developer_uid: chai_backend_admin
submission_id: zonemercy-virgo-edit-v1-1e5_v10
model_name: zonemercy-virgo-edit-v1-1e5_v10
model_group: zonemercy/Virgo-Edit-v1-
status: torndown
timestamp: 2024-09-11T01:51:02+00:00
num_battles: 11927
num_wins: 6137
celo_rating: 1253.95
family_friendly_score: 0.0
submission_type: basic
model_repo: zonemercy/Virgo-Edit-v1-1e5
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6110624111246534, 'latency_mean': 1.6364020645618438, 'latency_p50': 1.6331865787506104, 'latency_p90': 1.8037928819656373}, {'batch_size': 3, 'throughput': 1.0706711364397725, 'latency_mean': 2.797131165266037, 'latency_p50': 2.831800103187561, 'latency_p90': 3.0786449670791627}, {'batch_size': 5, 'throughput': 1.2236183169853991, 'latency_mean': 4.076263797283173, 'latency_p50': 4.1043713092803955, 'latency_p90': 4.5286478996276855}, {'batch_size': 6, 'throughput': 1.250972872962612, 'latency_mean': 4.773483377695084, 'latency_p50': 4.780811429023743, 'latency_p90': 5.343654489517212}, {'batch_size': 8, 'throughput': 1.2311607188172393, 'latency_mean': 6.440966438055039, 'latency_p50': 6.468402862548828, 'latency_p90': 7.354597592353821}, {'batch_size': 10, 'throughput': 1.207824705618566, 'latency_mean': 8.24301845908165, 'latency_p50': 8.219377279281616, 'latency_p90': 9.295857191085815}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: zonemercy-virgo-edit-v1-1e5_v10
is_internal_developer: True
language_model: zonemercy/Virgo-Edit-v1-1e5
model_size: 13B
ranking_group: single
throughput_3p7s: 1.19
us_pacific_date: 2024-09-10
win_ratio: 0.5145468265280456
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'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
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}
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-v1-1e5-v10-mkmlizer
Waiting for job on zonemercy-virgo-edit-v1-1e5-v10-mkmlizer to finish
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: ║ _____ __ __ ║
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: ║ /___/ ║
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: ║ ║
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: ║ Version: 0.10.1 ║
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: ║ https://mk1.ai ║
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: ║ ║
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: ║ The license key for the current software has been verified as ║
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: ║ belonging to: ║
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: ║ ║
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: ║ Chai Research Corp. ║
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: ║ ║
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: Downloaded to shared memory in 42.741s
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1yx00baf, device:0
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: quantized model in 38.826s
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: Processed model zonemercy/Virgo-Edit-v1-1e5 in 81.567s
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-virgo-edit-v1-1e5-v10
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-virgo-edit-v1-1e5-v10/config.json
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-virgo-edit-v1-1e5-v10/special_tokens_map.json
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-virgo-edit-v1-1e5-v10/tokenizer_config.json
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-virgo-edit-v1-1e5-v10/tokenizer.json
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-virgo-edit-v1-1e5-v10/flywheel_model.0.safetensors
zonemercy-virgo-edit-v1-1e5-v10-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:14, 24.38it/s] Loading 0: 3%|▎ | 10/363 [00:00<00:11, 31.44it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:12, 27.99it/s] Loading 0: 6%|▌ | 21/363 [00:00<00:08, 39.57it/s] Loading 0: 7%|▋ | 26/363 [00:00<00:14, 23.48it/s] Loading 0: 9%|▊ | 31/363 [00:01<00:11, 28.02it/s] Loading 0: 10%|▉ | 35/363 [00:01<00:10, 29.93it/s] Loading 0: 11%|█ | 39/363 [00:01<00:10, 31.78it/s] Loading 0: 12%|█▏ | 43/363 [00:01<00:10, 31.12it/s] Loading 0: 13%|█▎ | 48/363 [00:01<00:09, 33.53it/s] Loading 0: 14%|█▍ | 52/363 [00:01<00:09, 31.70it/s] Loading 0: 15%|█▌ | 56/363 [00:01<00:09, 32.39it/s] Loading 0: 17%|█▋ | 61/363 [00:02<00:10, 27.67it/s] Loading 0: 18%|█▊ | 65/363 [00:02<00:11, 25.53it/s] Loading 0: 20%|█▉ | 71/363 [00:02<00:09, 30.97it/s] Loading 0: 21%|██ | 75/363 [00:02<00:09, 30.91it/s] Loading 0: 22%|██▏ | 79/363 [00:02<00:09, 30.15it/s] Loading 0: 23%|██▎ | 84/363 [00:02<00:08, 32.69it/s] Loading 0: 24%|██▍ | 88/363 [00:02<00:08, 31.94it/s] Loading 0: 26%|██▌ | 93/363 [00:03<00:07, 34.79it/s] Loading 0: 27%|██▋ | 97/363 [00:03<00:07, 33.30it/s] Loading 0: 28%|██▊ | 101/363 [00:03<00:09, 26.75it/s] Loading 0: 29%|██▊ | 104/363 [00:03<00:11, 23.49it/s] Loading 0: 31%|███ | 111/363 [00:03<00:08, 30.55it/s] Loading 0: 32%|███▏ | 115/363 [00:03<00:08, 30.15it/s] Loading 0: 33%|███▎ | 120/363 [00:03<00:07, 33.33it/s] Loading 0: 34%|███▍ | 124/363 [00:04<00:07, 32.37it/s] Loading 0: 36%|███▌ | 129/363 [00:04<00:06, 34.57it/s] Loading 0: 37%|███▋ | 133/363 [00:04<00:06, 32.88it/s] Loading 0: 38%|███▊ | 137/363 [00:04<00:06, 32.85it/s] Loading 0: 39%|███▉ | 142/363 [00:04<00:07, 28.27it/s] Loading 0: 40%|███▉ | 145/363 [00:04<00:08, 26.10it/s] Loading 0: 41%|████ | 149/363 [00:05<00:08, 24.72it/s] Loading 0: 43%|████▎ | 156/363 [00:05<00:06, 32.21it/s] Loading 0: 44%|████▍ | 160/363 [00:05<00:06, 31.45it/s] Loading 0: 45%|████▌ | 165/363 [00:05<00:05, 33.55it/s] Loading 0: 47%|████▋ | 169/363 [00:05<00:06, 32.23it/s] Loading 0: 48%|████▊ | 174/363 [00:05<00:05, 34.96it/s] Loading 0: 49%|████▉ | 178/363 [00:05<00:05, 33.49it/s] Loading 0: 50%|█████ | 182/363 [00:06<00:06, 26.79it/s] Loading 0: 51%|█████ | 185/363 [00:06<00:07, 23.56it/s] Loading 0: 53%|█████▎ | 192/363 [00:06<00:05, 31.39it/s] Loading 0: 54%|█████▍ | 196/363 [00:06<00:05, 30.77it/s] Loading 0: 55%|█████▌ | 201/363 [00:06<00:04, 33.73it/s] Loading 0: 56%|█████▋ | 205/363 [00:06<00:04, 32.59it/s] Loading 0: 58%|█████▊ | 210/363 [00:06<00:04, 35.32it/s] Loading 0: 59%|█████▉ | 214/363 [00:06<00:04, 33.03it/s] Loading 0: 60%|██████ | 218/363 [00:07<00:04, 32.78it/s] Loading 0: 61%|██████▏ | 223/363 [00:07<00:04, 28.47it/s] Loading 0: 63%|██████▎ | 227/363 [00:07<00:04, 28.53it/s] Loading 0: 63%|██████▎ | 230/363 [00:07<00:05, 24.42it/s] Loading 0: 65%|██████▌ | 237/363 [00:07<00:03, 32.22it/s] Loading 0: 66%|██████▋ | 241/363 [00:07<00:03, 31.61it/s] Loading 0: 68%|██████▊ | 246/363 [00:08<00:03, 33.72it/s] Loading 0: 69%|██████▉ | 250/363 [00:08<00:03, 32.17it/s] Loading 0: 70%|███████ | 255/363 [00:08<00:03, 34.93it/s] Loading 0: 71%|███████▏ | 259/363 [00:08<00:03, 33.37it/s] Loading 0: 72%|███████▏ | 263/363 [00:08<00:03, 27.05it/s] Loading 0: 73%|███████▎ | 266/363 [00:08<00:04, 23.33it/s] Loading 0: 75%|███████▌ | 273/363 [00:08<00:02, 31.14it/s] Loading 0: 76%|███████▋ | 277/363 [00:09<00:02, 30.67it/s] Loading 0: 78%|███████▊ | 282/363 [00:09<00:02, 32.85it/s] Loading 0: 79%|███████▉ | 286/363 [00:09<00:02, 31.61it/s] Loading 0: 80%|████████ | 291/363 [00:09<00:02, 34.47it/s] Loading 0: 81%|████████▏ | 295/363 [00:09<00:02, 33.17it/s] Loading 0: 82%|████████▏ | 299/363 [00:09<00:01, 32.46it/s] Loading 0: 84%|████████▎ | 304/363 [00:09<00:02, 28.10it/s] Loading 0: 85%|████████▍ | 307/363 [00:10<00:02, 26.42it/s] Loading 0: 86%|████████▌ | 311/363 [00:10<00:02, 25.31it/s] Loading 0: 88%|████████▊ | 318/363 [00:10<00:01, 32.76it/s] Loading 0: 89%|████████▊ | 322/363 [00:10<00:01, 32.05it/s] Loading 0: 90%|█████████ | 327/363 [00:10<00:01, 34.66it/s] Loading 0: 91%|█████████ | 331/363 [00:10<00:00, 33.01it/s] Loading 0: 93%|█████████▎| 336/363 [00:10<00:00, 35.30it/s] Loading 0: 94%|█████████▎| 340/363 [00:11<00:00, 33.46it/s] Loading 0: 95%|█████████▍| 344/363 [00:17<00:09, 2.01it/s] Loading 0: 96%|█████████▌| 348/363 [00:18<00:05, 2.70it/s] Loading 0: 97%|█████████▋| 353/363 [00:18<00:02, 3.93it/s] Loading 0: 98%|█████████▊| 357/363 [00:18<00:01, 5.10it/s]
Job zonemercy-virgo-edit-v1-1e5-v10-mkmlizer completed after 109.28s with status: succeeded
Stopping job with name zonemercy-virgo-edit-v1-1e5-v10-mkmlizer
Pipeline stage MKMLizer completed in 110.74s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.43s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-virgo-edit-v1-1e5-v10
Waiting for inference service zonemercy-virgo-edit-v1-1e5-v10 to be ready
Inference service zonemercy-virgo-edit-v1-1e5-v10 ready after 30.5292010307312s
Pipeline stage MKMLDeployer completed in 31.78s
run pipeline stage %s
Running pipeline stage StressChecker
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 3.0815439224243164s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.2638180255889893s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 2.0643348693847656s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.8894681930541992s
HTTP Request: %s %s "%s %d %s"
Received healthy response to inference request in 1.9631829261779785s
5 requests
0 failed requests
5th percentile: 1.9042111396789552
10th percentile: 1.918954086303711
20th percentile: 1.9484399795532226
30th percentile: 1.983413314819336
40th percentile: 2.0238740921020506
50th percentile: 2.0643348693847656
60th percentile: 2.144128131866455
70th percentile: 2.2239213943481446
80th percentile: 2.427363204956055
90th percentile: 2.7544535636901855
95th percentile: 2.9179987430572507
99th percentile: 3.048834886550903
mean time: 2.2524695873260496
Pipeline stage StressChecker completed in 15.24s
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 3.67s
Shutdown handler de-registered
zonemercy-virgo-edit-v1-1e5_v10 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service zonemercy-virgo-edit-v1-1e5-v10-profiler
Waiting for inference service zonemercy-virgo-edit-v1-1e5-v10-profiler to be ready
Inference service zonemercy-virgo-edit-v1-1e5-v10-profiler ready after 160.3770444393158s
Pipeline stage MKMLProfilerDeployer completed in 160.75s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-virgo-edit3a2676405feadacefec4f00a42a5475b-deploznhrg:/code/chaiverse_profiler_1726019828 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-virgo-edit3a2676405feadacefec4f00a42a5475b-deploznhrg --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726019828 && 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_1726019828/summary.json'
kubectl exec -it zonemercy-virgo-edit3a2676405feadacefec4f00a42a5475b-deploznhrg --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726019828/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1171.97s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-virgo-edit-v1-1e5-v10-profiler is running
Tearing down inference service zonemercy-virgo-edit-v1-1e5-v10-profiler
Service zonemercy-virgo-edit-v1-1e5-v10-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.92s
Shutdown handler de-registered
zonemercy-virgo-edit-v1-1e5_v10 status is now inactive due to auto deactivation removed underperforming models
zonemercy-virgo-edit-v1-1e5_v10 status is now torndown due to DeploymentManager action