chaiml-exp201-simpo-b01_34008

developer_uid: NischayDnk

submission_id: chaiml-exp201-simpo-b01_34008_v1

model_name: chaiml-exp201-simpo-b01_34008_v1

model_group: ChaiML/exp201-simpo-b01-

status: torndown

timestamp: 2025-04-12T13:40:39+00:00

num_battles: 10772

num_wins: 6126

celo_rating: 1330.25

family_friendly_score: 0.497

family_friendly_standard_error: 0.007070940531499328

submission_type: basic

model_repo: ChaiML/exp201-simpo-b01-2e-ft-mistral31dpo3e-exp1-selfdist-9kconv-s75-1

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': 0.36933831097428743, 'latency_mean': 2.70746368765831, 'latency_p50': 2.706455945968628, 'latency_p90': 2.989161419868469}, {'batch_size': 2, 'throughput': 0.5758798186111423, 'latency_mean': 3.462696306705475, 'latency_p50': 3.4533268213272095, 'latency_p90': 3.826027584075928}, {'batch_size': 3, 'throughput': 0.7302698996137964, 'latency_mean': 4.090377787351608, 'latency_p50': 4.062857270240784, 'latency_p90': 4.508340978622436}, {'batch_size': 4, 'throughput': 0.8518816759679841, 'latency_mean': 4.688287814855576, 'latency_p50': 4.687125086784363, 'latency_p90': 5.198470234870911}, {'batch_size': 5, 'throughput': 0.9328835104102338, 'latency_mean': 5.337944151163101, 'latency_p50': 5.356256127357483, 'latency_p90': 5.981005144119263}]

gpu_counts: {'NVIDIA RTX A6000': 1}

display_name: chaiml-exp201-simpo-b01_34008_v1

is_internal_developer: False

language_model: ChaiML/exp201-simpo-b01-2e-ft-mistral31dpo3e-exp1-selfdist-9kconv-s75-1

model_size: 24B

ranking_group: single

throughput_3p7s: 0.64

us_pacific_date: 2025-04-12

win_ratio: 0.5686966208689194

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-exp201-simpo-b01-34008-v1-mkmlizer
Waiting for job on chaiml-exp201-simpo-b01-34008-v1-mkmlizer to finish
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: ║       /___/                                                         ║
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: ║                                                                     ║
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: ║                                                                     ║
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: ║                                                                     ║
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: ║                                                                     ║
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission jellywibble-felix-black_21853_v1: HTTPConnectionPool(host='jellywibble-felix-black-21853-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: Downloaded to shared memory in 79.782s
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpiacbnorf, device:0
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission jellywibble-felix-black_21853_v1: HTTPConnectionPool(host='jellywibble-felix-black-21853-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: quantized model in 53.443s
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: Processed model ChaiML/exp201-simpo-b01-2e-ft-mistral31dpo3e-exp1-selfdist-9kconv-s75-1 in 133.226s
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp201-simpo-b01-34008-v1
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp201-simpo-b01-34008-v1/config.json
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp201-simpo-b01-34008-v1/special_tokens_map.json
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp201-simpo-b01-34008-v1/tokenizer_config.json
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp201-simpo-b01-34008-v1/tokenizer.json
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp201-simpo-b01-34008-v1/flywheel_model.1.safetensors
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp201-simpo-b01-34008-v1/flywheel_model.0.safetensors
chaiml-exp201-simpo-b01-34008-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 21.02it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 37.77it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 33.91it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 34.98it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 32.16it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 38.51it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.70it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 22.66it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:10, 29.15it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.38it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 30.39it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 28.67it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.98it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 26.54it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 22.15it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.81it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:10, 25.94it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:09, 27.91it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 27.05it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 22.06it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 29.66it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 28.74it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:10, 24.08it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 26.65it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 26.25it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 29.18it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.37it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.82it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 29.31it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:07, 30.23it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.27it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:06, 35.01it/s]
Loading 0:  42%|████▏     | 152/363 [00:05<00:08, 24.22it/s]
Loading 0:  43%|████▎     | 156/363 [00:05<00:08, 23.88it/s]
Loading 0:  44%|████▍     | 159/363 [00:05<00:08, 22.77it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:07, 28.02it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 26.90it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.03it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 27.48it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.29it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 26.11it/s]
Loading 0:  52%|█████▏    | 190/363 [00:06<00:07, 23.20it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 24.10it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.15it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.15it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<03:01,  1.12s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:30,  1.07it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:30,  1.71it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.18it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.87it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.11it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:27,  5.23it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.34it/s]
Loading 0:  63%|██████▎   | 229/363 [00:22<00:14,  9.32it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.09it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.07it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 16.30it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 22.10it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 22.49it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 25.66it/s]
Loading 0:  71%|███████▏  | 259/363 [00:23<00:04, 25.26it/s]
Loading 0:  73%|███████▎  | 265/363 [00:24<00:03, 31.96it/s]
Loading 0:  74%|███████▍  | 269/363 [00:24<00:03, 23.62it/s]
Loading 0:  75%|███████▌  | 273/363 [00:24<00:03, 23.61it/s]
Loading 0:  76%|███████▌  | 276/363 [00:24<00:03, 22.67it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:02, 27.29it/s]
Loading 0:  79%|███████▉  | 286/363 [00:24<00:02, 26.02it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 28.38it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 26.79it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.36it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 25.59it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.44it/s]
Loading 0:  85%|████████▌ | 310/363 [00:25<00:02, 24.37it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:01, 25.44it/s]
Loading 0:  87%|████████▋ | 316/363 [00:26<00:01, 26.41it/s]
Loading 0:  88%|████████▊ | 319/363 [00:26<00:01, 26.39it/s]
Loading 0:  89%|████████▊ | 322/363 [00:26<00:01, 26.12it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 30.19it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 28.56it/s]
Loading 0:  92%|█████████▏| 335/363 [00:26<00:00, 28.83it/s]
Loading 0:  93%|█████████▎| 338/363 [00:26<00:00, 27.95it/s]
Loading 0:  94%|█████████▍| 341/363 [00:33<00:13,  1.60it/s]
Loading 0:  96%|█████████▌| 347/363 [00:33<00:05,  2.72it/s]
Loading 0:  96%|█████████▋| 350/363 [00:34<00:03,  3.44it/s]
Loading 0:  98%|█████████▊| 355/363 [00:34<00:01,  5.15it/s]
Loading 0:  99%|█████████▉| 359/363 [00:34<00:00,  6.67it/s]
                                                            
Job chaiml-exp201-simpo-b01-34008-v1-mkmlizer completed after 168.23s with status: succeeded
Stopping job with name chaiml-exp201-simpo-b01-34008-v1-mkmlizer
Pipeline stage MKMLizer completed in 168.78s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.33s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-exp201-simpo-b01-34008-v1
Waiting for inference service chaiml-exp201-simpo-b01-34008-v1 to be ready
Inference service chaiml-exp201-simpo-b01-34008-v1 ready after 110.45493173599243s
Pipeline stage MKMLDeployer completed in 111.05s
run pipeline stage %s
Running pipeline stage StressChecker
Failed to get response for submission jellywibble-felix-black_21853_v1: HTTPConnectionPool(host='jellywibble-felix-black-21853-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Received healthy response to inference request in 2.9401795864105225s
Received healthy response to inference request in 2.550105333328247s
Received healthy response to inference request in 2.5633156299591064s
Received healthy response to inference request in 2.675849437713623s
Received healthy response to inference request in 2.5797178745269775s
5 requests
0 failed requests
5th percentile: 2.552747392654419
10th percentile: 2.5553894519805906
20th percentile: 2.5606735706329347
30th percentile: 2.5665960788726805
40th percentile: 2.573156976699829
50th percentile: 2.5797178745269775
60th percentile: 2.6181704998016357
70th percentile: 2.656623125076294
80th percentile: 2.7287154674530028
90th percentile: 2.8344475269317626
95th percentile: 2.8873135566711428
99th percentile: 2.9296063804626464
mean time: 2.661833572387695
Pipeline stage StressChecker completed in 14.77s
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 0.71s
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 1.08s
Shutdown handler de-registered
chaiml-exp201-simpo-b01_34008_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 2975.05s
Shutdown handler de-registered
chaiml-exp201-simpo-b01_34008_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-exp201-simpo-b01_34008_v1 status is now torndown due to DeploymentManager action