submission_id: jic062-instruct-v19_v1
developer_uid: chace9580
alignment_samples: 11347
alignment_score: 0.7930158280955504
best_of: 16
celo_rating: 1245.98
display_name: jic062-instruct-v19_v1
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': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '|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: jic062/instruct-v19
latencies: [{'batch_size': 1, 'throughput': 0.8962937885445508, 'latency_mean': 1.115614128112793, 'latency_p50': 1.1126842498779297, 'latency_p90': 1.2479995965957642}, {'batch_size': 3, 'throughput': 1.5694444708452553, 'latency_mean': 1.9027322399616242, 'latency_p50': 1.9192768335342407, 'latency_p90': 2.125701975822449}, {'batch_size': 5, 'throughput': 1.7305612809998232, 'latency_mean': 2.8759174394607543, 'latency_p50': 2.883982300758362, 'latency_p90': 3.1879494190216064}, {'batch_size': 6, 'throughput': 1.7505467792779874, 'latency_mean': 3.4149155902862547, 'latency_p50': 3.4159613847732544, 'latency_p90': 3.818722724914551}, {'batch_size': 8, 'throughput': 1.756991239633194, 'latency_mean': 4.519664288759231, 'latency_p50': 4.532433986663818, 'latency_p90': 5.0817595481872555}, {'batch_size': 10, 'throughput': 1.749961987292955, 'latency_mean': 5.663554173707962, 'latency_p50': 5.61333703994751, 'latency_p90': 6.59605598449707}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: jic062/instruct-v19
model_name: jic062-instruct-v19_v1
model_num_parameters: 8030261248.0
model_repo: jic062/instruct-v19
model_size: 8B
num_battles: 11347
num_wins: 5747
propriety_score: 0.7485436893203884
propriety_total_count: 1030.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.76
timestamp: 2024-09-05T15:41:16+00:00
us_pacific_date: 2024-09-05
win_ratio: 0.5064774830351635
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 jic062-instruct-v19-v1-mkmlizer
Waiting for job on jic062-instruct-v19-v1-mkmlizer to finish
jic062-instruct-v19-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-instruct-v19-v1-mkmlizer: ║ _____ __ __ ║
jic062-instruct-v19-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-instruct-v19-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-instruct-v19-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-instruct-v19-v1-mkmlizer: ║ /___/ ║
jic062-instruct-v19-v1-mkmlizer: ║ ║
jic062-instruct-v19-v1-mkmlizer: ║ Version: 0.10.1 ║
jic062-instruct-v19-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-instruct-v19-v1-mkmlizer: ║ https://mk1.ai ║
jic062-instruct-v19-v1-mkmlizer: ║ ║
jic062-instruct-v19-v1-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-instruct-v19-v1-mkmlizer: ║ belonging to: ║
jic062-instruct-v19-v1-mkmlizer: ║ ║
jic062-instruct-v19-v1-mkmlizer: ║ Chai Research Corp. ║
jic062-instruct-v19-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-instruct-v19-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-instruct-v19-v1-mkmlizer: ║ ║
jic062-instruct-v19-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-instruct-v19-v1-mkmlizer: Downloaded to shared memory in 45.129s
jic062-instruct-v19-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmppikeneqj, device:0
jic062-instruct-v19-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-instruct-v19-v1-mkmlizer: quantized model in 26.105s
jic062-instruct-v19-v1-mkmlizer: Processed model jic062/instruct-v19 in 71.234s
jic062-instruct-v19-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-instruct-v19-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-instruct-v19-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-instruct-v19-v1
jic062-instruct-v19-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-instruct-v19-v1/config.json
jic062-instruct-v19-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-instruct-v19-v1/special_tokens_map.json
jic062-instruct-v19-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-instruct-v19-v1/tokenizer_config.json
jic062-instruct-v19-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-instruct-v19-v1/tokenizer.json
jic062-instruct-v19-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-instruct-v19-v1/flywheel_model.0.safetensors
jic062-instruct-v19-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:07, 38.65it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:05, 48.75it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:05, 51.95it/s] Loading 0: 11%|█ | 32/291 [00:00<00:04, 51.83it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:04, 57.89it/s] Loading 0: 16%|█▌ | 46/291 [00:00<00:04, 52.65it/s] Loading 0: 18%|█▊ | 52/291 [00:00<00:04, 52.20it/s] Loading 0: 20%|█▉ | 58/291 [00:01<00:04, 52.85it/s] Loading 0: 22%|██▏ | 64/291 [00:01<00:04, 48.40it/s] Loading 0: 24%|██▎ | 69/291 [00:01<00:04, 46.91it/s] Loading 0: 26%|██▌ | 76/291 [00:01<00:04, 50.69it/s] Loading 0: 28%|██▊ | 82/291 [00:01<00:04, 46.72it/s] Loading 0: 30%|██▉ | 87/291 [00:01<00:06, 33.87it/s] Loading 0: 32%|███▏ | 93/291 [00:02<00:05, 38.18it/s] Loading 0: 34%|███▎ | 98/291 [00:02<00:04, 40.69it/s] Loading 0: 36%|███▌ | 104/291 [00:02<00:04, 39.46it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:03, 48.13it/s] Loading 0: 41%|████ | 118/291 [00:02<00:03, 46.66it/s] Loading 0: 42%|████▏ | 123/291 [00:02<00:03, 46.62it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:03, 50.94it/s] Loading 0: 47%|████▋ | 136/291 [00:02<00:03, 47.36it/s] Loading 0: 48%|████▊ | 141/291 [00:03<00:03, 46.04it/s] Loading 0: 51%|█████ | 147/291 [00:03<00:02, 48.64it/s] Loading 0: 52%|█████▏ | 152/291 [00:03<00:02, 48.46it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 48.14it/s] Loading 0: 56%|█████▌ | 163/291 [00:03<00:02, 45.02it/s] Loading 0: 58%|█████▊ | 168/291 [00:03<00:02, 44.61it/s] Loading 0: 59%|█████▉ | 173/291 [00:03<00:02, 45.13it/s] Loading 0: 62%|██████▏ | 179/291 [00:03<00:02, 48.90it/s] Loading 0: 63%|██████▎ | 184/291 [00:03<00:02, 47.89it/s] Loading 0: 65%|██████▍ | 189/291 [00:04<00:03, 30.28it/s] Loading 0: 67%|██████▋ | 194/291 [00:04<00:02, 32.95it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 42.32it/s] Loading 0: 71%|███████▏ | 208/291 [00:04<00:01, 41.96it/s] Loading 0: 73%|███████▎ | 213/291 [00:04<00:01, 42.82it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 47.77it/s] Loading 0: 78%|███████▊ | 226/291 [00:04<00:01, 45.45it/s] Loading 0: 79%|███████▉ | 231/291 [00:05<00:01, 45.28it/s] Loading 0: 81%|████████▏ | 237/291 [00:05<00:01, 48.59it/s] Loading 0: 84%|████████▎ | 243/291 [00:05<00:00, 50.15it/s] Loading 0: 86%|████████▌ | 249/291 [00:05<00:00, 44.85it/s] Loading 0: 88%|████████▊ | 255/291 [00:05<00:00, 48.10it/s] Loading 0: 90%|████████▉ | 261/291 [00:05<00:00, 50.03it/s] Loading 0: 92%|█████████▏| 267/291 [00:05<00:00, 43.60it/s] Loading 0: 94%|█████████▍| 273/291 [00:05<00:00, 47.08it/s] Loading 0: 96%|█████████▌| 278/291 [00:06<00:00, 47.54it/s] Loading 0: 97%|█████████▋| 283/291 [00:06<00:00, 41.77it/s] Loading 0: 99%|█████████▉| 288/291 [00:11<00:00, 3.14it/s]
Job jic062-instruct-v19-v1-mkmlizer completed after 95.72s with status: succeeded
Stopping job with name jic062-instruct-v19-v1-mkmlizer
Pipeline stage MKMLizer completed in 97.93s
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 jic062-instruct-v19-v1
Waiting for inference service jic062-instruct-v19-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service jic062-instruct-v19-v1 ready after 131.15133261680603s
Pipeline stage MKMLDeployer completed in 131.90s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.225039482116699s
Received healthy response to inference request in 1.5548319816589355s
Received healthy response to inference request in 1.4685230255126953s
Received healthy response to inference request in 2.3010339736938477s
Received healthy response to inference request in 2.0785365104675293s
5 requests
0 failed requests
5th percentile: 1.4857848167419434
10th percentile: 1.5030466079711915
20th percentile: 1.5375701904296875
30th percentile: 1.6595728874206543
40th percentile: 1.869054698944092
50th percentile: 2.0785365104675293
60th percentile: 2.137137699127197
70th percentile: 2.1957388877868653
80th percentile: 2.240238380432129
90th percentile: 2.2706361770629884
95th percentile: 2.285835075378418
99th percentile: 2.2979941940307618
mean time: 1.9255929946899415
Pipeline stage StressChecker completed in 10.91s
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 5.79s
Shutdown handler de-registered
jic062-instruct-v19_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 jic062-instruct-v19-v1-profiler
Waiting for inference service jic062-instruct-v19-v1-profiler to be ready
Inference service jic062-instruct-v19-v1-profiler ready after 150.3532953262329s
Pipeline stage MKMLProfilerDeployer completed in 150.74s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/jic062-instruct-v19-v1-profiler-predictor-00001-deploymentwm7wg:/code/chaiverse_profiler_1725551322 --namespace tenant-chaiml-guanaco
kubectl exec -it jic062-instruct-v19-v1-profiler-predictor-00001-deploymentwm7wg --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725551322 && 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_1725551322/summary.json'
kubectl exec -it jic062-instruct-v19-v1-profiler-predictor-00001-deploymentwm7wg --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725551322/summary.json'
Pipeline stage MKMLProfilerRunner completed in 814.62s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service jic062-instruct-v19-v1-profiler is running
Tearing down inference service jic062-instruct-v19-v1-profiler
Service jic062-instruct-v19-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.92s
Shutdown handler de-registered
jic062-instruct-v19_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics