submission_id: cycy233-l3-bp-v1-c2_v1
developer_uid: shiroe40
alignment_samples: 11326
alignment_score: -0.15135471218622343
best_of: 16
celo_rating: 1264.19
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-bp-v1-c2
latencies: [{'batch_size': 1, 'throughput': 0.9153186790849998, 'latency_mean': 1.092457401752472, 'latency_p50': 1.0825554132461548, 'latency_p90': 1.231495189666748}, {'batch_size': 4, 'throughput': 1.7987332385109958, 'latency_mean': 2.213798063993454, 'latency_p50': 2.2015727758407593, 'latency_p90': 2.483605456352234}, {'batch_size': 5, 'throughput': 1.913592155516044, 'latency_mean': 2.5972221946716307, 'latency_p50': 2.568681240081787, 'latency_p90': 2.9290196895599365}, {'batch_size': 8, 'throughput': 2.0130866634901974, 'latency_mean': 3.944922788143158, 'latency_p50': 3.957442879676819, 'latency_p90': 4.443481969833374}, {'batch_size': 10, 'throughput': 2.0528081919923897, 'latency_mean': 4.825207097530365, 'latency_p50': 4.852195382118225, 'latency_p90': 5.589925622940063}, {'batch_size': 12, 'throughput': 2.040891255870017, 'latency_mean': 5.800060760974884, 'latency_p50': 5.804870247840881, 'latency_p90': 6.680076622962952}, {'batch_size': 15, 'throughput': 2.0470927520818227, 'latency_mean': 7.16130334854126, 'latency_p50': 7.262287378311157, 'latency_p90': 8.018777847290039}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: cycy233/L3-bp-v1-c2
model_name: auto
model_num_parameters: 8030261248.0
model_repo: cycy233/L3-bp-v1-c2
model_size: 8B
num_battles: 11326
num_wins: 6068
propriety_score: 0.7087753134040502
propriety_total_count: 1037.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 2.01
timestamp: 2024-08-25T02:27:29+00:00
us_pacific_date: 2024-08-24
win_ratio: 0.5357584319265407
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bp-v1-c2-v1-mkmlizer
Waiting for job on cycy233-l3-bp-v1-c2-v1-mkmlizer to finish
cycy233-l3-bp-v1-c2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bp-v1-c2-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bp-v1-c2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bp-v1-c2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bp-v1-c2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bp-v1-c2-v1-mkmlizer: ║ /___/ ║
cycy233-l3-bp-v1-c2-v1-mkmlizer: ║ ║
cycy233-l3-bp-v1-c2-v1-mkmlizer: ║ Version: 0.10.1 ║
cycy233-l3-bp-v1-c2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bp-v1-c2-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bp-v1-c2-v1-mkmlizer: ║ ║
cycy233-l3-bp-v1-c2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bp-v1-c2-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-bp-v1-c2-v1-mkmlizer: ║ ║
cycy233-l3-bp-v1-c2-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bp-v1-c2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bp-v1-c2-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-bp-v1-c2-v1-mkmlizer: ║ ║
cycy233-l3-bp-v1-c2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bp-v1-c2-v1-mkmlizer: Downloaded to shared memory in 34.354s
cycy233-l3-bp-v1-c2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpk07c80zs, device:0
cycy233-l3-bp-v1-c2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bp-v1-c2-v1-mkmlizer: quantized model in 26.112s
cycy233-l3-bp-v1-c2-v1-mkmlizer: Processed model cycy233/L3-bp-v1-c2 in 60.467s
cycy233-l3-bp-v1-c2-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bp-v1-c2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bp-v1-c2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bp-v1-c2-v1
cycy233-l3-bp-v1-c2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bp-v1-c2-v1/config.json
cycy233-l3-bp-v1-c2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bp-v1-c2-v1/special_tokens_map.json
cycy233-l3-bp-v1-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bp-v1-c2-v1/tokenizer_config.json
cycy233-l3-bp-v1-c2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bp-v1-c2-v1/tokenizer.json
cycy233-l3-bp-v1-c2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bp-v1-c2-v1/flywheel_model.0.safetensors
cycy233-l3-bp-v1-c2-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:07, 39.67it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 56.46it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:03, 68.95it/s] Loading 0: 11%|█ | 31/291 [00:00<00:03, 73.50it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:03, 74.93it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:03, 76.99it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 77.75it/s] Loading 0: 23%|██▎ | 67/291 [00:00<00:02, 79.78it/s] Loading 0: 27%|██▋ | 79/291 [00:01<00:02, 81.30it/s] Loading 0: 30%|███ | 88/291 [00:02<00:09, 21.74it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:05, 31.73it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:04, 37.70it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 43.41it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 50.35it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 54.45it/s] Loading 0: 51%|█████ | 148/291 [00:02<00:02, 59.39it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 61.27it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:01, 67.43it/s] Loading 0: 60%|██████ | 175/291 [00:03<00:01, 71.36it/s] Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 72.01it/s] Loading 0: 66%|██████▌ | 192/291 [00:04<00:04, 21.26it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:03, 27.38it/s] Loading 0: 74%|███████▎ | 214/291 [00:04<00:02, 36.10it/s] Loading 0: 79%|███████▊ | 229/291 [00:04<00:01, 47.72it/s] Loading 0: 83%|████████▎ | 241/291 [00:05<00:00, 54.15it/s] Loading 0: 86%|████████▌ | 250/291 [00:05<00:00, 58.69it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 61.20it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 66.52it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 67.45it/s] Loading 0: 98%|█████████▊| 286/291 [00:05<00:00, 70.70it/s]
Job cycy233-l3-bp-v1-c2-v1-mkmlizer completed after 84.53s with status: succeeded
Stopping job with name cycy233-l3-bp-v1-c2-v1-mkmlizer
Pipeline stage MKMLizer completed in 85.28s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-bp-v1-c2-v1
Waiting for inference service cycy233-l3-bp-v1-c2-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cycy233-l3-bp-v1-c2-v1 ready after 152.26479077339172s
Pipeline stage ISVCDeployer completed in 153.10s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.986793041229248s
Received healthy response to inference request in 2.1596062183380127s
Received healthy response to inference request in 2.170632839202881s
Received healthy response to inference request in 2.0638415813446045s
Received healthy response to inference request in 1.8448526859283447s
5 requests
0 failed requests
5th percentile: 1.8732407569885254
10th percentile: 1.9016288280487061
20th percentile: 1.9584049701690673
30th percentile: 2.0022027492523193
40th percentile: 2.033022165298462
50th percentile: 2.0638415813446045
60th percentile: 2.102147436141968
70th percentile: 2.1404532909393312
80th percentile: 2.1618115425109865
90th percentile: 2.1662221908569337
95th percentile: 2.168427515029907
99th percentile: 2.170191774368286
mean time: 2.045145273208618
Pipeline stage StressChecker completed in 11.18s
cycy233-l3-bp-v1-c2_v1 status is now deployed due to DeploymentManager action
cycy233-l3-bp-v1-c2_v1 status is now inactive due to auto deactivation removed underperforming models
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 0.13s
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-bp-v1-c2-v1-profiler
Waiting for inference service cycy233-l3-bp-v1-c2-v1-profiler to be ready
Inference service cycy233-l3-bp-v1-c2-v1-profiler ready after 150.37120580673218s
Pipeline stage MKMLProfilerDeployer completed in 150.76s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-bp-v1-c2-v1-profiler-predictor-00001-deploymentk6cc2:/code/chaiverse_profiler_1725502291 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-bp-v1-c2-v1-profiler-predictor-00001-deploymentk6cc2 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725502291 && 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_1725502291/summary.json'
kubectl exec -it cycy233-l3-bp-v1-c2-v1-profiler-predictor-00001-deploymentk6cc2 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725502291/summary.json'
Pipeline stage MKMLProfilerRunner completed in 832.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-bp-v1-c2-v1-profiler is running
Tearing down inference service cycy233-l3-bp-v1-c2-v1-profiler
Service cycy233-l3-bp-v1-c2-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.53s
Shutdown handler de-registered

Usage Metrics

Latency Metrics