developer_uid: NischayDnk
submission_id: chaiml-nis-gemma27b-pro_85310_v4
model_name: chaiml-nis-gemma27b-pro_85310_v4
model_group: ChaiML/nis-gemma27B-proj
status: torndown
timestamp: 2025-03-28T23:19:16+00:00
num_battles: 7609
num_wins: 3576
celo_rating: 1256.39
family_friendly_score: 0.5708
family_friendly_standard_error: 0.006999819426242366
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': 0.27680597049192895, 'latency_mean': 3.6125383257865904, 'latency_p50': 3.61892032623291, 'latency_p90': 4.0003389596939085}, {'batch_size': 2, 'throughput': 0.4214658636989449, 'latency_mean': 4.737889150381088, 'latency_p50': 4.768292188644409, 'latency_p90': 5.244726610183716}, {'batch_size': 3, 'throughput': 0.5303359431405356, 'latency_mean': 5.64484075307846, 'latency_p50': 5.656798362731934, 'latency_p90': 6.180431938171386}, {'batch_size': 5, 'throughput': 0.6781081519404379, 'latency_mean': 7.318954046964645, 'latency_p50': 7.331761837005615, 'latency_p90': 8.143590450286865}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-nis-gemma27b-pro_85310_v4
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: 0.46996977263766593
generation_params: {'temperature': 0.5, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.5, 'frequency_penalty': 0.5, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', '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-v4-mkmlizer
Waiting for job on chaiml-nis-gemma27b-pro-85310-v4-mkmlizer to finish
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: ║ _____ __ __ ║
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: ║ /___/ ║
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: ║ ║
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: ║ Version: 0.12.8 ║
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: ║ https://mk1.ai ║
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: ║ ║
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: ║ belonging to: ║
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: ║ ║
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: ║ Chai Research Corp. ║
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: ║ ║
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: Downloaded to shared memory in 73.817s
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0tx1w7kz, device:0
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: quantized model in 68.844s
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: Processed model ChaiML/nis-gemma27B-proj1-exp1-del5ktop-1 in 142.661s
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nis-gemma27b-pro-85310-v4
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nis-gemma27b-pro-85310-v4/config.json
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nis-gemma27b-pro-85310-v4/tokenizer_config.json
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nis-gemma27b-pro-85310-v4/special_tokens_map.json
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-nis-gemma27b-pro-85310-v4/flywheel_model.2.safetensors
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nis-gemma27b-pro-85310-v4/flywheel_model.0.safetensors
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-nis-gemma27b-pro-85310-v4/flywheel_model.1.safetensors
chaiml-nis-gemma27b-pro-85310-v4-mkmlizer: Loading 0: 0%| | 0/508 [00:00<?, ?it/s] Loading 0: 1%| | 4/508 [00:00<00:12, 39.55it/s] Loading 0: 2%|▏ | 12/508 [00:00<00:11, 45.01it/s] Loading 0: 3%|▎ | 17/508 [00:00<00:14, 33.47it/s] Loading 0: 5%|▍ | 23/508 [00:00<00:12, 40.32it/s] Loading 0: 6%|▌ | 28/508 [00:00<00:16, 29.37it/s] Loading 0: 6%|▋ | 32/508 [00:00<00:16, 28.47it/s] Loading 0: 7%|▋ | 38/508 [00:01<00:14, 31.84it/s] Loading 0: 9%|▉ | 47/508 [00:01<00:11, 39.96it/s] Loading 0: 10%|█ | 52/508 [00:01<00:11, 41.39it/s] Loading 0: 11%|█▏ | 58/508 [00:01<00:11, 39.87it/s] Loading 0: 12%|█▏ | 63/508 [00:01<00:10, 41.66it/s] Loading 0: 13%|█▎ | 68/508 [00:01<00:11, 37.89it/s] Loading 0: 14%|█▍ | 73/508 [00:02<00:16, 26.56it/s] Loading 0: 15%|█▌ | 78/508 [00:02<00:14, 28.73it/s] Loading 0: 16%|█▌ | 82/508 [00:02<00:14, 29.37it/s] Loading 0: 17%|█▋ | 88/508 [00:02<00:12, 32.40it/s] Loading 0: 19%|█▉ | 97/508 [00:02<00:10, 39.99it/s] Loading 0: 20%|██ | 102/508 [00:02<00:09, 42.03it/s] Loading 0: 21%|██▏ | 108/508 [00:03<00:10, 39.68it/s] Loading 0: 22%|██▏ | 113/508 [00:03<00:09, 40.83it/s] Loading 0: 23%|██▎ | 118/508 [00:03<00:12, 31.48it/s] Loading 0: 25%|██▍ | 125/508 [00:03<00:10, 35.53it/s] Loading 0: 26%|██▌ | 133/508 [00:03<00:09, 41.29it/s] Loading 0: 27%|██▋ | 138/508 [00:03<00:09, 37.56it/s] Loading 0: 29%|██▊ | 146/508 [00:03<00:08, 41.77it/s] Loading 0: 30%|██▉ | 151/508 [00:04<00:08, 43.09it/s] Loading 0: 31%|███ | 157/508 [00:04<00:08, 41.56it/s] Loading 0: 32%|███▏ | 162/508 [00:04<00:08, 42.53it/s] Loading 0: 33%|███▎ | 167/508 [00:04<00:07, 43.43it/s] Loading 0: 34%|███▍ | 172/508 [00:04<00:11, 28.78it/s] Loading 0: 35%|███▍ | 176/508 [00:04<00:10, 30.72it/s] Loading 0: 35%|███▌ | 180/508 [00:05<00:10, 32.46it/s] Loading 0: 37%|███▋ | 188/508 [00:05<00:08, 39.70it/s] Loading 0: 38%|███▊ | 193/508 [00:19<04:22, 1.20it/s] Loading 0: 39%|███▉ | 199/508 [00:20<02:56, 1.75it/s] Loading 0: 40%|████ | 204/508 [00:20<02:12, 2.29it/s] Loading 0: 42%|████▏ | 211/508 [00:20<01:25, 3.46it/s] Loading 0: 43%|████▎ | 216/508 [00:20<01:06, 4.42it/s] Loading 0: 43%|████▎ | 220/508 [00:21<00:51, 5.58it/s] Loading 0: 44%|████▍ | 225/508 [00:21<00:38, 7.39it/s] Loading 0: 46%|████▌ | 234/508 [00:21<00:23, 11.76it/s] Loading 0: 47%|████▋ | 240/508 [00:21<00:17, 15.32it/s] Loading 0: 48%|████▊ | 245/508 [00:21<00:14, 17.83it/s] Loading 0: 49%|████▉ | 250/508 [00:21<00:12, 21.49it/s] Loading 0: 50%|█████ | 255/508 [00:21<00:10, 23.53it/s] Loading 0: 51%|█████ | 260/508 [00:21<00:09, 26.16it/s] Loading 0: 52%|█████▏ | 264/508 [00:22<00:10, 23.39it/s] Loading 0: 53%|█████▎ | 268/508 [00:22<00:09, 26.10it/s] Loading 0: 54%|█████▍ | 276/508 [00:22<00:07, 32.92it/s] Loading 0: 55%|█████▌ | 280/508 [00:22<00:07, 30.05it/s] Loading 0: 57%|█████▋ | 289/508 [00:22<00:05, 36.87it/s] Loading 0: 58%|█████▊ | 294/508 [00:22<00:05, 39.12it/s] Loading 0: 59%|█████▉ | 300/508 [00:23<00:05, 38.21it/s] Loading 0: 60%|██████ | 305/508 [00:23<00:05, 40.35it/s] Loading 0: 61%|██████ | 311/508 [00:23<00:04, 44.03it/s] Loading 0: 62%|██████▏ | 316/508 [00:23<00:06, 28.94it/s] Loading 0: 63%|██████▎ | 322/508 [00:23<00:05, 34.61it/s] Loading 0: 64%|██████▍ | 327/508 [00:23<00:04, 37.43it/s] Loading 0: 66%|██████▌ | 333/508 [00:23<00:04, 37.46it/s] Loading 0: 67%|██████▋ | 338/508 [00:24<00:04, 40.10it/s] Loading 0: 68%|██████▊ | 344/508 [00:24<00:04, 38.60it/s] Loading 0: 69%|██████▊ | 349/508 [00:24<00:03, 40.31it/s] Loading 0: 70%|██████▉ | 354/508 [00:24<00:04, 35.35it/s] Loading 0: 71%|███████ | 359/508 [00:24<00:05, 29.76it/s] Loading 0: 71%|███████▏ | 363/508 [00:24<00:04, 31.72it/s] Loading 0: 72%|███████▏ | 367/508 [00:24<00:04, 33.32it/s] Loading 0: 74%|███████▍ | 375/508 [00:25<00:03, 40.32it/s] Loading 0: 75%|███████▍ | 380/508 [00:25<00:03, 36.01it/s] Loading 0: 76%|███████▋ | 388/508 [00:25<00:02, 40.68it/s] Loading 0: 77%|███████▋ | 393/508 [00:25<00:02, 42.68it/s] Loading 0: 78%|███████▊ | 398/508 [00:25<00:02, 39.61it/s] Loading 0: 79%|███████▉ | 403/508 [00:25<00:02, 39.13it/s] Loading 0: 80%|████████ | 408/508 [00:26<00:03, 32.85it/s] Loading 0: 81%|████████ | 412/508 [00:26<00:03, 30.75it/s] Loading 0: 83%|████████▎ | 421/508 [00:26<00:02, 38.21it/s] Loading 0: 84%|████████▎ | 425/508 [00:26<00:02, 38.27it/s] Loading 0: 85%|████████▌ | 432/508 [00:26<00:01, 41.37it/s] Loading 0: 86%|████████▌ | 437/508 [00:26<00:01, 43.01it/s] Loading 0: 87%|████████▋ | 443/508 [00:26<00:01, 41.16it/s] Loading 0: 88%|████████▊ | 448/508 [00:27<00:01, 42.63it/s] Loading 0: 89%|████████▉ | 451/508 [00:41<00:01, 42.63it/s] Loading 0: 89%|████████▉ | 452/508 [00:41<00:48, 1.14it/s] Loading 0: 90%|████████▉ | 456/508 [00:41<00:34, 1.51it/s] Loading 0: 91%|█████████ | 461/508 [00:41<00:22, 2.10it/s] Loading 0: 92%|█████████▏| 467/508 [00:42<00:13, 3.13it/s] Loading 0: 94%|█████████▎| 476/508 [00:42<00:06, 5.23it/s] Loading 0: 95%|█████████▍| 481/508 [00:42<00:03, 6.75it/s] Loading 0: 96%|█████████▌| 487/508 [00:42<00:02, 9.05it/s] Loading 0: 97%|█████████▋| 492/508 [00:42<00:01, 11.53it/s] Loading 0: 98%|█████████▊| 497/508 [00:42<00:00, 14.06it/s] Loading 0: 99%|█████████▉| 502/508 [00:43<00:00, 15.23it/s] Loading 0: 100%|█████████▉| 506/508 [00:43<00:00, 17.84it/s]
Job chaiml-nis-gemma27b-pro-85310-v4-mkmlizer completed after 176.0s with status: succeeded
Stopping job with name chaiml-nis-gemma27b-pro-85310-v4-mkmlizer
Pipeline stage MKMLizer completed in 176.47s
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-nis-gemma27b-pro-85310-v4
Waiting for inference service chaiml-nis-gemma27b-pro-85310-v4 to be ready
Inference service chaiml-nis-gemma27b-pro-85310-v4 ready after 120.48972702026367s
Pipeline stage MKMLDeployer completed in 121.04s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.1510632038116455s
Received healthy response to inference request in 3.3803417682647705s
Received healthy response to inference request in 3.185983419418335s
Received healthy response to inference request in 3.4696969985961914s
Received healthy response to inference request in 3.2021782398223877s
5 requests
0 failed requests
5th percentile: 3.1892223834991453
10th percentile: 3.192461347579956
20th percentile: 3.1989392757415773
30th percentile: 3.2378109455108643
40th percentile: 3.309076356887817
50th percentile: 3.3803417682647705
60th percentile: 3.4160838603973387
70th percentile: 3.4518259525299073
80th percentile: 3.6059702396392823
90th percentile: 3.8785167217254637
95th percentile: 4.014789962768554
99th percentile: 4.123808555603027
mean time: 3.477852725982666
Pipeline stage StressChecker completed in 18.62s
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 0.65s
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 0.62s
Shutdown handler de-registered
chaiml-nis-gemma27b-pro_85310_v4 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 6205.25s
Shutdown handler de-registered
chaiml-nis-gemma27b-pro_85310_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-nis-gemma27b-pro_85310_v4 status is now torndown due to DeploymentManager action