chaiml-snugstable1-5-12b_5927

developer_uid: zonemercy

submission_id: chaiml-snugstable1-5-12b_5927_v2

model_name: tempv1-5

model_group: ChaiML/SnugStable1.5-12b

status: torndown

timestamp: 2024-12-27T14:45:11+00:00

num_battles: 14673

num_wins: 8161

celo_rating: 1300.42

family_friendly_score: 0.5953999999999999

family_friendly_standard_error: 0.006941164743758788

submission_type: basic

model_repo: ChaiML/SnugStable1.5-12b0-l1e5r7

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': 0.6383244800563443, 'latency_mean': 1.5665075087547302, 'latency_p50': 1.5572431087493896, 'latency_p90': 1.7266204595565795}, {'batch_size': 3, 'throughput': 1.2548160978681788, 'latency_mean': 2.3812147331237794, 'latency_p50': 2.3844566345214844, 'latency_p90': 2.6171414613723756}, {'batch_size': 5, 'throughput': 1.5907432341404248, 'latency_mean': 3.12553294301033, 'latency_p50': 3.1441017389297485, 'latency_p90': 3.542444610595703}, {'batch_size': 6, 'throughput': 1.7107962633443883, 'latency_mean': 3.4850790536403657, 'latency_p50': 3.461613178253174, 'latency_p90': 3.9263114452362062}, {'batch_size': 8, 'throughput': 1.8529764744289237, 'latency_mean': 4.292458738088608, 'latency_p50': 4.255595922470093, 'latency_p90': 4.8624390125274655}, {'batch_size': 10, 'throughput': 1.9369522482822858, 'latency_mean': 5.115090042352676, 'latency_p50': 5.1261667013168335, 'latency_p90': 5.770760703086853}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: tempv1-5

is_internal_developer: True

language_model: ChaiML/SnugStable1.5-12b0-l1e5r7

model_size: 13B

ranking_group: single

throughput_3p7s: 1.77

us_pacific_date: 2024-12-27

win_ratio: 0.5561916445171403

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 4, '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-snugstable1-5-12b-5927-v2-mkmlizer
Waiting for job on chaiml-snugstable1-5-12b-5927-v2-mkmlizer to finish
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: ║       /___/                                                         ║
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: ║                                                                     ║
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: ║                                                                     ║
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: ║                                                                     ║
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: ║                                                                     ║
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: Downloaded to shared memory in 52.732s
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9rj1l92y, device:0
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: quantized model in 36.480s
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: Processed model ChaiML/SnugStable1.5-12b0-l1e5r7 in 89.212s
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-snugstable1-5-12b-5927-v2
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12b-5927-v2/config.json
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12b-5927-v2/special_tokens_map.json
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12b-5927-v2/tokenizer_config.json
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-snugstable1-5-12b-5927-v2/tokenizer.json
chaiml-snugstable1-5-12b-5927-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.88it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.85it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.16it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.84it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 49.84it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.51it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.58it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 49.27it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 47.68it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 34.92it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 35.11it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 38.88it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:07, 40.83it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:07, 35.18it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 43.62it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 43.51it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 40.54it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 42.36it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 46.16it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 44.41it/s]
Loading 0:  34%|███▍      | 123/363 [00:02<00:05, 43.42it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:05, 42.79it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:04, 47.42it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:04, 45.39it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 27.31it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.28it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 37.39it/s]
Loading 0:  45%|████▍     | 163/363 [00:04<00:05, 37.67it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:05, 38.24it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 43.97it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 44.25it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 43.68it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 48.07it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 46.05it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 45.12it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 50.14it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 47.56it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 35.24it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 35.37it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:03, 35.19it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 39.83it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 39.91it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 40.84it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 45.68it/s]
Loading 0:  72%|███████▏  | 261/363 [00:06<00:02, 46.25it/s]
Loading 0:  73%|███████▎  | 266/363 [00:06<00:02, 40.10it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:01, 46.43it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:01, 43.10it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 41.59it/s]
Loading 0:  79%|███████▉  | 288/363 [00:06<00:01, 41.85it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:02, 33.96it/s]
Loading 0:  83%|████████▎ | 300/363 [00:07<00:01, 41.64it/s]
Loading 0:  84%|████████▍ | 305/363 [00:14<00:22,  2.54it/s]
Loading 0:  85%|████████▌ | 309/363 [00:14<00:16,  3.25it/s]
Loading 0:  86%|████████▌ | 313/363 [00:14<00:11,  4.20it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.57it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  9.08it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 11.46it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.09it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:01, 19.56it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 21.33it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 28.96it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 32.11it/s]
                                                            
Job chaiml-snugstable1-5-12b-5927-v2-mkmlizer completed after 115.08s with status: succeeded
Stopping job with name chaiml-snugstable1-5-12b-5927-v2-mkmlizer
Pipeline stage MKMLizer completed in 115.65s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-snugstable1-5-12b-5927-v2
Waiting for inference service chaiml-snugstable1-5-12b-5927-v2 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-snugstable1-5-12b-5927-v2 ready after 281.0962941646576s
Pipeline stage MKMLDeployer completed in 281.65s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.261134386062622s
Received healthy response to inference request in 1.3743574619293213s
Received healthy response to inference request in 1.5156428813934326s
Received healthy response to inference request in 1.6669788360595703s
Received healthy response to inference request in 1.354379415512085s
5 requests
0 failed requests
5th percentile: 1.3583750247955322
10th percentile: 1.3623706340789794
20th percentile: 1.370361852645874
30th percentile: 1.4026145458221435
40th percentile: 1.4591287136077882
50th percentile: 1.5156428813934326
60th percentile: 1.5761772632598876
70th percentile: 1.6367116451263428
80th percentile: 1.7858099460601808
90th percentile: 2.0234721660614015
95th percentile: 2.1423032760620115
99th percentile: 2.2373681640625
mean time: 1.6344985961914062
Pipeline stage StressChecker completed in 10.00s
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 0.82s
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-snugstable1-5-12b_5927_v2 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-snugstable1-5-12b-5927-v2-profiler
Waiting for inference service chaiml-snugstable1-5-12b-5927-v2-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 2526.07s
Shutdown handler de-registered
chaiml-snugstable1-5-12b_5927_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-snugstable1-5-12b_5927_v2 status is now torndown due to DeploymentManager action
chaiml-snugstable1-5-12b_5927_v2 status is now torndown due to DeploymentManager action
chaiml-snugstable1-5-12b_5927_v2 status is now torndown due to DeploymentManager action