developer_uid: zonemercy
submission_id: zonemercy-vingt-deux-v1-1e5_v2
model_name: zonemercy-vingt-deux-v1-1e5_v2
model_group: zonemercy/Vingt-Deux-v1-
status: torndown
timestamp: 2024-09-24T11:25:04+00:00
num_battles: 5614
num_wins: 2745
celo_rating: 1245.84
family_friendly_score: 0.0
submission_type: basic
model_repo: zonemercy/Vingt-Deux-v1-1e5
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.3836068039040047, 'latency_mean': 2.606773419380188, 'latency_p50': 2.589654803276062, 'latency_p90': 2.894978880882263}, {'batch_size': 2, 'throughput': 0.6058322057260922, 'latency_mean': 3.298228219747543, 'latency_p50': 3.3084954023361206, 'latency_p90': 3.6527648687362673}, {'batch_size': 3, 'throughput': 0.7541734891772094, 'latency_mean': 3.955590329170227, 'latency_p50': 4.000321269035339, 'latency_p90': 4.314647746086121}, {'batch_size': 4, 'throughput': 0.8879485925274566, 'latency_mean': 4.472525690793991, 'latency_p50': 4.455906391143799, 'latency_p90': 4.937253212928772}, {'batch_size': 5, 'throughput': 0.9777121356907157, 'latency_mean': 5.084086667299271, 'latency_p50': 5.057344317436218, 'latency_p90': 5.735641312599182}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: zonemercy-vingt-deux-v1-1e5_v2
is_internal_developer: True
language_model: zonemercy/Vingt-Deux-v1-1e5
model_size: 22B
ranking_group: single
throughput_3p7s: 0.71
us_pacific_date: 2024-09-24
win_ratio: 0.4889561809761311
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|>', '<|eot_id|>'], '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-vingt-deux-v1-1e5-v2-mkmlizer
Waiting for job on zonemercy-vingt-deux-v1-1e5-v2-mkmlizer to finish
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: ║ _____ __ __ ║
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: ║ /___/ ║
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: ║ ║
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: ║ Version: 0.10.1 ║
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: ║ https://mk1.ai ║
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: ║ ║
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: ║ The license key for the current software has been verified as ║
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: ║ belonging to: ║
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: ║ ║
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: ║ Chai Research Corp. ║
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: ║ ║
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: Downloaded to shared memory in 50.255s
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2abv8msn, device:0
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: quantized model in 42.158s
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: Processed model zonemercy/Vingt-Deux-v1-1e5 in 92.413s
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-vingt-deux-v1-1e5-v2
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v1-1e5-v2/special_tokens_map.json
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v1-1e5-v2/config.json
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v1-1e5-v2/tokenizer_config.json
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v1-1e5-v2/tokenizer.json
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v1-1e5-v2/flywheel_model.1.safetensors
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v1-1e5-v2/flywheel_model.0.safetensors
zonemercy-vingt-deux-v1-1e5-v2-mkmlizer: Loading 0: 0%| | 0/507 [00:00<?, ?it/s] Loading 0: 1%| | 5/507 [00:00<00:17, 28.86it/s] Loading 0: 2%|▏ | 12/507 [00:00<00:11, 44.38it/s] Loading 0: 3%|▎ | 17/507 [00:00<00:11, 41.79it/s] Loading 0: 4%|▍ | 22/507 [00:00<00:11, 41.81it/s] Loading 0: 5%|▌ | 27/507 [00:00<00:11, 43.09it/s] Loading 0: 6%|▋ | 32/507 [00:00<00:13, 35.79it/s] Loading 0: 8%|▊ | 39/507 [00:00<00:10, 43.31it/s] Loading 0: 9%|▊ | 44/507 [00:01<00:11, 41.01it/s] Loading 0: 10%|▉ | 49/507 [00:01<00:12, 35.47it/s] Loading 0: 10%|█ | 53/507 [00:01<00:16, 27.28it/s] Loading 0: 11%|█ | 57/507 [00:01<00:16, 27.19it/s] Loading 0: 12%|█▏ | 63/507 [00:01<00:13, 32.52it/s] Loading 0: 13%|█▎ | 67/507 [00:01<00:13, 33.15it/s] Loading 0: 14%|█▍ | 73/507 [00:02<00:12, 35.45it/s] Loading 0: 16%|█▌ | 80/507 [00:02<00:11, 37.84it/s] Loading 0: 17%|█▋ | 87/507 [00:02<00:09, 43.35it/s] Loading 0: 18%|█▊ | 92/507 [00:02<00:09, 41.50it/s] Loading 0: 19%|█▉ | 97/507 [00:02<00:10, 40.55it/s] Loading 0: 20%|██ | 102/507 [00:02<00:09, 41.51it/s] Loading 0: 21%|██ | 107/507 [00:02<00:11, 34.90it/s] Loading 0: 22%|██▏ | 113/507 [00:03<00:12, 30.59it/s] Loading 0: 23%|██▎ | 117/507 [00:03<00:12, 30.18it/s] Loading 0: 24%|██▍ | 122/507 [00:03<00:12, 30.57it/s] Loading 0: 25%|██▌ | 129/507 [00:03<00:10, 37.34it/s] Loading 0: 26%|██▋ | 134/507 [00:03<00:10, 36.73it/s] Loading 0: 27%|██▋ | 139/507 [00:03<00:09, 37.43it/s] Loading 0: 28%|██▊ | 143/507 [00:03<00:09, 37.55it/s] Loading 0: 29%|██▉ | 148/507 [00:04<00:09, 38.90it/s] Loading 0: 30%|███ | 153/507 [00:04<00:08, 40.80it/s] Loading 0: 31%|███ | 158/507 [00:04<00:10, 34.65it/s] Loading 0: 32%|███▏ | 164/507 [00:04<00:08, 40.31it/s] Loading 0: 33%|███▎ | 169/507 [00:04<00:10, 32.21it/s] Loading 0: 34%|███▍ | 173/507 [00:04<00:10, 33.18it/s] Loading 0: 35%|███▍ | 177/507 [00:04<00:10, 30.90it/s] Loading 0: 36%|███▌ | 181/507 [00:05<00:09, 32.93it/s] Loading 0: 36%|███▋ | 185/507 [00:05<00:10, 31.27it/s] Loading 0: 38%|███▊ | 192/507 [00:05<00:07, 39.53it/s] Loading 0: 39%|███▉ | 197/507 [00:05<00:07, 39.52it/s] Loading 0: 40%|███▉ | 202/507 [00:05<00:07, 40.29it/s] Loading 0: 41%|████ | 207/507 [00:05<00:07, 42.63it/s] Loading 0: 42%|████▏ | 212/507 [00:05<00:08, 36.20it/s] Loading 0: 43%|████▎ | 218/507 [00:05<00:06, 41.31it/s] Loading 0: 44%|████▍ | 223/507 [00:06<00:07, 37.18it/s] Loading 0: 45%|████▍ | 227/507 [00:06<00:09, 31.02it/s] Loading 0: 46%|████▌ | 231/507 [00:06<00:09, 30.13it/s] Loading 0: 47%|████▋ | 237/507 [00:06<00:07, 34.96it/s] Loading 0: 48%|████▊ | 241/507 [00:06<00:07, 34.91it/s] Loading 0: 49%|████▊ | 246/507 [00:06<00:06, 37.37it/s] Loading 0: 49%|████▉ | 250/507 [00:06<00:07, 36.41it/s] Loading 0: 50%|█████ | 255/507 [00:07<00:06, 38.51it/s] Loading 0: 51%|█████ | 259/507 [00:07<00:06, 37.14it/s] Loading 0: 52%|█████▏ | 264/507 [00:07<00:06, 39.29it/s] Loading 0: 53%|█████▎ | 268/507 [00:07<00:06, 37.41it/s] Loading 0: 54%|█████▍ | 273/507 [00:07<00:05, 39.83it/s] Loading 0: 55%|█████▍ | 278/507 [00:07<00:05, 39.63it/s] Loading 0: 56%|█████▌ | 283/507 [00:07<00:05, 39.27it/s] Loading 0: 57%|█████▋ | 287/507 [00:08<00:08, 25.52it/s] Loading 0: 58%|█████▊ | 293/507 [00:08<00:07, 28.89it/s] Loading 0: 59%|█████▉ | 299/507 [00:22<00:07, 28.89it/s] Loading 0: 59%|█████▉ | 300/507 [00:22<02:43, 1.27it/s] Loading 0: 60%|█████▉ | 302/507 [00:22<02:22, 1.44it/s] Loading 0: 61%|██████ | 307/507 [00:22<01:36, 2.08it/s] Loading 0: 61%|██████ | 310/507 [00:23<01:16, 2.58it/s] Loading 0: 62%|██████▏ | 314/507 [00:23<00:54, 3.54it/s] Loading 0: 63%|██████▎ | 319/507 [00:23<00:36, 5.16it/s] Loading 0: 64%|██████▍ | 324/507 [00:23<00:25, 7.30it/s] Loading 0: 65%|██████▍ | 328/507 [00:23<00:19, 9.35it/s] Loading 0: 65%|██████▌ | 332/507 [00:23<00:14, 11.85it/s] Loading 0: 66%|██████▋ | 336/507 [00:23<00:11, 14.83it/s] Loading 0: 67%|██████▋ | 340/507 [00:23<00:11, 14.93it/s] Loading 0: 68%|██████▊ | 344/507 [00:24<00:09, 17.73it/s] Loading 0: 69%|██████▊ | 348/507 [00:24<00:08, 19.83it/s] Loading 0: 70%|██████▉ | 354/507 [00:24<00:05, 26.23it/s] Loading 0: 71%|███████ | 358/507 [00:24<00:05, 27.93it/s] Loading 0: 72%|███████▏ | 363/507 [00:24<00:04, 31.97it/s] Loading 0: 72%|███████▏ | 367/507 [00:24<00:04, 32.29it/s] Loading 0: 73%|███████▎ | 372/507 [00:24<00:03, 35.64it/s] Loading 0: 74%|███████▍ | 376/507 [00:24<00:03, 35.23it/s] Loading 0: 75%|███████▌ | 381/507 [00:24<00:03, 38.68it/s] Loading 0: 76%|███████▌ | 386/507 [00:25<00:03, 39.48it/s] Loading 0: 77%|███████▋ | 391/507 [00:25<00:03, 34.93it/s] Loading 0: 78%|███████▊ | 395/507 [00:25<00:04, 27.27it/s] Loading 0: 79%|███████▉ | 401/507 [00:25<00:03, 29.42it/s] Loading 0: 80%|████████ | 408/507 [00:25<00:02, 35.72it/s] Loading 0: 81%|████████▏ | 412/507 [00:25<00:02, 34.42it/s] Loading 0: 82%|████████▏ | 417/507 [00:26<00:02, 36.90it/s] Loading 0: 83%|████████▎ | 421/507 [00:26<00:02, 35.51it/s] Loading 0: 84%|████████▍ | 426/507 [00:26<00:02, 37.48it/s] Loading 0: 85%|████████▍ | 430/507 [00:26<00:02, 36.57it/s] Loading 0: 86%|████████▌ | 435/507 [00:26<00:01, 39.55it/s] Loading 0: 87%|████████▋ | 440/507 [00:26<00:01, 40.15it/s] Loading 0: 88%|████████▊ | 445/507 [00:26<00:01, 40.60it/s] Loading 0: 89%|████████▉ | 450/507 [00:26<00:01, 41.97it/s] Loading 0: 90%|████████▉ | 455/507 [00:29<00:08, 6.43it/s] Loading 0: 91%|█████████ | 459/507 [00:29<00:05, 8.04it/s] Loading 0: 92%|█████████▏| 465/507 [00:29<00:03, 11.19it/s] Loading 0: 93%|█████████▎| 472/507 [00:29<00:02, 16.01it/s] Loading 0: 94%|█████████▍| 477/507 [00:29<00:01, 18.99it/s] Loading 0: 95%|█████████▌| 482/507 [00:29<00:01, 22.30it/s] Loading 0: 96%|█████████▌| 486/507 [00:29<00:00, 24.80it/s] Loading 0: 97%|█████████▋| 490/507 [00:30<00:00, 27.38it/s] Loading 0: 97%|█████████▋| 494/507 [00:30<00:00, 29.12it/s] Loading 0: 98%|█████████▊| 499/507 [00:30<00:00, 32.60it/s] Loading 0: 99%|█████████▉| 503/507 [00:30<00:00, 33.29it/s]
Job zonemercy-vingt-deux-v1-1e5-v2-mkmlizer completed after 124.67s with status: succeeded
Stopping job with name zonemercy-vingt-deux-v1-1e5-v2-mkmlizer
Pipeline stage MKMLizer completed in 125.57s
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 zonemercy-vingt-deux-v1-1e5-v2
Waiting for inference service zonemercy-vingt-deux-v1-1e5-v2 to be ready
Inference service zonemercy-vingt-deux-v1-1e5-v2 ready after 202.54178667068481s
Pipeline stage MKMLDeployer completed in 202.86s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9859015941619873s
Received healthy response to inference request in 3.0353634357452393s
Received healthy response to inference request in 3.1336145401000977s
Received healthy response to inference request in 3.8212811946868896s
Received healthy response to inference request in 5.193262577056885s
5 requests
0 failed requests
5th percentile: 2.9957939624786376
10th percentile: 3.005686330795288
20th percentile: 3.025471067428589
30th percentile: 3.055013656616211
40th percentile: 3.0943140983581543
50th percentile: 3.1336145401000977
60th percentile: 3.4086812019348143
70th percentile: 3.683747863769531
80th percentile: 4.095677471160889
90th percentile: 4.6444700241088865
95th percentile: 4.918866300582885
99th percentile: 5.138383321762085
mean time: 3.6338846683502197
Pipeline stage StressChecker completed in 18.81s
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 6.66s
Shutdown handler de-registered
zonemercy-vingt-deux-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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service zonemercy-vingt-deux-v1-1e5-v2-profiler
Waiting for inference service zonemercy-vingt-deux-v1-1e5-v2-profiler to be ready
Inference service zonemercy-vingt-deux-v1-1e5-v2-profiler ready after 200.45490217208862s
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/zonemercy-vingt-deuxf8fbc320b905f37a7fe362cc49af53a1-deploc55x5:/code/chaiverse_profiler_1727177703 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-vingt-deuxf8fbc320b905f37a7fe362cc49af53a1-deploc55x5 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727177703 && 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_1727177703/summary.json'
kubectl exec -it zonemercy-vingt-deuxf8fbc320b905f37a7fe362cc49af53a1-deploc55x5 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727177703/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1550.91s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-vingt-deux-v1-1e5-v2-profiler is running
Tearing down inference service zonemercy-vingt-deux-v1-1e5-v2-profiler
Service zonemercy-vingt-deux-v1-1e5-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.08s
Shutdown handler de-registered
zonemercy-vingt-deux-v1-1e5_v2 status is now inactive due to auto deactivation removed underperforming models
zonemercy-vingt-deux-v1-1e5_v2 status is now torndown due to DeploymentManager action