submission_id: chaiml-virgo-edit-v1-1e5_v2
developer_uid: chai_backend_admin
best_of: 8
celo_rating: 1253.16
display_name: 0919v1-0
family_friendly_score: 0.0
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
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': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A5000': 1}
is_internal_developer: True
language_model: ChaiML/Virgo-Edit-v1-1e5
latencies: [{'batch_size': 1, 'throughput': 0.6152806537834583, 'latency_mean': 1.6252060961723327, 'latency_p50': 1.6255213022232056, 'latency_p90': 1.801904845237732}, {'batch_size': 3, 'throughput': 1.0623507223164348, 'latency_mean': 2.8092096865177156, 'latency_p50': 2.807545781135559, 'latency_p90': 3.108489680290222}, {'batch_size': 5, 'throughput': 1.2220707260251362, 'latency_mean': 4.075864751338958, 'latency_p50': 4.067276358604431, 'latency_p90': 4.573030710220337}, {'batch_size': 6, 'throughput': 1.237650196031913, 'latency_mean': 4.826239596605301, 'latency_p50': 4.837889313697815, 'latency_p90': 5.471385741233825}, {'batch_size': 8, 'throughput': 1.2322047888033618, 'latency_mean': 6.459537959098816, 'latency_p50': 6.490670561790466, 'latency_p90': 7.395546841621399}, {'batch_size': 10, 'throughput': 1.1838899977307316, 'latency_mean': 8.39556142926216, 'latency_p50': 8.431013226509094, 'latency_p90': 9.412282133102417}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: ChaiML/Virgo-Edit-v1-1e5
model_name: 0919v1-0
model_num_parameters: 12772070400.0
model_repo: ChaiML/Virgo-Edit-v1-1e5
model_size: 13B
num_battles: 14172
num_wins: 7197
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.19
timestamp: 2024-09-19T13:52:28+00:00
us_pacific_date: 2024-09-19
win_ratio: 0.5078323454699407
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-virgo-edit-v1-1e5-v2-mkmlizer
Waiting for job on chaiml-virgo-edit-v1-1e5-v2-mkmlizer to finish
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: ║ _____ __ __ ║
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: ║ /___/ ║
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: ║ ║
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: ║ Version: 0.10.1 ║
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: ║ ║
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: ║ belonging to: ║
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: ║ ║
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: ║ ║
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: Downloaded to shared memory in 87.032s
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnp45ffok, device:0
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: quantized model in 40.499s
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: Processed model ChaiML/Virgo-Edit-v1-1e5 in 127.532s
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-virgo-edit-v1-1e5-v2/special_tokens_map.json
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-virgo-edit-v1-1e5-v2/tokenizer_config.json
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-virgo-edit-v1-1e5-v2/tokenizer.json
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-virgo-edit-v1-1e5-v2/flywheel_model.0.safetensors
chaiml-virgo-edit-v1-1e5-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:14, 24.94it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:11, 30.80it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:13, 26.26it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:09, 37.10it/s] Loading 0: 7%|▋ | 26/363 [00:01<00:15, 22.19it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:13, 24.51it/s] Loading 0: 11%|█ | 39/363 [00:01<00:10, 29.96it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:10, 29.51it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:09, 31.75it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:10, 30.43it/s] Loading 0: 15%|█▌ | 56/363 [00:01<00:10, 30.68it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:11, 26.83it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:12, 23.66it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:09, 30.61it/s] Loading 0: 21%|██ | 75/363 [00:02<00:09, 29.80it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:09, 28.61it/s] Loading 0: 23%|██▎ | 84/363 [00:02<00:08, 31.11it/s] Loading 0: 24%|██▍ | 88/363 [00:03<00:09, 29.45it/s] Loading 0: 25%|██▌ | 92/363 [00:03<00:08, 31.71it/s] Loading 0: 26%|██▋ | 96/363 [00:03<00:09, 27.85it/s] Loading 0: 28%|██▊ | 101/363 [00:03<00:10, 24.94it/s] Loading 0: 29%|██▊ | 104/363 [00:03<00:11, 22.27it/s] Loading 0: 31%|███ | 111/363 [00:03<00:08, 29.10it/s] Loading 0: 32%|███▏ | 115/363 [00:04<00:08, 28.72it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:07, 31.28it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:08, 29.55it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:07, 32.10it/s] Loading 0: 37%|███▋ | 133/363 [00:04<00:07, 30.06it/s] Loading 0: 38%|███▊ | 137/363 [00:04<00:07, 29.89it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:08, 26.01it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:08, 24.88it/s] Loading 0: 41%|████ | 149/363 [00:05<00:09, 23.49it/s] Loading 0: 43%|████▎ | 156/363 [00:05<00:06, 30.03it/s] Loading 0: 44%|████▍ | 160/363 [00:05<00:06, 29.02it/s] Loading 0: 45%|████▌ | 165/363 [00:05<00:06, 31.42it/s] Loading 0: 47%|████▋ | 169/363 [00:05<00:06, 30.36it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:05, 32.45it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:05, 30.87it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:07, 24.70it/s] Loading 0: 51%|█████ | 185/363 [00:06<00:08, 22.09it/s] Loading 0: 53%|█████▎ | 192/363 [00:06<00:05, 29.13it/s] Loading 0: 54%|█████▍ | 196/363 [00:06<00:05, 28.38it/s] Loading 0: 55%|█████▌ | 201/363 [00:07<00:05, 31.30it/s] Loading 0: 56%|█████▋ | 205/363 [00:07<00:05, 30.27it/s] Loading 0: 58%|█████▊ | 210/363 [00:07<00:04, 32.44it/s] Loading 0: 59%|█████▉ | 214/363 [00:07<00:04, 30.37it/s] Loading 0: 60%|██████ | 218/363 [00:07<00:04, 30.41it/s] Loading 0: 61%|██████▏ | 223/363 [00:07<00:05, 25.94it/s] Loading 0: 62%|██████▏ | 226/363 [00:07<00:05, 24.86it/s] Loading 0: 63%|██████▎ | 230/363 [00:08<00:05, 23.89it/s] Loading 0: 65%|██████▌ | 237/363 [00:08<00:04, 30.79it/s] Loading 0: 66%|██████▋ | 241/363 [00:08<00:04, 29.92it/s] Loading 0: 68%|██████▊ | 246/363 [00:08<00:03, 32.48it/s] Loading 0: 69%|██████▉ | 250/363 [00:08<00:03, 31.03it/s] Loading 0: 70%|███████ | 255/363 [00:08<00:03, 32.51it/s] Loading 0: 71%|███████▏ | 259/363 [00:09<00:03, 30.82it/s] Loading 0: 72%|███████▏ | 263/363 [00:09<00:03, 25.16it/s] Loading 0: 73%|███████▎ | 266/363 [00:09<00:04, 22.56it/s] Loading 0: 75%|███████▌ | 273/363 [00:09<00:03, 29.62it/s] Loading 0: 76%|███████▋ | 277/363 [00:09<00:02, 29.45it/s] Loading 0: 78%|███████▊ | 282/363 [00:09<00:02, 32.38it/s] Loading 0: 79%|███████▉ | 286/363 [00:09<00:02, 31.01it/s] Loading 0: 80%|████████ | 291/363 [00:10<00:02, 33.17it/s] Loading 0: 81%|████████▏ | 295/363 [00:10<00:02, 31.39it/s] Loading 0: 82%|████████▏ | 299/363 [00:10<00:02, 30.84it/s] Loading 0: 84%|████████▎ | 304/363 [00:10<00:02, 26.10it/s] Loading 0: 85%|████████▍ | 307/363 [00:10<00:02, 24.80it/s] Loading 0: 86%|████████▌ | 311/363 [00:10<00:02, 23.61it/s] Loading 0: 88%|████████▊ | 318/363 [00:11<00:01, 30.36it/s] Loading 0: 89%|████████▊ | 322/363 [00:11<00:01, 29.11it/s] Loading 0: 90%|█████████ | 327/363 [00:11<00:01, 31.41it/s] Loading 0: 91%|█████████ | 331/363 [00:11<00:01, 29.66it/s] Loading 0: 93%|█████████▎| 336/363 [00:11<00:00, 31.44it/s] Loading 0: 94%|█████████▎| 340/363 [00:11<00:00, 29.87it/s] Loading 0: 95%|█████████▍| 344/363 [00:18<00:09, 1.98it/s] Loading 0: 96%|█████████▌| 348/363 [00:18<00:05, 2.67it/s] Loading 0: 97%|█████████▋| 353/363 [00:19<00:02, 3.87it/s] Loading 0: 98%|█████████▊| 357/363 [00:19<00:01, 5.03it/s]
Job chaiml-virgo-edit-v1-1e5-v2-mkmlizer completed after 155.85s with status: succeeded
Stopping job with name chaiml-virgo-edit-v1-1e5-v2-mkmlizer
Pipeline stage MKMLizer completed in 156.75s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-virgo-edit-v1-1e5-v2
Waiting for inference service chaiml-virgo-edit-v1-1e5-v2 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
Inference service chaiml-virgo-edit-v1-1e5-v2 ready after 180.89289379119873s
Pipeline stage MKMLDeployer completed in 181.92s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.63594126701355s
Received healthy response to inference request in 1.6124436855316162s
Received healthy response to inference request in 1.6255273818969727s
Received healthy response to inference request in 1.8197321891784668s
Received healthy response to inference request in 1.6212759017944336s
5 requests
0 failed requests
5th percentile: 1.6142101287841797
10th percentile: 1.6159765720367432
20th percentile: 1.6195094585418701
30th percentile: 1.6221261978149415
40th percentile: 1.623826789855957
50th percentile: 1.6255273818969727
60th percentile: 1.7032093048095702
70th percentile: 1.780891227722168
80th percentile: 1.9829740047454836
90th percentile: 2.3094576358795167
95th percentile: 2.472699451446533
99th percentile: 2.6032929039001464
mean time: 1.8629840850830077
Pipeline stage StressChecker completed in 10.49s
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 5.53s
Shutdown handler de-registered
chaiml-virgo-edit-v1-1e5_v2 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-virgo-edit-v1-1e5-v2-profiler
Waiting for inference service chaiml-virgo-edit-v1-1e5-v2-profiler to be ready
Inference service chaiml-virgo-edit-v1-1e5-v2-profiler ready after 200.44580793380737s
Pipeline stage MKMLProfilerDeployer completed in 200.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-virgo-edit-v1-1e5-v2-profiler-predictor-00001-deploq4mzc:/code/chaiverse_profiler_1726754554 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-virgo-edit-v1-1e5-v2-profiler-predictor-00001-deploq4mzc --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726754554 && 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_1726754554/summary.json'
kubectl exec -it chaiml-virgo-edit-v1-1e5-v2-profiler-predictor-00001-deploq4mzc --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726754554/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1176.96s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-virgo-edit-v1-1e5-v2-profiler is running
Tearing down inference service chaiml-virgo-edit-v1-1e5-v2-profiler
Service chaiml-virgo-edit-v1-1e5-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.38s
Shutdown handler de-registered
chaiml-virgo-edit-v1-1e5_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-virgo-edit-v1-1e5_v2 status is now torndown due to DeploymentManager action
Pipeline stage MKMLModelDeleter completed in 4.01s
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
run pipeline %s
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of cycy233-l3-p-v1-c2_v1
chaiml-virgo-edit-v1-1e5_v2 status is now torndown due to DeploymentManager action
Pipeline stage MKMLDeleter completed in 3.48s
chaiml-virgo-edit-v1-1e5_v1 status is now torndown due to DeploymentManager action
Running pipeline stage MKMLDeleter
Pipeline stage %s skipped, reason=%s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLModelDeleter
admin requested tearing down of cycy233-l3-p-v1-c2_v1
run pipeline stage %s
Shutdown handler de-registered
chaiml-virgo-edit-v1-1e5_v2 status is now torndown due to DeploymentManager action
Pipeline stage MKMLDeleter completed in 4.65s