chaiml-mistral-nemo-simp_4360

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-simp_4360_v1

model_name: chaiml-mistral-nemo-simp_4360_v1

model_group: ChaiML/mistral_nemo_simp

status: inactive

timestamp: 2024-12-18T21:34:43+00:00

num_battles: 16002

num_wins: 7266

celo_rating: 1235.68

family_friendly_score: 0.5912

family_friendly_standard_error: 0.006952446475881709

submission_type: basic

model_repo: ChaiML/mistral_nemo_simpo_baseline_albert_20241217_v1-checkpoint-625

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6270249089582168, 'latency_mean': 1.5947467124462127, 'latency_p50': 1.5991718769073486, 'latency_p90': 1.764720869064331}, {'batch_size': 3, 'throughput': 1.2461044899880087, 'latency_mean': 2.403913267850876, 'latency_p50': 2.4086519479751587, 'latency_p90': 2.670658493041992}, {'batch_size': 5, 'throughput': 1.5594791232409484, 'latency_mean': 3.1898126125335695, 'latency_p50': 3.1997135877609253, 'latency_p90': 3.5941229343414305}, {'batch_size': 6, 'throughput': 1.6658383289537022, 'latency_mean': 3.578129309415817, 'latency_p50': 3.5914729833602905, 'latency_p90': 4.0590862274169925}, {'batch_size': 8, 'throughput': 1.8096380268118049, 'latency_mean': 4.400668954849243, 'latency_p50': 4.404448866844177, 'latency_p90': 4.956406426429749}, {'batch_size': 10, 'throughput': 1.8845839737891432, 'latency_mean': 5.258278584480285, 'latency_p50': 5.291950941085815, 'latency_p90': 5.994783902168274}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-simp_4360_v1

is_internal_developer: True

language_model: ChaiML/mistral_nemo_simpo_baseline_albert_20241217_v1-checkpoint-625

model_size: 13B

ranking_group: single

throughput_3p7s: 1.7

us_pacific_date: 2024-12-18

win_ratio: 0.4540682414698163

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-4360-v1-mkmlizer
Waiting for job on chaiml-mistral-nemo-simp-4360-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
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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-4360-v1-mkmlizer: Downloaded to shared memory in 48.557s
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgpqwi6om, device:0
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: quantized model in 36.430s
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: Processed model ChaiML/mistral_nemo_simpo_baseline_albert_20241217_v1-checkpoint-625 in 84.987s
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-4360-v1
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-4360-v1/config.json
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-4360-v1/special_tokens_map.json
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-4360-v1/tokenizer_config.json
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-4360-v1/tokenizer.json
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-4360-v1/flywheel_model.0.safetensors
chaiml-mistral-nemo-simp-4360-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 28.29it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.96it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.31it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.17it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 50.24it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 47.11it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 44.22it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 48.43it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:06, 47.44it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:06, 43.83it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:10, 28.91it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 34.06it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:08, 35.81it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:07, 38.47it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:07, 39.23it/s]
Loading 0:  25%|██▌       | 92/363 [00:02<00:07, 38.68it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 42.91it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 42.30it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 46.49it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 38.16it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:06, 36.65it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 39.98it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 39.11it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 39.03it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 40.54it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 26.27it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:08, 26.03it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 33.44it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 34.93it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.13it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 39.61it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 34.27it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 41.84it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 41.97it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 41.91it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 42.63it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 35.14it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 42.60it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 42.29it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 43.86it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:05, 26.64it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 28.97it/s]
Loading 0:  66%|██████▌   | 238/363 [00:06<00:03, 37.94it/s]
Loading 0:  67%|██████▋   | 243/363 [00:06<00:02, 40.40it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 35.94it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 43.27it/s]
Loading 0:  72%|███████▏  | 260/363 [00:06<00:02, 44.25it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 44.92it/s]
Loading 0:  74%|███████▍  | 270/363 [00:06<00:02, 46.09it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 37.86it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:01, 44.50it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 43.39it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 43.02it/s]
Loading 0:  82%|████████▏ | 297/363 [00:07<00:01, 43.71it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 44.75it/s]
Loading 0:  85%|████████▍ | 307/363 [00:14<00:23,  2.37it/s]
Loading 0:  86%|████████▌ | 312/363 [00:14<00:15,  3.28it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:08,  5.33it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:05,  7.24it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:03,  9.29it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:01, 13.16it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:01, 16.48it/s]
Loading 0:  96%|█████████▌| 349/363 [00:15<00:00, 19.60it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 25.74it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 29.38it/s]
                                                            
Job chaiml-mistral-nemo-simp-4360-v1-mkmlizer completed after 114.31s with status: succeeded
Stopping job with name chaiml-mistral-nemo-simp-4360-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.86s
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-simp-4360-v1
Waiting for inference service chaiml-mistral-nemo-simp-4360-v1 to be ready
Inference service chaiml-mistral-nemo-simp-4360-v1 ready after 251.3663511276245s
Pipeline stage MKMLDeployer completed in 251.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4584293365478516s
Received healthy response to inference request in 1.1264431476593018s
Received healthy response to inference request in 1.395132064819336s
Received healthy response to inference request in 0.5987591743469238s
Received healthy response to inference request in 3.299027442932129s
5 requests
0 failed requests
5th percentile: 0.7042959690093994
10th percentile: 0.809832763671875
20th percentile: 1.020906352996826
30th percentile: 1.1801809310913085
40th percentile: 1.2876564979553222
50th percentile: 1.395132064819336
60th percentile: 1.4204509735107422
70th percentile: 1.4457698822021485
80th percentile: 1.8265489578247074
90th percentile: 2.562788200378418
95th percentile: 2.930907821655273
99th percentile: 3.2254035186767576
mean time: 1.5755582332611084
Pipeline stage StressChecker completed in 9.27s
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 2.13s
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 2.00s
Shutdown handler de-registered
chaiml-mistral-nemo-simp_4360_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 3212.33s
Shutdown handler de-registered
chaiml-mistral-nemo-simp_4360_v1 status is now inactive due to auto deactivation removed underperforming models