zonemercy-vingt-deux-v0-1e5

submission_id: zonemercy-vingt-deux-v0-1e5_v11

developer_uid: chai_backend_admin

best_of: 8

celo_rating: 1244.43

display_name: temp-1

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|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A6000': 1}

is_internal_developer: True

language_model: zonemercy/Vingt-Deux-v0-1e5

latencies: [{'batch_size': 1, 'throughput': 0.3811362558929825, 'latency_mean': 2.623663182258606, 'latency_p50': 2.6313390731811523, 'latency_p90': 2.878469729423523}, {'batch_size': 2, 'throughput': 0.6040290671879988, 'latency_mean': 3.3011492121219637, 'latency_p50': 3.294635057449341, 'latency_p90': 3.650034046173096}, {'batch_size': 3, 'throughput': 0.7694975717139663, 'latency_mean': 3.886502457857132, 'latency_p50': 3.904481291770935, 'latency_p90': 4.269832611083984}, {'batch_size': 4, 'throughput': 0.8878663195891594, 'latency_mean': 4.471962881088257, 'latency_p50': 4.47950005531311, 'latency_p90': 4.940419292449951}, {'batch_size': 5, 'throughput': 0.9814517369731743, 'latency_mean': 5.063315694332123, 'latency_p50': 5.084156513214111, 'latency_p90': 5.651275539398194}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: zonemercy/Vingt-Deux-v0-

model_name: temp-1

model_num_parameters: 22247282688.0

model_repo: zonemercy/Vingt-Deux-v0-1e5

model_size: 22B

num_battles: 53151

num_wins: 26519

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 0.72

timestamp: 2024-09-23T09:38:44+00:00

us_pacific_date: 2024-09-23

win_ratio: 0.49893699083742543

Download Preference Data

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-v0-1e5-v11-mkmlizer
Waiting for job on zonemercy-vingt-deux-v0-1e5-v11-mkmlizer to finish
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: ║     _____            __           __                                ║
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: ║       /___/                                                         ║
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: ║  Version: 0.10.1                                                    ║
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: ║  https://mk1.ai                                                     ║
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: ║  The license key for the current software has been verified as      ║
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: ║  belonging to:                                                      ║
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: ║  Chai Research Corp.                                                ║
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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-v0-1e5-v11-mkmlizer: Downloaded to shared memory in 49.573s
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5ge_4oy0, device:0
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: quantized model in 42.406s
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: Processed model zonemercy/Vingt-Deux-v0-1e5 in 91.979s
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v11
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v11/config.json
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v11/special_tokens_map.json
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v11/tokenizer_config.json
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v11/tokenizer.json
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v11/flywheel_model.1.safetensors
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v11/flywheel_model.0.safetensors
zonemercy-vingt-deux-v0-1e5-v11-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:18, 26.46it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:11, 43.57it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 39.51it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 38.36it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:12, 38.44it/s]
Loading 0:   6%|▌         | 31/507 [00:00<00:13, 35.54it/s]
Loading 0:   7%|▋         | 35/507 [00:00<00:13, 36.11it/s]
Loading 0:   8%|▊         | 40/507 [00:01<00:12, 37.85it/s]
Loading 0:   9%|▉         | 45/507 [00:01<00:11, 40.79it/s]
Loading 0:  10%|▉         | 50/507 [00:01<00:12, 36.23it/s]
Loading 0:  11%|█         | 54/507 [00:01<00:16, 27.50it/s]
Loading 0:  11%|█▏        | 58/507 [00:01<00:15, 28.67it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:13, 32.91it/s]
Loading 0:  13%|█▎        | 67/507 [00:01<00:13, 33.66it/s]
Loading 0:  14%|█▍        | 73/507 [00:02<00:11, 37.14it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:11, 37.62it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 41.96it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 41.26it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 40.79it/s]
Loading 0:  20%|██        | 102/507 [00:02<00:09, 41.80it/s]
Loading 0:  21%|██        | 107/507 [00:02<00:11, 34.43it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:12, 30.39it/s]
Loading 0:  23%|██▎       | 117/507 [00:03<00:13, 29.42it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:12, 30.18it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:10, 36.94it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:10, 35.98it/s]
Loading 0:  27%|██▋       | 138/507 [00:03<00:09, 38.72it/s]
Loading 0:  28%|██▊       | 143/507 [00:03<00:09, 39.31it/s]
Loading 0:  29%|██▉       | 148/507 [00:04<00:08, 40.38it/s]
Loading 0:  30%|███       | 153/507 [00:04<00:08, 41.76it/s]
Loading 0:  31%|███       | 158/507 [00:04<00:09, 36.91it/s]
Loading 0:  33%|███▎      | 166/507 [00:04<00:07, 46.35it/s]
Loading 0:  34%|███▎      | 171/507 [00:04<00:11, 30.48it/s]
Loading 0:  35%|███▍      | 176/507 [00:04<00:10, 31.68it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:08, 37.98it/s]
Loading 0:  37%|███▋      | 188/507 [00:05<00:08, 36.21it/s]
Loading 0:  38%|███▊      | 193/507 [00:05<00:08, 37.27it/s]
Loading 0:  39%|███▉      | 198/507 [00:05<00:07, 39.63it/s]
Loading 0:  40%|████      | 203/507 [00:05<00:08, 35.94it/s]
Loading 0:  42%|████▏     | 211/507 [00:05<00:06, 43.60it/s]
Loading 0:  43%|████▎     | 217/507 [00:05<00:06, 43.89it/s]
Loading 0:  44%|████▍     | 222/507 [00:05<00:06, 42.46it/s]
Loading 0:  45%|████▍     | 227/507 [00:06<00:08, 34.44it/s]
Loading 0:  46%|████▌     | 231/507 [00:06<00:08, 32.00it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:07, 37.22it/s]
Loading 0:  48%|████▊     | 242/507 [00:06<00:06, 38.53it/s]
Loading 0:  49%|████▊     | 247/507 [00:06<00:06, 39.04it/s]
Loading 0:  50%|████▉     | 252/507 [00:06<00:06, 41.65it/s]
Loading 0:  51%|█████     | 257/507 [00:06<00:06, 36.45it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:05, 43.53it/s]
Loading 0:  53%|█████▎    | 269/507 [00:07<00:05, 42.44it/s]
Loading 0:  54%|█████▍    | 274/507 [00:07<00:05, 42.94it/s]
Loading 0:  55%|█████▌    | 279/507 [00:07<00:05, 44.67it/s]
Loading 0:  56%|█████▌    | 284/507 [00:07<00:06, 32.21it/s]
Loading 0:  57%|█████▋    | 288/507 [00:07<00:07, 31.04it/s]
Loading 0:  58%|█████▊    | 293/507 [00:07<00:06, 31.88it/s]
Loading 0:  59%|█████▉    | 299/507 [00:22<00:06, 31.88it/s]
Loading 0:  59%|█████▉    | 300/507 [00:22<02:47,  1.24it/s]
Loading 0:  60%|█████▉    | 302/507 [00:22<02:25,  1.41it/s]
Loading 0:  61%|██████    | 307/507 [00:22<01:38,  2.04it/s]
Loading 0:  61%|██████    | 310/507 [00:22<01:17,  2.54it/s]
Loading 0:  62%|██████▏   | 314/507 [00:23<00:55,  3.50it/s]
Loading 0:  63%|██████▎   | 319/507 [00:23<00:36,  5.10it/s]
Loading 0:  64%|██████▍   | 324/507 [00:23<00:25,  7.23it/s]
Loading 0:  65%|██████▍   | 328/507 [00:23<00:19,  9.22it/s]
Loading 0:  66%|██████▌   | 333/507 [00:23<00:13, 12.51it/s]
Loading 0:  67%|██████▋   | 339/507 [00:23<00:10, 16.68it/s]
Loading 0:  68%|██████▊   | 344/507 [00:23<00:09, 17.13it/s]
Loading 0:  69%|██████▊   | 348/507 [00:24<00:08, 18.81it/s]
Loading 0:  70%|██████▉   | 354/507 [00:24<00:06, 24.43it/s]
Loading 0:  71%|███████   | 358/507 [00:24<00:05, 26.06it/s]
Loading 0:  72%|███████▏  | 364/507 [00:24<00:04, 30.89it/s]
Loading 0:  73%|███████▎  | 369/507 [00:24<00:04, 34.23it/s]
Loading 0:  74%|███████▍  | 374/507 [00:24<00:04, 32.04it/s]
Loading 0:  75%|███████▌  | 382/507 [00:24<00:03, 39.95it/s]
Loading 0:  76%|███████▋  | 387/507 [00:24<00:02, 41.71it/s]
Loading 0:  77%|███████▋  | 392/507 [00:25<00:03, 37.31it/s]
Loading 0:  78%|███████▊  | 397/507 [00:25<00:03, 29.39it/s]
Loading 0:  79%|███████▉  | 401/507 [00:25<00:03, 28.63it/s]
Loading 0:  80%|████████  | 408/507 [00:25<00:02, 35.17it/s]
Loading 0:  81%|████████▏ | 412/507 [00:25<00:02, 34.90it/s]
Loading 0:  82%|████████▏ | 417/507 [00:25<00:02, 38.02it/s]
Loading 0:  83%|████████▎ | 422/507 [00:26<00:02, 38.49it/s]
Loading 0:  84%|████████▍ | 427/507 [00:26<00:02, 37.40it/s]
Loading 0:  85%|████████▌ | 431/507 [00:26<00:02, 37.21it/s]
Loading 0:  86%|████████▌ | 436/507 [00:26<00:01, 38.34it/s]
Loading 0:  87%|████████▋ | 442/507 [00:26<00:01, 39.39it/s]
Loading 0:  88%|████████▊ | 446/507 [00:26<00:01, 36.21it/s]
Loading 0:  90%|████████▉ | 454/507 [00:26<00:01, 44.11it/s]
Loading 0:  91%|█████████ | 459/507 [00:29<00:06,  7.12it/s]
Loading 0:  92%|█████████▏| 465/507 [00:29<00:04,  9.58it/s]
Loading 0:  93%|█████████▎| 472/507 [00:29<00:02, 13.48it/s]
Loading 0:  94%|█████████▍| 477/507 [00:29<00:01, 16.09it/s]
Loading 0:  95%|█████████▌| 482/507 [00:29<00:01, 19.41it/s]
Loading 0:  96%|█████████▌| 487/507 [00:29<00:00, 23.27it/s]
Loading 0:  97%|█████████▋| 492/507 [00:29<00:00, 24.31it/s]
Loading 0:  98%|█████████▊| 497/507 [00:30<00:00, 28.27it/s]
Loading 0:  99%|█████████▉| 502/507 [00:30<00:00, 29.40it/s]
Loading 0: 100%|█████████▉| 506/507 [00:30<00:00, 31.07it/s]
                                                            
Job zonemercy-vingt-deux-v0-1e5-v11-mkmlizer completed after 116.07s with status: succeeded
Stopping job with name zonemercy-vingt-deux-v0-1e5-v11-mkmlizer
Pipeline stage MKMLizer completed in 117.41s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-vingt-deux-v0-1e5-v11
Waiting for inference service zonemercy-vingt-deux-v0-1e5-v11 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
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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service zonemercy-vingt-deux-v0-1e5-v11 ready after 191.98475742340088s
Pipeline stage MKMLDeployer completed in 192.42s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.844283103942871s
Received healthy response to inference request in 3.2150819301605225s
Received healthy response to inference request in 2.3152849674224854s
Received healthy response to inference request in 5.477906703948975s
Received healthy response to inference request in 2.998854398727417s
5 requests
0 failed requests
5th percentile: 2.4210845947265627
10th percentile: 2.5268842220306396
20th percentile: 2.7384834766387938
30th percentile: 2.8751973628997805
40th percentile: 2.9370258808135987
50th percentile: 2.998854398727417
60th percentile: 3.085345411300659
70th percentile: 3.171836423873901
80th percentile: 3.6676468849182133
90th percentile: 4.572776794433594
95th percentile: 5.025341749191284
99th percentile: 5.3873937129974365
mean time: 3.370282220840454
Pipeline stage StressChecker completed in 17.49s
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 5.12s
Shutdown handler de-registered
zonemercy-vingt-deux-v0-1e5_v11 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service zonemercy-vingt-deux-v0-1e5-v11-profiler
Waiting for inference service zonemercy-vingt-deux-v0-1e5-v11-profiler to be ready
Inference service zonemercy-vingt-deux-v0-1e5-v11-profiler ready after 190.47228407859802s
Pipeline stage MKMLProfilerDeployer completed in 190.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-vingt-deuxf7a13227423fe701fd963d92cb8e395a-deplo8hhlp:/code/chaiverse_profiler_1727084889 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-vingt-deuxf7a13227423fe701fd963d92cb8e395a-deplo8hhlp --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727084889 && 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_1727084889/summary.json'
kubectl exec -it zonemercy-vingt-deuxf7a13227423fe701fd963d92cb8e395a-deplo8hhlp --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727084889/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1549.57s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-vingt-deux-v0-1e5-v11-profiler is running
Tearing down inference service zonemercy-vingt-deux-v0-1e5-v11-profiler
Service zonemercy-vingt-deux-v0-1e5-v11-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.96s
Shutdown handler de-registered
zonemercy-vingt-deux-v0-1e5_v11 status is now inactive due to auto deactivation removed underperforming models
zonemercy-vingt-deux-v0-1e5_v11 status is now torndown due to DeploymentManager action