developer_uid: cloudyu
submission_id: cloudyu-nemo-dpo-v18_v2
model_name: cloudyu-nemo-dpo-v18_v1
model_group: cloudyu/Nemo-DPO-V18
status: inactive
timestamp: 2024-12-08T11:12:36+00:00
num_battles: 17892
num_wins: 9274
celo_rating: 1276.59
family_friendly_score: 0.5542
family_friendly_standard_error: 0.007029400543431851
submission_type: basic
model_repo: cloudyu/Nemo-DPO-V18
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6185934616894099, 'latency_mean': 1.6164839124679566, 'latency_p50': 1.6118409633636475, 'latency_p90': 1.7720469951629638}, {'batch_size': 3, 'throughput': 1.1537095207363381, 'latency_mean': 2.5924099922180175, 'latency_p50': 2.6032835245132446, 'latency_p90': 2.8210866451263428}, {'batch_size': 5, 'throughput': 1.4037426686347605, 'latency_mean': 3.5509005296230316, 'latency_p50': 3.5323541164398193, 'latency_p90': 3.9558151006698608}, {'batch_size': 6, 'throughput': 1.4721069672061153, 'latency_mean': 4.0551077127456665, 'latency_p50': 4.064503192901611, 'latency_p90': 4.559428930282593}, {'batch_size': 8, 'throughput': 1.5583895213130983, 'latency_mean': 5.101028301715851, 'latency_p50': 5.100046396255493, 'latency_p90': 5.750931763648986}, {'batch_size': 10, 'throughput': 1.591496602641024, 'latency_mean': 6.233836488723755, 'latency_p50': 6.229183793067932, 'latency_p90': 7.022669100761413}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-nemo-dpo-v18_v1
is_internal_developer: False
language_model: cloudyu/Nemo-DPO-V18
model_size: 13B
ranking_group: single
throughput_3p7s: 1.43
us_pacific_date: 2024-12-08
win_ratio: 0.518332215515314
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-nemo-dpo-v18-v2-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v18-v2-mkmlizer to finish
cloudyu-nemo-dpo-v18-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v18-v2-mkmlizer: ║ _____ __ __ ║
cloudyu-nemo-dpo-v18-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cloudyu-nemo-dpo-v18-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cloudyu-nemo-dpo-v18-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cloudyu-nemo-dpo-v18-v2-mkmlizer: ║ /___/ ║
cloudyu-nemo-dpo-v18-v2-mkmlizer: ║ ║
cloudyu-nemo-dpo-v18-v2-mkmlizer: ║ Version: 0.11.12 ║
cloudyu-nemo-dpo-v18-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cloudyu-nemo-dpo-v18-v2-mkmlizer: ║ https://mk1.ai ║
cloudyu-nemo-dpo-v18-v2-mkmlizer: ║ ║
cloudyu-nemo-dpo-v18-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cloudyu-nemo-dpo-v18-v2-mkmlizer: ║ belonging to: ║
cloudyu-nemo-dpo-v18-v2-mkmlizer: ║ ║
cloudyu-nemo-dpo-v18-v2-mkmlizer: ║ Chai Research Corp. ║
cloudyu-nemo-dpo-v18-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cloudyu-nemo-dpo-v18-v2-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
cloudyu-nemo-dpo-v18-v2-mkmlizer: ║ ║
cloudyu-nemo-dpo-v18-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v18-v2-mkmlizer: Downloaded to shared memory in 50.028s
cloudyu-nemo-dpo-v18-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpmqrb0vah, device:0
cloudyu-nemo-dpo-v18-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v18-v2-mkmlizer: quantized model in 37.199s
cloudyu-nemo-dpo-v18-v2-mkmlizer: Processed model cloudyu/Nemo-DPO-V18 in 87.228s
cloudyu-nemo-dpo-v18-v2-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v18-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v18-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v18-v2
cloudyu-nemo-dpo-v18-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v18-v2/config.json
cloudyu-nemo-dpo-v18-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v18-v2/special_tokens_map.json
cloudyu-nemo-dpo-v18-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v18-v2/tokenizer_config.json
cloudyu-nemo-dpo-v18-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v18-v2/tokenizer.json
cloudyu-nemo-dpo-v18-v2-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:12, 27.88it/s] Loading 0: 4%|▎ | 13/363 [00:00<00:07, 48.65it/s] Loading 0: 5%|▌ | 19/363 [00:00<00:07, 47.02it/s] Loading 0: 7%|▋ | 24/363 [00:00<00:07, 45.72it/s] Loading 0: 9%|▊ | 31/363 [00:00<00:06, 51.86it/s] Loading 0: 10%|█ | 37/363 [00:00<00:06, 47.07it/s] Loading 0: 12%|█▏ | 42/363 [00:00<00:07, 44.86it/s] Loading 0: 13%|█▎ | 49/363 [00:01<00:06, 50.12it/s] Loading 0: 15%|█▌ | 55/363 [00:01<00:06, 47.85it/s] Loading 0: 17%|█▋ | 61/363 [00:01<00:08, 34.70it/s] Loading 0: 18%|█▊ | 66/363 [00:01<00:08, 33.63it/s] Loading 0: 20%|█▉ | 71/363 [00:01<00:07, 36.51it/s] Loading 0: 21%|██ | 76/363 [00:01<00:07, 37.48it/s] Loading 0: 22%|██▏ | 81/363 [00:01<00:07, 39.32it/s] Loading 0: 24%|██▍ | 87/363 [00:02<00:06, 40.08it/s] Loading 0: 25%|██▌ | 92/363 [00:02<00:06, 40.49it/s] Loading 0: 27%|██▋ | 99/363 [00:02<00:05, 45.20it/s] Loading 0: 29%|██▉ | 105/363 [00:02<00:05, 44.18it/s] Loading 0: 31%|███ | 112/363 [00:02<00:05, 47.92it/s] Loading 0: 32%|███▏ | 117/363 [00:02<00:05, 45.50it/s] Loading 0: 34%|███▍ | 123/363 [00:02<00:05, 43.07it/s] Loading 0: 35%|███▌ | 128/363 [00:03<00:05, 40.74it/s] Loading 0: 37%|███▋ | 134/363 [00:03<00:05, 43.64it/s] Loading 0: 38%|███▊ | 139/363 [00:03<00:05, 44.59it/s] Loading 0: 40%|███▉ | 144/363 [00:03<00:07, 27.45it/s] Loading 0: 41%|████ | 149/363 [00:03<00:07, 29.90it/s] Loading 0: 43%|████▎ | 157/363 [00:03<00:05, 38.04it/s] Loading 0: 45%|████▍ | 163/363 [00:04<00:05, 37.42it/s] Loading 0: 46%|████▋ | 168/363 [00:04<00:05, 37.46it/s] Loading 0: 48%|████▊ | 175/363 [00:04<00:04, 42.70it/s] Loading 0: 50%|████▉ | 180/363 [00:04<00:04, 44.05it/s] Loading 0: 51%|█████ | 185/363 [00:04<00:04, 38.06it/s] Loading 0: 53%|█████▎ | 193/363 [00:04<00:03, 46.23it/s] Loading 0: 55%|█████▍ | 199/363 [00:04<00:03, 45.43it/s] Loading 0: 56%|█████▌ | 204/363 [00:04<00:03, 43.96it/s] Loading 0: 58%|█████▊ | 211/363 [00:05<00:03, 47.72it/s] Loading 0: 60%|█████▉ | 216/363 [00:05<00:03, 47.69it/s] Loading 0: 61%|██████ | 221/363 [00:05<00:02, 47.98it/s] Loading 0: 62%|██████▏ | 226/363 [00:05<00:04, 28.62it/s] Loading 0: 63%|██████▎ | 230/363 [00:05<00:04, 28.26it/s] Loading 0: 66%|██████▌ | 238/363 [00:05<00:03, 36.69it/s] Loading 0: 67%|██████▋ | 244/363 [00:06<00:03, 38.06it/s] Loading 0: 69%|██████▊ | 249/363 [00:06<00:02, 38.03it/s] Loading 0: 70%|███████ | 255/363 [00:06<00:02, 42.42it/s] Loading 0: 72%|███████▏ | 260/363 [00:06<00:02, 41.61it/s] Loading 0: 73%|███████▎ | 265/363 [00:06<00:02, 42.77it/s] Loading 0: 75%|███████▍ | 271/363 [00:06<00:02, 42.58it/s] Loading 0: 76%|███████▌ | 276/363 [00:06<00:02, 41.33it/s] Loading 0: 78%|███████▊ | 282/363 [00:06<00:01, 45.74it/s] Loading 0: 79%|███████▉ | 287/363 [00:07<00:01, 45.64it/s] Loading 0: 80%|████████ | 292/363 [00:07<00:01, 45.02it/s] Loading 0: 82%|████████▏ | 298/363 [00:07<00:01, 44.03it/s] Loading 0: 84%|████████▎ | 304/363 [00:14<00:22, 2.59it/s] Loading 0: 85%|████████▍ | 308/363 [00:14<00:16, 3.30it/s] Loading 0: 86%|████████▌ | 312/363 [00:14<00:11, 4.26it/s] Loading 0: 88%|████████▊ | 320/363 [00:14<00:06, 7.01it/s] Loading 0: 90%|████████▉ | 326/363 [00:14<00:03, 9.48it/s] Loading 0: 91%|█████████ | 331/363 [00:14<00:02, 12.00it/s] Loading 0: 93%|█████████▎| 338/363 [00:14<00:01, 16.72it/s] Loading 0: 94%|█████████▍| 343/363 [00:15<00:00, 20.10it/s] Loading 0: 96%|█████████▌| 348/363 [00:15<00:00, 22.01it/s] Loading 0: 98%|█████████▊| 356/363 [00:15<00:00, 29.75it/s] Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 32.42it/s]
Job cloudyu-nemo-dpo-v18-v2-mkmlizer completed after 115.07s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v18-v2-mkmlizer
Pipeline stage MKMLizer completed in 115.55s
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-nemo-dpo-v18-v2
Waiting for inference service cloudyu-nemo-dpo-v18-v2 to be ready
Inference service cloudyu-nemo-dpo-v18-v2 ready after 171.08655405044556s
Pipeline stage MKMLDeployer completed in 171.62s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4984517097473145s
Received healthy response to inference request in 1.9165058135986328s
Received healthy response to inference request in 1.6757092475891113s
Received healthy response to inference request in 2.0725412368774414s
Received healthy response to inference request in 1.8960561752319336s
5 requests
0 failed requests
5th percentile: 1.7197786331176759
10th percentile: 1.7638480186462402
20th percentile: 1.851986789703369
30th percentile: 1.9001461029052735
40th percentile: 1.9083259582519532
50th percentile: 1.9165058135986328
60th percentile: 1.9789199829101562
70th percentile: 2.0413341522216797
80th percentile: 2.157723331451416
90th percentile: 2.3280875205993654
95th percentile: 2.41326961517334
99th percentile: 2.4814152908325195
mean time: 2.011852836608887
Pipeline stage StressChecker completed in 11.51s
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 2.48s
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 2.37s
Shutdown handler de-registered
cloudyu-nemo-dpo-v18_v2 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 cloudyu-nemo-dpo-v18-v2-profiler
Waiting for inference service cloudyu-nemo-dpo-v18-v2-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 2657.68s
Shutdown handler de-registered
cloudyu-nemo-dpo-v18_v2 status is now inactive due to auto deactivation removed underperforming models