cloudyu-nemo-dpo-v22

developer_uid: cloudyu

submission_id: cloudyu-nemo-dpo-v22_v6

model_name: cloudyu-nemo-dpo-v22_v1

model_group: cloudyu/Nemo-DPO-V22

status: inactive

timestamp: 2024-12-18T15:18:27+00:00

num_battles: 15954

num_wins: 8480

celo_rating: 1282.77

family_friendly_score: 0.5648

family_friendly_standard_error: 0.007011432949119602

submission_type: basic

model_repo: cloudyu/Nemo-DPO-V22

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6127308638329929, 'latency_mean': 1.631970052719116, 'latency_p50': 1.6441903114318848, 'latency_p90': 1.802332615852356}, {'batch_size': 3, 'throughput': 1.1450811912856633, 'latency_mean': 2.6137441301345827, 'latency_p50': 2.6076126098632812, 'latency_p90': 2.9091959953308106}, {'batch_size': 5, 'throughput': 1.366801986984009, 'latency_mean': 3.6425125396251676, 'latency_p50': 3.659770131111145, 'latency_p90': 4.032335567474365}, {'batch_size': 6, 'throughput': 1.4542373805445445, 'latency_mean': 4.110252357721329, 'latency_p50': 4.123161673545837, 'latency_p90': 4.551632142066955}, {'batch_size': 8, 'throughput': 1.5153337198334444, 'latency_mean': 5.25178246974945, 'latency_p50': 5.208604216575623, 'latency_p90': 5.9239026546478275}, {'batch_size': 10, 'throughput': 1.567452378500489, 'latency_mean': 6.327618579864502, 'latency_p50': 6.336181640625, 'latency_p90': 7.1544983863830565}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cloudyu-nemo-dpo-v22_v1

is_internal_developer: False

language_model: cloudyu/Nemo-DPO-V22

model_size: 13B

ranking_group: single

throughput_3p7s: 1.38

us_pacific_date: 2024-12-18

win_ratio: 0.5315281434123104

generation_params: {'temperature': 1.25, '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-v22-v6-mkmlizer
Waiting for job on cloudyu-nemo-dpo-v22-v6-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
cloudyu-nemo-dpo-v22-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-nemo-dpo-v22-v6-mkmlizer: ║     _____            __           __                                ║
cloudyu-nemo-dpo-v22-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-nemo-dpo-v22-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-nemo-dpo-v22-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-nemo-dpo-v22-v6-mkmlizer: ║       /___/                                                         ║
cloudyu-nemo-dpo-v22-v6-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v6-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-nemo-dpo-v22-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-nemo-dpo-v22-v6-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-nemo-dpo-v22-v6-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-nemo-dpo-v22-v6-mkmlizer: ║  belonging to:                                                      ║
cloudyu-nemo-dpo-v22-v6-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v6-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-nemo-dpo-v22-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-nemo-dpo-v22-v6-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-nemo-dpo-v22-v6-mkmlizer: ║                                                                     ║
cloudyu-nemo-dpo-v22-v6-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
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
Connection pool is full, discarding connection: %s. Connection pool size: %s
cloudyu-nemo-dpo-v22-v6-mkmlizer: Downloaded to shared memory in 49.453s
cloudyu-nemo-dpo-v22-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7jocg3ww, device:0
cloudyu-nemo-dpo-v22-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-nemo-dpo-v22-v6-mkmlizer: quantized model in 36.245s
cloudyu-nemo-dpo-v22-v6-mkmlizer: Processed model cloudyu/Nemo-DPO-V22 in 85.698s
cloudyu-nemo-dpo-v22-v6-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-nemo-dpo-v22-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-nemo-dpo-v22-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v6
cloudyu-nemo-dpo-v22-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v6/config.json
cloudyu-nemo-dpo-v22-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v6/special_tokens_map.json
cloudyu-nemo-dpo-v22-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-nemo-dpo-v22-v6/flywheel_model.0.safetensors
cloudyu-nemo-dpo-v22-v6-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.71it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 47.07it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 45.85it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 36.47it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 46.17it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 43.21it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 42.59it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 47.66it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:06, 48.21it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 44.37it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 29.18it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 34.79it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 36.65it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 39.18it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:07, 38.62it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:06, 38.93it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 43.41it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 43.15it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 47.07it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 39.27it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:06, 39.38it/s]
Loading 0:  35%|███▍      | 126/363 [00:03<00:05, 45.07it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:05, 43.25it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 43.04it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:07, 31.19it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 32.03it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 31.85it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 38.68it/s]
Loading 0:  45%|████▍     | 162/363 [00:04<00:04, 41.25it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:05, 35.72it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:04, 43.30it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 43.18it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:04, 42.90it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:04, 40.92it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:04, 39.33it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:03, 42.49it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:03, 41.71it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 43.07it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 41.74it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:03, 42.50it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 30.98it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 31.27it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:03, 38.20it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 38.52it/s]
Loading 0:  69%|██████▊   | 249/363 [00:06<00:02, 38.38it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 42.54it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 41.03it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 41.63it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 40.83it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 40.78it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:01, 44.78it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 43.34it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 42.00it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 43.57it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 45.27it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:23,  2.36it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:15,  3.27it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:08,  5.32it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:05,  6.96it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:03,  8.75it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 13.18it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:01, 16.15it/s]
Loading 0:  96%|█████████▌| 348/363 [00:15<00:00, 17.81it/s]
Loading 0:  98%|█████████▊| 355/363 [00:15<00:00, 23.97it/s]
Loading 0:  99%|█████████▉| 360/363 [00:15<00:00, 27.30it/s]
                                                            
Job cloudyu-nemo-dpo-v22-v6-mkmlizer completed after 115.66s with status: succeeded
Stopping job with name cloudyu-nemo-dpo-v22-v6-mkmlizer
Pipeline stage MKMLizer completed in 116.18s
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-v22-v6
Waiting for inference service cloudyu-nemo-dpo-v22-v6 to be ready
Inference service cloudyu-nemo-dpo-v22-v6 ready after 241.2701132297516s
Pipeline stage MKMLDeployer completed in 241.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2216174602508545s
Received healthy response to inference request in 1.9301354885101318s
Received healthy response to inference request in 1.645348072052002s
Received healthy response to inference request in 1.6442794799804688s
Received healthy response to inference request in 1.9896111488342285s
5 requests
0 failed requests
5th percentile: 1.6444931983947755
10th percentile: 1.644706916809082
20th percentile: 1.6451343536376952
30th percentile: 1.702305555343628
40th percentile: 1.8162205219268799
50th percentile: 1.9301354885101318
60th percentile: 1.9539257526397704
70th percentile: 1.9777160167694092
80th percentile: 2.0360124111175537
90th percentile: 2.128814935684204
95th percentile: 2.1752161979675293
99th percentile: 2.2123372077941896
mean time: 1.8861983299255372
Pipeline stage StressChecker completed in 10.82s
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 2.41s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v6 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 3335.81s
Shutdown handler de-registered
cloudyu-nemo-dpo-v22_v6 status is now inactive due to auto deactivation removed underperforming models