developer_uid: shiroe40
submission_id: cycy233-l3-bpf-v0-c1_v2
model_name: auto
model_group: cycy233/L3-bpf-v0-c1
status: torndown
timestamp: 2024-09-03T02:54:27+00:00
num_battles: 11102
num_wins: 5243
celo_rating: 1219.11
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-bpf-v0-c1
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
display_name: auto
is_internal_developer: False
language_model: cycy233/L3-bpf-v0-c1
model_size: 8B
ranking_group: single
us_pacific_date: 2024-09-02
win_ratio: 0.47225725094577553
generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
Resubmit model
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bpf-v0-c1-v2-mkmlizer
Waiting for job on cycy233-l3-bpf-v0-c1-v2-mkmlizer to finish
cycy233-l3-bpf-v0-c1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bpf-v0-c1-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bpf-v0-c1-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bpf-v0-c1-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bpf-v0-c1-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bpf-v0-c1-v2-mkmlizer: ║ /___/ ║
cycy233-l3-bpf-v0-c1-v2-mkmlizer: ║ ║
cycy233-l3-bpf-v0-c1-v2-mkmlizer: ║ Version: 0.10.1 ║
cycy233-l3-bpf-v0-c1-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bpf-v0-c1-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bpf-v0-c1-v2-mkmlizer: ║ ║
cycy233-l3-bpf-v0-c1-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bpf-v0-c1-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-bpf-v0-c1-v2-mkmlizer: ║ ║
cycy233-l3-bpf-v0-c1-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bpf-v0-c1-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bpf-v0-c1-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-bpf-v0-c1-v2-mkmlizer: ║ ║
cycy233-l3-bpf-v0-c1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bpf-v0-c1-v2-mkmlizer: Downloaded to shared memory in 37.552s
cycy233-l3-bpf-v0-c1-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2owohz_l, device:0
cycy233-l3-bpf-v0-c1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bpf-v0-c1-v2-mkmlizer: quantized model in 25.555s
cycy233-l3-bpf-v0-c1-v2-mkmlizer: Processed model cycy233/L3-bpf-v0-c1 in 63.108s
cycy233-l3-bpf-v0-c1-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bpf-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c1-v2/config.json
cycy233-l3-bpf-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c1-v2/tokenizer_config.json
cycy233-l3-bpf-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c1-v2/special_tokens_map.json
cycy233-l3-bpf-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c1-v2/tokenizer.json
cycy233-l3-bpf-v0-c1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c1-v2/flywheel_model.0.safetensors
cycy233-l3-bpf-v0-c1-v2-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:07, 37.67it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:04, 68.70it/s] Loading 0: 11%|█ | 31/291 [00:00<00:03, 85.81it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:02, 88.27it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 97.11it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 93.42it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:07, 27.60it/s] Loading 0: 31%|███ | 90/291 [00:02<00:06, 30.61it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:04, 39.55it/s] Loading 0: 40%|███▉ | 115/291 [00:02<00:03, 47.86it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:02, 60.05it/s] Loading 0: 49%|████▉ | 142/291 [00:02<00:02, 66.54it/s] Loading 0: 54%|█████▍ | 157/291 [00:02<00:01, 78.17it/s] Loading 0: 58%|█████▊ | 169/291 [00:02<00:01, 81.86it/s] Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 88.77it/s] Loading 0: 67%|██████▋ | 194/291 [00:04<00:03, 28.74it/s] Loading 0: 70%|███████ | 205/291 [00:04<00:02, 34.68it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 45.55it/s] Loading 0: 80%|███████▉ | 232/291 [00:04<00:01, 52.44it/s] Loading 0: 85%|████████▍ | 247/291 [00:04<00:00, 62.74it/s] Loading 0: 88%|████████▊ | 256/291 [00:04<00:00, 67.12it/s] Loading 0: 91%|█████████ | 265/291 [00:04<00:00, 70.31it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 75.11it/s] Loading 0: 99%|█████████▊| 287/291 [00:05<00:00, 46.62it/s]
Job cycy233-l3-bpf-v0-c1-v2-mkmlizer completed after 84.64s with status: succeeded
Stopping job with name cycy233-l3-bpf-v0-c1-v2-mkmlizer
Pipeline stage MKMLizer completed in 85.47s
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 cycy233-l3-bpf-v0-c1-v2
Waiting for inference service cycy233-l3-bpf-v0-c1-v2 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
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cycy233-l3-bpf-v0-c1-v2 ready after 150.82918691635132s
Pipeline stage MKMLDeployer completed in 151.33s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1858067512512207s
Received healthy response to inference request in 1.7759642601013184s
Received healthy response to inference request in 2.402153253555298s
Received healthy response to inference request in 1.882126808166504s
Received healthy response to inference request in 1.6493966579437256s
5 requests
0 failed requests
5th percentile: 1.674710178375244
10th percentile: 1.7000236988067627
20th percentile: 1.7506507396698
30th percentile: 1.7971967697143554
40th percentile: 1.8396617889404296
50th percentile: 1.882126808166504
60th percentile: 2.0035987854003907
70th percentile: 2.125070762634277
80th percentile: 2.229076051712036
90th percentile: 2.315614652633667
95th percentile: 2.3588839530944825
99th percentile: 2.393499393463135
mean time: 1.9790895462036133
Pipeline stage StressChecker completed in 10.99s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.22s
cycy233-l3-bpf-v0-c1_v2 status is now deployed due to DeploymentManager action
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-l3-bpf-v0-c1-v2-profiler
Waiting for inference service cycy233-l3-bpf-v0-c1-v2-profiler to be ready
Inference service cycy233-l3-bpf-v0-c1-v2-profiler ready after 150.3399600982666s
Pipeline stage MKMLProfilerDeployer completed in 150.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-bpf-v0-c1-v2-profiler-predictor-00001-deploymenk8ggz:/code/chaiverse_profiler_1725332514 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-bpf-v0-c1-v2-profiler-predictor-00001-deploymenk8ggz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725332514 && chmod +x profiles.py && python profiles.py profile --best_of_n 4 --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_1725332514/summary.json'
cycy233-l3-bpf-v0-c1_v2 status is now inactive due to auto deactivation removed underperforming models
cycy233-l3-bpf-v0-c1_v2 status is now torndown due to DeploymentManager action