.25it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:17, 16.95it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 20.25it/s]
Loading 0:  20%|█▉        | 71/363 [00:05<00:20, 14.21it/s]
Loading 0:  20%|██        | 73/363 [00:05<00:21, 13.53it/s]
Loading 0:  21%|██        | 75/363 [00:05<00:20, 14.26it/s]
Loading 0:  21%|██        | 77/363 [00:05<00:24, 11.46it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.11it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.51it/s]
Loading 0:  25%|██▍       | 89/363 [00:06<00:19, 14.12it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:20, 13.44it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:15, 17.33it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 20.68it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 18.78it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:18, 14.04it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:19, 12.93it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:20, 12.66it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.58it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:22, 11.17it/s]
Loading 0:  33%|███▎      | 118/363 [00:08<00:14, 17.02it/s]
Loading 0:  34%|███▎      | 122/363 [00:08<00:11, 20.57it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:16, 14.79it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:16, 14.01it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:15, 14.80it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:19, 11.61it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:12, 17.53it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:10, 21.08it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:15, 14.55it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:14, 15.21it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:15, 13.47it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:16, 12.68it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:12, 16.70it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:10, 20.46it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:14, 14.32it/s]
Loading 0:  45%|████▍     | 163/363 [00:11<00:14, 13.62it/s]
Loading 0:  45%|████▌     | 165/363 [00:11<00:13, 14.38it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:17, 11.39it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:11, 17.19it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:08, 20.96it/s]
Loading 0:  49%|████▉     | 179/363 [00:12<00:12, 15.04it/s]
Loading 0:  50%|█████     | 182/363 [00:12<00:11, 15.63it/s]
Loading 0:  51%|█████     | 184/363 [00:12<00:12, 13.77it/s]
Loading 0:  51%|█████     | 186/363 [00:12<00:13, 13.12it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:09, 17.49it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:07, 21.40it/s]
Loading 0:  54%|█████▍    | 197/363 [00:13<00:11, 14.86it/s]
Loading 0:  55%|█████▌    | 200/363 [00:13<00:10, 15.32it/s]
Loading 0:  56%|█████▌    | 202/363 [00:28<04:29,  1.67s/it]
Loading 0:  56%|█████▌    | 203/363 [00:28<03:56,  1.48s/it]
Loading 0:  57%|█████▋    | 207/363 [00:28<02:12,  1.17it/s]
Loading 0:  58%|█████▊    | 210/363 [00:29<01:31,  1.67it/s]
Loading 0:  59%|█████▊    | 213/363 [00:29<01:06,  2.26it/s]
Loading 0:  59%|█████▉    | 215/363 [00:29<00:53,  2.74it/s]
Loading 0:  60%|█████▉    | 217/363 [00:29<00:43,  3.37it/s]
Loading 0:  60%|██████    | 219/363 [00:29<00:33,  4.25it/s]
Loading 0:  61%|██████    | 221/363 [00:30<00:29,  4.78it/s]
Loading 0:  62%|██████▏   | 226/363 [00:30<00:16,  8.42it/s]
Loading 0:  63%|██████▎   | 230/363 [00:30<00:11, 11.48it/s]
Loading 0:  64%|██████▍   | 233/363 [00:30<00:12, 10.29it/s]
Loading 0:  65%|██████▍   | 235/363 [00:30<00:12, 10.49it/s]
Loading 0:  65%|██████▌   | 237/363 [00:31<00:10, 11.56it/s]
Loading 0:  66%|██████▌   | 239/363 [00:31<00:12, 10.02it/s]
Loading 0:  67%|██████▋   | 244/363 [00:31<00:07, 15.55it/s]
Loading 0:  68%|██████▊   | 248/363 [00:31<00:06, 18.77it/s]
Loading 0:  69%|██████▉   | 251/363 [00:31<00:08, 13.30it/s]
Loading 0:  70%|██████▉   | 253/363 [00:32<00:08, 12.49it/s]
Loading 0:  70%|███████   | 255/363 [00:32<00:08, 13.26it/s]
Loading 0:  71%|███████   | 257/363 [00:32<00:09, 10.98it/s]
Loading 0:  72%|███████▏  | 262/363 [00:32<00:06, 16.69it/s]
Loading 0:  73%|███████▎  | 266/363 [00:32<00:04, 20.33it/s]
Loading 0:  74%|███████▍  | 269/363 [00:33<00:06, 14.10it/s]
Loading 0:  75%|███████▍  | 272/363 [00:33<00:06, 14.53it/s]
Loading 0:  75%|███████▌  | 274/363 [00:33<00:06, 12.85it/s]
Loading 0:  76%|███████▌  | 276/363 [00:33<00:07, 12.20it/s]
Loading 0:  77%|███████▋  | 280/363 [00:33<00:05, 15.92it/s]
Loading 0:  78%|███████▊  | 284/363 [00:34<00:04, 19.03it/s]
Loading 0:  79%|███████▉  | 287/363 [00:34<00:05, 13.47it/s]
Loading 0:  80%|███████▉  | 289/363 [00:34<00:05, 12.84it/s]
Loading 0:  80%|████████  | 291/363 [00:34<00:05, 13.73it/s]
Loading 0:  81%|████████  | 293/363 [00:35<00:06, 11.15it/s]
Loading 0:  82%|████████▏ | 298/363 [00:35<00:03, 16.71it/s]
Loading 0:  83%|████████▎ | 302/363 [00:35<00:03, 19.71it/s]
Loading 0:  84%|████████▍ | 305/363 [00:35<00:04, 13.34it/s]
Loading 0:  85%|████████▍ | 307/363 [00:35<00:04, 12.55it/s]
Loading 0:  85%|████████▌ | 309/363 [00:36<00:04, 13.03it/s]
Loading 0:  86%|████████▌ | 311/363 [00:36<00:04, 10.48it/s]
Loading 0:  87%|████████▋ | 316/363 [00:36<00:02, 15.92it/s]
Loading 0:  88%|████████▊ | 320/363 [00:36<00:02, 19.30it/s]
Loading 0:  89%|████████▉ | 323/363 [00:37<00:02, 13.88it/s]
Loading 0:  90%|████████▉ | 325/363 [00:37<00:02, 13.01it/s]
Loading 0:  90%|█████████ | 327/363 [00:37<00:02, 13.58it/s]
Loading 0:  91%|█████████ | 329/363 [00:37<00:03, 11.07it/s]
Loading 0:  92%|█████████▏| 334/363 [00:37<00:01, 16.75it/s]
Loading 0:  93%|█████████▎| 338/363 [00:37<00:01, 19.96it/s]
Loading 0:  94%|█████████▍| 341/363 [00:38<00:01, 14.26it/s]
Loading 0:  94%|█████████▍| 343/363 [00:38<00:01, 13.31it/s]
Loading 0:  95%|█████████▌| 345/363 [00:38<00:01, 14.05it/s]
Loading 0:  96%|█████████▌| 347/363 [00:38<00:01, 11.47it/s]
Loading 0:  97%|█████████▋| 352/363 [00:38<00:00, 17.38it/s]
Loading 0:  98%|█████████▊| 356/363 [00:39<00:00, 21.03it/s]
Loading 0:  99%|█████████▉| 359/363 [00:46<00:02,  1.47it/s]
Loading 0:  99%|█████████▉| 361/363 [00:46<00:01,  1.75it/s]
                                                            
Job rirv938-tune-mistral-gr-51403-v1-mkmlizer completed after 278.56s with status: succeeded
Stopping job with name rirv938-tune-mistral-gr-51403-v1-mkmlizer
Pipeline stage MKMLizer completed in 279.01s
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-51403-v1
Waiting for inference service rirv938-tune-mistral-gr-51403-v1 to be ready
Inference service rirv938-tune-mistral-gr-51403-v1 ready after 140.47783493995667s
Pipeline stage MKMLDeployer completed in 140.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.415665864944458s
Received healthy response to inference request in 2.105619430541992s
Received healthy response to inference request in 2.329936981201172s
Received healthy response to inference request in 1.8098843097686768s
Received healthy response to inference request in 1.787353277206421s
5 requests
0 failed requests
5th percentile: 1.7918594837188722
10th percentile: 1.7963656902313232
20th percentile: 1.8053781032562255
30th percentile: 1.8690313339233398
40th percentile: 1.987325382232666
50th percentile: 2.105619430541992
60th percentile: 2.195346450805664
70th percentile: 2.285073471069336
80th percentile: 2.347082757949829
90th percentile: 2.3813743114471437
95th percentile: 2.398520088195801
99th percentile: 2.4122367095947266
mean time: 2.089691972732544
Pipeline stage StressChecker completed in 11.86s
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 0.63s
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_51403_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 0.11s
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-51403-v1-profiler
Waiting for inference service rirv938-tune-mistral-gr-51403-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 2751.42s
Shutdown handler de-registered
rirv938-tune-mistral-gr_51403_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-tune-mistral-gr_51403_v1 status is now torndown due to DeploymentManager action