chaiml-gy-exp28-sft-gy-_41285

developer_uid: bogoconic1

submission_id: chaiml-gy-exp28-sft-gy-_41285_v1

model_name: chaiml-gy-exp28-sft-gy-_41285_v1

model_group: ChaiML/gy-exp28-sft-gy-e

status: torndown

timestamp: 2025-06-27T14:46:03+00:00

num_battles: 8705

num_wins: 4526

celo_rating: 1297.58

family_friendly_score: 0.5287999999999999

family_friendly_standard_error: 0.007059328013345179

submission_type: basic

model_repo: ChaiML/gy-exp28-sft-gy-exp24sftdata-rmv-trunc-history-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': 0.5838384628100133, 'latency_mean': 1.7126995134353638, 'latency_p50': 1.7179069519042969, 'latency_p90': 1.8838853359222412}, {'batch_size': 3, 'throughput': 1.0515875179310694, 'latency_mean': 2.8432553279399873, 'latency_p50': 2.8343379497528076, 'latency_p90': 3.104262113571167}, {'batch_size': 5, 'throughput': 1.2491995252307706, 'latency_mean': 3.9891022753715517, 'latency_p50': 4.004368185997009, 'latency_p90': 4.436050271987915}, {'batch_size': 6, 'throughput': 1.3197015381227424, 'latency_mean': 4.527930645942688, 'latency_p50': 4.5223692655563354, 'latency_p90': 5.037262654304504}, {'batch_size': 8, 'throughput': 1.365460489619, 'latency_mean': 5.829671763181686, 'latency_p50': 5.817296028137207, 'latency_p90': 6.507918047904968}, {'batch_size': 10, 'throughput': 1.4102675824929718, 'latency_mean': 7.043715672492981, 'latency_p50': 7.129202723503113, 'latency_p90': 7.9579321384429935}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp28-sft-gy-_41285_v1

is_internal_developer: True

language_model: ChaiML/gy-exp28-sft-gy-exp24sftdata-rmv-trunc-history-ep2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.21

us_pacific_date: 2025-06-27

win_ratio: 0.5199310740953476

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': ['\n', '<|im_start|>', '<|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-exp28-sft-gy-41285-v1-mkmlizer
Waiting for job on chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer to finish
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: Downloaded to shared memory in 43.191s
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: Checking if ChaiML/gy-exp28-sft-gy-exp24sftdata-rmv-trunc-history-ep2 already exists in ChaiML
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplxn7vcc6, device:0
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: quantized model in 31.577s
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: Processed model ChaiML/gy-exp28-sft-gy-exp24sftdata-rmv-trunc-history-ep2 in 74.768s
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp28-sft-gy-41285-v1/config.json
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp28-sft-gy-41285-v1/special_tokens_map.json
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp28-sft-gy-41285-v1/tokenizer_config.json
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp28-sft-gy-41285-v1/tokenizer.json
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp28-sft-gy-41285-v1/flywheel_model.0.safetensors
chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.90it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 46.06it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 46.57it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 36.16it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 44.99it/s]
Loading 0:  10%|▉         | 36/363 [00:00<00:07, 46.30it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:08, 37.27it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:07, 44.39it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:07, 43.49it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:06, 47.44it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:11, 26.69it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:09, 31.70it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 33.17it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 35.40it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 37.40it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 33.33it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 40.92it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 41.54it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 43.59it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 35.95it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 35.39it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 42.53it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 41.97it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 42.13it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 43.51it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 26.12it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 26.22it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 33.60it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 35.44it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.06it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 39.42it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 33.70it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 40.82it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 41.30it/s]
Loading 0:  53%|█████▎    | 193/363 [00:05<00:04, 41.92it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 43.39it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 35.41it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 42.68it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 41.45it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 42.63it/s]
Loading 0:  62%|██████▏   | 225/363 [00:06<00:05, 25.54it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 27.89it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 34.83it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 35.27it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:03, 36.07it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 38.47it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 33.84it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 41.04it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 41.31it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 41.82it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 43.18it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 35.47it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 42.62it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 42.18it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 42.61it/s]
Loading 0:  84%|████████▍ | 306/363 [00:08<00:02, 22.01it/s]
Loading 0:  85%|████████▌ | 310/363 [00:08<00:02, 23.17it/s]
Loading 0:  87%|████████▋ | 314/363 [00:08<00:01, 25.48it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 31.04it/s]
Loading 0:  90%|████████▉ | 325/363 [00:08<00:01, 34.86it/s]
Loading 0:  91%|█████████ | 330/363 [00:09<00:01, 31.92it/s]
Loading 0:  93%|█████████▎| 337/363 [00:09<00:00, 39.97it/s]
Loading 0:  94%|█████████▍| 342/363 [00:09<00:00, 40.58it/s]
Loading 0:  96%|█████████▌| 347/363 [00:09<00:00, 41.87it/s]
Loading 0:  97%|█████████▋| 352/363 [00:09<00:00, 42.45it/s]
Loading 0:  98%|█████████▊| 357/363 [00:09<00:00, 36.09it/s]
                                                            
Job chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer completed after 94.05s with status: succeeded
Stopping job with name chaiml-gy-exp28-sft-gy-41285-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.55s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.60s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp28-sft-gy-41285-v1
Waiting for inference service chaiml-gy-exp28-sft-gy-41285-v1 to be ready
Inference service chaiml-gy-exp28-sft-gy-41285-v1 ready after 151.24770665168762s
Pipeline stage MKMLDeployer completed in 151.82s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.266230583190918s
Received healthy response to inference request in 1.694817304611206s
Received healthy response to inference request in 2.0700180530548096s
Received healthy response to inference request in 1.632028579711914s
Received healthy response to inference request in 1.7093980312347412s
5 requests
0 failed requests
5th percentile: 1.6445863246917725
10th percentile: 1.6571440696716309
20th percentile: 1.6822595596313477
30th percentile: 1.6977334499359131
40th percentile: 1.703565740585327
50th percentile: 1.7093980312347412
60th percentile: 1.8536460399627686
70th percentile: 1.997894048690796
80th percentile: 2.1092605590820312
90th percentile: 2.1877455711364746
95th percentile: 2.2269880771636963
99th percentile: 2.2583820819854736
mean time: 1.8744985103607177
Pipeline stage StressChecker completed in 10.58s
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 0.70s
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 0.67s
Shutdown handler de-registered
chaiml-gy-exp28-sft-gy-_41285_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 0.12s
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-gy-exp28-sft-gy-41285-v1-profiler
Waiting for inference service chaiml-gy-exp28-sft-gy-41285-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 4784.00s
Shutdown handler de-registered
chaiml-gy-exp28-sft-gy-_41285_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp28-sft-gy-_41285_v1 status is now torndown due to DeploymentManager action