developer_uid: cycy233
submission_id: cycy233-model3-6_v1
model_name: 486
model_group: cycy233/model3-6
status: torndown
timestamp: 2025-02-27T03:38:16+00:00
num_battles: 5457
num_wins: 2603
celo_rating: 1247.99
family_friendly_score: 0.5038
family_friendly_standard_error: 0.007070863596478156
submission_type: basic
model_repo: cycy233/model3-6
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': 0.8453917786567416, 'latency_mean': 1.1828107392787934, 'latency_p50': 1.182231068611145, 'latency_p90': 1.3058176279067992}, {'batch_size': 4, 'throughput': 1.7828737160291799, 'latency_mean': 2.228506249189377, 'latency_p50': 2.2295846939086914, 'latency_p90': 2.5259087800979616}, {'batch_size': 5, 'throughput': 1.9296160219136966, 'latency_mean': 2.582780503034592, 'latency_p50': 2.5949862003326416, 'latency_p90': 2.871094226837158}, {'batch_size': 8, 'throughput': 2.1105609317927168, 'latency_mean': 3.76985933303833, 'latency_p50': 3.7855457067489624, 'latency_p90': 4.227060866355896}, {'batch_size': 10, 'throughput': 2.191675083525103, 'latency_mean': 4.526541191339493, 'latency_p50': 4.496828675270081, 'latency_p90': 5.20080931186676}, {'batch_size': 12, 'throughput': 2.2003691782947823, 'latency_mean': 5.390115679502487, 'latency_p50': 5.373257160186768, 'latency_p90': 6.188199663162232}, {'batch_size': 15, 'throughput': 2.2136019331039027, 'latency_mean': 6.683097126483918, 'latency_p50': 6.731946229934692, 'latency_p90': 7.479174876213074}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: 486
is_internal_developer: False
language_model: cycy233/model3-6
model_size: 8B
ranking_group: single
throughput_3p7s: 2.11
us_pacific_date: 2025-02-26
win_ratio: 0.47700201575957485
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-model3-6-v1-mkmlizer
Waiting for job on cycy233-model3-6-v1-mkmlizer to finish
cycy233-model3-6-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-model3-6-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-model3-6-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-model3-6-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-model3-6-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-model3-6-v1-mkmlizer: ║       /___/                                                         ║
cycy233-model3-6-v1-mkmlizer: ║                                                                     ║
cycy233-model3-6-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
cycy233-model3-6-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-model3-6-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-model3-6-v1-mkmlizer: ║                                                                     ║
cycy233-model3-6-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-model3-6-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-model3-6-v1-mkmlizer: ║                                                                     ║
cycy233-model3-6-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-model3-6-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-model3-6-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cycy233-model3-6-v1-mkmlizer: ║                                                                     ║
cycy233-model3-6-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-model3-6-v1-mkmlizer: Downloaded to shared memory in 31.877s
cycy233-model3-6-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjgfua724, device:0
cycy233-model3-6-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission mistralai-mistral-smal_78605_v18: HTTPConnectionPool(host='mistralai-mistral-smal-78605-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
cycy233-model3-6-v1-mkmlizer: quantized model in 26.142s
cycy233-model3-6-v1-mkmlizer: Processed model cycy233/model3-6 in 58.020s
cycy233-model3-6-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-model3-6-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-model3-6-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-model3-6-v1
cycy233-model3-6-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-model3-6-v1/config.json
cycy233-model3-6-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-model3-6-v1/special_tokens_map.json
cycy233-model3-6-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-model3-6-v1/tokenizer_config.json
cycy233-model3-6-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-model3-6-v1/tokenizer.json
cycy233-model3-6-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-model3-6-v1/flywheel_model.0.safetensors
Job cycy233-model3-6-v1-mkmlizer completed after 83.6s with status: succeeded
Stopping job with name cycy233-model3-6-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.06s
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-model3-6-v1
Waiting for inference service cycy233-model3-6-v1 to be ready
Failed to get response for submission nischaydnk-mistral24bas_99124_v4: HTTPConnectionPool(host='nischaydnk-mistral24bas-99124-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-mistral24bas_99124_v4: HTTPConnectionPool(host='nischaydnk-mistral24bas-99124-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission nischaydnk-mistral24bas_99124_v4: HTTPConnectionPool(host='nischaydnk-mistral24bas-99124-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission mistralai-mistral-smal_78605_v18: HTTPConnectionPool(host='mistralai-mistral-smal-78605-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service cycy233-model3-6-v1 ready after 281.65621995925903s
Pipeline stage MKMLDeployer completed in 282.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.981290340423584s
Received healthy response to inference request in 1.0987184047698975s
Received healthy response to inference request in 1.3636629581451416s
Received healthy response to inference request in 1.083491563796997s
Received healthy response to inference request in 1.1179566383361816s
5 requests
0 failed requests
5th percentile: 1.0865369319915772
10th percentile: 1.0895823001861573
20th percentile: 1.0956730365753173
30th percentile: 1.1025660514831543
40th percentile: 1.1102613449096679
50th percentile: 1.1179566383361816
60th percentile: 1.2162391662597656
70th percentile: 1.3145216941833495
80th percentile: 1.4871884346008302
90th percentile: 1.734239387512207
95th percentile: 1.8577648639678954
99th percentile: 1.9565852451324464
mean time: 1.3290239810943603
Pipeline stage StressChecker completed in 7.90s
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 0.65s
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 0.65s
Shutdown handler de-registered
cycy233-model3-6_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 2322.31s
Shutdown handler de-registered
cycy233-model3-6_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-model3-6_v1 status is now torndown due to DeploymentManager action