chaiml-gy-exp49-sft-gy-_46647

developer_uid: bogoconic1

submission_id: chaiml-gy-exp49-sft-gy-_46647_v1

model_name: chaiml-gy-exp49-sft-gy-_46647_v1

model_group: ChaiML/gy-exp49-sft-gy-d

status: torndown

timestamp: 2025-07-01T06:12:31+00:00

num_battles: 9364

num_wins: 4160

celo_rating: 1249.44

family_friendly_score: 0.6308

family_friendly_standard_error: 0.006824827616870627

submission_type: basic

model_repo: ChaiML/gy-exp49-sft-gy-datamix-v1-head1000-grok-history-prefill5x5-gen20x20-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': 0.586786003256825, 'latency_mean': 1.704030363559723, 'latency_p50': 1.700717806816101, 'latency_p90': 1.8656599521636963}, {'batch_size': 3, 'throughput': 1.046231172310938, 'latency_mean': 2.861285345554352, 'latency_p50': 2.8400176763534546, 'latency_p90': 3.1308356523513794}, {'batch_size': 5, 'throughput': 1.2599911630673297, 'latency_mean': 3.9528264713287355, 'latency_p50': 3.9604196548461914, 'latency_p90': 4.408802223205567}, {'batch_size': 6, 'throughput': 1.302608910763803, 'latency_mean': 4.578553997278213, 'latency_p50': 4.578714609146118, 'latency_p90': 5.266686129570007}, {'batch_size': 8, 'throughput': 1.3555437876051097, 'latency_mean': 5.85054552435875, 'latency_p50': 5.893072128295898, 'latency_p90': 6.587305688858033}, {'batch_size': 10, 'throughput': 1.404756505412113, 'latency_mean': 7.072749503850937, 'latency_p50': 7.065028786659241, 'latency_p90': 7.9549274921417235}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp49-sft-gy-_46647_v1

is_internal_developer: True

language_model: ChaiML/gy-exp49-sft-gy-datamix-v1-head1000-grok-history-prefill5x5-gen20x20-ep2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.23

us_pacific_date: 2025-06-30

win_ratio: 0.4442545920546775

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_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-gy-exp49-sft-gy-46647-v1-mkmlizer
Waiting for job on chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer to finish
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: Downloaded to shared memory in 43.052s
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: Checking if ChaiML/gy-exp49-sft-gy-datamix-v1-head1000-grok-history-prefill5x5-gen20x20-ep2 already exists in ChaiML
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpq86l8xwx, device:0
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: quantized model in 31.583s
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: Processed model ChaiML/gy-exp49-sft-gy-datamix-v1-head1000-grok-history-prefill5x5-gen20x20-ep2 in 74.636s
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp49-sft-gy-46647-v1
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp49-sft-gy-46647-v1/config.json
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp49-sft-gy-46647-v1/special_tokens_map.json
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp49-sft-gy-46647-v1/tokenizer_config.json
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp49-sft-gy-46647-v1/tokenizer.json
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp49-sft-gy-46647-v1/flywheel_model.0.safetensors
chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.35it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 48.43it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 46.03it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 34.84it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 43.52it/s]
Loading 0:  10%|▉         | 35/363 [00:00<00:07, 43.11it/s]
Loading 0:  11%|█         | 40/363 [00:00<00:07, 43.26it/s]
Loading 0:  12%|█▏        | 45/363 [00:01<00:07, 45.07it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 36.74it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:07, 42.15it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:10, 30.03it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 29.90it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 36.00it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 36.90it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 38.59it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 40.89it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 34.29it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 41.18it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 40.25it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:06, 42.24it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 35.72it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 35.08it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 41.76it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 41.33it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 40.18it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 41.47it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 25.37it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 25.91it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 32.98it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:06, 32.97it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 35.90it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:05, 36.70it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:05, 36.89it/s]
Loading 0:  49%|████▉     | 178/363 [00:04<00:05, 35.67it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 37.93it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:04, 36.74it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 38.73it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:04, 37.34it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 39.87it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:03, 40.16it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 39.90it/s]
Loading 0:  60%|█████▉    | 216/363 [00:05<00:03, 41.47it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 43.04it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:05, 25.63it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:05, 25.83it/s]
Loading 0:  65%|██████▍   | 235/363 [00:06<00:04, 30.00it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:04, 29.11it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 36.06it/s]
Loading 0:  69%|██████▉   | 251/363 [00:06<00:02, 37.48it/s]
Loading 0:  71%|███████   | 256/363 [00:07<00:02, 38.06it/s]
Loading 0:  72%|███████▏  | 261/363 [00:07<00:02, 40.33it/s]
Loading 0:  73%|███████▎  | 266/363 [00:07<00:02, 34.04it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 40.34it/s]
Loading 0:  77%|███████▋  | 278/363 [00:07<00:02, 39.46it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:02, 39.12it/s]
Loading 0:  79%|███████▉  | 288/363 [00:07<00:01, 40.44it/s]
Loading 0:  81%|████████  | 293/363 [00:08<00:02, 33.59it/s]
Loading 0:  82%|████████▏ | 299/363 [00:08<00:01, 38.03it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 21.22it/s]
Loading 0:  85%|████████▍ | 308/363 [00:08<00:02, 23.32it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:02, 23.92it/s]
Loading 0:  88%|████████▊ | 319/363 [00:09<00:01, 32.17it/s]
Loading 0:  89%|████████▉ | 324/363 [00:09<00:01, 34.76it/s]
Loading 0:  91%|█████████ | 329/363 [00:09<00:00, 37.02it/s]
Loading 0:  92%|█████████▏| 334/363 [00:09<00:00, 39.61it/s]
Loading 0:  93%|█████████▎| 339/363 [00:09<00:00, 34.34it/s]
Loading 0:  95%|█████████▌| 346/363 [00:09<00:00, 41.73it/s]
Loading 0:  97%|█████████▋| 351/363 [00:09<00:00, 41.46it/s]
Loading 0:  98%|█████████▊| 356/363 [00:09<00:00, 42.06it/s]
Loading 0:  99%|█████████▉| 361/363 [00:10<00:00, 43.30it/s]
                                                            
Job chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer completed after 108.44s with status: succeeded
Stopping job with name chaiml-gy-exp49-sft-gy-46647-v1-mkmlizer
Pipeline stage MKMLizer completed in 110.01s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.28s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp49-sft-gy-46647-v1
Waiting for inference service chaiml-gy-exp49-sft-gy-46647-v1 to be ready
Inference service chaiml-gy-exp49-sft-gy-46647-v1 ready after 211.07358479499817s
Pipeline stage MKMLDeployer completed in 211.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2632625102996826s
Received healthy response to inference request in 1.8215508460998535s
Received healthy response to inference request in 2.0692977905273438s
Received healthy response to inference request in 1.4193828105926514s
Received healthy response to inference request in 1.4879536628723145s
5 requests
0 failed requests
5th percentile: 1.433096981048584
10th percentile: 1.4468111515045166
20th percentile: 1.4742394924163817
30th percentile: 1.5546730995178222
40th percentile: 1.6881119728088378
50th percentile: 1.8215508460998535
60th percentile: 1.9206496238708497
70th percentile: 2.019748401641846
80th percentile: 2.1080907344818116
90th percentile: 2.185676622390747
95th percentile: 2.2244695663452148
99th percentile: 2.255503921508789
mean time: 1.8122895240783692
Pipeline stage StressChecker completed in 11.90s
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 1.23s
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 1.42s
Shutdown handler de-registered
chaiml-gy-exp49-sft-gy-_46647_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 3008.99s
Shutdown handler de-registered
chaiml-gy-exp49-sft-gy-_46647_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp49-sft-gy-_46647_v1 status is now torndown due to DeploymentManager action