submission_id: sao10k-hina-1_v1
developer_uid: sao10k
alignment_samples: 13299
alignment_score: -0.6121717355007653
best_of: 8
celo_rating: 1237.14
display_name: Hina1
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': 1.2, 'top_p': 1.0, 'min_p': 0.2, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\n\n', '<|eot_id|>', '\n\n{user_name}', '\nYou:', '<|end_header_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: Sao10K/Hina-1
latencies: [{'batch_size': 1, 'throughput': 0.86914723852222, 'latency_mean': 1.1504905104637146, 'latency_p50': 1.14077627658844, 'latency_p90': 1.2704403162002562}, {'batch_size': 4, 'throughput': 1.8162224367409112, 'latency_mean': 2.1902089738845825, 'latency_p50': 2.1900335550308228, 'latency_p90': 2.4000712633132935}, {'batch_size': 5, 'throughput': 1.9647713732367216, 'latency_mean': 2.535273655653, 'latency_p50': 2.5306466817855835, 'latency_p90': 2.860601878166199}, {'batch_size': 8, 'throughput': 2.1267917514440935, 'latency_mean': 3.735635291337967, 'latency_p50': 3.752841591835022, 'latency_p90': 4.1572837114334105}, {'batch_size': 10, 'throughput': 2.148239987961099, 'latency_mean': 4.6163728129863735, 'latency_p50': 4.607988357543945, 'latency_p90': 5.154895257949829}, {'batch_size': 12, 'throughput': 2.1840315293391392, 'latency_mean': 5.446751741170883, 'latency_p50': 5.4524245262146, 'latency_p90': 6.116923713684082}, {'batch_size': 15, 'throughput': 2.1493874288822568, 'latency_mean': 6.900958112478256, 'latency_p50': 6.955800533294678, 'latency_p90': 7.647743368148804}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Sao10K/Hina-1
model_name: Hina1
model_num_parameters: 8030261248.0
model_repo: Sao10K/Hina-1
model_size: 8B
num_battles: 13299
num_wins: 6552
propriety_score: 0.7427272727272727
propriety_total_count: 1100.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 2.14
timestamp: 2024-09-06T21:52:47+00:00
us_pacific_date: 2024-09-06
win_ratio: 0.49266862170087977
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 sao10k-hina-1-v1-mkmlizer
Waiting for job on sao10k-hina-1-v1-mkmlizer to finish
sao10k-hina-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-hina-1-v1-mkmlizer: ║ _____ __ __ ║
sao10k-hina-1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-hina-1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-hina-1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-hina-1-v1-mkmlizer: ║ /___/ ║
sao10k-hina-1-v1-mkmlizer: ║ ║
sao10k-hina-1-v1-mkmlizer: ║ Version: 0.10.1 ║
sao10k-hina-1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-hina-1-v1-mkmlizer: ║ https://mk1.ai ║
sao10k-hina-1-v1-mkmlizer: ║ ║
sao10k-hina-1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-hina-1-v1-mkmlizer: ║ belonging to: ║
sao10k-hina-1-v1-mkmlizer: ║ ║
sao10k-hina-1-v1-mkmlizer: ║ Chai Research Corp. ║
sao10k-hina-1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-hina-1-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
sao10k-hina-1-v1-mkmlizer: ║ ║
sao10k-hina-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission neversleep-noromaid-v0_8068_v150: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:60134->127.0.0.1:8080: read: connection reset by peer\n')
sao10k-hina-1-v1-mkmlizer: Downloaded to shared memory in 28.626s
sao10k-hina-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8k8wulbs, device:0
sao10k-hina-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-hina-1-v1-mkmlizer: quantized model in 25.717s
sao10k-hina-1-v1-mkmlizer: Processed model Sao10K/Hina-1 in 54.344s
sao10k-hina-1-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-hina-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-hina-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-hina-1-v1
sao10k-hina-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-hina-1-v1/config.json
sao10k-hina-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-hina-1-v1/special_tokens_map.json
sao10k-hina-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-hina-1-v1/tokenizer_config.json
sao10k-hina-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-hina-1-v1/tokenizer.json
sao10k-hina-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-hina-1-v1/flywheel_model.0.safetensors
sao10k-hina-1-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 2/291 [00:04<11:24, 2.37s/it] Loading 0: 2%|▏ | 6/291 [00:04<03:02, 1.56it/s] Loading 0: 4%|▍ | 13/291 [00:04<01:05, 4.27it/s] Loading 0: 7%|▋ | 20/291 [00:05<00:35, 7.53it/s] Loading 0: 9%|▊ | 25/291 [00:05<00:25, 10.36it/s] Loading 0: 11%|█▏ | 33/291 [00:05<00:16, 15.61it/s] Loading 0: 14%|█▍ | 41/291 [00:05<00:11, 22.44it/s] Loading 0: 16%|█▌ | 47/291 [00:05<00:09, 25.68it/s] Loading 0: 18%|█▊ | 53/291 [00:05<00:07, 30.43it/s] Loading 0: 20%|██ | 59/291 [00:05<00:06, 35.04it/s] Loading 0: 22%|██▏ | 65/291 [00:06<00:06, 36.02it/s] Loading 0: 24%|██▍ | 70/291 [00:06<00:05, 38.07it/s] Loading 0: 26%|██▋ | 77/291 [00:06<00:04, 44.79it/s] Loading 0: 29%|██▊ | 83/291 [00:06<00:06, 31.50it/s] Loading 0: 30%|███ | 88/291 [00:06<00:06, 33.81it/s] Loading 0: 33%|███▎ | 95/291 [00:06<00:04, 40.71it/s] Loading 0: 35%|███▍ | 101/291 [00:06<00:04, 40.91it/s] Loading 0: 36%|███▋ | 106/291 [00:07<00:04, 42.22it/s] Loading 0: 38%|███▊ | 112/291 [00:07<00:03, 45.86it/s] Loading 0: 41%|████ | 118/291 [00:07<00:03, 48.18it/s] Loading 0: 43%|████▎ | 124/291 [00:07<00:03, 42.79it/s] Loading 0: 45%|████▌ | 131/291 [00:07<00:03, 48.10it/s] Loading 0: 47%|████▋ | 137/291 [00:07<00:03, 46.07it/s] Loading 0: 49%|████▉ | 142/291 [00:07<00:03, 44.63it/s] Loading 0: 51%|█████ | 149/291 [00:07<00:02, 49.66it/s] Loading 0: 53%|█████▎ | 155/291 [00:08<00:03, 45.03it/s] Loading 0: 55%|█████▍ | 160/291 [00:08<00:02, 44.89it/s] Loading 0: 57%|█████▋ | 167/291 [00:08<00:02, 49.44it/s] Loading 0: 59%|█████▉ | 173/291 [00:08<00:02, 47.44it/s] Loading 0: 61%|██████ | 178/291 [00:08<00:02, 47.13it/s] Loading 0: 63%|██████▎ | 184/291 [00:08<00:02, 50.42it/s] Loading 0: 65%|██████▌ | 190/291 [00:08<00:01, 51.18it/s] Loading 0: 67%|██████▋ | 196/291 [00:08<00:02, 44.01it/s] Loading 0: 70%|██████▉ | 203/291 [00:09<00:01, 49.24it/s] Loading 0: 72%|███████▏ | 209/291 [00:09<00:02, 31.75it/s] Loading 0: 74%|███████▎ | 214/291 [00:09<00:02, 34.02it/s] Loading 0: 76%|███████▌ | 221/291 [00:09<00:01, 40.80it/s] Loading 0: 78%|███████▊ | 227/291 [00:09<00:01, 40.12it/s] Loading 0: 80%|███████▉ | 232/291 [00:09<00:01, 41.68it/s] Loading 0: 82%|████████▏ | 238/291 [00:10<00:01, 45.97it/s] Loading 0: 84%|████████▍ | 244/291 [00:10<00:00, 48.35it/s] Loading 0: 86%|████████▌ | 250/291 [00:10<00:00, 44.48it/s] Loading 0: 88%|████████▊ | 256/291 [00:10<00:00, 48.05it/s] Loading 0: 90%|█████████ | 262/291 [00:10<00:00, 49.24it/s] Loading 0: 92%|█████████▏| 268/291 [00:10<00:00, 43.27it/s] Loading 0: 95%|█████████▍| 275/291 [00:10<00:00, 48.21it/s] Loading 0: 97%|█████████▋| 281/291 [00:10<00:00, 45.39it/s] Loading 0: 98%|█████████▊| 286/291 [00:11<00:00, 45.55it/s]
Job sao10k-hina-1-v1-mkmlizer completed after 73.78s with status: succeeded
Stopping job with name sao10k-hina-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 74.57s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sao10k-hina-1-v1
Waiting for inference service sao10k-hina-1-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
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 sao10k-hina-1-v1 ready after 151.24511075019836s
Pipeline stage MKMLDeployer completed in 151.65s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.405804395675659s
Received healthy response to inference request in 1.834975242614746s
Received healthy response to inference request in 1.6545298099517822s
Received healthy response to inference request in 1.4938075542449951s
Received healthy response to inference request in 2.1337766647338867s
5 requests
0 failed requests
5th percentile: 1.5259520053863525
10th percentile: 1.55809645652771
20th percentile: 1.622385358810425
30th percentile: 1.690618896484375
40th percentile: 1.7627970695495605
50th percentile: 1.834975242614746
60th percentile: 1.9544958114624023
70th percentile: 2.0740163803100584
80th percentile: 2.1881822109222413
90th percentile: 2.29699330329895
95th percentile: 2.3513988494873046
99th percentile: 2.3949232864379884
mean time: 1.904578733444214
Pipeline stage StressChecker completed in 10.79s
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 4.15s
Shutdown handler de-registered
sao10k-hina-1_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sao10k-hina-1-v1-profiler
Waiting for inference service sao10k-hina-1-v1-profiler to be ready
Inference service sao10k-hina-1-v1-profiler ready after 150.36594104766846s
Pipeline stage MKMLProfilerDeployer completed in 150.72s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sao10k-hina-1-v1-profiler-predictor-00001-deployment-7d8b5ktxff:/code/chaiverse_profiler_1725659996 --namespace tenant-chaiml-guanaco
kubectl exec -it sao10k-hina-1-v1-profiler-predictor-00001-deployment-7d8b5ktxff --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725659996 && 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_1725659996/summary.json'
kubectl exec -it sao10k-hina-1-v1-profiler-predictor-00001-deployment-7d8b5ktxff --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725659996/summary.json'
Pipeline stage MKMLProfilerRunner completed in 820.59s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sao10k-hina-1-v1-profiler is running
Tearing down inference service sao10k-hina-1-v1-profiler
Service sao10k-hina-1-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.76s
Shutdown handler de-registered
sao10k-hina-1_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics