zonemercy-vingt-deux-v0-1e5

submission_id: zonemercy-vingt-deux-v0-1e5_v34

developer_uid: chai_backend_admin

best_of: 1

celo_rating: 1200.86

display_name: temp-2

family_friendly_score: 0.0

formatter: {'memory_template': 'Bot Name: {bot_name}\n####\n', 'prompt_template': '', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', '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': 0.3972157608140743, 'latency_mean': 2.5174512124061583, 'latency_p50': 2.5303343534469604, 'latency_p90': 2.7824416875839235}, {'batch_size': 3, 'throughput': 0.8629759714144477, 'latency_mean': 3.455860183238983, 'latency_p50': 3.4814186096191406, 'latency_p90': 3.8111302614212037}, {'batch_size': 5, 'throughput': 1.1727628649772863, 'latency_mean': 4.233585003614426, 'latency_p50': 4.236809611320496, 'latency_p90': 4.813975834846497}, {'batch_size': 6, 'throughput': 1.2893930184081221, 'latency_mean': 4.626329085826874, 'latency_p50': 4.6392035484313965, 'latency_p90': 5.144730591773987}, {'batch_size': 8, 'throughput': 1.4697927221385036, 'latency_mean': 5.395985177755356, 'latency_p50': 5.353442668914795, 'latency_p90': 6.093606185913086}, {'batch_size': 10, 'throughput': 1.5962839680326086, 'latency_mean': 6.212711547613144, 'latency_p50': 6.1900399923324585, 'latency_p90': 7.143588089942932}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: zonemercy/Vingt-Deux-v0-

model_name: temp-2

model_num_parameters: 22247282688.0

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

model_size: 22B

num_battles: 3333

num_wins: 1475

ranking_group: single

status: torndown

submission_type: basic

throughput_3p7s: 0.98

timestamp: 2024-09-24T10:01:27+00:00

us_pacific_date: 2024-09-24

win_ratio: 0.44254425442544254

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-v34-mkmlizer
Waiting for job on zonemercy-vingt-deux-v0-1e5-v34-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
zonemercy-vingt-deux-v0-1e5-v34-mkmlizer: Downloaded to shared memory in 57.530s
zonemercy-vingt-deux-v0-1e5-v34-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpk09d7_nd, device:0
zonemercy-vingt-deux-v0-1e5-v34-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Retrying (%r) after connection broken by '%r': %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
zonemercy-vingt-deux-v0-1e5-v34-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-vingt-deux-v0-1e5-v34-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-vingt-deux-v0-1e5-v34-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v34
zonemercy-vingt-deux-v0-1e5-v34-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v34/special_tokens_map.json
zonemercy-vingt-deux-v0-1e5-v34-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v34/config.json
zonemercy-vingt-deux-v0-1e5-v34-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v34/tokenizer_config.json
zonemercy-vingt-deux-v0-1e5-v34-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v34/tokenizer.json
zonemercy-vingt-deux-v0-1e5-v34-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-1e5-v34/flywheel_model.0.safetensors
zonemercy-vingt-deux-v0-1e5-v34-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:19, 25.89it/s]
Loading 0:   2%|▏         | 10/507 [00:00<00:13, 36.04it/s]
Loading 0:   3%|▎         | 14/507 [00:00<00:16, 29.89it/s]
Loading 0:   4%|▍         | 21/507 [00:00<00:12, 38.24it/s]
Loading 0:   5%|▌         | 26/507 [00:00<00:13, 35.98it/s]
Loading 0:   6%|▌         | 30/507 [00:00<00:13, 36.63it/s]
Loading 0:   7%|▋         | 34/507 [00:01<00:14, 32.50it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:13, 34.44it/s]
Loading 0:   8%|▊         | 43/507 [00:01<00:14, 32.65it/s]
Loading 0:   9%|▉         | 47/507 [00:01<00:14, 31.87it/s]
Loading 0:  10%|█         | 51/507 [00:01<00:14, 30.97it/s]
Loading 0:  11%|█         | 55/507 [00:01<00:22, 20.17it/s]
Loading 0:  11%|█▏        | 58/507 [00:02<00:21, 21.29it/s]
Loading 0:  12%|█▏        | 62/507 [00:02<00:17, 24.92it/s]
Loading 0:  13%|█▎        | 65/507 [00:02<00:19, 22.25it/s]
Loading 0:  14%|█▍        | 70/507 [00:02<00:15, 27.56it/s]
Loading 0:  15%|█▍        | 75/507 [00:02<00:14, 30.32it/s]
Loading 0:  16%|█▌        | 80/507 [00:02<00:14, 30.41it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:11, 36.41it/s]
Loading 0:  18%|█▊        | 91/507 [00:02<00:12, 33.87it/s]
Loading 0:  19%|█▉        | 96/507 [00:03<00:11, 34.58it/s]
Loading 0:  20%|█▉        | 100/507 [00:03<00:12, 32.60it/s]
Loading 0:  21%|██        | 104/507 [00:03<00:12, 33.33it/s]
Loading 0:  21%|██▏       | 108/507 [00:03<00:13, 29.79it/s]
Loading 0:  22%|██▏       | 112/507 [00:03<00:12, 30.98it/s]
Loading 0:  23%|██▎       | 116/507 [00:04<00:19, 20.12it/s]
Loading 0:  24%|██▍       | 122/507 [00:04<00:16, 23.53it/s]
Loading 0:  25%|██▌       | 127/507 [00:04<00:13, 28.00it/s]
Loading 0:  26%|██▌       | 131/507 [00:04<00:14, 26.14it/s]
Loading 0:  27%|██▋       | 136/507 [00:04<00:12, 30.63it/s]
Loading 0:  28%|██▊       | 140/507 [00:04<00:12, 28.43it/s]
Loading 0:  29%|██▊       | 145/507 [00:04<00:11, 32.51it/s]
Loading 0:  29%|██▉       | 149/507 [00:05<00:11, 29.94it/s]
Loading 0:  30%|███       | 154/507 [00:05<00:10, 34.31it/s]
Loading 0:  31%|███       | 158/507 [00:05<00:11, 30.93it/s]
Loading 0:  32%|███▏      | 164/507 [00:05<00:09, 35.42it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:12, 27.10it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:12, 27.50it/s]
Loading 0:  35%|███▍      | 177/507 [00:06<00:12, 26.33it/s]
Loading 0:  36%|███▌      | 181/507 [00:06<00:11, 28.91it/s]
Loading 0:  36%|███▋      | 185/507 [00:06<00:11, 27.32it/s]
Loading 0:  37%|███▋      | 190/507 [00:06<00:09, 31.88it/s]
Loading 0:  38%|███▊      | 194/507 [00:06<00:10, 29.55it/s]
Loading 0:  39%|███▉      | 199/507 [00:06<00:09, 32.97it/s]
Loading 0:  40%|████      | 203/507 [00:06<00:10, 29.97it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:07, 37.13it/s]
Loading 0:  42%|████▏     | 214/507 [00:07<00:08, 35.09it/s]
Loading 0:  43%|████▎     | 218/507 [00:07<00:08, 34.62it/s]
Loading 0:  44%|████▍     | 222/507 [00:07<00:08, 33.49it/s]
Loading 0:  45%|████▍     | 226/507 [00:07<00:11, 23.99it/s]
Loading 0:  45%|████▌     | 230/507 [00:07<00:11, 24.22it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:08, 31.07it/s]
Loading 0:  48%|████▊     | 241/507 [00:08<00:08, 30.10it/s]
Loading 0:  49%|████▊     | 246/507 [00:08<00:08, 31.98it/s]
Loading 0:  49%|████▉     | 250/507 [00:08<00:08, 31.30it/s]
Loading 0:  50%|█████     | 255/507 [00:08<00:07, 32.96it/s]
Loading 0:  51%|█████     | 259/507 [00:08<00:07, 31.69it/s]
Loading 0:  52%|█████▏    | 264/507 [00:08<00:07, 33.89it/s]
Loading 0:  53%|█████▎    | 268/507 [00:08<00:07, 32.69it/s]
Loading 0:  54%|█████▍    | 273/507 [00:09<00:06, 34.80it/s]
Loading 0:  55%|█████▍    | 277/507 [00:09<00:06, 33.16it/s]
Loading 0:  56%|█████▌    | 282/507 [00:09<00:06, 36.96it/s]
Loading 0:  56%|█████▋    | 286/507 [00:09<00:08, 24.78it/s]
Loading 0:  57%|█████▋    | 290/507 [00:09<00:08, 26.76it/s]
Loading 0:  58%|█████▊    | 294/507 [00:09<00:08, 26.02it/s]
Loading 0:  59%|█████▉    | 298/507 [00:09<00:07, 28.86it/s]
Loading 0:  59%|█████▉    | 299/507 [00:20<00:07, 28.86it/s]
Loading 0:  59%|█████▉    | 300/507 [00:24<04:29,  1.30s/it]
Loading 0:  60%|█████▉    | 302/507 [00:24<03:38,  1.06s/it]
Loading 0:  61%|██████    | 307/507 [00:25<02:07,  1.57it/s]
Loading 0:  61%|██████    | 310/507 [00:25<01:35,  2.07it/s]
Loading 0:  62%|██████▏   | 313/507 [00:25<01:10,  2.76it/s]
Loading 0:  63%|██████▎   | 318/507 [00:25<00:43,  4.36it/s]
Loading 0:  64%|██████▎   | 322/507 [00:25<00:31,  5.94it/s]
Loading 0:  64%|██████▍   | 327/507 [00:25<00:21,  8.57it/s]
Loading 0:  65%|██████▌   | 331/507 [00:25<00:16, 10.76it/s]
Loading 0:  66%|██████▌   | 335/507 [00:26<00:12, 13.31it/s]
Loading 0:  67%|██████▋   | 339/507 [00:26<00:10, 16.51it/s]
Loading 0:  68%|██████▊   | 343/507 [00:26<00:10, 15.18it/s]
Loading 0:  68%|██████▊   | 347/507 [00:26<00:09, 16.90it/s]
Loading 0:  69%|██████▉   | 352/507 [00:26<00:07, 21.77it/s]
Loading 0:  70%|███████   | 356/507 [00:26<00:06, 22.42it/s]
Loading 0:  71%|███████   | 361/507 [00:26<00:05, 27.35it/s]
Loading 0:  72%|███████▏  | 365/507 [00:27<00:05, 26.28it/s]
Loading 0:  73%|███████▎  | 370/507 [00:27<00:04, 30.43it/s]
Loading 0:  74%|███████▍  | 374/507 [00:27<00:04, 28.87it/s]
Loading 0:  75%|███████▌  | 381/507 [00:27<00:03, 36.32it/s]
Loading 0:  76%|███████▌  | 386/507 [00:27<00:03, 35.25it/s]
Loading 0:  77%|███████▋  | 390/507 [00:27<00:03, 29.44it/s]
Loading 0:  78%|███████▊  | 395/507 [00:28<00:04, 24.91it/s]
Loading 0:  79%|███████▉  | 401/507 [00:28<00:03, 26.82it/s]
Loading 0:  80%|████████  | 406/507 [00:28<00:03, 30.96it/s]
Loading 0:  81%|████████  | 410/507 [00:28<00:03, 28.63it/s]
Loading 0:  82%|████████▏ | 415/507 [00:28<00:02, 32.48it/s]
Loading 0:  83%|████████▎ | 419/507 [00:28<00:02, 29.92it/s]
Loading 0:  84%|████████▎ | 424/507 [00:29<00:02, 34.08it/s]
Loading 0:  84%|████████▍ | 428/507 [00:29<00:02, 30.62it/s]
Loading 0:  86%|████████▌ | 435/507 [00:29<00:01, 37.25it/s]
Loading 0:  87%|████████▋ | 439/507 [00:29<00:01, 34.91it/s]
Loading 0:  88%|████████▊ | 444/507 [00:29<00:01, 36.14it/s]
Loading 0:  88%|████████▊ | 448/507 [00:29<00:01, 33.89it/s]
Loading 0:  89%|████████▉ | 453/507 [00:29<00:01, 37.09it/s]
Loading 0:  90%|█████████ | 457/507 [00:32<00:08,  5.79it/s]
Loading 0:  91%|█████████ | 460/507 [00:32<00:06,  6.96it/s]
Loading 0:  92%|█████████▏| 465/507 [00:32<00:04,  9.49it/s]
Loading 0:  93%|█████████▎| 472/507 [00:32<00:02, 14.38it/s]
Loading 0:  94%|█████████▍| 476/507 [00:32<00:01, 16.67it/s]
Loading 0:  95%|█████████▍| 481/507 [00:32<00:01, 20.66it/s]
Loading 0:  96%|█████████▌| 485/507 [00:32<00:00, 22.18it/s]
Loading 0:  97%|█████████▋| 490/507 [00:33<00:00, 25.89it/s]
Loading 0:  97%|█████████▋| 494/507 [00:33<00:00, 26.60it/s]
Loading 0:  98%|█████████▊| 499/507 [00:33<00:00, 29.60it/s]
Loading 0:  99%|█████████▉| 503/507 [00:33<00:00, 29.52it/s]
                                                            
Connection pool is full, discarding connection: %s. Connection pool size: %s
Job zonemercy-vingt-deux-v0-1e5-v34-mkmlizer completed after 160.58s with status: succeeded
Stopping job with name zonemercy-vingt-deux-v0-1e5-v34-mkmlizer
Pipeline stage MKMLizer completed in 162.28s
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-v34
Waiting for inference service zonemercy-vingt-deux-v0-1e5-v34 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
admin requested tearing down of nousresearch-meta-llama_4939_v19
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service zonemercy-vingt-deux-v0-1e5-v34 ready after 193.1626045703888s
Pipeline stage MKMLDeployer completed in 194.70s
run pipeline stage %s
Running pipeline stage StressChecker
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
Received healthy response to inference request in 3.6601052284240723s
Received healthy response to inference request in 3.1127257347106934s
Received healthy response to inference request in 2.299546480178833s
Received healthy response to inference request in 2.475182294845581s
Received healthy response to inference request in 3.694777011871338s
5 requests
0 failed requests
5th percentile: 2.3346736431121826
10th percentile: 2.3698008060455322
20th percentile: 2.4400551319122314
30th percentile: 2.6026909828186033
40th percentile: 2.8577083587646483
50th percentile: 3.1127257347106934
60th percentile: 3.331677532196045
70th percentile: 3.550629329681396
80th percentile: 3.6670395851135256
90th percentile: 3.6809082984924317
95th percentile: 3.6878426551818846
99th percentile: 3.693390140533447
mean time: 3.0484673500061037
Pipeline stage StressChecker completed in 17.35s
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 5.65s
Shutdown handler de-registered
zonemercy-vingt-deux-v0-1e5_v34 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 0.15s
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-vingt-deux-v0-1e5-v34-profiler
Waiting for inference service zonemercy-vingt-deux-v0-1e5-v34-profiler to be ready
Inference service zonemercy-vingt-deux-v0-1e5-v34-profiler ready after 200.46597528457642s
Pipeline stage MKMLProfilerDeployer completed in 200.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-vingt-deuxcbb5246aeb6ff5534e967e9d7be3e54a-deplorlpsq:/code/chaiverse_profiler_1727172728 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-vingt-deuxcbb5246aeb6ff5534e967e9d7be3e54a-deplorlpsq --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727172728 && 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_1727172728/summary.json'
kubectl exec -it zonemercy-vingt-deuxcbb5246aeb6ff5534e967e9d7be3e54a-deplorlpsq --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727172728/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1328.19s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-vingt-deux-v0-1e5-v34-profiler is running
Tearing down inference service zonemercy-vingt-deux-v0-1e5-v34-profiler
Service zonemercy-vingt-deux-v0-1e5-v34-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.20s
Shutdown handler de-registered
zonemercy-vingt-deux-v0-1e5_v34 status is now inactive due to auto deactivation removed underperforming models
Deleting key zonemercy-vingt-deux-v0-1e5-v37/tokenizer.json from bucket guanaco-mkml-models
zonemercy-vingt-deux-v0-1e5_v34 status is now torndown due to DeploymentManager action