cycy233-l3-p-v5-c1

submission_id: cycy233-l3-p-v5-c1_v3

developer_uid: shiroe40

alignment_samples: 12684

alignment_score: -0.10880103903254351

best_of: 16

celo_rating: 1241.76

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': ['<|end_header_id|>', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: False

language_model: cycy233/L3-p-v5-c1

latencies: [{'batch_size': 1, 'throughput': 0.9145738940173362, 'latency_mean': 1.0933468794822694, 'latency_p50': 1.0995087623596191, 'latency_p90': 1.2139590978622437}, {'batch_size': 4, 'throughput': 1.8274968412117796, 'latency_mean': 2.1819527769088745, 'latency_p50': 2.156458616256714, 'latency_p90': 2.480332088470459}, {'batch_size': 5, 'throughput': 1.9075102494867127, 'latency_mean': 2.613308149576187, 'latency_p50': 2.61690616607666, 'latency_p90': 2.9116379737854006}, {'batch_size': 8, 'throughput': 2.025861131377713, 'latency_mean': 3.919261761903763, 'latency_p50': 3.9209364652633667, 'latency_p90': 4.389924359321594}, {'batch_size': 10, 'throughput': 2.0122725624544535, 'latency_mean': 4.923188816308976, 'latency_p50': 4.885538816452026, 'latency_p90': 5.697251963615417}, {'batch_size': 12, 'throughput': 2.0570292182641943, 'latency_mean': 5.759002622365951, 'latency_p50': 5.726300239562988, 'latency_p90': 6.724875545501709}, {'batch_size': 15, 'throughput': 2.040011785004986, 'latency_mean': 7.196201275587082, 'latency_p50': 7.306679844856262, 'latency_p90': 8.04200370311737}]

max_input_tokens: 512

max_output_tokens: 64

model_architecture: LlamaForCausalLM

model_group: cycy233/L3-p-v5-c1

model_name: auto

model_num_parameters: 8030261248.0

model_repo: cycy233/L3-p-v5-c1

model_size: 8B

num_battles: 12683

num_wins: 6153

propriety_score: 0.75177304964539

propriety_total_count: 1128.0

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 2.03

timestamp: 2024-09-14T10:27:40+00:00

us_pacific_date: 2024-09-14

win_ratio: 0.4851375857446976

Download Preference Data

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 cycy233-l3-p-v5-c1-v3-mkmlizer
Waiting for job on cycy233-l3-p-v5-c1-v3-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
cycy233-l3-p-v5-c1-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-p-v5-c1-v3-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-p-v5-c1-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-p-v5-c1-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-p-v5-c1-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-p-v5-c1-v3-mkmlizer: ║       /___/                                                         ║
cycy233-l3-p-v5-c1-v3-mkmlizer: ║                                                                     ║
cycy233-l3-p-v5-c1-v3-mkmlizer: ║  Version: 0.10.1                                                    ║
cycy233-l3-p-v5-c1-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-p-v5-c1-v3-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-p-v5-c1-v3-mkmlizer: ║                                                                     ║
cycy233-l3-p-v5-c1-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-p-v5-c1-v3-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-p-v5-c1-v3-mkmlizer: ║                                                                     ║
cycy233-l3-p-v5-c1-v3-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-p-v5-c1-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-p-v5-c1-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-p-v5-c1-v3-mkmlizer: ║                                                                     ║
cycy233-l3-p-v5-c1-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-p-v5-c1-v3-mkmlizer: Downloaded to shared memory in 33.039s
cycy233-l3-p-v5-c1-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp05aat9yw, device:0
cycy233-l3-p-v5-c1-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-p-v5-c1-v3-mkmlizer: quantized model in 26.591s
cycy233-l3-p-v5-c1-v3-mkmlizer: Processed model cycy233/L3-p-v5-c1 in 59.630s
cycy233-l3-p-v5-c1-v3-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-p-v5-c1-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-p-v5-c1-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-p-v5-c1-v3
cycy233-l3-p-v5-c1-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-p-v5-c1-v3/config.json
cycy233-l3-p-v5-c1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-p-v5-c1-v3/tokenizer_config.json
cycy233-l3-p-v5-c1-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-p-v5-c1-v3/special_tokens_map.json
cycy233-l3-p-v5-c1-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-p-v5-c1-v3/tokenizer.json
cycy233-l3-p-v5-c1-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-p-v5-c1-v3/flywheel_model.0.safetensors
cycy233-l3-p-v5-c1-v3-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 4/291 [00:00<00:07, 37.98it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 62.26it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:03, 72.65it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:03, 78.09it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:03, 79.51it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:02, 81.77it/s]
Loading 0:  20%|█▉        | 58/291 [00:00<00:03, 76.04it/s]
Loading 0:  23%|██▎       | 67/291 [00:00<00:03, 74.62it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 69.46it/s]
Loading 0:  29%|██▉       | 84/291 [00:02<00:10, 19.13it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:09, 21.65it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:07, 25.62it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:05, 32.50it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:04, 39.71it/s]
Loading 0:  43%|████▎     | 124/291 [00:02<00:03, 47.87it/s]
Loading 0:  46%|████▌     | 133/291 [00:03<00:03, 52.18it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:02, 66.40it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:01, 68.36it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:01, 73.10it/s]
Loading 0:  62%|██████▏   | 180/291 [00:03<00:01, 81.48it/s]
Loading 0:  65%|██████▍   | 189/291 [00:04<00:04, 23.62it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:03, 27.12it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:02, 38.96it/s]
Loading 0:  77%|███████▋  | 223/291 [00:05<00:01, 47.29it/s]
Loading 0:  80%|███████▉  | 232/291 [00:05<00:01, 51.60it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 64.01it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 67.19it/s]
Loading 0:  91%|█████████ | 265/291 [00:05<00:00, 69.48it/s]
Loading 0:  95%|█████████▌| 277/291 [00:05<00:00, 73.89it/s]
Loading 0:  98%|█████████▊| 286/291 [00:05<00:00, 77.16it/s]
                                                            
Job cycy233-l3-p-v5-c1-v3-mkmlizer completed after 85.84s with status: succeeded
Stopping job with name cycy233-l3-p-v5-c1-v3-mkmlizer
Pipeline stage MKMLizer completed in 86.74s
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-p-v5-c1-v3
Waiting for inference service cycy233-l3-p-v5-c1-v3 to be ready
Failed to get response for submission blend_puheb_2024-09-09: ('http://sao10k-mn-12b-lyra-v4a1-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:54026->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission blend_hokok_2024-09-09: ('http://neversleep-noromaid-v0-8068-v150-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service cycy233-l3-p-v5-c1-v3 ready after 161.23309755325317s
Pipeline stage MKMLDeployer completed in 166.58s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.495166063308716s
Received healthy response to inference request in 5.537160158157349s
Received healthy response to inference request in 1.709752082824707s
Received healthy response to inference request in 1.7283403873443604s
Received healthy response to inference request in 2.1941394805908203s
5 requests
0 failed requests
5th percentile: 1.7134697437286377
10th percentile: 1.7171874046325684
20th percentile: 1.7246227264404297
30th percentile: 1.8215002059936523
40th percentile: 2.0078198432922365
50th percentile: 2.1941394805908203
60th percentile: 2.3145501136779787
70th percentile: 2.4349607467651366
80th percentile: 3.1035648822784427
90th percentile: 4.320362520217896
95th percentile: 4.928761339187622
99th percentile: 5.415480394363403
mean time: 2.7329116344451903
Pipeline stage StressChecker completed in 19.24s
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 7.51s
Shutdown handler de-registered
cycy233-l3-p-v5-c1_v3 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 0.11s
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 cycy233-l3-p-v5-c1-v3-profiler
Waiting for inference service cycy233-l3-p-v5-c1-v3-profiler to be ready
Inference service cycy233-l3-p-v5-c1-v3-profiler ready after 170.4365406036377s
Pipeline stage MKMLProfilerDeployer completed in 171.57s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-l3-p-v5-c1-v3-profiler-predictor-00001-deployment-lvwrq:/code/chaiverse_profiler_1726310160 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-l3-p-v5-c1-v3-profiler-predictor-00001-deployment-lvwrq --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726310160 && 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_1726310160/summary.json'
kubectl exec -it cycy233-l3-p-v5-c1-v3-profiler-predictor-00001-deployment-lvwrq --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726310160/summary.json'
Pipeline stage MKMLProfilerRunner completed in 834.95s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-l3-p-v5-c1-v3-profiler is running
Tearing down inference service cycy233-l3-p-v5-c1-v3-profiler
Service cycy233-l3-p-v5-c1-v3-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.73s
Shutdown handler de-registered
cycy233-l3-p-v5-c1_v3 status is now inactive due to auto deactivation removed underperforming models