chaiml-mistral-nemo-dpo-_2408

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-dpo-_2408_v4

model_name: chaiml-mistral-nemo-dpo-_2408_v4

model_group: ChaiML/mistral_nemo_dpo_

status: inactive

timestamp: 2024-12-19T18:48:52+00:00

num_battles: 179150

num_wins: 95851

celo_rating: 1274.46

family_friendly_score: 0.5776

family_friendly_standard_error: 0.006985388178190243

submission_type: basic

model_repo: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-6240

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.614430507164715, 'latency_mean': 1.627438327074051, 'latency_p50': 1.6219648122787476, 'latency_p90': 1.796909713745117}, {'batch_size': 3, 'throughput': 1.139590771667777, 'latency_mean': 2.627093507051468, 'latency_p50': 2.6402465105056763, 'latency_p90': 2.872571015357971}, {'batch_size': 5, 'throughput': 1.3970082372530535, 'latency_mean': 3.567156809568405, 'latency_p50': 3.5703800916671753, 'latency_p90': 4.059770011901856}, {'batch_size': 6, 'throughput': 1.4449061493304722, 'latency_mean': 4.134009790420532, 'latency_p50': 4.130888938903809, 'latency_p90': 4.598968815803528}, {'batch_size': 8, 'throughput': 1.534233893959036, 'latency_mean': 5.182193729877472, 'latency_p50': 5.152330040931702, 'latency_p90': 5.747220468521118}, {'batch_size': 10, 'throughput': 1.5733692590202166, 'latency_mean': 6.314811191558838, 'latency_p50': 6.294515013694763, 'latency_p90': 7.124659872055053}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-dpo-_2408_v4

is_internal_developer: True

language_model: ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-6240

model_size: 13B

ranking_group: single

throughput_3p7s: 1.41

us_pacific_date: 2024-12-19

win_ratio: 0.5350320960089311

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': 8, '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-2408-v4-mkmlizer
Waiting for job on chaiml-mistral-nemo-dpo-2408-v4-mkmlizer to finish
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: Downloaded to shared memory in 50.495s
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2qub8cdq, device:0
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: quantized model in 36.406s
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: Processed model ChaiML/mistral_nemo_dpo_241217_albert_v1-checkpoint-6240 in 86.901s
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2408-v4
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2408-v4/config.json
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2408-v4/special_tokens_map.json
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2408-v4/tokenizer_config.json
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2408-v4/tokenizer.json
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-dpo-2408-v4/flywheel_model.0.safetensors
chaiml-mistral-nemo-dpo-2408-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.53it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 45.85it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:08, 42.59it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 40.09it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 46.31it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 43.43it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:07, 40.44it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:07, 43.35it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:07, 42.17it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:06, 45.96it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:11, 26.09it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 33.30it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 34.95it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 37.34it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 40.06it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 35.11it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 42.71it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 42.63it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 46.58it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:06, 40.35it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:06, 38.70it/s]
Loading 0:  35%|███▍      | 126/363 [00:03<00:05, 42.26it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:05, 41.34it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 41.59it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 32.54it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 32.36it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 31.46it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:05, 38.12it/s]
Loading 0:  45%|████▍     | 162/363 [00:04<00:05, 39.55it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:05, 34.77it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 43.73it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 41.85it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:04, 40.43it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 45.87it/s]
Loading 0:  55%|█████▍    | 199/363 [00:05<00:03, 44.25it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:03, 42.68it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 47.87it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 45.54it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:03, 44.76it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 31.32it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 30.65it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:03, 37.02it/s]
Loading 0:  67%|██████▋   | 243/363 [00:06<00:03, 39.10it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 33.51it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 40.15it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 40.83it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 41.17it/s]
Loading 0:  74%|███████▍  | 270/363 [00:06<00:02, 42.93it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 36.06it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 44.13it/s]
Loading 0:  79%|███████▉  | 288/363 [00:07<00:01, 45.42it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:01, 37.67it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 42.40it/s]
Loading 0:  84%|████████▎ | 304/363 [00:14<00:23,  2.54it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:16,  3.26it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:12,  4.23it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:06,  6.99it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.41it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:02, 11.90it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 16.72it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 20.11it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 23.44it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 30.02it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 32.79it/s]
                                                            
Job chaiml-mistral-nemo-dpo-2408-v4-mkmlizer completed after 115.74s with status: succeeded
Stopping job with name chaiml-mistral-nemo-dpo-2408-v4-mkmlizer
Pipeline stage MKMLizer completed in 116.23s
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 chaiml-mistral-nemo-dpo-2408-v4
Waiting for inference service chaiml-mistral-nemo-dpo-2408-v4 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 chaiml-mistral-nemo-dpo-2408-v4 ready after 251.58752417564392s
Pipeline stage MKMLDeployer completed in 252.18s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.317694664001465s
Received healthy response to inference request in 1.0592114925384521s
Received healthy response to inference request in 1.5507760047912598s
Received healthy response to inference request in 1.5797090530395508s
Received healthy response to inference request in 1.5298058986663818s
5 requests
0 failed requests
5th percentile: 1.1533303737640381
10th percentile: 1.2474492549896241
20th percentile: 1.4356870174407959
30th percentile: 1.5339999198913574
40th percentile: 1.5423879623413086
50th percentile: 1.5507760047912598
60th percentile: 1.562349224090576
70th percentile: 1.5739224433898926
80th percentile: 1.7273061752319336
90th percentile: 2.022500419616699
95th percentile: 2.1700975418090818
99th percentile: 2.2881752395629884
mean time: 1.6074394226074218
Pipeline stage StressChecker completed in 9.38s
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 2.11s
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 2.08s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_2408_v4 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-dpo-2408-v4-profiler
Waiting for inference service chaiml-mistral-nemo-dpo-2408-v4-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 7293.65s
Shutdown handler de-registered
chaiml-mistral-nemo-dpo-_2408_v4 status is now inactive due to auto deactivation removed underperforming models