submission_id: cycy233-l3-bpf-v0-c4_v5
developer_uid: shiroe40
alignment_samples: 12836
alignment_score: -0.5890454640251654
best_of: 4
celo_rating: 1224.09
display_name: auto
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}
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}
is_internal_developer: False
language_model: cycy233/L3-bpf-v0-c4
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: cycy233/L3-bpf-v0-c4
model_name: auto
model_num_parameters: 8030261248.0
model_repo: cycy233/L3-bpf-v0-c4
model_size: 8B
num_battles: 12836
num_wins: 6151
propriety_score: 0.7166821994408201
propriety_total_count: 1073.0
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-09-03T02:46:34+00:00
us_pacific_date: 2024-09-02
win_ratio: 0.47919912745403553
Download Preference Data
Resubmit model
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name cycy233-l3-bpf-v0-c4-v5-mkmlizer
Waiting for job on cycy233-l3-bpf-v0-c4-v5-mkmlizer to finish
cycy233-l3-bpf-v0-c4-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-bpf-v0-c4-v5-mkmlizer: ║ _____ __ __ ║
cycy233-l3-bpf-v0-c4-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-bpf-v0-c4-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-bpf-v0-c4-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-bpf-v0-c4-v5-mkmlizer: ║ /___/ ║
cycy233-l3-bpf-v0-c4-v5-mkmlizer: ║ ║
cycy233-l3-bpf-v0-c4-v5-mkmlizer: ║ Version: 0.10.1 ║
cycy233-l3-bpf-v0-c4-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-bpf-v0-c4-v5-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-bpf-v0-c4-v5-mkmlizer: ║ ║
cycy233-l3-bpf-v0-c4-v5-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-bpf-v0-c4-v5-mkmlizer: ║ belonging to: ║
cycy233-l3-bpf-v0-c4-v5-mkmlizer: ║ ║
cycy233-l3-bpf-v0-c4-v5-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-bpf-v0-c4-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-bpf-v0-c4-v5-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-bpf-v0-c4-v5-mkmlizer: ║ ║
cycy233-l3-bpf-v0-c4-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-bpf-v0-c4-v5-mkmlizer: Downloaded to shared memory in 20.652s
cycy233-l3-bpf-v0-c4-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp63f48ia7, device:0
cycy233-l3-bpf-v0-c4-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-bpf-v0-c4-v5-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-bpf-v0-c4-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-bpf-v0-c4-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c4-v5
cycy233-l3-bpf-v0-c4-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c4-v5/config.json
cycy233-l3-bpf-v0-c4-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c4-v5/special_tokens_map.json
cycy233-l3-bpf-v0-c4-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c4-v5/tokenizer_config.json
cycy233-l3-bpf-v0-c4-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c4-v5/tokenizer.json
cycy233-l3-bpf-v0-c4-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-bpf-v0-c4-v5/flywheel_model.0.safetensors
cycy233-l3-bpf-v0-c4-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:07, 38.87it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:03, 71.50it/s] Loading 0: 11%|█ | 31/291 [00:00<00:02, 89.46it/s] Loading 0: 15%|█▍ | 43/291 [00:00<00:02, 87.63it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:02, 96.27it/s] Loading 0: 24%|██▍ | 70/291 [00:00<00:02, 93.07it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:07, 27.66it/s] Loading 0: 31%|███ | 90/291 [00:02<00:06, 30.58it/s] Loading 0: 33%|███▎ | 97/291 [00:02<00:05, 34.19it/s] Loading 0: 38%|███▊ | 112/291 [00:02<00:03, 47.15it/s] Loading 0: 43%|████▎ | 124/291 [00:02<00:03, 54.54it/s] Loading 0: 46%|████▌ | 133/291 [00:02<00:02, 59.83it/s] Loading 0: 49%|████▉ | 142/291 [00:02<00:02, 65.39it/s] Loading 0: 54%|█████▍ | 157/291 [00:02<00:01, 77.63it/s] Loading 0: 58%|█████▊ | 169/291 [00:02<00:01, 80.93it/s] Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 87.94it/s] Loading 0: 67%|██████▋ | 194/291 [00:04<00:03, 26.58it/s] Loading 0: 69%|██████▉ | 202/291 [00:04<00:02, 30.73it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:02, 36.40it/s] Loading 0: 77%|███████▋ | 223/291 [00:04<00:01, 45.17it/s] Loading 0: 82%|████████▏ | 238/291 [00:04<00:00, 57.50it/s] Loading 0: 86%|████████▌ | 250/291 [00:04<00:00, 63.86it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 74.66it/s] Loading 0: 95%|█████████▍| 275/291 [00:05<00:00, 78.24it/s] Loading 0: 98%|█████████▊| 286/291 [00:05<00:00, 78.77it/s]
Job cycy233-l3-bpf-v0-c4-v5-mkmlizer completed after 64.05s with status: succeeded
Stopping job with name cycy233-l3-bpf-v0-c4-v5-mkmlizer
Pipeline stage MKMLizer completed in 65.24s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-l3-bpf-v0-c4-v5
Waiting for inference service cycy233-l3-bpf-v0-c4-v5 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission blend_fedek_2024-08-24: ('http://chaiml-elo-alignment-run-3-v36-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
Inference service cycy233-l3-bpf-v0-c4-v5 ready after 150.71542406082153s
Pipeline stage MKMLDeployer completed in 151.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.949977159500122s
Received healthy response to inference request in 1.645040512084961s
Received healthy response to inference request in 1.6675395965576172s
Received healthy response to inference request in 1.6089651584625244s
Received healthy response to inference request in 1.3538227081298828s
5 requests
0 failed requests
5th percentile: 1.4048511981964111
10th percentile: 1.4558796882629395
20th percentile: 1.557936668395996
30th percentile: 1.6161802291870118
40th percentile: 1.6306103706359862
50th percentile: 1.645040512084961
60th percentile: 1.6540401458740235
70th percentile: 1.663039779663086
80th percentile: 1.7240271091461181
90th percentile: 1.8370021343231202
95th percentile: 1.8934896469116211
99th percentile: 1.9386796569824218
mean time: 1.6450690269470214
Pipeline stage StressChecker completed in 9.40s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 8.07s
cycy233-l3-bpf-v0-c4_v5 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-v5-profiler
Waiting for inference service cycy233-l3-bpf-v0-c4-v5-profiler to be ready
Inference service cycy233-l3-bpf-v0-c4-v5-profiler ready after 150.36974930763245s
Pipeline stage MKMLProfilerDeployer completed in 150.86s
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-v5-profiler-predictor-00001-deploymenthghw:/code/chaiverse_profiler_1725332023 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-bpf-v0-c4-v5-profiler-predictor-00001-deploymenthghw --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725332023 && 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_1725332023/summary.json'
cycy233-l3-bpf-v0-c4_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics