cloudyu-nemo-dpo-v16

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v16_v7

model_name: cloudyu-nemo-dpo-v16_v1

model_group: cloudyu/Nemo-DPO-V16

status: inactive

timestamp: 2024-12-07T02:28:00+00:00

num_battles: 11789

num_wins: 6040

celo_rating: 1274.11

family_friendly_score: 0.5466

family_friendly_standard_error: 0.007040290334922275

submission_type: basic

model_repo: cloudyu/Nemo-DPO-V16

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6116606400427721, 'latency_mean': 1.6348363411426545, 'latency_p50': 1.6246204376220703, 'latency_p90': 1.8097162246704102}, {'batch_size': 3, 'throughput': 1.1036109886617373, 'latency_mean': 2.707248787879944, 'latency_p50': 2.7238996028900146, 'latency_p90': 2.97237651348114}, {'batch_size': 5, 'throughput': 1.328036109274657, 'latency_mean': 3.7557480692863465, 'latency_p50': 3.7494877576828003, 'latency_p90': 4.16509952545166}, {'batch_size': 6, 'throughput': 1.3924200922664751, 'latency_mean': 4.279556013345719, 'latency_p50': 4.311206698417664, 'latency_p90': 4.796412634849548}, {'batch_size': 8, 'throughput': 1.4853036097579704, 'latency_mean': 5.354783228635788, 'latency_p50': 5.357611179351807, 'latency_p90': 6.143912005424499}, {'batch_size': 10, 'throughput': 1.513119410639343, 'latency_mean': 6.570211764574051, 'latency_p50': 6.559880971908569, 'latency_p90': 7.4678069114685055}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-nemo-dpo-v16_v1

is_internal_developer: False

language_model: cloudyu/Nemo-DPO-V16

model_size: 13B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2024-12-06

win_ratio: 0.5123420137416236

generation_params: {'temperature': 1.2, '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-v16-v7-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v16-v7-mkmlizer to finish
cloudyu-nemo-dpo-v16-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v16-v7-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v16-v7-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v16-v7-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v16-v7-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v16-v7-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v16-v7-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v16-v7-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v16-v7-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v16-v7-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v16-v7-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v16-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v16-v7-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v16-v7-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v16-v7-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v16-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v16-v7-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v16-v7-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v16-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-nemo-dpo-v16-v7-mkmlizer: Downloaded to shared memory in 35.046s
cloudyu-nemo-dpo-v16-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphf4sg3aw, device:0
cloudyu-nemo-dpo-v16-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v16-v7-mkmlizer: quantized model in 36.139s
cloudyu-nemo-dpo-v16-v7-mkmlizer: Processed model cloudyu/Nemo-DPO-V16 in 71.186s
cloudyu-nemo-dpo-v16-v7-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v16-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v16-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v7
cloudyu-nemo-dpo-v16-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v7/config.json
cloudyu-nemo-dpo-v16-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v7/special_tokens_map.json
cloudyu-nemo-dpo-v16-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v7/tokenizer_config.json
cloudyu-nemo-dpo-v16-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v7/tokenizer.json
cloudyu-nemo-dpo-v16-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v16-v7/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v16-v7-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.26it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:09, 36.09it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:10, 33.82it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:07, 47.52it/s]
Loading 0:   8%|▊         | 28/363 [00:00<00:07, 45.75it/s]
Loading 0:   9%|▉         | 33/363 [00:00<00:07, 45.18it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:06, 50.44it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:07, 45.15it/s]
Loading 0:  14%|█▍        | 51/363 [00:01<00:07, 41.58it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 42.25it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.61it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 31.35it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 36.87it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 38.05it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 39.30it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 40.91it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 34.85it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 41.79it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 41.78it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 46.16it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 37.64it/s]
Loading 0:  33%|███▎      | 119/363 [00:03<00:06, 36.01it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 40.94it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 41.20it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 42.19it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 43.51it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 28.17it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.76it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 36.87it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 38.02it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 39.54it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 41.76it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 37.04it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 45.58it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:03, 44.71it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:03, 43.76it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:03, 48.56it/s]
Loading 0:  57%|█████▋    | 208/363 [00:05<00:03, 47.10it/s]
Loading 0:  59%|█████▊    | 213/363 [00:05<00:03, 46.45it/s]
Loading 0:  60%|██████    | 219/363 [00:05<00:02, 49.84it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:04, 32.37it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:03, 33.87it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:02, 42.22it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:02, 41.12it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:03, 37.77it/s]
Loading 0:  70%|██████▉   | 254/363 [00:06<00:02, 38.06it/s]
Loading 0:  71%|███████▏  | 259/363 [00:06<00:02, 37.07it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 41.66it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 41.20it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 40.73it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 46.02it/s]
Loading 0:  79%|███████▉  | 288/363 [00:07<00:01, 44.78it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:02, 34.07it/s]
Loading 0:  83%|████████▎ | 300/363 [00:07<00:01, 41.46it/s]
Loading 0:  84%|████████▍ | 305/363 [00:14<00:22,  2.61it/s]
Loading 0:  85%|████████▌ | 309/363 [00:14<00:16,  3.32it/s]
Loading 0:  86%|████████▌ | 313/363 [00:14<00:11,  4.28it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.69it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  9.18it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:02, 11.76it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 16.54it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 20.13it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 23.39it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 29.88it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 32.44it/s]
                                                            
Job cloudyu-nemo-dpo-v16-v7-mkmlizer completed after 94.22s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v16-v7-mkmlizer
Pipeline stage MKMLizer completed in 94.83s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-nemo-dpo-v16-v7
Waiting for inference service cloudyu-nemo-dpo-v16-v7 to be ready
Inference service cloudyu-nemo-dpo-v16-v7 ready after 180.64675617218018s
Pipeline stage MKMLDeployer completed in 181.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.353222370147705s
Received healthy response to inference request in 1.7588598728179932s
Received healthy response to inference request in 1.9695334434509277s
Received healthy response to inference request in 1.6624901294708252s
Received healthy response to inference request in 2.202677011489868s
5 requests
0 failed requests
5th percentile: 1.6817640781402587
10th percentile: 1.7010380268096923
20th percentile: 1.7395859241485596
30th percentile: 1.80099458694458
40th percentile: 1.885264015197754
50th percentile: 1.9695334434509277
60th percentile: 2.062790870666504
70th percentile: 2.15604829788208
80th percentile: 2.2327860832214355
90th percentile: 2.2930042266845705
95th percentile: 2.323113298416138
99th percentile: 2.3472005558013915
mean time: 1.989356565475464
Pipeline stage StressChecker completed in 11.32s
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 2.28s
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 2.49s
Shutdown handler de-registered
cloudyu-nemo-dpo-v16_v7 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-v16-v7-profiler
Waiting for inference service cloudyu-nemo-dpo-v16-v7-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 2683.40s
Shutdown handler de-registered
cloudyu-nemo-dpo-v16_v7 status is now inactive due to auto deactivation removed underperforming models