developer_uid: NischayDnk
submission_id: chaiml-sft-gemma2-28b-v_83370_v5
model_name: chaiml-sft-gemma2-28b-v_83370_v5
model_group: ChaiML/sft-gemma2-28b-v2
status: torndown
timestamp: 2025-04-03T15:38:16+00:00
num_battles: 43
num_wins: 24
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: 1
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.2972182277205494, 'latency_mean': 3.3644703960418703, 'latency_p50': 3.3967604637145996, 'latency_p90': 3.712402844429016}, {'batch_size': 2, 'throughput': 0.47967630568458075, 'latency_mean': 4.161236312389374, 'latency_p50': 4.125921010971069, 'latency_p90': 4.550186991691589}, {'batch_size': 3, 'throughput': 0.642754192791148, 'latency_mean': 4.645341594219207, 'latency_p50': 4.602119326591492, 'latency_p90': 5.188334631919861}, {'batch_size': 4, 'throughput': 0.7641780574752594, 'latency_mean': 5.2142102551460265, 'latency_p50': 5.24214506149292, 'latency_p90': 5.741063022613525}, {'batch_size': 5, 'throughput': 0.8651782166621107, 'latency_mean': 5.747967282533645, 'latency_p50': 5.724665284156799, 'latency_p90': 6.540565872192383}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-sft-gemma2-28b-v_83370_v5
ineligible_reason: num_battles<5000
is_internal_developer: False
language_model: ChaiML/sft-gemma2-28b-v2-exp1-del12ktop
model_size: 29B
ranking_group: single
throughput_3p7s: 0.38
us_pacific_date: 2025-04-03
win_ratio: 0.5581395348837209
generation_params: {'temperature': 0.45, 'top_p': 0.925, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 1, '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-sft-gemma2-28b-v-83370-v5-mkmlizer
Waiting for job on chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer to finish
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: ║ _____ __ __ ║
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: ║ /___/ ║
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: ║ Version: 0.12.8 ║
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: ║ https://mk1.ai ║
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: ║ belonging to: ║
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: ║ Chai Research Corp. ║
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: Downloaded to shared memory in 98.007s
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkx4s_l1s, device:0
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: quantized model in 66.432s
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: Processed model ChaiML/sft-gemma2-28b-v2-exp1-del12ktop in 164.439s
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v5
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v5/config.json
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v5/special_tokens_map.json
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v5/tokenizer_config.json
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v5/tokenizer.model
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v5/tokenizer.json
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v-83370-v5/flywheel_model.2.safetensors
chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer: Loading 0: 0%| | 0/508 [00:00<?, ?it/s] Loading 0: 1%| | 5/508 [00:00<00:14, 34.16it/s] Loading 0: 2%|▏ | 12/508 [00:00<00:10, 48.72it/s] Loading 0: 4%|▎ | 18/508 [00:00<00:12, 38.12it/s] Loading 0: 5%|▌ | 27/508 [00:00<00:10, 45.46it/s] Loading 0: 6%|▋ | 32/508 [00:00<00:16, 29.18it/s] Loading 0: 7%|▋ | 38/508 [00:01<00:14, 32.38it/s] Loading 0: 9%|▉ | 47/508 [00:01<00:11, 39.71it/s] Loading 0: 11%|█ | 55/508 [00:01<00:09, 47.51it/s] Loading 0: 12%|█▏ | 61/508 [00:01<00:11, 39.77it/s] Loading 0: 13%|█▎ | 68/508 [00:01<00:10, 41.86it/s] Loading 0: 14%|█▍ | 73/508 [00:02<00:13, 31.11it/s] Loading 0: 15%|█▌ | 78/508 [00:02<00:13, 32.02it/s] Loading 0: 16%|█▌ | 82/508 [00:02<00:13, 32.11it/s] Loading 0: 17%|█▋ | 88/508 [00:02<00:11, 35.12it/s] Loading 0: 19%|█▉ | 97/508 [00:02<00:09, 42.78it/s] Loading 0: 20%|██ | 104/508 [00:02<00:08, 48.21it/s] Loading 0: 22%|██▏ | 110/508 [00:02<00:10, 38.31it/s] Loading 0: 23%|██▎ | 118/508 [00:03<00:10, 36.20it/s] Loading 0: 24%|██▍ | 124/508 [00:03<00:09, 40.50it/s] Loading 0: 26%|██▌ | 131/508 [00:03<00:08, 46.31it/s] Loading 0: 27%|██▋ | 137/508 [00:03<00:09, 38.01it/s] Loading 0: 29%|██▊ | 146/508 [00:03<00:08, 44.21it/s] Loading 0: 30%|███ | 153/508 [00:03<00:07, 49.26it/s] Loading 0: 31%|███▏ | 159/508 [00:04<00:08, 40.13it/s] Loading 0: 33%|███▎ | 168/508 [00:04<00:06, 48.59it/s] Loading 0: 34%|███▍ | 174/508 [00:04<00:10, 32.15it/s] Loading 0: 36%|███▌ | 181/508 [00:04<00:09, 35.94it/s] Loading 0: 37%|███▋ | 190/508 [00:04<00:07, 42.21it/s] Loading 0: 39%|███▊ | 196/508 [00:18<03:10, 1.64it/s] Loading 0: 39%|███▉ | 199/508 [00:19<02:41, 1.91it/s] Loading 0: 40%|████ | 204/508 [00:19<02:02, 2.48it/s] Loading 0: 42%|████▏ | 211/508 [00:19<01:20, 3.70it/s] Loading 0: 43%|████▎ | 216/508 [00:19<01:02, 4.71it/s] Loading 0: 43%|████▎ | 220/508 [00:19<00:48, 5.91it/s] Loading 0: 44%|████▍ | 225/508 [00:20<00:36, 7.80it/s] Loading 0: 46%|████▌ | 232/508 [00:20<00:23, 11.59it/s] Loading 0: 47%|████▋ | 237/508 [00:20<00:19, 13.85it/s] Loading 0: 48%|████▊ | 245/508 [00:20<00:13, 19.38it/s] Loading 0: 49%|████▉ | 251/508 [00:20<00:10, 24.14it/s] Loading 0: 50%|█████ | 256/508 [00:20<00:10, 24.38it/s] Loading 0: 51%|█████▏ | 261/508 [00:21<00:10, 22.81it/s] Loading 0: 53%|█████▎ | 268/508 [00:21<00:08, 28.14it/s] Loading 0: 54%|█████▍ | 276/508 [00:21<00:06, 34.97it/s] Loading 0: 55%|█████▌ | 281/508 [00:21<00:06, 33.74it/s] Loading 0: 57%|█████▋ | 289/508 [00:21<00:05, 39.03it/s] Loading 0: 58%|█████▊ | 296/508 [00:21<00:04, 44.87it/s] Loading 0: 59%|█████▉ | 302/508 [00:21<00:05, 36.51it/s] Loading 0: 61%|██████ | 311/508 [00:22<00:04, 46.35it/s] Loading 0: 62%|██████▏ | 317/508 [00:22<00:06, 31.01it/s] Loading 0: 64%|██████▍ | 324/508 [00:22<00:05, 35.02it/s] Loading 0: 66%|██████▌ | 333/508 [00:22<00:04, 41.02it/s] Loading 0: 67%|██████▋ | 340/508 [00:22<00:03, 46.08it/s] Loading 0: 68%|██████▊ | 346/508 [00:23<00:04, 38.26it/s] Loading 0: 70%|██████▉ | 354/508 [00:23<00:03, 42.16it/s] Loading 0: 71%|███████ | 359/508 [00:23<00:04, 34.06it/s] Loading 0: 72%|███████▏ | 366/508 [00:23<00:03, 37.71it/s] Loading 0: 73%|███████▎ | 373/508 [00:23<00:03, 43.73it/s] Loading 0: 75%|███████▍ | 379/508 [00:23<00:03, 36.32it/s] Loading 0: 76%|███████▋ | 388/508 [00:24<00:02, 42.53it/s] Loading 0: 78%|███████▊ | 395/508 [00:24<00:02, 47.61it/s] Loading 0: 79%|███████▉ | 401/508 [00:24<00:02, 40.72it/s] Loading 0: 80%|███████▉ | 406/508 [00:24<00:03, 30.56it/s] Loading 0: 81%|████████ | 412/508 [00:24<00:02, 33.30it/s] Loading 0: 83%|████████▎ | 421/508 [00:25<00:02, 38.61it/s] Loading 0: 84%|████████▍ | 428/508 [00:25<00:01, 44.24it/s] Loading 0: 85%|████████▌ | 434/508 [00:25<00:02, 36.57it/s] Loading 0: 87%|████████▋ | 443/508 [00:25<00:01, 42.64it/s] Loading 0: 89%|████████▊ | 450/508 [00:25<00:01, 47.61it/s] Loading 0: 90%|████████▉ | 456/508 [00:39<00:32, 1.59it/s] Loading 0: 90%|████████▉ | 457/508 [00:39<00:30, 1.66it/s] Loading 0: 91%|█████████ | 461/508 [00:39<00:21, 2.18it/s] Loading 0: 92%|█████████▏| 466/508 [00:40<00:13, 3.06it/s] Loading 0: 93%|█████████▎| 474/508 [00:40<00:06, 5.05it/s] Loading 0: 94%|█████████▍| 479/508 [00:40<00:04, 6.48it/s] Loading 0: 96%|█████████▌| 487/508 [00:40<00:02, 9.75it/s] Loading 0: 97%|█████████▋| 494/508 [00:40<00:01, 13.46it/s] Loading 0: 98%|█████████▊| 500/508 [00:40<00:00, 16.25it/s] Loading 0: 99%|█████████▉| 505/508 [00:41<00:00, 15.84it/s]
Job chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer completed after 258.05s with status: succeeded
Stopping job with name chaiml-sft-gemma2-28b-v-83370-v5-mkmlizer
Pipeline stage MKMLizer completed in 258.54s
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-v5
Waiting for inference service chaiml-sft-gemma2-28b-v-83370-v5 to be ready
Inference service chaiml-sft-gemma2-28b-v-83370-v5 ready after 120.432373046875s
Pipeline stage MKMLDeployer completed in 120.92s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.7472991943359375s
Received healthy response to inference request in 2.852923631668091s
Received healthy response to inference request in 2.844266414642334s
Received healthy response to inference request in 2.833073377609253s
Received healthy response to inference request in 2.840846538543701s
5 requests
0 failed requests
5th percentile: 2.8346280097961425
10th percentile: 2.836182641983032
20th percentile: 2.8392919063568116
30th percentile: 2.841530513763428
40th percentile: 2.842898464202881
50th percentile: 2.844266414642334
60th percentile: 2.847729301452637
70th percentile: 2.8511921882629396
80th percentile: 3.0317987442016605
90th percentile: 3.389548969268799
95th percentile: 3.568424081802368
99th percentile: 3.7115241718292236
mean time: 3.0236818313598635
Pipeline stage StressChecker completed in 16.28s
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 0.93s
Shutdown handler de-registered
chaiml-sft-gemma2-28b-v_83370_v5 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 0.09s
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-v5-profiler
Waiting for inference service chaiml-sft-gemma2-28b-v-83370-v5-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_v5 status is now torndown due to DeploymentManager action