submission_id: cycy233-l3-p-v4-c2_v2
developer_uid: shiroe40
alignment_samples: 11987
alignment_score: 0.4122617407065727
best_of: 16
celo_rating: 1248.58
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-v4-c2
latencies: [{'batch_size': 1, 'throughput': 0.9093250471627231, 'latency_mean': 1.0996559822559357, 'latency_p50': 1.0971759557724, 'latency_p90': 1.223753809928894}, {'batch_size': 4, 'throughput': 1.7974931639034113, 'latency_mean': 2.2158111453056337, 'latency_p50': 2.2062342166900635, 'latency_p90': 2.481570506095886}, {'batch_size': 5, 'throughput': 1.9033668259411474, 'latency_mean': 2.6161681532859804, 'latency_p50': 2.6071763038635254, 'latency_p90': 2.9250736951828005}, {'batch_size': 8, 'throughput': 2.0252790441151713, 'latency_mean': 3.9243143260478974, 'latency_p50': 3.9407827854156494, 'latency_p90': 4.37947690486908}, {'batch_size': 10, 'throughput': 2.0552542748628286, 'latency_mean': 4.815507111549377, 'latency_p50': 4.792764902114868, 'latency_p90': 5.6048270702362055}, {'batch_size': 12, 'throughput': 2.048324246327655, 'latency_mean': 5.787768824100494, 'latency_p50': 5.806396842002869, 'latency_p90': 6.504469561576843}, {'batch_size': 15, 'throughput': 2.0700300982227433, 'latency_mean': 7.108118033409118, 'latency_p50': 7.170152187347412, 'latency_p90': 7.936805701255798}]
max_input_tokens: 512
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: 11987
num_wins: 6058
propriety_score: 0.7287958115183246
propriety_total_count: 955.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 2.02
timestamp: 2024-09-13T02:31:15+00:00
us_pacific_date: 2024-09-12
win_ratio: 0.5053808292316676
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-v2-mkmlizer
Waiting for job on cycy233-l3-p-v4-c2-v2-mkmlizer to finish
cycy233-l3-p-v4-c2-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-p-v4-c2-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-p-v4-c2-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-p-v4-c2-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-p-v4-c2-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-p-v4-c2-v2-mkmlizer: ║ /___/ ║
cycy233-l3-p-v4-c2-v2-mkmlizer: ║ ║
cycy233-l3-p-v4-c2-v2-mkmlizer: ║ Version: 0.10.1 ║
cycy233-l3-p-v4-c2-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-p-v4-c2-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-p-v4-c2-v2-mkmlizer: ║ ║
cycy233-l3-p-v4-c2-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-p-v4-c2-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-p-v4-c2-v2-mkmlizer: ║ ║
cycy233-l3-p-v4-c2-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-p-v4-c2-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-p-v4-c2-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-p-v4-c2-v2-mkmlizer: ║ ║
cycy233-l3-p-v4-c2-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-p-v4-c2-v2-mkmlizer: Downloaded to shared memory in 32.978s
cycy233-l3-p-v4-c2-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqjgizy0d, device:0
cycy233-l3-p-v4-c2-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-p-v4-c2-v2-mkmlizer: quantized model in 25.573s
cycy233-l3-p-v4-c2-v2-mkmlizer: Processed model cycy233/L3-p-v4-c2 in 58.552s
cycy233-l3-p-v4-c2-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-p-v4-c2-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-p-v4-c2-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-p-v4-c2-v2
cycy233-l3-p-v4-c2-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-p-v4-c2-v2/config.json
cycy233-l3-p-v4-c2-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-p-v4-c2-v2/special_tokens_map.json
cycy233-l3-p-v4-c2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-p-v4-c2-v2/tokenizer_config.json
cycy233-l3-p-v4-c2-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-p-v4-c2-v2/tokenizer.json
cycy233-l3-p-v4-c2-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-p-v4-c2-v2/flywheel_model.0.safetensors
cycy233-l3-p-v4-c2-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:08, 35.70it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:04, 67.88it/s] Loading 0: 11%|█ | 31/291 [00:00<00:02, 87.15it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 85.09it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:02, 83.84it/s] Loading 0: 21%|██ | 61/291 [00:00<00:02, 84.22it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 84.69it/s] Loading 0: 27%|██▋ | 79/291 [00:00<00:02, 81.53it/s] Loading 0: 30%|███ | 88/291 [00:02<00:09, 22.39it/s] Loading 0: 33%|███▎ | 97/291 [00:02<00:06, 28.37it/s] Loading 0: 36%|███▋ | 106/291 [00:02<00:05, 35.17it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 48.92it/s] Loading 0: 46%|████▌ | 133/291 [00:02<00:02, 56.11it/s] Loading 0: 49%|████▉ | 142/291 [00:02<00:02, 61.64it/s] Loading 0: 54%|█████▍ | 157/291 [00:02<00:01, 71.54it/s] Loading 0: 57%|█████▋ | 166/291 [00:02<00:01, 73.85it/s] Loading 0: 61%|██████ | 178/291 [00:03<00:01, 77.11it/s] Loading 0: 64%|██████▍ | 187/291 [00:04<00:04, 25.62it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 35.92it/s] Loading 0: 73%|███████▎ | 212/291 [00:04<00:01, 43.24it/s] Loading 0: 77%|███████▋ | 223/291 [00:04<00:01, 49.81it/s] Loading 0: 80%|███████▉ | 232/291 [00:04<00:01, 54.52it/s] Loading 0: 85%|████████▍ | 247/291 [00:04<00:00, 66.88it/s] Loading 0: 89%|████████▉ | 259/291 [00:04<00:00, 70.56it/s] Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 74.15it/s] Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 83.22it/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
Job cycy233-l3-p-v4-c2-v2-mkmlizer completed after 83.5s with status: succeeded
Stopping job with name cycy233-l3-p-v4-c2-v2-mkmlizer
Pipeline stage MKMLizer completed in 84.64s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-l3-p-v4-c2-v2
Waiting for inference service cycy233-l3-p-v4-c2-v2 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
Inference service cycy233-l3-p-v4-c2-v2 ready after 181.21188712120056s
Pipeline stage MKMLDeployer completed in 181.57s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.473802328109741s
Received healthy response to inference request in 2.245502233505249s
Received healthy response to inference request in 1.8452515602111816s
Received healthy response to inference request in 1.8580846786499023s
Received healthy response to inference request in 1.6184303760528564s
5 requests
0 failed requests
5th percentile: 1.6637946128845216
10th percentile: 1.7091588497161865
20th percentile: 1.7998873233795165
30th percentile: 1.8478181838989258
40th percentile: 1.852951431274414
50th percentile: 1.8580846786499023
60th percentile: 2.013051700592041
70th percentile: 2.1680187225341796
80th percentile: 2.2911622524261475
90th percentile: 2.3824822902679443
95th percentile: 2.4281423091888428
99th percentile: 2.4646703243255614
mean time: 2.008214235305786
Pipeline stage StressChecker completed in 14.88s
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 5.13s
Shutdown handler de-registered
cycy233-l3-p-v4-c2_v2 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-p-v4-c2-v2-profiler
Waiting for inference service cycy233-l3-p-v4-c2-v2-profiler to be ready
Inference service cycy233-l3-p-v4-c2-v2-profiler ready after 180.50162649154663s
Pipeline stage MKMLProfilerDeployer completed in 180.85s
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-v2-profiler-predictor-00001-deployment-ztwvn:/code/chaiverse_profiler_1726195185 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-p-v4-c2-v2-profiler-predictor-00001-deployment-ztwvn --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726195185 && 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_1726195185/summary.json'
kubectl exec -it cycy233-l3-p-v4-c2-v2-profiler-predictor-00001-deployment-ztwvn --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726195185/summary.json'
Pipeline stage MKMLProfilerRunner completed in 834.77s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-p-v4-c2-v2-profiler is running
Tearing down inference service cycy233-l3-p-v4-c2-v2-profiler
Service cycy233-l3-p-v4-c2-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.93s
Shutdown handler de-registered
cycy233-l3-p-v4-c2_v2 status is now inactive due to auto deactivation removed underperforming models