cycy233-model4-8

developer_uid: cycy233

submission_id: cycy233-model4-8_v1

model_name: 486

model_group: cycy233/model4-8

status: torndown

timestamp: 2025-03-03T07:35:15+00:00

num_battles: 6150

num_wins: 2928

celo_rating: 1244.61

family_friendly_score: 0.536

family_friendly_standard_error: 0.007052715788970942

submission_type: basic

model_repo: cycy233/model4-8

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': 0.8494565041997, 'latency_mean': 1.1771282398700713, 'latency_p50': 1.1752893924713135, 'latency_p90': 1.3045363187789918}, {'batch_size': 4, 'throughput': 1.7697720977658762, 'latency_mean': 2.2502838826179503, 'latency_p50': 2.259702205657959, 'latency_p90': 2.5213520526885986}, {'batch_size': 5, 'throughput': 1.9005841076700647, 'latency_mean': 2.6135327076911925, 'latency_p50': 2.623162627220154, 'latency_p90': 2.922148585319519}, {'batch_size': 8, 'throughput': 2.1150614947126285, 'latency_mean': 3.755845944881439, 'latency_p50': 3.7658697366714478, 'latency_p90': 4.2789599895477295}, {'batch_size': 10, 'throughput': 2.143214507353709, 'latency_mean': 4.629068202972412, 'latency_p50': 4.624700903892517, 'latency_p90': 5.1436197519302365}, {'batch_size': 12, 'throughput': 2.179777524248748, 'latency_mean': 5.447369445562362, 'latency_p50': 5.4315025806427, 'latency_p90': 6.088837909698486}, {'batch_size': 15, 'throughput': 2.201818757359206, 'latency_mean': 6.733813710212708, 'latency_p50': 6.784533739089966, 'latency_p90': 7.5338037490844725}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: 486

is_internal_developer: False

language_model: cycy233/model4-8

model_size: 8B

ranking_group: single

throughput_3p7s: 2.12

us_pacific_date: 2025-03-02

win_ratio: 0.47609756097560973

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-model4-8-v1-mkmlizer
Waiting for job on cycy233-model4-8-v1-mkmlizer to finish
cycy233-model4-8-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-model4-8-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-model4-8-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-model4-8-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-model4-8-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-model4-8-v1-mkmlizer: ║       /___/                                                         ║
cycy233-model4-8-v1-mkmlizer: ║                                                                     ║
cycy233-model4-8-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
cycy233-model4-8-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-model4-8-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-model4-8-v1-mkmlizer: ║                                                                     ║
cycy233-model4-8-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-model4-8-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-model4-8-v1-mkmlizer: ║                                                                     ║
cycy233-model4-8-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-model4-8-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-model4-8-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cycy233-model4-8-v1-mkmlizer: ║                                                                     ║
cycy233-model4-8-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-model4-8-v1-mkmlizer: Downloaded to shared memory in 27.955s
cycy233-model4-8-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5qwkkr2a, device:0
cycy233-model4-8-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-model4-8-v1-mkmlizer: quantized model in 26.547s
cycy233-model4-8-v1-mkmlizer: Processed model cycy233/model4-8 in 54.508s
cycy233-model4-8-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-model4-8-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-model4-8-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-model4-8-v1
cycy233-model4-8-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-model4-8-v1/config.json
cycy233-model4-8-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-model4-8-v1/special_tokens_map.json
cycy233-model4-8-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-model4-8-v1/tokenizer_config.json
cycy233-model4-8-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-model4-8-v1/tokenizer.json
cycy233-model4-8-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-model4-8-v1/flywheel_model.0.safetensors
cycy233-model4-8-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 33.74it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 54.46it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 46.82it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:05, 45.47it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:05, 46.76it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:05, 49.78it/s]
Loading 0:  17%|█▋        | 50/291 [00:01<00:04, 51.84it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 52.28it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:03, 57.94it/s]
Loading 0:  25%|██▌       | 73/291 [00:01<00:04, 51.32it/s]
Loading 0:  27%|██▋       | 79/291 [00:01<00:04, 50.67it/s]
Loading 0:  29%|██▉       | 85/291 [00:01<00:05, 38.04it/s]
Loading 0:  31%|███▏      | 91/291 [00:01<00:05, 38.43it/s]
Loading 0:  33%|███▎      | 96/291 [00:02<00:04, 39.92it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 45.13it/s]
Loading 0:  37%|███▋      | 109/291 [00:02<00:04, 43.79it/s]
Loading 0:  39%|███▉      | 114/291 [00:02<00:04, 43.99it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 49.52it/s]
Loading 0:  44%|████▎     | 127/291 [00:02<00:03, 46.74it/s]
Loading 0:  45%|████▌     | 132/291 [00:02<00:03, 46.09it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:02, 51.19it/s]
Loading 0:  50%|████▉     | 145/291 [00:03<00:03, 48.23it/s]
Loading 0:  52%|█████▏    | 150/291 [00:03<00:02, 47.68it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 52.80it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 49.06it/s]
Loading 0:  58%|█████▊    | 169/291 [00:03<00:02, 50.04it/s]
Loading 0:  61%|██████    | 177/291 [00:03<00:02, 51.51it/s]
Loading 0:  63%|██████▎   | 183/291 [00:03<00:02, 50.62it/s]
Loading 0:  65%|██████▍   | 189/291 [00:04<00:03, 33.74it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:02, 35.36it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 42.41it/s]
Loading 0:  71%|███████   | 206/291 [00:04<00:01, 43.14it/s]
Loading 0:  73%|███████▎  | 212/291 [00:04<00:01, 40.38it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 47.40it/s]
Loading 0:  78%|███████▊  | 226/291 [00:04<00:01, 45.28it/s]
Loading 0:  79%|███████▉  | 231/291 [00:05<00:01, 45.17it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 49.48it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:01, 45.71it/s]
Loading 0:  86%|████████▌ | 249/291 [00:05<00:00, 45.55it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 50.52it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 44.08it/s]
Loading 0:  92%|█████████▏| 267/291 [00:05<00:00, 42.31it/s]
Loading 0:  94%|█████████▍| 273/291 [00:05<00:00, 45.64it/s]
Loading 0:  96%|█████████▌| 278/291 [00:06<00:00, 45.23it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 39.22it/s]
Loading 0:  99%|█████████▉| 288/291 [00:11<00:00,  3.08it/s]
                                                            
Job cycy233-model4-8-v1-mkmlizer completed after 93.76s with status: succeeded
Stopping job with name cycy233-model4-8-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.37s
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-model4-8-v1
Waiting for inference service cycy233-model4-8-v1 to be ready
Failed to get response for submission nischaydnk-exp14-exp9dp_94555_v3: HTTPConnectionPool(host='nischaydnk-exp14-exp9dp-94555-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service cycy233-model4-8-v1 ready after 140.7354278564453s
Pipeline stage MKMLDeployer completed in 141.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8060741424560547s
Received healthy response to inference request in 0.8907361030578613s
Received healthy response to inference request in 1.237396001815796s
Received healthy response to inference request in 0.9992272853851318s
Received healthy response to inference request in 0.5819363594055176s
5 requests
0 failed requests
5th percentile: 0.6436963081359863
10th percentile: 0.7054562568664551
20th percentile: 0.8289761543273926
30th percentile: 0.9124343395233154
40th percentile: 0.9558308124542236
50th percentile: 0.9992272853851318
60th percentile: 1.0944947719573974
70th percentile: 1.189762258529663
80th percentile: 1.3511316299438478
90th percentile: 1.5786028861999513
95th percentile: 1.6923385143280028
99th percentile: 1.7833270168304443
mean time: 1.1030739784240722
Pipeline stage StressChecker completed in 6.80s
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 0.60s
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-model4-8_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 2285.08s
Shutdown handler de-registered
cycy233-model4-8_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-model4-8_v1 status is now torndown due to DeploymentManager action