developer_uid: chai_backend_admin
submission_id: chaiml-ca18-v1-7-dpo-b025_v1
model_name: training123
model_group: ChaiML/ca18-v1-7-dpo_b02
status: torndown
timestamp: 2025-11-19T12:26:15+00:00
num_battles: 6857
num_wins: 3713
celo_rating: 1310.0
family_friendly_score: 0.5102
family_friendly_standard_error: 0.007069596310964298
submission_type: basic
model_repo: ChaiML/ca18-v1-7-dpo_b025
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.6835519866449946, 'latency_mean': 1.462824161052704, 'latency_p50': 1.4544583559036255, 'latency_p90': 1.621590495109558}, {'batch_size': 3, 'throughput': 1.2530657329460182, 'latency_mean': 2.3894653630256655, 'latency_p50': 2.4096503257751465, 'latency_p90': 2.5867326736450194}, {'batch_size': 5, 'throughput': 1.551579375936674, 'latency_mean': 3.210823367834091, 'latency_p50': 3.2079602479934692, 'latency_p90': 3.538021779060364}, {'batch_size': 6, 'throughput': 1.6266762519587443, 'latency_mean': 3.667047551870346, 'latency_p50': 3.677996873855591, 'latency_p90': 4.137199902534484}, {'batch_size': 8, 'throughput': 1.7316553532033843, 'latency_mean': 4.589316613674164, 'latency_p50': 4.60050094127655, 'latency_p90': 5.188780784606934}, {'batch_size': 10, 'throughput': 1.810449240215052, 'latency_mean': 5.47729177236557, 'latency_p50': 5.519266605377197, 'latency_p90': 6.125942611694336}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
is_internal_developer: True
language_model: ChaiML/ca18-v1-7-dpo_b025
model_size: 13B
ranking_group: single
throughput_3p7s: 1.64
us_pacific_date: 2025-11-16
win_ratio: 0.5414904477176608
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['User:', '</s>', 'You:', '\n'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
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-ca18-v1-7-dpo-b025-v1-mkmlizer
Waiting for job on chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer to finish
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ Version: 0.30.2 ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ belonging to: ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ║ ║
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: Downloaded to shared memory in 24.371s
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: Checking if ChaiML/ca18-v1-7-dpo_b025 already exists in ChaiML
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpw_y0ps7y, device:0
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: quantized model in 25.654s
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: Processed model ChaiML/ca18-v1-7-dpo_b025 in 50.026s
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v1-7-dpo-b025-v1/nvidia
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v1-7-dpo-b025-v1/nvidia/special_tokens_map.json
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v1-7-dpo-b025-v1/nvidia/config.json
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v1-7-dpo-b025-v1/nvidia/tokenizer_config.json
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v1-7-dpo-b025-v1/nvidia/tokenizer.json
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v1-7-dpo-b025-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:10, 34.63it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:07, 48.60it/s] Loading 0: 6%|▋ | 23/363 [00:00<00:06, 53.68it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:06, 55.00it/s] Loading 0: 11%|█▏ | 41/363 [00:00<00:05, 56.91it/s] Loading 0: 14%|█▍ | 50/363 [00:00<00:05, 57.70it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:04, 63.80it/s] Loading 0: 18%|█▊ | 67/363 [00:01<00:06, 48.76it/s] Loading 0: 20%|██ | 73/363 [00:01<00:06, 46.29it/s] Loading 0: 23%|██▎ | 82/363 [00:01<00:05, 49.54it/s] Loading 0: 25%|██▌ | 91/363 [00:01<00:05, 51.16it/s] Loading 0: 28%|██▊ | 100/363 [00:01<00:05, 52.40it/s] Loading 0: 30%|███ | 110/363 [00:02<00:04, 55.38it/s] Loading 0: 32%|███▏ | 116/363 [00:02<00:04, 55.52it/s] Loading 0: 34%|███▍ | 123/363 [00:02<00:04, 53.65it/s] Loading 0: 36%|███▌ | 129/363 [00:02<00:04, 52.79it/s] Loading 0: 37%|███▋ | 136/363 [00:02<00:04, 50.04it/s] Loading 0: 39%|███▉ | 142/363 [00:02<00:05, 43.58it/s] Loading 0: 40%|████ | 147/363 [00:02<00:04, 43.25it/s] Loading 0: 42%|████▏ | 153/363 [00:03<00:04, 47.00it/s] Loading 0: 44%|████▎ | 158/363 [00:03<00:04, 42.25it/s] Loading 0: 46%|████▌ | 166/363 [00:03<00:03, 50.97it/s] Loading 0: 47%|████▋ | 172/363 [00:03<00:03, 50.06it/s] Loading 0: 49%|████▉ | 178/363 [00:03<00:03, 51.25it/s] Loading 0: 51%|█████ | 185/363 [00:03<00:03, 48.42it/s] Loading 0: 53%|█████▎ | 193/363 [00:03<00:03, 55.87it/s] Loading 0: 55%|█████▍ | 199/363 [00:03<00:03, 53.54it/s] Loading 0: 56%|█████▋ | 205/363 [00:03<00:02, 53.85it/s] Loading 0: 58%|█████▊ | 212/363 [00:04<00:03, 50.25it/s] Loading 0: 61%|██████ | 222/363 [00:04<00:02, 56.72it/s] Loading 0: 63%|██████▎ | 228/363 [00:04<00:03, 42.69it/s] Loading 0: 65%|██████▍ | 235/363 [00:04<00:02, 43.86it/s] Loading 0: 66%|██████▌ | 240/363 [00:04<00:02, 44.74it/s] Loading 0: 68%|██████▊ | 247/363 [00:04<00:02, 50.29it/s] Loading 0: 70%|██████▉ | 253/363 [00:05<00:02, 49.60it/s] Loading 0: 71%|███████▏ | 259/363 [00:05<00:02, 50.70it/s] Loading 0: 73%|███████▎ | 266/363 [00:05<00:02, 48.17it/s] Loading 0: 75%|███████▌ | 274/363 [00:05<00:01, 55.59it/s] Loading 0: 77%|███████▋ | 280/363 [00:05<00:01, 53.30it/s] Loading 0: 79%|███████▉ | 286/363 [00:05<00:01, 53.63it/s] Loading 0: 80%|████████ | 292/363 [00:05<00:01, 55.24it/s] Loading 0: 82%|████████▏ | 298/363 [00:05<00:01, 52.99it/s] Loading 0: 84%|████████▎ | 304/363 [00:06<00:01, 31.59it/s] Loading 0: 85%|████████▌ | 310/363 [00:06<00:01, 34.43it/s] Loading 0: 87%|████████▋ | 317/363 [00:06<00:01, 38.51it/s] Loading 0: 89%|████████▊ | 322/363 [00:06<00:01, 40.84it/s] Loading 0: 91%|█████████ | 330/363 [00:06<00:00, 44.33it/s] Loading 0: 93%|█████████▎| 339/363 [00:06<00:00, 48.22it/s] Loading 0: 96%|█████████▌| 348/363 [00:07<00:00, 50.81it/s] Loading 0: 98%|█████████▊| 357/363 [00:07<00:00, 51.47it/s]
Job chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer completed after 83.37s with status: succeeded
Stopping job with name chaiml-ca18-v1-7-dpo-b025-v1-mkmlizer
Pipeline stage MKMLizer completed in 84.11s
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-ca18-v1-7-dpo-b025-v1
Waiting for inference service chaiml-ca18-v1-7-dpo-b025-v1 to be ready
Inference service chaiml-ca18-v1-7-dpo-b025-v1 ready after 171.08503031730652s
Pipeline stage MKMLDeployer completed in 171.62s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.689727544784546s
Received healthy response to inference request in 1.583155632019043s
Received healthy response to inference request in 1.2656104564666748s
Received healthy response to inference request in 1.6754512786865234s
Received healthy response to inference request in 1.234257698059082s
5 requests
0 failed requests
5th percentile: 1.2405282497406005
10th percentile: 1.2467988014221192
20th percentile: 1.2593399047851563
30th percentile: 1.3291194915771485
40th percentile: 1.4561375617980956
50th percentile: 1.583155632019043
60th percentile: 1.6200738906860352
70th percentile: 1.6569921493530273
80th percentile: 1.6783065319061279
90th percentile: 1.684017038345337
95th percentile: 1.6868722915649415
99th percentile: 1.689156494140625
mean time: 1.4896405220031739
Pipeline stage StressChecker completed in 8.82s
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 0.71s
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 0.62s
Shutdown handler de-registered
chaiml-ca18-v1-7-dpo-b025_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2220.48s
Shutdown handler de-registered
chaiml-ca18-v1-7-dpo-b025_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v1-7-dpo-b025_v1 status is now torndown due to DeploymentManager action