cycy233-model3-3

developer_uid: cycy233

submission_id: cycy233-model3-3_v1

model_name: 486

model_group: cycy233/model3-3

status: torndown

timestamp: 2025-02-28T09:15:23+00:00

num_battles: 7591

num_wins: 3840

celo_rating: 1259.18

family_friendly_score: 0.4942

family_friendly_standard_error: 0.007070592054418074

submission_type: basic

model_repo: cycy233/model3-3

model_architecture: LlamaForCausalLM

model_num_parameters: 8030261248.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.8554599280117787, 'latency_mean': 1.168903467655182, 'latency_p50': 1.175571084022522, 'latency_p90': 1.2836002826690673}, {'batch_size': 4, 'throughput': 1.820777032603323, 'latency_mean': 2.188174067735672, 'latency_p50': 2.1859357357025146, 'latency_p90': 2.458777117729187}, {'batch_size': 5, 'throughput': 1.960370853315462, 'latency_mean': 2.5366059243679047, 'latency_p50': 2.548197031021118, 'latency_p90': 2.7861700534820555}, {'batch_size': 8, 'throughput': 2.182096857398275, 'latency_mean': 3.6534268450737, 'latency_p50': 3.6688075065612793, 'latency_p90': 4.12011616230011}, {'batch_size': 10, 'throughput': 2.2516429957753217, 'latency_mean': 4.4096358096599575, 'latency_p50': 4.426763534545898, 'latency_p90': 4.932537174224853}, {'batch_size': 12, 'throughput': 2.28265710590376, 'latency_mean': 5.205763462781906, 'latency_p50': 5.2088035345077515, 'latency_p90': 6.003928470611572}, {'batch_size': 15, 'throughput': 2.2710985984850196, 'latency_mean': 6.518890701532364, 'latency_p50': 6.524255633354187, 'latency_p90': 7.220128917694092}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: 486

is_internal_developer: False

language_model: cycy233/model3-3

model_size: 8B

ranking_group: single

throughput_3p7s: 2.2

us_pacific_date: 2025-02-28

win_ratio: 0.505862205243051

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-model3-3-v1-mkmlizer
Waiting for job on cycy233-model3-3-v1-mkmlizer to finish
cycy233-model3-3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-model3-3-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-model3-3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-model3-3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-model3-3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-model3-3-v1-mkmlizer: ║       /___/                                                         ║
cycy233-model3-3-v1-mkmlizer: ║                                                                     ║
cycy233-model3-3-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
cycy233-model3-3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-model3-3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-model3-3-v1-mkmlizer: ║                                                                     ║
cycy233-model3-3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-model3-3-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-model3-3-v1-mkmlizer: ║                                                                     ║
cycy233-model3-3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-model3-3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-model3-3-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cycy233-model3-3-v1-mkmlizer: ║                                                                     ║
cycy233-model3-3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-model3-3-v1-mkmlizer: Downloaded to shared memory in 29.659s
cycy233-model3-3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp85549r4h, device:0
cycy233-model3-3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-model3-3-v1-mkmlizer: quantized model in 27.980s
cycy233-model3-3-v1-mkmlizer: Processed model cycy233/model3-3 in 57.640s
cycy233-model3-3-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-model3-3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-model3-3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-model3-3-v1
cycy233-model3-3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-model3-3-v1/special_tokens_map.json
cycy233-model3-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-model3-3-v1/tokenizer_config.json
cycy233-model3-3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-model3-3-v1/config.json
cycy233-model3-3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-model3-3-v1/tokenizer.json
cycy233-model3-3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-model3-3-v1/flywheel_model.0.safetensors
cycy233-model3-3-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 31.86it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 52.03it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:06, 44.62it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:06, 43.51it/s]
Loading 0:  10%|█         | 30/291 [00:00<00:05, 48.10it/s]
Loading 0:  12%|█▏        | 35/291 [00:00<00:05, 46.72it/s]
Loading 0:  14%|█▎        | 40/291 [00:00<00:05, 46.41it/s]
Loading 0:  16%|█▌        | 46/291 [00:01<00:05, 42.38it/s]
Loading 0:  18%|█▊        | 51/291 [00:01<00:05, 41.78it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:04, 47.12it/s]
Loading 0:  22%|██▏       | 63/291 [00:01<00:04, 47.85it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:05, 39.13it/s]
Loading 0:  26%|██▌       | 75/291 [00:01<00:04, 45.96it/s]
Loading 0:  27%|██▋       | 80/291 [00:01<00:04, 45.06it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:06, 29.52it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 33.12it/s]
Loading 0:  33%|███▎      | 95/291 [00:02<00:06, 30.36it/s]
Loading 0:  35%|███▌      | 102/291 [00:02<00:05, 37.22it/s]
Loading 0:  37%|███▋      | 107/291 [00:02<00:04, 38.57it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:05, 35.26it/s]
Loading 0:  40%|███▉      | 116/291 [00:02<00:04, 35.22it/s]
Loading 0:  41%|████      | 120/291 [00:03<00:04, 35.78it/s]
Loading 0:  43%|████▎     | 124/291 [00:03<00:04, 35.24it/s]
Loading 0:  44%|████▍     | 129/291 [00:03<00:04, 38.33it/s]
Loading 0:  46%|████▌     | 133/291 [00:03<00:04, 37.46it/s]
Loading 0:  47%|████▋     | 138/291 [00:03<00:03, 39.74it/s]
Loading 0:  49%|████▉     | 143/291 [00:03<00:03, 40.20it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 41.30it/s]
Loading 0:  53%|█████▎    | 153/291 [00:03<00:03, 43.19it/s]
Loading 0:  54%|█████▍    | 158/291 [00:04<00:03, 35.41it/s]
Loading 0:  57%|█████▋    | 165/291 [00:04<00:03, 41.74it/s]
Loading 0:  58%|█████▊    | 170/291 [00:04<00:02, 40.95it/s]
Loading 0:  60%|██████    | 175/291 [00:04<00:02, 42.17it/s]
Loading 0:  62%|██████▏   | 180/291 [00:04<00:02, 41.35it/s]
Loading 0:  64%|██████▎   | 185/291 [00:04<00:02, 41.94it/s]
Loading 0:  65%|██████▌   | 190/291 [00:05<00:04, 24.97it/s]
Loading 0:  67%|██████▋   | 194/291 [00:05<00:03, 25.35it/s]
Loading 0:  69%|██████▉   | 201/291 [00:05<00:02, 32.91it/s]
Loading 0:  71%|███████   | 206/291 [00:05<00:02, 35.13it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:02, 36.51it/s]
Loading 0:  74%|███████▍  | 216/291 [00:05<00:01, 38.18it/s]
Loading 0:  76%|███████▌  | 221/291 [00:05<00:02, 33.38it/s]
Loading 0:  78%|███████▊  | 228/291 [00:05<00:01, 40.20it/s]
Loading 0:  80%|████████  | 233/291 [00:06<00:01, 40.57it/s]
Loading 0:  82%|████████▏ | 238/291 [00:06<00:01, 39.72it/s]
Loading 0:  84%|████████▎ | 243/291 [00:06<00:01, 41.10it/s]
Loading 0:  85%|████████▌ | 248/291 [00:06<00:01, 33.79it/s]
Loading 0:  87%|████████▋ | 253/291 [00:06<00:01, 37.20it/s]
Loading 0:  89%|████████▊ | 258/291 [00:06<00:00, 36.32it/s]
Loading 0:  90%|█████████ | 262/291 [00:06<00:00, 37.18it/s]
Loading 0:  91%|█████████▏| 266/291 [00:07<00:00, 35.00it/s]
Loading 0:  94%|█████████▍| 273/291 [00:07<00:00, 42.27it/s]
Loading 0:  96%|█████████▌| 278/291 [00:07<00:00, 42.39it/s]
Loading 0:  97%|█████████▋| 283/291 [00:07<00:00, 36.13it/s]
Loading 0:  99%|█████████▊| 287/291 [00:13<00:01,  2.68it/s]
                                                            
Job cycy233-model3-3-v1-mkmlizer completed after 83.61s with status: succeeded
Stopping job with name cycy233-model3-3-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.08s
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-model3-3-v1
Waiting for inference service cycy233-model3-3-v1 to be ready
Failed to get response for submission nischaydnk-exp26-mistra_55673_v5: HTTPConnectionPool(host='nischaydnk-exp26-mistra-55673-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-exp26-mistra_55673_v5: HTTPConnectionPool(host='nischaydnk-exp26-mistra-55673-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-exp26-mistra_55673_v5: HTTPConnectionPool(host='nischaydnk-exp26-mistra-55673-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-exp26-mistra_55673_v5: HTTPConnectionPool(host='nischaydnk-exp26-mistra-55673-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-exp26-mistra_55673_v5: HTTPConnectionPool(host='nischaydnk-exp26-mistra-55673-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service cycy233-model3-3-v1 ready after 160.68730783462524s
Pipeline stage MKMLDeployer completed in 161.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9065585136413574s
Received healthy response to inference request in 1.314925193786621s
Received healthy response to inference request in 1.015151023864746s
Received healthy response to inference request in 1.36039137840271s
Received healthy response to inference request in 0.6205470561981201s
5 requests
0 failed requests
5th percentile: 0.6994678497314453
10th percentile: 0.7783886432647705
20th percentile: 0.9362302303314209
30th percentile: 1.075105857849121
40th percentile: 1.1950155258178712
50th percentile: 1.314925193786621
60th percentile: 1.3331116676330566
70th percentile: 1.3512981414794922
80th percentile: 1.4696248054504395
90th percentile: 1.6880916595458986
95th percentile: 1.7973250865936279
99th percentile: 1.8847118282318116
mean time: 1.243514633178711
Pipeline stage StressChecker completed in 7.59s
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 0.67s
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 0.74s
Shutdown handler de-registered
cycy233-model3-3_v1 status is now deployed due to DeploymentManager action
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 2149.47s
Shutdown handler de-registered
cycy233-model3-3_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-model3-3_v1 status is now torndown due to DeploymentManager action