developer_uid: NischayDnk
submission_id: chaiml-sft-gemma2it-28b_47770_v3
model_name: chaiml-sft-gemma2it-28b_47770_v3
model_group: ChaiML/sft-gemma2it-28b-
status: torndown
timestamp: 2025-04-01T04:21:17+00:00
num_battles: 11
num_wins: 4
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: ChaiML/sft-gemma2it-28b-v2-exp1
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': 0.2788564411358239, 'latency_mean': 3.586010061502457, 'latency_p50': 3.5434727668762207, 'latency_p90': 3.9835196018218992}, {'batch_size': 2, 'throughput': 0.4249089396180649, 'latency_mean': 4.696206716299057, 'latency_p50': 4.702696323394775, 'latency_p90': 5.198600697517395}, {'batch_size': 3, 'throughput': 0.535177752419583, 'latency_mean': 5.601511807441711, 'latency_p50': 5.623057126998901, 'latency_p90': 6.124519515037536}, {'batch_size': 5, 'throughput': 0.6831440892073957, 'latency_mean': 7.283300530910492, 'latency_p50': 7.369640231132507, 'latency_p90': 8.012235474586486}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-sft-gemma2it-28b_47770_v3
ineligible_reason: num_battles<5000
is_internal_developer: False
language_model: ChaiML/sft-gemma2it-28b-v2-exp1
model_size: 29B
ranking_group: single
throughput_3p7s: 0.3
us_pacific_date: 2025-03-31
win_ratio: 0.36363636363636365
generation_params: {'temperature': 0.4, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.05, 'frequency_penalty': 0.05, 'stopping_words': ['<|im_end|>', '\n'], '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-gemma2it-28b-47770-v3-mkmlizer
Waiting for job on chaiml-sft-gemma2it-28b-47770-v3-mkmlizer to finish
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: ║ _____ __ __ ║
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: ║ /___/ ║
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: ║ ║
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: ║ Version: 0.12.8 ║
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: ║ ║
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: ║ belonging to: ║
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: ║ ║
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: ║ ║
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: quantized model in 69.011s
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: Processed model ChaiML/sft-gemma2it-28b-v2-exp1 in 142.032s
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sft-gemma2it-28b-47770-v3
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sft-gemma2it-28b-47770-v3/config.json
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sft-gemma2it-28b-47770-v3/special_tokens_map.json
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sft-gemma2it-28b-47770-v3/tokenizer_config.json
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-sft-gemma2it-28b-47770-v3/flywheel_model.2.safetensors
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sft-gemma2it-28b-47770-v3/flywheel_model.0.safetensors
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-sft-gemma2it-28b-47770-v3/flywheel_model.1.safetensors
chaiml-sft-gemma2it-28b-47770-v3-mkmlizer: Loading 0: 0%| | 0/508 [00:00<?, ?it/s] Loading 0: 1%| | 4/508 [00:00<00:12, 39.23it/s] Loading 0: 2%|▏ | 12/508 [00:00<00:10, 45.63it/s] Loading 0: 3%|▎ | 17/508 [00:00<00:14, 34.27it/s] Loading 0: 5%|▌ | 27/508 [00:00<00:10, 45.80it/s] Loading 0: 6%|▋ | 32/508 [00:00<00:15, 29.87it/s] Loading 0: 7%|▋ | 38/508 [00:01<00:14, 32.41it/s] Loading 0: 9%|▉ | 47/508 [00:01<00:11, 39.90it/s] Loading 0: 10%|█ | 52/508 [00:01<00:10, 41.59it/s] Loading 0: 11%|█▏ | 58/508 [00:01<00:11, 40.63it/s] Loading 0: 12%|█▏ | 63/508 [00:01<00:10, 42.43it/s] Loading 0: 13%|█▎ | 68/508 [00:01<00:10, 40.29it/s] Loading 0: 14%|█▍ | 73/508 [00:02<00:14, 29.19it/s] Loading 0: 15%|█▌ | 78/508 [00:02<00:13, 31.12it/s] Loading 0: 16%|█▌ | 82/508 [00:02<00:13, 30.94it/s] Loading 0: 17%|█▋ | 87/508 [00:02<00:12, 34.96it/s] Loading 0: 19%|█▊ | 95/508 [00:02<00:09, 41.85it/s] Loading 0: 20%|█▉ | 100/508 [00:02<00:10, 37.34it/s] Loading 0: 21%|██▏ | 108/508 [00:02<00:09, 40.71it/s] Loading 0: 22%|██▏ | 113/508 [00:02<00:09, 42.44it/s] Loading 0: 23%|██▎ | 118/508 [00:03<00:11, 32.55it/s] Loading 0: 24%|██▍ | 124/508 [00:03<00:10, 37.88it/s] Loading 0: 25%|██▌ | 129/508 [00:03<00:09, 40.05it/s] Loading 0: 27%|██▋ | 135/508 [00:03<00:09, 39.66it/s] Loading 0: 28%|██▊ | 140/508 [00:03<00:08, 41.84it/s] Loading 0: 29%|██▊ | 146/508 [00:03<00:08, 41.31it/s] Loading 0: 30%|██▉ | 151/508 [00:03<00:08, 42.85it/s] Loading 0: 31%|███ | 157/508 [00:04<00:08, 41.95it/s] Loading 0: 32%|███▏ | 162/508 [00:04<00:07, 43.43it/s] Loading 0: 33%|███▎ | 168/508 [00:04<00:07, 46.27it/s] Loading 0: 34%|███▍ | 173/508 [00:04<00:11, 29.47it/s] Loading 0: 35%|███▌ | 179/508 [00:04<00:09, 35.16it/s] Loading 0: 36%|███▌ | 184/508 [00:04<00:08, 38.00it/s] Loading 0: 37%|███▋ | 190/508 [00:05<00:08, 37.67it/s] Loading 0: 38%|███▊ | 195/508 [00:19<04:15, 1.23it/s] Loading 0: 39%|███▉ | 199/508 [00:19<03:13, 1.60it/s] Loading 0: 40%|████ | 204/508 [00:19<02:20, 2.17it/s] Loading 0: 42%|████▏ | 211/508 [00:20<01:28, 3.36it/s] Loading 0: 43%|████▎ | 216/508 [00:20<01:06, 4.36it/s] Loading 0: 43%|████▎ | 220/508 [00:20<00:51, 5.54it/s] Loading 0: 44%|████▍ | 225/508 [00:20<00:38, 7.39it/s] Loading 0: 46%|████▌ | 234/508 [00:20<00:23, 11.86it/s] Loading 0: 47%|████▋ | 238/508 [00:20<00:19, 13.95it/s] Loading 0: 48%|████▊ | 245/508 [00:21<00:14, 18.32it/s] Loading 0: 49%|████▉ | 250/508 [00:21<00:11, 21.89it/s] Loading 0: 50%|█████ | 255/508 [00:21<00:10, 23.60it/s] Loading 0: 51%|█████ | 260/508 [00:21<00:09, 26.09it/s] Loading 0: 52%|█████▏ | 264/508 [00:21<00:10, 23.49it/s] Loading 0: 53%|█████▎ | 268/508 [00:21<00:09, 26.06it/s] Loading 0: 54%|█████▍ | 276/508 [00:21<00:06, 34.17it/s] Loading 0: 55%|█████▌ | 281/508 [00:22<00:06, 32.47it/s] Loading 0: 57%|█████▋ | 289/508 [00:22<00:05, 38.20it/s] Loading 0: 58%|█████▊ | 294/508 [00:22<00:05, 40.24it/s] Loading 0: 59%|█████▉ | 300/508 [00:22<00:05, 38.12it/s] Loading 0: 60%|██████ | 305/508 [00:22<00:05, 40.31it/s] Loading 0: 61%|██████ | 311/508 [00:22<00:04, 43.77it/s] Loading 0: 62%|██████▏ | 316/508 [00:23<00:06, 28.98it/s] Loading 0: 63%|██████▎ | 322/508 [00:23<00:05, 34.21it/s] Loading 0: 64%|██████▍ | 327/508 [00:23<00:04, 37.14it/s] Loading 0: 66%|██████▌ | 333/508 [00:23<00:04, 37.13it/s] Loading 0: 67%|██████▋ | 338/508 [00:23<00:04, 39.77it/s] Loading 0: 68%|██████▊ | 344/508 [00:23<00:04, 38.52it/s] Loading 0: 69%|██████▊ | 349/508 [00:23<00:03, 40.65it/s] Loading 0: 70%|██████▉ | 354/508 [00:23<00:04, 37.59it/s] Loading 0: 71%|███████ | 359/508 [00:24<00:04, 31.05it/s] Loading 0: 71%|███████▏ | 363/508 [00:24<00:04, 32.65it/s] Loading 0: 72%|███████▏ | 368/508 [00:24<00:04, 32.87it/s] Loading 0: 74%|███████▍ | 377/508 [00:24<00:03, 39.52it/s] Loading 0: 75%|███████▌ | 382/508 [00:24<00:03, 41.57it/s] Loading 0: 76%|███████▋ | 388/508 [00:24<00:02, 40.09it/s] Loading 0: 77%|███████▋ | 393/508 [00:24<00:02, 42.13it/s] Loading 0: 78%|███████▊ | 398/508 [00:25<00:02, 38.94it/s] Loading 0: 79%|███████▉ | 403/508 [00:25<00:02, 39.09it/s] Loading 0: 80%|████████ | 407/508 [00:25<00:03, 30.97it/s] Loading 0: 81%|████████ | 412/508 [00:25<00:03, 31.72it/s] Loading 0: 83%|████████▎ | 421/508 [00:25<00:02, 38.75it/s] Loading 0: 84%|████████▎ | 425/508 [00:25<00:02, 38.66it/s] Loading 0: 85%|████████▌ | 432/508 [00:26<00:01, 40.37it/s] Loading 0: 86%|████████▌ | 437/508 [00:26<00:01, 42.18it/s] Loading 0: 87%|████████▋ | 443/508 [00:26<00:01, 41.35it/s] Loading 0: 88%|████████▊ | 448/508 [00:26<00:01, 43.00it/s] Loading 0: 89%|████████▉ | 451/508 [00:40<00:01, 43.00it/s] Loading 0: 89%|████████▉ | 452/508 [00:41<00:49, 1.13it/s] Loading 0: 90%|████████▉ | 456/508 [00:41<00:34, 1.50it/s] Loading 0: 91%|█████████ | 461/508 [00:41<00:22, 2.08it/s] Loading 0: 92%|█████████▏| 467/508 [00:41<00:13, 3.11it/s] Loading 0: 94%|█████████▎| 476/508 [00:41<00:06, 5.19it/s] Loading 0: 95%|█████████▍| 481/508 [00:41<00:04, 6.71it/s] Loading 0: 96%|█████████▌| 487/508 [00:42<00:02, 8.93it/s] Loading 0: 97%|█████████▋| 492/508 [00:42<00:01, 11.39it/s] Loading 0: 98%|█████████▊| 497/508 [00:42<00:00, 13.91it/s] Loading 0: 99%|█████████▉| 502/508 [00:42<00:00, 15.44it/s] Loading 0: 100%|█████████▉| 506/508 [00:42<00:00, 18.10it/s]
Job chaiml-sft-gemma2it-28b-47770-v3-mkmlizer completed after 176.46s with status: succeeded
Stopping job with name chaiml-sft-gemma2it-28b-47770-v3-mkmlizer
Pipeline stage MKMLizer completed in 176.97s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-sft-gemma2it-28b-47770-v3
Waiting for inference service chaiml-sft-gemma2it-28b-47770-v3 to be ready
Inference service chaiml-sft-gemma2it-28b-47770-v3 ready after 110.57224035263062s
Pipeline stage MKMLDeployer completed in 111.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.677109479904175s
Received healthy response to inference request in 3.18888783454895s
Received healthy response to inference request in 3.1264045238494873s
Received healthy response to inference request in 3.1925039291381836s
Received healthy response to inference request in 3.1918768882751465s
5 requests
0 failed requests
5th percentile: 3.13890118598938
10th percentile: 3.1513978481292724
20th percentile: 3.1763911724090574
30th percentile: 3.1894856452941895
40th percentile: 3.190681266784668
50th percentile: 3.1918768882751465
60th percentile: 3.1921277046203613
70th percentile: 3.192378520965576
80th percentile: 3.2894250392913817
90th percentile: 3.4832672595977785
95th percentile: 3.5801883697509767
99th percentile: 3.657725257873535
mean time: 3.2753565311431885
Pipeline stage StressChecker completed in 17.66s
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 0.66s
Shutdown handler de-registered
chaiml-sft-gemma2it-28b_47770_v3 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
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-gemma2it-28b_47770_v3 status is now inactive due to admin request
chaiml-sft-gemma2it-28b_47770_v3 status is now torndown due to DeploymentManager action