chaiml-mistral-nemo-simp_7503

developer_uid: azuruce

submission_id: chaiml-mistral-nemo-simp_7503_v2

model_name: chaiml-mistral-nemo-simp_7503_v2

model_group: ChaiML/mistral_nemo_simp

status: inactive

timestamp: 2024-12-15T23:15:38+00:00

num_battles: 8939

num_wins: 3566

celo_rating: 1159.68

family_friendly_score: 0.5489999999999999

family_friendly_standard_error: 0.007037030623778754

submission_type: basic

model_repo: ChaiML/mistral_nemo_simpo_baseline_albert_20241213_v2_mad-checkpoint-1872

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6409608603414902, 'latency_mean': 1.560066430568695, 'latency_p50': 1.561326026916504, 'latency_p90': 1.7214289903640747}, {'batch_size': 3, 'throughput': 1.2700202869370452, 'latency_mean': 2.3523371160030364, 'latency_p50': 2.3566536903381348, 'latency_p90': 2.5842374324798585}, {'batch_size': 5, 'throughput': 1.588033420274007, 'latency_mean': 3.1327064728736875, 'latency_p50': 3.149488687515259, 'latency_p90': 3.5249019622802735}, {'batch_size': 6, 'throughput': 1.7278119749535679, 'latency_mean': 3.460967583656311, 'latency_p50': 3.434225559234619, 'latency_p90': 3.93249135017395}, {'batch_size': 8, 'throughput': 1.8832945275858763, 'latency_mean': 4.218361850976944, 'latency_p50': 4.213778972625732, 'latency_p90': 4.7217031955719}, {'batch_size': 10, 'throughput': 1.9566758109594897, 'latency_mean': 5.068644764423371, 'latency_p50': 5.086099863052368, 'latency_p90': 5.698744940757751}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-mistral-nemo-simp_7503_v2

is_internal_developer: True

language_model: ChaiML/mistral_nemo_simpo_baseline_albert_20241213_v2_mad-checkpoint-1872

model_size: 13B

ranking_group: single

throughput_3p7s: 1.79

us_pacific_date: 2024-12-15

win_ratio: 0.3989260543684976

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-7503-v2-mkmlizer
Waiting for job on chaiml-mistral-nemo-simp-7503-v2-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: ║       /___/                                                         ║
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: Downloaded to shared memory in 36.934s
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzvfl9b6q, device:0
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
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-7503-v2-mkmlizer: quantized model in 38.277s
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: Processed model ChaiML/mistral_nemo_simpo_baseline_albert_20241213_v2_mad-checkpoint-1872 in 75.212s
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-7503-v2
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-7503-v2/config.json
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-7503-v2/special_tokens_map.json
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-7503-v2/tokenizer_config.json
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-7503-v2/tokenizer.json
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-nemo-simp-7503-v2/flywheel_model.0.safetensors
chaiml-mistral-nemo-simp-7503-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 25.64it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 41.70it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 39.54it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 38.99it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:08, 40.05it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:10, 31.60it/s]
Loading 0:  11%|█         | 39/363 [00:01<00:08, 38.64it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:08, 38.16it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:08, 38.42it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:07, 39.27it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:07, 40.37it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:12, 23.93it/s]
Loading 0:  20%|█▉        | 71/363 [00:02<00:09, 30.82it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 32.91it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:08, 34.83it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 35.82it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 30.31it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:07, 36.74it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 37.27it/s]
Loading 0:  30%|██▉       | 108/363 [00:03<00:06, 38.64it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:08, 30.65it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:08, 30.60it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 36.93it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:06, 36.90it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:06, 36.74it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 34.98it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:09, 24.28it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:09, 23.37it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 24.20it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 31.99it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 31.76it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 34.49it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:05, 33.08it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 35.40it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 33.39it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 34.23it/s]
Loading 0:  51%|█████     | 186/363 [00:05<00:05, 31.19it/s]
Loading 0:  52%|█████▏    | 190/363 [00:05<00:05, 33.14it/s]
Loading 0:  53%|█████▎    | 194/363 [00:05<00:05, 30.92it/s]
Loading 0:  55%|█████▍    | 199/363 [00:05<00:04, 34.92it/s]
Loading 0:  56%|█████▌    | 203/363 [00:06<00:05, 31.21it/s]
Loading 0:  58%|█████▊    | 210/363 [00:06<00:04, 37.41it/s]
Loading 0:  59%|█████▉    | 214/363 [00:06<00:04, 35.41it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:04, 34.28it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:05, 25.60it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:05, 25.10it/s]
Loading 0:  63%|██████▎   | 230/363 [00:07<00:05, 25.37it/s]
Loading 0:  65%|██████▍   | 235/363 [00:07<00:04, 30.22it/s]
Loading 0:  66%|██████▌   | 239/363 [00:07<00:04, 28.43it/s]
Loading 0:  67%|██████▋   | 244/363 [00:07<00:03, 32.47it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 29.77it/s]
Loading 0:  70%|██████▉   | 253/363 [00:07<00:03, 34.06it/s]
Loading 0:  71%|███████   | 257/363 [00:07<00:03, 31.68it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 38.94it/s]
Loading 0:  74%|███████▍  | 269/363 [00:08<00:02, 38.65it/s]
Loading 0:  75%|███████▌  | 274/363 [00:08<00:02, 38.05it/s]
Loading 0:  77%|███████▋  | 278/363 [00:08<00:02, 37.49it/s]
Loading 0:  78%|███████▊  | 282/363 [00:08<00:02, 37.56it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 35.01it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:02, 35.98it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:02, 33.18it/s]
Loading 0:  82%|████████▏ | 299/363 [00:08<00:01, 35.60it/s]
Loading 0:  84%|████████▎ | 304/363 [00:15<00:27,  2.14it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:20,  2.67it/s]
Loading 0:  86%|████████▌ | 312/363 [00:16<00:12,  3.92it/s]
Loading 0:  88%|████████▊ | 319/363 [00:16<00:06,  6.35it/s]
Loading 0:  89%|████████▉ | 324/363 [00:16<00:04,  8.47it/s]
Loading 0:  91%|█████████ | 329/363 [00:16<00:03, 11.01it/s]
Loading 0:  92%|█████████▏| 334/363 [00:16<00:02, 14.21it/s]
Loading 0:  93%|█████████▎| 339/363 [00:16<00:01, 16.23it/s]
Loading 0:  95%|█████████▌| 346/363 [00:16<00:00, 22.37it/s]
Loading 0:  97%|█████████▋| 351/363 [00:17<00:00, 25.29it/s]
Loading 0:  98%|█████████▊| 356/363 [00:17<00:00, 28.43it/s]
Loading 0:  99%|█████████▉| 361/363 [00:17<00:00, 32.00it/s]
                                                            
Job chaiml-mistral-nemo-simp-7503-v2-mkmlizer completed after 105.27s with status: succeeded
Stopping job with name chaiml-mistral-nemo-simp-7503-v2-mkmlizer
Pipeline stage MKMLizer completed in 105.75s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-nemo-simp-7503-v2
Waiting for inference service chaiml-mistral-nemo-simp-7503-v2 to be ready
Inference service chaiml-mistral-nemo-simp-7503-v2 ready after 211.04970240592957s
Pipeline stage MKMLDeployer completed in 211.60s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9803974628448486s
Received healthy response to inference request in 1.368680477142334s
Received healthy response to inference request in 1.6733729839324951s
Received healthy response to inference request in 1.7249500751495361s
Received healthy response to inference request in 1.357966423034668s
5 requests
0 failed requests
5th percentile: 1.360109233856201
10th percentile: 1.3622520446777344
20th percentile: 1.3665376663208009
30th percentile: 1.4296189785003661
40th percentile: 1.5514959812164306
50th percentile: 1.6733729839324951
60th percentile: 1.6940038204193115
70th percentile: 1.714634656906128
80th percentile: 1.7760395526885986
90th percentile: 1.8782185077667237
95th percentile: 1.9293079853057862
99th percentile: 1.9701795673370361
mean time: 1.6210734844207764
Pipeline stage StressChecker completed in 9.58s
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 2.17s
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 2.61s
Shutdown handler de-registered
chaiml-mistral-nemo-simp_7503_v2 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
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 2479.73s
Shutdown handler de-registered
chaiml-mistral-nemo-simp_7503_v2 status is now inactive due to auto deactivation removed underperforming models