chaiml-gy-exp12-sft-gro_87898

developer_uid: bogoconic1

submission_id: chaiml-gy-exp12-sft-gro_87898_v1

model_name: chaiml-gy-exp12-sft-gro_87898_v1

model_group: ChaiML/gy-exp12-sft-grok

status: torndown

timestamp: 2025-06-26T12:28:47+00:00

num_battles: 9728

num_wins: 4972

celo_rating: 1296.91

family_friendly_score: 0.5516

family_friendly_standard_error: 0.007033312732987209

submission_type: basic

model_repo: ChaiML/gy-exp12-sft-grok-dpo-orig-ep2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5917660429594014, 'latency_mean': 1.6897561371326446, 'latency_p50': 1.7166240215301514, 'latency_p90': 1.8568048000335693}, {'batch_size': 3, 'throughput': 1.080320162773337, 'latency_mean': 2.772628597021103, 'latency_p50': 2.793465733528137, 'latency_p90': 3.0567046403884888}, {'batch_size': 5, 'throughput': 1.298634700536023, 'latency_mean': 3.823324879407883, 'latency_p50': 3.7874162197113037, 'latency_p90': 4.285556578636169}, {'batch_size': 6, 'throughput': 1.3521659679867284, 'latency_mean': 4.413242621421814, 'latency_p50': 4.41654372215271, 'latency_p90': 4.919622135162354}, {'batch_size': 8, 'throughput': 1.4246110997630905, 'latency_mean': 5.586625233888626, 'latency_p50': 5.536685347557068, 'latency_p90': 6.3588834524154665}, {'batch_size': 10, 'throughput': 1.4519620369079411, 'latency_mean': 6.831487783193588, 'latency_p50': 6.870050430297852, 'latency_p90': 7.5707923650741575}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp12-sft-gro_87898_v1

is_internal_developer: True

language_model: ChaiML/gy-exp12-sft-grok-dpo-orig-ep2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.29

us_pacific_date: 2025-06-26

win_ratio: 0.5111019736842105

generation_params: {'temperature': 0.8, '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': 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-gy-exp12-sft-gro-87898-v1-mkmlizer
Waiting for job on chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer to finish
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: Downloaded to shared memory in 40.486s
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: Checking if ChaiML/gy-exp12-sft-grok-dpo-orig-ep2 already exists in ChaiML
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0izjp8wp, device:0
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: quantized model in 30.930s
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: Processed model ChaiML/gy-exp12-sft-grok-dpo-orig-ep2 in 71.417s
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp12-sft-gro-87898-v1
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp12-sft-gro-87898-v1/config.json
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp12-sft-gro-87898-v1/special_tokens_map.json
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp12-sft-gro-87898-v1/tokenizer_config.json
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp12-sft-gro-87898-v1/tokenizer.json
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp12-sft-gro-87898-v1/flywheel_model.0.safetensors
chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.48it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 47.98it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 48.86it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 40.34it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 46.11it/s]
Loading 0:  10%|▉         | 36/363 [00:00<00:07, 46.44it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:08, 38.11it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:07, 44.38it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:07, 43.53it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:06, 44.75it/s]
Loading 0:  17%|█▋        | 63/363 [00:01<00:09, 30.98it/s]
Loading 0:  19%|█▊        | 68/363 [00:01<00:08, 34.41it/s]
Loading 0:  20%|██        | 73/363 [00:01<00:09, 31.72it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:07, 39.60it/s]
Loading 0:  23%|██▎       | 85/363 [00:02<00:07, 38.81it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:07, 38.66it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:06, 39.50it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:07, 33.45it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 37.87it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:06, 40.35it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:06, 37.98it/s]
Loading 0:  33%|███▎      | 121/363 [00:03<00:06, 37.95it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:06, 38.41it/s]
Loading 0:  36%|███▌      | 129/363 [00:03<00:06, 36.60it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 39.08it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 36.25it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:08, 25.62it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 27.35it/s]
Loading 0:  41%|████▏     | 150/363 [00:04<00:07, 27.63it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 33.05it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 34.00it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.49it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 38.85it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 37.63it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 42.60it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 42.15it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:03, 42.56it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 44.37it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 35.93it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 42.80it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 42.18it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 41.74it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:04, 27.73it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 29.59it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 36.71it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 37.90it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 40.04it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 37.52it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 36.24it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 39.95it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 39.32it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 39.18it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:02, 40.39it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 34.62it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 41.56it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 41.89it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 43.89it/s]
Loading 0:  84%|████████▍ | 306/363 [00:08<00:02, 23.51it/s]
Loading 0:  85%|████████▌ | 310/363 [00:08<00:02, 24.37it/s]
Loading 0:  87%|████████▋ | 314/363 [00:08<00:01, 26.04it/s]
Loading 0:  88%|████████▊ | 319/363 [00:08<00:01, 30.14it/s]
Loading 0:  89%|████████▉ | 323/363 [00:08<00:01, 31.09it/s]
Loading 0:  91%|█████████ | 329/363 [00:08<00:00, 35.83it/s]
Loading 0:  92%|█████████▏| 333/363 [00:09<00:00, 36.37it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 39.40it/s]
Loading 0:  94%|█████████▍| 343/363 [00:09<00:00, 41.34it/s]
Loading 0:  96%|█████████▌| 348/363 [00:09<00:00, 35.86it/s]
Loading 0:  98%|█████████▊| 356/363 [00:09<00:00, 44.92it/s]
Loading 0:  99%|█████████▉| 361/363 [00:09<00:00, 44.98it/s]
                                                            
Job chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer completed after 94.56s with status: succeeded
Stopping job with name chaiml-gy-exp12-sft-gro-87898-v1-mkmlizer
Pipeline stage MKMLizer completed in 95.04s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp12-sft-gro-87898-v1
Waiting for inference service chaiml-gy-exp12-sft-gro-87898-v1 to be ready
Inference service chaiml-gy-exp12-sft-gro-87898-v1 ready after 140.52480053901672s
Pipeline stage MKMLDeployer completed in 141.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1393861770629883s
Received healthy response to inference request in 1.9366700649261475s
Received healthy response to inference request in 1.7322375774383545s
Received healthy response to inference request in 1.4717581272125244s
Received healthy response to inference request in 1.5597107410430908s
5 requests
0 failed requests
5th percentile: 1.4893486499786377
10th percentile: 1.506939172744751
20th percentile: 1.5421202182769775
30th percentile: 1.5942161083221436
40th percentile: 1.663226842880249
50th percentile: 1.7322375774383545
60th percentile: 1.8140105724334716
70th percentile: 1.8957835674285888
80th percentile: 1.9772132873535158
90th percentile: 2.058299732208252
95th percentile: 2.09884295463562
99th percentile: 2.131277532577515
mean time: 1.7679525375366212
Pipeline stage StressChecker completed in 10.45s
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 0.76s
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 0.81s
Shutdown handler de-registered
chaiml-gy-exp12-sft-gro_87898_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 3079.21s
Shutdown handler de-registered
chaiml-gy-exp12-sft-gro_87898_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp12-sft-gro_87898_v1 status is now torndown due to DeploymentManager action