zonemercy-vingt-deux-v0-1e5

submission_id: zonemercy-vingt-deux-v0-1e5_v50

developer_uid: chai_backend_admin

best_of: 1

celo_rating: 1211.07

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': 1, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A6000': 1}

ineligible_reason: num_battles<5000

is_internal_developer: True

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

latencies: [{'batch_size': 1, 'throughput': 0.39666234512896775, 'latency_mean': 2.5209606862068177, 'latency_p50': 2.5613423585891724, 'latency_p90': 2.779471516609192}, {'batch_size': 3, 'throughput': 0.8570699460883737, 'latency_mean': 3.482161387205124, 'latency_p50': 3.493536949157715, 'latency_p90': 3.867747116088867}, {'batch_size': 5, 'throughput': 1.165034687754655, 'latency_mean': 4.272225122451783, 'latency_p50': 4.290209174156189, 'latency_p90': 4.79003369808197}, {'batch_size': 6, 'throughput': 1.2804174876868268, 'latency_mean': 4.655457677841187, 'latency_p50': 4.61836850643158, 'latency_p90': 5.2252470493316645}, {'batch_size': 8, 'throughput': 1.4516056875333017, 'latency_mean': 5.4625867247581485, 'latency_p50': 5.469113349914551, 'latency_p90': 6.087079286575317}, {'batch_size': 10, 'throughput': 1.5744341507057946, 'latency_mean': 6.301669685840607, 'latency_p50': 6.3148273229599, 'latency_p90': 7.07746353149414}]

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: 4709

num_wins: 2174

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 0.96

timestamp: 2024-09-24T12:24:46+00:00

us_pacific_date: 2024-09-24

win_ratio: 0.4616691441919728

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-v50-mkmlizer
Waiting for job on zonemercy-vingt-deux-v0-1e5-v50-mkmlizer to finish
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: ║     _____            __           __                                ║
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: ║       /___/                                                         ║
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: ║  Version: 0.10.1                                                    ║
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: ║  https://mk1.ai                                                     ║
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: ║  The license key for the current software has been verified as      ║
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: ║  belonging to:                                                      ║
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: ║  Chai Research Corp.                                                ║
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v0-1e5-v50-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: Downloaded to shared memory in 48.386s
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3vvtxzca, device:0
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: quantized model in 44.436s
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: Processed model zonemercy/Vingt-Deux-v0-1e5 in 92.823s
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v50
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v50/config.json
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v50/special_tokens_map.json
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
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v50/flywheel_model.1.safetensors
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v50/flywheel_model.0.safetensors
zonemercy-vingt-deux-v0-1e5-v50-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:17, 28.60it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:10, 45.54it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 40.76it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:11, 42.04it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:10, 43.83it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:12, 37.28it/s]
Loading 0:   8%|▊         | 39/507 [00:00<00:10, 45.37it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:10, 44.89it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:11, 39.60it/s]
Loading 0:  11%|█         | 54/507 [00:01<00:15, 29.89it/s]
Loading 0:  11%|█▏        | 58/507 [00:01<00:15, 29.59it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:13, 33.01it/s]
Loading 0:  13%|█▎        | 67/507 [00:01<00:13, 32.74it/s]
Loading 0:  14%|█▍        | 73/507 [00:01<00:12, 35.62it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:11, 36.23it/s]
Loading 0:  17%|█▋        | 85/507 [00:02<00:10, 38.95it/s]
Loading 0:  18%|█▊        | 90/507 [00:02<00:11, 36.00it/s]
Loading 0:  19%|█▉        | 96/507 [00:02<00:10, 38.31it/s]
Loading 0:  20%|█▉        | 100/507 [00:02<00:11, 35.55it/s]
Loading 0:  21%|██        | 104/507 [00:02<00:11, 36.04it/s]
Loading 0:  21%|██▏       | 108/507 [00:02<00:12, 31.76it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:15, 25.82it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:16, 23.73it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 26.91it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:11, 33.55it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:11, 32.15it/s]
Loading 0:  27%|██▋       | 138/507 [00:03<00:10, 34.75it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 33.19it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:10, 35.05it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:10, 33.76it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 36.31it/s]
Loading 0:  32%|███▏      | 160/507 [00:04<00:09, 35.96it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:09, 36.59it/s]
Loading 0:  33%|███▎      | 169/507 [00:04<00:12, 28.16it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 29.01it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:11, 27.98it/s]
Loading 0:  36%|███▌      | 182/507 [00:05<00:09, 32.80it/s]
Loading 0:  37%|███▋      | 186/507 [00:05<00:11, 29.14it/s]
Loading 0:  37%|███▋      | 190/507 [00:05<00:10, 30.82it/s]
Loading 0:  38%|███▊      | 194/507 [00:05<00:10, 28.50it/s]
Loading 0:  39%|███▉      | 199/507 [00:05<00:09, 32.97it/s]
Loading 0:  40%|████      | 203/507 [00:06<00:10, 30.27it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:07, 37.82it/s]
Loading 0:  42%|████▏     | 215/507 [00:06<00:07, 37.68it/s]
Loading 0:  43%|████▎     | 219/507 [00:06<00:09, 31.40it/s]
Loading 0:  44%|████▍     | 223/507 [00:06<00:08, 32.74it/s]
Loading 0:  45%|████▍     | 227/507 [00:06<00:10, 27.31it/s]
Loading 0:  46%|████▌     | 231/507 [00:06<00:10, 26.69it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:08, 31.42it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:08, 31.30it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 33.20it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:08, 31.99it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:07, 33.82it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:07, 32.51it/s]
Loading 0:  52%|█████▏    | 263/507 [00:07<00:07, 34.18it/s]
Loading 0:  53%|█████▎    | 267/507 [00:08<00:07, 30.58it/s]
Loading 0:  53%|█████▎    | 271/507 [00:08<00:07, 32.64it/s]
Loading 0:  54%|█████▍    | 275/507 [00:08<00:07, 30.22it/s]
Loading 0:  56%|█████▌    | 282/507 [00:08<00:05, 39.51it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:08, 24.49it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 27.35it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 27.35it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:41,  1.28it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:21,  1.45it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:36,  2.08it/s]
Loading 0:  61%|██████    | 310/507 [00:24<01:16,  2.56it/s]
Loading 0:  62%|██████▏   | 313/507 [00:24<00:59,  3.25it/s]
Loading 0:  63%|██████▎   | 318/507 [00:24<00:39,  4.84it/s]
Loading 0:  64%|██████▎   | 322/507 [00:24<00:28,  6.45it/s]
Loading 0:  64%|██████▍   | 327/507 [00:24<00:19,  9.17it/s]
Loading 0:  65%|██████▌   | 331/507 [00:24<00:15, 11.56it/s]
Loading 0:  66%|██████▌   | 335/507 [00:24<00:11, 14.43it/s]
Loading 0:  67%|██████▋   | 340/507 [00:24<00:10, 15.84it/s]
Loading 0:  68%|██████▊   | 344/507 [00:25<00:08, 18.30it/s]
Loading 0:  69%|██████▊   | 348/507 [00:25<00:08, 19.80it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:05, 25.66it/s]
Loading 0:  71%|███████   | 358/507 [00:25<00:05, 27.43it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 31.82it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 32.23it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:03, 36.19it/s]
Loading 0:  74%|███████▍  | 377/507 [00:25<00:03, 36.39it/s]
Loading 0:  75%|███████▌  | 382/507 [00:26<00:03, 37.22it/s]
Loading 0:  76%|███████▌  | 386/507 [00:26<00:03, 37.37it/s]
Loading 0:  77%|███████▋  | 390/507 [00:26<00:03, 29.95it/s]
Loading 0:  78%|███████▊  | 395/507 [00:26<00:04, 25.73it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:03, 27.50it/s]
Loading 0:  80%|████████  | 406/507 [00:26<00:03, 31.44it/s]
Loading 0:  81%|████████  | 410/507 [00:27<00:03, 28.83it/s]
Loading 0:  82%|████████▏ | 415/507 [00:27<00:02, 33.00it/s]
Loading 0:  83%|████████▎ | 419/507 [00:27<00:02, 30.28it/s]
Loading 0:  84%|████████▍ | 426/507 [00:27<00:02, 36.79it/s]
Loading 0:  85%|████████▍ | 430/507 [00:27<00:02, 34.95it/s]
Loading 0:  86%|████████▌ | 435/507 [00:27<00:01, 37.44it/s]
Loading 0:  87%|████████▋ | 439/507 [00:27<00:01, 35.76it/s]
Loading 0:  88%|████████▊ | 444/507 [00:27<00:01, 38.37it/s]
Loading 0:  88%|████████▊ | 448/507 [00:28<00:01, 36.35it/s]
Loading 0:  90%|████████▉ | 454/507 [00:28<00:01, 37.27it/s]
Loading 0:  90%|█████████ | 458/507 [00:30<00:08,  6.08it/s]
Loading 0:  91%|█████████ | 461/507 [00:30<00:06,  7.27it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:04,  9.21it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 14.15it/s]
Loading 0:  94%|█████████▍| 476/507 [00:31<00:01, 16.67it/s]
Loading 0:  95%|█████████▍| 481/507 [00:31<00:01, 20.60it/s]
Loading 0:  96%|█████████▌| 485/507 [00:31<00:00, 22.58it/s]
Loading 0:  97%|█████████▋| 490/507 [00:31<00:00, 26.77it/s]
Loading 0:  97%|█████████▋| 494/507 [00:31<00:00, 28.87it/s]
Loading 0:  98%|█████████▊| 499/507 [00:31<00:00, 31.34it/s]
Loading 0:  99%|█████████▉| 503/507 [00:31<00:00, 32.22it/s]
                                                            
Job zonemercy-vingt-deux-v0-1e5-v50-mkmlizer completed after 125.93s with status: succeeded
Stopping job with name zonemercy-vingt-deux-v0-1e5-v50-mkmlizer
Pipeline stage MKMLizer completed in 128.21s
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-vingt-deux-v0-1e5-v50
Waiting for inference service zonemercy-vingt-deux-v0-1e5-v50 to be ready
Inference service zonemercy-vingt-deux-v0-1e5-v50 ready after 210.51561546325684s
Pipeline stage MKMLDeployer completed in 211.75s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9263148307800293s
Received healthy response to inference request in 2.8409769535064697s
Received healthy response to inference request in 1.5580663681030273s
Received healthy response to inference request in 2.889124870300293s
Received healthy response to inference request in 2.34616756439209s
5 requests
0 failed requests
5th percentile: 1.6317160606384278
10th percentile: 1.7053657531738282
20th percentile: 1.8526651382446289
30th percentile: 2.0102853775024414
40th percentile: 2.1782264709472656
50th percentile: 2.34616756439209
60th percentile: 2.544091320037842
70th percentile: 2.7420150756835935
80th percentile: 2.8506065368652345
90th percentile: 2.8698657035827635
95th percentile: 2.8794952869415282
99th percentile: 2.88719895362854
mean time: 2.3121301174163817
Pipeline stage StressChecker completed in 12.37s
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 4.98s
Shutdown handler de-registered
zonemercy-vingt-deux-v0-1e5_v50 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service zonemercy-vingt-deux-v0-1e5-v50-profiler
Waiting for inference service zonemercy-vingt-deux-v0-1e5-v50-profiler to be ready
Inference service zonemercy-vingt-deux-v0-1e5-v50-profiler ready after 210.46669483184814s
Pipeline stage MKMLProfilerDeployer completed in 210.88s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-vingt-deux7e160e99229ceed3305a3d24d526002e-deplop5jh5:/code/chaiverse_profiler_1727181294 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-vingt-deux7e160e99229ceed3305a3d24d526002e-deplop5jh5 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727181294 && python profiles.py profile --best_of_n 1 --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_1727181294/summary.json'
kubectl exec -it zonemercy-vingt-deux7e160e99229ceed3305a3d24d526002e-deplop5jh5 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727181294/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1335.29s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-vingt-deux-v0-1e5-v50-profiler is running
Tearing down inference service zonemercy-vingt-deux-v0-1e5-v50-profiler
Service zonemercy-vingt-deux-v0-1e5-v50-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.14s
Shutdown handler de-registered
zonemercy-vingt-deux-v0-1e5_v50 status is now inactive due to auto deactivation removed underperforming models
Pipeline stage MKMLModelDeleter completed in 3.06s
zonemercy-vingt-deux-v0-1e5_v50 status is now torndown due to DeploymentManager action
Shutdown handler de-registered