chaiml-mistral-nemo-simp_1866

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-simp_1866_v1

model_name: chaiml-mistral-nemo-simp_1866_v1

model_group: ChaiML/mistral_nemo_simp

status: inactive

timestamp: 2024-12-18T19:02:01+00:00

num_battles: 17439

num_wins: 8132

celo_rating: 1234.54

family_friendly_score: 0.5906

family_friendly_standard_error: 0.006954015243008891

submission_type: basic

model_repo: ChaiML/mistral_nemo_simpo_baseline_albert_20241217_v1-checkpoint-125

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6311760592992585, 'latency_mean': 1.5842874121665955, 'latency_p50': 1.570407748222351, 'latency_p90': 1.7537912607192994}, {'batch_size': 3, 'throughput': 1.2262966351748215, 'latency_mean': 2.437671629190445, 'latency_p50': 2.441817879676819, 'latency_p90': 2.732010507583618}, {'batch_size': 5, 'throughput': 1.5450777134982439, 'latency_mean': 3.2223865282535553, 'latency_p50': 3.189793586730957, 'latency_p90': 3.626115274429321}, {'batch_size': 6, 'throughput': 1.6447125610009241, 'latency_mean': 3.6308539080619813, 'latency_p50': 3.6126787662506104, 'latency_p90': 4.110178923606872}, {'batch_size': 8, 'throughput': 1.7851549717694308, 'latency_mean': 4.4444322681427, 'latency_p50': 4.465616345405579, 'latency_p90': 4.908846735954285}, {'batch_size': 10, 'throughput': 1.8652084100589652, 'latency_mean': 5.332782416343689, 'latency_p50': 5.326969027519226, 'latency_p90': 6.131725287437439}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-simp_1866_v1

is_internal_developer: True

language_model: ChaiML/mistral_nemo_simpo_baseline_albert_20241217_v1-checkpoint-125

model_size: 13B

ranking_group: single

throughput_3p7s: 1.67

us_pacific_date: 2024-12-18

win_ratio: 0.4663111416939045

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-simp-1866-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-simp-1866-v1-mkmlizer to finish
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
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: Downloaded to shared memory in 46.435s
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsnvqpmqa, device:0
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: quantized model in 35.687s
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: Processed model ChaiML/mistral_nemo_simpo_baseline_albert_20241217_v1-checkpoint-125 in 82.122s
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-1866-v1
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-1866-v1/tokenizer_config.json
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-1866-v1/tokenizer.json
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-1866-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-simp-1866-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.76it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 46.69it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.49it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 42.08it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 48.43it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 45.82it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 44.04it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 49.55it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 46.05it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.72it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 32.41it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 39.44it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 41.32it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:06, 41.76it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 47.95it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 47.17it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 43.03it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:04, 51.79it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 48.76it/s]
Loading 0:  33%|███▎      | 121/363 [00:02<00:05, 46.89it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:05, 47.32it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:05, 44.65it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 42.66it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 33.00it/s]
Loading 0:  40%|████      | 147/363 [00:03<00:06, 34.47it/s]
Loading 0:  42%|████▏     | 152/363 [00:03<00:05, 37.49it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:05, 40.41it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 42.13it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 41.78it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:03, 47.46it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:03, 45.76it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:03, 44.96it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 50.28it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 48.63it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 47.16it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 51.77it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:03, 47.56it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 36.28it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 36.24it/s]
Loading 0:  64%|██████▍   | 232/363 [00:05<00:03, 34.30it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 38.44it/s]
Loading 0:  67%|██████▋   | 244/363 [00:05<00:02, 40.10it/s]
Loading 0:  69%|██████▊   | 249/363 [00:05<00:02, 40.86it/s]
Loading 0:  71%|███████   | 256/363 [00:05<00:02, 46.29it/s]
Loading 0:  72%|███████▏  | 262/363 [00:06<00:02, 43.56it/s]
Loading 0:  74%|███████▎  | 267/363 [00:06<00:02, 41.87it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:01, 46.08it/s]
Loading 0:  77%|███████▋  | 278/363 [00:06<00:01, 46.87it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 45.92it/s]
Loading 0:  80%|███████▉  | 289/363 [00:06<00:01, 44.08it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 43.22it/s]
Loading 0:  83%|████████▎ | 302/363 [00:06<00:01, 52.17it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:19,  2.85it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:14,  3.57it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.64it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:04,  7.58it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.56it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.44it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 16.82it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 19.78it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 25.65it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 27.86it/s]
                                                            
Job chaiml-mistral-nemo-simp-1866-v1-mkmlizer completed after 104.92s with status: succeeded
Stopping job with name chaiml-mistral-nemo-simp-1866-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.45s
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 chaiml-mistral-nemo-simp-1866-v1
Waiting for inference service chaiml-mistral-nemo-simp-1866-v1 to be ready
Inference service chaiml-mistral-nemo-simp-1866-v1 ready after 240.98190999031067s
Pipeline stage MKMLDeployer completed in 241.56s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7376933097839355s
Received healthy response to inference request in 1.568422794342041s
Received healthy response to inference request in 0.9576714038848877s
Received healthy response to inference request in 0.9695343971252441s
Received healthy response to inference request in 0.8172311782836914s
5 requests
0 failed requests
5th percentile: 0.8453192234039306
10th percentile: 0.8734072685241699
20th percentile: 0.9295833587646485
30th percentile: 0.960044002532959
40th percentile: 0.9647891998291016
50th percentile: 0.9695343971252441
60th percentile: 1.209089756011963
70th percentile: 1.4486451148986816
80th percentile: 1.60227689743042
90th percentile: 1.6699851036071778
95th percentile: 1.7038392066955566
99th percentile: 1.7309224891662598
mean time: 1.21011061668396
Pipeline stage StressChecker completed in 7.44s
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 2.54s
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 2.33s
Shutdown handler de-registered
chaiml-mistral-nemo-simp_1866_v1 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral-nemo-simp-1866-v1-profiler
Waiting for inference service chaiml-mistral-nemo-simp-1866-v1-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 2847.81s
Shutdown handler de-registered
chaiml-mistral-nemo-simp_1866_v1 status is now inactive due to auto deactivation removed underperforming models