developer_uid: cloudyu
submission_id: cloudyu-chaiml-nemo-dpo-v6_v12
model_name: cloudyu-chaiml-nemo-dpo-v6_v11
model_group: cloudyu/ChaiML-Nemo-DPO-
status: inactive
timestamp: 2024-12-03T02:41:02+00:00
num_battles: 12754
num_wins: 6520
celo_rating: 1267.09
family_friendly_score: 0.5608
family_friendly_standard_error: 0.007018594731140985
submission_type: basic
model_repo: cloudyu/ChaiML-Nemo-DPO-V6
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6162411554049746, 'latency_mean': 1.6226826155185698, 'latency_p50': 1.633551836013794, 'latency_p90': 1.8017825365066529}, {'batch_size': 3, 'throughput': 1.1478201391229037, 'latency_mean': 2.6100754749774935, 'latency_p50': 2.5887175798416138, 'latency_p90': 2.8580991983413697}, {'batch_size': 5, 'throughput': 1.373004753812058, 'latency_mean': 3.6307579255104065, 'latency_p50': 3.6663763523101807, 'latency_p90': 4.04755711555481}, {'batch_size': 6, 'throughput': 1.4407999860217493, 'latency_mean': 4.131124488115311, 'latency_p50': 4.1521148681640625, 'latency_p90': 4.63221652507782}, {'batch_size': 8, 'throughput': 1.5109953945287602, 'latency_mean': 5.252897309064865, 'latency_p50': 5.262063384056091, 'latency_p90': 5.918384528160095}, {'batch_size': 10, 'throughput': 1.549961188370292, 'latency_mean': 6.407828789949417, 'latency_p50': 6.45058012008667, 'latency_p90': 7.316335940361023}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cloudyu-chaiml-nemo-dpo-v6_v11
is_internal_developer: False
language_model: cloudyu/ChaiML-Nemo-DPO-V6
model_size: 13B
ranking_group: single
throughput_3p7s: 1.39
us_pacific_date: 2024-12-02
win_ratio: 0.5112121687313784
generation_params: {'temperature': 0.95, 'top_p': 0.95, 'min_p': 0.05, '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-v6-v12-mkmlizer
Waiting for job on cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer to finish
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: ║     _____            __           __                                ║
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: ║       /___/                                                         ║
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: ║  Version: 0.11.12                                                   ║
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: ║  https://mk1.ai                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: ║  The license key for the current software has been verified as      ║
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: ║  belonging to:                                                      ║
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: ║  Chai Research Corp.                                                ║
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: ║                                                                     ║
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: Downloaded to shared memory in 35.770s
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpy73u6eel, device:0
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: quantized model in 35.578s
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: Processed model cloudyu/ChaiML-Nemo-DPO-V6 in 71.348s
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: creating bucket guanaco-mkml-models
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v12
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v12/tokenizer_config.json
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v12/tokenizer.json
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cloudyu-chaiml-nemo-dpo-v6-v12/flywheel_model.0.safetensors
cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.15it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 51.38it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:06, 49.49it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 51.09it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 53.42it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 49.99it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 50.03it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:06, 52.01it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 47.97it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.65it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 35.54it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 39.80it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 39.83it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 40.26it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 46.09it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 43.75it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 43.59it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 49.96it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 46.45it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 44.41it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 49.31it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:05, 45.71it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:04, 45.37it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 35.93it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 35.79it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 33.77it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 40.68it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 40.47it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 40.71it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 46.66it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 44.35it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 42.94it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 47.64it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 46.41it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 44.77it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 49.68it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:03, 47.50it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:02, 48.08it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 33.82it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 32.64it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 38.10it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:03, 38.29it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 40.18it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 41.29it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 40.69it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 46.30it/s]
Loading 0:  74%|███████▍  | 270/363 [00:06<00:01, 47.16it/s]
Loading 0:  76%|███████▌  | 275/363 [00:06<00:02, 33.33it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 41.47it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 41.58it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 40.61it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 42.24it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:23,  2.52it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:16,  3.25it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:12,  4.24it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  7.05it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.51it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 12.02it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.88it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 20.72it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 24.18it/s]
Loading 0:  98%|█████████▊| 355/363 [00:14<00:00, 29.67it/s]
Loading 0:  99%|█████████▉| 361/363 [00:14<00:00, 33.64it/s]
                                                            

Job cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer completed after 104.5s with status: succeeded
Stopping job with name cloudyu-chaiml-nemo-dpo-v6-v12-mkmlizer
Pipeline stage MKMLizer completed in 105.01s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v6-v12
Waiting for inference service cloudyu-chaiml-nemo-dpo-v6-v12 to be ready
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
Inference service cloudyu-chaiml-nemo-dpo-v6-v12 ready after 140.5193350315094s
Pipeline stage MKMLDeployer completed in 141.04s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0458831787109375s
Received healthy response to inference request in 1.817664384841919s
Received healthy response to inference request in 1.828547477722168s
Received healthy response to inference request in 1.8093013763427734s
Received healthy response to inference request in 1.763551950454712s
5 requests
0 failed requests
5th percentile: 1.7727018356323243
10th percentile: 1.7818517208099365
20th percentile: 1.800151491165161
30th percentile: 1.8109739780426026
40th percentile: 1.8143191814422608
50th percentile: 1.817664384841919
60th percentile: 1.8220176219940185
70th percentile: 1.826370859146118
80th percentile: 1.872014617919922
90th percentile: 1.9589488983154297
95th percentile: 2.0024160385131835
99th percentile: 2.0371897506713865
mean time: 1.852989673614502
Pipeline stage StressChecker completed in 10.67s
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 2.69s
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 2.06s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v6_v12 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cloudyu-chaiml-nemo-dpo-v6-v12-profiler
Waiting for inference service cloudyu-chaiml-nemo-dpo-v6-v12-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 3150.74s
Shutdown handler de-registered
cloudyu-chaiml-nemo-dpo-v6_v12 status is now inactive due to auto deactivation removed underperforming models