developer_uid: NischayDnk
submission_id: chaiml-sft-gemma2-28b-v2-_453_v1
model_name: chaiml-sft-gemma2-28b-v2-_453_v1
model_group: ChaiML/sft-gemma2-28b-v2
status: torndown
timestamp: 2025-04-01T06:09:57+00:00
num_battles: 9870
num_wins: 5069
celo_rating: 1289.54
family_friendly_score: 0.5780000000000001
family_friendly_standard_error: 0.006984497118619207
submission_type: basic
model_repo: ChaiML/sft-gemma2-28b-v2-exp1-del5ktop
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': 0.27851226226208364, 'latency_mean': 3.590422742366791, 'latency_p50': 3.5817363262176514, 'latency_p90': 3.968704915046692}, {'batch_size': 2, 'throughput': 0.4231966523615831, 'latency_mean': 4.71773663520813, 'latency_p50': 4.725746273994446, 'latency_p90': 5.242685008049011}, {'batch_size': 3, 'throughput': 0.5315952511761782, 'latency_mean': 5.627605903148651, 'latency_p50': 5.680003046989441, 'latency_p90': 6.139738845825195}, {'batch_size': 5, 'throughput': 0.6736634452816959, 'latency_mean': 7.362246159315109, 'latency_p50': 7.365886807441711, 'latency_p90': 8.117873692512513}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-sft-gemma2-28b-v2-_453_v1
is_internal_developer: False
language_model: ChaiML/sft-gemma2-28b-v2-exp1-del5ktop
model_size: 29B
ranking_group: single
throughput_3p7s: 0.3
us_pacific_date: 2025-03-31
win_ratio: 0.5135764944275583
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-v2-453-v1-mkmlizer
Waiting for job on chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer to finish
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: ║ _____ __ __ ║
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: ║ /___/ ║
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: ║ belonging to: ║
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: ║ Expiration: 2025-04-15 23:59:59 ║
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: ║ ║
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-sft-gemma2it-28b_47770_v3: HTTPConnectionPool(host='chaiml-sft-gemma2it-28b-47770-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: Downloaded to shared memory in 90.686s
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp34915sjc, device:0
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-sft-gemma2it-28b_47770_v3: HTTPConnectionPool(host='chaiml-sft-gemma2it-28b-47770-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: quantized model in 67.852s
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: Processed model ChaiML/sft-gemma2-28b-v2-exp1-del5ktop in 158.538s
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v2-453-v1
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v2-453-v1/config.json
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v2-453-v1/special_tokens_map.json
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v2-453-v1/tokenizer_config.json
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v2-453-v1/tokenizer.model
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v2-453-v1/tokenizer.json
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v2-453-v1/flywheel_model.2.safetensors
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v2-453-v1/flywheel_model.1.safetensors
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sft-gemma2-28b-v2-453-v1/flywheel_model.0.safetensors
chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer: Loading 0: 0%| | 0/508 [00:00<?, ?it/s] Loading 0: 1%| | 4/508 [00:00<00:13, 36.57it/s] Loading 0: 2%|▏ | 12/508 [00:00<00:11, 44.46it/s] Loading 0: 3%|▎ | 17/508 [00:00<00:14, 33.57it/s] Loading 0: 5%|▌ | 27/508 [00:00<00:10, 45.19it/s] Loading 0: 6%|▋ | 32/508 [00:00<00:16, 29.04it/s] Loading 0: 7%|▋ | 37/508 [00:01<00:14, 32.85it/s] Loading 0: 9%|▉ | 45/508 [00:01<00:11, 39.51it/s] Loading 0: 10%|▉ | 50/508 [00:01<00:12, 36.51it/s] Loading 0: 11%|█▏ | 58/508 [00:01<00:10, 42.61it/s] Loading 0: 12%|█▏ | 63/508 [00:01<00:10, 43.80it/s] Loading 0: 13%|█▎ | 68/508 [00:01<00:11, 39.99it/s] Loading 0: 14%|█▍ | 73/508 [00:02<00:14, 29.39it/s] Loading 0: 15%|█▌ | 78/508 [00:02<00:13, 31.11it/s] Loading 0: 16%|█▌ | 82/508 [00:02<00:13, 30.97it/s] Loading 0: 17%|█▋ | 87/508 [00:02<00:12, 34.76it/s] Loading 0: 19%|█▊ | 95/508 [00:02<00:09, 42.23it/s] Loading 0: 20%|█▉ | 100/508 [00:02<00:10, 37.47it/s] Loading 0: 21%|██▏ | 108/508 [00:02<00:09, 40.85it/s] Loading 0: 22%|██▏ | 113/508 [00:03<00:09, 42.48it/s] Loading 0: 23%|██▎ | 118/508 [00:03<00:12, 31.63it/s] Loading 0: 24%|██▍ | 124/508 [00:03<00:10, 36.32it/s] Loading 0: 25%|██▌ | 129/508 [00:03<00:09, 38.45it/s] Loading 0: 27%|██▋ | 135/508 [00:03<00:09, 38.41it/s] Loading 0: 28%|██▊ | 140/508 [00:03<00:09, 40.55it/s] Loading 0: 29%|██▊ | 146/508 [00:03<00:08, 40.89it/s] Loading 0: 30%|██▉ | 151/508 [00:04<00:08, 42.48it/s] Loading 0: 31%|███ | 157/508 [00:04<00:08, 41.10it/s] Loading 0: 32%|███▏ | 162/508 [00:04<00:08, 42.07it/s] Loading 0: 33%|███▎ | 168/508 [00:04<00:07, 44.18it/s] Loading 0: 34%|███▍ | 173/508 [00:04<00:11, 28.87it/s] Loading 0: 35%|███▌ | 179/508 [00:04<00:09, 34.54it/s] Loading 0: 36%|███▌ | 184/508 [00:04<00:08, 37.56it/s] Loading 0: 37%|███▋ | 190/508 [00:05<00:08, 38.02it/s] Loading 0: 38%|███▊ | 195/508 [00:19<04:18, 1.21it/s] Loading 0: 39%|███▉ | 199/508 [00:19<03:15, 1.58it/s] Loading 0: 40%|████ | 204/508 [00:20<02:21, 2.15it/s] Loading 0: 42%|████▏ | 211/508 [00:20<01:29, 3.34it/s] Loading 0: 43%|████▎ | 216/508 [00:20<01:07, 4.35it/s] Loading 0: 43%|████▎ | 220/508 [00:20<00:52, 5.52it/s] Loading 0: 44%|████▍ | 224/508 [00:20<00:40, 7.08it/s] Loading 0: 46%|████▌ | 232/508 [00:20<00:24, 11.23it/s] Loading 0: 47%|████▋ | 237/508 [00:21<00:20, 13.42it/s] Loading 0: 48%|████▊ | 245/508 [00:21<00:13, 19.08it/s] Loading 0: 49%|████▉ | 250/508 [00:21<00:11, 22.53it/s] Loading 0: 50%|█████ | 255/508 [00:21<00:10, 24.76it/s] Loading 0: 51%|█████ | 260/508 [00:21<00:08, 27.76it/s] Loading 0: 52%|█████▏ | 265/508 [00:21<00:09, 26.22it/s] Loading 0: 53%|█████▎ | 269/508 [00:21<00:09, 26.24it/s] Loading 0: 55%|█████▍ | 278/508 [00:22<00:06, 34.58it/s] Loading 0: 56%|█████▌ | 283/508 [00:22<00:06, 37.22it/s] Loading 0: 57%|█████▋ | 289/508 [00:22<00:05, 38.19it/s] Loading 0: 58%|█████▊ | 294/508 [00:22<00:05, 40.39it/s] Loading 0: 59%|█████▉ | 300/508 [00:22<00:05, 40.06it/s] Loading 0: 60%|██████ | 305/508 [00:22<00:04, 41.78it/s] Loading 0: 61%|██████ | 311/508 [00:22<00:04, 45.75it/s] Loading 0: 62%|██████▏ | 316/508 [00:23<00:06, 29.68it/s] Loading 0: 63%|██████▎ | 322/508 [00:23<00:05, 35.07it/s] Loading 0: 64%|██████▍ | 327/508 [00:23<00:04, 37.32it/s] Loading 0: 66%|██████▌ | 333/508 [00:23<00:04, 37.86it/s] Loading 0: 67%|██████▋ | 338/508 [00:23<00:04, 40.11it/s] Loading 0: 68%|██████▊ | 344/508 [00:23<00:04, 38.98it/s] Loading 0: 69%|██████▊ | 349/508 [00:23<00:03, 41.05it/s] Loading 0: 70%|██████▉ | 354/508 [00:24<00:04, 37.07it/s] Loading 0: 71%|███████ | 359/508 [00:24<00:04, 30.11it/s] Loading 0: 71%|███████▏ | 363/508 [00:24<00:04, 31.81it/s] Loading 0: 72%|███████▏ | 367/508 [00:24<00:04, 33.53it/s] Loading 0: 74%|███████▍ | 375/508 [00:24<00:03, 40.26it/s] Loading 0: 75%|███████▍ | 380/508 [00:24<00:03, 35.94it/s] Loading 0: 76%|███████▋ | 388/508 [00:24<00:02, 41.51it/s] Loading 0: 77%|███████▋ | 393/508 [00:25<00:02, 43.04it/s] Loading 0: 78%|███████▊ | 398/508 [00:25<00:02, 40.18it/s] Loading 0: 79%|███████▉ | 403/508 [00:25<00:02, 40.66it/s] Loading 0: 80%|████████ | 408/508 [00:25<00:02, 33.79it/s] Loading 0: 81%|████████ | 412/508 [00:25<00:03, 31.54it/s] Loading 0: 83%|████████▎ | 421/508 [00:25<00:02, 38.92it/s] Loading 0: 84%|████████▎ | 425/508 [00:25<00:02, 38.77it/s] Loading 0: 85%|████████▌ | 432/508 [00:26<00:01, 41.02it/s] Loading 0: 86%|████████▌ | 437/508 [00:26<00:01, 42.66it/s] Loading 0: 87%|████████▋ | 443/508 [00:26<00:01, 39.78it/s] Loading 0: 88%|████████▊ | 448/508 [00:26<00:01, 41.23it/s] Loading 0: 89%|████████▉ | 451/508 [00:40<00:01, 41.23it/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, 4.96it/s] Loading 0: 94%|█████████▍| 479/508 [00:41<00:04, 6.36it/s] Loading 0: 96%|█████████▌| 487/508 [00:41<00:02, 9.63it/s] Loading 0: 97%|█████████▋| 492/508 [00:41<00:01, 12.08it/s] Loading 0: 98%|█████████▊| 497/508 [00:41<00:00, 14.62it/s] Loading 0: 99%|█████████▉| 502/508 [00:42<00:00, 15.92it/s] Loading 0: 100%|█████████▉| 506/508 [00:42<00:00, 18.45it/s]
Job chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer completed after 187.7s with status: succeeded
Stopping job with name chaiml-sft-gemma2-28b-v2-453-v1-mkmlizer
Pipeline stage MKMLizer completed in 188.14s
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-v2-453-v1
Waiting for inference service chaiml-sft-gemma2-28b-v2-453-v1 to be ready
Failed to get response for submission chaiml-sft-gemma2it-28b_47770_v3: HTTPConnectionPool(host='chaiml-sft-gemma2it-28b-47770-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-sft-gemma2it-28b_47770_v3: HTTPConnectionPool(host='chaiml-sft-gemma2it-28b-47770-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-sft-gemma2-28b-v2-453-v1 ready after 120.49519991874695s
Pipeline stage MKMLDeployer completed in 120.95s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.7708284854888916s
Received healthy response to inference request in 3.415334701538086s
Received healthy response to inference request in 3.6758742332458496s
Received healthy response to inference request in 3.674730062484741s
Received healthy response to inference request in 3.349123001098633s
5 requests
0 failed requests
5th percentile: 3.3623653411865235
10th percentile: 3.3756076812744142
20th percentile: 3.4020923614501952
30th percentile: 3.467213773727417
40th percentile: 3.5709719181060793
50th percentile: 3.674730062484741
60th percentile: 3.6751877307891845
70th percentile: 3.6756453990936278
80th percentile: 3.694865083694458
90th percentile: 3.7328467845916746
95th percentile: 3.751837635040283
99th percentile: 3.76703031539917
mean time: 3.5771780967712403
Pipeline stage StressChecker completed in 19.05s
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 0.60s
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 0.65s
Shutdown handler de-registered
chaiml-sft-gemma2-28b-v2-_453_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 5578.63s
Shutdown handler de-registered
chaiml-sft-gemma2-28b-v2-_453_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-sft-gemma2-28b-v2-_453_v1 status is now torndown due to DeploymentManager action