submission_id: cycy233-l3-p-v2-c2_v1
developer_uid: shiroe40
alignment_samples: 12345
alignment_score: -0.25124785005644146
best_of: 16
celo_rating: 1246.78
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': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: cycy233/L3-p-v2-c2
latencies: [{'batch_size': 1, 'throughput': 0.9144263858383497, 'latency_mean': 1.0934885406494141, 'latency_p50': 1.0789849758148193, 'latency_p90': 1.228066611289978}, {'batch_size': 4, 'throughput': 1.8143600188331108, 'latency_mean': 2.199453605413437, 'latency_p50': 2.1866092681884766, 'latency_p90': 2.4710525274276733}, {'batch_size': 5, 'throughput': 1.8864044043531756, 'latency_mean': 2.6435090386867524, 'latency_p50': 2.6495699882507324, 'latency_p90': 2.932551956176758}, {'batch_size': 8, 'throughput': 1.9980992517210474, 'latency_mean': 3.973411853313446, 'latency_p50': 3.9587947130203247, 'latency_p90': 4.469381332397461}, {'batch_size': 10, 'throughput': 2.021754721392651, 'latency_mean': 4.899687888622284, 'latency_p50': 4.8817020654678345, 'latency_p90': 5.631745100021362}, {'batch_size': 12, 'throughput': 2.018412584668954, 'latency_mean': 5.868164737224578, 'latency_p50': 5.807479619979858, 'latency_p90': 6.730306911468506}, {'batch_size': 15, 'throughput': 2.0185485244672448, 'latency_mean': 7.283468351364136, 'latency_p50': 7.316380500793457, 'latency_p90': 8.177747249603271}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: cycy233/L3-p-v2-c2
model_name: auto
model_num_parameters: 8030261248.0
model_repo: cycy233/L3-p-v2-c2
model_size: 8B
num_battles: 12345
num_wins: 6239
propriety_score: 0.7240684793554885
propriety_total_count: 993.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 2.0
timestamp: 2024-09-10T02:50:33+00:00
us_pacific_date: 2024-09-09
win_ratio: 0.505386796273795
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-p-v2-c2-v1-mkmlizer
Waiting for job on cycy233-l3-p-v2-c2-v1-mkmlizer to finish
cycy233-l3-p-v2-c2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-p-v2-c2-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-p-v2-c2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-p-v2-c2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-p-v2-c2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-p-v2-c2-v1-mkmlizer: ║       /___/                                                         ║
cycy233-l3-p-v2-c2-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v2-c2-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
cycy233-l3-p-v2-c2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-p-v2-c2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-p-v2-c2-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v2-c2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-p-v2-c2-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-p-v2-c2-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v2-c2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-p-v2-c2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-p-v2-c2-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-p-v2-c2-v1-mkmlizer: ║                                                                     ║
cycy233-l3-p-v2-c2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-p-v2-c1-v1-mkmlizer: Downloaded to shared memory in 33.956s
cycy233-l3-p-v2-c1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfzydeu5y, device:0
cycy233-l3-p-v2-c1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
cycy233-l3-p-v2-c2-v1-mkmlizer: Downloaded to shared memory in 34.121s
cycy233-l3-p-v2-c2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqdn__z99, device:0
cycy233-l3-p-v2-c2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-p-v2-c1-v1-mkmlizer: quantized model in 25.858s
cycy233-l3-p-v2-c1-v1-mkmlizer: Processed model cycy233/L3-p-v2-c1 in 59.814s
cycy233-l3-p-v2-c1-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-p-v2-c1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-p-v2-c1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-p-v2-c1-v1
cycy233-l3-p-v2-c1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-p-v2-c1-v1/config.json
cycy233-l3-p-v2-c1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-p-v2-c1-v1/special_tokens_map.json
cycy233-l3-p-v2-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-p-v2-c1-v1/tokenizer_config.json
cycy233-l3-p-v2-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-p-v2-c1-v1/tokenizer.json
cycy233-l3-p-v2-c1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-p-v2-c1-v1/flywheel_model.0.safetensors
cycy233-l3-p-v2-c1-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 36.73it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:03, 72.57it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:03, 75.96it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 80.12it/s]
Loading 0:  15%|█▍        | 43/291 [00:00<00:03, 79.03it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:02, 91.96it/s]
Loading 0:  23%|██▎       | 68/291 [00:00<00:02, 93.90it/s]
Loading 0:  27%|██▋       | 79/291 [00:00<00:02, 88.07it/s]
Loading 0:  30%|███       | 88/291 [00:02<00:08, 23.56it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 33.59it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 39.35it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 45.46it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 49.10it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 56.11it/s]
Loading 0:  52%|█████▏    | 151/291 [00:02<00:02, 64.76it/s]
Loading 0:  57%|█████▋    | 166/291 [00:02<00:01, 74.01it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 75.91it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:04, 25.16it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 30.79it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 42.10it/s]
Loading 0:  77%|███████▋  | 223/291 [00:04<00:01, 49.98it/s]
Loading 0:  80%|███████▉  | 232/291 [00:04<00:01, 55.97it/s]
Loading 0:  83%|████████▎ | 241/291 [00:04<00:00, 57.57it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 69.73it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 72.31it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 73.20it/s]
Loading 0:  99%|█████████▊| 287/291 [00:05<00:00, 45.93it/s]
                                                            

Job cycy233-l3-p-v2-c1-v1-mkmlizer completed after 84.84s with status: succeeded
Stopping job with name cycy233-l3-p-v2-c1-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.52s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-l3-p-v2-c1-v1
Waiting for inference service cycy233-l3-p-v2-c1-v1 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
cycy233-l3-p-v2-c2-v1-mkmlizer: quantized model in 26.235s
cycy233-l3-p-v2-c2-v1-mkmlizer: Processed model cycy233/L3-p-v2-c2 in 60.356s
cycy233-l3-p-v2-c2-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-p-v2-c2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-p-v2-c2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-p-v2-c2-v1
cycy233-l3-p-v2-c2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-p-v2-c2-v1/config.json
cycy233-l3-p-v2-c2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-p-v2-c2-v1/special_tokens_map.json
cycy233-l3-p-v2-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-p-v2-c2-v1/tokenizer_config.json
cycy233-l3-p-v2-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-p-v2-c2-v1/tokenizer.json
cycy233-l3-p-v2-c2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-p-v2-c2-v1/flywheel_model.0.safetensors
cycy233-l3-p-v2-c2-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:08, 35.41it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 52.20it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:04, 58.54it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:04, 59.88it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:04, 62.35it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:03, 66.34it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 68.42it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:03, 68.83it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 67.52it/s]
Loading 0:  29%|██▊       | 83/291 [00:02<00:10, 19.46it/s]
Loading 0:  30%|███       | 88/291 [00:02<00:09, 21.77it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:06, 29.62it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:04, 38.00it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:03, 46.29it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 54.16it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:02, 59.57it/s]
Loading 0:  49%|████▉     | 142/291 [00:03<00:02, 64.44it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:01, 77.08it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 80.50it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 87.68it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:03, 26.41it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 31.16it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:02, 37.39it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 43.46it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 50.13it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:00, 56.89it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 63.38it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 68.27it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 70.89it/s]
Loading 0:  94%|█████████▍| 274/291 [00:05<00:00, 69.50it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 68.72it/s]
Loading 0: 100%|██████████| 291/291 [00:11<00:00,  5.10it/s]
                                                            

Job cycy233-l3-p-v2-c2-v1-mkmlizer completed after 86.47s with status: succeeded
Stopping job with name cycy233-l3-p-v2-c2-v1-mkmlizer
Pipeline stage MKMLizer completed in 86.91s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-l3-p-v2-c2-v1
Waiting for inference service cycy233-l3-p-v2-c2-v1 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
Inference service cycy233-l3-p-v2-c1-v1 ready after 141.01398301124573s
Pipeline stage MKMLDeployer completed in 141.56s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.469740867614746s
Received healthy response to inference request in 2.288065195083618s
Received healthy response to inference request in 1.4797906875610352s
Received healthy response to inference request in 1.4168586730957031s
Received healthy response to inference request in 2.2975921630859375s
5 requests
0 failed requests
5th percentile: 1.4294450759887696
10th percentile: 1.442031478881836
20th percentile: 1.4672042846679687
30th percentile: 1.6414455890655517
40th percentile: 1.964755392074585
50th percentile: 2.288065195083618
60th percentile: 2.291875982284546
70th percentile: 2.2956867694854735
80th percentile: 2.3320219039916994
90th percentile: 2.4008813858032227
95th percentile: 2.435311126708984
99th percentile: 2.462854919433594
mean time: 1.990409517288208
Pipeline stage StressChecker completed in 13.04s
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 4.84s
Shutdown handler de-registered
cycy233-l3-p-v2-c1_v1 status is now deployed due to DeploymentManager action
Inference service cycy233-l3-p-v2-c2-v1 ready after 150.8548183441162s
Pipeline stage MKMLDeployer completed in 151.42s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1303961277008057s
Received healthy response to inference request in 1.6865968704223633s
Received healthy response to inference request in 1.6211700439453125s
Received healthy response to inference request in 1.7492284774780273s
Received healthy response to inference request in 2.069676637649536s
5 requests
0 failed requests
5th percentile: 1.6342554092407227
10th percentile: 1.6473407745361328
20th percentile: 1.6735115051269531
30th percentile: 1.6991231918334961
40th percentile: 1.7241758346557616
50th percentile: 1.7492284774780273
60th percentile: 1.8774077415466308
70th percentile: 2.0055870056152343
80th percentile: 2.08182053565979
90th percentile: 2.1061083316802978
95th percentile: 2.118252229690552
99th percentile: 2.127967348098755
mean time: 1.851413631439209
Pipeline stage StressChecker completed in 10.82s
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 3.55s
Shutdown handler de-registered
cycy233-l3-p-v2-c2_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 0.16s
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 cycy233-l3-p-v2-c2-v1-profiler
Waiting for inference service cycy233-l3-p-v2-c2-v1-profiler to be ready
Inference service cycy233-l3-p-v2-c2-v1-profiler ready after 160.37623476982117s
Pipeline stage MKMLProfilerDeployer completed in 161.54s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-p-v2-c2-v1-profiler-predictor-00001-deployment-hl5jk:/code/chaiverse_profiler_1725937093 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-p-v2-c2-v1-profiler-predictor-00001-deployment-hl5jk --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725937093 && 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_1725937093/summary.json'
kubectl exec -it cycy233-l3-p-v2-c2-v1-profiler-predictor-00001-deployment-hl5jk --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725937093/summary.json'
Pipeline stage MKMLProfilerRunner completed in 838.62s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-p-v2-c2-v1-profiler is running
Tearing down inference service cycy233-l3-p-v2-c2-v1-profiler
Service cycy233-l3-p-v2-c2-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.71s
Shutdown handler de-registered
cycy233-l3-p-v2-c2_v1 status is now inactive due to auto deactivation removed underperforming models