chaiml-mistral-nemo-dpo-_8035

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_8035_v1

model_name: chaiml-mistral-nemo-dpo-_8035_v1

model_group: ChaiML/mistral_nemo_dpo_

status: inactive

timestamp: 2024-12-12T08:49:43+00:00

num_battles: 7697

num_wins: 3864

celo_rating: 1263.25

family_friendly_score: 0.5746

family_friendly_standard_error: 0.006991921624274688

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_baseline_albert_241210_5k_v3

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6314044110806742, 'latency_mean': 1.583701730966568, 'latency_p50': 1.5972442626953125, 'latency_p90': 1.7300838947296142}, {'batch_size': 3, 'throughput': 1.2549630054804277, 'latency_mean': 2.3897122490406035, 'latency_p50': 2.3773072957992554, 'latency_p90': 2.6290609359741213}, {'batch_size': 5, 'throughput': 1.5862694391025558, 'latency_mean': 3.1391201996803284, 'latency_p50': 3.147382378578186, 'latency_p90': 3.547430157661438}, {'batch_size': 6, 'throughput': 1.7062935468688871, 'latency_mean': 3.4951254403591157, 'latency_p50': 3.494232654571533, 'latency_p90': 3.9684337854385374}, {'batch_size': 8, 'throughput': 1.8659521670382522, 'latency_mean': 4.26220175743103, 'latency_p50': 4.233704924583435, 'latency_p90': 4.844301724433899}, {'batch_size': 10, 'throughput': 1.9376816794282214, 'latency_mean': 5.125260103940963, 'latency_p50': 5.06558620929718, 'latency_p90': 5.906585669517517}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_8035_v1

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_baseline_albert_241210_5k_v3

model_size: 13B

ranking_group: single

throughput_3p7s: 1.77

us_pacific_date: 2024-12-12

win_ratio: 0.5020137715993244

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', '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 chaiml-mistral-nemo-dpo-8035-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-8035-v1-mkmlizer to finish
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: Downloaded to shared memory in 49.421s
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpq6k3ocw9, device:0
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: quantized model in 37.582s
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_baseline_albert_241210_5k_v3 in 87.003s
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8035-v1
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8035-v1/config.json
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8035-v1/special_tokens_map.json
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8035-v1/tokenizer_config.json
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8035-v1/tokenizer.json
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-8035-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-8035-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.41it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 44.16it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 42.20it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 41.91it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:07, 43.04it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 33.64it/s]
Loading 0:  11%|█         | 39/363 [00:00<00:07, 41.15it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:08, 39.70it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 40.97it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:07, 40.53it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 30.63it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 28.72it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 34.50it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 35.60it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:06, 40.77it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:06, 41.84it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:06, 41.93it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:05, 46.87it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:05, 44.25it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 44.47it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 36.08it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 33.33it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 40.07it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 39.22it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 40.22it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:05, 40.14it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 28.45it/s]
Loading 0:  41%|████▏     | 150/363 [00:04<00:07, 28.83it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:05, 35.70it/s]
Loading 0:  45%|████▍     | 162/363 [00:04<00:05, 37.13it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:06, 32.24it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 40.56it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 40.98it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 40.59it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:03, 45.50it/s]
Loading 0:  55%|█████▍    | 199/363 [00:05<00:03, 44.57it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:03, 43.47it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 47.90it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 45.78it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 34.40it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 33.92it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 31.17it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 35.81it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 34.56it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 35.87it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 35.70it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 38.86it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 39.02it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 39.74it/s]
Loading 0:  74%|███████▍  | 270/363 [00:07<00:02, 41.18it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 34.60it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:01, 42.59it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 42.84it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 42.76it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 43.35it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 44.09it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:24,  2.32it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:15,  3.20it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:08,  4.94it/s]
Loading 0:  89%|████████▉ | 324/363 [00:15<00:05,  6.52it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:03,  8.60it/s]
Loading 0:  92%|█████████▏| 335/363 [00:15<00:02, 11.53it/s]
Loading 0:  94%|█████████▎| 340/363 [00:15<00:01, 14.38it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 19.68it/s]
Loading 0:  97%|█████████▋| 352/363 [00:15<00:00, 23.43it/s]
Loading 0:  98%|█████████▊| 357/363 [00:16<00:00, 24.15it/s]
                                                            
Job chaiml-mistral-nemo-dpo-8035-v1-mkmlizer completed after 114.85s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-8035-v1-mkmlizer
Pipeline stage MKMLizer completed in 115.82s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-nemo-dpo-8035-v1
Waiting for inference service chaiml-mistral-nemo-dpo-8035-v1 to be ready
Inference service chaiml-mistral-nemo-dpo-8035-v1 ready after 181.53970170021057s
Pipeline stage MKMLDeployer completed in 182.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5450351238250732s
Received healthy response to inference request in 2.1580886840820312s
Received healthy response to inference request in 1.5396144390106201s
Received healthy response to inference request in 1.4032585620880127s
Received healthy response to inference request in 0.5409822463989258s
5 requests
0 failed requests
5th percentile: 0.7134375095367431
10th percentile: 0.8858927726745606
20th percentile: 1.2308032989501954
30th percentile: 1.430529737472534
40th percentile: 1.485072088241577
50th percentile: 1.5396144390106201
60th percentile: 1.7870041370391845
70th percentile: 2.034393835067749
80th percentile: 2.23547797203064
90th percentile: 2.3902565479278564
95th percentile: 2.4676458358764646
99th percentile: 2.5295572662353516
mean time: 1.6373958110809326
Pipeline stage StressChecker completed in 9.55s
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 2.27s
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 2.07s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_8035_v1 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 2340.67s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_8035_v1 status is now inactive due to auto deactivation removed underperforming models