sicarius-prototyping-com_3807

developer_uid: SicariusSicariiStuff

submission_id: sicarius-prototyping-com_3807_v2

model_name: sicarius-prototyping-com_3807_v2

model_group: Sicarius-Prototyping/Com

status: torndown

timestamp: 2024-09-18T18:15:12+00:00

num_battles: 10414

num_wins: 4758

celo_rating: 1216.3

family_friendly_score: 0.0

submission_type: basic

model_repo: Sicarius-Prototyping/Compliance_PreAlpha_Roleplay

model_architecture: LlamaForCausalLM

model_num_parameters: 8030277632.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.8714281174776437, 'latency_mean': 1.1474821472167969, 'latency_p50': 1.1533602476119995, 'latency_p90': 1.2550143718719482}, {'batch_size': 4, 'throughput': 1.860727795990501, 'latency_mean': 2.1433835101127623, 'latency_p50': 2.1507142782211304, 'latency_p90': 2.3809799671173097}, {'batch_size': 5, 'throughput': 1.9860896672011452, 'latency_mean': 2.503343263864517, 'latency_p50': 2.5073959827423096, 'latency_p90': 2.8163687944412232}, {'batch_size': 8, 'throughput': 2.1611815861960197, 'latency_mean': 3.671372069120407, 'latency_p50': 3.670240044593811, 'latency_p90': 4.117341804504394}, {'batch_size': 10, 'throughput': 2.1911842508673764, 'latency_mean': 4.525566720962525, 'latency_p50': 4.4994529485702515, 'latency_p90': 5.1293100118637085}, {'batch_size': 12, 'throughput': 2.2261703244831095, 'latency_mean': 5.351224395036698, 'latency_p50': 5.395782709121704, 'latency_p90': 6.037756824493408}, {'batch_size': 15, 'throughput': 2.190011927624934, 'latency_mean': 6.770259716510773, 'latency_p50': 6.763471007347107, 'latency_p90': 7.654078531265259}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: sicarius-prototyping-com_3807_v2

is_internal_developer: False

language_model: Sicarius-Prototyping/Compliance_PreAlpha_Roleplay

model_size: 8B

ranking_group: single

throughput_3p7s: 2.18

us_pacific_date: 2024-09-18

win_ratio: 0.4568849625504129

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': 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 sicarius-prototyping-com-3807-v2-mkmlizer
Waiting for job on sicarius-prototyping-com-3807-v2-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
sicarius-prototyping-com-3807-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sicarius-prototyping-com-3807-v2-mkmlizer: ║     _____            __           __                                ║
sicarius-prototyping-com-3807-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sicarius-prototyping-com-3807-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sicarius-prototyping-com-3807-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sicarius-prototyping-com-3807-v2-mkmlizer: ║       /___/                                                         ║
sicarius-prototyping-com-3807-v2-mkmlizer: ║                                                                     ║
sicarius-prototyping-com-3807-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
sicarius-prototyping-com-3807-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sicarius-prototyping-com-3807-v2-mkmlizer: ║  https://mk1.ai                                                     ║
sicarius-prototyping-com-3807-v2-mkmlizer: ║                                                                     ║
sicarius-prototyping-com-3807-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
sicarius-prototyping-com-3807-v2-mkmlizer: ║  belonging to:                                                      ║
sicarius-prototyping-com-3807-v2-mkmlizer: ║                                                                     ║
sicarius-prototyping-com-3807-v2-mkmlizer: ║  Chai Research Corp.                                                ║
sicarius-prototyping-com-3807-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sicarius-prototyping-com-3807-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sicarius-prototyping-com-3807-v2-mkmlizer: ║                                                                     ║
sicarius-prototyping-com-3807-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
sicarius-prototyping-com-3807-v2-mkmlizer: Downloaded to shared memory in 40.556s
sicarius-prototyping-com-3807-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8rdgrq2e, device:0
sicarius-prototyping-com-3807-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sicarius-prototyping-com-3807-v2-mkmlizer: quantized model in 25.978s
sicarius-prototyping-com-3807-v2-mkmlizer: Processed model Sicarius-Prototyping/Compliance_PreAlpha_Roleplay in 66.535s
sicarius-prototyping-com-3807-v2-mkmlizer: creating bucket guanaco-mkml-models
sicarius-prototyping-com-3807-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sicarius-prototyping-com-3807-v2/config.json
sicarius-prototyping-com-3807-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sicarius-prototyping-com-3807-v2/special_tokens_map.json
sicarius-prototyping-com-3807-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sicarius-prototyping-com-3807-v2/tokenizer_config.json
sicarius-prototyping-com-3807-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sicarius-prototyping-com-3807-v2/tokenizer.json
sicarius-prototyping-com-3807-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sicarius-prototyping-com-3807-v2/flywheel_model.0.safetensors
sicarius-prototyping-com-3807-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 32.35it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:06, 44.45it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:04, 54.60it/s]
Loading 0:  10%|▉         | 28/291 [00:00<00:05, 50.10it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:04, 52.06it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:04, 53.31it/s]
Loading 0:  16%|█▌        | 46/291 [00:00<00:05, 46.69it/s]
Loading 0:  18%|█▊        | 51/291 [00:01<00:05, 45.55it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:04, 51.26it/s]
Loading 0:  22%|██▏       | 64/291 [00:01<00:04, 48.86it/s]
Loading 0:  24%|██▍       | 70/291 [00:01<00:04, 50.67it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:04, 52.13it/s]
Loading 0:  28%|██▊       | 82/291 [00:01<00:04, 48.72it/s]
Loading 0:  30%|██▉       | 87/291 [00:01<00:06, 33.67it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:04, 40.67it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 40.81it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 40.59it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 46.08it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 43.48it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:03, 43.80it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 49.45it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 47.52it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:03, 47.41it/s]
Loading 0:  51%|█████     | 147/291 [00:03<00:02, 50.66it/s]
Loading 0:  53%|█████▎    | 153/291 [00:03<00:02, 50.81it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:02, 44.48it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 49.99it/s]
Loading 0:  59%|█████▉    | 172/291 [00:03<00:02, 46.21it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:02, 50.42it/s]
Loading 0:  64%|██████▎   | 185/291 [00:03<00:02, 52.19it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 35.72it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 37.46it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 41.29it/s]
Loading 0:  71%|███████   | 207/291 [00:04<00:01, 42.60it/s]
Loading 0:  73%|███████▎  | 212/291 [00:04<00:02, 37.64it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 47.13it/s]
Loading 0:  78%|███████▊  | 226/291 [00:04<00:01, 45.25it/s]
Loading 0:  79%|███████▉  | 231/291 [00:05<00:01, 44.62it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 50.68it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:00, 48.42it/s]
Loading 0:  86%|████████▌ | 250/291 [00:05<00:00, 49.91it/s]
Loading 0:  88%|████████▊ | 257/291 [00:05<00:00, 46.46it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 53.42it/s]
Loading 0:  93%|█████████▎| 271/291 [00:05<00:00, 49.43it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 50.59it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 46.20it/s]
Loading 0:  99%|█████████▉| 288/291 [00:11<00:00,  3.45it/s]
                                                            
Job sicarius-prototyping-com-3807-v2-mkmlizer completed after 84.37s with status: succeeded
Stopping job with name sicarius-prototyping-com-3807-v2-mkmlizer
Pipeline stage MKMLizer completed in 85.18s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.07s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sicarius-prototyping-com-3807-v2
Waiting for inference service sicarius-prototyping-com-3807-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
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
Failed to get response for submission chaiml-lexical-nemo-v4-1k1e5_v3: ('http://chaiml-lexical-nemo-v4-1k1e5-v3-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:49018->127.0.0.1:8080: read: connection reset by peer\n')
Inference service sicarius-prototyping-com-3807-v2 ready after 190.70218062400818s
Pipeline stage MKMLDeployer completed in 191.65s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1434829235076904s
Received healthy response to inference request in 1.3982491493225098s
Received healthy response to inference request in 1.7974865436553955s
Received healthy response to inference request in 1.6167805194854736s
Received healthy response to inference request in 1.295428991317749s
5 requests
0 failed requests
5th percentile: 1.3159930229187011
10th percentile: 1.3365570545196532
20th percentile: 1.3776851177215577
30th percentile: 1.4419554233551026
40th percentile: 1.5293679714202881
50th percentile: 1.6167805194854736
60th percentile: 1.6890629291534425
70th percentile: 1.761345338821411
80th percentile: 1.8666858196258547
90th percentile: 2.0050843715667725
95th percentile: 2.0742836475372313
99th percentile: 2.1296430683135985
mean time: 1.6502856254577636
Pipeline stage StressChecker completed in 9.00s
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 6.09s
Shutdown handler de-registered
sicarius-prototyping-com_3807_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 0.14s
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 sicarius-prototyping-com-3807-v2-profiler
Waiting for inference service sicarius-prototyping-com-3807-v2-profiler to be ready
Inference service sicarius-prototyping-com-3807-v2-profiler ready after 190.49008870124817s
Pipeline stage MKMLProfilerDeployer completed in 190.85s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sicarius--deplolct5z:/code/chaiverse_profiler_1726683848 --namespace tenant-chaiml-guanaco
kubectl exec -it sicarius--deplolct5z --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726683848 && 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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1726683848/summary.json'
kubectl exec -it sicarius--deplolct5z --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726683848/summary.json'
Pipeline stage MKMLProfilerRunner completed in 809.30s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sicarius-prototyping-com-3807-v2-profiler is running
Tearing down inference service sicarius-prototyping-com-3807-v2-profiler
Service sicarius-prototyping-com-3807-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.93s
Shutdown handler de-registered
sicarius-prototyping-com_3807_v2 status is now inactive due to auto deactivation removed underperforming models
sicarius-prototyping-com_3807_v2 status is now torndown due to DeploymentManager action