submission_id: cycy233-l3-p-v4-c2_v3
developer_uid: shiroe40
alignment_samples: 10585
alignment_score: 0.5258272111704642
best_of: 8
celo_rating: 1241.1
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': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: cycy233/L3-p-v4-c2
latencies: [{'batch_size': 1, 'throughput': 0.8734833649835473, 'latency_mean': 1.144774159193039, 'latency_p50': 1.1383663415908813, 'latency_p90': 1.2678894758224488}, {'batch_size': 4, 'throughput': 1.8546715629100232, 'latency_mean': 2.144614440202713, 'latency_p50': 2.1519609689712524, 'latency_p90': 2.4137515306472777}, {'batch_size': 5, 'throughput': 1.9987387557322005, 'latency_mean': 2.4839293432235716, 'latency_p50': 2.47461473941803, 'latency_p90': 2.814882755279541}, {'batch_size': 8, 'throughput': 2.22625961287042, 'latency_mean': 3.568619283437729, 'latency_p50': 3.589035749435425, 'latency_p90': 4.007189035415649}, {'batch_size': 10, 'throughput': 2.277125495959271, 'latency_mean': 4.356592643260956, 'latency_p50': 4.349764823913574, 'latency_p90': 4.918292832374573}, {'batch_size': 12, 'throughput': 2.3365675076133696, 'latency_mean': 5.088702703714371, 'latency_p50': 5.123193621635437, 'latency_p90': 5.684483218193054}, {'batch_size': 15, 'throughput': 2.3371321859679988, 'latency_mean': 6.3404380488395695, 'latency_p50': 6.33609926700592, 'latency_p90': 7.091358160972595}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: cycy233/L3-p-v4-c2
model_name: auto
model_num_parameters: 8030261248.0
model_repo: cycy233/L3-p-v4-c2
model_size: 8B
num_battles: 10585
num_wins: 5300
propriety_score: 0.7205882352941176
propriety_total_count: 884.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 2.25
timestamp: 2024-09-13T09:42:25+00:00
us_pacific_date: 2024-09-13
win_ratio: 0.5007085498346717
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-v4-c2-v3-mkmlizer
Waiting for job on cycy233-l3-p-v4-c2-v3-mkmlizer to finish
cycy233-l3-p-v4-c2-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-p-v4-c2-v3-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-p-v4-c2-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-p-v4-c2-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-p-v4-c2-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-p-v4-c2-v3-mkmlizer: ║       /___/                                                         ║
cycy233-l3-p-v4-c2-v3-mkmlizer: ║                                                                     ║
cycy233-l3-p-v4-c2-v3-mkmlizer: ║  Version: 0.10.1                                                    ║
cycy233-l3-p-v4-c2-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-p-v4-c2-v3-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-p-v4-c2-v3-mkmlizer: ║                                                                     ║
cycy233-l3-p-v4-c2-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-p-v4-c2-v3-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-p-v4-c2-v3-mkmlizer: ║                                                                     ║
cycy233-l3-p-v4-c2-v3-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-p-v4-c2-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-p-v4-c2-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-p-v4-c2-v3-mkmlizer: ║                                                                     ║
cycy233-l3-p-v4-c2-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-p-v4-c2-v3-mkmlizer: Downloaded to shared memory in 24.946s
cycy233-l3-p-v4-c2-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp59jscrot, device:0
cycy233-l3-p-v4-c2-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-p-v4-c2-v3-mkmlizer: quantized model in 25.259s
cycy233-l3-p-v4-c2-v3-mkmlizer: Processed model cycy233/L3-p-v4-c2 in 50.206s
cycy233-l3-p-v4-c2-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-p-v4-c2-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-p-v4-c2-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-p-v4-c2-v3
cycy233-l3-p-v4-c2-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-p-v4-c2-v3/config.json
cycy233-l3-p-v4-c2-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-p-v4-c2-v3/special_tokens_map.json
cycy233-l3-p-v4-c2-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-p-v4-c2-v3/tokenizer_config.json
cycy233-l3-p-v4-c2-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-p-v4-c2-v3/tokenizer.json
cycy233-l3-p-v4-c2-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-p-v4-c2-v3/flywheel_model.0.safetensors
cycy233-l3-p-v4-c2-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 7/291 [00:00<00:05, 48.01it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 82.42it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:03, 84.11it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:02, 93.89it/s]
Loading 0:  21%|██        | 61/291 [00:00<00:02, 90.99it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:02, 97.15it/s]
Loading 0:  30%|██▉       | 86/291 [00:01<00:07, 26.44it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 31.28it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:05, 37.57it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:03, 46.87it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:02, 59.59it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 65.52it/s]
Loading 0:  54%|█████▍    | 157/291 [00:02<00:01, 76.55it/s]
Loading 0:  58%|█████▊    | 169/291 [00:02<00:01, 79.26it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 86.37it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:03, 28.19it/s]
Loading 0:  70%|███████   | 205/291 [00:04<00:02, 34.26it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 44.95it/s]
Loading 0:  80%|███████▉  | 232/291 [00:04<00:01, 52.15it/s]
Loading 0:  85%|████████▍ | 247/291 [00:04<00:00, 63.07it/s]
Loading 0:  89%|████████▉ | 259/291 [00:04<00:00, 68.36it/s]
Loading 0:  94%|█████████▍| 274/291 [00:04<00:00, 78.31it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 80.89it/s]
                                                            

Job cycy233-l3-p-v4-c2-v3-mkmlizer completed after 73.32s with status: succeeded
Stopping job with name cycy233-l3-p-v4-c2-v3-mkmlizer
Pipeline stage MKMLizer completed in 74.11s
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 cycy233-l3-p-v4-c2-v3
Waiting for inference service cycy233-l3-p-v4-c2-v3 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
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-v4-c2-v3 ready after 180.91268754005432s
Pipeline stage MKMLDeployer completed in 181.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.9154717922210693s
Received healthy response to inference request in 1.602515459060669s
Received healthy response to inference request in 1.7193048000335693s
Received healthy response to inference request in 2.5598785877227783s
Received healthy response to inference request in 1.602534532546997s
5 requests
0 failed requests
5th percentile: 1.6025192737579346
10th percentile: 1.6025230884552002
20th percentile: 1.6025307178497314
30th percentile: 1.6258885860443115
40th percentile: 1.6725966930389404
50th percentile: 1.7193048000335693
60th percentile: 2.0555343151092527
70th percentile: 2.3917638301849364
80th percentile: 2.8309972286224365
90th percentile: 3.373234510421753
95th percentile: 3.644353151321411
99th percentile: 3.8612480640411375
mean time: 2.279941034317017
Pipeline stage StressChecker completed in 13.99s
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 3.74s
Shutdown handler de-registered
cycy233-l3-p-v4-c2_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 0.10s
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 cycy233-l3-p-v4-c2-v3-profiler
Waiting for inference service cycy233-l3-p-v4-c2-v3-profiler to be ready
Inference service cycy233-l3-p-v4-c2-v3-profiler ready after 180.41639113426208s
Pipeline stage MKMLProfilerDeployer completed in 181.02s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-p-v4-c2-v3-profiler-predictor-00001-deployment-s78qd:/code/chaiverse_profiler_1726221050 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-p-v4-c2-v3-profiler-predictor-00001-deployment-s78qd --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726221050 && 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_1726221050/summary.json'
kubectl exec -it cycy233-l3-p-v4-c2-v3-profiler-predictor-00001-deployment-s78qd --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726221050/summary.json'
Pipeline stage MKMLProfilerRunner completed in 792.47s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-p-v4-c2-v3-profiler is running
Tearing down inference service cycy233-l3-p-v4-c2-v3-profiler
Service cycy233-l3-p-v4-c2-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.76s
Shutdown handler de-registered
cycy233-l3-p-v4-c2_v3 status is now inactive due to auto deactivation removed underperforming models