developer_uid: NischayDnk
submission_id: chaiml-exp51-grok-sft-a_20059_v2
model_name: chaiml-exp51-grok-sft-a_20059_v2
model_group: ChaiML/exp51-grok-sft-al
status: torndown
timestamp: 2025-03-08T10:10:27+00:00
num_battles: 8605
num_wins: 4289
celo_rating: 1278.0
family_friendly_score: 0.5548
family_friendly_standard_error: 0.007028470103799261
submission_type: basic
model_repo: ChaiML/exp51-grok-sft-allsamples-try-swloss
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': 0.3669006132662279, 'latency_mean': 2.725445193052292, 'latency_p50': 2.729580521583557, 'latency_p90': 2.988932251930237}, {'batch_size': 2, 'throughput': 0.5728907954416316, 'latency_mean': 3.4882213819026946, 'latency_p50': 3.4654523134231567, 'latency_p90': 3.830431866645813}, {'batch_size': 3, 'throughput': 0.7281363492213457, 'latency_mean': 4.111305185556412, 'latency_p50': 4.101014494895935, 'latency_p90': 4.553005242347717}, {'batch_size': 4, 'throughput': 0.841368752819774, 'latency_mean': 4.7250248503684995, 'latency_p50': 4.699243783950806, 'latency_p90': 5.390859627723694}, {'batch_size': 5, 'throughput': 0.9367521102645004, 'latency_mean': 5.315631853342056, 'latency_p50': 5.314342260360718, 'latency_p90': 5.945250153541565}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-exp51-grok-sft-a_20059_v2
is_internal_developer: False
language_model: ChaiML/exp51-grok-sft-allsamples-try-swloss
model_size: 24B
ranking_group: single
throughput_3p7s: 0.63
us_pacific_date: 2025-03-08
win_ratio: 0.49843114468332367
generation_params: {'temperature': 0.6, 'top_p': 0.9, 'min_p': 0.2, 'top_k': 80, 'presence_penalty': 0.4, 'frequency_penalty': 0.45, '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{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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 chaiml-exp51-grok-sft-a-20059-v2-mkmlizer
Waiting for job on chaiml-exp51-grok-sft-a-20059-v2-mkmlizer to finish
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: ║       /___/                                                         ║
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: ║                                                                     ║
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: ║                                                                     ║
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: ║                                                                     ║
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: ║                                                                     ║
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: Downloaded to shared memory in 63.526s
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpuc7esog2, device:0
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: quantized model in 52.842s
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: Processed model ChaiML/exp51-grok-sft-allsamples-try-swloss in 116.368s
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp51-grok-sft-a-20059-v2
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp51-grok-sft-a-20059-v2/config.json
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp51-grok-sft-a-20059-v2/special_tokens_map.json
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp51-grok-sft-a-20059-v2/tokenizer_config.json
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp51-grok-sft-a-20059-v2/tokenizer.json
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp51-grok-sft-a-20059-v2/flywheel_model.0.safetensors
chaiml-exp51-grok-sft-a-20059-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.79it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 30.43it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 31.39it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 28.45it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 33.19it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 29.67it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 35.93it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.68it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 24.37it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.92it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 28.46it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.85it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 31.37it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 29.70it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 30.48it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 27.43it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:12, 22.89it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 28.32it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 28.69it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:11, 24.71it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:10, 27.05it/s]
Loading 0:  26%|██▌       | 94/363 [00:03<00:10, 26.39it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 29.44it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 28.29it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:10, 23.72it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 26.54it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 26.19it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.43it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 25.74it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.40it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.40it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:07, 31.04it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.91it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:06, 35.45it/s]
Loading 0:  42%|████▏     | 152/363 [00:05<00:08, 24.26it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:08, 23.44it/s]
Loading 0:  44%|████▍     | 159/363 [00:05<00:09, 22.34it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:07, 27.46it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 26.82it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.34it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.07it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.87it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 26.30it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:07, 24.10it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:06, 24.94it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 25.58it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 25.58it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:59,  1.11s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:28,  1.08it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:29,  1.74it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:08,  2.21it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.91it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.16it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.30it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.40it/s]
Loading 0:  63%|██████▎   | 229/363 [00:22<00:14,  9.40it/s]
Loading 0:  64%|██████▍   | 232/363 [00:22<00:11, 11.12it/s]
Loading 0:  65%|██████▌   | 237/363 [00:22<00:08, 15.26it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 16.44it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 22.11it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:04, 23.28it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 26.93it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:03, 26.80it/s]
Loading 0:  73%|███████▎  | 266/363 [00:23<00:02, 32.40it/s]
Loading 0:  74%|███████▍  | 270/363 [00:24<00:04, 22.11it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 24.57it/s]
Loading 0:  77%|███████▋  | 278/363 [00:24<00:03, 25.89it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:02, 27.66it/s]
Loading 0:  79%|███████▉  | 286/363 [00:24<00:02, 27.33it/s]
Loading 0:  80%|████████  | 291/363 [00:24<00:02, 30.19it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 28.55it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 28.31it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 26.22it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.53it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 24.24it/s]
Loading 0:  86%|████████▌ | 313/363 [00:25<00:02, 24.32it/s]
Loading 0:  88%|████████▊ | 318/363 [00:25<00:01, 27.81it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 25.84it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 31.29it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 29.71it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 29.52it/s]
Loading 0:  93%|█████████▎| 338/363 [00:26<00:00, 27.49it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:13,  1.68it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:05,  2.80it/s]
Loading 0:  96%|█████████▋| 350/363 [00:33<00:03,  3.51it/s]
Loading 0:  98%|█████████▊| 355/363 [00:33<00:01,  5.22it/s]
Loading 0:  99%|█████████▉| 359/363 [00:33<00:00,  6.79it/s]
                                                            

Job chaiml-exp51-grok-sft-a-20059-v2-mkmlizer completed after 144.95s with status: succeeded
Stopping job with name chaiml-exp51-grok-sft-a-20059-v2-mkmlizer
Pipeline stage MKMLizer completed in 145.43s
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-exp51-grok-sft-a-20059-v2
Waiting for inference service chaiml-exp51-grok-sft-a-20059-v2 to be ready
Inference service chaiml-exp51-grok-sft-a-20059-v2 ready after 90.53713536262512s
Pipeline stage MKMLDeployer completed in 90.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.457688808441162s
Received healthy response to inference request in 2.5408878326416016s
Received healthy response to inference request in 2.7817347049713135s
Received healthy response to inference request in 2.9892349243164062s
Received healthy response to inference request in 2.6129214763641357s
5 requests
0 failed requests
5th percentile: 2.555294561386108
10th percentile: 2.5697012901306153
20th percentile: 2.598514747619629
30th percentile: 2.6466841220855715
40th percentile: 2.7142094135284425
50th percentile: 2.7817347049713135
60th percentile: 2.8647347927093505
70th percentile: 2.9477348804473875
80th percentile: 3.0829257011413573
90th percentile: 3.27030725479126
95th percentile: 3.363998031616211
99th percentile: 3.438950653076172
mean time: 2.876493549346924
Pipeline stage StressChecker completed in 15.52s
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 0.66s
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 0.63s
Shutdown handler de-registered
chaiml-exp51-grok-sft-a_20059_v2 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5272.43s
Shutdown handler de-registered
chaiml-exp51-grok-sft-a_20059_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp51-grok-sft-a_20059_v2 status is now torndown due to DeploymentManager action