cycy233-l3-bpf-v0-c4

developer_uid: shiroe40

submission_id: cycy233-l3-bpf-v0-c4_v4

model_name: auto

model_group: cycy233/L3-bpf-v0-c4

status: torndown

timestamp: 2024-09-03T02:44:08+00:00

num_battles: 13547

num_wins: 7118

celo_rating: 1255.31

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/L3-bpf-v0-c4

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: auto

is_internal_developer: False

language_model: cycy233/L3-bpf-v0-c4

model_size: 8B

ranking_group: single

us_pacific_date: 2024-09-02

win_ratio: 0.5254299844984129

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': 16, '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-c4-v4-mkmlizer
Waiting for job on cycy233-l3-bpf-v0-c4-v4-mkmlizer to finish
cycy233-l3-bpf-v0-c4-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bpf-v0-c4-v4-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-bpf-v0-c4-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-bpf-v0-c4-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-bpf-v0-c4-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-bpf-v0-c4-v4-mkmlizer: ║       /___/                                                         ║
cycy233-l3-bpf-v0-c4-v4-mkmlizer: ║                                                                     ║
cycy233-l3-bpf-v0-c4-v4-mkmlizer: ║  Version: 0.10.1                                                    ║
cycy233-l3-bpf-v0-c4-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-bpf-v0-c4-v4-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-bpf-v0-c4-v4-mkmlizer: ║                                                                     ║
cycy233-l3-bpf-v0-c4-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-bpf-v0-c4-v4-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-bpf-v0-c4-v4-mkmlizer: ║                                                                     ║
cycy233-l3-bpf-v0-c4-v4-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-bpf-v0-c4-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-bpf-v0-c4-v4-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-bpf-v0-c4-v4-mkmlizer: ║                                                                     ║
cycy233-l3-bpf-v0-c4-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bpf-v0-c4-v4-mkmlizer: Downloaded to shared memory in 24.028s
cycy233-l3-bpf-v0-c4-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzyw9lvgu, device:0
cycy233-l3-bpf-v0-c4-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_lobuf_2024-08-22: ('http://mistralai-mixtral-8x7b-3473-v130-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:43040->127.0.0.1:8080: read: connection reset by peer\n')
cycy233-l3-bpf-v0-c4-v4-mkmlizer: quantized model in 25.872s
cycy233-l3-bpf-v0-c4-v4-mkmlizer: Processed model cycy233/L3-bpf-v0-c4 in 49.900s
cycy233-l3-bpf-v0-c4-v4-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bpf-v0-c4-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bpf-v0-c4-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c4-v4
cycy233-l3-bpf-v0-c4-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c4-v4/special_tokens_map.json
cycy233-l3-bpf-v0-c4-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c4-v4/config.json
cycy233-l3-bpf-v0-c4-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c4-v4/tokenizer_config.json
cycy233-l3-bpf-v0-c4-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c4-v4/tokenizer.json
cycy233-l3-bpf-v0-c4-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c4-v4/flywheel_model.0.safetensors
cycy233-l3-bpf-v0-c4-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 39.86it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:03, 74.95it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:02, 88.35it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:02, 88.15it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:02, 88.19it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:02, 88.47it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:02, 83.89it/s]
Loading 0:  26%|██▌       | 76/291 [00:00<00:02, 83.76it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:11, 18.47it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:08, 23.54it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 32.21it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 44.49it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:03, 52.41it/s]
Loading 0:  51%|█████     | 148/291 [00:02<00:02, 64.44it/s]
Loading 0:  55%|█████▍    | 160/291 [00:03<00:01, 70.99it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:01, 81.94it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:03, 27.90it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 33.17it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 44.22it/s]
Loading 0:  77%|███████▋  | 223/291 [00:04<00:01, 51.27it/s]
Loading 0:  80%|███████▉  | 232/291 [00:04<00:01, 55.41it/s]
Loading 0:  85%|████████▍ | 247/291 [00:04<00:00, 67.83it/s]
Loading 0:  89%|████████▉ | 259/291 [00:05<00:00, 73.65it/s]
Loading 0:  92%|█████████▏| 269/291 [00:05<00:00, 78.35it/s]
Loading 0:  97%|█████████▋| 283/291 [00:05<00:00, 82.36it/s]
                                                            
Job cycy233-l3-bpf-v0-c4-v4-mkmlizer completed after 74.32s with status: succeeded
Stopping job with name cycy233-l3-bpf-v0-c4-v4-mkmlizer
Pipeline stage MKMLizer completed in 75.30s
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 cycy233-l3-bpf-v0-c4-v4
Waiting for inference service cycy233-l3-bpf-v0-c4-v4 to be ready
Inference service cycy233-l3-bpf-v0-c4-v4 ready after 150.5917296409607s
Pipeline stage MKMLDeployer completed in 151.60s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.240255832672119s
Received healthy response to inference request in 1.5183579921722412s
Received healthy response to inference request in 1.969651222229004s
Received healthy response to inference request in 1.7472305297851562s
Received healthy response to inference request in 2.054074287414551s
5 requests
0 failed requests
5th percentile: 1.5641324996948243
10th percentile: 1.6099070072174073
20th percentile: 1.7014560222625732
30th percentile: 1.7917146682739258
40th percentile: 1.8806829452514648
50th percentile: 1.969651222229004
60th percentile: 2.0034204483032227
70th percentile: 2.0371896743774416
80th percentile: 2.0913105964660645
90th percentile: 2.1657832145690916
95th percentile: 2.2030195236206054
99th percentile: 2.2328085708618164
mean time: 1.9059139728546142
Pipeline stage StressChecker completed in 10.34s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 7.50s
cycy233-l3-bpf-v0-c4_v4 status is now deployed due to DeploymentManager action
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-l3-bpf-v0-c4-v4-profiler
Waiting for inference service cycy233-l3-bpf-v0-c4-v4-profiler to be ready
Inference service cycy233-l3-bpf-v0-c4-v4-profiler ready after 150.57690620422363s
Pipeline stage MKMLProfilerDeployer completed in 151.00s
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-c4-v4-profiler-predictor-00001-deploymenr5v64:/code/chaiverse_profiler_1725331880 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-bpf-v0-c4-v4-profiler-predictor-00001-deploymenr5v64 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725331880 && chmod +x profiles.py && python profiles.py profile --best_of_n 16 --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_1725331880/summary.json'
cycy233-l3-bpf-v0-c4_v4 status is now inactive due to auto deactivation removed underperforming models
cycy233-l3-bpf-v0-c4_v4 status is now torndown due to DeploymentManager action