developer_uid: chai_backend_admin
submission_id: chaiml-ca18-v1-10-dpo-lr1_955_v1
model_name: training123
model_group: ChaiML/ca18-v1-10-dpo_lr
status: torndown
timestamp: 2025-11-20T12:01:23+00:00
num_battles: 5356
num_wins: 2826
celo_rating: 1303.53
family_friendly_score: 0.512
family_friendly_standard_error: 0.007069031050999847
submission_type: basic
model_repo: ChaiML/ca18-v1-10-dpo_lr15-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': 0.6881133374068363, 'latency_mean': 1.4531520354747771, 'latency_p50': 1.462049961090088, 'latency_p90': 1.602515196800232}, {'batch_size': 3, 'throughput': 1.3078996370482963, 'latency_mean': 2.292134748697281, 'latency_p50': 2.3144980669021606, 'latency_p90': 2.5177761316299434}, {'batch_size': 5, 'throughput': 1.6054096654357848, 'latency_mean': 3.1032791364192964, 'latency_p50': 3.1103246212005615, 'latency_p90': 3.4913328170776365}, {'batch_size': 6, 'throughput': 1.6911432672185436, 'latency_mean': 3.532349226474762, 'latency_p50': 3.5379486083984375, 'latency_p90': 3.974959397315979}, {'batch_size': 8, 'throughput': 1.8171534092621386, 'latency_mean': 4.362077068090439, 'latency_p50': 4.364191651344299, 'latency_p90': 4.9933614253997805}, {'batch_size': 10, 'throughput': 1.9028557735328409, 'latency_mean': 5.203597161769867, 'latency_p50': 5.1871267557144165, 'latency_p90': 5.946211481094361}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
is_internal_developer: True
language_model: ChaiML/ca18-v1-10-dpo_lr15-b025
model_size: 13B
ranking_group: single
throughput_3p7s: 1.73
us_pacific_date: 2025-11-17
win_ratio: 0.5276325616131441
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': ['</s>', 'You:', 'User:', '\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-v1-10-dpo-lr1-955-v1-mkmlizer
Waiting for job on chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer to finish
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: Downloaded to shared memory in 32.743s
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: Checking if ChaiML/ca18-v1-10-dpo_lr15-b025 already exists in ChaiML
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5elqfgqj, device:0
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: quantized model in 25.722s
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: Processed model ChaiML/ca18-v1-10-dpo_lr15-b025 in 58.465s
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v1-10-dpo-lr1-955-v1/nvidia
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v1-10-dpo-lr1-955-v1/nvidia/config.json
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v1-10-dpo-lr1-955-v1/nvidia/special_tokens_map.json
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v1-10-dpo-lr1-955-v1/nvidia/tokenizer_config.json
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v1-10-dpo-lr1-955-v1/nvidia/tokenizer.json
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v1-10-dpo-lr1-955-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 34.17it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 46.98it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:06, 50.18it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 52.97it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:05, 54.75it/s]
Loading 0:  14%|█▍        | 50/363 [00:00<00:05, 55.87it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:04, 61.91it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:06, 45.27it/s]
Loading 0:  20%|██        | 73/363 [00:01<00:06, 43.21it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:05, 50.53it/s]
Loading 0:  24%|██▍       | 87/363 [00:01<00:05, 48.08it/s]
Loading 0:  26%|██▌       | 93/363 [00:01<00:05, 48.96it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:05, 47.28it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:04, 54.62it/s]
Loading 0:  32%|███▏      | 116/363 [00:02<00:04, 54.45it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:04, 54.80it/s]
Loading 0:  35%|███▌      | 128/363 [00:02<00:04, 49.62it/s]
Loading 0:  37%|███▋      | 135/363 [00:02<00:04, 54.19it/s]
Loading 0:  39%|███▉      | 141/363 [00:02<00:04, 51.87it/s]
Loading 0:  40%|████      | 147/363 [00:03<00:05, 37.57it/s]
Loading 0:  42%|████▏     | 152/363 [00:03<00:05, 39.48it/s]
Loading 0:  44%|████▎     | 158/363 [00:03<00:05, 38.61it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 47.33it/s]
Loading 0:  47%|████▋     | 172/363 [00:03<00:04, 47.64it/s]
Loading 0:  49%|████▉     | 178/363 [00:03<00:03, 48.65it/s]
Loading 0:  51%|█████     | 185/363 [00:03<00:03, 46.91it/s]
Loading 0:  53%|█████▎    | 193/363 [00:03<00:03, 54.40it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 52.08it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 53.08it/s]
Loading 0:  58%|█████▊    | 212/363 [00:04<00:03, 49.33it/s]
Loading 0:  61%|██████    | 222/363 [00:04<00:02, 55.63it/s]
Loading 0:  63%|██████▎   | 228/363 [00:04<00:03, 42.06it/s]
Loading 0:  64%|██████▍   | 234/363 [00:04<00:02, 45.50it/s]
Loading 0:  66%|██████▌   | 240/363 [00:04<00:02, 43.52it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 48.83it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 47.46it/s]
Loading 0:  71%|███████▏  | 259/363 [00:05<00:02, 49.53it/s]
Loading 0:  73%|███████▎  | 266/363 [00:05<00:02, 47.66it/s]
Loading 0:  75%|███████▌  | 274/363 [00:05<00:01, 55.09it/s]
Loading 0:  77%|███████▋  | 280/363 [00:05<00:01, 52.74it/s]
Loading 0:  79%|███████▉  | 286/363 [00:05<00:01, 53.60it/s]
Loading 0:  81%|████████  | 293/363 [00:05<00:01, 50.27it/s]
Loading 0:  83%|████████▎ | 303/363 [00:06<00:01, 56.57it/s]
Loading 0:  85%|████████▌ | 309/363 [00:06<00:01, 34.46it/s]
Loading 0:  87%|████████▋ | 314/363 [00:06<00:01, 35.54it/s]
Loading 0:  88%|████████▊ | 321/363 [00:06<00:01, 37.90it/s]
Loading 0:  91%|█████████ | 330/363 [00:06<00:00, 43.59it/s]
Loading 0:  93%|█████████▎| 338/363 [00:07<00:00, 50.83it/s]
Loading 0:  95%|█████████▍| 344/363 [00:07<00:00, 50.36it/s]
Loading 0:  96%|█████████▋| 350/363 [00:07<00:00, 51.98it/s]
Loading 0:  98%|█████████▊| 357/363 [00:07<00:00, 49.94it/s]
                                                            

Job chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer completed after 119.36s with status: succeeded
Stopping job with name chaiml-ca18-v1-10-dpo-lr1-955-v1-mkmlizer
Pipeline stage MKMLizer completed in 119.86s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ca18-v1-10-dpo-lr1-955-v1
Waiting for inference service chaiml-ca18-v1-10-dpo-lr1-955-v1 to be ready
Inference service chaiml-ca18-v1-10-dpo-lr1-955-v1 ready after 160.8340358734131s
Pipeline stage MKMLDeployer completed in 161.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.831709623336792s
Received healthy response to inference request in 1.6588854789733887s
Received healthy response to inference request in 1.5392298698425293s
Received healthy response to inference request in 1.4799273014068604s
Received healthy response to inference request in 1.3659906387329102s
5 requests
0 failed requests
5th percentile: 1.3887779712677002
10th percentile: 1.4115653038024902
20th percentile: 1.4571399688720703
30th percentile: 1.491787815093994
40th percentile: 1.5155088424682617
50th percentile: 1.5392298698425293
60th percentile: 1.587092113494873
70th percentile: 1.6349543571472167
80th percentile: 1.6934503078460694
90th percentile: 1.7625799655914307
95th percentile: 1.7971447944641112
99th percentile: 1.8247966575622558
mean time: 1.575148582458496
Pipeline stage StressChecker completed in 9.14s
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 0.63s
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 0.82s
Shutdown handler de-registered
chaiml-ca18-v1-10-dpo-lr1_955_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ca18-v1-10-dpo-lr1-955-v1-profiler
Waiting for inference service chaiml-ca18-v1-10-dpo-lr1-955-v1-profiler to be ready
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 2520.87s
Shutdown handler de-registered
chaiml-ca18-v1-10-dpo-lr1_955_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v1-10-dpo-lr1_955_v1 status is now torndown due to DeploymentManager action