rica40325-reference

developer_uid: rica40325
submission_id: rica40325-reference_v1
model_name: rica40325-reference_v1
model_group: rica40325/reference
status: torndown
timestamp: 2024-09-04T15:30:36+00:00
num_battles: 13023
num_wins: 6607
celo_rating: 1245.95
family_friendly_score: 0.0
submission_type: basic
model_repo: rica40325/reference
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: rica40325-reference_v1
is_internal_developer: False
language_model: rica40325/reference
model_size: 8B
ranking_group: single
us_pacific_date: 2024-09-04
win_ratio: 0.5073331797588881
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': 512, 'best_of': 16, '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
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name rica40325-reference-v1-mkmlizer
Waiting for job on rica40325-reference-v1-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
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-reference-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-reference-v1-mkmlizer: ║     _____            __           __                                ║
rica40325-reference-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-reference-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-reference-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-reference-v1-mkmlizer: ║       /___/                                                         ║
rica40325-reference-v1-mkmlizer: ║                                                                     ║
rica40325-reference-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
rica40325-reference-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-reference-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-reference-v1-mkmlizer: ║                                                                     ║
rica40325-reference-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-reference-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-reference-v1-mkmlizer: ║                                                                     ║
rica40325-reference-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-reference-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-reference-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rica40325-reference-v1-mkmlizer: ║                                                                     ║
rica40325-reference-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-reference-v1-mkmlizer: Downloaded to shared memory in 74.470s
rica40325-reference-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcmejk97t, device:0
rica40325-reference-v1-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
rica40325-reference-v1-mkmlizer: quantized model in 29.322s
rica40325-reference-v1-mkmlizer: Processed model rica40325/reference in 103.792s
rica40325-reference-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-reference-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-reference-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-reference-v1
rica40325-reference-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-reference-v1/config.json
rica40325-reference-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-reference-v1/special_tokens_map.json
rica40325-reference-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-reference-v1/tokenizer_config.json
rica40325-reference-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-reference-v1/tokenizer.json
rica40325-reference-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-reference-v1/flywheel_model.0.safetensors
rica40325-reference-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:11, 24.51it/s]
Loading 0:   3%|▎         | 10/291 [00:00<00:08, 34.01it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:11, 24.57it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 33.80it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:08, 31.81it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 38.47it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:10, 24.18it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 25.64it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 31.51it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 30.43it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:07, 33.30it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:07, 32.42it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 35.05it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 32.88it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 33.36it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 32.50it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 23.65it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 24.45it/s]
Loading 0:  31%|███       | 90/291 [00:03<00:07, 28.63it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:06, 28.50it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:06, 31.87it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:06, 31.03it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 33.83it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 32.64it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 33.15it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 37.95it/s]
Loading 0:  44%|████▎     | 127/291 [00:04<00:04, 35.93it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 31.44it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:04, 31.02it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 28.36it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 32.92it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 31.41it/s]
Loading 0:  54%|█████▎    | 156/291 [00:05<00:04, 33.72it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:04, 31.71it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 34.15it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 32.36it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 35.17it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 33.57it/s]
Loading 0:  63%|██████▎   | 184/291 [00:05<00:02, 39.54it/s]
Loading 0:  65%|██████▍   | 189/291 [00:06<00:04, 24.24it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:03, 25.39it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 32.26it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 31.36it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 34.04it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 31.95it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:02, 33.78it/s]
Loading 0:  77%|███████▋  | 223/291 [00:07<00:02, 32.05it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:02, 31.33it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 31.69it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 25.18it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 24.76it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 32.31it/s]
Loading 0:  86%|████████▌ | 250/291 [00:08<00:01, 31.32it/s]
Loading 0:  87%|████████▋ | 254/291 [00:08<00:01, 33.23it/s]
Loading 0:  89%|████████▊ | 258/291 [00:08<00:01, 29.03it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 33.32it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 32.34it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 35.16it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 31.80it/s]
Loading 0:  97%|█████████▋| 281/291 [00:09<00:00, 31.18it/s]
Loading 0:  98%|█████████▊| 285/291 [00:09<00:00, 33.17it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  2.36it/s]
                                                            
Job rica40325-reference-v1-mkmlizer completed after 125.16s with status: succeeded
Stopping job with name rica40325-reference-v1-mkmlizer
Pipeline stage MKMLizer completed in 126.29s
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-reference-v1
Waiting for inference service rica40325-reference-v1 to be ready
Inference service rica40325-reference-v1 ready after 141.14044284820557s
Pipeline stage MKMLDeployer completed in 141.56s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3951632976531982s
Received healthy response to inference request in 1.4384369850158691s
Received healthy response to inference request in 1.5648183822631836s
Received healthy response to inference request in 1.7573449611663818s
Received healthy response to inference request in 2.2274012565612793s
5 requests
0 failed requests
5th percentile: 1.4637132644653321
10th percentile: 1.4889895439147949
20th percentile: 1.5395421028137206
30th percentile: 1.6033236980438232
40th percentile: 1.6803343296051025
50th percentile: 1.7573449611663818
60th percentile: 1.9453674793243407
70th percentile: 2.1333899974822996
80th percentile: 2.260953664779663
90th percentile: 2.3280584812164307
95th percentile: 2.3616108894348145
99th percentile: 2.3884528160095213
mean time: 1.8766329765319825
Pipeline stage StressChecker completed in 10.63s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 4.05s
rica40325-reference_v1 status is now deployed due to DeploymentManager action
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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-reference-v1-profiler
Waiting for inference service rica40325-reference-v1-profiler to be ready
Inference service rica40325-reference-v1-profiler ready after 380.9525475502014s
Pipeline stage MKMLProfilerDeployer completed in 381.37s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rica40325-reference-v1-profiler-predictor-00001-deploymentcdpf9:/code/chaiverse_profiler_1725464545 --namespace tenant-chaiml-guanaco
kubectl exec -it rica40325-reference-v1-profiler-predictor-00001-deploymentcdpf9 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725464545 && python profiles.py profile --best_of_n 16 --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_1725464545/summary.json'
Received signal 15, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rica40325-reference-v1-profiler is running
Tearing down inference service rica40325-reference-v1-profiler
Service rica40325-reference-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.72s
Shutdown handler unregistered and original handlers restored
rica40325-reference_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-reference_v1 status is now torndown due to DeploymentManager action