submission_id: cycy233-l3-p-v1-c4_v1
developer_uid: shiroe40
alignment_samples: 11304
alignment_score: 0.04919057381662737
best_of: 16
celo_rating: 1255.3
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-v1-c4
latencies: [{'batch_size': 1, 'throughput': 0.8999603240457869, 'latency_mean': 1.1110937345027923, 'latency_p50': 1.124469518661499, 'latency_p90': 1.2322253704071044}, {'batch_size': 4, 'throughput': 1.7980640296536456, 'latency_mean': 2.2167507660388948, 'latency_p50': 2.223546862602234, 'latency_p90': 2.481722187995911}, {'batch_size': 5, 'throughput': 1.8844079444717539, 'latency_mean': 2.6437380361557006, 'latency_p50': 2.622496008872986, 'latency_p90': 2.9454896688461303}, {'batch_size': 8, 'throughput': 2.000995568650382, 'latency_mean': 3.9738320899009705, 'latency_p50': 4.026252031326294, 'latency_p90': 4.500487518310547}, {'batch_size': 10, 'throughput': 2.029597153052243, 'latency_mean': 4.883272210359573, 'latency_p50': 4.881932258605957, 'latency_p90': 5.723604393005371}, {'batch_size': 12, 'throughput': 2.033177338032037, 'latency_mean': 5.816126766204834, 'latency_p50': 5.805496454238892, 'latency_p90': 6.736151576042175}, {'batch_size': 15, 'throughput': 2.043013670005117, 'latency_mean': 7.203268933296203, 'latency_p50': 7.303053259849548, 'latency_p90': 8.10137152671814}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: cycy233/L3-p-v1-c4
model_name: auto
model_num_parameters: 8030261248.0
model_repo: cycy233/L3-p-v1-c4
model_size: 8B
num_battles: 11304
num_wins: 5815
propriety_score: 0.710261569416499
propriety_total_count: 994.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 2.0
timestamp: 2024-09-09T03:23:11+00:00
us_pacific_date: 2024-09-08
win_ratio: 0.5144196744515216
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-v1-c4-v1-mkmlizer
Waiting for job on cycy233-l3-p-v1-c4-v1-mkmlizer to finish
cycy233-l3-p-v1-c4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-p-v1-c4-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-p-v1-c4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-p-v1-c4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-p-v1-c4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-p-v1-c4-v1-mkmlizer: ║ /___/ ║
cycy233-l3-p-v1-c4-v1-mkmlizer: ║ ║
cycy233-l3-p-v1-c4-v1-mkmlizer: ║ Version: 0.10.1 ║
cycy233-l3-p-v1-c4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-p-v1-c4-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-p-v1-c4-v1-mkmlizer: ║ ║
cycy233-l3-p-v1-c4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-p-v1-c4-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-p-v1-c4-v1-mkmlizer: ║ ║
cycy233-l3-p-v1-c4-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-p-v1-c4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-p-v1-c4-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-p-v1-c4-v1-mkmlizer: ║ ║
cycy233-l3-p-v1-c4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-p-v1-c4-v1-mkmlizer: Downloaded to shared memory in 36.029s
cycy233-l3-p-v1-c4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9znn7s8m, device:0
cycy233-l3-p-v1-c4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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
cycy233-l3-p-v1-c4-v1-mkmlizer: quantized model in 25.801s
cycy233-l3-p-v1-c4-v1-mkmlizer: Processed model cycy233/L3-p-v1-c4 in 61.830s
cycy233-l3-p-v1-c4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-p-v1-c4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-p-v1-c4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-p-v1-c4-v1
cycy233-l3-p-v1-c4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-p-v1-c4-v1/config.json
cycy233-l3-p-v1-c4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-p-v1-c4-v1/special_tokens_map.json
cycy233-l3-p-v1-c4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-p-v1-c4-v1/tokenizer_config.json
cycy233-l3-p-v1-c4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-p-v1-c4-v1/flywheel_model.0.safetensors
cycy233-l3-p-v1-c4-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:07, 39.29it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:04, 68.30it/s] Loading 0: 11%|█ | 31/291 [00:00<00:03, 86.55it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:02, 87.31it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 94.03it/s] Loading 0: 23%|██▎ | 68/291 [00:00<00:02, 95.38it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:02, 87.45it/s] Loading 0: 30%|███ | 88/291 [00:02<00:08, 23.53it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:05, 33.58it/s] Loading 0: 39%|███▉ | 114/291 [00:02<00:04, 41.94it/s] Loading 0: 43%|████▎ | 124/291 [00:02<00:03, 46.85it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 58.58it/s] Loading 0: 52%|█████▏ | 151/291 [00:02<00:02, 64.40it/s] Loading 0: 55%|█████▍ | 160/291 [00:02<00:01, 68.65it/s] Loading 0: 60%|██████ | 175/291 [00:03<00:01, 78.23it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:03, 26.83it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:02, 32.17it/s] Loading 0: 70%|███████ | 205/291 [00:04<00:02, 38.47it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 50.76it/s] Loading 0: 79%|███████▊ | 229/291 [00:04<00:01, 56.54it/s] Loading 0: 82%|████████▏ | 238/291 [00:04<00:00, 61.89it/s] Loading 0: 86%|████████▌ | 250/291 [00:04<00:00, 67.74it/s] Loading 0: 91%|█████████ | 265/291 [00:04<00:00, 78.39it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 79.77it/s] Loading 0: 99%|█████████▊| 287/291 [00:05<00:00, 48.44it/s]
Job cycy233-l3-p-v1-c4-v1-mkmlizer completed after 84.04s with status: succeeded
Stopping job with name cycy233-l3-p-v1-c4-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.82s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.80s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-l3-p-v1-c4-v1
Waiting for inference service cycy233-l3-p-v1-c4-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-v1-c4-v1 ready after 151.79049038887024s
Pipeline stage MKMLDeployer completed in 152.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0386667251586914s
Received healthy response to inference request in 2.1806859970092773s
Received healthy response to inference request in 1.9352214336395264s
Received healthy response to inference request in 2.370138645172119s
Received healthy response to inference request in 2.699394702911377s
5 requests
0 failed requests
5th percentile: 1.9559104919433594
10th percentile: 1.9765995502471925
20th percentile: 2.0179776668548586
30th percentile: 2.0670705795288087
40th percentile: 2.123878288269043
50th percentile: 2.1806859970092773
60th percentile: 2.2564670562744142
70th percentile: 2.3322481155395507
80th percentile: 2.4359898567199707
90th percentile: 2.567692279815674
95th percentile: 2.6335434913635254
99th percentile: 2.6862244606018066
mean time: 2.2448215007781984
Pipeline stage StressChecker completed in 12.06s
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 4.55s
Shutdown handler de-registered
cycy233-l3-p-v1-c4_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 0.11s
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-v1-c4-v1-profiler
Waiting for inference service cycy233-l3-p-v1-c4-v1-profiler to be ready
Inference service cycy233-l3-p-v1-c4-v1-profiler ready after 150.35387563705444s
Pipeline stage MKMLProfilerDeployer completed in 151.56s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-p-v1-c4-v1-profiler-predictor-00001-deployment-lfxvj:/code/chaiverse_profiler_1725852635 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-p-v1-c4-v1-profiler-predictor-00001-deployment-lfxvj --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725852635 && 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_1725852635/summary.json'
kubectl exec -it cycy233-l3-p-v1-c4-v1-profiler-predictor-00001-deployment-lfxvj --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725852635/summary.json'
Pipeline stage MKMLProfilerRunner completed in 839.71s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-p-v1-c4-v1-profiler is running
Tearing down inference service cycy233-l3-p-v1-c4-v1-profiler
Service cycy233-l3-p-v1-c4-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.72s
Shutdown handler de-registered
cycy233-l3-p-v1-c4_v1 status is now inactive due to auto deactivation removed underperforming models