developer_uid: NischayDnk
submission_id: chaiml-sft-gemma2-28b-v_83370_v1
model_name: chaiml-sft-gemma2-28b-v_83370_v1
model_group: ChaiML/sft-gemma2-28b-v2
status: torndown
timestamp: 2025-04-02T16:16:23+00:00
num_battles: 7006
num_wins: 3396
celo_rating: 1287.73
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/sft-gemma2-28b-v2-exp1-del12ktop
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': 0.27328282902542234, 'latency_mean': 3.659116133451462, 'latency_p50': 3.6593520641326904, 'latency_p90': 4.05393283367157}, {'batch_size': 2, 'throughput': 0.4209273194122412, 'latency_mean': 4.736173815727234, 'latency_p50': 4.731330513954163, 'latency_p90': 5.2472776651382445}, {'batch_size': 3, 'throughput': 0.5258321132306935, 'latency_mean': 5.682359178066253, 'latency_p50': 5.68738865852356, 'latency_p90': 6.189660048484802}, {'batch_size': 5, 'throughput': 0.6663832889380762, 'latency_mean': 7.456385149955749, 'latency_p50': 7.439383268356323, 'latency_p90': 8.308804917335511}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-sft-gemma2-28b-v_83370_v1
is_internal_developer: False
language_model: ChaiML/sft-gemma2-28b-v2-exp1-del12ktop
model_size: 29B
ranking_group: single
throughput_3p7s: 0.28
us_pacific_date: 2025-04-02
win_ratio: 0.48472737653439907
generation_params: {'temperature': 0.5, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, 'stopping_words': ['\n', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, '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-sft-gemma2-28b-v-83370-v1-mkmlizer
Waiting for job on chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer to finish
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: ║ _____ __ __ ║
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: ║ /___/ ║
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: ║ belonging to: ║
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: Downloaded to shared memory in 95.318s
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpn82ery9n, device:0
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: quantized model in 68.878s
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: Processed model ChaiML/sft-gemma2-28b-v2-exp1-del12ktop in 164.196s
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v1/config.json
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v1/special_tokens_map.json
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v1/tokenizer_config.json
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v1/tokenizer.model
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v1/tokenizer.json
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v1/flywheel_model.2.safetensors
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v1/flywheel_model.0.safetensors
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v1/flywheel_model.1.safetensors
chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer: Loading 0: 0%| | 0/508 [00:00<?, ?it/s] Loading 0: 1%| | 4/508 [00:00<00:13, 37.06it/s] Loading 0: 2%|▏ | 12/508 [00:00<00:11, 44.23it/s] Loading 0: 3%|▎ | 17/508 [00:00<00:14, 33.47it/s] Loading 0: 5%|▌ | 27/508 [00:00<00:10, 46.54it/s] Loading 0: 6%|▋ | 32/508 [00:00<00:16, 29.13it/s] Loading 0: 7%|▋ | 37/508 [00:01<00:14, 32.89it/s] Loading 0: 9%|▉ | 45/508 [00:01<00:11, 38.70it/s] Loading 0: 10%|▉ | 50/508 [00:01<00:12, 35.95it/s] Loading 0: 11%|█▏ | 58/508 [00:01<00:10, 40.92it/s] Loading 0: 12%|█▏ | 63/508 [00:01<00:10, 42.69it/s] Loading 0: 13%|█▎ | 68/508 [00:01<00:11, 39.38it/s] Loading 0: 14%|█▍ | 73/508 [00:02<00:15, 28.51it/s] Loading 0: 15%|█▌ | 78/508 [00:02<00:14, 30.16it/s] Loading 0: 16%|█▌ | 82/508 [00:02<00:14, 30.21it/s] Loading 0: 17%|█▋ | 87/508 [00:02<00:12, 33.97it/s] Loading 0: 19%|█▊ | 95/508 [00:02<00:10, 40.66it/s] Loading 0: 20%|█▉ | 100/508 [00:02<00:11, 36.53it/s] Loading 0: 21%|██▏ | 108/508 [00:02<00:09, 40.95it/s] Loading 0: 22%|██▏ | 113/508 [00:03<00:09, 42.49it/s] Loading 0: 23%|██▎ | 118/508 [00:03<00:11, 33.46it/s] Loading 0: 24%|██▍ | 124/508 [00:03<00:10, 38.37it/s] Loading 0: 25%|██▌ | 129/508 [00:03<00:09, 40.34it/s] Loading 0: 27%|██▋ | 135/508 [00:03<00:09, 40.16it/s] Loading 0: 28%|██▊ | 140/508 [00:03<00:08, 41.65it/s] Loading 0: 29%|██▊ | 146/508 [00:03<00:08, 41.01it/s] Loading 0: 30%|██▉ | 151/508 [00:04<00:08, 42.52it/s] Loading 0: 31%|███ | 157/508 [00:04<00:08, 42.29it/s] Loading 0: 32%|███▏ | 162/508 [00:04<00:07, 43.57it/s] Loading 0: 33%|███▎ | 168/508 [00:04<00:07, 45.92it/s] Loading 0: 34%|███▍ | 173/508 [00:04<00:11, 29.57it/s] Loading 0: 35%|███▌ | 179/508 [00:04<00:09, 35.13it/s] Loading 0: 36%|███▌ | 184/508 [00:04<00:08, 38.06it/s] Loading 0: 37%|███▋ | 190/508 [00:05<00:08, 38.45it/s] Loading 0: 38%|███▊ | 195/508 [00:19<04:17, 1.21it/s] Loading 0: 39%|███▉ | 199/508 [00:19<03:15, 1.58it/s] Loading 0: 40%|███▉ | 203/508 [00:20<02:30, 2.02it/s] Loading 0: 41%|████▏ | 210/508 [00:20<01:31, 3.25it/s] Loading 0: 42%|████▏ | 215/508 [00:20<01:07, 4.36it/s] Loading 0: 43%|████▎ | 219/508 [00:20<00:55, 5.25it/s] Loading 0: 44%|████▍ | 224/508 [00:20<00:39, 7.22it/s] Loading 0: 46%|████▌ | 232/508 [00:20<00:24, 11.27it/s] Loading 0: 47%|████▋ | 237/508 [00:21<00:20, 13.38it/s] Loading 0: 48%|████▊ | 245/508 [00:21<00:14, 18.72it/s] Loading 0: 49%|████▉ | 250/508 [00:21<00:11, 22.10it/s] Loading 0: 50%|█████ | 255/508 [00:21<00:10, 23.82it/s] Loading 0: 51%|█████ | 260/508 [00:21<00:09, 26.01it/s] Loading 0: 52%|█████▏ | 264/508 [00:21<00:10, 23.79it/s] Loading 0: 53%|█████▎ | 268/508 [00:21<00:09, 26.46it/s] Loading 0: 54%|█████▍ | 276/508 [00:22<00:06, 33.65it/s] Loading 0: 55%|█████▌ | 281/508 [00:22<00:07, 32.21it/s] Loading 0: 57%|█████▋ | 289/508 [00:22<00:05, 37.63it/s] Loading 0: 58%|█████▊ | 294/508 [00:22<00:05, 39.58it/s] Loading 0: 59%|█████▉ | 300/508 [00:22<00:05, 38.91it/s] Loading 0: 60%|██████ | 305/508 [00:22<00:04, 41.03it/s] Loading 0: 61%|██████ | 311/508 [00:22<00:04, 45.16it/s] Loading 0: 62%|██████▏ | 316/508 [00:23<00:06, 29.70it/s] Loading 0: 63%|██████▎ | 322/508 [00:23<00:05, 35.00it/s] Loading 0: 64%|██████▍ | 327/508 [00:23<00:04, 37.84it/s] Loading 0: 66%|██████▌ | 333/508 [00:23<00:04, 37.59it/s] Loading 0: 67%|██████▋ | 338/508 [00:23<00:04, 39.94it/s] Loading 0: 68%|██████▊ | 344/508 [00:23<00:04, 40.40it/s] Loading 0: 69%|██████▊ | 349/508 [00:23<00:03, 42.17it/s] Loading 0: 70%|██████▉ | 354/508 [00:24<00:03, 38.79it/s] Loading 0: 71%|███████ | 359/508 [00:24<00:04, 31.56it/s] Loading 0: 71%|███████▏ | 363/508 [00:24<00:04, 32.83it/s] Loading 0: 72%|███████▏ | 368/508 [00:24<00:04, 33.03it/s] Loading 0: 74%|███████▍ | 377/508 [00:24<00:03, 40.25it/s] Loading 0: 75%|███████▌ | 382/508 [00:24<00:02, 42.05it/s] Loading 0: 76%|███████▋ | 388/508 [00:24<00:02, 41.22it/s] Loading 0: 77%|███████▋ | 393/508 [00:25<00:02, 43.07it/s] Loading 0: 78%|███████▊ | 398/508 [00:25<00:02, 39.94it/s] Loading 0: 79%|███████▉ | 403/508 [00:25<00:02, 40.10it/s] Loading 0: 80%|████████ | 408/508 [00:25<00:02, 33.41it/s] Loading 0: 81%|████████ | 412/508 [00:25<00:03, 31.44it/s] Loading 0: 83%|████████▎ | 421/508 [00:25<00:02, 38.57it/s] Loading 0: 84%|████████▎ | 425/508 [00:26<00:02, 37.92it/s] Loading 0: 85%|████████▌ | 432/508 [00:26<00:01, 40.23it/s] Loading 0: 86%|████████▌ | 437/508 [00:26<00:01, 42.23it/s] Loading 0: 87%|████████▋ | 443/508 [00:26<00:01, 40.75it/s] Loading 0: 88%|████████▊ | 448/508 [00:26<00:01, 42.80it/s] Loading 0: 89%|████████▉ | 451/508 [00:40<00:01, 42.80it/s] Loading 0: 89%|████████▉ | 452/508 [00:40<00:48, 1.17it/s] Loading 0: 90%|████████▉ | 456/508 [00:40<00:33, 1.54it/s] Loading 0: 91%|█████████ | 461/508 [00:41<00:21, 2.14it/s] Loading 0: 92%|█████████▏| 466/508 [00:41<00:13, 3.03it/s] Loading 0: 93%|█████████▎| 474/508 [00:41<00:06, 4.97it/s] Loading 0: 94%|█████████▍| 479/508 [00:41<00:04, 6.36it/s] Loading 0: 96%|█████████▌| 487/508 [00:41<00:02, 9.56it/s] Loading 0: 97%|█████████▋| 492/508 [00:41<00:01, 12.02it/s] Loading 0: 98%|█████████▊| 497/508 [00:42<00:00, 14.42it/s] Loading 0: 99%|█████████▉| 502/508 [00:42<00:00, 16.01it/s] Loading 0: 100%|█████████▉| 506/508 [00:42<00:00, 18.54it/s]
Job chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer completed after 196.15s with status: succeeded
Stopping job with name chaiml-sft-gemma2-28b-v-83370-v1-mkmlizer
Pipeline stage MKMLizer completed in 196.65s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-sft-gemma2-28b-v-83370-v1
Waiting for inference service chaiml-sft-gemma2-28b-v-83370-v1 to be ready
Inference service chaiml-sft-gemma2-28b-v-83370-v1 ready after 110.61280870437622s
Pipeline stage MKMLDeployer completed in 111.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.831915855407715s
Received healthy response to inference request in 3.4236948490142822s
Received healthy response to inference request in 3.401991367340088s
Received healthy response to inference request in 3.411896228790283s
Received healthy response to inference request in 3.198209047317505s
5 requests
0 failed requests
5th percentile: 3.2389655113220215
10th percentile: 3.279721975326538
20th percentile: 3.3612349033355713
30th percentile: 3.403972339630127
40th percentile: 3.407934284210205
50th percentile: 3.411896228790283
60th percentile: 3.416615676879883
70th percentile: 3.4213351249694823
80th percentile: 3.5053390502929687
90th percentile: 3.668627452850342
95th percentile: 3.7502716541290284
99th percentile: 3.8155870151519777
mean time: 3.453541469573975
Pipeline stage StressChecker completed in 18.55s
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 0.80s
Shutdown handler de-registered
chaiml-sft-gemma2-28b-v_83370_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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-sft-gemma2-28b-v-83370-v1-profiler
Waiting for inference service chaiml-sft-gemma2-28b-v-83370-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
%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
%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
chaiml-sft-gemma2-28b-v_83370_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-sft-gemma2-28b-v_83370_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-sft-gemma2-28b-v_83370_v1 status is now torndown due to DeploymentManager action