valentin87-callan

developer_uid: valentin87

submission_id: valentin87-callan_v2

model_name: valentin87-callan_v1

model_group: valentin87/Callan

status: torndown

timestamp: 2024-09-05T23:11:17+00:00

num_battles: 12336

num_wins: 6282

celo_rating: 1243.85

family_friendly_score: 0.0

submission_type: basic

model_repo: valentin87/Callan

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 512

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6974911305543099, 'latency_mean': 1.433647599220276, 'latency_p50': 1.4295687675476074, 'latency_p90': 1.6055643796920775}, {'batch_size': 3, 'throughput': 1.341630540868594, 'latency_mean': 2.231556010246277, 'latency_p50': 2.2134371995925903, 'latency_p90': 2.4743623971939086}, {'batch_size': 5, 'throughput': 1.5553993202481653, 'latency_mean': 3.197986798286438, 'latency_p50': 3.191556453704834, 'latency_p90': 3.537922358512878}, {'batch_size': 6, 'throughput': 1.62523095356287, 'latency_mean': 3.682164628505707, 'latency_p50': 3.6794570684432983, 'latency_p90': 4.069953870773316}, {'batch_size': 8, 'throughput': 1.5987419780744923, 'latency_mean': 4.969917448759079, 'latency_p50': 5.014817714691162, 'latency_p90': 5.6235167503356935}, {'batch_size': 10, 'throughput': 1.5691044698213712, 'latency_mean': 6.328599858283996, 'latency_p50': 6.333798289299011, 'latency_p90': 7.178371834754944}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: valentin87-callan_v1

is_internal_developer: True

language_model: valentin87/Callan

model_size: 13B

ranking_group: single

throughput_3p7s: 1.63

us_pacific_date: 2024-09-05

win_ratio: 0.5092412451361867

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, '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 valentin87-callan-v2-mkmlizer
Waiting for job on valentin87-callan-v2-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
valentin87-callan-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
valentin87-callan-v2-mkmlizer: ║     _____            __           __                                ║
valentin87-callan-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
valentin87-callan-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
valentin87-callan-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
valentin87-callan-v2-mkmlizer: ║       /___/                                                         ║
valentin87-callan-v2-mkmlizer: ║                                                                     ║
valentin87-callan-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
valentin87-callan-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
valentin87-callan-v2-mkmlizer: ║  https://mk1.ai                                                     ║
valentin87-callan-v2-mkmlizer: ║                                                                     ║
valentin87-callan-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
valentin87-callan-v2-mkmlizer: ║  belonging to:                                                      ║
valentin87-callan-v2-mkmlizer: ║                                                                     ║
valentin87-callan-v2-mkmlizer: ║  Chai Research Corp.                                                ║
valentin87-callan-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
valentin87-callan-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
valentin87-callan-v2-mkmlizer: ║                                                                     ║
valentin87-callan-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
valentin87-callan-v2-mkmlizer: Downloaded to shared memory in 68.767s
valentin87-callan-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpuldeeoxu, device:0
valentin87-callan-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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
valentin87-callan-v2-mkmlizer: quantized model in 40.137s
valentin87-callan-v2-mkmlizer: Processed model valentin87/Callan in 108.905s
valentin87-callan-v2-mkmlizer: creating bucket guanaco-mkml-models
valentin87-callan-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
valentin87-callan-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/valentin87-callan-v2
valentin87-callan-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/valentin87-callan-v2/config.json
valentin87-callan-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/valentin87-callan-v2/special_tokens_map.json
valentin87-callan-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/valentin87-callan-v2/tokenizer_config.json
valentin87-callan-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/valentin87-callan-v2/tokenizer.json
valentin87-callan-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 23.43it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:11, 29.45it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:14, 24.67it/s]
Loading 0:   6%|▌         | 20/363 [00:00<00:10, 33.41it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:14, 23.08it/s]
Loading 0:   7%|▋         | 27/363 [00:01<00:15, 22.12it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:12, 25.60it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:12, 27.10it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:11, 28.43it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:11, 27.19it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 30.09it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.20it/s]
Loading 0:  15%|█▌        | 56/363 [00:02<00:10, 30.26it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.09it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:13, 22.92it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 30.39it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 29.18it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.37it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:09, 29.13it/s]
Loading 0:  24%|██▍       | 88/363 [00:03<00:09, 28.13it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:09, 29.74it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:09, 28.73it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:11, 23.24it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:12, 20.98it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:08, 28.49it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:08, 27.97it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 31.06it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 29.90it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 32.71it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 30.26it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 31.22it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 26.56it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 24.52it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:09, 23.55it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:06, 30.25it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:07, 29.00it/s]
Loading 0:  45%|████▌     | 164/363 [00:05<00:06, 31.06it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:07, 26.81it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 31.76it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 30.72it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:07, 24.42it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:08, 21.50it/s]
Loading 0:  53%|█████▎    | 192/363 [00:06<00:06, 28.35it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 27.81it/s]
Loading 0:  55%|█████▌    | 201/363 [00:07<00:05, 30.86it/s]
Loading 0:  56%|█████▋    | 205/363 [00:07<00:05, 29.52it/s]
Loading 0:  58%|█████▊    | 210/363 [00:07<00:04, 30.77it/s]
Loading 0:  59%|█████▉    | 214/363 [00:07<00:05, 29.55it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 29.56it/s]
Loading 0:  61%|██████    | 222/363 [00:07<00:04, 31.43it/s]
Loading 0:  62%|██████▏   | 226/363 [00:08<00:06, 21.86it/s]
Loading 0:  63%|██████▎   | 230/363 [00:08<00:06, 21.64it/s]
Loading 0:  65%|██████▌   | 237/363 [00:08<00:04, 28.63it/s]
Loading 0:  66%|██████▋   | 241/363 [00:08<00:04, 28.19it/s]
Loading 0:  68%|██████▊   | 246/363 [00:08<00:03, 30.95it/s]
Loading 0:  69%|██████▉   | 250/363 [00:09<00:03, 29.75it/s]
Loading 0:  70%|███████   | 255/363 [00:09<00:03, 31.40it/s]
Loading 0:  71%|███████▏  | 259/363 [00:09<00:03, 29.93it/s]
Loading 0:  72%|███████▏  | 263/363 [00:09<00:04, 24.36it/s]
Loading 0:  73%|███████▎  | 266/363 [00:09<00:04, 21.48it/s]
Loading 0:  75%|███████▌  | 273/363 [00:09<00:03, 28.17it/s]
Loading 0:  76%|███████▋  | 277/363 [00:10<00:03, 27.54it/s]
Loading 0:  78%|███████▊  | 282/363 [00:10<00:02, 29.79it/s]
Loading 0:  79%|███████▉  | 286/363 [00:10<00:02, 28.49it/s]
Loading 0:  80%|████████  | 291/363 [00:10<00:02, 30.25it/s]
Loading 0:  81%|████████▏ | 295/363 [00:10<00:02, 28.54it/s]
Loading 0:  82%|████████▏ | 299/363 [00:10<00:02, 28.14it/s]
Loading 0:  84%|████████▎ | 304/363 [00:11<00:02, 23.78it/s]
Loading 0:  85%|████████▍ | 307/363 [00:11<00:02, 22.93it/s]
Loading 0:  86%|████████▌ | 311/363 [00:11<00:02, 21.92it/s]
Loading 0:  87%|████████▋ | 316/363 [00:11<00:01, 27.17it/s]
Loading 0:  88%|████████▊ | 320/363 [00:11<00:01, 25.13it/s]
Loading 0:  90%|█████████ | 327/363 [00:11<00:01, 32.07it/s]
Loading 0:  91%|█████████ | 331/363 [00:11<00:01, 30.12it/s]
Loading 0:  93%|█████████▎| 336/363 [00:12<00:00, 31.40it/s]
Loading 0:  94%|█████████▎| 340/363 [00:12<00:00, 30.07it/s]
Loading 0:  95%|█████████▍| 344/363 [00:19<00:09,  2.03it/s]
Loading 0:  96%|█████████▌| 348/363 [00:19<00:05,  2.71it/s]
Loading 0:  97%|█████████▋| 353/363 [00:19<00:02,  3.92it/s]
Loading 0:  98%|█████████▊| 357/363 [00:19<00:01,  5.08it/s]
                                                            
Job valentin87-callan-v2-mkmlizer completed after 136.36s with status: succeeded
Stopping job with name valentin87-callan-v2-mkmlizer
Pipeline stage MKMLizer completed in 140.62s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service valentin87-callan-v2
Waiting for inference service valentin87-callan-v2 to be ready
Inference service valentin87-callan-v2 ready after 150.8156864643097s
Pipeline stage MKMLDeployer completed in 151.58s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.447399139404297s
Received healthy response to inference request in 1.9613370895385742s
Received healthy response to inference request in 2.226205348968506s
Received healthy response to inference request in 1.81284499168396s
Received healthy response to inference request in 1.514503002166748s
5 requests
0 failed requests
5th percentile: 1.5741714000701905
10th percentile: 1.6338397979736328
20th percentile: 1.7531765937805175
30th percentile: 1.8425434112548829
40th percentile: 1.9019402503967284
50th percentile: 1.9613370895385742
60th percentile: 2.0672843933105467
70th percentile: 2.1732316970825196
80th percentile: 2.2704441070556642
90th percentile: 2.3589216232299806
95th percentile: 2.4031603813171385
99th percentile: 2.438551387786865
mean time: 1.992457914352417
Pipeline stage StressChecker completed in 10.70s
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 5.92s
Shutdown handler de-registered
valentin87-callan_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 0.11s
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 valentin87-callan-v2-profiler
Waiting for inference service valentin87-callan-v2-profiler to be ready
Inference service valentin87-callan-v2-profiler ready after 150.35964965820312s
Pipeline stage MKMLProfilerDeployer completed in 150.72s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/valentin87-callan-v2-profiler-predictor-00001-deployment-65bzs5:/code/chaiverse_profiler_1725578375 --namespace tenant-chaiml-guanaco
kubectl exec -it valentin87-callan-v2-profiler-predictor-00001-deployment-65bzs5 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725578375 && 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 512 --output_tokens 64 --summary /code/chaiverse_profiler_1725578375/summary.json'
kubectl exec -it valentin87-callan-v2-profiler-predictor-00001-deployment-65bzs5 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725578375/summary.json'
Pipeline stage MKMLProfilerRunner completed in 945.96s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service valentin87-callan-v2-profiler is running
Tearing down inference service valentin87-callan-v2-profiler
Service valentin87-callan-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.70s
Shutdown handler de-registered
valentin87-callan_v2 status is now inactive due to auto deactivation removed underperforming models
valentin87-callan_v2 status is now torndown due to DeploymentManager action