rica40325-spin-first

developer_uid: rica40325

submission_id: rica40325-spin-first_v4

model_name: rica40325-spin-first_v2

model_group: rica40325/spin_first

status: torndown

timestamp: 2024-09-19T12:46:03+00:00

num_battles: 16387

num_wins: 8200

celo_rating: 1251.31

family_friendly_score: 0.0

submission_type: basic

model_repo: rica40325/spin_first

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.8774822814434295, 'latency_mean': 1.139530099630356, 'latency_p50': 1.1340105533599854, 'latency_p90': 1.2602927923202514}, {'batch_size': 4, 'throughput': 1.8805776239575183, 'latency_mean': 2.117472733259201, 'latency_p50': 2.112957239151001, 'latency_p90': 2.3679921627044678}, {'batch_size': 5, 'throughput': 2.029201528562096, 'latency_mean': 2.451303708553314, 'latency_p50': 2.4590145349502563, 'latency_p90': 2.7426636695861815}, {'batch_size': 8, 'throughput': 2.257866496970385, 'latency_mean': 3.51349081158638, 'latency_p50': 3.487810969352722, 'latency_p90': 3.953903889656067}, {'batch_size': 10, 'throughput': 2.3340561232088195, 'latency_mean': 4.259744461774826, 'latency_p50': 4.258525013923645, 'latency_p90': 4.799982404708862}, {'batch_size': 12, 'throughput': 2.390242597139857, 'latency_mean': 4.966891789436341, 'latency_p50': 5.0094313621521, 'latency_p90': 5.657481718063354}, {'batch_size': 15, 'throughput': 2.359708884900272, 'latency_mean': 6.263965179920197, 'latency_p50': 6.27416718006134, 'latency_p90': 7.01330873966217}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rica40325-spin-first_v2

is_internal_developer: False

language_model: rica40325/spin_first

model_size: 8B

ranking_group: single

throughput_3p7s: 2.3

us_pacific_date: 2024-09-19

win_ratio: 0.5003966558857631

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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 rica40325-spin-first-v4-mkmlizer
Waiting for job on rica40325-spin-first-v4-mkmlizer to finish
rica40325-spin-first-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-spin-first-v4-mkmlizer: ║     _____            __           __                                ║
rica40325-spin-first-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-spin-first-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-spin-first-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-spin-first-v4-mkmlizer: ║       /___/                                                         ║
rica40325-spin-first-v4-mkmlizer: ║                                                                     ║
rica40325-spin-first-v4-mkmlizer: ║  Version: 0.10.1                                                    ║
rica40325-spin-first-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-spin-first-v4-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-spin-first-v4-mkmlizer: ║                                                                     ║
rica40325-spin-first-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-spin-first-v4-mkmlizer: ║  belonging to:                                                      ║
rica40325-spin-first-v4-mkmlizer: ║                                                                     ║
rica40325-spin-first-v4-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-spin-first-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-spin-first-v4-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-spin-first-v4-mkmlizer: ║                                                                     ║
rica40325-spin-first-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission zonemercy-lexical-nemov8_5966_v2: ('http://zonemercy-lexical-nemov8-5966-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:33742->127.0.0.1:8080: read: connection reset by peer\n')
rica40325-spin-first-v4-mkmlizer: Downloaded to shared memory in 37.455s
rica40325-spin-first-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplhd1wrxu, device:0
rica40325-spin-first-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-spin-first-v4-mkmlizer: quantized model in 28.348s
rica40325-spin-first-v4-mkmlizer: Processed model rica40325/spin_first in 65.803s
rica40325-spin-first-v4-mkmlizer: creating bucket guanaco-mkml-models
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
rica40325-spin-first-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-spin-first-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-spin-first-v4
rica40325-spin-first-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-spin-first-v4/config.json
rica40325-spin-first-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-spin-first-v4/special_tokens_map.json
rica40325-spin-first-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-spin-first-v4/tokenizer_config.json
rica40325-spin-first-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-spin-first-v4/tokenizer.json
rica40325-spin-first-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-spin-first-v4/flywheel_model.0.safetensors
rica40325-spin-first-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 26.85it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:06, 43.26it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:06, 40.27it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:06, 39.09it/s]
Loading 0:   9%|▉         | 27/291 [00:00<00:06, 40.87it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:06, 39.70it/s]
Loading 0:  13%|█▎        | 37/291 [00:01<00:09, 26.37it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 26.27it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 34.40it/s]
Loading 0:  18%|█▊        | 53/291 [00:01<00:06, 34.61it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:06, 35.62it/s]
Loading 0:  21%|██▏       | 62/291 [00:01<00:06, 36.56it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:06, 36.96it/s]
Loading 0:  24%|██▍       | 71/291 [00:02<00:05, 37.67it/s]
Loading 0:  26%|██▌       | 75/291 [00:02<00:07, 30.32it/s]
Loading 0:  27%|██▋       | 79/291 [00:02<00:06, 32.41it/s]
Loading 0:  29%|██▊       | 83/291 [00:02<00:09, 21.79it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 29.94it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:06, 30.55it/s]
Loading 0:  34%|███▍      | 99/291 [00:02<00:05, 33.96it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 33.37it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 35.81it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 33.68it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 32.98it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 38.07it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 36.38it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 31.32it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:04, 31.51it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 29.31it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 34.12it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 33.35it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 35.69it/s]
Loading 0:  55%|█████▍    | 160/291 [00:04<00:03, 34.42it/s]
Loading 0:  57%|█████▋    | 165/291 [00:04<00:03, 37.25it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 35.68it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 38.06it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 35.76it/s]
Loading 0:  63%|██████▎   | 183/291 [00:05<00:02, 37.79it/s]
Loading 0:  64%|██████▍   | 187/291 [00:05<00:03, 26.93it/s]
Loading 0:  66%|██████▌   | 191/291 [00:05<00:03, 27.62it/s]
Loading 0:  67%|██████▋   | 195/291 [00:05<00:03, 26.71it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 31.79it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 31.76it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 34.70it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 34.09it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:01, 36.77it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:01, 34.39it/s]
Loading 0:  78%|███████▊  | 227/291 [00:06<00:01, 33.81it/s]
Loading 0:  79%|███████▉  | 231/291 [00:06<00:01, 33.70it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 25.54it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 25.80it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 33.68it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 32.40it/s]
Loading 0:  88%|████████▊ | 255/291 [00:07<00:01, 34.79it/s]
Loading 0:  89%|████████▉ | 259/291 [00:07<00:00, 33.98it/s]
Loading 0:  91%|█████████ | 264/291 [00:07<00:00, 36.90it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 35.34it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 36.62it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 34.29it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 34.15it/s]
Loading 0:  98%|█████████▊| 286/291 [00:13<00:01,  2.62it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.27it/s]
                                                            
Job rica40325-spin-first-v4-mkmlizer completed after 84.23s with status: succeeded
Stopping job with name rica40325-spin-first-v4-mkmlizer
Pipeline stage MKMLizer completed in 87.40s
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 rica40325-spin-first-v4
Waiting for inference service rica40325-spin-first-v4 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
Inference service rica40325-spin-first-v4 ready after 201.00560522079468s
Pipeline stage MKMLDeployer completed in 201.33s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.4591572284698486s
Received healthy response to inference request in 1.521895408630371s
Received healthy response to inference request in 2.6828017234802246s
Received healthy response to inference request in 2.019960641860962s
Received healthy response to inference request in 1.309354305267334s
5 requests
0 failed requests
5th percentile: 1.3518625259399415
10th percentile: 1.3943707466125488
20th percentile: 1.4793871879577636
30th percentile: 1.6215084552764893
40th percentile: 1.8207345485687256
50th percentile: 2.019960641860962
60th percentile: 2.285097074508667
70th percentile: 2.550233507156372
80th percentile: 2.8380728244781497
90th percentile: 3.148615026473999
95th percentile: 3.3038861274719236
99th percentile: 3.4281030082702637
mean time: 2.1986338615417482
Pipeline stage StressChecker completed in 11.79s
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 6.28s
Shutdown handler de-registered
rica40325-spin-first_v4 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 rica40325-spin-first-v4-profiler
Waiting for inference service rica40325-spin-first-v4-profiler to be ready
Inference service rica40325-spin-first-v4-profiler ready after 200.47069811820984s
Pipeline stage MKMLProfilerDeployer completed in 200.83s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-spin-first-v4-profiler-predictor-00001-deploymenj45n8:/code/chaiverse_profiler_1726750518 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-spin-first-v4-profiler-predictor-00001-deploymenj45n8 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726750518 && 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_1726750518/summary.json'
kubectl exec -it rica40325-spin-first-v4-profiler-predictor-00001-deploymenj45n8 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726750518/summary.json'
Pipeline stage MKMLProfilerRunner completed in 781.48s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-spin-first-v4-profiler is running
Tearing down inference service rica40325-spin-first-v4-profiler
Service rica40325-spin-first-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.10s
Shutdown handler de-registered
rica40325-spin-first_v4 status is now inactive due to auto deactivation removed underperforming models
rica40325-spin-first_v4 status is now torndown due to DeploymentManager action