developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v20_v9
model_name: cloudyu-nemo-dpo-v20_v1
model_group: cloudyu/Nemo-DPO-V20
status: inactive
timestamp: 2024-12-17T10:43:08+00:00
num_battles: 14337
num_wins: 7515
celo_rating: 1277.72
family_friendly_score: 0.562
family_friendly_standard_error: 0.00701649485141976
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V20
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6237755648169846, 'latency_mean': 1.6030819535255432, 'latency_p50': 1.6003714799880981, 'latency_p90': 1.7666399717330932}, {'batch_size': 3, 'throughput': 1.1507275661724614, 'latency_mean': 2.5974078357219694, 'latency_p50': 2.6077741384506226, 'latency_p90': 2.8820641756057737}, {'batch_size': 5, 'throughput': 1.400797291457838, 'latency_mean': 3.549156030416489, 'latency_p50': 3.551231861114502, 'latency_p90': 3.9877018690109254}, {'batch_size': 6, 'throughput': 1.4733906216624755, 'latency_mean': 4.05038787484169, 'latency_p50': 4.002458095550537, 'latency_p90': 4.537640976905823}, {'batch_size': 8, 'throughput': 1.5352515180328008, 'latency_mean': 5.176488189697266, 'latency_p50': 5.191644310951233, 'latency_p90': 5.748145174980164}, {'batch_size': 10, 'throughput': 1.5708391382802591, 'latency_mean': 6.317075905799865, 'latency_p50': 6.364191770553589, 'latency_p90': 7.1616055250167845}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v20_v1
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V20
model_size: 13B
ranking_group: single
throughput_3p7s: 1.43
us_pacific_date: 2024-12-17
win_ratio: 0.5241682360326428
generation_params: {'temperature': 0.95, '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-nemo-dpo-v20-v9-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v20-v9-mkmlizer to finish
cloudyu-nemo-dpo-v20-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v20-v9-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v20-v9-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v20-v9-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v20-v9-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v20-v9-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v20-v9-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v9-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v20-v9-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v20-v9-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v20-v9-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v9-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v20-v9-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v20-v9-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v9-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v20-v9-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v20-v9-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v20-v9-mkmlizer: ║ ║
cloudyu-nemo-dpo-v20-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v20-v9-mkmlizer: Downloaded to shared memory in 34.287s
cloudyu-nemo-dpo-v20-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpt88ak06p, device:0
cloudyu-nemo-dpo-v20-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v20-v9-mkmlizer: quantized model in 37.159s
cloudyu-nemo-dpo-v20-v9-mkmlizer: Processed model cloudyu/Nemo-DPO-V20 in 71.447s
cloudyu-nemo-dpo-v20-v9-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v20-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v20-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v9
cloudyu-nemo-dpo-v20-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v9/config.json
cloudyu-nemo-dpo-v20-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v9/special_tokens_map.json
cloudyu-nemo-dpo-v20-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v9/tokenizer_config.json
cloudyu-nemo-dpo-v20-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v9/tokenizer.json
cloudyu-nemo-dpo-v20-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v20-v9/flywheel_model.0.safetensors
Job cloudyu-nemo-dpo-v20-v9-mkmlizer completed after 105.13s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v20-v9-mkmlizer
Pipeline stage MKMLizer completed in 105.66s
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 cloudyu-nemo-dpo-v20-v9
Waiting for inference service cloudyu-nemo-dpo-v20-v9 to be ready
Inference service cloudyu-nemo-dpo-v20-v9 ready after 230.83213305473328s
Pipeline stage MKMLDeployer completed in 231.36s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0540177822113037s
Received healthy response to inference request in 2.0118796825408936s
Received healthy response to inference request in 1.656301498413086s
Received healthy response to inference request in 1.652061939239502s
Received healthy response to inference request in 1.770068645477295s
5 requests
0 failed requests
5th percentile: 1.6529098510742188
10th percentile: 1.6537577629089355
20th percentile: 1.655453586578369
30th percentile: 1.6790549278259277
40th percentile: 1.7245617866516114
50th percentile: 1.770068645477295
60th percentile: 1.8667930603027343
70th percentile: 1.9635174751281739
80th percentile: 2.0203073024749756
90th percentile: 2.0371625423431396
95th percentile: 2.0455901622772217
99th percentile: 2.0523322582244874
mean time: 1.828865909576416
Pipeline stage StressChecker completed in 10.55s
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 2.47s
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 2.30s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v9 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 3074.60s
Shutdown handler de-registered
cloudyu-nemo-dpo-v20_v9 status is now inactive due to auto deactivation removed underperforming models