developer_uid: cloudyu
submission_id: cloudyu-chaiml-nemo-dpo-v6_v14
model_name: cloudyu-chaiml-nemo-dpo-v6_v14
model_group: cloudyu/ChaiML-Nemo-DPO-
status: inactive
timestamp: 2024-12-03T09:59:01+00:00
num_battles: 15988
num_wins: 8073
celo_rating: 1267.55
family_friendly_score: 0.5662
family_friendly_standard_error: 0.007008816733229655
submission_type: basic
model_repo: cloudyu/ChaiML-Nemo-DPO-V6
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6168506876934795, 'latency_mean': 1.6210683727264403, 'latency_p50': 1.61712646484375, 'latency_p90': 1.7869763135910035}, {'batch_size': 3, 'throughput': 1.136989948670644, 'latency_mean': 2.6296489703655244, 'latency_p50': 2.6318836212158203, 'latency_p90': 2.9546835660934447}, {'batch_size': 5, 'throughput': 1.3941330057626353, 'latency_mean': 3.57532853603363, 'latency_p50': 3.580472946166992, 'latency_p90': 3.9691739320755004}, {'batch_size': 6, 'throughput': 1.4714538213357584, 'latency_mean': 4.052050609588623, 'latency_p50': 4.065367817878723, 'latency_p90': 4.521886157989502}, {'batch_size': 8, 'throughput': 1.5323003149465428, 'latency_mean': 5.195695128440857, 'latency_p50': 5.17520272731781, 'latency_p90': 5.865659189224243}, {'batch_size': 10, 'throughput': 1.566182809008679, 'latency_mean': 6.343037420511246, 'latency_p50': 6.3803664445877075, 'latency_p90': 7.2147478580474855}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-chaiml-nemo-dpo-v6_v14
is_internal_developer: False
language_model: cloudyu/ChaiML-Nemo-DPO-V6
model_size: 13B
ranking_group: single
throughput_3p7s: 1.42
us_pacific_date: 2024-12-03
win_ratio: 0.5049412059044284
generation_params: {'temperature': 0.99, 'top_p': 0.99, 'min_p': 0.01, 'top_k': 80, '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': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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 cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: ║     _____            __           __                                ║
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: ║       /___/                                                         ║
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: ║  belonging to:                                                      ║
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: Downloaded to shared memory in 47.306s
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpam1iwx5z, device:0
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: quantized model in 36.518s
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V6 in 83.825s
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v14
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v14/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v14/config.json
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v14/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v14/tokenizer.json
cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v14/flywheel_model.0.safetensors
Job cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer completed after 114.62s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v6-v14-mkmlizer
Pipeline stage MKMLizer completed in 115.14s
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 cloudyu-chaiml-nemo-dpo-v6-v14
Waiting for inference service cloudyu-chaiml-nemo-dpo-v6-v14 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cloudyu-chaiml-nemo-dpo-v6-v14 ready after 150.57972884178162s
Pipeline stage MKMLDeployer completed in 151.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.060256242752075s
Received healthy response to inference request in 1.8241252899169922s
Received healthy response to inference request in 1.8699569702148438s
Received healthy response to inference request in 1.8067731857299805s
Received healthy response to inference request in 1.7703299522399902s
5 requests
0 failed requests
5th percentile: 1.7776185989379882
10th percentile: 1.7849072456359862
20th percentile: 1.7994845390319825
30th percentile: 1.8102436065673828
40th percentile: 1.8171844482421875
50th percentile: 1.8241252899169922
60th percentile: 1.8424579620361328
70th percentile: 1.8607906341552733
80th percentile: 1.9080168247222902
90th percentile: 1.9841365337371826
95th percentile: 2.022196388244629
99th percentile: 2.052644271850586
mean time: 1.8662883281707763
Pipeline stage StressChecker completed in 10.70s
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 2.44s
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 2.33s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v6_v14 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v6-v14-profiler
Waiting for inference service cloudyu-chaiml-nemo-dpo-v6-v14-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 3058.22s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v6_v14 status is now inactive due to auto deactivation removed underperforming models