submission_id: jic062-nemo-v1-1_v1
developer_uid: chace9580
alignment_samples: 12889
alignment_score: 0.6795833448612293
best_of: 8
celo_rating: 1263.21
display_name: jic062-nemo-v1-1_v1
formatter: {'memory_template': '[INST]system\n{memory}[/INST]\n', 'prompt_template': '[INST]user\n{prompt}[/INST]\n', 'bot_template': '[INST]assistant\n{bot_name}: {message}[/INST]\n', 'user_template': '[INST]user\n{user_name}: {message}[/INST]\n', 'response_template': '[INST]assistant\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 0.75, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '\n\n', '\nYou:', '[/INST]', '<|im_end|>', '</s>'], 'max_input_tokens': 512, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: jic062/Nemo-v1.1
latencies: [{'batch_size': 1, 'throughput': 0.7059671289946611, 'latency_mean': 1.4164082872867585, 'latency_p50': 1.4182798862457275, 'latency_p90': 1.5767731666564941}, {'batch_size': 3, 'throughput': 1.3398784173703329, 'latency_mean': 2.2303199422359468, 'latency_p50': 2.226584553718567, 'latency_p90': 2.4911309480667114}, {'batch_size': 5, 'throughput': 1.5715819819981849, 'latency_mean': 3.1717437398433685, 'latency_p50': 3.2193158864974976, 'latency_p90': 3.5628271102905273}, {'batch_size': 6, 'throughput': 1.6234078475521665, 'latency_mean': 3.668849414587021, 'latency_p50': 3.6624194383621216, 'latency_p90': 4.146455907821656}, {'batch_size': 8, 'throughput': 1.6235813478927135, 'latency_mean': 4.903011841773987, 'latency_p50': 4.881819844245911, 'latency_p90': 5.539766812324524}, {'batch_size': 10, 'throughput': 1.5523468988181603, 'latency_mean': 6.397405602931976, 'latency_p50': 6.4297614097595215, 'latency_p90': 7.178028273582458}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: jic062/Nemo-v1.1
model_name: jic062-nemo-v1-1_v1
model_num_parameters: 12772070400.0
model_repo: jic062/Nemo-v1.1
model_size: 13B
num_battles: 12889
num_wins: 6851
propriety_score: 0.7473118279569892
propriety_total_count: 1116.0
ranking_group: single
status: inactive
submission_type: basic
throughput_3p7s: 1.64
timestamp: 2024-09-02T21:38:15+00:00
us_pacific_date: 2024-09-02
win_ratio: 0.5315385212196446
Download Preference Data
Resubmit model
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name jic062-nemo-v1-1-v1-mkmlizer
Waiting for job on jic062-nemo-v1-1-v1-mkmlizer to finish
jic062-nemo-v1-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-nemo-v1-1-v1-mkmlizer: ║ _____ __ __ ║
jic062-nemo-v1-1-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-nemo-v1-1-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-nemo-v1-1-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-nemo-v1-1-v1-mkmlizer: ║ /___/ ║
jic062-nemo-v1-1-v1-mkmlizer: ║ ║
jic062-nemo-v1-1-v1-mkmlizer: ║ Version: 0.10.1 ║
jic062-nemo-v1-1-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-nemo-v1-1-v1-mkmlizer: ║ https://mk1.ai ║
jic062-nemo-v1-1-v1-mkmlizer: ║ ║
jic062-nemo-v1-1-v1-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-nemo-v1-1-v1-mkmlizer: ║ belonging to: ║
jic062-nemo-v1-1-v1-mkmlizer: ║ ║
jic062-nemo-v1-1-v1-mkmlizer: ║ Chai Research Corp. ║
jic062-nemo-v1-1-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-nemo-v1-1-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-nemo-v1-1-v1-mkmlizer: ║ ║
jic062-nemo-v1-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
jic062-nemo-v1-1-v1-mkmlizer: Downloaded to shared memory in 67.500s
jic062-nemo-v1-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpiq6gjf72, device:0
jic062-nemo-v1-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-nemo-v1-1-v1-mkmlizer: quantized model in 36.603s
jic062-nemo-v1-1-v1-mkmlizer: Processed model jic062/Nemo-v1.1 in 104.103s
jic062-nemo-v1-1-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-nemo-v1-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-nemo-v1-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-nemo-v1-1-v1
jic062-nemo-v1-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-nemo-v1-1-v1/config.json
jic062-nemo-v1-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-nemo-v1-1-v1/special_tokens_map.json
jic062-nemo-v1-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-nemo-v1-1-v1/tokenizer_config.json
jic062-nemo-v1-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-nemo-v1-1-v1/tokenizer.json
jic062-nemo-v1-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-nemo-v1-1-v1/flywheel_model.0.safetensors
jic062-nemo-v1-1-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:10, 32.78it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 53.73it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 45.20it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 42.43it/s] Loading 0: 8%|▊ | 30/363 [00:00<00:07, 47.04it/s] Loading 0: 10%|▉ | 35/363 [00:00<00:07, 44.74it/s] Loading 0: 11%|█ | 40/363 [00:00<00:07, 43.88it/s] Loading 0: 12%|█▏ | 45/363 [00:01<00:07, 44.91it/s] Loading 0: 14%|█▍ | 50/363 [00:01<00:08, 36.29it/s] Loading 0: 15%|█▌ | 56/363 [00:01<00:07, 41.51it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:09, 31.72it/s] Loading 0: 18%|█▊ | 65/363 [00:01<00:09, 31.63it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 38.86it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:07, 39.51it/s] Loading 0: 23%|██▎ | 83/363 [00:02<00:06, 40.03it/s] Loading 0: 25%|██▍ | 90/363 [00:02<00:06, 45.10it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:06, 43.60it/s] Loading 0: 28%|██▊ | 101/363 [00:02<00:06, 42.49it/s] Loading 0: 30%|██▉ | 108/363 [00:02<00:05, 49.03it/s] Loading 0: 31%|███▏ | 114/363 [00:02<00:05, 44.92it/s] Loading 0: 33%|███▎ | 119/363 [00:02<00:05, 42.64it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:05, 46.81it/s] Loading 0: 36%|███▋ | 132/363 [00:03<00:05, 45.22it/s] Loading 0: 38%|███▊ | 137/363 [00:03<00:05, 42.73it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 32.60it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 32.98it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 31.33it/s] Loading 0: 43%|████▎ | 156/363 [00:03<00:05, 36.35it/s] Loading 0: 44%|████▍ | 160/363 [00:03<00:05, 36.95it/s] Loading 0: 45%|████▌ | 165/363 [00:04<00:05, 39.21it/s] Loading 0: 47%|████▋ | 170/363 [00:04<00:04, 40.36it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 42.37it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:04, 40.89it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 40.80it/s] Loading 0: 53%|█████▎ | 192/363 [00:04<00:03, 45.06it/s] Loading 0: 54%|█████▍ | 197/363 [00:04<00:03, 43.40it/s] Loading 0: 56%|█████▌ | 202/363 [00:04<00:03, 43.79it/s] Loading 0: 57%|█████▋ | 207/363 [00:05<00:03, 43.13it/s] Loading 0: 58%|█████▊ | 212/363 [00:05<00:04, 34.74it/s] Loading 0: 60%|██████ | 218/363 [00:05<00:03, 39.09it/s] Loading 0: 61%|██████▏ | 223/363 [00:05<00:04, 31.90it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 32.96it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 31.93it/s] Loading 0: 65%|██████▌ | 237/363 [00:05<00:03, 38.16it/s] Loading 0: 67%|██████▋ | 242/363 [00:06<00:03, 39.17it/s] Loading 0: 68%|██████▊ | 247/363 [00:06<00:02, 39.75it/s] Loading 0: 69%|██████▉ | 252/363 [00:06<00:02, 41.00it/s] Loading 0: 71%|███████ | 257/363 [00:06<00:03, 34.40it/s] Loading 0: 73%|███████▎ | 264/363 [00:06<00:02, 41.22it/s] Loading 0: 74%|███████▍ | 269/363 [00:06<00:02, 42.19it/s] Loading 0: 75%|███████▌ | 274/363 [00:06<00:02, 43.37it/s] Loading 0: 77%|███████▋ | 280/363 [00:06<00:01, 42.74it/s] Loading 0: 79%|███████▊ | 285/363 [00:07<00:01, 41.37it/s] Loading 0: 80%|████████ | 291/363 [00:07<00:01, 45.29it/s] Loading 0: 82%|████████▏ | 296/363 [00:07<00:01, 42.32it/s] Loading 0: 83%|████████▎ | 301/363 [00:07<00:01, 42.65it/s] Loading 0: 84%|████████▍ | 306/363 [00:14<00:23, 2.44it/s] Loading 0: 85%|████████▌ | 310/363 [00:14<00:16, 3.17it/s] Loading 0: 87%|████████▋ | 314/363 [00:14<00:11, 4.17it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 6.26it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:04, 8.77it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 11.20it/s] Loading 0: 93%|█████████▎| 338/363 [00:15<00:01, 15.85it/s] Loading 0: 94%|█████████▍| 343/363 [00:15<00:01, 19.39it/s] Loading 0: 96%|█████████▌| 348/363 [00:15<00:00, 21.29it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 29.04it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 31.67it/s]
Job jic062-nemo-v1-1-v1-mkmlizer completed after 126.49s with status: succeeded
Stopping job with name jic062-nemo-v1-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 127.82s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service jic062-nemo-v1-1-v1
Waiting for inference service jic062-nemo-v1-1-v1 to be ready
Inference service jic062-nemo-v1-1-v1 ready after 150.48812890052795s
Pipeline stage MKMLDeployer completed in 150.92s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2781286239624023s
Received healthy response to inference request in 2.0036659240722656s
Received healthy response to inference request in 1.655580997467041s
Received healthy response to inference request in 2.0838286876678467s
Received healthy response to inference request in 2.8896827697753906s
5 requests
0 failed requests
5th percentile: 1.725197982788086
10th percentile: 1.7948149681091308
20th percentile: 1.9340489387512207
30th percentile: 2.019698476791382
40th percentile: 2.051763582229614
50th percentile: 2.0838286876678467
60th percentile: 2.1615486621856688
70th percentile: 2.2392686367034913
80th percentile: 2.400439453125
90th percentile: 2.6450611114501954
95th percentile: 2.767371940612793
99th percentile: 2.865220603942871
mean time: 2.1821774005889893
Pipeline stage StressChecker completed in 11.95s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 4.57s
jic062-nemo-v1-1_v1 status is now deployed due to DeploymentManager action
jic062-nemo-v1-1_v1 status is now inactive due to auto deactivation removed underperforming models
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service jic062-nemo-v1-1-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 1.43s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service jic062-nemo-v1-1-v1-profiler
Waiting for inference service jic062-nemo-v1-1-v1-profiler to be ready
Inference service jic062-nemo-v1-1-v1-profiler ready after 150.3476402759552s
Pipeline stage MKMLProfilerDeployer completed in 150.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/jic062-nemo-v1-1-v1-profiler-predictor-00001-deployment-67ntx6l:/code/chaiverse_profiler_1725340094 --namespace tenant-chaiml-guanaco
kubectl exec -it jic062-nemo-v1-1-v1-profiler-predictor-00001-deployment-67ntx6l --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725340094 && chmod +x profiles.py && python profiles.py profile --best_of_n 8 --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_1725340094/summary.json'
kubectl exec -it jic062-nemo-v1-1-v1-profiler-predictor-00001-deployment-67ntx6l --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725340094/summary.json'
Pipeline stage MKMLProfilerRunner completed in 548.44s
cleanup pipeline after completion
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service jic062-nemo-v1-1-v1-profiler is running
Tearing down inference service jic062-nemo-v1-1-v1-profiler
Service jic062-nemo-v1-1-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.47s
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service jic062-nemo-v1-1-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 1.67s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service jic062-nemo-v1-1-v1-profiler
Waiting for inference service jic062-nemo-v1-1-v1-profiler to be ready
Inference service jic062-nemo-v1-1-v1-profiler ready after 150.36198902130127s
Pipeline stage MKMLProfilerDeployer completed in 150.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/jic062-nemo-v1-1-v1-profiler-predictor-00001-deployment-67b9xl8:/code/chaiverse_profiler_1725396995 --namespace tenant-chaiml-guanaco
kubectl exec -it jic062-nemo-v1-1-v1-profiler-predictor-00001-deployment-67b9xl8 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725396995 && chmod +x profiles.py && 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 512 --output_tokens 64 --summary /code/chaiverse_profiler_1725396995/summary.json'
kubectl exec -it jic062-nemo-v1-1-v1-profiler-predictor-00001-deployment-67b9xl8 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725396995/summary.json'
Pipeline stage MKMLProfilerRunner completed in 941.29s
cleanup pipeline after completion
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service jic062-nemo-v1-1-v1-profiler is running
Tearing down inference service jic062-nemo-v1-1-v1-profiler
Service jic062-nemo-v1-1-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.58s

Usage Metrics

Latency Metrics