chaiml-graft-cogent-v1-a_9690

developer_uid: azuruce

submission_id: chaiml-graft-cogent-v1-a_9690_v1

model_name: 0815v1-7

model_group: ChaiML/Graft-Cogent-v1-A

status: torndown

timestamp: 2024-09-26T02:14:13+00:00

num_battles: 8031

num_wins: 4148

celo_rating: 1271.13

family_friendly_score: 0.5331256956931244

family_friendly_standard_error: 0.005629785683064078

submission_type: basic

model_repo: ChaiML/Graft-Cogent-v1-Acute-Nemo-v0-5e6ep1

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6302973405971555, 'latency_mean': 1.5863948214054107, 'latency_p50': 1.5950239896774292, 'latency_p90': 1.7640701055526733}, {'batch_size': 2, 'throughput': 0.8550920077042324, 'latency_mean': 2.3377232265472414, 'latency_p50': 2.341878890991211, 'latency_p90': 2.586395835876465}, {'batch_size': 3, 'throughput': 0.9388358642689422, 'latency_mean': 3.1917427587509155, 'latency_p50': 3.1977490186691284, 'latency_p90': 3.5154475927352906}, {'batch_size': 4, 'throughput': 0.950197522775823, 'latency_mean': 4.1945730078220365, 'latency_p50': 4.1747859716415405, 'latency_p90': 4.82175657749176}, {'batch_size': 5, 'throughput': 0.9067857472696704, 'latency_mean': 5.500395107269287, 'latency_p50': 5.532310128211975, 'latency_p90': 6.219492173194885}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: 0815v1-7

is_internal_developer: True

language_model: ChaiML/Graft-Cogent-v1-Acute-Nemo-v0-5e6ep1

model_size: 13B

ranking_group: single

throughput_3p7s: 0.95

us_pacific_date: 2024-09-25

win_ratio: 0.5164985680488109

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '###', 'Bot:', 'User:', 'You:', '<|im_end|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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 chaiml-graft-cogent-v1-a-9690-v1-mkmlizer
Waiting for job on chaiml-graft-cogent-v1-a-9690-v1-mkmlizer to finish
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: ║       /___/                                                         ║
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: ║                                                                     ║
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: ║                                                                     ║
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: ║                                                                     ║
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: ║                                                                     ║
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: Downloaded to shared memory in 92.479s
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpe6z5zsx4, device:0
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: quantized model in 41.414s
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: Processed model ChaiML/Graft-Cogent-v1-Acute-Nemo-v0-5e6ep1 in 133.894s
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-graft-cogent-v1-a-9690-v1
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-graft-cogent-v1-a-9690-v1/config.json
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-graft-cogent-v1-a-9690-v1/special_tokens_map.json
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-graft-cogent-v1-a-9690-v1/tokenizer_config.json
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-graft-cogent-v1-a-9690-v1/flywheel_model.0.safetensors
chaiml-graft-cogent-v1-a-9690-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.78it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:12, 27.69it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:13, 25.12it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 36.69it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:16, 20.58it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:13, 25.40it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:11, 27.68it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:10, 29.78it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:10, 29.26it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 32.43it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.83it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:09, 31.27it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 27.24it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:12, 23.45it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 30.51it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 30.33it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.75it/s]
Loading 0:  23%|██▎       | 84/363 [00:02<00:08, 32.27it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:08, 30.76it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:08, 33.30it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 31.50it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:10, 26.04it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:11, 22.62it/s]
Loading 0:  31%|███       | 111/363 [00:03<00:08, 29.97it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 29.02it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 31.95it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.85it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 33.69it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 32.06it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 32.21it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:08, 27.43it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 25.60it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:08, 23.83it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 30.93it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 30.45it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 32.72it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 31.68it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 34.37it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 32.82it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 26.84it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:07, 23.32it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:05, 30.53it/s]
Loading 0:  54%|█████▍    | 196/363 [00:06<00:05, 29.67it/s]
Loading 0:  55%|█████▌    | 201/363 [00:06<00:04, 32.82it/s]
Loading 0:  56%|█████▋    | 205/363 [00:06<00:04, 31.80it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 34.39it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:04, 32.82it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 33.12it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:04, 28.86it/s]
Loading 0:  63%|██████▎   | 227/363 [00:07<00:04, 28.42it/s]
Loading 0:  63%|██████▎   | 230/363 [00:07<00:05, 24.59it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:03, 32.12it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:03, 31.50it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 34.00it/s]
Loading 0:  69%|██████▉   | 250/363 [00:08<00:04, 27.40it/s]
Loading 0:  70%|██████▉   | 254/363 [00:08<00:03, 28.03it/s]
Loading 0:  71%|███████   | 258/363 [00:08<00:04, 21.94it/s]
Loading 0:  72%|███████▏  | 262/363 [00:09<00:04, 23.65it/s]
Loading 0:  73%|███████▎  | 265/363 [00:09<00:06, 14.00it/s]
Loading 0:  74%|███████▍  | 268/363 [00:09<00:06, 14.68it/s]
Loading 0:  75%|███████▍  | 271/363 [00:09<00:05, 16.19it/s]
Loading 0:  75%|███████▌  | 274/363 [00:10<00:05, 17.69it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:04, 17.48it/s]
Loading 0:  77%|███████▋  | 280/363 [00:10<00:04, 18.64it/s]
Loading 0:  78%|███████▊  | 283/363 [00:10<00:04, 19.79it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:04, 18.86it/s]
Loading 0:  80%|███████▉  | 289/363 [00:10<00:03, 19.92it/s]
Loading 0:  80%|████████  | 292/363 [00:10<00:03, 20.85it/s]
Loading 0:  81%|████████▏ | 295/363 [00:11<00:03, 19.95it/s]
Loading 0:  82%|████████▏ | 298/363 [00:11<00:03, 20.81it/s]
Loading 0:  83%|████████▎ | 302/363 [00:11<00:02, 24.75it/s]
Loading 0:  84%|████████▍ | 305/363 [00:11<00:04, 12.52it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:04, 13.20it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:03, 15.45it/s]
Loading 0:  88%|████████▊ | 318/363 [00:12<00:01, 23.50it/s]
Loading 0:  88%|████████▊ | 321/363 [00:12<00:01, 23.05it/s]
Loading 0:  90%|█████████ | 327/363 [00:12<00:01, 28.65it/s]
Loading 0:  91%|█████████ | 331/363 [00:12<00:01, 28.49it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 31.49it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 30.24it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  1.96it/s]
Loading 0:  96%|█████████▌| 348/363 [00:20<00:05,  2.65it/s]
Loading 0:  97%|█████████▋| 353/363 [00:20<00:02,  3.85it/s]
Loading 0:  98%|█████████▊| 357/363 [00:20<00:01,  4.96it/s]
                                                            
Job chaiml-graft-cogent-v1-a-9690-v1-mkmlizer completed after 153.15s with status: succeeded
Stopping job with name chaiml-graft-cogent-v1-a-9690-v1-mkmlizer
Pipeline stage MKMLizer completed in 154.55s
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 chaiml-graft-cogent-v1-a-9690-v1
Waiting for inference service chaiml-graft-cogent-v1-a-9690-v1 to be ready
Inference service chaiml-graft-cogent-v1-a-9690-v1 ready after 210.49911904335022s
Pipeline stage MKMLDeployer completed in 210.81s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0479753017425537s
Received healthy response to inference request in 1.9753227233886719s
Received healthy response to inference request in 1.828597068786621s
Received healthy response to inference request in 1.7444655895233154s
Received healthy response to inference request in 1.8314614295959473s
5 requests
0 failed requests
5th percentile: 1.7612918853759765
10th percentile: 1.7781181812286377
20th percentile: 1.81177077293396
30th percentile: 1.8291699409484863
40th percentile: 1.8303156852722169
50th percentile: 1.8314614295959473
60th percentile: 1.8890059471130372
70th percentile: 1.9465504646301268
80th percentile: 2.1898532390594485
90th percentile: 2.618914270401001
95th percentile: 2.833444786071777
99th percentile: 3.0050691986083984
mean time: 2.0855644226074217
Pipeline stage StressChecker completed in 11.00s
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 7.19s
Shutdown handler de-registered
chaiml-graft-cogent-v1-a_9690_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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-graft-cogent-v1-a-9690-v1-profiler
Waiting for inference service chaiml-graft-cogent-v1-a-9690-v1-profiler to be ready
Inference service chaiml-graft-cogent-v1-a-9690-v1-profiler ready after 210.47063732147217s
Pipeline stage MKMLProfilerDeployer completed in 210.88s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-graft-cogent-b6cbd25be02f157b595b159fd646827a-deplomfq6z:/code/chaiverse_profiler_1727317496 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-graft-cogent-b6cbd25be02f157b595b159fd646827a-deplomfq6z --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727317496 && 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_1727317496/summary.json'
kubectl exec -it chaiml-graft-cogent-b6cbd25be02f157b595b159fd646827a-deplomfq6z --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727317496/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1200.93s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-graft-cogent-v1-a-9690-v1-profiler is running
Tearing down inference service chaiml-graft-cogent-v1-a-9690-v1-profiler
Service chaiml-graft-cogent-v1-a-9690-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.28s
Shutdown handler de-registered
chaiml-graft-cogent-v1-a_9690_v1 status is now inactive due to auto deactivation removed underperforming models
Shutdown handler de-registered
chaiml-graft-cogent-v1-a_9690_v1 status is now torndown due to DeploymentManager action