developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v19_v10
model_name: cloudyu-nemo-dpo-v19_v1
model_group: cloudyu/Nemo-DPO-V19
status: inactive
timestamp: 2024-12-17T00:04:29+00:00
num_battles: 14875
num_wins: 7780
celo_rating: 1279.74
family_friendly_score: 0.5644
family_friendly_standard_error: 0.007012169992234929
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V19
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6126367129315615, 'latency_mean': 1.6322091937065124, 'latency_p50': 1.6316273212432861, 'latency_p90': 1.807605767250061}, {'batch_size': 3, 'throughput': 1.1449831582837207, 'latency_mean': 2.6167904806137083, 'latency_p50': 2.6037737131118774, 'latency_p90': 2.886856770515442}, {'batch_size': 5, 'throughput': 1.3740649570267762, 'latency_mean': 3.6242519676685334, 'latency_p50': 3.6150786876678467, 'latency_p90': 4.0864969253540036}, {'batch_size': 6, 'throughput': 1.4542104184613645, 'latency_mean': 4.097355215549469, 'latency_p50': 4.088532567024231, 'latency_p90': 4.64776337146759}, {'batch_size': 8, 'throughput': 1.520237156045267, 'latency_mean': 5.228150981664657, 'latency_p50': 5.225556373596191, 'latency_p90': 5.890201568603516}, {'batch_size': 10, 'throughput': 1.563330683448793, 'latency_mean': 6.346830761432647, 'latency_p50': 6.355870604515076, 'latency_p90': 7.203092098236084}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v19_v1
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V19
model_size: 13B
ranking_group: single
throughput_3p7s: 1.39
us_pacific_date: 2024-12-16
win_ratio: 0.5230252100840336
generation_params: {'temperature': 1.1, 'top_p': 0.95, 'min_p': 0.05, '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-v19-v10-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v19-v10-mkmlizer to finish
cloudyu-nemo-dpo-v19-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v19-v10-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v19-v10-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v19-v10-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v19-v10-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v19-v10-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v19-v10-mkmlizer: ║ ║
cloudyu-nemo-dpo-v19-v10-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v19-v10-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v19-v10-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v19-v10-mkmlizer: ║ ║
cloudyu-nemo-dpo-v19-v10-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v19-v10-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v19-v10-mkmlizer: ║ ║
cloudyu-nemo-dpo-v19-v10-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v19-v10-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v19-v10-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v19-v10-mkmlizer: ║ ║
cloudyu-nemo-dpo-v19-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v19-v10-mkmlizer: Downloaded to shared memory in 32.344s
cloudyu-nemo-dpo-v19-v10-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkkvf5ycf, device:0
cloudyu-nemo-dpo-v19-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v19-v10-mkmlizer: quantized model in 36.509s
cloudyu-nemo-dpo-v19-v10-mkmlizer: Processed model cloudyu/Nemo-DPO-V19 in 68.853s
cloudyu-nemo-dpo-v19-v10-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v19-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v19-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v10
cloudyu-nemo-dpo-v19-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v10/config.json
cloudyu-nemo-dpo-v19-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v10/special_tokens_map.json
cloudyu-nemo-dpo-v19-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v10/tokenizer_config.json
cloudyu-nemo-dpo-v19-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v10/tokenizer.json
cloudyu-nemo-dpo-v19-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v19-v10/flywheel_model.0.safetensors
Job cloudyu-nemo-dpo-v19-v10-mkmlizer completed after 94.87s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v19-v10-mkmlizer
Pipeline stage MKMLizer completed in 95.37s
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-v19-v10
Waiting for inference service cloudyu-nemo-dpo-v19-v10 to be ready
Inference service cloudyu-nemo-dpo-v19-v10 ready after 231.46545362472534s
Pipeline stage MKMLDeployer completed in 231.99s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9166126251220703s
Received healthy response to inference request in 1.6497302055358887s
Received healthy response to inference request in 2.172698974609375s
Received healthy response to inference request in 1.808119535446167s
Received healthy response to inference request in 1.697746992111206s
5 requests
0 failed requests
5th percentile: 1.6593335628509522
10th percentile: 1.6689369201660156
20th percentile: 1.6881436347961425
30th percentile: 1.7198215007781983
40th percentile: 1.7639705181121825
50th percentile: 1.808119535446167
60th percentile: 1.9539513111114502
70th percentile: 2.0997830867767333
80th percentile: 2.321481704711914
90th percentile: 2.619047164916992
95th percentile: 2.7678298950195312
99th percentile: 2.8868560791015625
mean time: 2.0489816665649414
Pipeline stage StressChecker completed in 11.59s
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 2.19s
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 2.05s
Shutdown handler de-registered
cloudyu-nemo-dpo-v19_v10 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 3015.96s
Shutdown handler de-registered
cloudyu-nemo-dpo-v19_v10 status is now inactive due to auto deactivation removed underperforming models