chaiml-lexens-v1-12b01e5r256

developer_uid: zonemercy

submission_id: chaiml-lexens-v1-12b01e5r256_v3

model_name: tempv1-3

model_group: ChaiML/LexEns-v1-12b01e5

status: inactive

timestamp: 2024-12-10T21:02:33+00:00

num_battles: 15284

num_wins: 7750

celo_rating: 1265.28

family_friendly_score: 0.5998

family_friendly_standard_error: 0.006928779979188255

submission_type: basic

model_repo: ChaiML/LexEns-v1-12b01e5r256

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6287368795316703, 'latency_mean': 1.590431444644928, 'latency_p50': 1.5944733619689941, 'latency_p90': 1.7509978771209718}, {'batch_size': 3, 'throughput': 1.2463094594074213, 'latency_mean': 2.399755175113678, 'latency_p50': 2.381433844566345, 'latency_p90': 2.6604752063751222}, {'batch_size': 5, 'throughput': 1.5614466745900806, 'latency_mean': 3.1812485575675966, 'latency_p50': 3.174760937690735, 'latency_p90': 3.569120979309082}, {'batch_size': 6, 'throughput': 1.6623260273415135, 'latency_mean': 3.585470761060715, 'latency_p50': 3.561691164970398, 'latency_p90': 4.088355922698975}, {'batch_size': 8, 'throughput': 1.8142022265585847, 'latency_mean': 4.379802289009095, 'latency_p50': 4.348205804824829, 'latency_p90': 4.905016446113587}, {'batch_size': 10, 'throughput': 1.9046684622383228, 'latency_mean': 5.202455670833587, 'latency_p50': 5.197505593299866, 'latency_p90': 5.930703854560852}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: tempv1-3

is_internal_developer: True

language_model: ChaiML/LexEns-v1-12b01e5r256

model_size: 13B

ranking_group: single

throughput_3p7s: 1.7

us_pacific_date: 2024-12-10

win_ratio: 0.5070662130332374

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', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], '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-lexens-v1-12b01e5r256-v3-mkmlizer
Waiting for job on chaiml-lexens-v1-12b01e5r256-v3-mkmlizer to finish
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: ║       /___/                                                         ║
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: ║                                                                     ║
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: ║                                                                     ║
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: ║                                                                     ║
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: ║                                                                     ║
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: Downloaded to shared memory in 34.594s
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4ti9br4o, device:0
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: quantized model in 38.556s
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: Processed model ChaiML/LexEns-v1-12b01e5r256 in 73.149s
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-lexens-v1-12b01e5r256-v3
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-lexens-v1-12b01e5r256-v3/config.json
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-lexens-v1-12b01e5r256-v3/special_tokens_map.json
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-lexens-v1-12b01e5r256-v3/tokenizer_config.json
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-lexens-v1-12b01e5r256-v3/tokenizer.json
chaiml-lexens-v1-12b01e5r256-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:14, 24.16it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 41.26it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 39.88it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 40.19it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:08, 41.41it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 33.30it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:07, 41.16it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:07, 40.04it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 40.25it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:07, 41.58it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:07, 42.70it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:12, 23.71it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 30.65it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 32.46it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:08, 34.67it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 36.55it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 31.58it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:07, 37.24it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:07, 37.08it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:06, 39.12it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:07, 33.52it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 33.44it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 39.64it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 40.18it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 40.82it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 42.95it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:08, 26.30it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 26.50it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 34.11it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 34.88it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 36.80it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 38.45it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:05, 32.60it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 39.24it/s]
Loading 0:  52%|█████▏    | 188/363 [00:05<00:04, 38.91it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:04, 40.10it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:04, 41.08it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 34.15it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 42.33it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 42.79it/s]
Loading 0:  61%|██████    | 221/363 [00:06<00:03, 43.37it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:05, 25.81it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:05, 25.78it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 33.31it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 34.64it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 35.37it/s]
Loading 0:  69%|██████▉   | 251/363 [00:07<00:03, 35.37it/s]
Loading 0:  70%|███████   | 255/363 [00:07<00:03, 35.68it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:03, 34.19it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 36.24it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:02, 34.45it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 35.88it/s]
Loading 0:  76%|███████▋  | 277/363 [00:07<00:02, 33.93it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:02, 36.36it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 34.67it/s]
Loading 0:  80%|████████  | 291/363 [00:08<00:01, 37.11it/s]
Loading 0:  81%|████████▏ | 295/363 [00:08<00:01, 36.35it/s]
Loading 0:  82%|████████▏ | 299/363 [00:08<00:01, 37.05it/s]
Loading 0:  84%|████████▎ | 304/363 [00:15<00:28,  2.07it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:21,  2.59it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:13,  3.82it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:07,  6.20it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:05,  7.77it/s]
Loading 0:  90%|█████████ | 328/363 [00:16<00:03, 10.41it/s]
Loading 0:  91%|█████████▏| 332/363 [00:16<00:02, 12.54it/s]
Loading 0:  93%|█████████▎| 337/363 [00:16<00:01, 16.13it/s]
Loading 0:  94%|█████████▍| 341/363 [00:16<00:01, 18.57it/s]
Loading 0:  95%|█████████▌| 346/363 [00:16<00:00, 23.24it/s]
Loading 0:  97%|█████████▋| 351/363 [00:16<00:00, 26.64it/s]
Loading 0:  98%|█████████▊| 356/363 [00:16<00:00, 29.80it/s]
Loading 0:  99%|█████████▉| 360/363 [00:16<00:00, 31.36it/s]
                                                            
Job chaiml-lexens-v1-12b01e5r256-v3-mkmlizer completed after 104.06s with status: succeeded
Stopping job with name chaiml-lexens-v1-12b01e5r256-v3-mkmlizer
Pipeline stage MKMLizer completed in 104.59s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.64s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-lexens-v1-12b01e5r256-v3
Waiting for inference service chaiml-lexens-v1-12b01e5r256-v3 to be ready
Retrying (%r) after connection broken by '%r': %s
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
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
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
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-lexens-v1-12b01e5r256-v3 ready after 190.92431688308716s
Pipeline stage MKMLDeployer completed in 191.45s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.344974994659424s
Received healthy response to inference request in 1.4862425327301025s
Received healthy response to inference request in 1.6274101734161377s
Received healthy response to inference request in 1.8441412448883057s
Received healthy response to inference request in 1.3966057300567627s
5 requests
0 failed requests
5th percentile: 1.4145330905914306
10th percentile: 1.4324604511260985
20th percentile: 1.4683151721954346
30th percentile: 1.5144760608673096
40th percentile: 1.5709431171417236
50th percentile: 1.6274101734161377
60th percentile: 1.714102602005005
70th percentile: 1.800795030593872
80th percentile: 1.9443079948425295
90th percentile: 2.1446414947509767
95th percentile: 2.2448082447052
99th percentile: 2.324941644668579
mean time: 1.7398749351501466
Pipeline stage StressChecker completed in 10.05s
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 2.38s
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 2.42s
Shutdown handler de-registered
chaiml-lexens-v1-12b01e5r256_v3 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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-lexens-v1-12b01e5r256-v3-profiler
Waiting for inference service chaiml-lexens-v1-12b01e5r256-v3-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 2464.48s
Shutdown handler de-registered
chaiml-lexens-v1-12b01e5r256_v3 status is now inactive due to auto deactivation removed underperforming models