trace2333-fd5w-dl1w-ultr_3048

developer_uid: Trace2333

submission_id: trace2333-fd5w-dl1w-ultr_3048_v1

model_name: trace2333-fd5w-dl1w-ultr_3048_v1

model_group: Trace2333/fd5w_dl1w_ultr

status: torndown

timestamp: 2024-09-05T10:23:05+00:00

num_battles: 13576

num_wins: 6594

celo_rating: 1225.51

family_friendly_score: 0.0

submission_type: basic

model_repo: Trace2333/fd5w_dl1w_ultra1w_2e5_8634s

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.90061796520311, 'latency_mean': 1.1102522206306458, 'latency_p50': 1.1096233129501343, 'latency_p90': 1.2324220418930054}, {'batch_size': 4, 'throughput': 1.7677748771460746, 'latency_mean': 2.2533728349208832, 'latency_p50': 2.245567798614502, 'latency_p90': 2.5095536708831787}, {'batch_size': 5, 'throughput': 1.8398478762254806, 'latency_mean': 2.7004631006717683, 'latency_p50': 2.7111963033676147, 'latency_p90': 3.0101707935333253}, {'batch_size': 8, 'throughput': 1.9530232310269036, 'latency_mean': 4.069871044158935, 'latency_p50': 4.1131685972213745, 'latency_p90': 4.546026396751404}, {'batch_size': 10, 'throughput': 1.9990415495454539, 'latency_mean': 4.955320119857788, 'latency_p50': 4.924360275268555, 'latency_p90': 5.715341210365295}, {'batch_size': 12, 'throughput': 2.0036486692662274, 'latency_mean': 5.906400769948959, 'latency_p50': 5.893176078796387, 'latency_p90': 6.895991086959839}, {'batch_size': 15, 'throughput': 2.002782309536183, 'latency_mean': 7.337203202247619, 'latency_p50': 7.3961135149002075, 'latency_p90': 8.084950852394105}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: trace2333-fd5w-dl1w-ultr_3048_v1

is_internal_developer: False

language_model: Trace2333/fd5w_dl1w_ultra1w_2e5_8634s

model_size: 8B

ranking_group: single

throughput_3p7s: 1.94

us_pacific_date: 2024-09-05

win_ratio: 0.4857100766057749

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

formatter: {'memory_template': "<|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\nYou: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\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 trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer
Waiting for job on trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer to finish
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: ║     _____            __           __                                ║
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: ║       /___/                                                         ║
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: ║                                                                     ║
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: ║  https://mk1.ai                                                     ║
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: ║                                                                     ║
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: ║  belonging to:                                                      ║
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: ║                                                                     ║
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: ║  Chai Research Corp.                                                ║
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: ║                                                                     ║
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: Downloaded to shared memory in 66.830s
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpeavnfjsa, device:0
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: quantized model in 28.494s
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: Processed model Trace2333/fd5w_dl1w_ultra1w_2e5_8634s in 95.324s
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-fd5w-dl1w-ultr-3048-v1
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-fd5w-dl1w-ultr-3048-v1/config.json
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-fd5w-dl1w-ultr-3048-v1/special_tokens_map.json
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-fd5w-dl1w-ultr-3048-v1/tokenizer_config.json
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-fd5w-dl1w-ultr-3048-v1/tokenizer.json
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-fd5w-dl1w-ultr-3048-v1/flywheel_model.0.safetensors
trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:11, 25.38it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 35.95it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 32.82it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 36.32it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 33.26it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:06, 37.63it/s]
Loading 0:  12%|█▏        | 34/291 [00:01<00:11, 22.89it/s]
Loading 0:  13%|█▎        | 38/291 [00:01<00:10, 24.81it/s]
Loading 0:  14%|█▍        | 42/291 [00:01<00:10, 24.66it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:08, 29.52it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:08, 29.43it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:07, 32.50it/s]
Loading 0:  21%|██        | 61/291 [00:02<00:07, 32.04it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 35.88it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 34.91it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 34.92it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 34.18it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 24.65it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 25.56it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 30.51it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:06, 30.67it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 35.02it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 34.11it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:04, 37.55it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:04, 36.12it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:04, 36.67it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 40.84it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 38.54it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:04, 33.52it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:04, 32.35it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 29.97it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 35.27it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 34.24it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 37.27it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 36.04it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 39.06it/s]
Loading 0:  58%|█████▊    | 170/291 [00:05<00:03, 38.69it/s]
Loading 0:  60%|██████    | 175/291 [00:05<00:03, 38.61it/s]
Loading 0:  62%|██████▏   | 180/291 [00:05<00:02, 41.08it/s]
Loading 0:  64%|██████▎   | 185/291 [00:05<00:02, 41.01it/s]
Loading 0:  65%|██████▌   | 190/291 [00:05<00:03, 27.17it/s]
Loading 0:  67%|██████▋   | 194/291 [00:05<00:03, 26.38it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 33.88it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 33.37it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 36.58it/s]
Loading 0:  74%|███████▍  | 215/291 [00:06<00:02, 37.03it/s]
Loading 0:  76%|███████▌  | 220/291 [00:06<00:01, 37.34it/s]
Loading 0:  77%|███████▋  | 224/291 [00:06<00:01, 37.69it/s]
Loading 0:  78%|███████▊  | 228/291 [00:06<00:02, 29.99it/s]
Loading 0:  80%|████████  | 233/291 [00:07<00:02, 26.89it/s]
Loading 0:  82%|████████▏ | 238/291 [00:07<00:01, 31.37it/s]
Loading 0:  83%|████████▎ | 242/291 [00:07<00:01, 32.42it/s]
Loading 0:  85%|████████▍ | 247/291 [00:07<00:01, 34.17it/s]
Loading 0:  86%|████████▋ | 251/291 [00:07<00:01, 35.46it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:00, 36.14it/s]
Loading 0:  89%|████████▉ | 259/291 [00:07<00:00, 34.36it/s]
Loading 0:  91%|█████████ | 264/291 [00:07<00:00, 37.57it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 35.92it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 38.76it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 36.15it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 35.16it/s]
Loading 0:  98%|█████████▊| 286/291 [00:13<00:01,  2.61it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.24it/s]
                                                            
Job trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer completed after 117.61s with status: succeeded
Stopping job with name trace2333-fd5w-dl1w-ultr-3048-v1-mkmlizer
Pipeline stage MKMLizer completed in 119.34s
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 trace2333-fd5w-dl1w-ultr-3048-v1
Waiting for inference service trace2333-fd5w-dl1w-ultr-3048-v1 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service trace2333-fd5w-dl1w-ultr-3048-v1 ready after 140.55272793769836s
Pipeline stage MKMLDeployer completed in 141.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.472937822341919s
Received healthy response to inference request in 2.204774856567383s
Received healthy response to inference request in 1.9540507793426514s
Received healthy response to inference request in 1.8702647686004639s
Received healthy response to inference request in 1.5341053009033203s
5 requests
0 failed requests
5th percentile: 1.601337194442749
10th percentile: 1.6685690879821777
20th percentile: 1.8030328750610352
30th percentile: 1.8870219707489013
40th percentile: 1.9205363750457765
50th percentile: 1.9540507793426514
60th percentile: 2.0543404102325438
70th percentile: 2.1546300411224366
80th percentile: 2.25840744972229
90th percentile: 2.3656726360321043
95th percentile: 2.4193052291870116
99th percentile: 2.4622113037109377
mean time: 2.0072267055511475
Pipeline stage StressChecker completed in 11.04s
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 7.50s
Shutdown handler de-registered
trace2333-fd5w-dl1w-ultr_3048_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service trace2333-fd5w-dl1w-ultr-3048-v1-profiler
Waiting for inference service trace2333-fd5w-dl1w-ultr-3048-v1-profiler to be ready
Inference service trace2333-fd5w-dl1w-ultr-3048-v1-profiler ready after 150.36554598808289s
Pipeline stage MKMLProfilerDeployer completed in 151.02s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/trace2333-fd5w-dl1w-a95c80962144c0f3ed4660856d498a25-deploqvdrw:/code/chaiverse_profiler_1725532260 --namespace tenant-chaiml-guanaco
kubectl exec -it trace2333-fd5w-dl1w-a95c80962144c0f3ed4660856d498a25-deploqvdrw --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725532260 && python profiles.py profile --best_of_n 16 --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_1725532260/summary.json'
kubectl exec -it trace2333-fd5w-dl1w-a95c80962144c0f3ed4660856d498a25-deploqvdrw --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725532260/summary.json'
Pipeline stage MKMLProfilerRunner completed in 852.48s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service trace2333-fd5w-dl1w-ultr-3048-v1-profiler is running
Tearing down inference service trace2333-fd5w-dl1w-ultr-3048-v1-profiler
Service trace2333-fd5w-dl1w-ultr-3048-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.56s
Shutdown handler de-registered
trace2333-fd5w-dl1w-ultr_3048_v1 status is now inactive due to auto deactivation removed underperforming models
trace2333-fd5w-dl1w-ultr_3048_v1 status is now torndown due to DeploymentManager action