developer_uid: NischayDnk
submission_id: chaiml-exp401-gemma28b-_21898_v1
model_name: chaiml-exp401-gemma28b-_21898_v1
model_group: ChaiML/exp401-gemma28b-d
status: inactive
timestamp: 2025-04-14T23:15:27+00:00
num_battles: 7121
num_wins: 3420
celo_rating: 1273.83
family_friendly_score: 0.585
family_friendly_standard_error: 0.00696814178960216
submission_type: basic
model_repo: ChaiML/exp401-gemma28b-dpo-datav1gemmasft
model_architecture: Gemma2ForCausalLM
model_num_parameters: 28731935232.0
best_of: 4
max_input_tokens: 768
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.30133461684337964, 'latency_mean': 3.3185057985782622, 'latency_p50': 3.305203914642334, 'latency_p90': 3.693068504333496}, {'batch_size': 2, 'throughput': 0.48912731213957, 'latency_mean': 4.07512231707573, 'latency_p50': 4.09472930431366, 'latency_p90': 4.524282908439636}, {'batch_size': 3, 'throughput': 0.6449147148999065, 'latency_mean': 4.6411027538776395, 'latency_p50': 4.629757285118103, 'latency_p90': 5.1302856445312495}, {'batch_size': 4, 'throughput': 0.7677216997124039, 'latency_mean': 5.181579685211181, 'latency_p50': 5.231895446777344, 'latency_p90': 5.63352210521698}, {'batch_size': 5, 'throughput': 0.8680569843403988, 'latency_mean': 5.718540252447128, 'latency_p50': 5.757474660873413, 'latency_p90': 6.422871994972229}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-exp401-gemma28b-_21898_v1
is_internal_developer: True
language_model: ChaiML/exp401-gemma28b-dpo-datav1gemmasft
model_size: 29B
ranking_group: single
throughput_3p7s: 0.41
us_pacific_date: 2025-04-14
win_ratio: 0.48026962505266113
generation_params: {'temperature': 0.5, 'top_p': 0.9, 'min_p': 0.04, 'top_k': 80, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, 'stopping_words': ['\n', '<|im_end|>', '<|im_start|>'], 'max_input_tokens': 768, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{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-exp401-gemma28b-21898-v1-mkmlizer
Waiting for job on chaiml-exp401-gemma28b-21898-v1-mkmlizer to finish
chaiml-exp401-gemma28b-21898-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-exp401-gemma28b-21898-v1-mkmlizer: ║ _____ __ __ ║
chaiml-exp401-gemma28b-21898-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-exp401-gemma28b-21898-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-exp401-gemma28b-21898-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-exp401-gemma28b-21898-v1-mkmlizer: ║ /___/ ║
chaiml-exp401-gemma28b-21898-v1-mkmlizer: ║ ║
chaiml-exp401-gemma28b-21898-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-exp401-gemma28b-21898-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-exp401-gemma28b-21898-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-exp401-gemma28b-21898-v1-mkmlizer: ║ ║
chaiml-exp401-gemma28b-21898-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-exp401-gemma28b-21898-v1-mkmlizer: ║ belonging to: ║
chaiml-exp401-gemma28b-21898-v1-mkmlizer: ║ ║
chaiml-exp401-gemma28b-21898-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-exp401-gemma28b-21898-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-exp401-gemma28b-21898-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-exp401-gemma28b-21898-v1-mkmlizer: ║ ║
chaiml-exp401-gemma28b-21898-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-exp401-gemma28b-21898-v1-mkmlizer: Downloaded to shared memory in 102.908s
chaiml-exp401-gemma28b-21898-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6qed6_u8, device:0
chaiml-exp401-gemma28b-21898-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-exp401-gemma28b-21898-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-exp401-gemma28b-21898-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-exp401-gemma28b-21898-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-exp401-gemma28b-21898-v1
chaiml-exp401-gemma28b-21898-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-exp401-gemma28b-21898-v1/config.json
chaiml-exp401-gemma28b-21898-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-exp401-gemma28b-21898-v1/special_tokens_map.json
chaiml-exp401-gemma28b-21898-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-exp401-gemma28b-21898-v1/tokenizer_config.json
chaiml-exp401-gemma28b-21898-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-exp401-gemma28b-21898-v1/tokenizer.model
chaiml-exp401-gemma28b-21898-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-exp401-gemma28b-21898-v1/tokenizer.json
chaiml-exp401-gemma28b-21898-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-exp401-gemma28b-21898-v1/flywheel_model.2.safetensors
chaiml-exp401-gemma28b-21898-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-exp401-gemma28b-21898-v1/flywheel_model.0.safetensors
chaiml-exp401-gemma28b-21898-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-exp401-gemma28b-21898-v1/flywheel_model.1.safetensors
chaiml-exp401-gemma28b-21898-v1-mkmlizer: Loading 0: 0%| | 0/508 [00:00<?, ?it/s] Loading 0: 1%| | 5/508 [00:00<00:14, 34.00it/s] Loading 0: 2%|▏ | 12/508 [00:00<00:10, 49.28it/s] Loading 0: 4%|▎ | 18/508 [00:00<00:12, 39.01it/s] Loading 0: 5%|▌ | 27/508 [00:00<00:10, 47.87it/s] Loading 0: 6%|▋ | 33/508 [00:00<00:14, 33.10it/s] Loading 0: 7%|▋ | 38/508 [00:01<00:14, 33.49it/s] Loading 0: 9%|▉ | 47/508 [00:01<00:11, 40.52it/s] Loading 0: 11%|█ | 54/508 [00:01<00:09, 46.34it/s] Loading 0: 12%|█▏ | 60/508 [00:01<00:11, 38.37it/s] Loading 0: 13%|█▎ | 68/508 [00:01<00:10, 42.67it/s] Loading 0: 14%|█▍ | 73/508 [00:01<00:13, 32.89it/s] Loading 0: 15%|█▌ | 78/508 [00:02<00:12, 34.29it/s] Loading 0: 16%|█▌ | 82/508 [00:02<00:12, 33.86it/s] Loading 0: 17%|█▋ | 88/508 [00:02<00:11, 35.88it/s] Loading 0: 19%|█▉ | 97/508 [00:02<00:09, 41.80it/s] Loading 0: 20%|██ | 102/508 [00:02<00:09, 43.03it/s] Loading 0: 21%|██▏ | 108/508 [00:02<00:09, 40.79it/s] Loading 0: 22%|██▏ | 113/508 [00:02<00:09, 42.06it/s] Loading 0: 23%|██▎ | 118/508 [00:03<00:12, 32.33it/s] Loading 0: 25%|██▍ | 125/508 [00:03<00:10, 36.28it/s] Loading 0: 26%|██▌ | 133/508 [00:03<00:08, 42.33it/s] Loading 0: 27%|██▋ | 138/508 [00:03<00:09, 38.56it/s] Loading 0: 29%|██▊ | 146/508 [00:03<00:08, 43.32it/s] Loading 0: 30%|██▉ | 152/508 [00:03<00:07, 46.75it/s] Loading 0: 31%|███ | 157/508 [00:03<00:08, 42.94it/s] Loading 0: 32%|███▏ | 163/508 [00:04<00:07, 46.71it/s] Loading 0: 33%|███▎ | 168/508 [00:04<00:07, 45.90it/s] Loading 0: 34%|███▍ | 173/508 [00:04<00:11, 30.20it/s] Loading 0: 35%|███▌ | 180/508 [00:04<00:09, 34.65it/s] Loading 0: 37%|███▋ | 188/508 [00:04<00:07, 40.86it/s] Loading 0: 38%|███▊ | 193/508 [00:18<03:43, 1.41it/s] Loading 0: 39%|███▉ | 199/508 [00:18<02:35, 1.98it/s] Loading 0: 40%|████ | 204/508 [00:19<01:59, 2.55it/s] Loading 0: 42%|████▏ | 211/508 [00:19<01:18, 3.77it/s] Loading 0: 43%|████▎ | 216/508 [00:19<01:01, 4.78it/s] Loading 0: 44%|████▍ | 223/508 [00:19<00:41, 6.90it/s] Loading 0: 45%|████▌ | 229/508 [00:19<00:29, 9.33it/s] Loading 0: 46%|████▌ | 234/508 [00:20<00:24, 11.39it/s] Loading 0: 47%|████▋ | 241/508 [00:20<00:16, 15.89it/s] Loading 0: 48%|████▊ | 246/508 [00:20<00:14, 17.96it/s] Loading 0: 50%|█████ | 254/508 [00:20<00:10, 24.40it/s] Loading 0: 51%|█████ | 259/508 [00:20<00:09, 26.38it/s] Loading 0: 52%|█████▏ | 264/508 [00:20<00:10, 23.29it/s] Loading 0: 53%|█████▎ | 269/508 [00:21<00:09, 25.56it/s] Loading 0: 55%|█████▍ | 278/508 [00:21<00:06, 33.36it/s] Loading 0: 56%|█████▌ | 284/508 [00:21<00:05, 38.03it/s] Loading 0: 57%|█████▋ | 289/508 [00:21<00:06, 36.36it/s] Loading 0: 58%|█████▊ | 295/508 [00:21<00:05, 41.02it/s] Loading 0: 59%|█████▉ | 300/508 [00:21<00:05, 38.60it/s] Loading 0: 60%|██████ | 305/508 [00:21<00:04, 41.16it/s] Loading 0: 61%|██████ | 311/508 [00:21<00:04, 45.20it/s] Loading 0: 62%|██████▏ | 316/508 [00:22<00:06, 28.44it/s] Loading 0: 63%|██████▎ | 322/508 [00:22<00:05, 33.37it/s] Loading 0: 64%|██████▍ | 327/508 [00:22<00:05, 35.47it/s] Loading 0: 66%|██████▌ | 333/508 [00:22<00:04, 35.74it/s] Loading 0: 67%|██████▋ | 338/508 [00:22<00:04, 37.63it/s] Loading 0: 68%|██████▊ | 344/508 [00:22<00:04, 36.84it/s] Loading 0: 69%|██████▊ | 348/508 [00:23<00:04, 36.85it/s] Loading 0: 70%|██████▉ | 354/508 [00:23<00:04, 37.43it/s] Loading 0: 71%|███████ | 359/508 [00:23<00:05, 28.52it/s] Loading 0: 71%|███████▏ | 363/508 [00:23<00:04, 30.16it/s] Loading 0: 72%|███████▏ | 367/508 [00:23<00:04, 32.07it/s] Loading 0: 74%|███████▍ | 375/508 [00:23<00:03, 39.50it/s] Loading 0: 75%|███████▍ | 380/508 [00:24<00:03, 34.90it/s] Loading 0: 76%|███████▋ | 388/508 [00:24<00:02, 40.19it/s] Loading 0: 77%|███████▋ | 393/508 [00:24<00:02, 41.92it/s] Loading 0: 78%|███████▊ | 398/508 [00:24<00:02, 37.79it/s] Loading 0: 79%|███████▉ | 403/508 [00:24<00:02, 37.96it/s] Loading 0: 80%|████████ | 407/508 [00:24<00:03, 28.91it/s] Loading 0: 81%|████████ | 411/508 [00:24<00:03, 31.10it/s] Loading 0: 82%|████████▏ | 419/508 [00:25<00:02, 39.21it/s] Loading 0: 83%|████████▎ | 424/508 [00:25<00:02, 35.07it/s] Loading 0: 85%|████████▌ | 432/508 [00:25<00:01, 38.83it/s] Loading 0: 86%|████████▌ | 437/508 [00:25<00:01, 40.99it/s] Loading 0: 87%|████████▋ | 443/508 [00:25<00:01, 40.98it/s] Loading 0: 88%|████████▊ | 448/508 [00:25<00:01, 42.93it/s] Loading 0: 89%|████████▉ | 453/508 [00:39<00:43, 1.26it/s] Loading 0: 90%|████████▉ | 456/508 [00:39<00:33, 1.54it/s] Loading 0: 91%|█████████ | 461/508 [00:40<00:21, 2.14it/s] Loading 0: 92%|█████████▏| 467/508 [00:40<00:12, 3.20it/s] Loading 0: 94%|█████████▎| 476/508 [00:40<00:05, 5.35it/s] Loading 0: 94%|█████████▍| 480/508 [00:40<00:04, 6.56it/s] Loading 0: 96%|█████████▌| 487/508 [00:40<00:02, 9.40it/s] Loading 0: 97%|█████████▋| 493/508 [00:40<00:01, 12.54it/s] Loading 0: 98%|█████████▊| 498/508 [00:41<00:00, 15.00it/s] Loading 0: 99%|█████████▉| 503/508 [00:41<00:00, 15.58it/s]
Job chaiml-exp401-gemma28b-21898-v1-mkmlizer completed after 197.74s with status: succeeded
Stopping job with name chaiml-exp401-gemma28b-21898-v1-mkmlizer
Pipeline stage MKMLizer completed in 198.22s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-exp401-gemma28b-21898-v1
Waiting for inference service chaiml-exp401-gemma28b-21898-v1 to be ready
Inference service chaiml-exp401-gemma28b-21898-v1 ready after 120.39901185035706s
Pipeline stage MKMLDeployer completed in 120.91s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.63740873336792s
Received healthy response to inference request in 3.0773677825927734s
Received healthy response to inference request in 3.214104413986206s
Received healthy response to inference request in 3.093968629837036s
Received healthy response to inference request in 2.96238112449646s
5 requests
0 failed requests
5th percentile: 2.985378456115723
10th percentile: 3.0083757877349853
20th percentile: 3.0543704509735106
30th percentile: 3.080687952041626
40th percentile: 3.087328290939331
50th percentile: 3.093968629837036
60th percentile: 3.142022943496704
70th percentile: 3.1900772571563722
80th percentile: 3.298765277862549
90th percentile: 3.468087005615234
95th percentile: 3.552747869491577
99th percentile: 3.6204765605926514
mean time: 3.197046136856079
Pipeline stage StressChecker completed in 17.38s
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 0.63s
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 0.69s
Shutdown handler de-registered
chaiml-exp401-gemma28b-_21898_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 3376.37s
Shutdown handler de-registered
chaiml-exp401-gemma28b-_21898_v1 status is now inactive due to auto deactivation removed underperforming models