chaiml-exp348-simpo-s3-_51244

developer_uid: NischayDnk

submission_id: chaiml-exp348-simpo-s3-_51244_v1

model_name: chaiml-exp348-simpo-s3-_51244_v1

model_group: ChaiML/exp348-simpo-s3-s

status: torndown

timestamp: 2025-04-16T22:49:13+00:00

num_battles: 6862

num_wins: 4034

celo_rating: 1350.98

family_friendly_score: 0.4254

family_friendly_standard_error: 0.006991921624274688

submission_type: basic

model_repo: ChaiML/exp348-simpo-s3-slerpv2-data31full1350

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.3703059691448776, 'latency_mean': 2.700404654741287, 'latency_p50': 2.695354461669922, 'latency_p90': 3.0186527729034425}, {'batch_size': 2, 'throughput': 0.5748608520742303, 'latency_mean': 3.476273674964905, 'latency_p50': 3.4598432779312134, 'latency_p90': 3.846395468711853}, {'batch_size': 3, 'throughput': 0.7231855768915099, 'latency_mean': 4.141888957023621, 'latency_p50': 4.141606569290161, 'latency_p90': 4.630266070365906}, {'batch_size': 4, 'throughput': 0.8385797189797344, 'latency_mean': 4.75202280163765, 'latency_p50': 4.778272867202759, 'latency_p90': 5.2982374906539915}, {'batch_size': 5, 'throughput': 0.9382226904584933, 'latency_mean': 5.3146078383922575, 'latency_p50': 5.293471574783325, 'latency_p90': 5.960350227355957}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-exp348-simpo-s3-_51244_v1

is_internal_developer: False

language_model: ChaiML/exp348-simpo-s3-slerpv2-data31full1350

model_size: 24B

ranking_group: single

throughput_3p7s: 0.63

us_pacific_date: 2025-04-16

win_ratio: 0.5878752550276887

generation_params: {'temperature': 0.5, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 70, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['<|im_end|>', '\n', '<|im_start|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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-exp348-simpo-s3-51244-v1-mkmlizer
Waiting for job on chaiml-exp348-simpo-s3-51244-v1-mkmlizer to finish
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: ║       /___/                                                         ║
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: ║                                                                     ║
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: ║                                                                     ║
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: ║                                                                     ║
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: ║                                                                     ║
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: Downloaded to shared memory in 80.268s
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvnurd3ye, device:0
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: quantized model in 53.200s
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: Processed model ChaiML/exp348-simpo-s3-slerpv2-data31full1350 in 133.468s
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp348-simpo-s3-51244-v1
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp348-simpo-s3-51244-v1/config.json
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp348-simpo-s3-51244-v1/special_tokens_map.json
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp348-simpo-s3-51244-v1/tokenizer_config.json
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp348-simpo-s3-51244-v1/tokenizer.json
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp348-simpo-s3-51244-v1/flywheel_model.0.safetensors
chaiml-exp348-simpo-s3-51244-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 37.63it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 30.28it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 32.59it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:11, 29.41it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 33.89it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 30.74it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 36.85it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 20.95it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.68it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.19it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.10it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.62it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 29.71it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 28.18it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.97it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 24.93it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 20.67it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.13it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 25.73it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 27.12it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:09, 27.44it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 22.45it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 29.12it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 28.14it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 23.05it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 25.79it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.39it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.42it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 25.82it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.29it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 28.91it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 31.12it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 29.05it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:06, 35.63it/s]
Loading 0:  42%|████▏     | 152/363 [00:05<00:08, 23.53it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:08, 23.41it/s]
Loading 0:  44%|████▍     | 159/363 [00:05<00:09, 22.51it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 27.00it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:07, 25.00it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.75it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.39it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.65it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:07, 23.74it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.54it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.64it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.83it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 23.83it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:56,  1.09s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:26,  1.09it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:28,  1.75it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:07,  2.24it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:50,  2.95it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:34,  4.20it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:26,  5.38it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.42it/s]
Loading 0:  63%|██████▎   | 228/363 [00:22<00:15,  9.00it/s]
Loading 0:  64%|██████▎   | 231/363 [00:22<00:12, 10.55it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.68it/s]
Loading 0:  66%|██████▋   | 241/363 [00:23<00:07, 17.36it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.08it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 22.27it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 25.74it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:04, 25.66it/s]
Loading 0:  73%|███████▎  | 265/363 [00:23<00:03, 32.42it/s]
Loading 0:  74%|███████▍  | 269/363 [00:24<00:04, 22.84it/s]
Loading 0:  75%|███████▌  | 273/363 [00:24<00:03, 22.66it/s]
Loading 0:  76%|███████▌  | 276/363 [00:24<00:03, 21.90it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:03, 26.54it/s]
Loading 0:  79%|███████▊  | 285/363 [00:24<00:03, 24.76it/s]
Loading 0:  80%|████████  | 291/363 [00:24<00:02, 29.54it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 28.51it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 28.41it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 25.04it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.55it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 24.25it/s]
Loading 0:  86%|████████▌ | 313/363 [00:25<00:01, 25.06it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 27.72it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 25.35it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 30.10it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 28.91it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 29.13it/s]
Loading 0:  93%|█████████▎| 338/363 [00:26<00:00, 27.87it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:13,  1.67it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:05,  2.79it/s]
Loading 0:  96%|█████████▋| 350/363 [00:33<00:03,  3.51it/s]
Loading 0:  98%|█████████▊| 355/363 [00:33<00:01,  5.21it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00,  6.79it/s]
                                                            
Job chaiml-exp348-simpo-s3-51244-v1-mkmlizer completed after 166.47s with status: succeeded
Stopping job with name chaiml-exp348-simpo-s3-51244-v1-mkmlizer
Pipeline stage MKMLizer completed in 167.22s
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-exp348-simpo-s3-51244-v1
Waiting for inference service chaiml-exp348-simpo-s3-51244-v1 to be ready
Inference service chaiml-exp348-simpo-s3-51244-v1 ready after 130.47771525382996s
Pipeline stage MKMLDeployer completed in 130.90s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0020787715911865s
Received healthy response to inference request in 2.5294322967529297s
Received healthy response to inference request in 2.6016321182250977s
Received healthy response to inference request in 2.6494040489196777s
Received healthy response to inference request in 2.6648690700531006s
5 requests
0 failed requests
5th percentile: 2.543872261047363
10th percentile: 2.5583122253417967
20th percentile: 2.587192153930664
30th percentile: 2.6111865043640137
40th percentile: 2.6302952766418457
50th percentile: 2.6494040489196777
60th percentile: 2.655590057373047
70th percentile: 2.661776065826416
80th percentile: 2.7323110103607178
90th percentile: 2.867194890975952
95th percentile: 2.9346368312835693
99th percentile: 2.988590383529663
mean time: 2.6894832611083985
Pipeline stage StressChecker completed in 14.66s
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 0.72s
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 0.66s
Shutdown handler de-registered
chaiml-exp348-simpo-s3-_51244_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 3001.81s
Shutdown handler de-registered
chaiml-exp348-simpo-s3-_51244_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp348-simpo-s3-_51244_v1 status is now torndown due to DeploymentManager action