cycy233-l3-e-v0-c4

submission_id: cycy233-l3-e-v0-c4_v5

developer_uid: shiroe40

alignment_samples: 10625

alignment_score: 3.010280577287421

best_of: 8

celo_rating: 1179.56

display_name: auto

formatter: {'memory_template': "<|begin_of_text|><|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': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: False

language_model: cycy233/L3-e-v0-c4

latencies: [{'batch_size': 1, 'throughput': 0.8663907436250502, 'latency_mean': 1.1541121566295625, 'latency_p50': 1.1599769592285156, 'latency_p90': 1.2788099288940429}, {'batch_size': 4, 'throughput': 1.8629856282786228, 'latency_mean': 2.141804404258728, 'latency_p50': 2.1291595697402954, 'latency_p90': 2.368330383300781}, {'batch_size': 5, 'throughput': 2.0091297310518987, 'latency_mean': 2.469928251504898, 'latency_p50': 2.446678638458252, 'latency_p90': 2.8176519155502318}, {'batch_size': 8, 'throughput': 2.217021256835885, 'latency_mean': 3.5917831575870514, 'latency_p50': 3.5784378051757812, 'latency_p90': 4.0082594871521}, {'batch_size': 10, 'throughput': 2.2612015994324137, 'latency_mean': 4.389200258255005, 'latency_p50': 4.386540055274963, 'latency_p90': 4.966599082946777}, {'batch_size': 12, 'throughput': 2.3201553497495326, 'latency_mean': 5.129438992738724, 'latency_p50': 5.158488154411316, 'latency_p90': 5.854466533660888}, {'batch_size': 15, 'throughput': 2.30429754185752, 'latency_mean': 6.414686115980149, 'latency_p50': 6.410224080085754, 'latency_p90': 7.142131376266479}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: cycy233/L3-e-v0-c4

model_name: auto

model_num_parameters: 8030261248.0

model_repo: cycy233/L3-e-v0-c4

model_size: 8B

num_battles: 10625

num_wins: 4356

propriety_score: 0.7610062893081762

propriety_total_count: 954.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 2.24

timestamp: 2024-09-13T09:40:28+00:00

us_pacific_date: 2024-09-13

win_ratio: 0.4099764705882353

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 cycy233-l3-e-v0-c4-v5-mkmlizer
Waiting for job on cycy233-l3-e-v0-c4-v5-mkmlizer to finish
cycy233-l3-e-v0-c4-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-e-v0-c4-v5-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-e-v0-c4-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-e-v0-c4-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-e-v0-c4-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-e-v0-c4-v5-mkmlizer: ║       /___/                                                         ║
cycy233-l3-e-v0-c4-v5-mkmlizer: ║                                                                     ║
cycy233-l3-e-v0-c4-v5-mkmlizer: ║  Version: 0.10.1                                                    ║
cycy233-l3-e-v0-c4-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-e-v0-c4-v5-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-e-v0-c4-v5-mkmlizer: ║                                                                     ║
cycy233-l3-e-v0-c4-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-e-v0-c4-v5-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-e-v0-c4-v5-mkmlizer: ║                                                                     ║
cycy233-l3-e-v0-c4-v5-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-e-v0-c4-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-e-v0-c4-v5-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-e-v0-c4-v5-mkmlizer: ║                                                                     ║
cycy233-l3-e-v0-c4-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-e-v0-c4-v5-mkmlizer: Downloaded to shared memory in 34.626s
cycy233-l3-e-v0-c4-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpz53bhipm, device:0
cycy233-l3-e-v0-c4-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-e-v0-c4-v5-mkmlizer: quantized model in 25.809s
cycy233-l3-e-v0-c4-v5-mkmlizer: Processed model cycy233/L3-e-v0-c4 in 60.435s
cycy233-l3-e-v0-c4-v5-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-e-v0-c4-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-e-v0-c4-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-e-v0-c4-v5
cycy233-l3-e-v0-c4-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-e-v0-c4-v5/config.json
cycy233-l3-e-v0-c4-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-e-v0-c4-v5/special_tokens_map.json
cycy233-l3-e-v0-c4-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-e-v0-c4-v5/tokenizer_config.json
cycy233-l3-e-v0-c4-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-e-v0-c4-v5/tokenizer.json
cycy233-l3-e-v0-c4-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-e-v0-c4-v5/flywheel_model.0.safetensors
cycy233-l3-e-v0-c4-v5-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 33.17it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 55.13it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 50.37it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:05, 52.84it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:05, 48.52it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:04, 50.63it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:04, 51.67it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 52.14it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:03, 57.45it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 52.19it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:04, 52.28it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:05, 37.65it/s]
Loading 0:  31%|███▏      | 91/291 [00:01<00:05, 38.80it/s]
Loading 0:  33%|███▎      | 96/291 [00:02<00:04, 40.26it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 46.79it/s]
Loading 0:  37%|███▋      | 109/291 [00:02<00:03, 45.78it/s]
Loading 0:  39%|███▉      | 114/291 [00:02<00:03, 45.67it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 49.78it/s]
Loading 0:  44%|████▎     | 127/291 [00:02<00:03, 45.24it/s]
Loading 0:  45%|████▌     | 132/291 [00:02<00:03, 43.14it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:03, 48.36it/s]
Loading 0:  50%|████▉     | 145/291 [00:03<00:03, 46.49it/s]
Loading 0:  52%|█████▏    | 150/291 [00:03<00:03, 46.57it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 51.45it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 47.51it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 46.92it/s]
Loading 0:  60%|██████    | 176/291 [00:03<00:02, 55.06it/s]
Loading 0:  63%|██████▎   | 182/291 [00:03<00:02, 47.34it/s]
Loading 0:  65%|██████▍   | 188/291 [00:04<00:02, 37.43it/s]
Loading 0:  66%|██████▋   | 193/291 [00:04<00:02, 39.00it/s]
Loading 0:  68%|██████▊   | 199/291 [00:04<00:02, 39.70it/s]
Loading 0:  70%|███████   | 204/291 [00:04<00:02, 41.43it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 47.67it/s]
Loading 0:  75%|███████▍  | 217/291 [00:04<00:01, 45.36it/s]
Loading 0:  76%|███████▋  | 222/291 [00:04<00:01, 45.23it/s]
Loading 0:  79%|███████▊  | 229/291 [00:04<00:01, 50.36it/s]
Loading 0:  81%|████████  | 235/291 [00:05<00:01, 47.97it/s]
Loading 0:  82%|████████▏ | 240/291 [00:05<00:01, 46.92it/s]
Loading 0:  85%|████████▍ | 246/291 [00:05<00:00, 49.90it/s]
Loading 0:  87%|████████▋ | 252/291 [00:05<00:00, 49.67it/s]
Loading 0:  89%|████████▊ | 258/291 [00:05<00:00, 44.15it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 48.84it/s]
Loading 0:  93%|█████████▎| 271/291 [00:05<00:00, 46.22it/s]
Loading 0:  95%|█████████▍| 276/291 [00:05<00:00, 45.49it/s]
Loading 0:  97%|█████████▋| 282/291 [00:06<00:00, 41.70it/s]
Loading 0:  99%|█████████▊| 287/291 [00:11<00:01,  3.31it/s]
                                                            
Job cycy233-l3-e-v0-c4-v5-mkmlizer completed after 84.9s with status: succeeded
Stopping job with name cycy233-l3-e-v0-c4-v5-mkmlizer
Pipeline stage MKMLizer completed in 87.61s
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 cycy233-l3-e-v0-c4-v5
Waiting for inference service cycy233-l3-e-v0-c4-v5 to be ready
Failed to get response for submission blend_fedek_2024-08-24: ('http://mistralai-mixtral-8x7b-3473-v131-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
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 cycy233-l3-e-v0-c4-v5 ready after 180.74123620986938s
Pipeline stage MKMLDeployer completed in 181.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4006664752960205s
Received healthy response to inference request in 2.124845027923584s
Received healthy response to inference request in 2.9953441619873047s
Received healthy response to inference request in 1.963094711303711s
Received healthy response to inference request in 1.433678388595581s
5 requests
0 failed requests
5th percentile: 1.539561653137207
10th percentile: 1.645444917678833
20th percentile: 1.857211446762085
30th percentile: 1.9954447746276855
40th percentile: 2.0601449012756348
50th percentile: 2.124845027923584
60th percentile: 2.473044681549072
70th percentile: 2.82124433517456
80th percentile: 3.076408624649048
90th percentile: 3.238537549972534
95th percentile: 3.3196020126342773
99th percentile: 3.3844535827636717
mean time: 2.38352575302124
Pipeline stage StressChecker completed in 13.18s
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 9.97s
Shutdown handler de-registered
cycy233-l3-e-v0-c4_v5 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 cycy233-l3-e-v0-c4-v5-profiler
Waiting for inference service cycy233-l3-e-v0-c4-v5-profiler to be ready
Inference service cycy233-l3-e-v0-c4-v5-profiler ready after 180.44190788269043s
Pipeline stage MKMLProfilerDeployer completed in 181.77s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-e-v0-c4-v5-profiler-predictor-00001-deployment-w6kwm:/code/chaiverse_profiler_1726220948 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-e-v0-c4-v5-profiler-predictor-00001-deployment-w6kwm --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726220948 && 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_1726220948/summary.json'
kubectl exec -it cycy233-l3-e-v0-c4-v5-profiler-predictor-00001-deployment-w6kwm --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726220948/summary.json'
Pipeline stage MKMLProfilerRunner completed in 795.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-e-v0-c4-v5-profiler is running
Tearing down inference service cycy233-l3-e-v0-c4-v5-profiler
Service cycy233-l3-e-v0-c4-v5-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.90s
Shutdown handler de-registered
cycy233-l3-e-v0-c4_v5 status is now inactive due to auto deactivation removed underperforming models