chaiml-gemma2rp-27b-sft-exp3

developer_uid: NischayDnk

submission_id: chaiml-gemma2rp-27b-sft-exp3_v1

model_name: chaiml-gemma2rp-27b-sft-exp3_v1

model_group: ChaiML/gemma2rp-27b-sft-

status: torndown

timestamp: 2025-04-26T19:35:35+00:00

num_battles: 12681

num_wins: 5315

celo_rating: 1236.24

family_friendly_score: 0.5608

family_friendly_standard_error: 0.007018594731140985

submission_type: basic

model_repo: ChaiML/gemma2rp-27b-sft-exp3

model_architecture: Gemma2ForCausalLM

model_num_parameters: 28731935232.0

best_of: 5

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.3886006705914621, 'latency_mean': 2.5732739007472993, 'latency_p50': 2.5770013332366943, 'latency_p90': 2.8687992334365844}, {'batch_size': 3, 'throughput': 0.8472729819981418, 'latency_mean': 3.52537371635437, 'latency_p50': 3.5400818586349487, 'latency_p90': 3.898005247116089}, {'batch_size': 5, 'throughput': 1.1664483222455657, 'latency_mean': 4.253273329734802, 'latency_p50': 4.237162828445435, 'latency_p90': 4.730460381507873}, {'batch_size': 6, 'throughput': 1.2817764150601931, 'latency_mean': 4.633972154855728, 'latency_p50': 4.624452710151672, 'latency_p90': 5.183105683326721}, {'batch_size': 8, 'throughput': 1.4687125738957236, 'latency_mean': 5.380018149614334, 'latency_p50': 5.377158880233765, 'latency_p90': 6.0158192873001095}, {'batch_size': 10, 'throughput': 1.6049548566937832, 'latency_mean': 6.165847178697586, 'latency_p50': 6.186244487762451, 'latency_p90': 7.105861639976501}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: chaiml-gemma2rp-27b-sft-exp3_v1

is_internal_developer: False

language_model: ChaiML/gemma2rp-27b-sft-exp3

model_size: 29B

ranking_group: single

throughput_3p7s: 0.94

us_pacific_date: 2025-04-26

win_ratio: 0.4191309833609337

generation_params: {'temperature': 0.45, 'top_p': 0.92, 'min_p': 0.03, 'top_k': 40, 'presence_penalty': 0.35, 'frequency_penalty': 0.35, 'stopping_words': ['\n', '<|im_end|>', '<|im_start|>'], 'max_input_tokens': 768, 'best_of': 5, '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-gemma2rp-27b-sft-exp3-v1-mkmlizer
Waiting for job on chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer to finish
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: ║       /___/                                                         ║
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: ║                                                                     ║
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: ║                                                                     ║
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: ║                                                                     ║
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: ║                                                                     ║
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: Downloaded to shared memory in 104.156s
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpknekc9k2, device:0
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: quantized model in 68.277s
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: Processed model ChaiML/gemma2rp-27b-sft-exp3 in 172.433s
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gemma2rp-27b-sft-exp3-v1
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gemma2rp-27b-sft-exp3-v1/config.json
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gemma2rp-27b-sft-exp3-v1/special_tokens_map.json
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gemma2rp-27b-sft-exp3-v1/tokenizer_config.json
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-gemma2rp-27b-sft-exp3-v1/tokenizer.model
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gemma2rp-27b-sft-exp3-v1/tokenizer.json
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-gemma2rp-27b-sft-exp3-v1/flywheel_model.2.safetensors
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gemma2rp-27b-sft-exp3-v1/flywheel_model.0.safetensors
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gemma2rp-27b-sft-exp3-v1/flywheel_model.1.safetensors
chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer: 
Loading 0:   0%|          | 0/508 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/508 [00:00<00:13, 37.38it/s]
Loading 0:   2%|▏         | 12/508 [00:00<00:11, 44.38it/s]
Loading 0:   3%|▎         | 17/508 [00:00<00:14, 33.80it/s]
Loading 0:   5%|▍         | 24/508 [00:00<00:11, 43.72it/s]
Loading 0:   6%|▌         | 29/508 [00:00<00:16, 29.01it/s]
Loading 0:   6%|▋         | 33/508 [00:00<00:15, 31.00it/s]
Loading 0:   7%|▋         | 38/508 [00:01<00:14, 31.66it/s]
Loading 0:   9%|▉         | 47/508 [00:01<00:11, 40.08it/s]
Loading 0:  10%|█         | 52/508 [00:01<00:10, 41.67it/s]
Loading 0:  11%|█▏        | 58/508 [00:01<00:11, 40.54it/s]
Loading 0:  12%|█▏        | 63/508 [00:01<00:10, 42.56it/s]
Loading 0:  13%|█▎        | 68/508 [00:01<00:10, 40.19it/s]
Loading 0:  14%|█▍        | 73/508 [00:02<00:15, 28.73it/s]
Loading 0:  15%|█▌        | 78/508 [00:02<00:13, 30.85it/s]
Loading 0:  16%|█▌        | 82/508 [00:02<00:13, 31.01it/s]
Loading 0:  17%|█▋        | 88/508 [00:02<00:12, 33.78it/s]
Loading 0:  19%|█▉        | 97/508 [00:02<00:09, 41.60it/s]
Loading 0:  20%|██        | 102/508 [00:02<00:09, 43.33it/s]
Loading 0:  21%|██▏       | 108/508 [00:02<00:09, 41.07it/s]
Loading 0:  22%|██▏       | 113/508 [00:03<00:09, 42.90it/s]
Loading 0:  23%|██▎       | 118/508 [00:03<00:12, 31.64it/s]
Loading 0:  25%|██▍       | 125/508 [00:03<00:10, 35.58it/s]
Loading 0:  26%|██▌       | 133/508 [00:03<00:09, 41.45it/s]
Loading 0:  27%|██▋       | 138/508 [00:03<00:09, 37.46it/s]
Loading 0:  29%|██▊       | 146/508 [00:03<00:08, 41.57it/s]
Loading 0:  30%|██▉       | 151/508 [00:04<00:08, 43.19it/s]
Loading 0:  31%|███       | 157/508 [00:04<00:08, 42.37it/s]
Loading 0:  32%|███▏      | 164/508 [00:04<00:07, 48.41it/s]
Loading 0:  33%|███▎      | 170/508 [00:04<00:07, 43.89it/s]
Loading 0:  34%|███▍      | 175/508 [00:04<00:10, 30.38it/s]
Loading 0:  35%|███▌      | 180/508 [00:04<00:09, 33.92it/s]
Loading 0:  37%|███▋      | 188/508 [00:04<00:07, 40.54it/s]
Loading 0:  38%|███▊      | 193/508 [00:19<03:59,  1.32it/s]
Loading 0:  39%|███▉      | 199/508 [00:19<02:46,  1.86it/s]
Loading 0:  40%|████      | 204/508 [00:20<02:05,  2.42it/s]
Loading 0:  42%|████▏     | 211/508 [00:20<01:22,  3.59it/s]
Loading 0:  43%|████▎     | 216/508 [00:20<01:03,  4.56it/s]
Loading 0:  43%|████▎     | 220/508 [00:20<00:50,  5.71it/s]
Loading 0:  44%|████▍     | 225/508 [00:20<00:37,  7.54it/s]
Loading 0:  46%|████▌     | 234/508 [00:20<00:22, 11.98it/s]
Loading 0:  47%|████▋     | 241/508 [00:21<00:16, 16.29it/s]
Loading 0:  48%|████▊     | 246/508 [00:21<00:14, 18.02it/s]
Loading 0:  50%|█████     | 254/508 [00:21<00:10, 23.88it/s]
Loading 0:  51%|█████     | 259/508 [00:21<00:09, 25.86it/s]
Loading 0:  52%|█████▏    | 264/508 [00:21<00:10, 22.95it/s]
Loading 0:  53%|█████▎    | 269/508 [00:21<00:09, 25.15it/s]
Loading 0:  55%|█████▍    | 278/508 [00:22<00:07, 32.61it/s]
Loading 0:  56%|█████▌    | 283/508 [00:22<00:06, 35.57it/s]
Loading 0:  57%|█████▋    | 289/508 [00:22<00:05, 36.64it/s]
Loading 0:  58%|█████▊    | 295/508 [00:22<00:05, 41.23it/s]
Loading 0:  59%|█████▉    | 300/508 [00:22<00:05, 38.34it/s]
Loading 0:  60%|██████    | 305/508 [00:22<00:05, 40.41it/s]
Loading 0:  61%|██████    | 311/508 [00:22<00:04, 44.67it/s]
Loading 0:  62%|██████▏   | 316/508 [00:23<00:06, 28.51it/s]
Loading 0:  63%|██████▎   | 322/508 [00:23<00:05, 34.14it/s]
Loading 0:  64%|██████▍   | 327/508 [00:23<00:04, 37.16it/s]
Loading 0:  66%|██████▌   | 333/508 [00:23<00:04, 37.37it/s]
Loading 0:  67%|██████▋   | 338/508 [00:23<00:04, 39.43it/s]
Loading 0:  68%|██████▊   | 344/508 [00:23<00:04, 37.89it/s]
Loading 0:  69%|██████▊   | 349/508 [00:23<00:03, 40.44it/s]
Loading 0:  70%|██████▉   | 354/508 [00:24<00:04, 37.09it/s]
Loading 0:  71%|███████   | 359/508 [00:24<00:04, 30.51it/s]
Loading 0:  71%|███████▏  | 363/508 [00:24<00:04, 32.31it/s]
Loading 0:  72%|███████▏  | 368/508 [00:24<00:04, 32.94it/s]
Loading 0:  74%|███████▍  | 377/508 [00:24<00:03, 40.13it/s]
Loading 0:  75%|███████▌  | 382/508 [00:24<00:02, 42.23it/s]
Loading 0:  76%|███████▋  | 388/508 [00:25<00:02, 40.59it/s]
Loading 0:  78%|███████▊  | 394/508 [00:25<00:02, 44.92it/s]
Loading 0:  79%|███████▊  | 399/508 [00:25<00:02, 37.17it/s]
Loading 0:  80%|███████▉  | 404/508 [00:25<00:03, 29.89it/s]
Loading 0:  81%|████████  | 410/508 [00:25<00:02, 35.59it/s]
Loading 0:  82%|████████▏ | 415/508 [00:25<00:02, 38.61it/s]
Loading 0:  83%|████████▎ | 421/508 [00:25<00:02, 37.64it/s]
Loading 0:  84%|████████▍ | 426/508 [00:26<00:02, 40.34it/s]
Loading 0:  85%|████████▌ | 432/508 [00:26<00:01, 40.17it/s]
Loading 0:  86%|████████▌ | 438/508 [00:26<00:01, 44.58it/s]
Loading 0:  87%|████████▋ | 443/508 [00:26<00:01, 40.72it/s]
Loading 0:  88%|████████▊ | 449/508 [00:26<00:01, 45.15it/s]
Loading 0:  89%|████████▉ | 451/508 [00:40<00:01, 45.15it/s]
Loading 0:  89%|████████▉ | 452/508 [00:41<00:51,  1.10it/s]
Loading 0:  90%|████████▉ | 456/508 [00:41<00:35,  1.47it/s]
Loading 0:  91%|█████████ | 461/508 [00:41<00:22,  2.06it/s]
Loading 0:  92%|█████████▏| 467/508 [00:41<00:13,  3.10it/s]
Loading 0:  93%|█████████▎| 474/508 [00:41<00:07,  4.79it/s]
Loading 0:  94%|█████████▍| 479/508 [00:41<00:04,  6.20it/s]
Loading 0:  96%|█████████▌| 487/508 [00:42<00:02,  9.37it/s]
Loading 0:  97%|█████████▋| 492/508 [00:42<00:01, 11.82it/s]
Loading 0:  98%|█████████▊| 497/508 [00:42<00:00, 14.16it/s]
Loading 0:  99%|█████████▉| 502/508 [00:42<00:00, 15.81it/s]
Loading 0: 100%|█████████▉| 506/508 [00:42<00:00, 18.42it/s]
                                                            
Job chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer completed after 207.59s with status: succeeded
Stopping job with name chaiml-gemma2rp-27b-sft-exp3-v1-mkmlizer
Pipeline stage MKMLizer completed in 208.12s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gemma2rp-27b-sft-exp3-v1
Waiting for inference service chaiml-gemma2rp-27b-sft-exp3-v1 to be ready
Inference service chaiml-gemma2rp-27b-sft-exp3-v1 ready after 130.67528200149536s
Pipeline stage MKMLDeployer completed in 131.44s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.399904251098633s
Received healthy response to inference request in 2.919633388519287s
Received healthy response to inference request in 2.743699312210083s
Received healthy response to inference request in 3.008289098739624s
Received healthy response to inference request in 2.6104624271392822s
5 requests
0 failed requests
5th percentile: 2.637109804153442
10th percentile: 2.6637571811676026
20th percentile: 2.717051935195923
30th percentile: 2.7788861274719237
40th percentile: 2.8492597579956054
50th percentile: 2.919633388519287
60th percentile: 2.955095672607422
70th percentile: 2.9905579566955565
80th percentile: 3.0866121292114257
90th percentile: 3.2432581901550295
95th percentile: 3.321581220626831
99th percentile: 3.3842396450042727
mean time: 2.9363976955413817
Pipeline stage StressChecker completed in 16.05s
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 0.66s
Shutdown handler de-registered
chaiml-gemma2rp-27b-sft-exp3_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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 3252.16s
Shutdown handler de-registered
chaiml-gemma2rp-27b-sft-exp3_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gemma2rp-27b-sft-exp3_v1 status is now torndown due to DeploymentManager action