developer_uid: NischayDnk
submission_id: chaiml-mergev8-mistral3_13321_v1
model_name: chaiml-mergev8-mistral3_13321_v1
model_group: ChaiML/mergev8_mistral3_
status: torndown
timestamp: 2025-04-08T22:15:26+00:00
num_battles: 8788
num_wins: 2866
celo_rating: 1137.07
family_friendly_score: 0.5636
family_friendly_standard_error: 0.007013630158484265
submission_type: basic
model_repo: ChaiML/mergev8_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': 0.3663696517583525, 'latency_mean': 2.7293910586833956, 'latency_p50': 2.727843403816223, 'latency_p90': 3.022299790382385}, {'batch_size': 2, 'throughput': 0.5679486522369128, 'latency_mean': 3.5119946324825286, 'latency_p50': 3.5209391117095947, 'latency_p90': 3.8313575744628907}, {'batch_size': 3, 'throughput': 0.7197644486384607, 'latency_mean': 4.160278809070587, 'latency_p50': 4.18899405002594, 'latency_p90': 4.598216772079468}, {'batch_size': 4, 'throughput': 0.8367563585948902, 'latency_mean': 4.762569063901902, 'latency_p50': 4.735523223876953, 'latency_p90': 5.271257972717285}, {'batch_size': 5, 'throughput': 0.9195812756220084, 'latency_mean': 5.419329261779785, 'latency_p50': 5.419592380523682, 'latency_p90': 5.939736366271973}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-mergev8-mistral3_13321_v1
is_internal_developer: False
language_model: ChaiML/mergev8_mistral3_31_sft_del5k
model_size: 24B
ranking_group: single
throughput_3p7s: 0.62
us_pacific_date: 2025-04-08
win_ratio: 0.3261265361857078
generation_params: {'temperature': 0.5, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.375, 'frequency_penalty': 0.375, 'stopping_words': ['\n', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '', '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-mergev8-mistral3-13321-v1-mkmlizer
Waiting for job on chaiml-mergev8-mistral3-13321-v1-mkmlizer to finish
chaiml-mergev8-mistral3-13321-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mergev8-mistral3-13321-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mergev8-mistral3-13321-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mergev8-mistral3-13321-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mergev8-mistral3-13321-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mergev8-mistral3-13321-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mergev8-mistral3-13321-v1-mkmlizer: ║                                                                     ║
chaiml-mergev8-mistral3-13321-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-mergev8-mistral3-13321-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mergev8-mistral3-13321-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mergev8-mistral3-13321-v1-mkmlizer: ║                                                                     ║
chaiml-mergev8-mistral3-13321-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mergev8-mistral3-13321-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mergev8-mistral3-13321-v1-mkmlizer: ║                                                                     ║
chaiml-mergev8-mistral3-13321-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mergev8-mistral3-13321-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mergev8-mistral3-13321-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-mergev8-mistral3-13321-v1-mkmlizer: ║                                                                     ║
chaiml-mergev8-mistral3-13321-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mergev8-mistral3-13321-v1-mkmlizer: Downloaded to shared memory in 80.629s
chaiml-mergev8-mistral3-13321-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpahae3ct4, device:0
chaiml-mergev8-mistral3-13321-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mergev8-mistral3-13321-v1-mkmlizer: quantized model in 54.014s
chaiml-mergev8-mistral3-13321-v1-mkmlizer: Processed model ChaiML/mergev8_mistral3_31_sft_del5k in 134.644s
chaiml-mergev8-mistral3-13321-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mergev8-mistral3-13321-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mergev8-mistral3-13321-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mergev8-mistral3-13321-v1
chaiml-mergev8-mistral3-13321-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mergev8-mistral3-13321-v1/config.json
chaiml-mergev8-mistral3-13321-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mergev8-mistral3-13321-v1/special_tokens_map.json
chaiml-mergev8-mistral3-13321-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mergev8-mistral3-13321-v1/tokenizer_config.json
chaiml-mergev8-mistral3-13321-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mergev8-mistral3-13321-v1/tokenizer.json
chaiml-mergev8-mistral3-13321-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mergev8-mistral3-13321-v1/flywheel_model.1.safetensors
chaiml-mergev8-mistral3-13321-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mergev8-mistral3-13321-v1/flywheel_model.0.safetensors
chaiml-mergev8-mistral3-13321-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:40,  3.10s/it]
Loading 0:   1%|▏         | 5/363 [00:06<06:02,  1.01s/it]
Loading 0:   2%|▏         | 7/363 [00:06<03:48,  1.56it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:28,  3.94it/s]
Loading 0:   4%|▍         | 16/363 [00:06<01:07,  5.18it/s]
Loading 0:   6%|▌         | 22/363 [00:07<00:43,  7.83it/s]
Loading 0:   7%|▋         | 25/363 [00:07<00:37,  9.08it/s]
Loading 0:   9%|▊         | 31/363 [00:07<00:24, 13.56it/s]
Loading 0:   9%|▉         | 34/363 [00:07<00:22, 14.40it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:16, 19.30it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:16, 19.08it/s]
Loading 0:  13%|█▎        | 49/363 [00:08<00:13, 23.63it/s]
Loading 0:  14%|█▍        | 52/363 [00:08<00:14, 22.11it/s]
Loading 0:  16%|█▌        | 58/363 [00:08<00:11, 27.20it/s]
Loading 0:  17%|█▋        | 62/363 [00:08<00:15, 19.58it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:12, 23.18it/s]
Loading 0:  19%|█▉        | 70/363 [00:09<00:13, 21.67it/s]
Loading 0:  21%|██        | 76/363 [00:09<00:10, 26.39it/s]
Loading 0:  22%|██▏       | 80/363 [00:09<00:11, 25.51it/s]
Loading 0:  23%|██▎       | 85/363 [00:09<00:10, 27.76it/s]
Loading 0:  24%|██▍       | 88/363 [00:09<00:11, 24.27it/s]
Loading 0:  26%|██▌       | 94/363 [00:09<00:09, 29.04it/s]
Loading 0:  27%|██▋       | 98/363 [00:10<00:12, 20.58it/s]
Loading 0:  28%|██▊       | 103/363 [00:10<00:10, 23.64it/s]
Loading 0:  29%|██▉       | 106/363 [00:10<00:11, 21.84it/s]
Loading 0:  31%|███       | 112/363 [00:10<00:09, 26.72it/s]
Loading 0:  32%|███▏      | 115/363 [00:10<00:10, 23.85it/s]
Loading 0:  33%|███▎      | 121/363 [00:10<00:08, 28.51it/s]
Loading 0:  34%|███▍      | 125/363 [00:11<00:08, 26.62it/s]
Loading 0:  36%|███▌      | 130/363 [00:11<00:08, 28.96it/s]
Loading 0:  37%|███▋      | 134/363 [00:11<00:08, 26.91it/s]
Loading 0:  38%|███▊      | 139/363 [00:11<00:10, 21.93it/s]
Loading 0:  39%|███▉      | 142/363 [00:11<00:10, 20.51it/s]
Loading 0:  41%|████      | 148/363 [00:12<00:08, 25.16it/s]
Loading 0:  42%|████▏     | 151/363 [00:12<00:09, 23.00it/s]
Loading 0:  43%|████▎     | 157/363 [00:12<00:07, 27.69it/s]
Loading 0:  44%|████▍     | 160/363 [00:12<00:08, 24.67it/s]
Loading 0:  46%|████▌     | 166/363 [00:12<00:06, 29.13it/s]
Loading 0:  47%|████▋     | 170/363 [00:12<00:07, 27.26it/s]
Loading 0:  48%|████▊     | 175/363 [00:13<00:06, 29.25it/s]
Loading 0:  49%|████▉     | 179/363 [00:13<00:08, 20.58it/s]
Loading 0:  51%|█████     | 184/363 [00:13<00:07, 23.91it/s]
Loading 0:  52%|█████▏    | 187/363 [00:27<03:09,  1.08s/it]
Loading 0:  53%|█████▎    | 191/363 [00:28<02:12,  1.30it/s]
Loading 0:  54%|█████▎    | 195/363 [00:28<01:35,  1.76it/s]
Loading 0:  56%|█████▌    | 202/363 [00:28<00:53,  2.99it/s]
Loading 0:  57%|█████▋    | 206/363 [00:28<00:40,  3.87it/s]
Loading 0:  58%|█████▊    | 211/363 [00:28<00:28,  5.38it/s]
Loading 0:  59%|█████▉    | 215/363 [00:29<00:23,  6.30it/s]
Loading 0:  61%|██████    | 220/363 [00:29<00:16,  8.65it/s]
Loading 0:  62%|██████▏   | 224/363 [00:29<00:13, 10.52it/s]
Loading 0:  63%|██████▎   | 229/363 [00:29<00:09, 13.81it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:08, 15.82it/s]
Loading 0:  66%|██████▌   | 238/363 [00:29<00:06, 19.29it/s]
Loading 0:  67%|██████▋   | 242/363 [00:30<00:05, 20.32it/s]
Loading 0:  68%|██████▊   | 247/363 [00:30<00:04, 24.32it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:04, 24.82it/s]
Loading 0:  71%|███████   | 256/363 [00:30<00:04, 21.89it/s]
Loading 0:  71%|███████▏  | 259/363 [00:30<00:04, 20.81it/s]
Loading 0:  73%|███████▎  | 265/363 [00:30<00:03, 25.82it/s]
Loading 0:  74%|███████▍  | 268/363 [00:31<00:04, 23.38it/s]
Loading 0:  75%|███████▌  | 274/363 [00:31<00:03, 28.32it/s]
Loading 0:  77%|███████▋  | 278/363 [00:31<00:03, 27.03it/s]
Loading 0:  78%|███████▊  | 283/363 [00:31<00:02, 29.08it/s]
Loading 0:  79%|███████▉  | 287/363 [00:31<00:02, 26.38it/s]
Loading 0:  80%|███████▉  | 290/363 [00:31<00:02, 26.64it/s]
Loading 0:  81%|████████  | 293/363 [00:32<00:03, 19.33it/s]
Loading 0:  82%|████████▏ | 296/363 [00:32<00:03, 20.23it/s]
Loading 0:  83%|████████▎ | 301/363 [00:32<00:02, 23.95it/s]
Loading 0:  84%|████████▎ | 304/363 [00:32<00:02, 22.02it/s]
Loading 0:  85%|████████▌ | 310/363 [00:32<00:01, 27.45it/s]
Loading 0:  86%|████████▌ | 313/363 [00:32<00:02, 24.77it/s]
Loading 0:  88%|████████▊ | 319/363 [00:32<00:01, 29.83it/s]
Loading 0:  89%|████████▉ | 323/363 [00:33<00:01, 28.08it/s]
Loading 0:  90%|█████████ | 328/363 [00:33<00:01, 30.94it/s]
Loading 0:  91%|█████████▏| 332/363 [00:33<00:01, 21.05it/s]
Loading 0:  93%|█████████▎| 337/363 [00:33<00:01, 24.15it/s]
Loading 0:  94%|█████████▎| 340/363 [00:33<00:01, 22.47it/s]
Loading 0:  95%|█████████▌| 346/363 [00:34<00:00, 27.88it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:00, 26.79it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:00, 29.94it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00, 28.46it/s]
                                                            

Job chaiml-mergev8-mistral3-13321-v1-mkmlizer completed after 166.04s with status: succeeded
Stopping job with name chaiml-mergev8-mistral3-13321-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.55s
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 chaiml-mergev8-mistral3-13321-v1
Waiting for inference service chaiml-mergev8-mistral3-13321-v1 to be ready
Inference service chaiml-mergev8-mistral3-13321-v1 ready after 100.36144018173218s
Pipeline stage MKMLDeployer completed in 100.88s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9952127933502197s
Received healthy response to inference request in 2.5315449237823486s
Received healthy response to inference request in 3.0805704593658447s
Received healthy response to inference request in 2.699092388153076s
Received healthy response to inference request in 2.6075143814086914s
5 requests
0 failed requests
5th percentile: 2.5467388153076174
10th percentile: 2.5619327068328857
20th percentile: 2.5923204898834227
30th percentile: 2.625829982757568
40th percentile: 2.662461185455322
50th percentile: 2.699092388153076
60th percentile: 2.8175405502319335
70th percentile: 2.935988712310791
80th percentile: 3.0122843265533445
90th percentile: 3.0464273929595946
95th percentile: 3.06349892616272
99th percentile: 3.0771561527252196
mean time: 2.782786989212036
Pipeline stage StressChecker completed in 15.25s
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 0.67s
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 0.65s
Shutdown handler de-registered
chaiml-mergev8-mistral3_13321_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 2861.32s
Shutdown handler de-registered
chaiml-mergev8-mistral3_13321_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-mergev8-mistral3_13321_v1 status is now torndown due to DeploymentManager action