developer_uid: chai_backend_admin
submission_id: chaiml-ca18-v1-5-dpo_v1
model_name: training123
model_group: ChaiML/ca18-v1-5-dpo
status: torndown
timestamp: 2025-11-19T09:21:19+00:00
num_battles: 6783
num_wins: 3630
celo_rating: 1305.07
family_friendly_score: 0.505
family_friendly_standard_error: 0.007070714249635605
submission_type: basic
model_repo: ChaiML/ca18-v1-5-dpo
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': 0.6925819546729313, 'latency_mean': 1.4437726175785064, 'latency_p50': 1.434664249420166, 'latency_p90': 1.5957677841186524}, {'batch_size': 3, 'throughput': 1.2731903935561832, 'latency_mean': 2.3540408885478974, 'latency_p50': 2.356023907661438, 'latency_p90': 2.58304762840271}, {'batch_size': 5, 'throughput': 1.5650416849460846, 'latency_mean': 3.183112680912018, 'latency_p50': 3.179410934448242, 'latency_p90': 3.6121853590011597}, {'batch_size': 6, 'throughput': 1.6505755836249245, 'latency_mean': 3.6218629014492034, 'latency_p50': 3.6253377199172974, 'latency_p90': 4.100892949104309}, {'batch_size': 8, 'throughput': 1.7662400364241866, 'latency_mean': 4.492908480167389, 'latency_p50': 4.494818806648254, 'latency_p90': 5.0929560422897335}, {'batch_size': 10, 'throughput': 1.8484032117190388, 'latency_mean': 5.368752089738845, 'latency_p50': 5.386519074440002, 'latency_p90': 6.2469116926193236}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
is_internal_developer: True
language_model: ChaiML/ca18-v1-5-dpo
model_size: 13B
ranking_group: single
throughput_3p7s: 1.67
us_pacific_date: 2025-11-16
win_ratio: 0.5351614329942503
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>', 'User:', '\n', 'You:'], '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-v1-5-dpo-v1-mkmlizer
Waiting for job on chaiml-ca18-v1-5-dpo-v1-mkmlizer to finish
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ Version: 0.30.2 ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ belonging to: ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ║ ║
chaiml-ca18-v1-5-dpo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v1-5-dpo-v1-mkmlizer: Downloaded to shared memory in 38.315s
chaiml-ca18-v1-5-dpo-v1-mkmlizer: Checking if ChaiML/ca18-v1-5-dpo already exists in ChaiML
chaiml-ca18-v1-5-dpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp28z8o9g6, device:0
chaiml-ca18-v1-5-dpo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v1-5-dpo-v1-mkmlizer: quantized model in 26.226s
chaiml-ca18-v1-5-dpo-v1-mkmlizer: Processed model ChaiML/ca18-v1-5-dpo in 64.541s
chaiml-ca18-v1-5-dpo-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v1-5-dpo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v1-5-dpo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v1-5-dpo-v1/nvidia
chaiml-ca18-v1-5-dpo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v1-5-dpo-v1/nvidia/config.json
chaiml-ca18-v1-5-dpo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v1-5-dpo-v1/nvidia/special_tokens_map.json
chaiml-ca18-v1-5-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v1-5-dpo-v1/nvidia/tokenizer_config.json
chaiml-ca18-v1-5-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v1-5-dpo-v1/nvidia/tokenizer.json
chaiml-ca18-v1-5-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v1-5-dpo-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v1-5-dpo-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:10, 33.86it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:07, 46.47it/s] Loading 0: 6%|▋ | 23/363 [00:00<00:06, 51.61it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:06, 53.25it/s] Loading 0: 11%|█▏ | 41/363 [00:00<00:05, 54.68it/s] Loading 0: 14%|█▍ | 50/363 [00:00<00:05, 55.75it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:04, 61.63it/s] Loading 0: 18%|█▊ | 67/363 [00:01<00:06, 46.74it/s] Loading 0: 20%|██ | 73/363 [00:01<00:06, 44.57it/s] Loading 0: 22%|██▏ | 81/363 [00:01<00:05, 51.72it/s] Loading 0: 24%|██▍ | 87/363 [00:01<00:05, 50.13it/s] Loading 0: 26%|██▌ | 93/363 [00:01<00:05, 51.30it/s] Loading 0: 28%|██▊ | 100/363 [00:01<00:05, 48.67it/s] Loading 0: 30%|███ | 110/363 [00:02<00:04, 55.19it/s] Loading 0: 32%|███▏ | 116/363 [00:02<00:04, 53.70it/s] Loading 0: 34%|███▎ | 122/363 [00:02<00:04, 54.38it/s] Loading 0: 35%|███▌ | 128/363 [00:02<00:04, 49.23it/s] Loading 0: 37%|███▋ | 135/363 [00:02<00:04, 53.65it/s] Loading 0: 39%|███▉ | 141/363 [00:02<00:04, 50.73it/s] Loading 0: 40%|████ | 147/363 [00:03<00:05, 38.05it/s] Loading 0: 42%|████▏ | 153/363 [00:03<00:04, 42.24it/s] Loading 0: 44%|████▎ | 158/363 [00:03<00:05, 35.53it/s] Loading 0: 46%|████▌ | 166/363 [00:03<00:04, 44.30it/s] Loading 0: 47%|████▋ | 172/363 [00:03<00:04, 44.65it/s] Loading 0: 49%|████▉ | 177/363 [00:03<00:04, 45.22it/s] Loading 0: 51%|█████ | 184/363 [00:03<00:03, 50.91it/s] Loading 0: 52%|█████▏ | 190/363 [00:03<00:03, 49.41it/s] Loading 0: 54%|█████▍ | 196/363 [00:03<00:03, 51.08it/s] Loading 0: 56%|█████▌ | 203/363 [00:04<00:03, 48.53it/s] Loading 0: 58%|█████▊ | 211/363 [00:04<00:02, 54.60it/s] Loading 0: 60%|█████▉ | 217/363 [00:04<00:02, 51.59it/s] Loading 0: 61%|██████▏ | 223/363 [00:04<00:03, 41.91it/s] Loading 0: 63%|██████▎ | 228/363 [00:04<00:03, 41.75it/s] Loading 0: 64%|██████▍ | 234/363 [00:04<00:02, 45.61it/s] Loading 0: 66%|██████▌ | 239/363 [00:04<00:03, 41.00it/s] Loading 0: 68%|██████▊ | 247/363 [00:05<00:02, 49.24it/s] Loading 0: 70%|██████▉ | 253/363 [00:05<00:02, 48.07it/s] Loading 0: 71%|███████▏ | 259/363 [00:05<00:02, 49.51it/s] Loading 0: 73%|███████▎ | 265/363 [00:05<00:01, 52.08it/s] Loading 0: 75%|███████▍ | 271/363 [00:05<00:01, 50.42it/s] Loading 0: 76%|███████▋ | 277/363 [00:05<00:01, 51.20it/s] Loading 0: 78%|███████▊ | 283/363 [00:05<00:01, 53.49it/s] Loading 0: 80%|███████▉ | 289/363 [00:05<00:01, 51.28it/s] Loading 0: 81%|████████▏ | 295/363 [00:06<00:01, 51.72it/s] Loading 0: 83%|████████▎ | 303/363 [00:06<00:01, 52.62it/s] Loading 0: 85%|████████▌ | 309/363 [00:06<00:01, 31.01it/s] Loading 0: 87%|████████▋ | 314/363 [00:06<00:01, 32.85it/s] Loading 0: 88%|████████▊ | 321/363 [00:06<00:01, 36.15it/s] Loading 0: 91%|█████████ | 330/363 [00:07<00:00, 41.98it/s] Loading 0: 93%|█████████▎| 338/363 [00:07<00:00, 48.64it/s] Loading 0: 95%|█████████▍| 344/363 [00:07<00:00, 48.19it/s] Loading 0: 96%|█████████▋| 350/363 [00:07<00:00, 49.99it/s] Loading 0: 98%|█████████▊| 357/363 [00:07<00:00, 47.74it/s]
Job chaiml-ca18-v1-5-dpo-v1-mkmlizer completed after 104.43s with status: succeeded
Stopping job with name chaiml-ca18-v1-5-dpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.96s
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-v1-5-dpo-v1
Waiting for inference service chaiml-ca18-v1-5-dpo-v1 to be ready
Inference service chaiml-ca18-v1-5-dpo-v1 ready after 170.65369534492493s
Pipeline stage MKMLDeployer completed in 171.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.630918264389038s
Received healthy response to inference request in 1.39387845993042s
Received healthy response to inference request in 1.6556353569030762s
Received healthy response to inference request in 1.8199644088745117s
Received healthy response to inference request in 1.261348009109497s
5 requests
0 failed requests
5th percentile: 1.2878540992736816
10th percentile: 1.3143601894378663
20th percentile: 1.3673723697662354
30th percentile: 1.4412864208221436
40th percentile: 1.5361023426055909
50th percentile: 1.630918264389038
60th percentile: 1.6408051013946534
70th percentile: 1.6506919384002685
80th percentile: 1.6885011672973633
90th percentile: 1.7542327880859374
95th percentile: 1.7870985984802246
99th percentile: 1.8133912467956543
mean time: 1.5523488998413086
Pipeline stage StressChecker completed in 9.38s
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 0.64s
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-ca18-v1-5-dpo_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 2490.08s
Shutdown handler de-registered
chaiml-ca18-v1-5-dpo_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v1-5-dpo_v1 status is now torndown due to DeploymentManager action