developer_uid: NischayDnk
submission_id: chaiml-qwen25-32b-sftmo_55653_v1
model_name: chaiml-qwen25-32b-sftmo_55653_v1
model_group: ChaiML/qwen25-32b-sftmor
status: torndown
timestamp: 2025-05-13T20:50:12+00:00
num_battles: 9709
num_wins: 4956
celo_rating: 1283.4
family_friendly_score: 0.5711999999999999
family_friendly_standard_error: 0.006999007929699752
submission_type: basic
model_repo: ChaiML/qwen25-32b-sftmorelora-retryv2-top20k-maskprompt-2e
model_architecture: Qwen2ForCausalLM
model_num_parameters: 32763417600.0
best_of: 5
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.3873296249600702, 'latency_mean': 2.581726384162903, 'latency_p50': 2.594767451286316, 'latency_p90': 2.8786208391189576}, {'batch_size': 3, 'throughput': 0.8745502357388957, 'latency_mean': 3.4077278316020965, 'latency_p50': 3.419059634208679, 'latency_p90': 3.8048784494400025}, {'batch_size': 5, 'throughput': 1.2033438806784362, 'latency_mean': 4.146637586355209, 'latency_p50': 4.157623291015625, 'latency_p90': 4.580155992507935}, {'batch_size': 6, 'throughput': 1.3131855345670833, 'latency_mean': 4.535572472810745, 'latency_p50': 4.559195876121521, 'latency_p90': 5.043654131889343}, {'batch_size': 8, 'throughput': 1.5010604882207912, 'latency_mean': 5.281764086484909, 'latency_p50': 5.30308985710144, 'latency_p90': 6.038395380973816}, {'batch_size': 10, 'throughput': 1.6231843742946672, 'latency_mean': 6.0651033496856686, 'latency_p50': 6.1245808601379395, 'latency_p90': 6.807820606231689}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-qwen25-32b-sftmo_55653_v1
is_internal_developer: False
language_model: ChaiML/qwen25-32b-sftmorelora-retryv2-top20k-maskprompt-2e
model_size: 33B
ranking_group: single
throughput_3p7s: 1.02
us_pacific_date: 2025-05-13
win_ratio: 0.5104542177361211
generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 40, 'presence_penalty': 0.35, 'frequency_penalty': 0.35, 'stopping_words': ['<|im_start|>', '\n', '<|im_end|>'], 'max_input_tokens': 768, 'best_of': 5, '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-qwen25-32b-sftmo-55653-v1-mkmlizer
Waiting for job on chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer to finish
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: ║ _____ __ __ ║
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: ║ /___/ ║
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: ║ ║
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: ║ ║
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: ║ belonging to: ║
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: ║ ║
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: ║ ║
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: Downloaded to shared memory in 147.413s
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8b5a1iy2, device:0
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: quantized model in 63.458s
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: Processed model ChaiML/qwen25-32b-sftmorelora-retryv2-top20k-maskprompt-2e in 210.872s
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v1
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v1/config.json
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: cp /dev/shm/model_cache/added_tokens.json s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v1/added_tokens.json
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v1/special_tokens_map.json
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v1/tokenizer_config.json
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: cp /dev/shm/model_cache/merges.txt s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v1/merges.txt
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: cp /dev/shm/model_cache/vocab.json s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v1/vocab.json
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v1/tokenizer.json
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v1/flywheel_model.2.safetensors
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v1/flywheel_model.0.safetensors
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-qwen25-32b-sftmo-55653-v1/flywheel_model.1.safetensors
chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 1%| | 5/771 [00:00<00:18, 40.65it/s] Loading 0: 2%|▏ | 17/771 [00:00<00:10, 68.88it/s] Loading 0: 4%|▎ | 28/771 [00:00<00:08, 84.84it/s] Loading 0: 5%|▍ | 38/771 [00:00<00:08, 90.21it/s] Loading 0: 6%|▌ | 48/771 [00:00<00:13, 52.85it/s] Loading 0: 7%|▋ | 55/771 [00:00<00:13, 53.67it/s] Loading 0: 8%|▊ | 65/771 [00:01<00:11, 58.91it/s] Loading 0: 10%|▉ | 77/771 [00:01<00:10, 66.85it/s] Loading 0: 11%|█▏ | 88/771 [00:01<00:08, 76.74it/s] Loading 0: 13%|█▎ | 98/771 [00:01<00:08, 82.32it/s] Loading 0: 14%|█▍ | 107/771 [00:01<00:10, 60.49it/s] Loading 0: 15%|█▍ | 115/771 [00:01<00:10, 64.58it/s] Loading 0: 16%|█▌ | 123/771 [00:01<00:10, 64.30it/s] Loading 0: 17%|█▋ | 132/771 [00:01<00:09, 70.26it/s] Loading 0: 18%|█▊ | 142/771 [00:02<00:08, 77.51it/s] Loading 0: 20%|█▉ | 152/771 [00:02<00:07, 82.84it/s] Loading 0: 21%|██ | 161/771 [00:02<00:07, 77.11it/s] Loading 0: 22%|██▏ | 170/771 [00:02<00:11, 53.88it/s] Loading 0: 23%|██▎ | 177/771 [00:02<00:11, 53.63it/s] Loading 0: 24%|██▍ | 185/771 [00:02<00:10, 55.52it/s] Loading 0: 25%|██▌ | 196/771 [00:02<00:08, 67.31it/s] Loading 0: 27%|██▋ | 207/771 [00:03<00:07, 77.33it/s] Loading 0: 28%|██▊ | 217/771 [00:03<00:06, 82.77it/s] Loading 0: 29%|██▉ | 226/771 [00:03<00:09, 60.24it/s] Loading 0: 30%|███ | 234/771 [00:03<00:10, 52.75it/s] Loading 0: 32%|███▏ | 245/771 [00:03<00:08, 59.84it/s] Loading 0: 33%|███▎ | 257/771 [00:03<00:07, 67.06it/s] Loading 0: 35%|███▍ | 268/771 [00:04<00:06, 76.20it/s] Loading 0: 36%|███▌ | 278/771 [00:04<00:06, 81.65it/s] Loading 0: 37%|███▋ | 287/771 [00:04<00:08, 59.72it/s] Loading 0: 38%|███▊ | 295/771 [00:04<00:08, 56.50it/s] Loading 0: 39%|███▉ | 303/771 [00:19<03:55, 1.99it/s] Loading 0: 40%|████ | 312/771 [00:19<02:42, 2.82it/s] Loading 0: 42%|████▏ | 320/771 [00:19<01:57, 3.84it/s] Loading 0: 43%|████▎ | 329/771 [00:19<01:21, 5.40it/s] Loading 0: 45%|████▍ | 346/771 [00:19<00:46, 9.23it/s] Loading 0: 46%|████▌ | 353/771 [00:20<00:39, 10.51it/s] Loading 0: 47%|████▋ | 365/771 [00:20<00:27, 14.99it/s] Loading 0: 49%|████▉ | 377/771 [00:20<00:19, 20.55it/s] Loading 0: 50%|█████ | 389/771 [00:20<00:14, 27.20it/s] Loading 0: 53%|█████▎ | 406/771 [00:20<00:10, 34.77it/s] Loading 0: 54%|█████▎ | 414/771 [00:20<00:10, 35.49it/s] Loading 0: 55%|█████▌ | 425/771 [00:21<00:08, 42.43it/s] Loading 0: 57%|█████▋ | 437/771 [00:21<00:06, 50.52it/s] Loading 0: 58%|█████▊ | 449/771 [00:21<00:05, 58.54it/s] Loading 0: 60%|██████ | 466/771 [00:21<00:04, 61.74it/s] Loading 0: 61%|██████▏ | 474/771 [00:21<00:05, 54.94it/s] Loading 0: 63%|██████▎ | 485/771 [00:21<00:04, 61.11it/s] Loading 0: 64%|██████▍ | 497/771 [00:22<00:04, 67.66it/s] Loading 0: 66%|██████▌ | 509/771 [00:22<00:03, 73.12it/s] Loading 0: 68%|██████▊ | 526/771 [00:22<00:03, 71.34it/s] Loading 0: 69%|██████▉ | 534/771 [00:22<00:03, 61.02it/s] Loading 0: 71%|███████ | 545/771 [00:22<00:03, 65.31it/s] Loading 0: 72%|███████▏ | 556/771 [00:22<00:02, 73.63it/s] Loading 0: 74%|███████▎ | 568/771 [00:23<00:02, 77.53it/s] Loading 0: 75%|███████▌ | 579/771 [00:23<00:02, 84.68it/s] Loading 0: 76%|███████▋ | 589/771 [00:23<00:03, 60.52it/s] Loading 0: 77%|███████▋ | 597/771 [00:23<00:02, 60.68it/s] Loading 0: 78%|███████▊ | 605/771 [00:23<00:02, 61.21it/s] Loading 0: 80%|███████▉ | 616/771 [00:23<00:02, 71.71it/s] Loading 0: 81%|████████▏ | 627/771 [00:38<01:02, 2.30it/s] Loading 0: 83%|████████▎ | 638/771 [00:38<00:40, 3.32it/s] Loading 0: 84%|████████▍ | 647/771 [00:38<00:28, 4.33it/s] Loading 0: 85%|████████▍ | 654/771 [00:39<00:21, 5.44it/s] Loading 0: 86%|████████▋ | 665/771 [00:39<00:13, 7.97it/s] Loading 0: 88%|████████▊ | 677/771 [00:39<00:08, 11.64it/s] Loading 0: 89%|████████▉ | 689/771 [00:39<00:05, 16.36it/s] Loading 0: 92%|█████████▏| 706/771 [00:39<00:02, 23.50it/s] Loading 0: 93%|█████████▎| 714/771 [00:39<00:02, 25.74it/s] Loading 0: 94%|█████████▍| 725/771 [00:40<00:01, 32.30it/s] Loading 0: 96%|█████████▌| 737/771 [00:40<00:00, 40.50it/s] Loading 0: 97%|█████████▋| 749/771 [00:40<00:00, 49.18it/s] Loading 0: 99%|█████████▉| 766/771 [00:48<00:00, 5.30it/s]
Job chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer completed after 249.29s with status: succeeded
Stopping job with name chaiml-qwen25-32b-sftmo-55653-v1-mkmlizer
Pipeline stage MKMLizer completed in 249.79s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-qwen25-32b-sftmo-55653-v1
Waiting for inference service chaiml-qwen25-32b-sftmo-55653-v1 to be ready
Inference service chaiml-qwen25-32b-sftmo-55653-v1 ready after 130.572096824646s
Pipeline stage MKMLDeployer completed in 131.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.0367085933685303s
Received healthy response to inference request in 2.882124423980713s
Received healthy response to inference request in 2.5356264114379883s
Received healthy response to inference request in 2.558478355407715s
Received healthy response to inference request in 2.7788290977478027s
5 requests
0 failed requests
5th percentile: 2.5401968002319335
10th percentile: 2.5447671890258787
20th percentile: 2.5539079666137696
30th percentile: 2.6025485038757323
40th percentile: 2.6906888008117678
50th percentile: 2.7788290977478027
60th percentile: 2.820147228240967
70th percentile: 2.8614653587341308
80th percentile: 2.9130412578582763
90th percentile: 2.9748749256134035
95th percentile: 3.005791759490967
99th percentile: 3.0305252265930176
mean time: 2.7583533763885497
Pipeline stage StressChecker completed in 14.95s
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 0.63s
Shutdown handler de-registered
chaiml-qwen25-32b-sftmo_55653_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
%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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2769.45s
Shutdown handler de-registered
chaiml-qwen25-32b-sftmo_55653_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-qwen25-32b-sftmo_55653_v1 status is now torndown due to DeploymentManager action