developer_uid: NischayDnk
submission_id: chaiml-qwen32b-sft-20k-_28534_v3
model_name: chaiml-qwen32b-sft-20k-_28534_v3
model_group: ChaiML/qwen32b-sft-20k-f
status: torndown
timestamp: 2025-04-16T18:02:01+00:00
num_battles: 6292
num_wins: 3080
celo_rating: 1281.34
family_friendly_score: 0.5684
family_friendly_standard_error: 0.007004590494811242
submission_type: basic
model_repo: ChaiML/qwen32b-sft-20k-ffsys-5e-exp1
model_architecture: Qwen2ForCausalLM
model_num_parameters: 32763417600.0
best_of: 4
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.2790245985361459, 'latency_mean': 3.5838139939308165, 'latency_p50': 3.5917251110076904, 'latency_p90': 3.981761908531189}, {'batch_size': 2, 'throughput': 0.44661837509155167, 'latency_mean': 4.47485652923584, 'latency_p50': 4.485369801521301, 'latency_p90': 4.925808215141296}, {'batch_size': 3, 'throughput': 0.6041557694272494, 'latency_mean': 4.939441328048706, 'latency_p50': 4.941832184791565, 'latency_p90': 5.513598537445068}, {'batch_size': 4, 'throughput': 0.7171960825676901, 'latency_mean': 5.548812555074692, 'latency_p50': 5.578993558883667, 'latency_p90': 6.134155011177063}, {'batch_size': 5, 'throughput': 0.8176225211067459, 'latency_mean': 6.09134538769722, 'latency_p50': 6.115275859832764, 'latency_p90': 6.768362927436828}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-qwen32b-sft-20k-_28534_v3
is_internal_developer: False
language_model: ChaiML/qwen32b-sft-20k-ffsys-5e-exp1
model_size: 33B
ranking_group: single
throughput_3p7s: 0.31
us_pacific_date: 2025-04-16
win_ratio: 0.48951048951048953
generation_params: {'temperature': 0.45, 'top_p': 0.94, 'min_p': 0.025, 'top_k': 40, 'presence_penalty': 0.3, 'frequency_penalty': 0.3, 'stopping_words': ['<|im_end|>', '<|im_start|>', '\n'], 'max_input_tokens': 768, 'best_of': 4, '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-qwen32b-sft-20k-28534-v3-mkmlizer
Waiting for job on chaiml-qwen32b-sft-20k-28534-v3-mkmlizer to finish
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: ║ _____ __ __ ║
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: ║ /___/ ║
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: ║ ║
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: ║ ║
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: ║ belonging to: ║
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: ║ ║
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: ║ ║
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: Downloaded to shared memory in 83.344s
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjfq0lv5o, device:0
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: quantized model in 62.667s
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: Processed model ChaiML/qwen32b-sft-20k-ffsys-5e-exp1 in 146.011s
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v3
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v3/config.json
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v3/added_tokens.json
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v3/tokenizer_config.json
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v3/special_tokens_map.json
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v3/merges.txt
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v3/vocab.json
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v3/tokenizer.json
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v3/flywheel_model.2.safetensors
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v3/flywheel_model.1.safetensors
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen32b-sft-20k-28534-v3/flywheel_model.0.safetensors
chaiml-qwen32b-sft-20k-28534-v3-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 1%| | 5/771 [00:00<00:19, 39.17it/s] Loading 0: 2%|▏ | 16/771 [00:00<00:09, 76.02it/s] Loading 0: 4%|▎ | 27/771 [00:00<00:08, 90.13it/s] Loading 0: 5%|▍ | 37/771 [00:00<00:07, 91.96it/s] Loading 0: 6%|▌ | 47/771 [00:00<00:13, 53.59it/s] Loading 0: 7%|▋ | 55/771 [00:00<00:13, 51.78it/s] Loading 0: 8%|▊ | 65/771 [00:01<00:12, 57.45it/s] Loading 0: 10%|▉ | 77/771 [00:01<00:10, 65.46it/s] Loading 0: 11%|█▏ | 88/771 [00:01<00:09, 75.23it/s] Loading 0: 13%|█▎ | 98/771 [00:01<00:08, 80.52it/s] Loading 0: 14%|█▍ | 107/771 [00:01<00:11, 60.19it/s] Loading 0: 15%|█▍ | 115/771 [00:01<00:10, 64.29it/s] Loading 0: 16%|█▌ | 123/771 [00:01<00:10, 64.20it/s] Loading 0: 17%|█▋ | 133/771 [00:02<00:09, 66.69it/s] Loading 0: 20%|█▉ | 151/771 [00:02<00:06, 89.47it/s] Loading 0: 21%|██ | 161/771 [00:02<00:07, 78.28it/s] Loading 0: 22%|██▏ | 170/771 [00:02<00:10, 56.39it/s] Loading 0: 23%|██▎ | 177/771 [00:02<00:10, 55.61it/s] Loading 0: 24%|██▍ | 185/771 [00:02<00:10, 56.76it/s] Loading 0: 25%|██▌ | 196/771 [00:02<00:08, 65.75it/s] Loading 0: 27%|██▋ | 207/771 [00:03<00:07, 75.47it/s] Loading 0: 28%|██▊ | 216/771 [00:03<00:07, 78.75it/s] Loading 0: 29%|██▉ | 226/771 [00:03<00:09, 59.72it/s] Loading 0: 30%|███ | 234/771 [00:03<00:10, 52.70it/s] Loading 0: 32%|███▏ | 245/771 [00:03<00:08, 59.61it/s] Loading 0: 33%|███▎ | 257/771 [00:03<00:07, 66.85it/s] Loading 0: 35%|███▍ | 269/771 [00:04<00:06, 72.29it/s] Loading 0: 37%|███▋ | 286/771 [00:04<00:07, 68.35it/s] Loading 0: 38%|███▊ | 294/771 [00:04<00:08, 58.33it/s] Loading 0: 39%|███▉ | 303/771 [00:18<03:12, 2.43it/s] Loading 0: 41%|████ | 315/771 [00:18<02:08, 3.56it/s] Loading 0: 42%|████▏ | 326/771 [00:18<01:28, 5.01it/s] Loading 0: 43%|████▎ | 335/771 [00:19<01:06, 6.59it/s] Loading 0: 45%|████▍ | 346/771 [00:19<00:47, 8.91it/s] Loading 0: 46%|████▌ | 353/771 [00:19<00:40, 10.26it/s] Loading 0: 47%|████▋ | 365/771 [00:19<00:27, 14.87it/s] Loading 0: 49%|████▉ | 377/771 [00:19<00:19, 20.58it/s] Loading 0: 50%|█████ | 389/771 [00:20<00:13, 27.32it/s] Loading 0: 53%|█████▎ | 406/771 [00:20<00:10, 35.44it/s] Loading 0: 54%|█████▎ | 414/771 [00:20<00:09, 35.80it/s] Loading 0: 55%|█████▌ | 425/771 [00:20<00:08, 42.81it/s] Loading 0: 57%|█████▋ | 437/771 [00:20<00:06, 50.93it/s] Loading 0: 58%|█████▊ | 449/771 [00:20<00:05, 58.37it/s] Loading 0: 60%|██████ | 466/771 [00:21<00:05, 60.97it/s] Loading 0: 61%|██████▏ | 474/771 [00:21<00:05, 54.74it/s] Loading 0: 63%|██████▎ | 485/771 [00:21<00:04, 60.34it/s] Loading 0: 64%|██████▍ | 497/771 [00:21<00:04, 66.82it/s] Loading 0: 66%|██████▌ | 509/771 [00:21<00:03, 71.79it/s] Loading 0: 68%|██████▊ | 526/771 [00:22<00:03, 67.35it/s] Loading 0: 69%|██████▉ | 534/771 [00:22<00:04, 58.85it/s] Loading 0: 71%|███████ | 545/771 [00:22<00:03, 64.29it/s] Loading 0: 72%|███████▏ | 557/771 [00:22<00:03, 70.06it/s] Loading 0: 74%|███████▍ | 569/771 [00:22<00:02, 74.68it/s] Loading 0: 76%|███████▌ | 586/771 [00:22<00:02, 71.91it/s] Loading 0: 77%|███████▋ | 594/771 [00:23<00:02, 61.72it/s] Loading 0: 78%|███████▊ | 605/771 [00:23<00:02, 66.20it/s] Loading 0: 80%|████████ | 617/771 [00:23<00:02, 71.62it/s] Loading 0: 81%|████████▏ | 627/771 [00:37<00:56, 2.54it/s] Loading 0: 82%|████████▏ | 635/771 [00:37<00:41, 3.29it/s] Loading 0: 84%|████████▍ | 646/771 [00:38<00:26, 4.64it/s] Loading 0: 85%|████████▍ | 653/771 [00:38<00:21, 5.62it/s] Loading 0: 86%|████████▋ | 665/771 [00:38<00:12, 8.39it/s] Loading 0: 88%|████████▊ | 677/771 [00:38<00:07, 12.03it/s] Loading 0: 89%|████████▉ | 689/771 [00:38<00:04, 16.69it/s] Loading 0: 92%|█████████▏| 706/771 [00:39<00:02, 23.71it/s] Loading 0: 93%|█████████▎| 714/771 [00:39<00:02, 25.86it/s] Loading 0: 94%|█████████▍| 725/771 [00:39<00:01, 32.29it/s] Loading 0: 96%|█████████▌| 737/771 [00:39<00:00, 40.25it/s] Loading 0: 97%|█████████▋| 749/771 [00:39<00:00, 48.30it/s] Loading 0: 99%|█████████▉| 766/771 [00:47<00:00, 5.32it/s]
Job chaiml-qwen32b-sft-20k-28534-v3-mkmlizer completed after 188.31s with status: succeeded
Stopping job with name chaiml-qwen32b-sft-20k-28534-v3-mkmlizer
Pipeline stage MKMLizer completed in 188.90s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen32b-sft-20k-28534-v3
Waiting for inference service chaiml-qwen32b-sft-20k-28534-v3 to be ready
Inference service chaiml-qwen32b-sft-20k-28534-v3 ready after 130.4722957611084s
Pipeline stage MKMLDeployer completed in 131.05s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.9806947708129883s
Received healthy response to inference request in 3.561479091644287s
Received healthy response to inference request in 3.500624179840088s
Received healthy response to inference request in 3.4664807319641113s
Received healthy response to inference request in 3.5189292430877686s
5 requests
0 failed requests
5th percentile: 3.4733094215393066
10th percentile: 3.4801381111145018
20th percentile: 3.4937954902648927
30th percentile: 3.504285192489624
40th percentile: 3.511607217788696
50th percentile: 3.5189292430877686
60th percentile: 3.535949182510376
70th percentile: 3.5529691219329833
80th percentile: 3.6453222274780273
90th percentile: 3.813008499145508
95th percentile: 3.896851634979248
99th percentile: 3.96392614364624
mean time: 3.6056416034698486
Pipeline stage StressChecker completed in 19.35s
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 0.73s
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 0.72s
Shutdown handler de-registered
chaiml-qwen32b-sft-20k-_28534_v3 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 5963.79s
Shutdown handler de-registered
chaiml-qwen32b-sft-20k-_28534_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen32b-sft-20k-_28534_v3 status is now torndown due to DeploymentManager action