cycy233-model3-12

developer_uid: cycy233

submission_id: cycy233-model3-12_v1

model_name: 486

model_group: cycy233/model3-12

status: torndown

timestamp: 2025-02-28T09:17:13+00:00

num_battles: 7050

num_wins: 3470

celo_rating: 1250.55

family_friendly_score: 0.529

family_friendly_standard_error: 0.007059164256482491

submission_type: basic

model_repo: cycy233/model3-12

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': 0.8547026817271101, 'latency_mean': 1.1699236679077147, 'latency_p50': 1.1673420667648315, 'latency_p90': 1.284334921836853}, {'batch_size': 4, 'throughput': 1.776434415209788, 'latency_mean': 2.2376906907558443, 'latency_p50': 2.242317318916321, 'latency_p90': 2.489157295227051}, {'batch_size': 5, 'throughput': 1.9184717783901963, 'latency_mean': 2.5965068900585173, 'latency_p50': 2.622049331665039, 'latency_p90': 2.827051854133606}, {'batch_size': 8, 'throughput': 2.141209969936431, 'latency_mean': 3.718655437231064, 'latency_p50': 3.7009503841400146, 'latency_p90': 4.172151827812195}, {'batch_size': 10, 'throughput': 2.1959009521503936, 'latency_mean': 4.504540874958038, 'latency_p50': 4.508257031440735, 'latency_p90': 5.0687016248703}, {'batch_size': 12, 'throughput': 2.216191039427136, 'latency_mean': 5.373047616481781, 'latency_p50': 5.369985222816467, 'latency_p90': 6.050981450080871}, {'batch_size': 15, 'throughput': 2.2409133835203847, 'latency_mean': 6.598541271686554, 'latency_p50': 6.655437469482422, 'latency_p90': 7.425503253936768}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: 486

is_internal_developer: False

language_model: cycy233/model3-12

model_size: 8B

ranking_group: single

throughput_3p7s: 2.15

us_pacific_date: 2025-02-28

win_ratio: 0.4921985815602837

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-model3-12-v1-mkmlizer
Waiting for job on cycy233-model3-12-v1-mkmlizer to finish
cycy233-model3-12-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-model3-12-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-model3-12-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-model3-12-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-model3-12-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-model3-12-v1-mkmlizer: ║       /___/                                                         ║
cycy233-model3-12-v1-mkmlizer: ║                                                                     ║
cycy233-model3-12-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
cycy233-model3-12-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-model3-12-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-model3-12-v1-mkmlizer: ║                                                                     ║
cycy233-model3-12-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-model3-12-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-model3-12-v1-mkmlizer: ║                                                                     ║
cycy233-model3-12-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-model3-12-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-model3-12-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cycy233-model3-12-v1-mkmlizer: ║                                                                     ║
cycy233-model3-12-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-model3-12-v1-mkmlizer: Downloaded to shared memory in 27.797s
cycy233-model3-12-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2my27dw0, device:0
cycy233-model3-12-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-model3-12-v1-mkmlizer: quantized model in 27.239s
cycy233-model3-12-v1-mkmlizer: Processed model cycy233/model3-12 in 55.140s
cycy233-model3-12-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-model3-12-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-model3-12-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-model3-12-v1
cycy233-model3-12-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-model3-12-v1/config.json
cycy233-model3-12-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-model3-12-v1/special_tokens_map.json
cycy233-model3-12-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-model3-12-v1/tokenizer_config.json
cycy233-model3-12-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-model3-12-v1/tokenizer.json
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-model3-12-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-model3-12-v1/flywheel_model.0.safetensors
cycy233-model3-12-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 32.63it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 51.92it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:06, 44.64it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:06, 44.24it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:05, 50.35it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:05, 44.92it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:05, 43.93it/s]
Loading 0:  17%|█▋        | 49/291 [00:01<00:04, 49.22it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:05, 44.74it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 43.82it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 48.65it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 44.44it/s]
Loading 0:  27%|██▋       | 78/291 [00:01<00:05, 40.98it/s]
Loading 0:  29%|██▊       | 83/291 [00:02<00:06, 30.70it/s]
Loading 0:  30%|██▉       | 87/291 [00:02<00:06, 30.50it/s]
Loading 0:  32%|███▏      | 93/291 [00:02<00:05, 36.25it/s]
Loading 0:  34%|███▎      | 98/291 [00:02<00:04, 38.94it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 41.02it/s]
Loading 0:  37%|███▋      | 109/291 [00:02<00:04, 39.83it/s]
Loading 0:  39%|███▉      | 114/291 [00:02<00:04, 40.97it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 46.36it/s]
Loading 0:  43%|████▎     | 126/291 [00:02<00:03, 46.42it/s]
Loading 0:  45%|████▌     | 131/291 [00:03<00:04, 37.07it/s]
Loading 0:  47%|████▋     | 138/291 [00:03<00:03, 42.98it/s]
Loading 0:  49%|████▉     | 143/291 [00:03<00:03, 42.66it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 42.69it/s]
Loading 0:  53%|█████▎    | 153/291 [00:03<00:03, 44.34it/s]
Loading 0:  54%|█████▍    | 158/291 [00:03<00:03, 36.10it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 44.92it/s]
Loading 0:  59%|█████▉    | 172/291 [00:04<00:02, 42.39it/s]
Loading 0:  62%|██████▏   | 179/291 [00:04<00:02, 46.72it/s]
Loading 0:  63%|██████▎   | 184/291 [00:04<00:02, 47.47it/s]
Loading 0:  65%|██████▍   | 189/291 [00:04<00:03, 30.12it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:03, 31.96it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 40.73it/s]
Loading 0:  71%|███████▏  | 208/291 [00:05<00:02, 40.16it/s]
Loading 0:  73%|███████▎  | 213/291 [00:05<00:01, 39.98it/s]
Loading 0:  75%|███████▌  | 219/291 [00:05<00:01, 44.02it/s]
Loading 0:  77%|███████▋  | 224/291 [00:05<00:01, 44.58it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 44.59it/s]
Loading 0:  81%|████████  | 235/291 [00:05<00:01, 41.80it/s]
Loading 0:  82%|████████▏ | 240/291 [00:05<00:01, 41.89it/s]
Loading 0:  85%|████████▍ | 246/291 [00:05<00:01, 44.91it/s]
Loading 0:  86%|████████▋ | 251/291 [00:06<00:00, 44.99it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 44.22it/s]
Loading 0:  90%|████████▉ | 261/291 [00:06<00:00, 45.19it/s]
Loading 0:  91%|█████████▏| 266/291 [00:06<00:00, 38.57it/s]
Loading 0:  94%|█████████▍| 273/291 [00:06<00:00, 45.71it/s]
Loading 0:  96%|█████████▌| 278/291 [00:06<00:00, 43.60it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 37.26it/s]
Loading 0:  99%|█████████▉| 288/291 [00:12<00:01,  2.99it/s]
                                                            
Job cycy233-model3-12-v1-mkmlizer completed after 83.82s with status: succeeded
Stopping job with name cycy233-model3-12-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.34s
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-model3-12-v1
Waiting for inference service cycy233-model3-12-v1 to be ready
Inference service cycy233-model3-12-v1 ready after 160.76655197143555s
Pipeline stage MKMLDeployer completed in 161.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9536809921264648s
Received healthy response to inference request in 1.234682559967041s
Received healthy response to inference request in 1.4381673336029053s
Received healthy response to inference request in 1.1133372783660889s
Received healthy response to inference request in 1.2211718559265137s
5 requests
0 failed requests
5th percentile: 1.1349041938781739
10th percentile: 1.1564711093902589
20th percentile: 1.1996049404144287
30th percentile: 1.223873996734619
40th percentile: 1.22927827835083
50th percentile: 1.234682559967041
60th percentile: 1.3160764694213867
70th percentile: 1.3974703788757323
80th percentile: 1.5412700653076172
90th percentile: 1.7474755287170411
95th percentile: 1.8505782604217529
99th percentile: 1.9330604457855225
mean time: 1.3922080039978026
Pipeline stage StressChecker completed in 8.22s
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 0.63s
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-model3-12_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 2456.33s
Shutdown handler de-registered
cycy233-model3-12_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-model3-12_v1 status is now torndown due to DeploymentManager action