arlineka-pharaoh-8b

submission_id: arlineka-pharaoh-8b_v3

developer_uid: asmog

alignment_samples: 10180

alignment_score: -0.9697447813123057

best_of: 16

celo_rating: 1234.84

display_name: arlineka-pharaoh-8b_v1

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\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\\User'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: False

language_model: arlineka/pharaoh-8b

latencies: [{'batch_size': 1, 'throughput': 0.9077301130216947, 'latency_mean': 1.101589745283127, 'latency_p50': 1.109457015991211, 'latency_p90': 1.2362771034240723}, {'batch_size': 4, 'throughput': 1.801573919416302, 'latency_mean': 2.204148496389389, 'latency_p50': 2.205120325088501, 'latency_p90': 2.451312446594238}, {'batch_size': 5, 'throughput': 1.8795678795872788, 'latency_mean': 2.64313752412796, 'latency_p50': 2.647327184677124, 'latency_p90': 2.9330997228622437}, {'batch_size': 8, 'throughput': 2.0158860299687946, 'latency_mean': 3.93712696313858, 'latency_p50': 3.9446202516555786, 'latency_p90': 4.421113848686218}, {'batch_size': 10, 'throughput': 2.04820359023675, 'latency_mean': 4.8293046581745145, 'latency_p50': 4.792124271392822, 'latency_p90': 5.562740063667297}, {'batch_size': 12, 'throughput': 2.0240751647073125, 'latency_mean': 5.846352944374084, 'latency_p50': 5.875734329223633, 'latency_p90': 6.8320306777954105}, {'batch_size': 15, 'throughput': 2.025325012976665, 'latency_mean': 7.2589801561832425, 'latency_p50': 7.350839257240295, 'latency_p90': 8.081198263168336}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: arlineka/pharaoh-8b

model_name: arlineka-pharaoh-8b_v1

model_num_parameters: 8030277632.0

model_repo: arlineka/pharaoh-8b

model_size: 8B

num_battles: 10180

num_wins: 4952

propriety_score: 0.752411575562701

propriety_total_count: 933.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 2.01

timestamp: 2024-09-12T13:38:54+00:00

us_pacific_date: 2024-09-12

win_ratio: 0.4864440078585462

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 arlineka-pharaoh-8b-v3-mkmlizer
Waiting for job on arlineka-pharaoh-8b-v3-mkmlizer to finish
arlineka-pharaoh-8b-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
arlineka-pharaoh-8b-v3-mkmlizer: ║     _____            __           __                                ║
arlineka-pharaoh-8b-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
arlineka-pharaoh-8b-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
arlineka-pharaoh-8b-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
arlineka-pharaoh-8b-v3-mkmlizer: ║       /___/                                                         ║
arlineka-pharaoh-8b-v3-mkmlizer: ║                                                                     ║
arlineka-pharaoh-8b-v3-mkmlizer: ║  Version: 0.10.1                                                    ║
arlineka-pharaoh-8b-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
arlineka-pharaoh-8b-v3-mkmlizer: ║  https://mk1.ai                                                     ║
arlineka-pharaoh-8b-v3-mkmlizer: ║                                                                     ║
arlineka-pharaoh-8b-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
arlineka-pharaoh-8b-v3-mkmlizer: ║  belonging to:                                                      ║
arlineka-pharaoh-8b-v3-mkmlizer: ║                                                                     ║
arlineka-pharaoh-8b-v3-mkmlizer: ║  Chai Research Corp.                                                ║
arlineka-pharaoh-8b-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
arlineka-pharaoh-8b-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
arlineka-pharaoh-8b-v3-mkmlizer: ║                                                                     ║
arlineka-pharaoh-8b-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
arlineka-pharaoh-8b-v3-mkmlizer: Downloaded to shared memory in 36.027s
arlineka-pharaoh-8b-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv51y6gl9, device:0
arlineka-pharaoh-8b-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
arlineka-pharaoh-8b-v3-mkmlizer: quantized model in 25.690s
arlineka-pharaoh-8b-v3-mkmlizer: Processed model arlineka/pharaoh-8b in 61.717s
arlineka-pharaoh-8b-v3-mkmlizer: creating bucket guanaco-mkml-models
arlineka-pharaoh-8b-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
arlineka-pharaoh-8b-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/arlineka-pharaoh-8b-v3
arlineka-pharaoh-8b-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/arlineka-pharaoh-8b-v3/config.json
arlineka-pharaoh-8b-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/arlineka-pharaoh-8b-v3/special_tokens_map.json
arlineka-pharaoh-8b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/arlineka-pharaoh-8b-v3/tokenizer_config.json
arlineka-pharaoh-8b-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/arlineka-pharaoh-8b-v3/tokenizer.json
arlineka-pharaoh-8b-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/arlineka-pharaoh-8b-v3/flywheel_model.0.safetensors
arlineka-pharaoh-8b-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:09, 30.76it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 51.67it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 49.15it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:05, 51.24it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:05, 47.09it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:05, 49.94it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:04, 57.02it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:04, 49.69it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:04, 49.83it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:04, 47.75it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:04, 53.09it/s]
Loading 0:  28%|██▊       | 82/291 [00:01<00:04, 49.71it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:05, 35.68it/s]
Loading 0:  33%|███▎      | 95/291 [00:02<00:05, 37.08it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 45.00it/s]
Loading 0:  37%|███▋      | 109/291 [00:02<00:04, 45.14it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:03, 46.76it/s]
Loading 0:  42%|████▏     | 122/291 [00:02<00:03, 45.06it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 52.12it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 48.52it/s]
Loading 0:  49%|████▉     | 142/291 [00:03<00:03, 47.86it/s]
Loading 0:  51%|█████     | 147/291 [00:03<00:03, 47.84it/s]
Loading 0:  52%|█████▏    | 152/291 [00:03<00:02, 48.31it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 47.99it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 46.97it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 45.63it/s]
Loading 0:  59%|█████▉    | 173/291 [00:03<00:02, 45.69it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:02, 48.19it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:02, 45.86it/s]
Loading 0:  65%|██████▍   | 189/291 [00:04<00:03, 29.21it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:03, 31.60it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 38.76it/s]
Loading 0:  71%|███████   | 207/291 [00:04<00:01, 43.37it/s]
Loading 0:  73%|███████▎  | 212/291 [00:04<00:01, 40.82it/s]
Loading 0:  76%|███████▌  | 221/291 [00:04<00:01, 45.86it/s]
Loading 0:  79%|███████▉  | 230/291 [00:05<00:01, 49.30it/s]
Loading 0:  82%|████████▏ | 239/291 [00:05<00:01, 50.69it/s]
Loading 0:  85%|████████▍ | 246/291 [00:05<00:00, 54.51it/s]
Loading 0:  87%|████████▋ | 252/291 [00:05<00:00, 54.08it/s]
Loading 0:  89%|████████▊ | 258/291 [00:05<00:00, 45.50it/s]
Loading 0:  91%|█████████ | 264/291 [00:05<00:00, 48.13it/s]
Loading 0:  93%|█████████▎| 270/291 [00:05<00:00, 50.27it/s]
Loading 0:  95%|█████████▍| 276/291 [00:05<00:00, 45.49it/s]
Loading 0:  97%|█████████▋| 282/291 [00:06<00:00, 41.34it/s]
Loading 0:  99%|█████████▊| 287/291 [00:11<00:01,  3.50it/s]
                                                            
Job arlineka-pharaoh-8b-v3-mkmlizer completed after 84.12s with status: succeeded
Stopping job with name arlineka-pharaoh-8b-v3-mkmlizer
Pipeline stage MKMLizer completed in 85.14s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service arlineka-pharaoh-8b-v3
Waiting for inference service arlineka-pharaoh-8b-v3 to be ready
Inference service arlineka-pharaoh-8b-v3 ready after 170.48110461235046s
Pipeline stage MKMLDeployer completed in 170.86s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2365658283233643s
Received healthy response to inference request in 1.7131381034851074s
Received healthy response to inference request in 1.6105475425720215s
Received healthy response to inference request in 1.5888736248016357s
Received healthy response to inference request in 4.075412273406982s
5 requests
0 failed requests
5th percentile: 1.593208408355713
10th percentile: 1.59754319190979
20th percentile: 1.6062127590179442
30th percentile: 1.6310656547546387
40th percentile: 1.672101879119873
50th percentile: 1.7131381034851074
60th percentile: 1.9225091934204102
70th percentile: 2.131880283355713
80th percentile: 2.604335117340088
90th percentile: 3.3398736953735355
95th percentile: 3.7076429843902585
99th percentile: 4.001858415603637
mean time: 2.2449074745178224
Pipeline stage StressChecker completed in 11.91s
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 6.56s
Shutdown handler de-registered
arlineka-pharaoh-8b_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 0.12s
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 arlineka-pharaoh-8b-v3-profiler
Waiting for inference service arlineka-pharaoh-8b-v3-profiler to be ready
Inference service arlineka-pharaoh-8b-v3-profiler ready after 170.42809009552002s
Pipeline stage MKMLProfilerDeployer completed in 170.81s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/arlineka-pharaoh-8b-v3-profiler-predictor-00001-deploymentrmhr4:/code/chaiverse_profiler_1726148832 --namespace tenant-chaiml-guanaco
kubectl exec -it arlineka-pharaoh-8b-v3-profiler-predictor-00001-deploymentrmhr4 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726148832 && 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_1726148832/summary.json'
kubectl exec -it arlineka-pharaoh-8b-v3-profiler-predictor-00001-deploymentrmhr4 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726148832/summary.json'
Pipeline stage MKMLProfilerRunner completed in 838.70s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service arlineka-pharaoh-8b-v3-profiler is running
Tearing down inference service arlineka-pharaoh-8b-v3-profiler
Service arlineka-pharaoh-8b-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.39s
Shutdown handler de-registered
arlineka-pharaoh-8b_v3 status is now inactive due to auto deactivation removed underperforming models