developer_uid: NischayDnk
submission_id: chaiml-nis-gemma27b-pro_85310_v2
model_name: chaiml-nis-gemma27b-pro_85310_v2
model_group: ChaiML/nis-gemma27B-proj
status: torndown
timestamp: 2025-03-28T23:03:23+00:00
num_battles: 7228
num_wins: 3372
celo_rating: 1253.49
family_friendly_score: 0.5571999999999999
family_friendly_standard_error: 0.007024644617345421
submission_type: basic
model_repo: ChaiML/nis-gemma27B-proj1-exp1-del5ktop-1
model_architecture: Gemma2ForCausalLM
model_num_parameters: 28731935232.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.27560462858893847, 'latency_mean': 3.628323551416397, 'latency_p50': 3.6172021627426147, 'latency_p90': 3.9988622188568117}, {'batch_size': 2, 'throughput': 0.4291404146844648, 'latency_mean': 4.642519124746323, 'latency_p50': 4.623069882392883, 'latency_p90': 5.1533358812332155}, {'batch_size': 3, 'throughput': 0.5356670619015151, 'latency_mean': 5.575024752616883, 'latency_p50': 5.595797181129456, 'latency_p90': 6.140654516220093}, {'batch_size': 5, 'throughput': 0.6924866257590774, 'latency_mean': 7.177428728342056, 'latency_p50': 7.170868277549744, 'latency_p90': 8.087727570533753}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-nis-gemma27b-pro_85310_v2
is_internal_developer: False
language_model: ChaiML/nis-gemma27B-proj1-exp1-del5ktop-1
model_size: 29B
ranking_group: single
throughput_3p7s: 0.29
us_pacific_date: 2025-03-28
win_ratio: 0.46651909241837297
generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', '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-nis-gemma27b-pro-85310-v2-mkmlizer
Waiting for job on chaiml-nis-gemma27b-pro-85310-v2-mkmlizer to finish
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: ║ _____ __ __ ║
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: ║ /___/ ║
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: ║ ║
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: ║ Version: 0.12.8 ║
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: ║ https://mk1.ai ║
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: ║ ║
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: ║ belonging to: ║
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: ║ ║
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: ║ Chai Research Corp. ║
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: ║ ║
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: Downloaded to shared memory in 76.106s
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3d_nt7bg, device:0
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: quantized model in 68.725s
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: Processed model ChaiML/nis-gemma27B-proj1-exp1-del5ktop-1 in 144.831s
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nis-gemma27b-pro-85310-v2
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nis-gemma27b-pro-85310-v2/config.json
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nis-gemma27b-pro-85310-v2/special_tokens_map.json
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nis-gemma27b-pro-85310-v2/tokenizer_config.json
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nis-gemma27b-pro-85310-v2/tokenizer.json
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-nis-gemma27b-pro-85310-v2/tokenizer.model
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-nis-gemma27b-pro-85310-v2/flywheel_model.2.safetensors
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nis-gemma27b-pro-85310-v2/flywheel_model.0.safetensors
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-nis-gemma27b-pro-85310-v2/flywheel_model.1.safetensors
chaiml-nis-gemma27b-pro-85310-v2-mkmlizer: Loading 0: 0%| | 0/508 [00:00<?, ?it/s] Loading 0: 1%| | 4/508 [00:00<00:13, 38.40it/s] Loading 0: 2%|▏ | 12/508 [00:00<00:11, 43.15it/s] Loading 0: 3%|▎ | 17/508 [00:00<00:14, 32.96it/s] Loading 0: 5%|▌ | 27/508 [00:00<00:10, 44.36it/s] Loading 0: 6%|▋ | 32/508 [00:00<00:16, 29.11it/s] Loading 0: 7%|▋ | 38/508 [00:01<00:14, 31.75it/s] Loading 0: 9%|▉ | 47/508 [00:01<00:11, 39.29it/s] Loading 0: 10%|█ | 52/508 [00:01<00:11, 40.81it/s] Loading 0: 11%|█▏ | 58/508 [00:01<00:11, 39.77it/s] Loading 0: 12%|█▏ | 63/508 [00:01<00:10, 41.34it/s] Loading 0: 13%|█▎ | 68/508 [00:01<00:11, 37.88it/s] Loading 0: 14%|█▍ | 73/508 [00:02<00:15, 27.87it/s] Loading 0: 15%|█▌ | 78/508 [00:02<00:14, 29.67it/s] Loading 0: 16%|█▌ | 82/508 [00:02<00:14, 30.12it/s] Loading 0: 17%|█▋ | 88/508 [00:02<00:12, 33.21it/s] Loading 0: 19%|█▉ | 97/508 [00:02<00:10, 40.13it/s] Loading 0: 20%|██ | 102/508 [00:02<00:09, 41.60it/s] Loading 0: 21%|██▏ | 108/508 [00:02<00:10, 39.35it/s] Loading 0: 22%|██▏ | 113/508 [00:03<00:09, 41.31it/s] Loading 0: 23%|██▎ | 118/508 [00:03<00:11, 32.69it/s] Loading 0: 24%|██▍ | 124/508 [00:03<00:10, 37.91it/s] Loading 0: 25%|██▌ | 129/508 [00:03<00:09, 39.48it/s] Loading 0: 27%|██▋ | 135/508 [00:03<00:09, 38.56it/s] Loading 0: 28%|██▊ | 140/508 [00:03<00:09, 40.42it/s] Loading 0: 29%|██▊ | 146/508 [00:03<00:09, 38.92it/s] Loading 0: 30%|██▉ | 151/508 [00:04<00:08, 40.76it/s] Loading 0: 31%|███ | 157/508 [00:04<00:08, 39.74it/s] Loading 0: 32%|███▏ | 162/508 [00:04<00:08, 41.39it/s] Loading 0: 33%|███▎ | 168/508 [00:04<00:07, 43.50it/s] Loading 0: 34%|███▍ | 173/508 [00:04<00:11, 28.30it/s] Loading 0: 35%|███▌ | 179/508 [00:04<00:09, 33.53it/s] Loading 0: 36%|███▌ | 184/508 [00:05<00:08, 36.32it/s] Loading 0: 37%|███▋ | 190/508 [00:05<00:08, 37.06it/s] Loading 0: 38%|███▊ | 195/508 [00:19<04:16, 1.22it/s] Loading 0: 39%|███▉ | 199/508 [00:19<03:14, 1.59it/s] Loading 0: 40%|███▉ | 203/508 [00:20<02:30, 2.03it/s] Loading 0: 42%|████▏ | 211/508 [00:20<01:27, 3.41it/s] Loading 0: 43%|████▎ | 216/508 [00:20<01:05, 4.43it/s] Loading 0: 43%|████▎ | 220/508 [00:20<00:51, 5.61it/s] Loading 0: 44%|████▍ | 224/508 [00:20<00:39, 7.16it/s] Loading 0: 46%|████▌ | 232/508 [00:20<00:24, 11.36it/s] Loading 0: 47%|████▋ | 237/508 [00:21<00:20, 13.54it/s] Loading 0: 48%|████▊ | 245/508 [00:21<00:14, 18.65it/s] Loading 0: 49%|████▉ | 250/508 [00:21<00:11, 22.04it/s] Loading 0: 50%|█████ | 255/508 [00:21<00:10, 23.90it/s] Loading 0: 51%|█████ | 260/508 [00:21<00:09, 26.07it/s] Loading 0: 52%|█████▏ | 264/508 [00:21<00:10, 23.40it/s] Loading 0: 53%|█████▎ | 268/508 [00:21<00:09, 26.07it/s] Loading 0: 54%|█████▍ | 276/508 [00:22<00:06, 33.88it/s] Loading 0: 55%|█████▌ | 281/508 [00:22<00:07, 32.19it/s] Loading 0: 57%|█████▋ | 289/508 [00:22<00:05, 37.92it/s] Loading 0: 58%|█████▊ | 294/508 [00:22<00:05, 39.93it/s] Loading 0: 59%|█████▉ | 300/508 [00:22<00:05, 39.21it/s] Loading 0: 60%|██████ | 305/508 [00:22<00:04, 41.33it/s] Loading 0: 61%|██████ | 311/508 [00:22<00:04, 45.52it/s] Loading 0: 62%|██████▏ | 316/508 [00:23<00:06, 29.08it/s] Loading 0: 63%|██████▎ | 322/508 [00:23<00:05, 34.61it/s] Loading 0: 64%|██████▍ | 327/508 [00:23<00:04, 37.16it/s] Loading 0: 66%|██████▌ | 333/508 [00:23<00:04, 36.80it/s] Loading 0: 67%|██████▋ | 338/508 [00:23<00:04, 39.34it/s] Loading 0: 68%|██████▊ | 344/508 [00:23<00:04, 39.07it/s] Loading 0: 69%|██████▊ | 349/508 [00:23<00:03, 41.08it/s] Loading 0: 70%|██████▉ | 354/508 [00:24<00:04, 37.75it/s] Loading 0: 71%|███████ | 359/508 [00:24<00:04, 31.06it/s] Loading 0: 71%|███████▏ | 363/508 [00:24<00:04, 32.53it/s] Loading 0: 72%|███████▏ | 367/508 [00:24<00:04, 34.15it/s] Loading 0: 74%|███████▍ | 375/508 [00:24<00:03, 41.65it/s] Loading 0: 75%|███████▍ | 380/508 [00:24<00:03, 36.37it/s] Loading 0: 76%|███████▋ | 388/508 [00:25<00:02, 40.44it/s] Loading 0: 77%|███████▋ | 393/508 [00:25<00:02, 42.08it/s] Loading 0: 78%|███████▊ | 398/508 [00:25<00:02, 38.19it/s] Loading 0: 79%|███████▉ | 403/508 [00:25<00:02, 37.31it/s] Loading 0: 80%|████████ | 407/508 [00:25<00:03, 28.99it/s] Loading 0: 81%|████████ | 411/508 [00:25<00:03, 31.06it/s] Loading 0: 82%|████████▏ | 419/508 [00:25<00:02, 37.92it/s] Loading 0: 83%|████████▎ | 424/508 [00:26<00:02, 34.33it/s] Loading 0: 85%|████████▌ | 432/508 [00:26<00:01, 38.75it/s] Loading 0: 86%|████████▌ | 437/508 [00:26<00:01, 40.57it/s] Loading 0: 87%|████████▋ | 443/508 [00:26<00:01, 38.78it/s] Loading 0: 88%|████████▊ | 448/508 [00:26<00:01, 40.94it/s] Loading 0: 89%|████████▉ | 451/508 [00:40<00:01, 40.94it/s] Loading 0: 89%|████████▉ | 452/508 [00:40<00:46, 1.20it/s] Loading 0: 90%|████████▉ | 456/508 [00:40<00:33, 1.58it/s] Loading 0: 91%|█████████ | 460/508 [00:41<00:23, 2.04it/s] Loading 0: 92%|█████████▏| 466/508 [00:41<00:13, 3.13it/s] Loading 0: 93%|█████████▎| 474/508 [00:41<00:06, 5.08it/s] Loading 0: 94%|█████████▍| 479/508 [00:41<00:04, 6.51it/s] Loading 0: 96%|█████████▌| 487/508 [00:41<00:02, 9.68it/s] Loading 0: 97%|█████████▋| 492/508 [00:41<00:01, 12.13it/s] Loading 0: 98%|█████████▊| 497/508 [00:41<00:00, 14.58it/s] Loading 0: 99%|█████████▉| 502/508 [00:42<00:00, 16.02it/s] Loading 0: 100%|█████████▉| 506/508 [00:42<00:00, 18.45it/s]
Job chaiml-nis-gemma27b-pro-85310-v2-mkmlizer completed after 186.38s with status: succeeded
Stopping job with name chaiml-nis-gemma27b-pro-85310-v2-mkmlizer
Pipeline stage MKMLizer completed in 186.85s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.30s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nis-gemma27b-pro-85310-v2
Waiting for inference service chaiml-nis-gemma27b-pro-85310-v2 to be ready
Inference service chaiml-nis-gemma27b-pro-85310-v2 ready after 110.81270360946655s
Pipeline stage MKMLDeployer completed in 111.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.6672985553741455s
Received healthy response to inference request in 3.2218408584594727s
Received healthy response to inference request in 3.550349235534668s
Received healthy response to inference request in 3.4101107120513916s
Received healthy response to inference request in 3.291957378387451s
5 requests
0 failed requests
5th percentile: 3.2358641624450684
10th percentile: 3.249887466430664
20th percentile: 3.2779340744018555
30th percentile: 3.315588045120239
40th percentile: 3.3628493785858153
50th percentile: 3.4101107120513916
60th percentile: 3.466206121444702
70th percentile: 3.522301530838013
80th percentile: 3.5737390995025633
90th percentile: 3.6205188274383544
95th percentile: 3.64390869140625
99th percentile: 3.6626205825805664
mean time: 3.428311347961426
Pipeline stage StressChecker completed in 18.37s
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 0.68s
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 0.75s
Shutdown handler de-registered
chaiml-nis-gemma27b-pro_85310_v2 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 6017.43s
Shutdown handler de-registered
chaiml-nis-gemma27b-pro_85310_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-nis-gemma27b-pro_85310_v2 status is now torndown due to DeploymentManager action