cycy233-model4-7

developer_uid: cycy233

submission_id: cycy233-model4-7_v1

model_name: 486

model_group: cycy233/model4-7

status: torndown

timestamp: 2025-03-03T07:35:00+00:00

num_battles: 6236

num_wins: 3014

celo_rating: 1248.4

family_friendly_score: 0.515

family_friendly_standard_error: 0.007067885115082163

submission_type: basic

model_repo: cycy233/model4-7

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': 0.8551498647995245, 'latency_mean': 1.1693249452114105, 'latency_p50': 1.1682881116867065, 'latency_p90': 1.2968875408172607}, {'batch_size': 4, 'throughput': 1.790880356008042, 'latency_mean': 2.2235182058811187, 'latency_p50': 2.1978269815444946, 'latency_p90': 2.480514168739319}, {'batch_size': 5, 'throughput': 1.919337711928043, 'latency_mean': 2.587018631696701, 'latency_p50': 2.565347194671631, 'latency_p90': 2.902236557006836}, {'batch_size': 8, 'throughput': 2.120849245418203, 'latency_mean': 3.7452615773677826, 'latency_p50': 3.739474058151245, 'latency_p90': 4.237939453125}, {'batch_size': 10, 'throughput': 2.1604624453529606, 'latency_mean': 4.588406893014908, 'latency_p50': 4.632211089134216, 'latency_p90': 5.139769649505615}, {'batch_size': 12, 'throughput': 2.1981235469980525, 'latency_mean': 5.405236378908158, 'latency_p50': 5.447193741798401, 'latency_p90': 6.052629899978637}, {'batch_size': 15, 'throughput': 2.1998246063361817, 'latency_mean': 6.730747809410095, 'latency_p50': 6.767307758331299, 'latency_p90': 7.617307448387146}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: 486

is_internal_developer: False

language_model: cycy233/model4-7

model_size: 8B

ranking_group: single

throughput_3p7s: 2.13

us_pacific_date: 2025-03-02

win_ratio: 0.4833226427196921

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': ['<|eot_id|>', '\n'], '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-model4-7-v1-mkmlizer
Waiting for job on cycy233-model4-7-v1-mkmlizer to finish
cycy233-model4-7-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-model4-7-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-model4-7-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-model4-7-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-model4-7-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-model4-7-v1-mkmlizer: ║       /___/                                                         ║
cycy233-model4-7-v1-mkmlizer: ║                                                                     ║
cycy233-model4-7-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
cycy233-model4-7-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-model4-7-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-model4-7-v1-mkmlizer: ║                                                                     ║
cycy233-model4-7-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-model4-7-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-model4-7-v1-mkmlizer: ║                                                                     ║
cycy233-model4-7-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-model4-7-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-model4-7-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cycy233-model4-7-v1-mkmlizer: ║                                                                     ║
cycy233-model4-7-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-model4-7-v1-mkmlizer: Downloaded to shared memory in 28.779s
cycy233-model4-7-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprsdybs66, device:0
cycy233-model4-7-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-model4-7-v1-mkmlizer: quantized model in 27.289s
cycy233-model4-7-v1-mkmlizer: Processed model cycy233/model4-7 in 56.069s
cycy233-model4-7-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-model4-7-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-model4-7-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-model4-7-v1
cycy233-model4-7-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-model4-7-v1/config.json
cycy233-model4-7-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-model4-7-v1/special_tokens_map.json
cycy233-model4-7-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-model4-7-v1/tokenizer_config.json
cycy233-model4-7-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-model4-7-v1/tokenizer.json
cycy233-model4-7-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:09, 31.08it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 51.39it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:06, 44.22it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:06, 42.82it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:05, 49.88it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 46.15it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 45.28it/s]
Loading 0:  17%|█▋        | 49/291 [00:01<00:04, 51.33it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:05, 46.47it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 43.73it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:04, 46.65it/s]
Loading 0:  24%|██▍       | 71/291 [00:01<00:04, 44.94it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:04, 44.05it/s]
Loading 0:  28%|██▊       | 81/291 [00:01<00:04, 43.49it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:07, 25.97it/s]
Loading 0:  32%|███▏      | 93/291 [00:02<00:05, 33.59it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:05, 35.78it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 38.64it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:04, 40.94it/s]
Loading 0:  39%|███▉      | 113/291 [00:02<00:05, 33.85it/s]
Loading 0:  41%|████      | 120/291 [00:02<00:04, 40.80it/s]
Loading 0:  43%|████▎     | 125/291 [00:03<00:04, 40.04it/s]
Loading 0:  45%|████▍     | 130/291 [00:03<00:04, 39.28it/s]
Loading 0:  46%|████▋     | 135/291 [00:03<00:03, 40.58it/s]
Loading 0:  48%|████▊     | 140/291 [00:03<00:04, 34.12it/s]
Loading 0:  51%|█████     | 147/291 [00:03<00:03, 40.37it/s]
Loading 0:  52%|█████▏    | 152/291 [00:03<00:03, 39.33it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:03, 39.02it/s]
Loading 0:  56%|█████▌    | 162/291 [00:04<00:03, 39.60it/s]
Loading 0:  57%|█████▋    | 167/291 [00:04<00:03, 33.03it/s]
Loading 0:  60%|██████    | 175/291 [00:04<00:02, 42.86it/s]
Loading 0:  62%|██████▏   | 180/291 [00:04<00:02, 44.12it/s]
Loading 0:  64%|██████▍   | 186/291 [00:04<00:02, 42.66it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:03, 31.44it/s]
Loading 0:  67%|██████▋   | 195/291 [00:04<00:03, 31.89it/s]
Loading 0:  69%|██████▉   | 201/291 [00:05<00:02, 36.57it/s]
Loading 0:  71%|███████   | 206/291 [00:05<00:02, 37.44it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:02, 38.89it/s]
Loading 0:  74%|███████▍  | 216/291 [00:05<00:01, 41.32it/s]
Loading 0:  76%|███████▌  | 221/291 [00:05<00:01, 35.65it/s]
Loading 0:  78%|███████▊  | 228/291 [00:05<00:01, 41.69it/s]
Loading 0:  80%|████████  | 233/291 [00:05<00:01, 41.55it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 42.53it/s]
Loading 0:  84%|████████▎ | 243/291 [00:06<00:01, 43.96it/s]
Loading 0:  85%|████████▌ | 248/291 [00:06<00:01, 35.55it/s]
Loading 0:  88%|████████▊ | 255/291 [00:06<00:00, 43.14it/s]
Loading 0:  89%|████████▉ | 260/291 [00:06<00:00, 42.04it/s]
Loading 0:  91%|█████████ | 265/291 [00:06<00:00, 40.79it/s]
Loading 0:  93%|█████████▎| 270/291 [00:06<00:00, 41.81it/s]
Loading 0:  95%|█████████▍| 275/291 [00:06<00:00, 34.44it/s]
Loading 0:  97%|█████████▋| 281/291 [00:07<00:00, 38.74it/s]
Loading 0:  98%|█████████▊| 286/291 [00:07<00:00, 35.20it/s]
Loading 0: 100%|█████████▉| 290/291 [00:12<00:00,  2.89it/s]
                                                            
Job cycy233-model4-7-v1-mkmlizer completed after 83.32s with status: succeeded
Stopping job with name cycy233-model4-7-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.83s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-model4-7-v1
Waiting for inference service cycy233-model4-7-v1 to be ready
Inference service cycy233-model4-7-v1 ready after 130.56431078910828s
Pipeline stage MKMLDeployer completed in 131.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9454050064086914s
Received healthy response to inference request in 1.34169602394104s
Received healthy response to inference request in 0.7016818523406982s
Received healthy response to inference request in 1.0891180038452148s
Received healthy response to inference request in 1.3123250007629395s
5 requests
0 failed requests
5th percentile: 0.7791690826416016
10th percentile: 0.8566563129425049
20th percentile: 1.0116307735443115
30th percentile: 1.1337594032287597
40th percentile: 1.2230422019958496
50th percentile: 1.3123250007629395
60th percentile: 1.3240734100341798
70th percentile: 1.3358218193054199
80th percentile: 1.4624378204345705
90th percentile: 1.703921413421631
95th percentile: 1.824663209915161
99th percentile: 1.9212566471099852
mean time: 1.2780451774597168
Pipeline stage StressChecker completed in 7.70s
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 0.73s
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 0.64s
Shutdown handler de-registered
cycy233-model4-7_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 0.11s
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-model4-7-v1-profiler
Waiting for inference service cycy233-model4-7-v1-profiler to be ready
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 2319.57s
Shutdown handler de-registered
cycy233-model4-7_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-model4-7_v1 status is now torndown due to DeploymentManager action