sao10k-mn-12b-lyra-v4a2

developer_uid: sao10k

submission_id: sao10k-mn-12b-lyra-v4a2_v2

model_name: lyra42

model_group: Sao10K/MN-12B-Lyra-v4a2

status: torndown

timestamp: 2024-09-05T15:48:36+00:00

num_battles: 12916

num_wins: 6646

celo_rating: 1252.73

family_friendly_score: 0.0

submission_type: basic

model_repo: Sao10K/MN-12B-Lyra-v4a2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6931583957433309, 'latency_mean': 1.4425806164741517, 'latency_p50': 1.4478161334991455, 'latency_p90': 1.6106695652008056}, {'batch_size': 3, 'throughput': 1.3301829037012305, 'latency_mean': 2.2461686968803405, 'latency_p50': 2.2347004413604736, 'latency_p90': 2.4729973554611204}, {'batch_size': 5, 'throughput': 1.5460484391630611, 'latency_mean': 3.2193285620212553, 'latency_p50': 3.2115466594696045, 'latency_p90': 3.577026700973511}, {'batch_size': 6, 'throughput': 1.5949272243991637, 'latency_mean': 3.7409205842018127, 'latency_p50': 3.7782459259033203, 'latency_p90': 4.1931809186935425}, {'batch_size': 8, 'throughput': 1.5753753077472992, 'latency_mean': 5.032341006994248, 'latency_p50': 5.061548233032227, 'latency_p90': 5.679836654663085}, {'batch_size': 10, 'throughput': 1.5196526280952847, 'latency_mean': 6.528875786066055, 'latency_p50': 6.580205917358398, 'latency_p90': 7.362384676933289}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: lyra42

is_internal_developer: False

language_model: Sao10K/MN-12B-Lyra-v4a2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.6

us_pacific_date: 2024-09-05

win_ratio: 0.5145555899659338

generation_params: {'temperature': 0.75, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\n\n', '\nYou:', '[/INST]', '<|im_end|>', '</s>'], 'max_input_tokens': 512, '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 sao10k-mn-12b-lyra-v4a2-v2-mkmlizer
Waiting for job on sao10k-mn-12b-lyra-v4a2-v2-mkmlizer to finish
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: ║     _____            __           __                                ║
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: ║       /___/                                                         ║
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: ║  belonging to:                                                      ║
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: ║                                                                     ║
sao10k-mn-12b-lyra-v4a2-v2-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
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: Downloaded to shared memory in 41.043s
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpaejl8_i0, device:0
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: creating bucket guanaco-mkml-models
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a2-v2
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a2-v2/config.json
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a2-v2/special_tokens_map.json
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a2-v2/tokenizer_config.json
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a2-v2/tokenizer.json
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-mn-12b-lyra-v4a2-v2/flywheel_model.0.safetensors
sao10k-mn-12b-lyra-v4a2-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:05,  3.01s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:48,  1.24it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:06,  2.77it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:20,  4.33it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:42,  8.06it/s]
Loading 0:   7%|▋         | 27/363 [00:06<00:30, 11.03it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:22, 14.48it/s]
Loading 0:  10%|█         | 37/363 [00:06<00:17, 18.39it/s]
Loading 0:  12%|█▏        | 42/363 [00:07<00:15, 20.18it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:11, 27.63it/s]
Loading 0:  15%|█▍        | 54/363 [00:07<00:10, 30.63it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:12, 23.39it/s]
Loading 0:  17%|█▋        | 63/363 [00:07<00:11, 25.86it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:10, 29.33it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:09, 31.17it/s]
Loading 0:  21%|██▏       | 78/363 [00:08<00:08, 32.45it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:06, 41.51it/s]
Loading 0:  25%|██▌       | 91/363 [00:08<00:06, 42.75it/s]
Loading 0:  26%|██▋       | 96/363 [00:08<00:07, 35.60it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:06, 42.28it/s]
Loading 0:  30%|██▉       | 108/363 [00:08<00:06, 40.74it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:06, 40.85it/s]
Loading 0:  33%|███▎      | 118/363 [00:09<00:05, 42.63it/s]
Loading 0:  34%|███▍      | 123/363 [00:09<00:06, 35.85it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:05, 41.67it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:05, 41.81it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:05, 41.79it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:05, 42.18it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:05, 36.21it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:07, 29.36it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:06, 30.88it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:05, 35.37it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:04, 38.33it/s]
Loading 0:  49%|████▉     | 177/363 [00:10<00:05, 33.01it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:04, 38.89it/s]
Loading 0:  52%|█████▏    | 189/363 [00:10<00:04, 39.12it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:04, 40.04it/s]
Loading 0:  55%|█████▌    | 200/363 [00:11<00:04, 39.40it/s]
Loading 0:  56%|█████▋    | 205/363 [00:11<00:04, 38.70it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:03, 42.29it/s]
Loading 0:  60%|█████▉    | 216/363 [00:11<00:03, 42.60it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 43.63it/s]
Loading 0:  63%|██████▎   | 227/363 [00:11<00:03, 41.82it/s]
Loading 0:  64%|██████▍   | 232/363 [00:12<00:03, 40.43it/s]
Loading 0:  66%|██████▌   | 238/363 [00:12<00:02, 45.08it/s]
Loading 0:  67%|██████▋   | 243/363 [00:12<00:02, 43.50it/s]
Loading 0:  68%|██████▊   | 248/363 [00:12<00:02, 42.13it/s]
Loading 0:  70%|██████▉   | 253/363 [00:12<00:02, 43.93it/s]
Loading 0:  71%|███████   | 258/363 [00:12<00:03, 26.77it/s]
Loading 0:  73%|███████▎  | 265/363 [00:12<00:02, 34.21it/s]
Loading 0:  74%|███████▍  | 270/363 [00:13<00:02, 35.58it/s]
Loading 0:  76%|███████▌  | 275/363 [00:13<00:02, 36.83it/s]
Loading 0:  77%|███████▋  | 280/363 [00:13<00:02, 38.91it/s]
Loading 0:  79%|███████▊  | 285/363 [00:13<00:02, 33.36it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:01, 40.22it/s]
Loading 0:  82%|████████▏ | 297/363 [00:13<00:01, 40.54it/s]
Loading 0:  83%|████████▎ | 302/363 [00:13<00:01, 40.05it/s]
Loading 0:  85%|████████▍ | 307/363 [00:13<00:01, 40.97it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:01, 34.46it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:01, 40.45it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:00, 40.88it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:00, 42.16it/s]
Loading 0:  92%|█████████▏| 335/363 [00:14<00:00, 41.53it/s]
Loading 0:  94%|█████████▎| 340/363 [00:14<00:00, 40.66it/s]
Loading 0:  95%|█████████▌| 346/363 [00:14<00:00, 45.24it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 44.90it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 29.55it/s]
Loading 0:  99%|█████████▉| 360/363 [00:15<00:00, 31.52it/s]
                                                            
Job sao10k-mn-12b-lyra-v4a2-v2-mkmlizer completed after 105.29s with status: succeeded
Stopping job with name sao10k-mn-12b-lyra-v4a2-v2-mkmlizer
Pipeline stage MKMLizer completed in 106.26s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sao10k-mn-12b-lyra-v4a2-v2
Waiting for inference service sao10k-mn-12b-lyra-v4a2-v2 to be ready
Inference service sao10k-mn-12b-lyra-v4a2-v2 ready after 140.87452864646912s
Pipeline stage MKMLDeployer completed in 141.35s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6207804679870605s
Received healthy response to inference request in 2.3969430923461914s
Received healthy response to inference request in 1.8947579860687256s
Received healthy response to inference request in 1.7093946933746338s
Received healthy response to inference request in 2.3990700244903564s
5 requests
0 failed requests
5th percentile: 1.7464673519134521
10th percentile: 1.7835400104522705
20th percentile: 1.8576853275299072
30th percentile: 1.9951950073242188
40th percentile: 2.196069049835205
50th percentile: 2.3969430923461914
60th percentile: 2.3977938652038575
70th percentile: 2.3986446380615236
80th percentile: 2.443412113189697
90th percentile: 2.532096290588379
95th percentile: 2.57643837928772
99th percentile: 2.6119120502471924
mean time: 2.2041892528533937
Pipeline stage StressChecker completed in 12.37s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.16s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a2_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sao10k-mn-12b-lyra-v4a2-v2-profiler
Waiting for inference service sao10k-mn-12b-lyra-v4a2-v2-profiler to be ready
Inference service sao10k-mn-12b-lyra-v4a2-v2-profiler ready after 150.4279429912567s
Pipeline stage MKMLProfilerDeployer completed in 150.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sao10k-mn-12b-lyra-v4a2-v2-profiler-predictor-00001-deployl6vzb:/code/chaiverse_profiler_1725551774 --namespace tenant-chaiml-guanaco
kubectl exec -it sao10k-mn-12b-lyra-v4a2-v2-profiler-predictor-00001-deployl6vzb --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725551774 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 64 --summary /code/chaiverse_profiler_1725551774/summary.json'
kubectl exec -it sao10k-mn-12b-lyra-v4a2-v2-profiler-predictor-00001-deployl6vzb --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725551774/summary.json'
Pipeline stage MKMLProfilerRunner completed in 958.27s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sao10k-mn-12b-lyra-v4a2-v2-profiler is running
Tearing down inference service sao10k-mn-12b-lyra-v4a2-v2-profiler
Service sao10k-mn-12b-lyra-v4a2-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.02s
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a2_v2 status is now inactive due to auto deactivation removed underperforming models
Running pipeline stage MKMLDeleter
run pipeline stage %s
admin requested tearing down of sao10k-mn-12b-lyra-v4a2_v2
Running pipeline stage MKMLDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
%s, retrying in %s seconds...
run pipeline stage %s
%s, retrying in %s seconds...
Running pipeline stage MKMLDeleter
clean up pipeline due to error=TeardownError("module 'kubernetes.config' has no attribute 'load_kube_config'")
%s, retrying in %s seconds...
Shutdown handler de-registered
clean up pipeline due to error=TeardownError("module 'kubernetes.config' has no attribute 'load_kube_config'")
Shutdown handler de-registered
sao10k-mn-12b-lyra-v4a2_v2 status is now torndown due to DeploymentManager action