jic062-nemo-v1-3

developer_uid: chace9580

submission_id: jic062-nemo-v1-3_v1

model_name: jic062-nemo-v1-3_v1

model_group: jic062/Nemo-v1.3

status: torndown

timestamp: 2024-09-18T04:47:06+00:00

num_battles: 11830

num_wins: 5959

celo_rating: 1256.69

family_friendly_score: 0.0

submission_type: basic

model_repo: jic062/Nemo-v1.3

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6862873417482753, 'latency_mean': 1.4570219397544861, 'latency_p50': 1.4703376293182373, 'latency_p90': 1.6165760517120362}, {'batch_size': 3, 'throughput': 1.339425352391072, 'latency_mean': 2.234926314353943, 'latency_p50': 2.2071553468704224, 'latency_p90': 2.5391850233078004}, {'batch_size': 5, 'throughput': 1.5488582908478612, 'latency_mean': 3.2025904083251953, 'latency_p50': 3.2274383306503296, 'latency_p90': 3.5273834228515626}, {'batch_size': 6, 'throughput': 1.6111409860796484, 'latency_mean': 3.7092076396942137, 'latency_p50': 3.6968674659729004, 'latency_p90': 4.229552364349365}, {'batch_size': 8, 'throughput': 1.6004864027051189, 'latency_mean': 4.970616000890732, 'latency_p50': 4.937532424926758, 'latency_p90': 5.693983745574951}, {'batch_size': 10, 'throughput': 1.5345958457377928, 'latency_mean': 6.4651674711704255, 'latency_p50': 6.4226826429367065, 'latency_p90': 7.447162103652954}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: jic062-nemo-v1-3_v1

is_internal_developer: False

language_model: jic062/Nemo-v1.3

model_size: 13B

ranking_group: single

throughput_3p7s: 1.62

us_pacific_date: 2024-09-17

win_ratio: 0.5037193575655114

generation_params: {'temperature': 0.75, 'top_p': 1.0, 'min_p': 0.1, 'top_k': 80, '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}

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}

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-v1-3-v1-mkmlizer
Waiting for job on jic062-nemo-v1-3-v1-mkmlizer to finish
jic062-nemo-v1-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-nemo-v1-3-v1-mkmlizer: ║     _____            __           __                                ║
jic062-nemo-v1-3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-nemo-v1-3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-nemo-v1-3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-nemo-v1-3-v1-mkmlizer: ║       /___/                                                         ║
jic062-nemo-v1-3-v1-mkmlizer: ║                                                                     ║
jic062-nemo-v1-3-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
jic062-nemo-v1-3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-nemo-v1-3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-nemo-v1-3-v1-mkmlizer: ║                                                                     ║
jic062-nemo-v1-3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-nemo-v1-3-v1-mkmlizer: ║  belonging to:                                                      ║
jic062-nemo-v1-3-v1-mkmlizer: ║                                                                     ║
jic062-nemo-v1-3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-nemo-v1-3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-nemo-v1-3-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-nemo-v1-3-v1-mkmlizer: ║                                                                     ║
jic062-nemo-v1-3-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
jic062-nemo-v1-3-v1-mkmlizer: Downloaded to shared memory in 50.905s
jic062-nemo-v1-3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgejcrcyy, device:0
jic062-nemo-v1-3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-nemo-v1-3-v1-mkmlizer: quantized model in 35.772s
jic062-nemo-v1-3-v1-mkmlizer: Processed model jic062/Nemo-v1.3 in 86.678s
jic062-nemo-v1-3-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-nemo-v1-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-nemo-v1-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-nemo-v1-3-v1
jic062-nemo-v1-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-nemo-v1-3-v1/config.json
jic062-nemo-v1-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-nemo-v1-3-v1/special_tokens_map.json
jic062-nemo-v1-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-nemo-v1-3-v1/tokenizer_config.json
jic062-nemo-v1-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-nemo-v1-3-v1/tokenizer.json
jic062-nemo-v1-3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-nemo-v1-3-v1/flywheel_model.0.safetensors
jic062-nemo-v1-3-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.48it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 52.85it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 48.75it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 49.42it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 49.23it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 45.14it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 41.87it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:06, 46.29it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:06, 46.83it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 48.44it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 32.08it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 38.94it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 39.64it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:07, 38.41it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 42.52it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 42.69it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 42.30it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:05, 43.39it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 44.85it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 37.12it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:06, 36.06it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 40.91it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 42.06it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 42.11it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 42.75it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 27.54it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.19it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 36.50it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 37.52it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.68it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 40.41it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 36.59it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 43.97it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 43.08it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 44.40it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 44.04it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:03, 43.34it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 48.52it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 45.62it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:03, 46.70it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 33.42it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 33.19it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 37.48it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:03, 38.95it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 41.31it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 42.05it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 36.68it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 41.62it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 42.88it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 42.06it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 41.77it/s]
Loading 0:  79%|███████▊  | 285/363 [00:07<00:01, 41.62it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 46.64it/s]
Loading 0:  82%|████████▏ | 298/363 [00:07<00:01, 44.45it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:21,  2.79it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:15,  3.52it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:11,  4.48it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:05,  7.30it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:04,  9.45it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:02, 11.76it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 17.55it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 20.91it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 24.33it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 30.66it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 32.48it/s]
                                                            
Job jic062-nemo-v1-3-v1-mkmlizer completed after 116.55s with status: succeeded
Stopping job with name jic062-nemo-v1-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 117.87s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.23s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service jic062-nemo-v1-3-v1
Waiting for inference service jic062-nemo-v1-3-v1 to be ready
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
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
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
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
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
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-v1-3-v1 ready after 181.52945375442505s
Pipeline stage MKMLDeployer completed in 182.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.621845245361328s
Received healthy response to inference request in 1.9330801963806152s
Received healthy response to inference request in 2.748857259750366s
Received healthy response to inference request in 2.5552163124084473s
Received healthy response to inference request in 1.7028005123138428s
5 requests
0 failed requests
5th percentile: 1.7488564491271972
10th percentile: 1.7949123859405518
20th percentile: 1.8870242595672608
30th percentile: 2.0575074195861816
40th percentile: 2.3063618659973146
50th percentile: 2.5552163124084473
60th percentile: 2.6326726913452148
70th percentile: 2.7101290702819822
80th percentile: 2.9234548568725587
90th percentile: 3.2726500511169436
95th percentile: 3.4472476482391357
99th percentile: 3.5869257259368896
mean time: 2.5123599052429197
Pipeline stage StressChecker completed in 13.33s
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 4.53s
Shutdown handler de-registered
jic062-nemo-v1-3_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 0.13s
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-v1-3-v1-profiler
Waiting for inference service jic062-nemo-v1-3-v1-profiler to be ready
Inference service jic062-nemo-v1-3-v1-profiler ready after 190.43986201286316s
Pipeline stage MKMLProfilerDeployer completed in 190.81s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/jic062-nemo-v1-3-v1-profiler-predictor-00001-deployment-74f82jm:/code/chaiverse_profiler_1726635389 --namespace tenant-chaiml-guanaco
kubectl exec -it jic062-nemo-v1-3-v1-profiler-predictor-00001-deployment-74f82jm --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726635389 && 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_1726635389/summary.json'
kubectl exec -it jic062-nemo-v1-3-v1-profiler-predictor-00001-deployment-74f82jm --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726635389/summary.json'
Pipeline stage MKMLProfilerRunner completed in 955.58s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service jic062-nemo-v1-3-v1-profiler is running
Tearing down inference service jic062-nemo-v1-3-v1-profiler
Service jic062-nemo-v1-3-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.09s
Shutdown handler de-registered
jic062-nemo-v1-3_v1 status is now inactive due to auto deactivation removed underperforming models
jic062-nemo-v1-3_v1 status is now torndown due to DeploymentManager action