cycy233-model4-10

developer_uid: cycy233

submission_id: cycy233-model4-10_v1

model_name: 486

model_group: cycy233/model4-10

status: torndown

timestamp: 2025-03-03T07:35:37+00:00

num_battles: 6062

num_wins: 2834

celo_rating: 1239.19

family_friendly_score: 0.5146

family_friendly_standard_error: 0.007068052631382989

submission_type: basic

model_repo: cycy233/model4-10

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': 0.4305945703197532, 'latency_mean': 2.3222685194015504, 'latency_p50': 1.776717185974121, 'latency_p90': 3.6279923915863033}, {'batch_size': 3, 'throughput': 1.4939344309302311, 'latency_mean': 1.9990349459648131, 'latency_p50': 1.931730031967163, 'latency_p90': 2.1246290683746336}, {'batch_size': 5, 'throughput': 1.2020254718879029, 'latency_mean': 4.120767574310303, 'latency_p50': 3.9337122440338135, 'latency_p90': 5.140776133537292}, {'batch_size': 6, 'throughput': 2.011810505464617, 'latency_mean': 2.963450707197189, 'latency_p50': 2.9737956523895264, 'latency_p90': 3.322427010536194}, {'batch_size': 8, 'throughput': 2.1166899958807526, 'latency_mean': 3.7516031634807585, 'latency_p50': 3.735415816307068, 'latency_p90': 4.261038327217102}, {'batch_size': 10, 'throughput': 1.3581435086087534, 'latency_mean': 7.229017055034637, 'latency_p50': 7.257298111915588, 'latency_p90': 7.944958782196045}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: 486

is_internal_developer: False

language_model: cycy233/model4-10

model_size: 8B

ranking_group: single

throughput_3p7s: 1.24

us_pacific_date: 2025-03-02

win_ratio: 0.4675024744308809

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-model4-10-v1-mkmlizer
Waiting for job on cycy233-model4-10-v1-mkmlizer to finish
cycy233-model4-10-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-model4-10-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-model4-10-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-model4-10-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-model4-10-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-model4-10-v1-mkmlizer: ║       /___/                                                         ║
cycy233-model4-10-v1-mkmlizer: ║                                                                     ║
cycy233-model4-10-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
cycy233-model4-10-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-model4-10-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-model4-10-v1-mkmlizer: ║                                                                     ║
cycy233-model4-10-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-model4-10-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-model4-10-v1-mkmlizer: ║                                                                     ║
cycy233-model4-10-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-model4-10-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-model4-10-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cycy233-model4-10-v1-mkmlizer: ║                                                                     ║
cycy233-model4-10-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-model4-10-v1-mkmlizer: Downloaded to shared memory in 26.548s
cycy233-model4-10-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpp7f0l0x_, device:0
cycy233-model4-10-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-model4-10-v1-mkmlizer: quantized model in 27.437s
cycy233-model4-10-v1-mkmlizer: Processed model cycy233/model4-10 in 53.986s
cycy233-model4-10-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-model4-10-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-model4-10-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-model4-10-v1
cycy233-model4-10-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-model4-10-v1/config.json
cycy233-model4-10-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-model4-10-v1/special_tokens_map.json
cycy233-model4-10-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-model4-10-v1/tokenizer_config.json
cycy233-model4-10-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-model4-10-v1/tokenizer.json
cycy233-model4-10-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:09, 28.97it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:06, 45.79it/s]
Loading 0:   6%|▌         | 17/291 [00:00<00:06, 44.33it/s]
Loading 0:   8%|▊         | 22/291 [00:00<00:06, 43.98it/s]
Loading 0:  10%|▉         | 28/291 [00:00<00:06, 40.07it/s]
Loading 0:  11%|█▏        | 33/291 [00:00<00:06, 39.43it/s]
Loading 0:  13%|█▎        | 39/291 [00:00<00:05, 44.23it/s]
Loading 0:  15%|█▌        | 44/291 [00:01<00:05, 44.27it/s]
Loading 0:  17%|█▋        | 49/291 [00:01<00:05, 44.87it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:05, 40.97it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 39.97it/s]
Loading 0:  23%|██▎       | 66/291 [00:01<00:05, 43.77it/s]
Loading 0:  24%|██▍       | 71/291 [00:01<00:05, 43.08it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:05, 42.73it/s]
Loading 0:  28%|██▊       | 81/291 [00:01<00:04, 43.85it/s]
Loading 0:  30%|██▉       | 86/291 [00:02<00:08, 24.74it/s]
Loading 0:  32%|███▏      | 93/291 [00:02<00:06, 32.17it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:05, 34.78it/s]
Loading 0:  36%|███▌      | 104/291 [00:02<00:05, 34.57it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 42.96it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:04, 40.40it/s]
Loading 0:  42%|████▏     | 123/291 [00:03<00:04, 39.16it/s]
Loading 0:  44%|████▍     | 129/291 [00:03<00:03, 43.60it/s]
Loading 0:  46%|████▌     | 134/291 [00:03<00:03, 44.11it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 42.77it/s]
Loading 0:  49%|████▉     | 144/291 [00:03<00:03, 43.98it/s]
Loading 0:  51%|█████     | 149/291 [00:03<00:03, 37.85it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 46.44it/s]
Loading 0:  56%|█████▌    | 163/291 [00:04<00:02, 43.37it/s]
Loading 0:  58%|█████▊    | 168/291 [00:04<00:02, 41.89it/s]
Loading 0:  59%|█████▉    | 173/291 [00:04<00:02, 42.10it/s]
Loading 0:  62%|██████▏   | 179/291 [00:04<00:02, 45.04it/s]
Loading 0:  63%|██████▎   | 184/291 [00:04<00:02, 43.61it/s]
Loading 0:  65%|██████▍   | 189/291 [00:04<00:03, 25.88it/s]
Loading 0:  67%|██████▋   | 194/291 [00:05<00:03, 28.13it/s]
Loading 0:  69%|██████▉   | 201/291 [00:05<00:02, 35.08it/s]
Loading 0:  71%|███████   | 206/291 [00:05<00:02, 36.64it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:02, 38.08it/s]
Loading 0:  74%|███████▍  | 216/291 [00:05<00:01, 40.20it/s]
Loading 0:  76%|███████▌  | 221/291 [00:05<00:02, 33.64it/s]
Loading 0:  78%|███████▊  | 228/291 [00:05<00:01, 40.56it/s]
Loading 0:  80%|████████  | 233/291 [00:05<00:01, 41.59it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:01, 40.54it/s]
Loading 0:  84%|████████▎ | 243/291 [00:06<00:01, 42.83it/s]
Loading 0:  85%|████████▌ | 248/291 [00:06<00:01, 35.36it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 44.07it/s]
Loading 0:  90%|█████████ | 262/291 [00:06<00:00, 42.32it/s]
Loading 0:  92%|█████████▏| 267/291 [00:06<00:00, 42.45it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 47.97it/s]
Loading 0:  96%|█████████▌| 280/291 [00:07<00:00, 45.60it/s]
Loading 0:  98%|█████████▊| 285/291 [00:07<00:00, 43.91it/s]
Loading 0: 100%|█████████▉| 290/291 [00:12<00:00,  3.23it/s]
                                                            
Job cycy233-model4-10-v1-mkmlizer completed after 83.2s with status: succeeded
Stopping job with name cycy233-model4-10-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.64s
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-model4-10-v1
Waiting for inference service cycy233-model4-10-v1 to be ready
Inference service cycy233-model4-10-v1 ready after 130.44168758392334s
Pipeline stage MKMLDeployer completed in 130.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7417995929718018s
Received healthy response to inference request in 1.2057983875274658s
Received healthy response to inference request in 1.0942506790161133s
Received healthy response to inference request in 0.6931655406951904s
Received healthy response to inference request in 1.0581109523773193s
5 requests
0 failed requests
5th percentile: 0.7661546230316162
10th percentile: 0.839143705368042
20th percentile: 0.9851218700408936
30th percentile: 1.0653388977050782
40th percentile: 1.0797947883605956
50th percentile: 1.0942506790161133
60th percentile: 1.1388697624206543
70th percentile: 1.1834888458251953
80th percentile: 1.312998628616333
90th percentile: 1.5273991107940674
95th percentile: 1.6345993518829345
99th percentile: 1.7203595447540283
mean time: 1.158625030517578
Pipeline stage StressChecker completed in 7.03s
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 0.68s
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 0.66s
Shutdown handler de-registered
cycy233-model4-10_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-model4-10-v1-profiler
Waiting for inference service cycy233-model4-10-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 2293.14s
Shutdown handler de-registered
cycy233-model4-10_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-model4-10_v1 status is now torndown due to DeploymentManager action