developer_uid: cycy233
submission_id: cycy233-model4-1_v1
model_name: 486
model_group: cycy233/model4-1
status: torndown
timestamp: 2025-03-03T04:24:23+00:00
num_battles: 7315
num_wins: 3253
celo_rating: 1236.7
family_friendly_score: 0.5362
family_friendly_standard_error: 0.007052511042174979
submission_type: basic
model_repo: cycy233/model4-1
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': 0.8414865493841017, 'latency_mean': 1.1882723212242126, 'latency_p50': 1.184419870376587, 'latency_p90': 1.3119648694992065}, {'batch_size': 4, 'throughput': 1.77601362859976, 'latency_mean': 2.2428560292720796, 'latency_p50': 2.2281566858291626, 'latency_p90': 2.5204134702682497}, {'batch_size': 5, 'throughput': 1.920415947512948, 'latency_mean': 2.5924129736423493, 'latency_p50': 2.6022651195526123, 'latency_p90': 2.9123254299163817}, {'batch_size': 8, 'throughput': 2.113690358843737, 'latency_mean': 3.756796125173569, 'latency_p50': 3.7597649097442627, 'latency_p90': 4.276481676101684}, {'batch_size': 10, 'throughput': 2.1714310540675306, 'latency_mean': 4.561838074922561, 'latency_p50': 4.58399772644043, 'latency_p90': 5.161147785186768}, {'batch_size': 12, 'throughput': 2.1982541314938415, 'latency_mean': 5.41392404794693, 'latency_p50': 5.4485485553741455, 'latency_p90': 6.05071988105774}, {'batch_size': 15, 'throughput': 2.1954423951179076, 'latency_mean': 6.750005801916123, 'latency_p50': 6.766065001487732, 'latency_p90': 7.655368208885193}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: 486
is_internal_developer: False
language_model: cycy233/model4-1
model_size: 8B
ranking_group: single
throughput_3p7s: 2.12
us_pacific_date: 2025-03-02
win_ratio: 0.4447026657552973
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-model4-1-v1-mkmlizer
Waiting for job on cycy233-model4-1-v1-mkmlizer to finish
cycy233-model4-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-model4-1-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-model4-1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-model4-1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-model4-1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-model4-1-v1-mkmlizer: ║       /___/                                                         ║
cycy233-model4-1-v1-mkmlizer: ║                                                                     ║
cycy233-model4-1-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
cycy233-model4-1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-model4-1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-model4-1-v1-mkmlizer: ║                                                                     ║
cycy233-model4-1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-model4-1-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-model4-1-v1-mkmlizer: ║                                                                     ║
cycy233-model4-1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-model4-1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-model4-1-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cycy233-model4-1-v1-mkmlizer: ║                                                                     ║
cycy233-model4-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-model4-1-v1-mkmlizer: Downloaded to shared memory in 28.810s
cycy233-model4-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpr9kpbf1b, device:0
cycy233-model4-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-model4-1-v1-mkmlizer: quantized model in 27.269s
cycy233-model4-1-v1-mkmlizer: Processed model cycy233/model4-1 in 56.080s
cycy233-model4-1-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-model4-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-model4-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-model4-1-v1
cycy233-model4-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-model4-1-v1/config.json
cycy233-model4-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-model4-1-v1/special_tokens_map.json
cycy233-model4-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-model4-1-v1/tokenizer_config.json
cycy233-model4-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-model4-1-v1/tokenizer.json
cycy233-model4-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-model4-1-v1/flywheel_model.0.safetensors
cycy233-model4-1-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:09, 31.27it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 51.03it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:06, 41.62it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:06, 41.39it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:05, 47.22it/s]
Loading 0:  13%|█▎        | 37/291 [00:00<00:06, 42.13it/s]
Loading 0:  14%|█▍        | 42/291 [00:00<00:06, 40.76it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:05, 44.46it/s]
Loading 0:  18%|█▊        | 53/291 [00:01<00:05, 43.46it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:05, 43.57it/s]
Loading 0:  22%|██▏       | 63/291 [00:01<00:05, 45.06it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:05, 37.60it/s]
Loading 0:  26%|██▌       | 75/291 [00:01<00:04, 45.32it/s]
Loading 0:  27%|██▋       | 80/291 [00:01<00:04, 45.99it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:06, 32.08it/s]
Loading 0:  31%|███▏      | 91/291 [00:02<00:06, 33.33it/s]
Loading 0:  33%|███▎      | 95/291 [00:02<00:05, 33.85it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 43.15it/s]
Loading 0:  37%|███▋      | 109/291 [00:02<00:04, 42.22it/s]
Loading 0:  39%|███▉      | 114/291 [00:02<00:04, 41.85it/s]
Loading 0:  42%|████▏     | 121/291 [00:02<00:03, 47.08it/s]
Loading 0:  43%|████▎     | 126/291 [00:02<00:03, 47.64it/s]
Loading 0:  45%|████▌     | 131/291 [00:03<00:04, 39.86it/s]
Loading 0:  47%|████▋     | 138/291 [00:03<00:03, 45.45it/s]
Loading 0:  49%|████▉     | 143/291 [00:03<00:03, 44.54it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 44.76it/s]
Loading 0:  53%|█████▎    | 153/291 [00:03<00:03, 45.71it/s]
Loading 0:  54%|█████▍    | 158/291 [00:03<00:03, 37.69it/s]
Loading 0:  57%|█████▋    | 165/291 [00:03<00:02, 45.00it/s]
Loading 0:  58%|█████▊    | 170/291 [00:04<00:02, 44.92it/s]
Loading 0:  60%|██████    | 175/291 [00:04<00:02, 46.06it/s]
Loading 0:  62%|██████▏   | 180/291 [00:04<00:02, 44.54it/s]
Loading 0:  64%|██████▎   | 185/291 [00:04<00:02, 44.38it/s]
Loading 0:  65%|██████▌   | 190/291 [00:04<00:03, 26.00it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:03, 26.76it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 34.71it/s]
Loading 0:  71%|███████   | 206/291 [00:05<00:02, 36.53it/s]
Loading 0:  73%|███████▎  | 211/291 [00:05<00:02, 38.32it/s]
Loading 0:  74%|███████▍  | 216/291 [00:05<00:01, 39.16it/s]
Loading 0:  76%|███████▌  | 221/291 [00:05<00:02, 34.08it/s]
Loading 0:  78%|███████▊  | 228/291 [00:05<00:01, 41.98it/s]
Loading 0:  80%|████████  | 233/291 [00:05<00:01, 42.84it/s]
Loading 0:  82%|████████▏ | 238/291 [00:05<00:01, 43.11it/s]
Loading 0:  84%|████████▎ | 243/291 [00:05<00:01, 44.04it/s]
Loading 0:  85%|████████▌ | 248/291 [00:06<00:01, 36.75it/s]
Loading 0:  88%|████████▊ | 255/291 [00:06<00:00, 43.11it/s]
Loading 0:  89%|████████▉ | 260/291 [00:06<00:00, 42.97it/s]
Loading 0:  91%|█████████ | 265/291 [00:06<00:00, 44.02it/s]
Loading 0:  93%|█████████▎| 271/291 [00:06<00:00, 41.95it/s]
Loading 0:  95%|█████████▍| 276/291 [00:06<00:00, 41.84it/s]
Loading 0:  97%|█████████▋| 281/291 [00:06<00:00, 41.97it/s]
Loading 0:  98%|█████████▊| 286/291 [00:07<00:00, 36.82it/s]
Loading 0: 100%|█████████▉| 290/291 [00:12<00:00,  2.82it/s]
                                                            

Job cycy233-model4-1-v1-mkmlizer completed after 83.41s with status: succeeded
Stopping job with name cycy233-model4-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.92s
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-model4-1-v1
Waiting for inference service cycy233-model4-1-v1 to be ready
Inference service cycy233-model4-1-v1 ready after 251.0062551498413s
Pipeline stage MKMLDeployer completed in 251.52s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.724381685256958s
Received healthy response to inference request in 1.1916239261627197s
Received healthy response to inference request in 1.2222304344177246s
Received healthy response to inference request in 1.118588924407959s
Received healthy response to inference request in 1.154961109161377s
5 requests
0 failed requests
5th percentile: 1.1258633613586426
10th percentile: 1.1331377983093263
20th percentile: 1.1476866722106933
30th percentile: 1.1622936725616455
40th percentile: 1.1769587993621826
50th percentile: 1.1916239261627197
60th percentile: 1.2038665294647217
70th percentile: 1.2161091327667237
80th percentile: 1.3226606845855713
90th percentile: 1.5235211849212646
95th percentile: 1.6239514350891113
99th percentile: 1.7042956352233887
mean time: 1.2823572158813477
Pipeline stage StressChecker completed in 7.75s
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 0.94s
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 0.64s
Shutdown handler de-registered
cycy233-model4-1_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 0.09s
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-model4-1-v1-profiler
Waiting for inference service cycy233-model4-1-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3597.09s
Shutdown handler de-registered
cycy233-model4-1_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-model4-1_v1 status is now torndown due to DeploymentManager action