developer_uid: cycy233
submission_id: cycy233-model1-4_v1
model_name: 486
model_group: cycy233/model1-4
status: torndown
timestamp: 2025-02-25T03:37:25+00:00
num_battles: 5574
num_wins: 2656
celo_rating: 1239.79
family_friendly_score: 0.528
family_friendly_standard_error: 0.007059971671331267
submission_type: basic
model_repo: cycy233/model1-4
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': 0.8513089562451482, 'latency_mean': 1.1745993173122407, 'latency_p50': 1.170725703239441, 'latency_p90': 1.293789267539978}, {'batch_size': 4, 'throughput': 1.769558747364212, 'latency_mean': 2.2466624069213865, 'latency_p50': 2.2278451919555664, 'latency_p90': 2.539469361305237}, {'batch_size': 5, 'throughput': 1.9148730950031494, 'latency_mean': 2.6068942952156067, 'latency_p50': 2.619665741920471, 'latency_p90': 2.90183744430542}, {'batch_size': 8, 'throughput': 2.1265516617862614, 'latency_mean': 3.741046350002289, 'latency_p50': 3.7245033979415894, 'latency_p90': 4.215614533424377}, {'batch_size': 10, 'throughput': 2.157814260070399, 'latency_mean': 4.604217330217361, 'latency_p50': 4.568861722946167, 'latency_p90': 5.333724284172058}, {'batch_size': 12, 'throughput': 2.212972414723414, 'latency_mean': 5.378939307928086, 'latency_p50': 5.3690232038497925, 'latency_p90': 6.202383589744568}, {'batch_size': 15, 'throughput': 2.208944552152969, 'latency_mean': 6.716609750986099, 'latency_p50': 6.687480807304382, 'latency_p90': 7.500982737541198}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: 486
is_internal_developer: False
language_model: cycy233/model1-4
model_size: 8B
ranking_group: single
throughput_3p7s: 2.13
us_pacific_date: 2025-02-24
win_ratio: 0.47649802655184786
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-model1-4-v1-mkmlizer
Waiting for job on cycy233-model1-4-v1-mkmlizer to finish
cycy233-model1-4-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-model1-4-v1-mkmlizer: ║ _____ __ __ ║
cycy233-model1-4-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-model1-4-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-model1-4-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-model1-4-v1-mkmlizer: ║ /___/ ║
cycy233-model1-4-v1-mkmlizer: ║ ║
cycy233-model1-4-v1-mkmlizer: ║ Version: 0.12.8 ║
cycy233-model1-4-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-model1-4-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-model1-4-v1-mkmlizer: ║ ║
cycy233-model1-4-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-model1-4-v1-mkmlizer: ║ belonging to: ║
cycy233-model1-4-v1-mkmlizer: ║ ║
cycy233-model1-4-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-model1-4-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-model1-4-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
cycy233-model1-4-v1-mkmlizer: ║ ║
cycy233-model1-4-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-model1-4-v1-mkmlizer: Downloaded to shared memory in 47.931s
cycy233-model1-4-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpu_s21m3e, device:0
cycy233-model1-4-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-model1-4-v1-mkmlizer: quantized model in 27.325s
cycy233-model1-4-v1-mkmlizer: Processed model cycy233/model1-4 in 75.257s
cycy233-model1-4-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-model1-4-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-model1-4-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-model1-4-v1
cycy233-model1-4-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-model1-4-v1/config.json
cycy233-model1-4-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-model1-4-v1/special_tokens_map.json
cycy233-model1-4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-model1-4-v1/tokenizer_config.json
cycy233-model1-4-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-model1-4-v1/tokenizer.json
cycy233-model1-4-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-model1-4-v1/flywheel_model.0.safetensors
cycy233-model1-4-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:09, 30.50it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:05, 52.50it/s] Loading 0: 7%|▋ | 19/291 [00:00<00:06, 44.32it/s] Loading 0: 8%|▊ | 24/291 [00:00<00:06, 42.67it/s] Loading 0: 11%|█ | 31/291 [00:00<00:05, 48.96it/s] Loading 0: 13%|█▎ | 37/291 [00:00<00:05, 43.90it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:05, 43.01it/s] Loading 0: 17%|█▋ | 49/291 [00:01<00:04, 48.68it/s] Loading 0: 19%|█▉ | 55/291 [00:01<00:05, 44.43it/s] Loading 0: 21%|██ | 60/291 [00:01<00:05, 43.03it/s] Loading 0: 23%|██▎ | 66/291 [00:01<00:04, 47.08it/s] Loading 0: 24%|██▍ | 71/291 [00:01<00:04, 45.72it/s] Loading 0: 26%|██▌ | 76/291 [00:01<00:04, 45.90it/s] Loading 0: 28%|██▊ | 81/291 [00:01<00:04, 45.50it/s] Loading 0: 30%|██▉ | 86/291 [00:02<00:07, 26.02it/s] Loading 0: 32%|███▏ | 93/291 [00:02<00:05, 33.43it/s] Loading 0: 34%|███▎ | 98/291 [00:02<00:05, 35.40it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:04, 37.76it/s] Loading 0: 37%|███▋ | 108/291 [00:02<00:04, 40.09it/s] Loading 0: 39%|███▉ | 113/291 [00:02<00:05, 34.26it/s] Loading 0: 41%|████ | 120/291 [00:02<00:04, 41.73it/s] Loading 0: 43%|████▎ | 125/291 [00:03<00:03, 41.87it/s] Loading 0: 45%|████▍ | 130/291 [00:03<00:03, 42.71it/s] Loading 0: 46%|████▋ | 135/291 [00:03<00:03, 43.94it/s] Loading 0: 48%|████▊ | 140/291 [00:03<00:04, 36.62it/s] Loading 0: 51%|█████ | 147/291 [00:03<00:03, 44.38it/s] Loading 0: 52%|█████▏ | 152/291 [00:03<00:03, 43.94it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:03, 44.63it/s] Loading 0: 56%|█████▌ | 162/291 [00:03<00:02, 45.57it/s] Loading 0: 57%|█████▋ | 167/291 [00:04<00:03, 36.26it/s] Loading 0: 59%|█████▉ | 173/291 [00:04<00:02, 40.37it/s] Loading 0: 62%|██████▏ | 179/291 [00:04<00:02, 44.26it/s] Loading 0: 63%|██████▎ | 184/291 [00:04<00:02, 43.75it/s] Loading 0: 65%|██████▍ | 189/291 [00:04<00:03, 27.49it/s] Loading 0: 67%|██████▋ | 194/291 [00:04<00:03, 30.17it/s] Loading 0: 69%|██████▉ | 201/291 [00:05<00:02, 37.87it/s] Loading 0: 71%|███████ | 206/291 [00:05<00:02, 39.20it/s] Loading 0: 73%|███████▎ | 211/291 [00:05<00:01, 41.05it/s] Loading 0: 74%|███████▍ | 216/291 [00:05<00:01, 42.93it/s] Loading 0: 76%|███████▌ | 221/291 [00:05<00:01, 35.79it/s] Loading 0: 78%|███████▊ | 228/291 [00:05<00:01, 43.34it/s] Loading 0: 80%|████████ | 233/291 [00:05<00:01, 43.43it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 43.47it/s] Loading 0: 84%|████████▎ | 243/291 [00:05<00:01, 44.60it/s] Loading 0: 85%|████████▌ | 248/291 [00:06<00:01, 37.26it/s] Loading 0: 88%|████████▊ | 255/291 [00:06<00:00, 44.86it/s] Loading 0: 89%|████████▉ | 260/291 [00:06<00:00, 44.13it/s] Loading 0: 91%|█████████ | 265/291 [00:06<00:00, 43.88it/s] Loading 0: 93%|█████████▎| 270/291 [00:06<00:00, 44.40it/s] Loading 0: 95%|█████████▍| 275/291 [00:06<00:00, 36.44it/s] Loading 0: 97%|█████████▋| 281/291 [00:06<00:00, 40.76it/s] Loading 0: 98%|█████████▊| 286/291 [00:07<00:00, 36.44it/s] Loading 0: 100%|█████████▉| 290/291 [00:12<00:00, 2.84it/s]
Job cycy233-model1-4-v1-mkmlizer completed after 103.6s with status: succeeded
Stopping job with name cycy233-model1-4-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.07s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-model1-4-v1
Waiting for inference service cycy233-model1-4-v1 to be ready
Inference service cycy233-model1-4-v1 ready after 441.51378774642944s
Pipeline stage MKMLDeployer completed in 441.98s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8943860530853271s
Received healthy response to inference request in 1.2840571403503418s
Received healthy response to inference request in 1.2093415260314941s
Received healthy response to inference request in 1.3572943210601807s
Received healthy response to inference request in 1.145024299621582s
5 requests
0 failed requests
5th percentile: 1.1578877449035645
10th percentile: 1.170751190185547
20th percentile: 1.1964780807495117
30th percentile: 1.2242846488952637
40th percentile: 1.2541708946228027
50th percentile: 1.2840571403503418
60th percentile: 1.3133520126342773
70th percentile: 1.342646884918213
80th percentile: 1.46471266746521
90th percentile: 1.6795493602752687
95th percentile: 1.7869677066802978
99th percentile: 1.8729023838043213
mean time: 1.378020668029785
Pipeline stage StressChecker completed in 7.99s
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 0.59s
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 0.57s
Shutdown handler de-registered
cycy233-model1-4_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-model1-4-v1-profiler
Waiting for inference service cycy233-model1-4-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2410.98s
Shutdown handler de-registered
cycy233-model1-4_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-model1-4_v1 status is now torndown due to DeploymentManager action