cloudyu-chaiml-nemo-dpo-v4

submission_id: cloudyu-chaiml-nemo-dpo-v4_v2

developer_uid: cloudyu

best_of: 8

celo_rating: 1247.01

display_name: cloudyu-chaiml-nemo-dpo-v4_v2

family_friendly_score: 0.5684

family_friendly_standard_error: 0.007004590494811242

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}

generation_params: {'temperature': 0.8, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

gpu_counts: {'NVIDIA RTX A5000': 1}

is_internal_developer: False

language_model: cloudyu/ChaiML-Nemo-DPO-V4

latencies: [{'batch_size': 1, 'throughput': 0.6146812965296979, 'latency_mean': 1.626801105737686, 'latency_p50': 1.6258602142333984, 'latency_p90': 1.8042897939682008}, {'batch_size': 3, 'throughput': 1.1234869199265682, 'latency_mean': 2.6622114312648772, 'latency_p50': 2.6410852670669556, 'latency_p90': 2.97819664478302}, {'batch_size': 5, 'throughput': 1.3634940787986316, 'latency_mean': 3.646839538812637, 'latency_p50': 3.64766788482666, 'latency_p90': 4.133780145645141}, {'batch_size': 6, 'throughput': 1.4221813958479232, 'latency_mean': 4.190485782623291, 'latency_p50': 4.1768879890441895, 'latency_p90': 4.698922491073608}, {'batch_size': 8, 'throughput': 1.490761712132738, 'latency_mean': 5.329201490879059, 'latency_p50': 5.3476632833480835, 'latency_p90': 5.995670580863953}, {'batch_size': 10, 'throughput': 1.5274535431582401, 'latency_mean': 6.5053834879398345, 'latency_p50': 6.561367750167847, 'latency_p90': 7.3303662776947025}]

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: cloudyu/ChaiML-Nemo-DPO-

model_name: cloudyu-chaiml-nemo-dpo-v4_v2

model_num_parameters: 12772070400.0

model_repo: cloudyu/ChaiML-Nemo-DPO-V4

model_size: 13B

num_battles: 15682

num_wins: 7656

ranking_group: single

status: inactive

submission_type: basic

throughput_3p7s: 1.38

timestamp: 2024-11-24T09:42:28+00:00

us_pacific_date: 2024-11-24

win_ratio: 0.48820303532712667

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-v4-v2-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: ║     _____            __           __                                ║
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: ║       /___/                                                         ║
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: ║  belonging to:                                                      ║
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: Downloaded to shared memory in 42.941s
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpth416m3c, device:0
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: quantized model in 36.297s
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V4 in 79.238s
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v4-v2
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v4-v2/config.json
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v4-v2/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v4-v2/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v4-v2/tokenizer.json
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v4-v2/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.35it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.99it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 47.80it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 48.34it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 51.33it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 49.07it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 49.62it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 52.38it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 50.08it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 37.58it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 37.87it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 42.65it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 43.51it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 44.27it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 49.68it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 46.60it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 43.48it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 49.73it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 44.19it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 43.08it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 48.30it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:04, 46.30it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:04, 45.32it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 35.37it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 35.40it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 34.75it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:04, 42.04it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 41.99it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 42.83it/s]
Loading 0:  48%|████▊     | 175/363 [00:03<00:03, 48.77it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:03, 46.98it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:03, 45.06it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 50.45it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 47.75it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 45.88it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 51.10it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:03, 47.40it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 37.75it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 36.77it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:03, 36.53it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 40.20it/s]
Loading 0:  67%|██████▋   | 243/363 [00:05<00:02, 41.59it/s]
Loading 0:  68%|██████▊   | 248/363 [00:05<00:03, 35.61it/s]
Loading 0:  70%|███████   | 255/363 [00:05<00:02, 43.06it/s]
Loading 0:  72%|███████▏  | 260/363 [00:05<00:02, 42.02it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 43.49it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 42.58it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 41.39it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 45.85it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 44.02it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 42.64it/s]
Loading 0:  82%|████████▏ | 299/363 [00:06<00:01, 42.69it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:24,  2.41it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:17,  3.13it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:12,  4.07it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.79it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  9.24it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 11.74it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.46it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 20.16it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 23.36it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 29.70it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 32.46it/s]
                                                            
Job cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer completed after 104.22s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v4-v2-mkmlizer
Pipeline stage MKMLizer completed in 104.82s
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-v4-v2
Waiting for inference service cloudyu-chaiml-nemo-dpo-v4-v2 to be ready
Inference service cloudyu-chaiml-nemo-dpo-v4-v2 ready after 120.4481143951416s
Pipeline stage MKMLDeployer completed in 121.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2062036991119385s
Received healthy response to inference request in 1.6853065490722656s
Received healthy response to inference request in 1.725999116897583s
Received healthy response to inference request in 1.6549708843231201s
Received healthy response to inference request in 1.7756738662719727s
5 requests
0 failed requests
5th percentile: 1.6610380172729493
10th percentile: 1.6671051502227783
20th percentile: 1.6792394161224364
30th percentile: 1.6934450626373292
40th percentile: 1.709722089767456
50th percentile: 1.725999116897583
60th percentile: 1.745869016647339
70th percentile: 1.7657389163970947
80th percentile: 1.861779832839966
90th percentile: 2.0339917659759523
95th percentile: 2.1200977325439454
99th percentile: 2.18898250579834
mean time: 1.809630823135376
Pipeline stage StressChecker completed in 10.73s
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 2.41s
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 2.43s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v4_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 0.12s
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-chaiml-nemo-dpo-v4-v2-profiler
Waiting for inference service cloudyu-chaiml-nemo-dpo-v4-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 2705.97s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v4_v2 status is now inactive due to auto deactivation removed underperforming models