jic062-dpo-v1-3-nemo

submission_id: jic062-dpo-v1-3-nemo_v1

developer_uid: chace9580

best_of: 8

celo_rating: 1232.77

display_name: jic062-dpo-v1-3-nemo_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': 0.75, '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/dpo-v1.3-Nemo

latencies: [{'batch_size': 1, 'throughput': 0.6944579316369992, 'latency_mean': 1.439909384250641, 'latency_p50': 1.444454550743103, 'latency_p90': 1.5938768148422242}, {'batch_size': 3, 'throughput': 1.3482498252565518, 'latency_mean': 2.2174251639842986, 'latency_p50': 2.221012830734253, 'latency_p90': 2.4668855905532836}, {'batch_size': 5, 'throughput': 1.5882380540319903, 'latency_mean': 3.137662442922592, 'latency_p50': 3.1381150484085083, 'latency_p90': 3.537899708747864}, {'batch_size': 6, 'throughput': 1.6459884148748556, 'latency_mean': 3.6246847784519196, 'latency_p50': 3.6564189195632935, 'latency_p90': 4.060385847091675}, {'batch_size': 8, 'throughput': 1.6309501161163789, 'latency_mean': 4.868891962766647, 'latency_p50': 4.86676025390625, 'latency_p90': 5.493939638137817}, {'batch_size': 10, 'throughput': 1.5700528605857258, 'latency_mean': 6.322702369689941, 'latency_p50': 6.314559102058411, 'latency_p90': 7.201911211013794}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: jic062/dpo-v1.3-Nemo

model_name: jic062-dpo-v1-3-nemo_v1

model_num_parameters: 12772070400.0

model_repo: jic062/dpo-v1.3-Nemo

model_size: 13B

num_battles: 10660

num_wins: 5157

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 1.65

timestamp: 2024-09-12T02:56:38+00:00

us_pacific_date: 2024-09-11

win_ratio: 0.48377110694183867

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-dpo-v1-3-nemo-v1-mkmlizer
Waiting for job on jic062-dpo-v1-3-nemo-v1-mkmlizer to finish
jic062-dpo-v1-3-nemo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-dpo-v1-3-nemo-v1-mkmlizer: ║     _____            __           __                                ║
jic062-dpo-v1-3-nemo-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-dpo-v1-3-nemo-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-dpo-v1-3-nemo-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-dpo-v1-3-nemo-v1-mkmlizer: ║       /___/                                                         ║
jic062-dpo-v1-3-nemo-v1-mkmlizer: ║                                                                     ║
jic062-dpo-v1-3-nemo-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
jic062-dpo-v1-3-nemo-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-dpo-v1-3-nemo-v1-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-dpo-v1-3-nemo-v1-mkmlizer: ║                                                                     ║
jic062-dpo-v1-3-nemo-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-dpo-v1-3-nemo-v1-mkmlizer: ║  belonging to:                                                      ║
jic062-dpo-v1-3-nemo-v1-mkmlizer: ║                                                                     ║
jic062-dpo-v1-3-nemo-v1-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-dpo-v1-3-nemo-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-dpo-v1-3-nemo-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-dpo-v1-3-nemo-v1-mkmlizer: ║                                                                     ║
jic062-dpo-v1-3-nemo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-dpo-v1-3-nemo-v1-mkmlizer: Downloaded to shared memory in 44.879s
jic062-dpo-v1-3-nemo-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpfw935wu_, device:0
jic062-dpo-v1-3-nemo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-dpo-v1-3-nemo-v1-mkmlizer: quantized model in 35.328s
jic062-dpo-v1-3-nemo-v1-mkmlizer: Processed model jic062/dpo-v1.3-Nemo in 80.207s
jic062-dpo-v1-3-nemo-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-dpo-v1-3-nemo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-dpo-v1-3-nemo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-dpo-v1-3-nemo-v1
jic062-dpo-v1-3-nemo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-dpo-v1-3-nemo-v1/special_tokens_map.json
jic062-dpo-v1-3-nemo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-dpo-v1-3-nemo-v1/config.json
jic062-dpo-v1-3-nemo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-dpo-v1-3-nemo-v1/tokenizer_config.json
jic062-dpo-v1-3-nemo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-dpo-v1-3-nemo-v1/tokenizer.json
jic062-dpo-v1-3-nemo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-dpo-v1-3-nemo-v1/flywheel_model.0.safetensors
jic062-dpo-v1-3-nemo-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 34.13it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 53.31it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.12it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.26it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 49.47it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 46.50it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 45.54it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 50.52it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 47.32it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.47it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.88it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 41.17it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 40.72it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 41.08it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 46.32it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 44.33it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 44.06it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 49.91it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 44.82it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 43.99it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 47.94it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:05, 45.26it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 44.10it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 33.42it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 34.77it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 34.32it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 39.80it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 40.12it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 41.85it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 43.72it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 35.55it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 42.95it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 44.20it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 44.70it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 43.06it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 42.67it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 47.26it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 47.89it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:03, 44.13it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 32.49it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 32.14it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 37.86it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:03, 39.97it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 41.53it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 40.17it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 40.15it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 44.51it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 43.72it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 44.49it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 42.92it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 40.94it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 46.03it/s]
Loading 0:  82%|████████▏ | 298/363 [00:07<00:01, 44.12it/s]
Loading 0:  83%|████████▎ | 303/363 [00:07<00:01, 44.15it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:21,  2.56it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:15,  3.29it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:08,  5.37it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:05,  7.32it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.39it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.36it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 16.82it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 20.04it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 26.32it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.60it/s]
                                                            
Job jic062-dpo-v1-3-nemo-v1-mkmlizer completed after 104.33s with status: succeeded
Stopping job with name jic062-dpo-v1-3-nemo-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.22s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service jic062-dpo-v1-3-nemo-v1
Waiting for inference service jic062-dpo-v1-3-nemo-v1 to be ready
Inference service jic062-dpo-v1-3-nemo-v1 ready after 170.70582389831543s
Pipeline stage MKMLDeployer completed in 171.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6443676948547363s
Received healthy response to inference request in 15.152331590652466s
Received healthy response to inference request in 1.609349012374878s
Received healthy response to inference request in 1.7557957172393799s
Received healthy response to inference request in 2.187499761581421s
5 requests
0 failed requests
5th percentile: 1.6386383533477784
10th percentile: 1.6679276943206787
20th percentile: 1.7265063762664794
30th percentile: 1.842136526107788
40th percentile: 2.0148181438446047
50th percentile: 2.187499761581421
60th percentile: 2.370246934890747
70th percentile: 2.5529941082000733
80th percentile: 5.145960474014284
90th percentile: 10.149146032333375
95th percentile: 12.650738811492918
99th percentile: 14.652013034820556
mean time: 4.669868755340576
Pipeline stage StressChecker completed in 23.94s
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 4.37s
Shutdown handler de-registered
jic062-dpo-v1-3-nemo_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service jic062-dpo-v1-3-nemo-v1-profiler
Waiting for inference service jic062-dpo-v1-3-nemo-v1-profiler to be ready
Inference service jic062-dpo-v1-3-nemo-v1-profiler ready after 170.42863082885742s
Pipeline stage MKMLProfilerDeployer completed in 170.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/jic062-dpo-v1-3-nemo-v1-profiler-predictor-00001-deploymen7x7lc:/code/chaiverse_profiler_1726110326 --namespace tenant-chaiml-guanaco
kubectl exec -it jic062-dpo-v1-3-nemo-v1-profiler-predictor-00001-deploymen7x7lc --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726110326 && 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_1726110326/summary.json'
kubectl exec -it jic062-dpo-v1-3-nemo-v1-profiler-predictor-00001-deploymen7x7lc --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726110326/summary.json'
Pipeline stage MKMLProfilerRunner completed in 938.96s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service jic062-dpo-v1-3-nemo-v1-profiler is running
Tearing down inference service jic062-dpo-v1-3-nemo-v1-profiler
Service jic062-dpo-v1-3-nemo-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.00s
Shutdown handler de-registered
jic062-dpo-v1-3-nemo_v1 status is now inactive due to auto deactivation removed underperforming models
jic062-dpo-v1-3-nemo_v1 status is now torndown due to DeploymentManager action