chaiml-exp316-simpo-ft-s_4491

developer_uid: NischayDnk

submission_id: chaiml-exp316-simpo-ft-s_4491_v4

model_name: chaiml-exp316-simpo-ft-s_4491_v4

model_group: ChaiML/exp316-simpo-ft-s

status: torndown

timestamp: 2025-05-15T18:15:50+00:00

num_battles: 8531

num_wins: 4465

celo_rating: 1305.5

family_friendly_score: 0.4302

family_friendly_standard_error: 0.007001827761377739

submission_type: basic

model_repo: ChaiML/exp316-simpo-ft-s3-simpofullv1-1360-ff4kexp3

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': 0.525727993288537, 'latency_mean': 1.9020302319526672, 'latency_p50': 1.9096053838729858, 'latency_p90': 2.106154751777649}, {'batch_size': 3, 'throughput': 1.0636747689440247, 'latency_mean': 2.8132043075561524, 'latency_p50': 2.837313175201416, 'latency_p90': 3.0983656883239745}, {'batch_size': 5, 'throughput': 1.3675817677510123, 'latency_mean': 3.639915647506714, 'latency_p50': 3.6473612785339355, 'latency_p90': 4.0939271450042725}, {'batch_size': 6, 'throughput': 1.4786487161100008, 'latency_mean': 4.03671857714653, 'latency_p50': 4.036883234977722, 'latency_p90': 4.574076795578003}, {'batch_size': 8, 'throughput': 1.620151471367626, 'latency_mean': 4.895881905555725, 'latency_p50': 4.899254202842712, 'latency_p90': 5.47044529914856}, {'batch_size': 10, 'throughput': 1.7185662801445034, 'latency_mean': 5.757213522195816, 'latency_p50': 5.783916234970093, 'latency_p90': 6.495677208900451}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: chaiml-exp316-simpo-ft-s_4491_v4

is_internal_developer: False

language_model: ChaiML/exp316-simpo-ft-s3-simpofullv1-1360-ff4kexp3

model_size: 24B

ranking_group: single

throughput_3p7s: 1.39

us_pacific_date: 2025-05-15

win_ratio: 0.5233853006681515

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_start|>', '<|im_end|>', '\n'], '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-exp316-simpo-ft-s-4491-v4-mkmlizer
Waiting for job on chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer to finish
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: ║     _____            __           __                                ║
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: ║       /___/                                                         ║
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: ║                                                                     ║
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: ║                                                                     ║
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: ║                                                                     ║
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: ║                                                                     ║
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: Downloaded to shared memory in 77.139s
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8nqs7our, device:0
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: quantized model in 54.719s
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: Processed model ChaiML/exp316-simpo-ft-s3-simpofullv1-1360-ff4kexp3 in 131.858s
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp316-simpo-ft-s-4491-v4
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp316-simpo-ft-s-4491-v4/config.json
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp316-simpo-ft-s-4491-v4/special_tokens_map.json
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp316-simpo-ft-s-4491-v4/tokenizer_config.json
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp316-simpo-ft-s-4491-v4/flywheel_model.1.safetensors
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp316-simpo-ft-s-4491-v4/flywheel_model.0.safetensors
chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.45it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 31.42it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 32.19it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:11, 29.26it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 34.00it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 30.93it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 36.88it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 22.11it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 24.69it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 26.24it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 28.26it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.93it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 29.80it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 28.28it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.95it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.54it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 20.49it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:11, 25.43it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.70it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.14it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.06it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 20.88it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 27.72it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:10, 24.65it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 21.42it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 24.59it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 22.87it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.17it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.71it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:08, 28.75it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:08, 25.88it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.62it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:09, 23.03it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:07, 27.54it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:09, 21.57it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:10, 20.68it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 22.13it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.28it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.67it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:07, 24.54it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.71it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.61it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.52it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:06, 25.66it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.96it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:06, 24.77it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 25.19it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 25.19it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:03,  1.13s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:31,  1.06it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:31,  1.70it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.17it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:52,  2.85it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.05it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.14it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.09it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.01it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:12, 10.79it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.70it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.46it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 20.48it/s]
Loading 0:  69%|██████▊   | 249/363 [00:24<00:05, 20.32it/s]
Loading 0:  70%|██████▉   | 253/363 [00:24<00:04, 23.73it/s]
Loading 0:  71%|███████   | 257/363 [00:24<00:04, 21.82it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 30.55it/s]
Loading 0:  74%|███████▍  | 268/363 [00:24<00:04, 23.22it/s]
Loading 0:  75%|███████▍  | 272/363 [00:25<00:03, 23.42it/s]
Loading 0:  76%|███████▌  | 275/363 [00:25<00:04, 19.84it/s]
Loading 0:  77%|███████▋  | 280/363 [00:25<00:03, 24.59it/s]
Loading 0:  78%|███████▊  | 284/363 [00:25<00:03, 22.14it/s]
Loading 0:  80%|███████▉  | 289/363 [00:25<00:02, 27.24it/s]
Loading 0:  81%|████████  | 293/363 [00:26<00:02, 23.70it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 27.61it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 23.73it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 21.81it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 22.88it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 22.81it/s]
Loading 0:  87%|████████▋ | 316/363 [00:26<00:01, 24.17it/s]
Loading 0:  88%|████████▊ | 319/363 [00:27<00:01, 25.18it/s]
Loading 0:  89%|████████▊ | 322/363 [00:27<00:01, 24.96it/s]
Loading 0:  90%|████████▉ | 325/363 [00:27<00:01, 26.14it/s]
Loading 0:  90%|█████████ | 328/363 [00:27<00:01, 26.70it/s]
Loading 0:  91%|█████████ | 331/363 [00:27<00:01, 25.68it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:01, 25.88it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:01, 24.30it/s]
Loading 0:  94%|█████████▍| 341/363 [00:34<00:14,  1.47it/s]
Loading 0:  96%|█████████▌| 347/363 [00:34<00:06,  2.58it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:03,  3.30it/s]
Loading 0:  98%|█████████▊| 355/363 [00:35<00:01,  4.94it/s]
Loading 0:  99%|█████████▊| 358/363 [00:35<00:00,  5.98it/s]
                                                            
Job chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer completed after 175.92s with status: succeeded
Stopping job with name chaiml-exp316-simpo-ft-s-4491-v4-mkmlizer
Pipeline stage MKMLizer completed in 176.43s
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-exp316-simpo-ft-s-4491-v4
Waiting for inference service chaiml-exp316-simpo-ft-s-4491-v4 to be ready
Inference service chaiml-exp316-simpo-ft-s-4491-v4 ready after 130.61530375480652s
Pipeline stage MKMLDeployer completed in 131.38s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.39902400970459s
Received healthy response to inference request in 1.9005241394042969s
Received healthy response to inference request in 1.8970212936401367s
Received healthy response to inference request in 1.9136168956756592s
Received healthy response to inference request in 2.067166566848755s
5 requests
0 failed requests
5th percentile: 1.8977218627929688
10th percentile: 1.8984224319458007
20th percentile: 1.8998235702514648
30th percentile: 1.9031426906585693
40th percentile: 1.9083797931671143
50th percentile: 1.9136168956756592
60th percentile: 1.9750367641448974
70th percentile: 2.0364566326141356
80th percentile: 2.133538055419922
90th percentile: 2.2662810325622558
95th percentile: 2.3326525211334226
99th percentile: 2.3857497119903566
mean time: 2.0354705810546876
Pipeline stage StressChecker completed in 11.45s
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 0.75s
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 0.72s
Shutdown handler de-registered
chaiml-exp316-simpo-ft-s_4491_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-exp316-simpo-ft-s-4491-v4-profiler
Waiting for inference service chaiml-exp316-simpo-ft-s-4491-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 5363.67s
Shutdown handler de-registered
chaiml-exp316-simpo-ft-s_4491_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp316-simpo-ft-s_4491_v4 status is now torndown due to DeploymentManager action