developer_uid: NischayDnk
submission_id: chaiml-mergev7-mistral3_80261_v1
model_name: chaiml-mergev7-mistral3_80261_v1
model_group: ChaiML/mergev7_mistral3_
status: torndown
timestamp: 2025-04-08T21:32:22+00:00
num_battles: 7891
num_wins: 3144
celo_rating: 1210.73
family_friendly_score: 0.5746
family_friendly_standard_error: 0.006991921624274688
submission_type: basic
model_repo: ChaiML/mergev7_mistral3_31_sft_del5k
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.3691758684531105, 'latency_mean': 2.7086425971984864, 'latency_p50': 2.7050070762634277, 'latency_p90': 2.9971096992492674}, {'batch_size': 2, 'throughput': 0.572628866122346, 'latency_mean': 3.485852643251419, 'latency_p50': 3.4869327545166016, 'latency_p90': 3.783342409133911}, {'batch_size': 3, 'throughput': 0.7237684303433078, 'latency_mean': 4.126536254882812, 'latency_p50': 4.121619462966919, 'latency_p90': 4.546071028709411}, {'batch_size': 4, 'throughput': 0.8418592881101298, 'latency_mean': 4.725566109418869, 'latency_p50': 4.726393461227417, 'latency_p90': 5.182833504676819}, {'batch_size': 5, 'throughput': 0.9356901652822163, 'latency_mean': 5.318809833526611, 'latency_p50': 5.317508816719055, 'latency_p90': 5.946421027183533}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-mergev7-mistral3_80261_v1
is_internal_developer: False
language_model: ChaiML/mergev7_mistral3_31_sft_del5k
model_size: 24B
ranking_group: single
throughput_3p7s: 0.63
us_pacific_date: 2025-04-08
win_ratio: 0.39842858953237864
generation_params: {'temperature': 0.45, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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 chaiml-mergev7-mistral3-80261-v1-mkmlizer
Waiting for job on chaiml-mergev7-mistral3-80261-v1-mkmlizer to finish
chaiml-mergev7-mistral3-80261-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mergev7-mistral3-80261-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mergev7-mistral3-80261-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mergev7-mistral3-80261-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mergev7-mistral3-80261-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mergev7-mistral3-80261-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mergev7-mistral3-80261-v1-mkmlizer: ║                                                                     ║
chaiml-mergev7-mistral3-80261-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-mergev7-mistral3-80261-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mergev7-mistral3-80261-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mergev7-mistral3-80261-v1-mkmlizer: ║                                                                     ║
chaiml-mergev7-mistral3-80261-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mergev7-mistral3-80261-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mergev7-mistral3-80261-v1-mkmlizer: ║                                                                     ║
chaiml-mergev7-mistral3-80261-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mergev7-mistral3-80261-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mergev7-mistral3-80261-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-mergev7-mistral3-80261-v1-mkmlizer: ║                                                                     ║
chaiml-mergev7-mistral3-80261-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mergev7-mistral3-80261-v1-mkmlizer: Downloaded to shared memory in 87.364s
chaiml-mergev7-mistral3-80261-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxuguilzy, device:0
chaiml-mergev7-mistral3-80261-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mergev7-mistral3-80261-v1-mkmlizer: quantized model in 52.991s
chaiml-mergev7-mistral3-80261-v1-mkmlizer: Processed model ChaiML/mergev7_mistral3_31_sft_del5k in 140.355s
chaiml-mergev7-mistral3-80261-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mergev7-mistral3-80261-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mergev7-mistral3-80261-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mergev7-mistral3-80261-v1
chaiml-mergev7-mistral3-80261-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mergev7-mistral3-80261-v1/config.json
chaiml-mergev7-mistral3-80261-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mergev7-mistral3-80261-v1/special_tokens_map.json
chaiml-mergev7-mistral3-80261-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mergev7-mistral3-80261-v1/tokenizer_config.json
chaiml-mergev7-mistral3-80261-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mergev7-mistral3-80261-v1/tokenizer.json
chaiml-mergev7-mistral3-80261-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mergev7-mistral3-80261-v1/flywheel_model.1.safetensors
chaiml-mergev7-mistral3-80261-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mergev7-mistral3-80261-v1/flywheel_model.0.safetensors
chaiml-mergev7-mistral3-80261-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:18,  3.04s/it]
Loading 0:   1%|▏         | 5/363 [00:06<05:54,  1.01it/s]
Loading 0:   2%|▏         | 7/363 [00:06<03:43,  1.59it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:26,  4.03it/s]
Loading 0:   4%|▍         | 16/363 [00:06<01:05,  5.29it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:42,  8.05it/s]
Loading 0:   7%|▋         | 25/363 [00:07<00:36,  9.31it/s]
Loading 0:   9%|▊         | 31/363 [00:07<00:23, 13.85it/s]
Loading 0:   9%|▉         | 34/363 [00:07<00:22, 14.87it/s]
Loading 0:  10%|█         | 38/363 [00:07<00:17, 18.31it/s]
Loading 0:  11%|█▏        | 41/363 [00:07<00:16, 20.09it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:15, 21.13it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:12, 25.88it/s]
Loading 0:  15%|█▍        | 53/363 [00:08<00:12, 25.46it/s]
Loading 0:  16%|█▌        | 58/363 [00:08<00:10, 29.36it/s]
Loading 0:  17%|█▋        | 62/363 [00:08<00:14, 20.81it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:12, 24.35it/s]
Loading 0:  19%|█▉        | 70/363 [00:08<00:12, 22.72it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:10, 28.12it/s]
Loading 0:  22%|██▏       | 80/363 [00:09<00:10, 27.17it/s]
Loading 0:  23%|██▎       | 85/363 [00:09<00:09, 30.55it/s]
Loading 0:  25%|██▍       | 89/363 [00:09<00:09, 28.31it/s]
Loading 0:  26%|██▌       | 94/363 [00:09<00:08, 31.42it/s]
Loading 0:  27%|██▋       | 98/363 [00:09<00:11, 22.27it/s]
Loading 0:  28%|██▊       | 103/363 [00:09<00:10, 25.97it/s]
Loading 0:  29%|██▉       | 107/363 [00:10<00:10, 23.77it/s]
Loading 0:  31%|███       | 112/363 [00:10<00:09, 27.32it/s]
Loading 0:  32%|███▏      | 116/363 [00:10<00:09, 27.11it/s]
Loading 0:  33%|███▎      | 121/363 [00:10<00:07, 30.40it/s]
Loading 0:  34%|███▍      | 125/363 [00:10<00:08, 28.96it/s]
Loading 0:  36%|███▌      | 130/363 [00:10<00:07, 32.11it/s]
Loading 0:  37%|███▋      | 134/363 [00:10<00:07, 30.51it/s]
Loading 0:  38%|███▊      | 139/363 [00:11<00:09, 24.86it/s]
Loading 0:  39%|███▉      | 142/363 [00:11<00:09, 23.24it/s]
Loading 0:  41%|████      | 148/363 [00:11<00:07, 28.93it/s]
Loading 0:  42%|████▏     | 152/363 [00:11<00:07, 27.95it/s]
Loading 0:  43%|████▎     | 157/363 [00:11<00:06, 30.83it/s]
Loading 0:  44%|████▍     | 161/363 [00:11<00:07, 28.53it/s]
Loading 0:  46%|████▌     | 166/363 [00:12<00:06, 31.69it/s]
Loading 0:  47%|████▋     | 170/363 [00:12<00:06, 29.51it/s]
Loading 0:  48%|████▊     | 175/363 [00:12<00:05, 31.95it/s]
Loading 0:  49%|████▉     | 179/363 [00:12<00:08, 22.14it/s]
Loading 0:  51%|█████     | 184/363 [00:12<00:07, 25.26it/s]
Loading 0:  52%|█████▏    | 187/363 [00:27<03:10,  1.08s/it]
Loading 0:  53%|█████▎    | 191/363 [00:27<02:12,  1.30it/s]
Loading 0:  54%|█████▎    | 195/363 [00:27<01:35,  1.76it/s]
Loading 0:  56%|█████▌    | 202/363 [00:27<00:53,  2.99it/s]
Loading 0:  57%|█████▋    | 206/363 [00:27<00:40,  3.88it/s]
Loading 0:  58%|█████▊    | 211/363 [00:28<00:28,  5.42it/s]
Loading 0:  59%|█████▉    | 215/363 [00:28<00:23,  6.37it/s]
Loading 0:  61%|██████    | 220/363 [00:28<00:16,  8.74it/s]
Loading 0:  62%|██████▏   | 224/363 [00:28<00:13, 10.44it/s]
Loading 0:  63%|██████▎   | 229/363 [00:28<00:09, 13.67it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:08, 15.55it/s]
Loading 0:  66%|██████▌   | 238/363 [00:29<00:06, 19.36it/s]
Loading 0:  67%|██████▋   | 242/363 [00:29<00:05, 20.92it/s]
Loading 0:  68%|██████▊   | 247/363 [00:29<00:04, 24.27it/s]
Loading 0:  69%|██████▉   | 251/363 [00:29<00:04, 24.90it/s]
Loading 0:  71%|███████   | 256/363 [00:29<00:04, 22.37it/s]
Loading 0:  71%|███████▏  | 259/363 [00:30<00:04, 21.25it/s]
Loading 0:  72%|███████▏  | 263/363 [00:30<00:04, 24.57it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:03, 25.56it/s]
Loading 0:  74%|███████▍  | 269/363 [00:30<00:03, 25.75it/s]
Loading 0:  75%|███████▌  | 274/363 [00:30<00:02, 30.00it/s]
Loading 0:  77%|███████▋  | 278/363 [00:30<00:03, 28.30it/s]
Loading 0:  78%|███████▊  | 283/363 [00:30<00:02, 31.47it/s]
Loading 0:  79%|███████▉  | 287/363 [00:30<00:02, 29.95it/s]
Loading 0:  80%|████████  | 292/363 [00:31<00:02, 32.54it/s]
Loading 0:  82%|████████▏ | 296/363 [00:31<00:03, 21.72it/s]
Loading 0:  83%|████████▎ | 301/363 [00:31<00:02, 25.01it/s]
Loading 0:  84%|████████▎ | 304/363 [00:31<00:02, 23.81it/s]
Loading 0:  85%|████████▌ | 310/363 [00:31<00:01, 29.58it/s]
Loading 0:  87%|████████▋ | 314/363 [00:31<00:01, 28.41it/s]
Loading 0:  88%|████████▊ | 319/363 [00:32<00:01, 31.49it/s]
Loading 0:  89%|████████▉ | 323/363 [00:32<00:01, 29.93it/s]
Loading 0:  90%|█████████ | 328/363 [00:32<00:01, 31.04it/s]
Loading 0:  91%|█████████▏| 332/363 [00:32<00:01, 21.25it/s]
Loading 0:  93%|█████████▎| 337/363 [00:32<00:01, 24.94it/s]
Loading 0:  94%|█████████▎| 340/363 [00:32<00:00, 23.80it/s]
Loading 0:  95%|█████████▌| 346/363 [00:33<00:00, 29.49it/s]
Loading 0:  96%|█████████▋| 350/363 [00:33<00:00, 28.49it/s]
Loading 0:  98%|█████████▊| 355/363 [00:33<00:00, 31.82it/s]
Loading 0:  99%|█████████▉| 359/363 [00:33<00:00, 28.30it/s]
                                                            

Job chaiml-mergev7-mistral3-80261-v1-mkmlizer completed after 177.17s with status: succeeded
Stopping job with name chaiml-mergev7-mistral3-80261-v1-mkmlizer
Pipeline stage MKMLizer completed in 177.67s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mergev7-mistral3-80261-v1
Waiting for inference service chaiml-mergev7-mistral3-80261-v1 to be ready
Inference service chaiml-mergev7-mistral3-80261-v1 ready after 100.35554313659668s
Pipeline stage MKMLDeployer completed in 100.90s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.180387020111084s
Received healthy response to inference request in 2.790724992752075s
Received healthy response to inference request in 2.3894553184509277s
Received healthy response to inference request in 2.357663631439209s
Received healthy response to inference request in 2.4327573776245117s
5 requests
0 failed requests
5th percentile: 2.364021968841553
10th percentile: 2.3703803062438964
20th percentile: 2.383096981048584
30th percentile: 2.3981157302856446
40th percentile: 2.415436553955078
50th percentile: 2.4327573776245117
60th percentile: 2.575944423675537
70th percentile: 2.7191314697265625
80th percentile: 2.868657398223877
90th percentile: 3.0245222091674804
95th percentile: 3.102454614639282
99th percentile: 3.1648005390167238
mean time: 2.6301976680755614
Pipeline stage StressChecker completed in 14.59s
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 0.91s
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
chaiml-mergev7-mistral3_80261_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 2852.35s
Shutdown handler de-registered
chaiml-mergev7-mistral3_80261_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mergev7-mistral3_80261_v1 status is now torndown due to DeploymentManager action