developer_uid: cycy233
submission_id: cycy233-model4-12_v1
model_name: 486
model_group: cycy233/model4-12
status: torndown
timestamp: 2025-03-03T07:35:59+00:00
num_battles: 5989
num_wins: 2792
celo_rating: 1239.55
family_friendly_score: 0.5356000000000001
family_friendly_standard_error: 0.007053121861984238
submission_type: basic
model_repo: cycy233/model4-12
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': 0.861041287277319, 'latency_mean': 1.16128955245018, 'latency_p50': 1.1607524156570435, 'latency_p90': 1.2862942695617676}, {'batch_size': 4, 'throughput': 1.7863137454441627, 'latency_mean': 2.225331162214279, 'latency_p50': 2.227347493171692, 'latency_p90': 2.5265262603759764}, {'batch_size': 5, 'throughput': 1.926178802806183, 'latency_mean': 2.5848665869235994, 'latency_p50': 2.59052574634552, 'latency_p90': 2.909319257736206}, {'batch_size': 8, 'throughput': 2.1081362595182975, 'latency_mean': 3.7617708504199983, 'latency_p50': 3.7527964115142822, 'latency_p90': 4.28162796497345}, {'batch_size': 10, 'throughput': 2.1903000740094396, 'latency_mean': 4.531755404472351, 'latency_p50': 4.566127419471741, 'latency_p90': 5.120795798301697}, {'batch_size': 12, 'throughput': 2.2145058628145997, 'latency_mean': 5.3674009168148045, 'latency_p50': 5.44965398311615, 'latency_p90': 6.1009351968765255}, {'batch_size': 15, 'throughput': 2.247119135796404, 'latency_mean': 6.580504899024963, 'latency_p50': 6.5776180028915405, 'latency_p90': 7.34928035736084}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: 486
is_internal_developer: False
language_model: cycy233/model4-12
model_size: 8B
ranking_group: single
throughput_3p7s: 2.12
us_pacific_date: 2025-03-02
win_ratio: 0.4661880113541493
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-model4-12-v1-mkmlizer
Waiting for job on cycy233-model4-12-v1-mkmlizer to finish
cycy233-model4-12-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-model4-12-v1-mkmlizer: ║ _____ __ __ ║
cycy233-model4-12-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-model4-12-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-model4-12-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-model4-12-v1-mkmlizer: ║ /___/ ║
cycy233-model4-12-v1-mkmlizer: ║ ║
cycy233-model4-12-v1-mkmlizer: ║ Version: 0.12.8 ║
cycy233-model4-12-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-model4-12-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-model4-12-v1-mkmlizer: ║ ║
cycy233-model4-12-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-model4-12-v1-mkmlizer: ║ belonging to: ║
cycy233-model4-12-v1-mkmlizer: ║ ║
cycy233-model4-12-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-model4-12-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-model4-12-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
cycy233-model4-12-v1-mkmlizer: ║ ║
cycy233-model4-12-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-model4-12-v1-mkmlizer: Downloaded to shared memory in 26.481s
cycy233-model4-12-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpp0mhd4v_, device:0
cycy233-model4-12-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-model4-12-v1-mkmlizer: quantized model in 25.948s
cycy233-model4-12-v1-mkmlizer: Processed model cycy233/model4-12 in 52.434s
cycy233-model4-12-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-model4-12-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-model4-12-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-model4-12-v1
cycy233-model4-12-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-model4-12-v1/config.json
cycy233-model4-12-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-model4-12-v1/special_tokens_map.json
cycy233-model4-12-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-model4-12-v1/tokenizer_config.json
cycy233-model4-12-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-model4-12-v1/tokenizer.json
cycy233-model4-12-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-model4-12-v1/flywheel_model.0.safetensors
cycy233-model4-12-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:08, 35.17it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:05, 48.99it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:05, 53.12it/s] Loading 0: 10%|█ | 30/291 [00:00<00:04, 58.05it/s] Loading 0: 12%|█▏ | 36/291 [00:00<00:04, 58.16it/s] Loading 0: 14%|█▍ | 42/291 [00:00<00:04, 52.02it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:04, 52.31it/s] Loading 0: 20%|██ | 59/291 [00:01<00:04, 52.85it/s] Loading 0: 23%|██▎ | 68/291 [00:01<00:04, 54.36it/s] Loading 0: 26%|██▋ | 77/291 [00:01<00:03, 54.98it/s] Loading 0: 29%|██▊ | 83/291 [00:01<00:04, 43.16it/s] Loading 0: 30%|███ | 88/291 [00:01<00:04, 42.91it/s] Loading 0: 33%|███▎ | 95/291 [00:01<00:04, 43.37it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:03, 50.92it/s] Loading 0: 37%|███▋ | 109/291 [00:02<00:03, 50.00it/s] Loading 0: 40%|███▉ | 115/291 [00:02<00:03, 51.96it/s] Loading 0: 42%|████▏ | 122/291 [00:02<00:03, 49.30it/s] Loading 0: 45%|████▍ | 130/291 [00:02<00:02, 55.80it/s] Loading 0: 47%|████▋ | 136/291 [00:02<00:02, 53.69it/s] Loading 0: 49%|████▉ | 142/291 [00:02<00:02, 54.88it/s] Loading 0: 51%|█████ | 149/291 [00:02<00:02, 51.14it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 57.71it/s] Loading 0: 56%|█████▋ | 164/291 [00:03<00:02, 55.93it/s] Loading 0: 58%|█████▊ | 170/291 [00:03<00:02, 51.63it/s] Loading 0: 60%|██████ | 176/291 [00:03<00:02, 49.61it/s] Loading 0: 63%|██████▎ | 182/291 [00:03<00:02, 42.86it/s] Loading 0: 64%|██████▍ | 187/291 [00:03<00:02, 34.97it/s] Loading 0: 66%|██████▌ | 192/291 [00:03<00:02, 36.41it/s] Loading 0: 68%|██████▊ | 198/291 [00:04<00:02, 41.25it/s] Loading 0: 70%|██████▉ | 203/291 [00:04<00:02, 39.02it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:01, 48.52it/s] Loading 0: 75%|███████▍ | 217/291 [00:04<00:01, 46.62it/s] Loading 0: 76%|███████▋ | 222/291 [00:04<00:01, 46.05it/s] Loading 0: 79%|███████▊ | 229/291 [00:04<00:01, 51.65it/s] Loading 0: 81%|████████ | 235/291 [00:04<00:01, 45.52it/s] Loading 0: 82%|████████▏ | 240/291 [00:04<00:01, 44.80it/s] Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 49.92it/s] Loading 0: 87%|████████▋ | 253/291 [00:05<00:00, 48.10it/s] Loading 0: 89%|████████▊ | 258/291 [00:05<00:00, 47.90it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 53.00it/s] Loading 0: 93%|█████████▎| 271/291 [00:05<00:00, 50.92it/s] Loading 0: 95%|█████████▌| 277/291 [00:05<00:00, 51.11it/s] Loading 0: 97%|█████████▋| 283/291 [00:05<00:00, 44.00it/s] Loading 0: 99%|█████████▉| 288/291 [00:11<00:00, 3.28it/s]
Job cycy233-model4-12-v1-mkmlizer completed after 83.38s with status: succeeded
Stopping job with name cycy233-model4-12-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.87s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-model4-12-v1
Waiting for inference service cycy233-model4-12-v1 to be ready
Inference service cycy233-model4-12-v1 ready after 140.6271412372589s
Pipeline stage MKMLDeployer completed in 141.06s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.0358476638793945s
Received healthy response to inference request in 0.9304335117340088s
Received healthy response to inference request in 1.2395339012145996s
Received healthy response to inference request in 1.1879947185516357s
5 requests
1 failed requests
5th percentile: 0.9819457530975342
10th percentile: 1.0334579944610596
20th percentile: 1.1364824771881104
30th percentile: 1.1983025550842286
40th percentile: 1.218918228149414
50th percentile: 1.2395339012145996
60th percentile: 1.5580594062805175
70th percentile: 1.8765849113464355
80th percentile: 5.654977369308475
90th percentile: 12.893236780166628
95th percentile: 16.5123664855957
99th percentile: 19.407670249938963
mean time: 5.105061197280884
%s, retrying in %s seconds...
Received healthy response to inference request in 1.3825647830963135s
Received healthy response to inference request in 1.2646565437316895s
Received healthy response to inference request in 1.083925724029541s
Received healthy response to inference request in 1.1665763854980469s
Received healthy response to inference request in 1.4247617721557617s
5 requests
0 failed requests
5th percentile: 1.1004558563232423
10th percentile: 1.1169859886169433
20th percentile: 1.1500462532043456
30th percentile: 1.1861924171447753
40th percentile: 1.2254244804382324
50th percentile: 1.2646565437316895
60th percentile: 1.311819839477539
70th percentile: 1.3589831352233888
80th percentile: 1.3910041809082032
90th percentile: 1.4078829765319825
95th percentile: 1.416322374343872
99th percentile: 1.4230738925933837
mean time: 1.2644970417022705
Pipeline stage StressChecker completed in 34.51s
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 0.66s
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 0.71s
Shutdown handler de-registered
cycy233-model4-12_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 0.11s
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-model4-12-v1-profiler
Waiting for inference service cycy233-model4-12-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 2347.53s
Shutdown handler de-registered
cycy233-model4-12_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-model4-12_v1 status is now torndown due to DeploymentManager action