chaiml-exp311-stage2-si_96959

developer_uid: NischayDnk

submission_id: chaiml-exp311-stage2-si_96959_v4

model_name: chaiml-exp311-stage2-si_96959_v4

model_group: ChaiML/exp311-stage2-sim

status: torndown

timestamp: 2025-04-16T15:51:48+00:00

num_battles: 6365

num_wins: 3847

celo_rating: 1357.73

family_friendly_score: 0.40959999999999996

family_friendly_standard_error: 0.006954535786089536

submission_type: basic

model_repo: ChaiML/exp311-stage2-simpo-v1-ft-simpo1350-datav1full

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.3848356212609461, 'latency_mean': 2.598450082540512, 'latency_p50': 2.5981972217559814, 'latency_p90': 2.8717974424362183}, {'batch_size': 3, 'throughput': 0.7914318633772118, 'latency_mean': 3.770044504404068, 'latency_p50': 3.767233729362488, 'latency_p90': 4.235427641868592}, {'batch_size': 5, 'throughput': 1.0480848360033037, 'latency_mean': 4.750995419025421, 'latency_p50': 4.752089500427246, 'latency_p90': 5.258355736732483}, {'batch_size': 6, 'throughput': 1.1296117061563207, 'latency_mean': 5.265635632276535, 'latency_p50': 5.309103608131409, 'latency_p90': 5.81250307559967}, {'batch_size': 10, 'throughput': 1.286359869501656, 'latency_mean': 7.707440618276596, 'latency_p50': 7.6996848583221436, 'latency_p90': 8.659425163269043}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-exp311-stage2-si_96959_v4

is_internal_developer: False

language_model: ChaiML/exp311-stage2-simpo-v1-ft-simpo1350-datav1full

model_size: 24B

ranking_group: single

throughput_3p7s: 0.78

us_pacific_date: 2025-04-16

win_ratio: 0.6043990573448547

generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_start|>', '\n', '<|im_end|>'], 'max_input_tokens': 768, '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-exp311-stage2-si-96959-v4-mkmlizer
Waiting for job on chaiml-exp311-stage2-si-96959-v4-mkmlizer to finish
chaiml-exp311-stage2-si-96959-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp311-stage2-si-96959-v4-mkmlizer: ║     _____            __           __                                ║
chaiml-exp311-stage2-si-96959-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp311-stage2-si-96959-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp311-stage2-si-96959-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp311-stage2-si-96959-v4-mkmlizer: ║       /___/                                                         ║
chaiml-exp311-stage2-si-96959-v4-mkmlizer: ║                                                                     ║
chaiml-exp311-stage2-si-96959-v4-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp311-stage2-si-96959-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp311-stage2-si-96959-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp311-stage2-si-96959-v4-mkmlizer: ║                                                                     ║
chaiml-exp311-stage2-si-96959-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp311-stage2-si-96959-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp311-stage2-si-96959-v4-mkmlizer: ║                                                                     ║
chaiml-exp311-stage2-si-96959-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp311-stage2-si-96959-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp311-stage2-si-96959-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-exp311-stage2-si-96959-v4-mkmlizer: ║                                                                     ║
chaiml-exp311-stage2-si-96959-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp311-stage2-si-96959-v4-mkmlizer: Downloaded to shared memory in 68.218s
chaiml-exp311-stage2-si-96959-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8and_zsk, device:0
chaiml-exp311-stage2-si-96959-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp311-stage2-si-96959-v4-mkmlizer: quantized model in 56.698s
chaiml-exp311-stage2-si-96959-v4-mkmlizer: Processed model ChaiML/exp311-stage2-simpo-v1-ft-simpo1350-datav1full in 124.916s
chaiml-exp311-stage2-si-96959-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp311-stage2-si-96959-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp311-stage2-si-96959-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp311-stage2-si-96959-v4
chaiml-exp311-stage2-si-96959-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp311-stage2-si-96959-v4/config.json
chaiml-exp311-stage2-si-96959-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp311-stage2-si-96959-v4/special_tokens_map.json
chaiml-exp311-stage2-si-96959-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp311-stage2-si-96959-v4/tokenizer_config.json
chaiml-exp311-stage2-si-96959-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp311-stage2-si-96959-v4/tokenizer.json
Unable to record family friendly update due to error: Invalid JSON input: JSON must contain 'User Safety' and 'Response Safety' fields
chaiml-exp311-stage2-si-96959-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp311-stage2-si-96959-v4/flywheel_model.1.safetensors
chaiml-exp311-stage2-si-96959-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp311-stage2-si-96959-v4/flywheel_model.0.safetensors
chaiml-exp311-stage2-si-96959-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.58it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 37.46it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 34.54it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 35.21it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 31.53it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 36.89it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 22.87it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:12, 25.32it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:11, 26.76it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 28.62it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.52it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 30.48it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 28.80it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 29.02it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.39it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.73it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 27.12it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:10, 26.37it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:09, 27.76it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.45it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.38it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.29it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:10, 25.62it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:11, 23.00it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 25.92it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.76it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.93it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 25.47it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.11it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.56it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:07, 30.64it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.05it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:06, 34.52it/s]
Loading 0:  42%|████▏     | 152/363 [00:05<00:08, 24.09it/s]
Loading 0:  43%|████▎     | 155/363 [00:05<00:08, 24.47it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:10, 20.21it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.48it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 24.02it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.11it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 27.24it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 27.68it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:07, 24.63it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.24it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:06, 24.36it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.19it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:06, 24.19it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<03:22,  1.25s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<02:47,  1.05s/it]
Loading 0:  57%|█████▋    | 208/363 [00:23<01:40,  1.54it/s]
Loading 0:  58%|█████▊    | 211/363 [00:24<01:17,  1.97it/s]
Loading 0:  59%|█████▉    | 214/363 [00:24<00:57,  2.60it/s]
Loading 0:  60%|██████    | 218/363 [00:24<00:38,  3.73it/s]
Loading 0:  61%|██████    | 221/363 [00:24<00:29,  4.79it/s]
Loading 0:  62%|██████▏   | 224/363 [00:24<00:24,  5.79it/s]
Loading 0:  63%|██████▎   | 229/363 [00:24<00:15,  8.59it/s]
Loading 0:  64%|██████▍   | 232/363 [00:25<00:12, 10.16it/s]
Loading 0:  65%|██████▌   | 237/363 [00:25<00:09, 13.86it/s]
Loading 0:  66%|██████▌   | 240/363 [00:25<00:08, 14.77it/s]
Loading 0:  68%|██████▊   | 246/363 [00:25<00:05, 19.92it/s]
Loading 0:  69%|██████▊   | 249/363 [00:25<00:05, 19.87it/s]
Loading 0:  70%|███████   | 255/363 [00:25<00:04, 25.06it/s]
Loading 0:  71%|███████▏  | 259/363 [00:25<00:04, 24.61it/s]
Loading 0:  73%|███████▎  | 264/363 [00:26<00:03, 29.40it/s]
Loading 0:  74%|███████▍  | 268/363 [00:26<00:04, 22.38it/s]
Loading 0:  75%|███████▍  | 271/363 [00:26<00:04, 21.30it/s]
Loading 0:  75%|███████▌  | 274/363 [00:26<00:03, 22.77it/s]
Loading 0:  76%|███████▋  | 277/363 [00:26<00:03, 23.29it/s]
Loading 0:  78%|███████▊  | 282/363 [00:26<00:03, 26.71it/s]
Loading 0:  79%|███████▊  | 285/363 [00:27<00:03, 24.29it/s]
Loading 0:  80%|████████  | 291/363 [00:27<00:02, 29.06it/s]
Loading 0:  81%|████████▏ | 295/363 [00:27<00:02, 27.52it/s]
Loading 0:  82%|████████▏ | 299/363 [00:27<00:02, 27.83it/s]
Loading 0:  84%|████████▎ | 304/363 [00:27<00:02, 24.32it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 22.60it/s]
Loading 0:  85%|████████▌ | 310/363 [00:28<00:02, 23.74it/s]
Loading 0:  86%|████████▌ | 313/363 [00:28<00:02, 24.02it/s]
Loading 0:  88%|████████▊ | 318/363 [00:28<00:01, 26.86it/s]
Loading 0:  88%|████████▊ | 321/363 [00:28<00:01, 24.36it/s]
Loading 0:  90%|█████████ | 327/363 [00:28<00:01, 29.13it/s]
Loading 0:  91%|█████████ | 330/363 [00:28<00:01, 26.19it/s]
Loading 0:  92%|█████████▏| 335/363 [00:28<00:00, 28.38it/s]
Loading 0:  93%|█████████▎| 338/363 [00:29<00:00, 27.35it/s]
Loading 0:  94%|█████████▍| 341/363 [00:36<00:13,  1.64it/s]
Loading 0:  96%|█████████▌| 347/363 [00:36<00:05,  2.72it/s]
Loading 0:  96%|█████████▋| 350/363 [00:36<00:03,  3.41it/s]
Loading 0:  98%|█████████▊| 355/363 [00:36<00:01,  5.05it/s]
Loading 0:  99%|█████████▉| 359/363 [00:36<00:00,  6.57it/s]
                                                            
Job chaiml-exp311-stage2-si-96959-v4-mkmlizer completed after 156.43s with status: succeeded
Stopping job with name chaiml-exp311-stage2-si-96959-v4-mkmlizer
Pipeline stage MKMLizer completed in 157.00s
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-exp311-stage2-si-96959-v4
Waiting for inference service chaiml-exp311-stage2-si-96959-v4 to be ready
Inference service chaiml-exp311-stage2-si-96959-v4 ready after 130.45905876159668s
Pipeline stage MKMLDeployer completed in 130.98s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.988161325454712s
Received healthy response to inference request in 2.493983507156372s
Received healthy response to inference request in 2.6335666179656982s
Received healthy response to inference request in 2.6106984615325928s
Received healthy response to inference request in 2.539547920227051s
5 requests
0 failed requests
5th percentile: 2.5030963897705076
10th percentile: 2.5122092723846436
20th percentile: 2.530435037612915
30th percentile: 2.5537780284881593
40th percentile: 2.582238245010376
50th percentile: 2.6106984615325928
60th percentile: 2.619845724105835
70th percentile: 2.6289929866790773
80th percentile: 2.704485559463501
90th percentile: 2.8463234424591066
95th percentile: 2.9172423839569093
99th percentile: 2.9739775371551516
mean time: 2.653191566467285
Pipeline stage StressChecker completed in 14.88s
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 0.82s
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 0.77s
Shutdown handler de-registered
chaiml-exp311-stage2-si_96959_v4 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5552.26s
Shutdown handler de-registered
chaiml-exp311-stage2-si_96959_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp311-stage2-si_96959_v4 status is now torndown due to DeploymentManager action