submission_id: zonemercy-virgo-edit-v5-1e5b1_v2
developer_uid: chai_backend_admin
best_of: 8
celo_rating: 1254.58
display_name: 0919v1-6
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: zonemercy/Virgo-Edit-v5-1e5b1
latencies: [{'batch_size': 1, 'throughput': 0.6156991414226565, 'latency_mean': 1.6240728425979614, 'latency_p50': 1.6144051551818848, 'latency_p90': 1.7954479932785035}, {'batch_size': 3, 'throughput': 1.077478148601245, 'latency_mean': 2.773519380092621, 'latency_p50': 2.786686062812805, 'latency_p90': 3.0085511684417723}, {'batch_size': 5, 'throughput': 1.2470216434383947, 'latency_mean': 3.9953466022014616, 'latency_p50': 3.9819530248641968, 'latency_p90': 4.468982267379761}, {'batch_size': 6, 'throughput': 1.263922594480482, 'latency_mean': 4.719791078567505, 'latency_p50': 4.71508526802063, 'latency_p90': 5.3459615230560305}, {'batch_size': 8, 'throughput': 1.259041141560765, 'latency_mean': 6.322519638538361, 'latency_p50': 6.332637548446655, 'latency_p90': 7.114299631118774}, {'batch_size': 10, 'throughput': 1.2179138884160805, 'latency_mean': 8.16641669511795, 'latency_p50': 8.243476033210754, 'latency_p90': 9.382959151268006}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: zonemercy/Virgo-Edit-v5-
model_name: 0919v1-6
model_num_parameters: 12772070400.0
model_repo: zonemercy/Virgo-Edit-v5-1e5b1
model_size: 13B
num_battles: 12244
num_wins: 6240
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 1.22
timestamp: 2024-09-19T13:54:20+00:00
us_pacific_date: 2024-09-19
win_ratio: 0.5096373734073832
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 zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer
Waiting for job on zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer to finish
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: ║ _____ __ __ ║
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: ║ /___/ ║
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: ║ ║
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: ║ Version: 0.10.1 ║
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: ║ https://mk1.ai ║
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: ║ ║
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: ║ The license key for the current software has been verified as ║
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: ║ belonging to: ║
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: ║ ║
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: ║ Chai Research Corp. ║
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: ║ ║
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: Downloaded to shared memory in 58.107s
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzurxx2m7, device:0
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: quantized model in 41.681s
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: Processed model zonemercy/Virgo-Edit-v5-1e5b1 in 99.789s
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-virgo-edit-v5-1e5b1-v2
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-virgo-edit-v5-1e5b1-v2/config.json
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-virgo-edit-v5-1e5b1-v2/special_tokens_map.json
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-virgo-edit-v5-1e5b1-v2/tokenizer_config.json
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-virgo-edit-v5-1e5b1-v2/tokenizer.json
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-virgo-edit-v5-1e5b1-v2/flywheel_model.0.safetensors
zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:16, 22.28it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:12, 27.54it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:14, 24.15it/s] Loading 0: 6%|▌ | 20/363 [00:00<00:10, 33.22it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:14, 23.86it/s] Loading 0: 7%|▋ | 27/363 [00:01<00:15, 22.40it/s] Loading 0: 9%|▊ | 31/363 [00:01<00:12, 25.76it/s] Loading 0: 9%|▉ | 34/363 [00:01<00:12, 25.51it/s] Loading 0: 11%|█ | 39/363 [00:01<00:11, 28.79it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:11, 27.37it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:10, 30.04it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:10, 28.29it/s] Loading 0: 15%|█▌ | 56/363 [00:02<00:10, 29.04it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:11, 25.52it/s] Loading 0: 18%|█▊ | 64/363 [00:02<00:13, 21.79it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:10, 28.58it/s] Loading 0: 21%|██ | 75/363 [00:02<00:10, 27.31it/s] Loading 0: 21%|██▏ | 78/363 [00:02<00:11, 25.49it/s] Loading 0: 23%|██▎ | 84/363 [00:03<00:09, 30.22it/s] Loading 0: 24%|██▍ | 88/363 [00:03<00:09, 29.29it/s] Loading 0: 26%|██▌ | 93/363 [00:03<00:08, 31.81it/s] Loading 0: 27%|██▋ | 97/363 [00:03<00:08, 30.04it/s] Loading 0: 28%|██▊ | 101/363 [00:03<00:10, 24.72it/s] Loading 0: 29%|██▊ | 104/363 [00:03<00:11, 21.71it/s] Loading 0: 31%|███ | 111/363 [00:04<00:08, 28.06it/s] Loading 0: 31%|███▏ | 114/363 [00:04<00:09, 25.86it/s] Loading 0: 33%|███▎ | 120/363 [00:04<00:07, 30.72it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:08, 29.75it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:07, 31.38it/s] Loading 0: 37%|███▋ | 133/363 [00:04<00:07, 29.11it/s] Loading 0: 38%|███▊ | 137/363 [00:04<00:07, 29.38it/s] Loading 0: 39%|███▉ | 142/363 [00:05<00:08, 25.57it/s] Loading 0: 40%|███▉ | 145/363 [00:05<00:09, 24.09it/s] Loading 0: 41%|████ | 149/363 [00:05<00:09, 22.77it/s] Loading 0: 43%|████▎ | 155/363 [00:05<00:06, 29.99it/s] Loading 0: 44%|████▍ | 159/363 [00:05<00:07, 26.38it/s] Loading 0: 45%|████▌ | 165/363 [00:06<00:06, 30.32it/s] Loading 0: 47%|████▋ | 169/363 [00:06<00:06, 28.73it/s] Loading 0: 48%|████▊ | 174/363 [00:06<00:06, 31.13it/s] Loading 0: 49%|████▉ | 178/363 [00:06<00:06, 29.88it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:07, 24.66it/s] Loading 0: 51%|█████ | 185/363 [00:06<00:08, 21.82it/s] Loading 0: 53%|█████▎ | 192/363 [00:07<00:05, 28.77it/s] Loading 0: 54%|█████▍ | 196/363 [00:07<00:05, 28.05it/s] Loading 0: 55%|█████▌ | 201/363 [00:07<00:05, 31.03it/s] Loading 0: 56%|█████▋ | 205/363 [00:07<00:05, 29.98it/s] Loading 0: 58%|█████▊ | 210/363 [00:07<00:04, 31.91it/s] Loading 0: 59%|█████▉ | 214/363 [00:07<00:05, 29.54it/s] Loading 0: 60%|██████ | 218/363 [00:07<00:04, 30.04it/s] Loading 0: 61%|██████▏ | 223/363 [00:08<00:05, 25.07it/s] Loading 0: 62%|██████▏ | 226/363 [00:08<00:05, 23.21it/s] Loading 0: 63%|██████▎ | 230/363 [00:08<00:06, 21.81it/s] Loading 0: 65%|██████▍ | 235/363 [00:08<00:04, 26.46it/s] Loading 0: 66%|██████▌ | 238/363 [00:08<00:04, 27.01it/s] Loading 0: 66%|██████▋ | 241/363 [00:08<00:04, 26.08it/s] Loading 0: 68%|██████▊ | 246/363 [00:09<00:04, 28.72it/s] Loading 0: 69%|██████▊ | 249/363 [00:09<00:04, 25.95it/s] Loading 0: 70%|███████ | 255/363 [00:09<00:03, 30.77it/s] Loading 0: 71%|███████▏ | 259/363 [00:09<00:03, 28.71it/s] Loading 0: 72%|███████▏ | 263/363 [00:09<00:04, 23.62it/s] Loading 0: 73%|███████▎ | 266/363 [00:09<00:04, 21.11it/s] Loading 0: 75%|███████▍ | 271/363 [00:10<00:03, 26.16it/s] Loading 0: 76%|███████▌ | 275/363 [00:10<00:03, 23.53it/s] Loading 0: 78%|███████▊ | 282/363 [00:10<00:02, 29.71it/s] Loading 0: 79%|███████▉ | 286/363 [00:10<00:02, 28.33it/s] Loading 0: 80%|████████ | 291/363 [00:10<00:02, 30.05it/s] Loading 0: 81%|████████▏ | 295/363 [00:10<00:02, 29.05it/s] Loading 0: 82%|████████▏ | 299/363 [00:10<00:02, 29.41it/s] Loading 0: 84%|████████▎ | 304/363 [00:11<00:02, 24.94it/s] Loading 0: 85%|████████▍ | 307/363 [00:11<00:02, 23.55it/s] Loading 0: 86%|████████▌ | 311/363 [00:11<00:02, 22.13it/s] Loading 0: 87%|████████▋ | 316/363 [00:11<00:01, 26.91it/s] Loading 0: 88%|████████▊ | 320/363 [00:11<00:01, 24.51it/s] Loading 0: 90%|█████████ | 327/363 [00:12<00:01, 30.35it/s] Loading 0: 91%|█████████ | 331/363 [00:12<00:01, 28.62it/s] Loading 0: 93%|█████████▎| 336/363 [00:12<00:00, 30.49it/s] Loading 0: 94%|█████████▎| 340/363 [00:12<00:00, 28.44it/s] Loading 0: 94%|█████████▍| 343/363 [00:12<00:00, 28.49it/s] Loading 0: 95%|█████████▌| 346/363 [00:19<00:10, 1.70it/s] Loading 0: 96%|█████████▌| 349/363 [00:19<00:06, 2.21it/s] Loading 0: 97%|█████████▋| 353/363 [00:20<00:03, 3.15it/s] Loading 0: 98%|█████████▊| 357/363 [00:20<00:01, 4.32it/s]
Job zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer completed after 124.06s with status: succeeded
Stopping job with name zonemercy-virgo-edit-v5-1e5b1-v2-mkmlizer
Pipeline stage MKMLizer completed in 126.22s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-virgo-edit-v5-1e5b1-v2
Waiting for inference service zonemercy-virgo-edit-v5-1e5b1-v2 to be ready
Inference service zonemercy-virgo-edit-v5-1e5b1-v2 ready after 191.07962083816528s
Pipeline stage MKMLDeployer completed in 191.41s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2215054035186768s
Received healthy response to inference request in 2.527174472808838s
Received healthy response to inference request in 1.6588475704193115s
Received healthy response to inference request in 1.5859224796295166s
Received healthy response to inference request in 1.5498335361480713s
5 requests
0 failed requests
5th percentile: 1.5570513248443603
10th percentile: 1.5642691135406495
20th percentile: 1.5787046909332276
30th percentile: 1.6005074977874756
40th percentile: 1.6296775341033936
50th percentile: 1.6588475704193115
60th percentile: 1.8839107036590577
70th percentile: 2.108973836898804
80th percentile: 2.282639217376709
90th percentile: 2.4049068450927735
95th percentile: 2.4660406589508055
99th percentile: 2.5149477100372315
mean time: 1.908656692504883
Pipeline stage StressChecker completed in 12.49s
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 5.13s
Shutdown handler de-registered
zonemercy-virgo-edit-v5-1e5b1_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 0.14s
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 zonemercy-virgo-edit-v5-1e5b1-v2-profiler
Waiting for inference service zonemercy-virgo-edit-v5-1e5b1-v2-profiler to be ready
Inference service zonemercy-virgo-edit-v5-1e5b1-v2-profiler ready after 200.48705744743347s
Pipeline stage MKMLProfilerDeployer completed in 200.89s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-virgo-editb0149b02653fccdf52a2e72ddcf8a871-deplortcxn:/code/chaiverse_profiler_1726754654 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-virgo-editb0149b02653fccdf52a2e72ddcf8a871-deplortcxn --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726754654 && 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_1726754654/summary.json'
kubectl exec -it zonemercy-virgo-editb0149b02653fccdf52a2e72ddcf8a871-deplortcxn --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726754654/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1157.31s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-virgo-edit-v5-1e5b1-v2-profiler is running
Tearing down inference service zonemercy-virgo-edit-v5-1e5b1-v2-profiler
Service zonemercy-virgo-edit-v5-1e5b1-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.01s
Shutdown handler de-registered
zonemercy-virgo-edit-v5-1e5b1_v2 status is now inactive due to auto deactivation removed underperforming models
Running pipeline stage MKMLModelDeleter
Service chaiml-albert-dpo-0912-v-1751-v2 has been torndown
Tearing down inference service chaiml-albert-dpo-0912-v-8296-v2
Checking if service chaiml-albert-dpo-0912-v-9673-v1 is running
40th percentile: 3.206769514083862
Cleaning model data from model cache
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of zonemercy-virgo-edit-v5-1e5b1_v2
Cleaning model data from S3
Pipeline stage MKMLDeleter completed in 53.53s
Service chaiml-albert-dpo-0912-v-8296-v2 has been torndown
Tearing down inference service chaiml-albert-dpo-0912-v-9673-v1
50th percentile: 3.2941057682037354
Checking if service zonemercy-cogent-nemo-v-3266-v11 is running
Deleting key chaiml-0916-intent-suppo-6584-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Running pipeline stage MKMLDeleter
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Cleaning model data from model cache
admin requested tearing down of blend_rofur_2024-10-03
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 66.07s
Service chaiml-albert-dpo-0912-v-9673-v1 has been torndown
60th percentile: 3.50522198677063
Tearing down inference service zonemercy-cogent-nemo-v-3266-v11
Deleting key chaiml-0916-intent-suppo-6584-v3/special_tokens_map.json from bucket guanaco-mkml-models
Checking if service zonemercy-elite-edit-v1-1e5-v1 is running
Running pipeline stage MKMLDeleter
run pipeline %s
run pipeline stage %s
run pipeline %s
Deleting key chaiml-0917-bot-dominant-6324-v5/config.json from bucket guanaco-mkml-models
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 86.49s
70th percentile: 3.7163382053375242
Service zonemercy-cogent-nemo-v-3266-v11 has been torndown
Deleting key chaiml-0916-intent-suppo-6584-v3/tokenizer.json from bucket guanaco-mkml-models
Tearing down inference service zonemercy-elite-edit-v1-1e5-v1
Checking if service zonemercy-elite-pref-v4-1e5-v1 is running
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline stage %s
Deleting key chaiml-0917-bot-dominant-6324-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
run pipeline %s
Cleaning model data from S3
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
80th percentile: 3.979185914993286
Pipeline stage MKMLDeleter completed in 105.02s
Deleting key chaiml-0916-intent-suppo-6584-v3/tokenizer_config.json from bucket guanaco-mkml-models
Service zonemercy-elite-edit-v1-1e5-v1 has been torndown
admin requested tearing down of chaiml-0917-bot-dominant_6324_v5
Tearing down inference service zonemercy-elite-pref-v4-1e5-v1
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLizer
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-0917-bot-dominant_6324_v5
Running pipeline stage MKMLModelDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline stage %s
Pipeline stage %s skipped, reason=%s
Pipeline stage MKMLDeleter completed in 71.47s
Running pipeline stage MKMLDeleter
run pipeline stage %s
Shutdown handler de-registered
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of zonemercy-virgo-edit-v5-1e5b1_v2
jic062-dpo-v1-9-nemo_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLModelDeleter completed in 85.36s
run pipeline %s
jic062-dpo-v1-9-nemo_v1 status is now torndown due to DeploymentManager action
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
zonemercy-virgo-edit-v5-1e5b1_v2 status is now torndown due to DeploymentManager action