chaiml-exp316-simpo-ft-s_4491

developer_uid: NischayDnk

submission_id: chaiml-exp316-simpo-ft-s_4491_v1

model_name: chaiml-exp316-simpo-ft-s_4491_v1

model_group: ChaiML/exp316-simpo-ft-s

status: torndown

timestamp: 2025-04-17T02:17:17+00:00

num_battles: 9029

num_wins: 5339

celo_rating: 1356.51

family_friendly_score: 0.41500000000000004

family_friendly_standard_error: 0.006968141789602161

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': 0.3682288521512786, 'latency_mean': 2.71560075879097, 'latency_p50': 2.7174177169799805, 'latency_p90': 3.003382611274719}, {'batch_size': 2, 'throughput': 0.5805739688198329, 'latency_mean': 3.4420112240314484, 'latency_p50': 3.4446253776550293, 'latency_p90': 3.7807285308837892}, {'batch_size': 3, 'throughput': 0.7369426901038781, 'latency_mean': 4.0527213394641874, 'latency_p50': 4.046690344810486, 'latency_p90': 4.51768045425415}, {'batch_size': 4, 'throughput': 0.8514410656743386, 'latency_mean': 4.692172354459762, 'latency_p50': 4.72613799571991, 'latency_p90': 5.146200180053711}, {'batch_size': 5, 'throughput': 0.9407698892267783, 'latency_mean': 5.295434656143189, 'latency_p50': 5.3298739194869995, 'latency_p90': 5.913465595245361}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-exp316-simpo-ft-s_4491_v1

is_internal_developer: False

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

model_size: 24B

ranking_group: single

throughput_3p7s: 0.65

us_pacific_date: 2025-04-16

win_ratio: 0.591316867870196

generation_params: {'temperature': 0.4, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 40, '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-exp316-simpo-ft-s-4491-v1-mkmlizer
Waiting for job on chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer to finish
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: ║       /___/                                                         ║
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: ║                                                                     ║
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: ║                                                                     ║
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: ║                                                                     ║
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: ║                                                                     ║
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: Downloaded to shared memory in 129.667s
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbjcere36, device:0
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: quantized model in 55.878s
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: Processed model ChaiML/exp316-simpo-ft-s3-simpofullv1-1360-ff4kexp3 in 185.546s
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp316-simpo-ft-s-4491-v1
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp316-simpo-ft-s-4491-v1/config.json
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp316-simpo-ft-s-4491-v1/special_tokens_map.json
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp316-simpo-ft-s-4491-v1/tokenizer_config.json
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp316-simpo-ft-s-4491-v1/tokenizer.json
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp316-simpo-ft-s-4491-v1/flywheel_model.1.safetensors
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp316-simpo-ft-s-4491-v1/flywheel_model.0.safetensors
chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 37.71it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 28.31it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 28.91it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:14, 23.44it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 29.71it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 26.52it/s]
Loading 0:   8%|▊         | 29/363 [00:01<00:11, 29.54it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:15, 21.14it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:17, 18.65it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 21.88it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:14, 22.57it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 26.46it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:13, 23.74it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 29.18it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 28.07it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.84it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.11it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.52it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:10, 26.53it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 25.68it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 27.04it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.27it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.17it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:10, 26.01it/s]
Loading 0:  28%|██▊       | 101/363 [00:04<00:11, 22.77it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:09, 28.00it/s]
Loading 0:  30%|███       | 110/363 [00:04<00:10, 23.37it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:12, 20.02it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:09, 26.41it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:09, 25.34it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:09, 26.15it/s]
Loading 0:  36%|███▌      | 130/363 [00:05<00:08, 26.02it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:09, 25.44it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 27.95it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:09, 24.46it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:07, 27.41it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:07, 30.21it/s]
Loading 0:  42%|████▏     | 153/363 [00:06<00:12, 17.16it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:10, 20.23it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:09, 20.37it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:09, 21.53it/s]
Loading 0:  46%|████▌     | 166/363 [00:06<00:08, 22.72it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:08, 22.58it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:08, 23.63it/s]
Loading 0:  48%|████▊     | 175/363 [00:07<00:07, 23.85it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:08, 22.37it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:07, 23.65it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:06, 25.48it/s]
Loading 0:  52%|█████▏    | 189/363 [00:08<00:11, 15.57it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 19.06it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:08, 19.79it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:07, 21.10it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:07, 21.10it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<04:05,  1.52s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<03:11,  1.20s/it]
Loading 0:  57%|█████▋    | 208/363 [00:23<01:44,  1.49it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:17,  1.97it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:56,  2.65it/s]
Loading 0:  60%|█████▉    | 217/363 [00:23<00:40,  3.58it/s]
Loading 0:  61%|██████    | 220/363 [00:23<00:31,  4.61it/s]
Loading 0:  61%|██████▏   | 223/363 [00:23<00:22,  6.13it/s]
Loading 0:  62%|██████▏   | 226/363 [00:24<00:19,  7.11it/s]
Loading 0:  63%|██████▎   | 230/363 [00:24<00:14,  9.11it/s]
Loading 0:  65%|██████▍   | 235/363 [00:24<00:09, 13.35it/s]
Loading 0:  66%|██████▌   | 238/363 [00:24<00:08, 15.33it/s]
Loading 0:  66%|██████▋   | 241/363 [00:24<00:07, 16.67it/s]
Loading 0:  67%|██████▋   | 244/363 [00:24<00:06, 18.91it/s]
Loading 0:  68%|██████▊   | 247/363 [00:24<00:05, 20.80it/s]
Loading 0:  69%|██████▉   | 250/363 [00:25<00:05, 21.36it/s]
Loading 0:  70%|██████▉   | 253/363 [00:25<00:04, 23.05it/s]
Loading 0:  71%|███████   | 256/363 [00:25<00:04, 24.28it/s]
Loading 0:  71%|███████▏  | 259/363 [00:25<00:04, 23.58it/s]
Loading 0:  72%|███████▏  | 262/363 [00:25<00:04, 24.91it/s]
Loading 0:  73%|███████▎  | 266/363 [00:25<00:03, 28.15it/s]
Loading 0:  74%|███████▍  | 269/363 [00:25<00:05, 18.39it/s]
Loading 0:  75%|███████▍  | 272/363 [00:26<00:04, 19.05it/s]
Loading 0:  76%|███████▌  | 275/363 [00:26<00:05, 16.46it/s]
Loading 0:  77%|███████▋  | 280/363 [00:26<00:03, 22.27it/s]
Loading 0:  78%|███████▊  | 283/363 [00:26<00:03, 23.52it/s]
Loading 0:  79%|███████▉  | 286/363 [00:26<00:03, 23.30it/s]
Loading 0:  80%|███████▉  | 290/363 [00:26<00:02, 27.13it/s]
Loading 0:  81%|████████  | 294/363 [00:26<00:03, 22.96it/s]
Loading 0:  82%|████████▏ | 298/363 [00:27<00:02, 26.19it/s]
Loading 0:  83%|████████▎ | 303/363 [00:27<00:02, 28.27it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 19.10it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 20.46it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 21.11it/s]
Loading 0:  87%|████████▋ | 316/363 [00:27<00:02, 22.87it/s]
Loading 0:  88%|████████▊ | 319/363 [00:28<00:01, 24.11it/s]
Loading 0:  89%|████████▊ | 322/363 [00:28<00:01, 24.59it/s]
Loading 0:  90%|█████████ | 327/363 [00:28<00:01, 27.66it/s]
Loading 0:  91%|█████████ | 330/363 [00:28<00:01, 24.33it/s]
Loading 0:  92%|█████████▏| 334/363 [00:28<00:01, 27.90it/s]
Loading 0:  93%|█████████▎| 337/363 [00:28<00:01, 23.55it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:13,  1.67it/s]
Loading 0:  96%|█████████▌| 347/363 [00:35<00:05,  2.77it/s]
Loading 0:  96%|█████████▋| 350/363 [00:35<00:03,  3.46it/s]
Loading 0:  98%|█████████▊| 355/363 [00:36<00:01,  5.12it/s]
Loading 0:  99%|█████████▊| 358/363 [00:36<00:00,  6.15it/s]
                                                            
Job chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer completed after 227.98s with status: succeeded
Stopping job with name chaiml-exp316-simpo-ft-s-4491-v1-mkmlizer
Pipeline stage MKMLizer completed in 228.57s
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-v1
Waiting for inference service chaiml-exp316-simpo-ft-s-4491-v1 to be ready
Inference service chaiml-exp316-simpo-ft-s-4491-v1 ready after 130.87021946907043s
Pipeline stage MKMLDeployer completed in 131.43s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.281031847000122s
Received healthy response to inference request in 2.757727861404419s
Received healthy response to inference request in 2.465226173400879s
Received healthy response to inference request in 2.4578747749328613s
Received healthy response to inference request in 2.5653398036956787s
5 requests
0 failed requests
5th percentile: 2.459345054626465
10th percentile: 2.4608153343200683
20th percentile: 2.463755893707275
30th percentile: 2.485248899459839
40th percentile: 2.5252943515777586
50th percentile: 2.5653398036956787
60th percentile: 2.6422950267791747
70th percentile: 2.7192502498626707
80th percentile: 2.86238865852356
90th percentile: 3.0717102527618407
95th percentile: 3.176371049880981
99th percentile: 3.260099687576294
mean time: 2.705440092086792
Pipeline stage StressChecker completed in 15.24s
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 0.73s
Shutdown handler de-registered
chaiml-exp316-simpo-ft-s_4491_v1 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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-exp316-simpo-ft-s-4491-v1-profiler
Waiting for inference service chaiml-exp316-simpo-ft-s-4491-v1-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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 2892.09s
Shutdown handler de-registered
chaiml-exp316-simpo-ft-s_4491_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp316-simpo-ft-s_4491_v1 status is now torndown due to DeploymentManager action