submission_id: jic062-nemo-v1-7_v1
developer_uid: chace9580
best_of: 8
celo_rating: 1261.37
display_name: jic062-nemo-v1-7_v1
family_friendly_score: 0.0
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': 0.85, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '/s', '[/INST]'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: False
language_model: jic062/Nemo-v1.7
latencies: [{'batch_size': 1, 'throughput': 0.6136987173660754, 'latency_mean': 1.6294046068191528, 'latency_p50': 1.6369775533676147, 'latency_p90': 1.8031785249710084}, {'batch_size': 3, 'throughput': 1.0772673750482473, 'latency_mean': 2.7709474647045136, 'latency_p50': 2.781137704849243, 'latency_p90': 3.0581368446350097}, {'batch_size': 5, 'throughput': 1.2222942137146013, 'latency_mean': 4.072827442884445, 'latency_p50': 4.06187105178833, 'latency_p90': 4.621717405319214}, {'batch_size': 6, 'throughput': 1.2392483350720553, 'latency_mean': 4.814882472753525, 'latency_p50': 4.826918125152588, 'latency_p90': 5.372453093528748}, {'batch_size': 8, 'throughput': 1.2352201556732256, 'latency_mean': 6.436115370988846, 'latency_p50': 6.437524914741516, 'latency_p90': 7.270096373558045}, {'batch_size': 10, 'throughput': 1.1995844104506208, 'latency_mean': 8.283906960487366, 'latency_p50': 8.322269558906555, 'latency_p90': 9.479323720932006}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: jic062/Nemo-v1.7
model_name: jic062-nemo-v1-7_v1
model_num_parameters: 12772070400.0
model_repo: jic062/Nemo-v1.7
model_size: 13B
num_battles: 425278
num_wins: 220730
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.2
timestamp: 2024-09-21T04:09:35+00:00
us_pacific_date: 2024-09-20
win_ratio: 0.5190252023382352
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-nemo-v1-7-v1-mkmlizer
Waiting for job on jic062-nemo-v1-7-v1-mkmlizer to finish
jic062-nemo-v1-7-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-nemo-v1-7-v1-mkmlizer: ║ _____ __ __ ║
jic062-nemo-v1-7-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jic062-nemo-v1-7-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jic062-nemo-v1-7-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jic062-nemo-v1-7-v1-mkmlizer: ║ /___/ ║
jic062-nemo-v1-7-v1-mkmlizer: ║ ║
jic062-nemo-v1-7-v1-mkmlizer: ║ Version: 0.10.1 ║
jic062-nemo-v1-7-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jic062-nemo-v1-7-v1-mkmlizer: ║ https://mk1.ai ║
jic062-nemo-v1-7-v1-mkmlizer: ║ ║
jic062-nemo-v1-7-v1-mkmlizer: ║ The license key for the current software has been verified as ║
jic062-nemo-v1-7-v1-mkmlizer: ║ belonging to: ║
jic062-nemo-v1-7-v1-mkmlizer: ║ ║
jic062-nemo-v1-7-v1-mkmlizer: ║ Chai Research Corp. ║
jic062-nemo-v1-7-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jic062-nemo-v1-7-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jic062-nemo-v1-7-v1-mkmlizer: ║ ║
jic062-nemo-v1-7-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-nemo-v1-7-v1-mkmlizer: Downloaded to shared memory in 49.710s
jic062-nemo-v1-7-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpp5rdt2w1, device:0
jic062-nemo-v1-7-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
jic062-nemo-v1-7-v1-mkmlizer: quantized model in 35.064s
jic062-nemo-v1-7-v1-mkmlizer: Processed model jic062/Nemo-v1.7 in 84.774s
jic062-nemo-v1-7-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-nemo-v1-7-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-nemo-v1-7-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-nemo-v1-7-v1
jic062-nemo-v1-7-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-nemo-v1-7-v1/flywheel_model.0.safetensors
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-v1-7-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:10, 33.43it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:06, 56.11it/s] Loading 0: 6%|▌ | 20/363 [00:00<00:05, 57.25it/s] Loading 0: 7%|▋ | 26/363 [00:00<00:06, 52.76it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:07, 46.99it/s] Loading 0: 11%|█ | 40/363 [00:00<00:05, 56.10it/s] Loading 0: 13%|█▎ | 46/363 [00:00<00:05, 53.73it/s] Loading 0: 14%|█▍ | 52/363 [00:00<00:05, 52.37it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:05, 53.33it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 37.08it/s] Loading 0: 20%|█▉ | 72/363 [00:01<00:07, 41.45it/s] Loading 0: 21%|██▏ | 78/363 [00:01<00:06, 42.93it/s] Loading 0: 23%|██▎ | 83/363 [00:01<00:06, 43.73it/s] Loading 0: 25%|██▍ | 90/363 [00:01<00:05, 49.30it/s] Loading 0: 26%|██▋ | 96/363 [00:02<00:05, 48.72it/s] Loading 0: 28%|██▊ | 102/363 [00:02<00:05, 48.56it/s] Loading 0: 30%|███ | 110/363 [00:02<00:05, 49.23it/s] Loading 0: 32%|███▏ | 116/363 [00:02<00:05, 48.23it/s] Loading 0: 33%|███▎ | 121/363 [00:02<00:05, 46.18it/s] Loading 0: 35%|███▍ | 126/363 [00:02<00:05, 46.11it/s] Loading 0: 36%|███▋ | 132/363 [00:02<00:05, 44.37it/s] Loading 0: 38%|███▊ | 137/363 [00:02<00:05, 43.07it/s] Loading 0: 39%|███▉ | 142/363 [00:03<00:06, 34.10it/s] Loading 0: 40%|████ | 146/363 [00:03<00:06, 34.25it/s] Loading 0: 41%|████▏ | 150/363 [00:03<00:06, 33.49it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 40.05it/s] Loading 0: 45%|████▍ | 163/363 [00:03<00:04, 41.40it/s] Loading 0: 46%|████▋ | 168/363 [00:03<00:04, 41.77it/s] Loading 0: 48%|████▊ | 175/363 [00:03<00:03, 47.11it/s] Loading 0: 50%|████▉ | 181/363 [00:04<00:03, 45.84it/s] Loading 0: 51%|█████ | 186/363 [00:04<00:04, 41.70it/s] Loading 0: 53%|█████▎ | 192/363 [00:04<00:03, 45.56it/s] Loading 0: 54%|█████▍ | 197/363 [00:04<00:03, 46.44it/s] Loading 0: 56%|█████▌ | 203/363 [00:04<00:03, 42.05it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:03, 49.26it/s] Loading 0: 60%|█████▉ | 217/363 [00:04<00:03, 42.70it/s] Loading 0: 61%|██████ | 222/363 [00:04<00:03, 43.35it/s] Loading 0: 63%|██████▎ | 227/363 [00:05<00:04, 31.26it/s] Loading 0: 64%|██████▎ | 231/363 [00:05<00:04, 30.18it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 37.09it/s] Loading 0: 67%|██████▋ | 244/363 [00:05<00:02, 40.04it/s] Loading 0: 69%|██████▊ | 249/363 [00:05<00:02, 40.92it/s] Loading 0: 70%|███████ | 255/363 [00:05<00:02, 44.07it/s] Loading 0: 72%|███████▏ | 260/363 [00:05<00:02, 43.21it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 44.51it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:02, 44.44it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:02, 42.29it/s] Loading 0: 78%|███████▊ | 282/363 [00:06<00:01, 46.70it/s] Loading 0: 79%|███████▉ | 287/363 [00:06<00:01, 46.56it/s] Loading 0: 81%|████████ | 293/363 [00:06<00:01, 42.99it/s] Loading 0: 83%|████████▎ | 301/363 [00:06<00:01, 51.56it/s] Loading 0: 85%|████████▍ | 307/363 [00:13<00:19, 2.91it/s] Loading 0: 86%|████████▌ | 312/363 [00:13<00:13, 3.83it/s] Loading 0: 88%|████████▊ | 320/363 [00:13<00:07, 5.91it/s] Loading 0: 90%|████████▉ | 326/363 [00:13<00:04, 7.88it/s] Loading 0: 91%|█████████▏| 332/363 [00:14<00:02, 10.49it/s] Loading 0: 93%|█████████▎| 339/363 [00:14<00:01, 13.90it/s] Loading 0: 96%|█████████▌| 347/363 [00:14<00:00, 19.38it/s] Loading 0: 97%|█████████▋| 353/363 [00:14<00:00, 23.03it/s] Loading 0: 99%|█████████▉| 359/363 [00:14<00:00, 27.40it/s]
Job jic062-nemo-v1-7-v1-mkmlizer completed after 127.4s with status: succeeded
Stopping job with name jic062-nemo-v1-7-v1-mkmlizer
Pipeline stage MKMLizer completed in 138.85s
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
run pipeline stage %s
Running pipeline stage MKMLTemplater
Connection pool is full, discarding connection: %s. Connection pool size: %s
Pipeline stage MKMLTemplater completed in 1.74s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service jic062-nemo-v1-7-v1
Waiting for inference service jic062-nemo-v1-7-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
Inference service jic062-nemo-v1-7-v1 ready after 200.82969975471497s
Pipeline stage MKMLDeployer completed in 201.23s
run pipeline stage %s
Running pipeline stage StressChecker
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
HTTPSConnectionPool(host='guanaco-submitter.chai-research.com', port=443): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.6738884449005127s
Received healthy response to inference request in 3.122897148132324s
Received healthy response to inference request in 2.589320659637451s
Received healthy response to inference request in 4.729764461517334s
5 requests
1 failed requests
5th percentile: 2.6062342166900634
10th percentile: 2.6231477737426756
20th percentile: 2.6569748878479005
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
30th percentile: 2.763690185546875
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
40th percentile: 2.9432936668395997
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
50th percentile: 3.122897148132324
60th percentile: 3.765644073486328
70th percentile: 4.408390998840332
80th percentile: 7.8057924270629915
90th percentile: 13.957848358154298
95th percentile: 17.03387632369995
99th percentile: 19.494698696136474
mean time: 6.645155000686645
%s, retrying in %s seconds...
Received healthy response to inference request in 3.768622636795044s
Received healthy response to inference request in 2.09641695022583s
Received healthy response to inference request in 2.310994863510132s
Received healthy response to inference request in 1.7236812114715576s
Received healthy response to inference request in 1.9878439903259277s
5 requests
0 failed requests
5th percentile: 1.7765137672424316
10th percentile: 1.8293463230133056
20th percentile: 1.9350114345550538
30th percentile: 2.009558582305908
40th percentile: 2.0529877662658693
50th percentile: 2.09641695022583
60th percentile: 2.182248115539551
70th percentile: 2.2680792808532715
80th percentile: 2.6025204181671144
90th percentile: 3.185571527481079
95th percentile: 3.4770970821380613
99th percentile: 3.7103175258636476
mean time: 2.3775119304656984
Pipeline stage StressChecker completed in 143.11s
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 4.24s
Shutdown handler de-registered
jic062-nemo-v1-7_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 0.15s
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-nemo-v1-7-v1-profiler
Waiting for inference service jic062-nemo-v1-7-v1-profiler to be ready
Inference service jic062-nemo-v1-7-v1-profiler ready after 190.43565201759338s
Pipeline stage MKMLProfilerDeployer completed in 199.66s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/jic062-nemo-v1-7-v1-profiler-predictor-00001-deployment-56kb575:/code/chaiverse_profiler_1726892551 --namespace tenant-chaiml-guanaco
kubectl exec -it jic062-nemo-v1-7-v1-profiler-predictor-00001-deployment-56kb575 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726892551 && 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_1726892551/summary.json'
kubectl exec -it jic062-nemo-v1-7-v1-profiler-predictor-00001-deployment-56kb575 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726892551/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1188.25s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service jic062-nemo-v1-7-v1-profiler is running
Tearing down inference service jic062-nemo-v1-7-v1-profiler
Service jic062-nemo-v1-7-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 3.91s
Shutdown handler de-registered
jic062-nemo-v1-7_v1 status is now inactive due to auto deactivation removed underperforming models
jic062-nemo-v1-7_v1 status is now torndown due to DeploymentManager action