developer_uid: cloudyu
submission_id: cloudyu-chaiml-nemo-dpo-v8_v3
model_name: cloudyu-chaiml-nemo-dpo-v8_v3
model_group: cloudyu/ChaiML-Nemo-DPO-
status: inactive
timestamp: 2024-12-03T12:20:05+00:00
num_battles: 17438
num_wins: 8884
celo_rating: 1270.82
family_friendly_score: 0.5558000000000001
family_friendly_standard_error: 0.0070268963276826565
submission_type: basic
model_repo: cloudyu/ChaiML-Nemo-DPO-V8
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6165086022582642, 'latency_mean': 1.6219786751270293, 'latency_p50': 1.626747488975525, 'latency_p90': 1.7782549142837525}, {'batch_size': 3, 'throughput': 1.130193958335601, 'latency_mean': 2.6452382683753966, 'latency_p50': 2.6593971252441406, 'latency_p90': 2.91169102191925}, {'batch_size': 5, 'throughput': 1.3731682258054365, 'latency_mean': 3.6297286534309388, 'latency_p50': 3.6120314598083496, 'latency_p90': 4.014313745498657}, {'batch_size': 6, 'throughput': 1.4319637363612416, 'latency_mean': 4.166610089540481, 'latency_p50': 4.192255020141602, 'latency_p90': 4.68114697933197}, {'batch_size': 8, 'throughput': 1.5016345319074829, 'latency_mean': 5.286456362009049, 'latency_p50': 5.334499359130859, 'latency_p90': 5.9817441463470455}, {'batch_size': 10, 'throughput': 1.54910571897778, 'latency_mean': 6.420510618686676, 'latency_p50': 6.435399055480957, 'latency_p90': 7.2766292810440065}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-chaiml-nemo-dpo-v8_v3
is_internal_developer: False
language_model: cloudyu/ChaiML-Nemo-DPO-V8
model_size: 13B
ranking_group: single
throughput_3p7s: 1.39
us_pacific_date: 2024-12-03
win_ratio: 0.5094620942768666
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-chaiml-nemo-dpo-v8-v3-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: ║     _____            __           __                                ║
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: ║       /___/                                                         ║
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: ║  belonging to:                                                      ║
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: Downloaded to shared memory in 47.785s
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_267q66l, device:0
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: quantized model in 36.160s
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V8 in 83.945s
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v8-v3
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v8-v3/special_tokens_map.json
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v8-v3/config.json
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v8-v3/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v8-v3/tokenizer.json
cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:29,  3.07s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:56,  1.20it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:45,  3.31it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:11,  4.84it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:43,  7.90it/s]
Loading 0:   8%|▊         | 28/363 [00:06<00:30, 10.97it/s]
Loading 0:   9%|▉         | 33/363 [00:06<00:24, 13.73it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:19, 16.84it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 19.25it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 24.71it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:10, 28.12it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:09, 30.47it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:08, 35.86it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:07, 37.54it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:07, 39.57it/s]
Loading 0:  23%|██▎       | 82/363 [00:08<00:06, 42.07it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:07, 36.17it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:06, 44.36it/s]
Loading 0:  28%|██▊       | 101/363 [00:08<00:06, 42.20it/s]
Loading 0:  29%|██▉       | 106/363 [00:08<00:06, 40.54it/s]
Loading 0:  31%|███       | 112/363 [00:08<00:05, 44.79it/s]
Loading 0:  32%|███▏      | 117/363 [00:08<00:05, 43.82it/s]
Loading 0:  34%|███▎      | 122/363 [00:09<00:07, 30.95it/s]
Loading 0:  35%|███▍      | 126/363 [00:09<00:07, 32.70it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 36.24it/s]
Loading 0:  38%|███▊      | 137/363 [00:09<00:06, 37.26it/s]
Loading 0:  39%|███▉      | 142/363 [00:09<00:05, 37.71it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:05, 43.00it/s]
Loading 0:  42%|████▏     | 153/363 [00:09<00:04, 42.80it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:04, 42.65it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:04, 43.74it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:05, 36.97it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:04, 44.50it/s]
Loading 0:  50%|████▉     | 180/363 [00:10<00:04, 44.28it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:03, 44.78it/s]
Loading 0:  52%|█████▏    | 190/363 [00:10<00:03, 46.11it/s]
Loading 0:  54%|█████▎    | 195/363 [00:10<00:04, 39.31it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:04, 33.01it/s]
Loading 0:  57%|█████▋    | 206/363 [00:11<00:04, 33.73it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:03, 38.80it/s]
Loading 0:  60%|██████    | 218/363 [00:11<00:03, 40.02it/s]
Loading 0:  61%|██████▏   | 223/363 [00:11<00:03, 38.52it/s]
Loading 0:  63%|██████▎   | 230/363 [00:11<00:03, 44.30it/s]
Loading 0:  65%|██████▌   | 236/363 [00:12<00:02, 43.81it/s]
Loading 0:  66%|██████▋   | 241/363 [00:12<00:02, 42.85it/s]
Loading 0:  68%|██████▊   | 247/363 [00:12<00:02, 46.90it/s]
Loading 0:  69%|██████▉   | 252/363 [00:12<00:02, 47.11it/s]
Loading 0:  71%|███████   | 258/363 [00:12<00:02, 43.12it/s]
Loading 0:  73%|███████▎  | 266/363 [00:12<00:01, 50.20it/s]
Loading 0:  75%|███████▍  | 272/363 [00:12<00:01, 46.76it/s]
Loading 0:  76%|███████▋  | 277/363 [00:12<00:01, 45.99it/s]
Loading 0:  78%|███████▊  | 283/363 [00:13<00:02, 35.42it/s]
Loading 0:  79%|███████▉  | 287/363 [00:13<00:02, 35.44it/s]
Loading 0:  81%|████████  | 293/363 [00:13<00:01, 40.08it/s]
Loading 0:  82%|████████▏ | 299/363 [00:13<00:01, 40.95it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:01, 41.61it/s]
Loading 0:  85%|████████▌ | 310/363 [00:13<00:01, 45.12it/s]
Loading 0:  87%|████████▋ | 315/363 [00:13<00:01, 43.02it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:00, 43.86it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:00, 41.93it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:00, 41.14it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 46.11it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 44.99it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 43.25it/s]
Loading 0:  98%|█████████▊| 355/363 [00:14<00:00, 47.39it/s]
Loading 0:  99%|█████████▉| 360/363 [00:14<00:00, 44.41it/s]
                                                            

Job cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer completed after 114.27s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v8-v3-mkmlizer
Pipeline stage MKMLizer completed in 114.77s
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-v8-v3
Waiting for inference service cloudyu-chaiml-nemo-dpo-v8-v3 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cloudyu-chaiml-nemo-dpo-v8-v3 ready after 150.54528641700745s
Pipeline stage MKMLDeployer completed in 151.07s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.145747423171997s
Received healthy response to inference request in 1.642329454421997s
Received healthy response to inference request in 1.7470767498016357s
Received healthy response to inference request in 1.6524052619934082s
Received healthy response to inference request in 2.0432732105255127s
5 requests
0 failed requests
5th percentile: 1.6443446159362793
10th percentile: 1.6463597774505616
20th percentile: 1.650390100479126
30th percentile: 1.6713395595550538
40th percentile: 1.7092081546783446
50th percentile: 1.7470767498016357
60th percentile: 1.8655553340911866
70th percentile: 1.9840339183807372
80th percentile: 2.0637680530548095
90th percentile: 2.1047577381134035
95th percentile: 2.1252525806427003
99th percentile: 2.1416484546661376
mean time: 1.8461664199829102
Pipeline stage StressChecker completed in 10.97s
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 2.10s
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 2.03s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v8_v3 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 3169.43s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v8_v3 status is now inactive due to auto deactivation removed underperforming models