meta-llama-meta-llama-3-_5386

submission_id: meta-llama-meta-llama-3-_5386_v8

developer_uid: chai_backend_admin

best_of: 8

celo_rating: 1198.52

display_name: meta-llama-meta-llama-3-_5386_v8

family_friendly_score: 0.6102564102564103

family_friendly_standard_error: 0.010511878565784297

formatter: {'memory_template': '### Instruction:\nYou are a safe and responsible AI roleplaying as {bot_name} safe for work edition. Only output responses that are safe for work. Never engage in anything sexual with the user.\n### Input:\n', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{bot_name} [SFW Only]:', 'truncate_by_message': False}

generation_params: {'temperature': 0.8, '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}

gpu_counts: {'NVIDIA RTX A5000': 1}

ineligible_reason: num_battles<5000

is_internal_developer: True

language_model: meta-llama/Meta-Llama-3-8B-Instruct

latencies: [{'batch_size': 1, 'throughput': 0.873354804775679, 'latency_mean': 1.1449516105651856, 'latency_p50': 1.147732138633728, 'latency_p90': 1.259465742111206}, {'batch_size': 4, 'throughput': 1.8726316738011337, 'latency_mean': 2.1300150609016417, 'latency_p50': 2.134204864501953, 'latency_p90': 2.385594058036804}, {'batch_size': 5, 'throughput': 2.0189512641475855, 'latency_mean': 2.456526347398758, 'latency_p50': 2.472929358482361, 'latency_p90': 2.797389030456543}, {'batch_size': 8, 'throughput': 2.2393351597879407, 'latency_mean': 3.5429446947574617, 'latency_p50': 3.534886956214905, 'latency_p90': 3.987132120132446}, {'batch_size': 10, 'throughput': 2.2931845862407982, 'latency_mean': 4.317500025033951, 'latency_p50': 4.336858630180359, 'latency_p90': 4.854929041862488}, {'batch_size': 12, 'throughput': 2.344275095420563, 'latency_mean': 5.063626316785812, 'latency_p50': 5.047536492347717, 'latency_p90': 5.708501768112183}, {'batch_size': 15, 'throughput': 2.3461969069901376, 'latency_mean': 6.314994287490845, 'latency_p50': 6.342889666557312, 'latency_p90': 7.071140456199646}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: meta-llama/Meta-Llama-3-

model_name: meta-llama-meta-llama-3-_5386_v8

model_num_parameters: 8030261248.0

model_repo: meta-llama/Meta-Llama-3-8B-Instruct

model_size: 8B

num_battles: 3904

num_wins: 1657

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 2.27

timestamp: 2024-09-25T02:45:51+00:00

us_pacific_date: 2024-09-24

win_ratio: 0.4244364754098361

Download Preference Data

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 meta-llama-meta-llama-3-5386-v8-mkmlizer
Waiting for job on meta-llama-meta-llama-3-5386-v8-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
meta-llama-meta-llama-3-5386-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meta-llama-meta-llama-3-5386-v8-mkmlizer: ║     _____            __           __                                ║
meta-llama-meta-llama-3-5386-v8-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
meta-llama-meta-llama-3-5386-v8-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
meta-llama-meta-llama-3-5386-v8-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
meta-llama-meta-llama-3-5386-v8-mkmlizer: ║       /___/                                                         ║
meta-llama-meta-llama-3-5386-v8-mkmlizer: ║                                                                     ║
meta-llama-meta-llama-3-5386-v8-mkmlizer: ║  Version: 0.11.12                                                   ║
meta-llama-meta-llama-3-5386-v8-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
meta-llama-meta-llama-3-5386-v8-mkmlizer: ║  https://mk1.ai                                                     ║
meta-llama-meta-llama-3-5386-v8-mkmlizer: ║                                                                     ║
meta-llama-meta-llama-3-5386-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
meta-llama-meta-llama-3-5386-v8-mkmlizer: ║  belonging to:                                                      ║
meta-llama-meta-llama-3-5386-v8-mkmlizer: ║                                                                     ║
meta-llama-meta-llama-3-5386-v8-mkmlizer: ║  Chai Research Corp.                                                ║
meta-llama-meta-llama-3-5386-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
meta-llama-meta-llama-3-5386-v8-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
meta-llama-meta-llama-3-5386-v8-mkmlizer: ║                                                                     ║
meta-llama-meta-llama-3-5386-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
meta-llama-meta-llama-3-5386-v8-mkmlizer: Downloaded to shared memory in 37.894s
meta-llama-meta-llama-3-5386-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpq99o079f, device:0
meta-llama-meta-llama-3-5386-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meta-llama-meta-llama-3-5386-v8-mkmlizer: quantized model in 26.689s
meta-llama-meta-llama-3-5386-v8-mkmlizer: Processed model meta-llama/Meta-Llama-3-8B-Instruct in 64.583s
meta-llama-meta-llama-3-5386-v8-mkmlizer: creating bucket guanaco-mkml-models
Connection pool is full, discarding connection: %s. Connection pool size: %s
meta-llama-meta-llama-3-5386-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-5386-v8/config.json
meta-llama-meta-llama-3-5386-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-5386-v8/special_tokens_map.json
meta-llama-meta-llama-3-5386-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-5386-v8/tokenizer_config.json
meta-llama-meta-llama-3-5386-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-5386-v8/tokenizer.json
meta-llama-meta-llama-3-5386-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meta-llama-meta-llama-3-5386-v8/flywheel_model.0.safetensors
meta-llama-meta-llama-3-5386-v8-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 33.11it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 55.76it/s]
Loading 0:   7%|▋         | 20/291 [00:00<00:05, 53.40it/s]
Loading 0:   9%|▉         | 26/291 [00:00<00:05, 51.43it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:05, 44.43it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:04, 53.41it/s]
Loading 0:  16%|█▌        | 46/291 [00:00<00:04, 51.42it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:04, 52.33it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 48.56it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 55.74it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 52.23it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:04, 51.88it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:05, 35.04it/s]
Loading 0:  31%|███▏      | 91/291 [00:02<00:05, 36.45it/s]
Loading 0:  33%|███▎      | 96/291 [00:02<00:05, 38.28it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 44.78it/s]
Loading 0:  37%|███▋      | 109/291 [00:02<00:04, 44.76it/s]
Loading 0:  39%|███▉      | 114/291 [00:02<00:03, 44.42it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 50.05it/s]
Loading 0:  44%|████▎     | 127/291 [00:02<00:03, 48.35it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:03, 48.36it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:03, 50.02it/s]
Loading 0:  50%|████▉     | 145/291 [00:03<00:03, 46.78it/s]
Loading 0:  52%|█████▏    | 150/291 [00:03<00:03, 45.11it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 49.60it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 45.59it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 44.99it/s]
Loading 0:  59%|█████▉    | 173/291 [00:03<00:02, 46.09it/s]
Loading 0:  62%|██████▏   | 180/291 [00:03<00:02, 51.39it/s]
Loading 0:  64%|██████▍   | 186/291 [00:03<00:02, 47.39it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:03, 31.34it/s]
Loading 0:  67%|██████▋   | 195/291 [00:04<00:03, 31.57it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 38.88it/s]
Loading 0:  71%|███████▏  | 208/291 [00:04<00:02, 38.73it/s]
Loading 0:  73%|███████▎  | 213/291 [00:04<00:02, 38.02it/s]
Loading 0:  75%|███████▌  | 219/291 [00:04<00:01, 41.41it/s]
Loading 0:  77%|███████▋  | 224/291 [00:05<00:01, 40.61it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 39.81it/s]
Loading 0:  80%|████████  | 234/291 [00:05<00:01, 41.98it/s]
Loading 0:  82%|████████▏ | 239/291 [00:05<00:01, 36.81it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 45.04it/s]
Loading 0:  87%|████████▋ | 253/291 [00:05<00:00, 44.50it/s]
Loading 0:  89%|████████▊ | 258/291 [00:05<00:00, 45.10it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 50.75it/s]
Loading 0:  93%|█████████▎| 271/291 [00:06<00:00, 48.09it/s]
Loading 0:  95%|█████████▍| 276/291 [00:06<00:00, 47.38it/s]
Loading 0:  97%|█████████▋| 282/291 [00:06<00:00, 43.68it/s]
Loading 0:  99%|█████████▊| 287/291 [00:11<00:01,  3.20it/s]
                                                            
Job meta-llama-meta-llama-3-5386-v8-mkmlizer completed after 87.7s with status: succeeded
Stopping job with name meta-llama-meta-llama-3-5386-v8-mkmlizer
Pipeline stage MKMLizer completed in 88.49s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.32s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service meta-llama-meta-llama-3-5386-v8
Waiting for inference service meta-llama-meta-llama-3-5386-v8 to be ready
Failed to get response for submission blend_dimam_2024-09-20: ('http://chaiml-lexical-nemo-v4-1k1e5-v3-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:42320->127.0.0.1:8080: read: connection reset by peer\n')
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
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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service meta-llama-meta-llama-3-5386-v8 ready after 212.60378241539001s
Pipeline stage MKMLDeployer completed in 215.59s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8772118091583252s
Received healthy response to inference request in 2.4506752490997314s
Received healthy response to inference request in 1.7060201168060303s
Received healthy response to inference request in 1.7225894927978516s
Received healthy response to inference request in 3.342621326446533s
5 requests
0 failed requests
5th percentile: 1.7093339920043946
10th percentile: 1.7126478672027587
20th percentile: 1.7192756175994872
30th percentile: 1.7535139560699462
40th percentile: 1.8153628826141357
50th percentile: 1.8772118091583252
60th percentile: 2.1065971851348877
70th percentile: 2.33598256111145
80th percentile: 2.629064464569092
90th percentile: 2.9858428955078127
95th percentile: 3.1642321109771725
99th percentile: 3.306943483352661
mean time: 2.2198235988616943
Pipeline stage StressChecker completed in 13.54s
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 10.67s
Shutdown handler de-registered
meta-llama-meta-llama-3-_5386_v8 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service meta-llama-meta-llama-3-5386-v8-profiler
Waiting for inference service meta-llama-meta-llama-3-5386-v8-profiler to be ready
Inference service meta-llama-meta-llama-3-5386-v8-profiler ready after 210.48057174682617s
Pipeline stage MKMLProfilerDeployer completed in 210.90s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/meta-llama-meta-llame22570c92a03faf4cd468212a4b3df3f-deploxg5kg:/code/chaiverse_profiler_1727232936 --namespace tenant-chaiml-guanaco
kubectl exec -it meta-llama-meta-llame22570c92a03faf4cd468212a4b3df3f-deploxg5kg --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727232936 && 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_1727232936/summary.json'
kubectl exec -it meta-llama-meta-llame22570c92a03faf4cd468212a4b3df3f-deploxg5kg --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727232936/summary.json'
Pipeline stage MKMLProfilerRunner completed in 788.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service meta-llama-meta-llama-3-5386-v8-profiler is running
Tearing down inference service meta-llama-meta-llama-3-5386-v8-profiler
Service meta-llama-meta-llama-3-5386-v8-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.32s
Shutdown handler de-registered
meta-llama-meta-llama-3-_5386_v8 status is now inactive due to auto deactivation removed underperforming models
meta-llama-meta-llama-3-_5386_v8 status is now inactive due to auto deactivation removed underperforming models
run pipeline stage %s
admin requested tearing down of meta-llama-meta-llama-3-_5386_v8
Running pipeline stage MKMLDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
%s, retrying in %s seconds...
%s, retrying in %s seconds...
clean up pipeline due to error=TeardownError("module 'kubernetes.config' has no attribute 'load_kube_config'")
Shutdown handler de-registered
meta-llama-meta-llama-3-_5386_v8 status is now torndown due to DeploymentManager action