chaiml-zl-az-405b-mini3_25127

developer_uid: zonemercy

submission_id: chaiml-zl-az-405b-mini3_25127_v1

model_name: chaiml-zl-az-405b-mini3_25127_v1

model_group: ChaiML/ZL-AZ-405b-mini3-

status: torndown

timestamp: 2025-01-03T23:47:19+00:00

num_battles: 11215

num_wins: 5018

celo_rating: 1218.76

family_friendly_score: 0.6002000000000001

family_friendly_standard_error: 0.006927625278549642

submission_type: basic

model_repo: ChaiML/ZL-AZ-405b-mini3-test-model

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6391911646172229, 'latency_mean': 1.5643791937828064, 'latency_p50': 1.562483549118042, 'latency_p90': 1.7233760118484496}, {'batch_size': 3, 'throughput': 1.2785066485963024, 'latency_mean': 2.3383206582069396, 'latency_p50': 2.3155970573425293, 'latency_p90': 2.5664023399353026}, {'batch_size': 5, 'throughput': 1.6114503312700426, 'latency_mean': 3.0832793700695036, 'latency_p50': 3.096466302871704, 'latency_p90': 3.452096128463745}, {'batch_size': 6, 'throughput': 1.7270209856237262, 'latency_mean': 3.4529026687145232, 'latency_p50': 3.446130156517029, 'latency_p90': 3.9433961629867555}, {'batch_size': 8, 'throughput': 1.8690622915894817, 'latency_mean': 4.2461454045772555, 'latency_p50': 4.24702262878418, 'latency_p90': 4.811437606811523}, {'batch_size': 10, 'throughput': 1.9652979542054057, 'latency_mean': 5.051381140947342, 'latency_p50': 5.041402220726013, 'latency_p90': 5.786190533638}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-zl-az-405b-mini3_25127_v1

is_internal_developer: True

language_model: ChaiML/ZL-AZ-405b-mini3-test-model

model_size: 13B

ranking_group: single

throughput_3p7s: 1.79

us_pacific_date: 2025-01-03

win_ratio: 0.44743646901471246

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', 'Bot:', 'You:', '<|im_end|>', '</s>', '<|eot_id|>', 'User:', '####'], 'max_input_tokens': 1024, 'best_of': 4, '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 chaiml-zl-az-405b-mini3-25127-v1-mkmlizer
Waiting for job on chaiml-zl-az-405b-mini3-25127-v1-mkmlizer to finish
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: ║       /___/                                                         ║
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: ║                                                                     ║
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: ║                                                                     ║
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: ║                                                                     ║
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: ║                                                                     ║
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: Downloaded to shared memory in 42.182s
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpl6wxtaqc, device:0
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: quantized model in 37.438s
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: Processed model ChaiML/ZL-AZ-405b-mini3-test-model in 79.620s
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-zl-az-405b-mini3-25127-v1
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-zl-az-405b-mini3-25127-v1/config.json
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-zl-az-405b-mini3-25127-v1/special_tokens_map.json
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-zl-az-405b-mini3-25127-v1/tokenizer_config.json
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-zl-az-405b-mini3-25127-v1/tokenizer.json
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-zl-az-405b-mini3-25127-v1/flywheel_model.0.safetensors
chaiml-zl-az-405b-mini3-25127-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.09it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 44.49it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 45.13it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 33.64it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 42.72it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 42.98it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 43.14it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:07, 41.79it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:07, 40.78it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 42.73it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.40it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 31.79it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 37.48it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 38.88it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:06, 41.07it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 42.51it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 35.39it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 42.68it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 42.49it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 46.49it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 38.61it/s]
Loading 0:  33%|███▎      | 119/363 [00:03<00:06, 37.70it/s]
Loading 0:  35%|███▍      | 126/363 [00:03<00:05, 43.13it/s]
Loading 0:  36%|███▌      | 131/363 [00:03<00:05, 44.14it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:06, 37.31it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 32.05it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 32.24it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 30.99it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 36.15it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 35.27it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 39.51it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 41.36it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 34.84it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 41.66it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 40.62it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 40.00it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 41.63it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 35.65it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 44.07it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 44.72it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:03, 43.02it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 31.37it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 31.28it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:03, 38.00it/s]
Loading 0:  67%|██████▋   | 243/363 [00:06<00:02, 40.15it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 35.73it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 42.77it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 43.23it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 43.70it/s]
Loading 0:  75%|███████▍  | 271/363 [00:07<00:03, 30.35it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 29.82it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:02, 37.43it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 38.77it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 40.60it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 42.44it/s]
Loading 0:  83%|████████▎ | 303/363 [00:07<00:01, 41.74it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:23,  2.39it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:16,  3.07it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:09,  4.80it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:06,  6.05it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:03,  8.61it/s]
Loading 0:  92%|█████████▏| 335/363 [00:15<00:02, 11.51it/s]
Loading 0:  94%|█████████▎| 340/363 [00:15<00:01, 14.25it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 18.90it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 22.46it/s]
Loading 0:  98%|█████████▊| 356/363 [00:16<00:00, 26.63it/s]
Loading 0: 100%|█████████▉| 362/363 [00:16<00:00, 30.17it/s]
                                                            
Job chaiml-zl-az-405b-mini3-25127-v1-mkmlizer completed after 114.52s with status: succeeded
Stopping job with name chaiml-zl-az-405b-mini3-25127-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.00s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-zl-az-405b-mini3-25127-v1
Waiting for inference service chaiml-zl-az-405b-mini3-25127-v1 to be ready
Inference service chaiml-zl-az-405b-mini3-25127-v1 ready after 321.88848400115967s
Pipeline stage MKMLDeployer completed in 322.43s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 0.9973421096801758s
Received healthy response to inference request in 1.15620756149292s
Received healthy response to inference request in 0.8032634258270264s
Received healthy response to inference request in 0.9440603256225586s
Received healthy response to inference request in 0.7563519477844238s
5 requests
0 failed requests
5th percentile: 0.7657342433929444
10th percentile: 0.7751165390014648
20th percentile: 0.7938811302185058
30th percentile: 0.8314228057861328
40th percentile: 0.8877415657043457
50th percentile: 0.9440603256225586
60th percentile: 0.9653730392456055
70th percentile: 0.9866857528686523
80th percentile: 1.0291152000427246
90th percentile: 1.0926613807678223
95th percentile: 1.124434471130371
99th percentile: 1.1498529434204101
mean time: 0.9314450740814209
Pipeline stage StressChecker completed in 6.05s
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 1.12s
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 0.66s
Shutdown handler de-registered
chaiml-zl-az-405b-mini3_25127_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-zl-az-405b-mini3-25127-v1-profiler
Waiting for inference service chaiml-zl-az-405b-mini3-25127-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 2361.40s
Shutdown handler de-registered
chaiml-zl-az-405b-mini3_25127_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-zl-az-405b-mini3_25127_v1 status is now torndown due to DeploymentManager action
chaiml-zl-az-405b-mini3_25127_v1 status is now torndown due to DeploymentManager action
chaiml-zl-az-405b-mini3_25127_v1 status is now torndown due to DeploymentManager action