chaiml-mistral-nemo-dpo-_5165

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_5165_v3

model_name: chaiml-mistral-nemo-dpo-_5165_v3

model_group: ChaiML/mistral_nemo_dpo_

status: inactive

timestamp: 2024-12-19T17:36:30+00:00

num_battles: 16923

num_wins: 8407

celo_rating: 1261.37

family_friendly_score: 0.5764

family_friendly_standard_error: 0.006988033199692171

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-4680

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6370696739182117, 'latency_mean': 1.5696264708042145, 'latency_p50': 1.5719548463821411, 'latency_p90': 1.7202823638916016}, {'batch_size': 3, 'throughput': 1.266255445951003, 'latency_mean': 2.367388417720795, 'latency_p50': 2.377028226852417, 'latency_p90': 2.576264190673828}, {'batch_size': 5, 'throughput': 1.6092568364401914, 'latency_mean': 3.0885044157505037, 'latency_p50': 3.110264778137207, 'latency_p90': 3.417519974708557}, {'batch_size': 6, 'throughput': 1.7207857960453945, 'latency_mean': 3.471217395067215, 'latency_p50': 3.46894633769989, 'latency_p90': 3.9356131553649902}, {'batch_size': 8, 'throughput': 1.8788562420339738, 'latency_mean': 4.2381870603561405, 'latency_p50': 4.271433234214783, 'latency_p90': 4.7467827796936035}, {'batch_size': 10, 'throughput': 1.961820643687646, 'latency_mean': 5.0619616234302525, 'latency_p50': 5.080780386924744, 'latency_p90': 5.695910143852234}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_5165_v3

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-4680

model_size: 13B

ranking_group: single

throughput_3p7s: 1.78

us_pacific_date: 2024-12-19

win_ratio: 0.49677953081604914

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-5165-v3-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-5165-v3-mkmlizer to finish
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: Downloaded to shared memory in 33.243s
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpa41v0u2m, device:0
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: quantized model in 35.746s
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-4680 in 68.989s
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5165-v3
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5165-v3/config.json
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5165-v3/special_tokens_map.json
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5165-v3/tokenizer_config.json
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5165-v3/tokenizer.json
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-5165-v3/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-5165-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 27.16it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.22it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 47.09it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 48.52it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 51.66it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 48.26it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 44.01it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:06, 46.46it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:06, 45.59it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 46.44it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 30.93it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 37.64it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 38.32it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:07, 39.35it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 45.47it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 44.91it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 44.38it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:04, 52.49it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 48.17it/s]
Loading 0:  33%|███▎      | 121/363 [00:02<00:05, 47.62it/s]
Loading 0:  35%|███▍      | 127/363 [00:02<00:05, 43.79it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:04, 50.86it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:04, 49.38it/s]
Loading 0:  40%|████      | 147/363 [00:03<00:06, 33.86it/s]
Loading 0:  42%|████▏     | 152/363 [00:03<00:05, 35.46it/s]
Loading 0:  44%|████▎     | 158/363 [00:03<00:05, 35.51it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 43.66it/s]
Loading 0:  47%|████▋     | 172/363 [00:03<00:04, 43.69it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 44.30it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 49.25it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:03, 48.22it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:03, 45.96it/s]
Loading 0:  55%|█████▌    | 201/363 [00:04<00:03, 46.73it/s]
Loading 0:  57%|█████▋    | 206/363 [00:04<00:03, 44.27it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 45.30it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:03, 45.06it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 36.45it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 36.85it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 35.77it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:02, 43.08it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 43.66it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 42.12it/s]
Loading 0:  71%|███████   | 256/363 [00:05<00:02, 46.83it/s]
Loading 0:  72%|███████▏  | 261/363 [00:06<00:02, 47.58it/s]
Loading 0:  73%|███████▎  | 266/363 [00:06<00:02, 41.28it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:01, 48.08it/s]
Loading 0:  77%|███████▋  | 279/363 [00:06<00:01, 49.93it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 45.93it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 50.44it/s]
Loading 0:  82%|████████▏ | 298/363 [00:06<00:01, 46.25it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:20,  2.88it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:15,  3.59it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:11,  4.55it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:05,  7.33it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.75it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 12.24it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 16.94it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 20.43it/s]
Loading 0:  96%|█████████▌| 348/363 [00:14<00:00, 22.28it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 30.02it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 30.22it/s]
                                                            
Job chaiml-mistral-nemo-dpo-5165-v3-mkmlizer completed after 94.83s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-5165-v3-mkmlizer
Pipeline stage MKMLizer completed in 95.34s
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 chaiml-mistral-nemo-dpo-5165-v3
Waiting for inference service chaiml-mistral-nemo-dpo-5165-v3 to be ready
Inference service chaiml-mistral-nemo-dpo-5165-v3 ready after 240.9812581539154s
Pipeline stage MKMLDeployer completed in 241.57s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.922271490097046s
Received healthy response to inference request in 1.7417042255401611s
Received healthy response to inference request in 1.431567907333374s
Received healthy response to inference request in 0.6308145523071289s
Received healthy response to inference request in 1.3394582271575928s
5 requests
0 failed requests
5th percentile: 0.7725432872772217
10th percentile: 0.9142720222473144
20th percentile: 1.1977294921875
30th percentile: 1.357880163192749
40th percentile: 1.3947240352630614
50th percentile: 1.431567907333374
60th percentile: 1.555622434616089
70th percentile: 1.6796769618988037
80th percentile: 1.777817678451538
90th percentile: 1.850044584274292
95th percentile: 1.886158037185669
99th percentile: 1.9150487995147705
mean time: 1.4131632804870606
Pipeline stage StressChecker completed in 8.37s
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 2.43s
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 2.24s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_5165_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 3196.61s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_5165_v3 status is now inactive due to auto deactivation removed underperforming models