cycy233-model3-9

developer_uid: cycy233

submission_id: cycy233-model3-9_v1

model_name: 486

model_group: cycy233/model3-9

status: torndown

timestamp: 2025-02-28T09:16:19+00:00

num_battles: 8182

num_wins: 3957

celo_rating: 1243.62

family_friendly_score: 0.5318

family_friendly_standard_error: 0.0070567522274768875

submission_type: basic

model_repo: cycy233/model3-9

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': 0.8444575683584735, 'latency_mean': 1.1840933465957642, 'latency_p50': 1.1788185834884644, 'latency_p90': 1.3100465059280395}, {'batch_size': 4, 'throughput': 1.7802309209801948, 'latency_mean': 2.235359152555466, 'latency_p50': 2.24258029460907, 'latency_p90': 2.4789023637771606}, {'batch_size': 5, 'throughput': 1.9064814231635026, 'latency_mean': 2.603581123352051, 'latency_p50': 2.5986897945404053, 'latency_p90': 2.9179279088973997}, {'batch_size': 8, 'throughput': 2.1027147160108464, 'latency_mean': 3.7796400272846222, 'latency_p50': 3.739711284637451, 'latency_p90': 4.2736330270767215}, {'batch_size': 10, 'throughput': 2.1802794208155594, 'latency_mean': 4.551362918615341, 'latency_p50': 4.529988527297974, 'latency_p90': 5.200538945198059}, {'batch_size': 12, 'throughput': 2.205462343928839, 'latency_mean': 5.386894377470017, 'latency_p50': 5.423020005226135, 'latency_p90': 6.048588037490845}, {'batch_size': 15, 'throughput': 2.224391957949587, 'latency_mean': 6.650952570438385, 'latency_p50': 6.674503326416016, 'latency_p90': 7.483591771125793}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: 486

is_internal_developer: False

language_model: cycy233/model3-9

model_size: 8B

ranking_group: single

throughput_3p7s: 2.11

us_pacific_date: 2025-02-28

win_ratio: 0.4836225861647519

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'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\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-model3-9-v1-mkmlizer
Waiting for job on cycy233-model3-9-v1-mkmlizer to finish
cycy233-model3-9-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-model3-9-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-model3-9-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-model3-9-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-model3-9-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-model3-9-v1-mkmlizer: ║       /___/                                                         ║
cycy233-model3-9-v1-mkmlizer: ║                                                                     ║
cycy233-model3-9-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
cycy233-model3-9-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-model3-9-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-model3-9-v1-mkmlizer: ║                                                                     ║
cycy233-model3-9-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-model3-9-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-model3-9-v1-mkmlizer: ║                                                                     ║
cycy233-model3-9-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-model3-9-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-model3-9-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cycy233-model3-9-v1-mkmlizer: ║                                                                     ║
cycy233-model3-9-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-model3-9-v1-mkmlizer: Downloaded to shared memory in 27.022s
cycy233-model3-9-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpt9axx7p6, device:0
cycy233-model3-9-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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)
cycy233-model3-9-v1-mkmlizer: quantized model in 26.912s
cycy233-model3-9-v1-mkmlizer: Processed model cycy233/model3-9 in 53.959s
cycy233-model3-9-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-model3-9-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-model3-9-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-model3-9-v1
cycy233-model3-9-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-model3-9-v1/config.json
cycy233-model3-9-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-model3-9-v1/special_tokens_map.json
cycy233-model3-9-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-model3-9-v1/tokenizer_config.json
cycy233-model3-9-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-model3-9-v1/tokenizer.json
cycy233-model3-9-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-model3-9-v1/flywheel_model.0.safetensors
cycy233-model3-9-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 32.67it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:06, 45.89it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:05, 50.69it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:04, 53.43it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:04, 55.11it/s]
Loading 0:  17%|█▋        | 50/291 [00:01<00:04, 48.87it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:04, 52.79it/s]
Loading 0:  22%|██▏       | 63/291 [00:01<00:04, 52.74it/s]
Loading 0:  24%|██▎       | 69/291 [00:01<00:05, 43.96it/s]
Loading 0:  25%|██▌       | 74/291 [00:01<00:05, 40.74it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:06, 34.59it/s]
Loading 0:  29%|██▊       | 83/291 [00:02<00:07, 27.45it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:07, 27.49it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:05, 35.05it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:05, 37.47it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 38.22it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:04, 44.24it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:04, 42.02it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:04, 40.31it/s]
Loading 0:  44%|████▍     | 129/291 [00:03<00:03, 44.43it/s]
Loading 0:  46%|████▌     | 134/291 [00:03<00:03, 44.05it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:03, 45.18it/s]
Loading 0:  50%|████▉     | 145/291 [00:03<00:03, 43.36it/s]
Loading 0:  52%|█████▏    | 150/291 [00:03<00:03, 43.81it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 50.10it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 47.15it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 46.48it/s]
Loading 0:  60%|██████    | 176/291 [00:04<00:02, 55.04it/s]
Loading 0:  63%|██████▎   | 182/291 [00:04<00:02, 45.87it/s]
Loading 0:  64%|██████▍   | 187/291 [00:04<00:02, 35.26it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:02, 36.16it/s]
Loading 0:  68%|██████▊   | 197/291 [00:04<00:02, 38.85it/s]
Loading 0:  70%|██████▉   | 203/291 [00:04<00:02, 38.32it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:01, 47.44it/s]
Loading 0:  75%|███████▍  | 217/291 [00:05<00:01, 45.06it/s]
Loading 0:  76%|███████▋  | 222/291 [00:05<00:01, 43.86it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 49.06it/s]
Loading 0:  81%|████████  | 235/291 [00:05<00:01, 42.80it/s]
Loading 0:  82%|████████▏ | 240/291 [00:05<00:01, 42.38it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:00, 48.17it/s]
Loading 0:  87%|████████▋ | 253/291 [00:05<00:00, 45.93it/s]
Loading 0:  89%|████████▊ | 258/291 [00:05<00:00, 44.93it/s]
Loading 0:  91%|█████████ | 265/291 [00:06<00:00, 49.17it/s]
Loading 0:  93%|█████████▎| 271/291 [00:06<00:00, 45.12it/s]
Loading 0:  95%|█████████▍| 276/291 [00:06<00:00, 42.62it/s]
Loading 0:  97%|█████████▋| 281/291 [00:06<00:00, 42.11it/s]
Loading 0:  98%|█████████▊| 286/291 [00:06<00:00, 39.00it/s]
Loading 0: 100%|█████████▉| 290/291 [00:12<00:00,  2.92it/s]
                                                            
Job cycy233-model3-9-v1-mkmlizer completed after 83.58s with status: succeeded
Stopping job with name cycy233-model3-9-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.03s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-model3-9-v1
Waiting for inference service cycy233-model3-9-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)
Inference service cycy233-model3-9-v1 ready after 160.5779688358307s
Pipeline stage MKMLDeployer completed in 161.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9667704105377197s
Received healthy response to inference request in 1.355619192123413s
Received healthy response to inference request in 1.4858741760253906s
Received healthy response to inference request in 1.5575273036956787s
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)
Received healthy response to inference request in 1.212324619293213s
5 requests
0 failed requests
5th percentile: 1.240983533859253
10th percentile: 1.269642448425293
20th percentile: 1.326960277557373
30th percentile: 1.3816701889038085
40th percentile: 1.4337721824645997
50th percentile: 1.4858741760253906
60th percentile: 1.5145354270935059
70th percentile: 1.543196678161621
80th percentile: 1.639375925064087
90th percentile: 1.8030731678009033
95th percentile: 1.8849217891693115
99th percentile: 1.9504006862640382
mean time: 1.515623140335083
Pipeline stage StressChecker completed in 8.75s
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 0.64s
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 0.61s
Shutdown handler de-registered
cycy233-model3-9_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4322.75s
Shutdown handler de-registered
cycy233-model3-9_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-model3-9_v1 status is now torndown due to DeploymentManager action