developer_uid: zonemercy
submission_id: chaiml-snugstable1-5-12_76771_v6
model_name: tempv1-2
model_group: ChaiML/SnugStable1.5-12b
status: torndown
timestamp: 2025-01-07T06:46:08+00:00
num_battles: 9446
num_wins: 4981
celo_rating: 1290.83
family_friendly_score: 0.5918
family_friendly_standard_error: 0.0069508669962818305
submission_type: basic
model_repo: ChaiML/SnugStable1.5-12b0-l1e5r7b4
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.651696204162076, 'latency_mean': 1.5343848741054535, 'latency_p50': 1.5466077327728271, 'latency_p90': 1.6936486959457397}, {'batch_size': 3, 'throughput': 1.262779990140372, 'latency_mean': 2.369581505060196, 'latency_p50': 2.3786706924438477, 'latency_p90': 2.5804402589797975}, {'batch_size': 5, 'throughput': 1.580381074679809, 'latency_mean': 3.156797775030136, 'latency_p50': 3.193356513977051, 'latency_p90': 3.533029270172119}, {'batch_size': 6, 'throughput': 1.67615224882017, 'latency_mean': 3.558007400035858, 'latency_p50': 3.537913680076599, 'latency_p90': 3.9781224489212037}, {'batch_size': 8, 'throughput': 1.7653508666014457, 'latency_mean': 4.4948158514499665, 'latency_p50': 4.457051515579224, 'latency_p90': 5.102606081962586}, {'batch_size': 10, 'throughput': 1.8120409472563221, 'latency_mean': 5.465846135616302, 'latency_p50': 5.50941526889801, 'latency_p90': 6.123502039909363}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tempv1-2
is_internal_developer: True
language_model: ChaiML/SnugStable1.5-12b0-l1e5r7b4
model_size: 13B
ranking_group: single
throughput_3p7s: 1.7
us_pacific_date: 2025-01-06
win_ratio: 0.5273131484226128
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['User:', '\n', 'Bot:', '<|eot_id|>', 'You:', '####', '</s>', '<|im_end|>'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
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-snugstable1-5-12-76771-v6-mkmlizer
Waiting for job on chaiml-snugstable1-5-12-76771-v6-mkmlizer to finish
chaiml-snugstable1-5-12-76771-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-snugstable1-5-12-76771-v6-mkmlizer: ║     _____            __           __                                ║
chaiml-snugstable1-5-12-76771-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-snugstable1-5-12-76771-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-snugstable1-5-12-76771-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-snugstable1-5-12-76771-v6-mkmlizer: ║       /___/                                                         ║
chaiml-snugstable1-5-12-76771-v6-mkmlizer: ║                                                                     ║
chaiml-snugstable1-5-12-76771-v6-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-snugstable1-5-12-76771-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-snugstable1-5-12-76771-v6-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-snugstable1-5-12-76771-v6-mkmlizer: ║                                                                     ║
chaiml-snugstable1-5-12-76771-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-snugstable1-5-12-76771-v6-mkmlizer: ║  belonging to:                                                      ║
chaiml-snugstable1-5-12-76771-v6-mkmlizer: ║                                                                     ║
chaiml-snugstable1-5-12-76771-v6-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-snugstable1-5-12-76771-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-snugstable1-5-12-76771-v6-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-snugstable1-5-12-76771-v6-mkmlizer: ║                                                                     ║
chaiml-snugstable1-5-12-76771-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-snugstable1-5-12-76771-v6-mkmlizer: Downloaded to shared memory in 48.212s
chaiml-snugstable1-5-12-76771-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphi1n9uhn, device:0
chaiml-snugstable1-5-12-76771-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-snugstable1-5-12-76771-v6-mkmlizer: quantized model in 37.749s
chaiml-snugstable1-5-12-76771-v6-mkmlizer: Processed model ChaiML/SnugStable1.5-12b0-l1e5r7b4 in 85.962s
chaiml-snugstable1-5-12-76771-v6-mkmlizer: creating bucket guanaco-mkml-models
chaiml-snugstable1-5-12-76771-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-snugstable1-5-12-76771-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-snugstable1-5-12-76771-v6
chaiml-snugstable1-5-12-76771-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-76771-v6/config.json
chaiml-snugstable1-5-12-76771-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-76771-v6/special_tokens_map.json
chaiml-snugstable1-5-12-76771-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-76771-v6/tokenizer_config.json
chaiml-snugstable1-5-12-76771-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12-76771-v6/tokenizer.json
chaiml-snugstable1-5-12-76771-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-snugstable1-5-12-76771-v6/flywheel_model.0.safetensors
chaiml-snugstable1-5-12-76771-v6-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.79it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 45.67it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 48.25it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 39.18it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 44.55it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 43.58it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 43.51it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 44.97it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 36.49it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 41.29it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.13it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 30.23it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 35.17it/s]
Loading 0:  21%|██        | 75/363 [00:01<00:08, 35.03it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:07, 37.93it/s]
Loading 0:  23%|██▎       | 85/363 [00:02<00:07, 38.56it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 39.82it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:06, 41.42it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:08, 31.63it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:07, 35.46it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:06, 38.48it/s]
Loading 0:  32%|███▏      | 115/363 [00:03<00:06, 38.41it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:06, 37.19it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 39.92it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 40.03it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 40.15it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 42.44it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 26.51it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 26.98it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 34.72it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 35.32it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 36.24it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:05, 34.25it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:05, 36.25it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:05, 36.20it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 36.61it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:04, 35.78it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 38.61it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:04, 36.61it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 38.84it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:04, 37.04it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 39.59it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 39.48it/s]
Loading 0:  60%|██████    | 219/363 [00:05<00:03, 38.71it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:05, 25.31it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 27.31it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 27.27it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 33.90it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 34.01it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 37.24it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 36.63it/s]
Loading 0:  70%|███████   | 255/363 [00:07<00:02, 38.18it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 36.63it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 38.11it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:02, 34.83it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 36.47it/s]
Loading 0:  76%|███████▋  | 277/363 [00:07<00:02, 35.17it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:02, 37.76it/s]
Loading 0:  79%|███████▉  | 286/363 [00:07<00:02, 36.15it/s]
Loading 0:  80%|████████  | 291/363 [00:08<00:01, 37.98it/s]
Loading 0:  81%|████████▏ | 295/363 [00:08<00:01, 36.48it/s]
Loading 0:  82%|████████▏ | 299/363 [00:08<00:01, 35.88it/s]
Loading 0:  84%|████████▎ | 304/363 [00:15<00:28,  2.10it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:21,  2.63it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:13,  3.88it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:06,  6.30it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:05,  7.93it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:03, 10.68it/s]
Loading 0:  92%|█████████▏| 333/363 [00:15<00:02, 13.85it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 17.34it/s]
Loading 0:  94%|█████████▍| 343/363 [00:16<00:00, 21.02it/s]
Loading 0:  96%|█████████▌| 348/363 [00:16<00:00, 21.82it/s]
Loading 0:  98%|█████████▊| 355/363 [00:16<00:00, 29.01it/s]
Loading 0:  99%|█████████▉| 360/363 [00:16<00:00, 31.04it/s]
                                                            

Job chaiml-snugstable1-5-12-76771-v6-mkmlizer completed after 114.02s with status: succeeded
Stopping job with name chaiml-snugstable1-5-12-76771-v6-mkmlizer
Pipeline stage MKMLizer completed in 114.49s
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-snugstable1-5-12-76771-v6
Waiting for inference service chaiml-snugstable1-5-12-76771-v6 to be ready
Inference service chaiml-snugstable1-5-12-76771-v6 ready after 361.4594144821167s
Pipeline stage MKMLDeployer completed in 362.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5632493495941162s
Received healthy response to inference request in 1.5383374691009521s
Received healthy response to inference request in 1.4573910236358643s
Received healthy response to inference request in 1.7080724239349365s
Received healthy response to inference request in 1.6055519580841064s
5 requests
0 failed requests
5th percentile: 1.4735803127288818
10th percentile: 1.4897696018218993
20th percentile: 1.5221481800079346
30th percentile: 1.5433198451995849
40th percentile: 1.5532845973968505
50th percentile: 1.5632493495941162
60th percentile: 1.5801703929901123
70th percentile: 1.5970914363861084
80th percentile: 1.6260560512542725
90th percentile: 1.6670642375946045
95th percentile: 1.6875683307647704
99th percentile: 1.7039716053009033
mean time: 1.5745204448699952
Pipeline stage StressChecker completed in 9.15s
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 0.65s
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 0.95s
Shutdown handler de-registered
chaiml-snugstable1-5-12_76771_v6 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 2541.63s
Shutdown handler de-registered
chaiml-snugstable1-5-12_76771_v6 status is now inactive due to auto deactivation removed underperforming models
chaiml-snugstable1-5-12_76771_v6 status is now torndown due to DeploymentManager action
chaiml-snugstable1-5-12_76771_v6 status is now torndown due to DeploymentManager action
chaiml-snugstable1-5-12_76771_v6 status is now torndown due to DeploymentManager action