developer_uid: chai_backend_admin
submission_id: chaiml-ca18-v1-10-dpo_v1
model_name: training123
model_group: ChaiML/ca18-v1-10-dpo
status: torndown
timestamp: 2025-11-20T10:51:18+00:00
num_battles: 5744
num_wins: 3087
celo_rating: 1310.24
family_friendly_score: 0.5025999999999999
family_friendly_standard_error: 0.007070972210382389
submission_type: basic
model_repo: ChaiML/ca18-v1-10-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': 0.6887859734288703, 'latency_mean': 1.4517269778251647, 'latency_p50': 1.4440747499465942, 'latency_p90': 1.6058581590652465}, {'batch_size': 3, 'throughput': 1.2429589858198098, 'latency_mean': 2.4054985880851745, 'latency_p50': 2.394718885421753, 'latency_p90': 2.7278447866439817}, {'batch_size': 5, 'throughput': 1.5187342835724194, 'latency_mean': 3.2808237075805664, 'latency_p50': 3.2706724405288696, 'latency_p90': 3.7371376752853394}, {'batch_size': 6, 'throughput': 1.589431328175837, 'latency_mean': 3.749702341556549, 'latency_p50': 3.7791757583618164, 'latency_p90': 4.235230875015259}, {'batch_size': 8, 'throughput': 1.70450920300797, 'latency_mean': 4.667212425470352, 'latency_p50': 4.664225935935974, 'latency_p90': 5.301710987091065}, {'batch_size': 10, 'throughput': 1.7713636967226625, 'latency_mean': 5.619555211067199, 'latency_p50': 5.572173833847046, 'latency_p90': 6.433851599693298}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
is_internal_developer: True
language_model: ChaiML/ca18-v1-10-dpo
model_size: 13B
ranking_group: single
throughput_3p7s: 1.59
us_pacific_date: 2025-11-17
win_ratio: 0.5374303621169917
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': ['You:', '</s>', '\n', 'User:'], '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-v1-mkmlizer
Waiting for job on chaiml-ca18-v1-10-dpo-v1-mkmlizer to finish
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ Version: 0.30.2 ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ https://mk1.ai ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ belonging to: ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ Chai Research Corp. ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ║ ║
chaiml-ca18-v1-10-dpo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v1-10-dpo-v1-mkmlizer: Downloaded to shared memory in 30.222s
chaiml-ca18-v1-10-dpo-v1-mkmlizer: Checking if ChaiML/ca18-v1-10-dpo already exists in ChaiML
chaiml-ca18-v1-10-dpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplfponwj3, device:0
chaiml-ca18-v1-10-dpo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v1-10-dpo-v1-mkmlizer: quantized model in 26.097s
chaiml-ca18-v1-10-dpo-v1-mkmlizer: Processed model ChaiML/ca18-v1-10-dpo in 56.319s
chaiml-ca18-v1-10-dpo-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v1-10-dpo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v1-10-dpo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v1-10-dpo-v1/nvidia
chaiml-ca18-v1-10-dpo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v1-10-dpo-v1/nvidia/special_tokens_map.json
chaiml-ca18-v1-10-dpo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v1-10-dpo-v1/nvidia/config.json
chaiml-ca18-v1-10-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v1-10-dpo-v1/nvidia/tokenizer_config.json
chaiml-ca18-v1-10-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v1-10-dpo-v1/nvidia/tokenizer.json
chaiml-ca18-v1-10-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v1-10-dpo-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v1-10-dpo-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%|▏ | 5/363 [00:00<00:10, 33.11it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:07, 47.01it/s] Loading 0: 6%|▋ | 23/363 [00:00<00:06, 51.33it/s] Loading 0: 9%|▉ | 32/363 [00:00<00:06, 53.69it/s] Loading 0: 11%|█▏ | 41/363 [00:00<00:05, 54.79it/s] Loading 0: 14%|█▍ | 50/363 [00:00<00:05, 55.06it/s] Loading 0: 17%|█▋ | 60/363 [00:01<00:04, 60.72it/s] Loading 0: 18%|█▊ | 67/363 [00:01<00:06, 45.26it/s] Loading 0: 20%|██ | 73/363 [00:01<00:06, 43.79it/s] Loading 0: 23%|██▎ | 82/363 [00:01<00:05, 47.27it/s] Loading 0: 25%|██▌ | 91/363 [00:01<00:05, 49.69it/s] Loading 0: 28%|██▊ | 100/363 [00:01<00:05, 51.36it/s] Loading 0: 30%|███ | 110/363 [00:02<00:04, 56.02it/s] Loading 0: 32%|███▏ | 116/363 [00:02<00:04, 55.35it/s] Loading 0: 34%|███▍ | 123/363 [00:02<00:04, 53.26it/s] Loading 0: 36%|███▌ | 129/363 [00:02<00:04, 53.80it/s] Loading 0: 37%|███▋ | 136/363 [00:02<00:04, 50.22it/s] Loading 0: 39%|███▉ | 142/363 [00:02<00:05, 43.71it/s] Loading 0: 40%|████ | 147/363 [00:02<00:04, 43.74it/s] Loading 0: 42%|████▏ | 153/363 [00:03<00:04, 47.18it/s] Loading 0: 44%|████▎ | 158/363 [00:03<00:04, 42.48it/s] Loading 0: 46%|████▌ | 166/363 [00:03<00:03, 51.16it/s] Loading 0: 47%|████▋ | 172/363 [00:03<00:03, 49.49it/s] Loading 0: 49%|████▉ | 178/363 [00:03<00:03, 50.50it/s] Loading 0: 51%|█████ | 185/363 [00:03<00:03, 47.92it/s] Loading 0: 53%|█████▎ | 193/363 [00:03<00:03, 54.87it/s] Loading 0: 55%|█████▍ | 199/363 [00:03<00:03, 52.30it/s] Loading 0: 56%|█████▋ | 205/363 [00:04<00:02, 52.71it/s] Loading 0: 58%|█████▊ | 212/363 [00:04<00:03, 49.16it/s] Loading 0: 61%|██████ | 222/363 [00:04<00:02, 55.15it/s] Loading 0: 63%|██████▎ | 228/363 [00:04<00:03, 42.32it/s] Loading 0: 64%|██████▍ | 234/363 [00:04<00:02, 45.72it/s] Loading 0: 66%|██████▌ | 240/363 [00:04<00:02, 43.56it/s] Loading 0: 68%|██████▊ | 247/363 [00:04<00:02, 48.21it/s] Loading 0: 70%|██████▉ | 253/363 [00:05<00:02, 47.29it/s] Loading 0: 71%|███████ | 258/363 [00:05<00:02, 46.97it/s] Loading 0: 73%|███████▎ | 265/363 [00:05<00:01, 52.33it/s] Loading 0: 75%|███████▍ | 271/363 [00:05<00:01, 50.34it/s] Loading 0: 76%|███████▋ | 277/363 [00:05<00:01, 50.96it/s] Loading 0: 78%|███████▊ | 283/363 [00:05<00:01, 52.00it/s] Loading 0: 80%|███████▉ | 289/363 [00:05<00:01, 48.69it/s] Loading 0: 81%|████████ | 294/363 [00:05<00:01, 48.20it/s] Loading 0: 83%|████████▎ | 302/363 [00:06<00:01, 56.55it/s] Loading 0: 85%|████████▍ | 308/363 [00:06<00:01, 29.08it/s] Loading 0: 86%|████████▌ | 313/363 [00:06<00:01, 31.25it/s] Loading 0: 88%|████████▊ | 321/363 [00:06<00:01, 36.31it/s] Loading 0: 91%|█████████ | 330/363 [00:06<00:00, 41.87it/s] Loading 0: 93%|█████████▎| 338/363 [00:07<00:00, 49.32it/s] Loading 0: 95%|█████████▍| 344/363 [00:07<00:00, 48.72it/s] Loading 0: 96%|█████████▋| 350/363 [00:07<00:00, 49.85it/s] Loading 0: 98%|█████████▊| 356/363 [00:07<00:00, 51.32it/s] Loading 0: 100%|█████████▉| 362/363 [00:07<00:00, 50.04it/s]
Job chaiml-ca18-v1-10-dpo-v1-mkmlizer completed after 114.19s with status: succeeded
Stopping job with name chaiml-ca18-v1-10-dpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.70s
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-v1
Waiting for inference service chaiml-ca18-v1-10-dpo-v1 to be ready
Inference service chaiml-ca18-v1-10-dpo-v1 ready after 160.7066900730133s
Pipeline stage MKMLDeployer completed in 161.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6193175315856934s
Received healthy response to inference request in 1.2247233390808105s
Received healthy response to inference request in 1.7848546504974365s
Received healthy response to inference request in 1.888826847076416s
Received healthy response to inference request in 1.3566625118255615s
5 requests
0 failed requests
5th percentile: 1.2511111736297607
10th percentile: 1.277499008178711
20th percentile: 1.3302746772766114
30th percentile: 1.409193515777588
40th percentile: 1.5142555236816406
50th percentile: 1.6193175315856934
60th percentile: 1.6855323791503907
70th percentile: 1.7517472267150878
80th percentile: 1.8056490898132325
90th percentile: 1.8472379684448241
95th percentile: 1.86803240776062
99th percentile: 1.884667959213257
mean time: 1.5748769760131835
Pipeline stage StressChecker completed in 9.00s
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 0.57s
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 0.59s
Shutdown handler de-registered
chaiml-ca18-v1-10-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 2429.83s
Shutdown handler de-registered
chaiml-ca18-v1-10-dpo_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v1-10-dpo_v1 status is now torndown due to DeploymentManager action