cycy233-model1-3

developer_uid: cycy233

submission_id: cycy233-model1-3_v1

model_name: 486

model_group: cycy233/model1-3

status: torndown

timestamp: 2025-02-25T03:24:11+00:00

num_battles: 6490

num_wins: 3190

celo_rating: 1250.85

family_friendly_score: 0.5294

family_friendly_standard_error: 0.0070588333313657435

submission_type: basic

model_repo: cycy233/model1-3

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.8435918792181766, 'latency_mean': 1.1853473830223082, 'latency_p50': 1.1775513887405396, 'latency_p90': 1.31781325340271}, {'batch_size': 4, 'throughput': 1.738410288948648, 'latency_mean': 2.290122801065445, 'latency_p50': 2.2802284955978394, 'latency_p90': 2.5395666122436524}, {'batch_size': 5, 'throughput': 1.8478566397857157, 'latency_mean': 2.6937547636032106, 'latency_p50': 2.6734355688095093, 'latency_p90': 3.012096095085144}, {'batch_size': 8, 'throughput': 2.027107950420185, 'latency_mean': 3.922968726158142, 'latency_p50': 3.9004132747650146, 'latency_p90': 4.400042390823364}, {'batch_size': 10, 'throughput': 2.0883105213562345, 'latency_mean': 4.7433852553367615, 'latency_p50': 4.739603281021118, 'latency_p90': 5.373621344566345}, {'batch_size': 12, 'throughput': 2.1191187960352957, 'latency_mean': 5.624299663305282, 'latency_p50': 5.6129292249679565, 'latency_p90': 6.352449250221253}, {'batch_size': 15, 'throughput': 2.1273943897899654, 'latency_mean': 6.9571892249584195, 'latency_p50': 7.022786617279053, 'latency_p90': 7.798721265792847}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: 486

is_internal_developer: False

language_model: cycy233/model1-3

model_size: 8B

ranking_group: single

throughput_3p7s: 2.02

us_pacific_date: 2025-02-24

win_ratio: 0.4915254237288136

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, '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

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-model1-3-v1-mkmlizer
Waiting for job on cycy233-model1-3-v1-mkmlizer to finish
cycy233-model1-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-model1-3-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-model1-3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-model1-3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-model1-3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-model1-3-v1-mkmlizer: ║       /___/                                                         ║
cycy233-model1-3-v1-mkmlizer: ║                                                                     ║
cycy233-model1-3-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
cycy233-model1-3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-model1-3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-model1-3-v1-mkmlizer: ║                                                                     ║
cycy233-model1-3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-model1-3-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-model1-3-v1-mkmlizer: ║                                                                     ║
cycy233-model1-3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-model1-3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-model1-3-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cycy233-model1-3-v1-mkmlizer: ║                                                                     ║
cycy233-model1-3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-model1-3-v1-mkmlizer: Downloaded to shared memory in 41.356s
cycy233-model1-3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpm6o9g93n, device:0
cycy233-model1-3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-model1-3-v1-mkmlizer: quantized model in 27.331s
cycy233-model1-3-v1-mkmlizer: Processed model cycy233/model1-3 in 68.688s
cycy233-model1-3-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-model1-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-model1-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-model1-3-v1
cycy233-model1-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-model1-3-v1/config.json
cycy233-model1-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-model1-3-v1/special_tokens_map.json
cycy233-model1-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-model1-3-v1/tokenizer_config.json
cycy233-model1-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-model1-3-v1/tokenizer.json
cycy233-model1-3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-model1-3-v1/flywheel_model.0.safetensors
cycy233-model1-3-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:09, 31.53it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:05, 46.70it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:05, 51.79it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:04, 53.66it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:04, 52.30it/s]
Loading 0:  17%|█▋        | 50/291 [00:00<00:04, 53.41it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 54.30it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:03, 60.03it/s]
Loading 0:  25%|██▌       | 74/291 [00:01<00:03, 55.81it/s]
Loading 0:  27%|██▋       | 80/291 [00:01<00:03, 54.34it/s]
Loading 0:  30%|██▉       | 86/291 [00:01<00:05, 35.12it/s]
Loading 0:  32%|███▏      | 94/291 [00:01<00:04, 42.52it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 41.17it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 42.26it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 47.44it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 45.67it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:03, 45.70it/s]
Loading 0:  45%|████▍     | 130/291 [00:02<00:03, 51.14it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:03, 47.70it/s]
Loading 0:  48%|████▊     | 141/291 [00:02<00:03, 47.20it/s]
Loading 0:  51%|█████     | 147/291 [00:03<00:02, 49.59it/s]
Loading 0:  53%|█████▎    | 153/291 [00:03<00:02, 49.23it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:03, 43.83it/s]
Loading 0:  57%|█████▋    | 165/291 [00:03<00:02, 47.36it/s]
Loading 0:  58%|█████▊    | 170/291 [00:03<00:02, 46.90it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 42.22it/s]
Loading 0:  62%|██████▏   | 180/291 [00:03<00:02, 38.82it/s]
Loading 0:  64%|██████▎   | 185/291 [00:03<00:02, 41.05it/s]
Loading 0:  65%|██████▌   | 190/291 [00:04<00:03, 26.48it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:03, 26.49it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 33.65it/s]
Loading 0:  71%|███████   | 206/291 [00:04<00:02, 36.09it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:02, 38.50it/s]
Loading 0:  75%|███████▍  | 217/291 [00:04<00:01, 38.78it/s]
Loading 0:  76%|███████▋  | 222/291 [00:05<00:01, 39.16it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 44.83it/s]
Loading 0:  80%|████████  | 234/291 [00:05<00:01, 45.07it/s]
Loading 0:  82%|████████▏ | 239/291 [00:05<00:01, 34.45it/s]
Loading 0:  85%|████████▍ | 246/291 [00:05<00:01, 41.60it/s]
Loading 0:  86%|████████▋ | 251/291 [00:05<00:00, 40.91it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 39.56it/s]
Loading 0:  90%|████████▉ | 261/291 [00:06<00:00, 37.76it/s]
Loading 0:  91%|█████████ | 265/291 [00:06<00:00, 36.46it/s]
Loading 0:  92%|█████████▏| 269/291 [00:06<00:00, 37.13it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 38.98it/s]
Loading 0:  96%|█████████▌| 278/291 [00:06<00:00, 39.10it/s]
Loading 0:  97%|█████████▋| 282/291 [00:06<00:00, 32.55it/s]
Loading 0:  99%|█████████▊| 287/291 [00:12<00:01,  2.65it/s]
                                                            
Job cycy233-model1-3-v1-mkmlizer completed after 93.83s with status: succeeded
Stopping job with name cycy233-model1-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.32s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-model1-3-v1
Waiting for inference service cycy233-model1-3-v1 to be ready
Inference service cycy233-model1-3-v1 ready after 250.8159303665161s
Pipeline stage MKMLDeployer completed in 251.34s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7572646141052246s
Received healthy response to inference request in 1.513216257095337s
Received healthy response to inference request in 1.536661148071289s
Received healthy response to inference request in 1.5212440490722656s
Received healthy response to inference request in 1.1510529518127441s
5 requests
0 failed requests
5th percentile: 1.2234856128692626
10th percentile: 1.2959182739257813
20th percentile: 1.4407835960388184
30th percentile: 1.5148218154907227
40th percentile: 1.518032932281494
50th percentile: 1.5212440490722656
60th percentile: 1.527410888671875
70th percentile: 1.5335777282714844
80th percentile: 1.5807818412780763
90th percentile: 1.6690232276916503
95th percentile: 1.7131439208984374
99th percentile: 1.7484404754638672
mean time: 1.4958878040313721
Pipeline stage StressChecker completed in 8.72s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.62s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.73s
Shutdown handler de-registered
cycy233-model1-3_v1 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 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-model1-3-v1-profiler
Waiting for inference service cycy233-model1-3-v1-profiler to be ready
Inference service cycy233-model1-3-v1-profiler ready after 251.01948022842407s
Pipeline stage MKMLProfilerDeployer completed in 251.39s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-model1-3-v1-profiler-predictor-00001-deployment-6czd2sw:/code/chaiverse_profiler_1740454534 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-model1-3-v1-profiler-predictor-00001-deployment-6czd2sw --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1740454534 && python profiles.py profile --best_of_n 8 --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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1740454534/summary.json'
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2006.18s
Shutdown handler de-registered
cycy233-model1-3_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-model1-3_v1 status is now torndown due to DeploymentManager action