developer_uid: NischayDnk
submission_id: chaiml-deepseek32b-sfts_56745_v1
model_name: chaiml-deepseek32b-sfts_56745_v1
model_group: ChaiML/deepseek32b-sfts1
status: torndown
timestamp: 2025-05-17T19:28:54+00:00
num_battles: 11269
num_wins: 5571
celo_rating: 1275.15
family_friendly_score: 0.589
family_friendly_standard_error: 0.006958146304871722
submission_type: basic
model_repo: ChaiML/deepseek32b-sfts1-retryv2top20k-1
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': 0.3875851641881194, 'latency_mean': 2.580017453432083, 'latency_p50': 2.5901756286621094, 'latency_p90': 2.8864848136901857}, {'batch_size': 3, 'throughput': 0.8730370706031793, 'latency_mean': 3.432435222864151, 'latency_p50': 3.428696632385254, 'latency_p90': 3.800770664215088}, {'batch_size': 5, 'throughput': 1.2023300562673045, 'latency_mean': 4.137108021974564, 'latency_p50': 4.159923672676086, 'latency_p90': 4.579379463195801}, {'batch_size': 6, 'throughput': 1.3094425078893033, 'latency_mean': 4.5553409707546235, 'latency_p50': 4.509570240974426, 'latency_p90': 5.122000098228455}, {'batch_size': 8, 'throughput': 1.4846794136565782, 'latency_mean': 5.332482438087464, 'latency_p50': 5.3142887353897095, 'latency_p90': 6.059824609756469}, {'batch_size': 10, 'throughput': 1.6284097001287348, 'latency_mean': 6.095003434419632, 'latency_p50': 6.050014853477478, 'latency_p90': 6.928724074363708}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-deepseek32b-sfts_56745_v1
is_internal_developer: False
language_model: ChaiML/deepseek32b-sfts1-retryv2top20k-1
model_size: 33B
ranking_group: single
throughput_3p7s: 1.02
us_pacific_date: 2025-05-17
win_ratio: 0.4943650723223001
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': ['\n', '<|im_end|>', '<|im_start|>'], '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-deepseek32b-sfts-56745-v1-mkmlizer
Waiting for job on chaiml-deepseek32b-sfts-56745-v1-mkmlizer to finish
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: ║ _____ __ __ ║
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: ║ /___/ ║
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: ║ ║
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: ║ Version: 0.12.8 ║
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: ║ ║
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: ║ belonging to: ║
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: ║ ║
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: ║ ║
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: Downloaded to shared memory in 111.222s
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8wcjwdaj, device:0
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: quantized model in 64.810s
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: Processed model ChaiML/deepseek32b-sfts1-retryv2top20k-1 in 176.032s
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-deepseek32b-sfts-56745-v1
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-deepseek32b-sfts-56745-v1/config.json
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-deepseek32b-sfts-56745-v1/special_tokens_map.json
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-deepseek32b-sfts-56745-v1/tokenizer_config.json
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-deepseek32b-sfts-56745-v1/tokenizer.json
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/chaiml-deepseek32b-sfts-56745-v1/flywheel_model.2.safetensors
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-deepseek32b-sfts-56745-v1/flywheel_model.0.safetensors
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-deepseek32b-sfts-56745-v1/flywheel_model.1.safetensors
chaiml-deepseek32b-sfts-56745-v1-mkmlizer: Loading 0: 0%| | 0/771 [00:00<?, ?it/s] Loading 0: 1%| | 5/771 [00:00<00:21, 36.36it/s] Loading 0: 2%|▏ | 16/771 [00:00<00:10, 69.72it/s] Loading 0: 4%|▎ | 27/771 [00:00<00:09, 81.87it/s] Loading 0: 5%|▍ | 36/771 [00:00<00:08, 81.68it/s] Loading 0: 6%|▌ | 46/771 [00:00<00:13, 52.43it/s] Loading 0: 7%|▋ | 53/771 [00:01<00:16, 43.87it/s] Loading 0: 8%|▊ | 64/771 [00:01<00:12, 55.78it/s] Loading 0: 10%|▉ | 75/771 [00:01<00:10, 65.77it/s] Loading 0: 11%|█ | 83/771 [00:01<00:10, 67.52it/s] Loading 0: 12%|█▏ | 91/771 [00:01<00:10, 64.84it/s] Loading 0: 14%|█▎ | 106/771 [00:01<00:11, 59.13it/s] Loading 0: 15%|█▍ | 113/771 [00:01<00:11, 56.47it/s] Loading 0: 16%|█▌ | 121/771 [00:02<00:11, 56.37it/s] Loading 0: 17%|█▋ | 132/771 [00:02<00:09, 66.60it/s] Loading 0: 18%|█▊ | 142/771 [00:02<00:08, 73.07it/s] Loading 0: 20%|█▉ | 152/771 [00:02<00:07, 77.93it/s] Loading 0: 21%|██ | 161/771 [00:02<00:08, 72.85it/s] Loading 0: 22%|██▏ | 169/771 [00:02<00:11, 50.21it/s] Loading 0: 23%|██▎ | 176/771 [00:02<00:11, 50.78it/s] Loading 0: 24%|██▍ | 184/771 [00:03<00:10, 56.55it/s] Loading 0: 25%|██▌ | 195/771 [00:03<00:08, 67.82it/s] Loading 0: 26%|██▋ | 203/771 [00:03<00:08, 68.77it/s] Loading 0: 27%|██▋ | 211/771 [00:03<00:08, 66.30it/s] Loading 0: 29%|██▉ | 226/771 [00:03<00:08, 62.11it/s] Loading 0: 30%|███ | 233/771 [00:03<00:10, 51.09it/s] Loading 0: 32%|███▏ | 244/771 [00:03<00:08, 61.39it/s] Loading 0: 33%|███▎ | 255/771 [00:04<00:07, 69.88it/s] Loading 0: 34%|███▍ | 263/771 [00:04<00:07, 70.46it/s] Loading 0: 35%|███▌ | 271/771 [00:04<00:07, 67.31it/s] Loading 0: 37%|███▋ | 286/771 [00:04<00:07, 61.75it/s] Loading 0: 38%|███▊ | 293/771 [00:04<00:09, 51.39it/s] Loading 0: 39%|███▉ | 303/771 [00:19<03:41, 2.11it/s] Loading 0: 40%|████ | 309/771 [00:19<02:55, 2.64it/s] Loading 0: 41%|████ | 317/771 [00:20<02:05, 3.62it/s] Loading 0: 43%|████▎ | 328/771 [00:20<01:20, 5.52it/s] Loading 0: 44%|████▍ | 338/771 [00:20<00:54, 7.87it/s] Loading 0: 45%|████▍ | 346/771 [00:20<00:42, 9.92it/s] Loading 0: 46%|████▌ | 353/771 [00:20<00:36, 11.40it/s] Loading 0: 47%|████▋ | 364/771 [00:20<00:24, 16.75it/s] Loading 0: 49%|████▊ | 375/771 [00:21<00:16, 23.35it/s] Loading 0: 50%|████▉ | 383/771 [00:21<00:13, 28.34it/s] Loading 0: 51%|█████ | 391/771 [00:21<00:11, 33.01it/s] Loading 0: 53%|█████▎ | 406/771 [00:21<00:09, 40.09it/s] Loading 0: 54%|█████▎ | 413/771 [00:21<00:09, 37.82it/s] Loading 0: 55%|█████▍ | 424/771 [00:21<00:07, 47.83it/s] Loading 0: 56%|█████▋ | 435/771 [00:22<00:05, 57.88it/s] Loading 0: 58%|█████▊ | 444/771 [00:22<00:05, 63.50it/s] Loading 0: 59%|█████▉ | 453/771 [00:22<00:04, 63.79it/s] Loading 0: 60%|██████ | 466/771 [00:22<00:05, 58.77it/s] Loading 0: 61%|██████▏ | 473/771 [00:22<00:05, 49.72it/s] Loading 0: 63%|██████▎ | 484/771 [00:22<00:04, 59.89it/s] Loading 0: 64%|██████▍ | 495/771 [00:22<00:04, 68.91it/s] Loading 0: 65%|██████▌ | 504/771 [00:23<00:03, 72.67it/s] Loading 0: 67%|██████▋ | 513/771 [00:23<00:03, 70.12it/s] Loading 0: 68%|██████▊ | 526/771 [00:23<00:03, 61.59it/s] Loading 0: 69%|██████▉ | 533/771 [00:23<00:04, 51.34it/s] Loading 0: 71%|███████ | 544/771 [00:23<00:03, 61.49it/s] Loading 0: 72%|███████▏ | 555/771 [00:23<00:03, 70.76it/s] Loading 0: 73%|███████▎ | 564/771 [00:24<00:02, 74.39it/s] Loading 0: 74%|███████▍ | 573/771 [00:24<00:02, 71.70it/s] Loading 0: 76%|███████▌ | 586/771 [00:24<00:02, 63.29it/s] Loading 0: 77%|███████▋ | 594/771 [00:24<00:03, 53.63it/s] Loading 0: 78%|███████▊ | 604/771 [00:24<00:02, 61.91it/s] Loading 0: 80%|███████▉ | 615/771 [00:24<00:02, 71.28it/s] Loading 0: 81%|████████ | 624/771 [00:24<00:01, 74.65it/s] Loading 0: 82%|████████▏ | 633/771 [00:39<01:03, 2.17it/s] Loading 0: 84%|████████▍ | 646/771 [00:39<00:37, 3.34it/s] Loading 0: 85%|████████▍ | 654/771 [00:40<00:27, 4.21it/s] Loading 0: 86%|████████▌ | 664/771 [00:40<00:18, 5.94it/s] Loading 0: 88%|████████▊ | 675/771 [00:40<00:11, 8.53it/s] Loading 0: 89%|████████▊ | 683/771 [00:40<00:08, 10.96it/s] Loading 0: 90%|████████▉ | 691/771 [00:40<00:05, 13.98it/s] Loading 0: 92%|█████████▏| 706/771 [00:40<00:03, 20.24it/s] Loading 0: 92%|█████████▏| 713/771 [00:40<00:02, 21.88it/s] Loading 0: 94%|█████████▍| 724/771 [00:41<00:01, 29.38it/s] Loading 0: 95%|█████████▌| 735/771 [00:41<00:00, 37.90it/s] Loading 0: 96%|█████████▋| 743/771 [00:41<00:00, 42.96it/s] Loading 0: 97%|█████████▋| 751/771 [00:41<00:00, 46.30it/s] Loading 0: 99%|█████████▉| 766/771 [00:49<00:01, 4.35it/s]
Job chaiml-deepseek32b-sfts-56745-v1-mkmlizer completed after 207.82s with status: succeeded
Stopping job with name chaiml-deepseek32b-sfts-56745-v1-mkmlizer
Pipeline stage MKMLizer completed in 208.31s
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-deepseek32b-sfts-56745-v1
Waiting for inference service chaiml-deepseek32b-sfts-56745-v1 to be ready
Inference service chaiml-deepseek32b-sfts-56745-v1 ready after 140.6061291694641s
Pipeline stage MKMLDeployer completed in 141.07s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1179873943328857s
Received healthy response to inference request in 2.5085084438323975s
Received healthy response to inference request in 2.898365020751953s
Received healthy response to inference request in 2.4519922733306885s
Received healthy response to inference request in 2.9458093643188477s
5 requests
0 failed requests
5th percentile: 2.46329550743103
10th percentile: 2.474598741531372
20th percentile: 2.497205209732056
30th percentile: 2.5864797592163087
40th percentile: 2.7424223899841307
50th percentile: 2.898365020751953
60th percentile: 2.917342758178711
70th percentile: 2.936320495605469
80th percentile: 2.9802449703216554
90th percentile: 3.0491161823272703
95th percentile: 3.083551788330078
99th percentile: 3.1111002731323243
mean time: 2.7845324993133547
Pipeline stage StressChecker completed in 15.44s
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 0.69s
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 0.64s
Shutdown handler de-registered
chaiml-deepseek32b-sfts_56745_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 4872.61s
Shutdown handler de-registered
chaiml-deepseek32b-sfts_56745_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-deepseek32b-sfts_56745_v1 status is now torndown due to DeploymentManager action