chaiml-ca18-v1-9-dpo-cosine

developer_uid: chai_backend_admin

submission_id: chaiml-ca18-v1-9-dpo-cosine_v1

model_name: training123

model_group: ChaiML/ca18-v1-9-dpo_cos

status: torndown

timestamp: 2025-11-20T09:41:12+00:00

num_battles: 5614

num_wins: 2975

celo_rating: 1309.17

family_friendly_score: 0.51

family_friendly_standard_error: 0.007069653456853455

submission_type: basic

model_repo: ChaiML/ca18-v1-9-dpo_cosine

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': 0.4354436564925694, 'latency_mean': 2.296385543346405, 'latency_p50': 1.5390397310256958, 'latency_p90': 4.613233923912048}, {'batch_size': 3, 'throughput': 1.2779046330171508, 'latency_mean': 2.3339581191539764, 'latency_p50': 2.323443651199341, 'latency_p90': 2.527770757675171}, {'batch_size': 5, 'throughput': 1.5674503048694102, 'latency_mean': 3.166358767747879, 'latency_p50': 3.1885138750076294, 'latency_p90': 3.6105472326278685}, {'batch_size': 6, 'throughput': 1.663903005341654, 'latency_mean': 3.584133040904999, 'latency_p50': 3.623117208480835, 'latency_p90': 4.017138481140137}, {'batch_size': 8, 'throughput': 1.7835694859349671, 'latency_mean': 4.460672581195832, 'latency_p50': 4.476754903793335, 'latency_p90': 5.019819378852844}, {'batch_size': 10, 'throughput': 1.850536599179575, 'latency_mean': 5.3662117421627045, 'latency_p50': 5.3562843799591064, 'latency_p90': 6.051163148880004}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ca18-v1-9-dpo_cosine

model_size: 13B

ranking_group: single

throughput_3p7s: 1.69

us_pacific_date: 2025-11-17

win_ratio: 0.529925187032419

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': ['\n', 'User:', 'You:', '</s>'], '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-v1-9-dpo-cosine-v1-mkmlizer
Waiting for job on chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer to finish
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: Downloaded to shared memory in 34.585s
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: Checking if ChaiML/ca18-v1-9-dpo_cosine already exists in ChaiML
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpcw67689_, device:0
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: quantized model in 25.776s
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: Processed model ChaiML/ca18-v1-9-dpo_cosine in 60.361s
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v1-9-dpo-cosine-v1/nvidia
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v1-9-dpo-cosine-v1/nvidia/config.json
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v1-9-dpo-cosine-v1/nvidia/special_tokens_map.json
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v1-9-dpo-cosine-v1/nvidia/tokenizer_config.json
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v1-9-dpo-cosine-v1/nvidia/tokenizer.json
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v1-9-dpo-cosine-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 34.21it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 48.73it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:06, 53.34it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:05, 55.97it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:05, 56.94it/s]
Loading 0:  14%|█▍        | 50/363 [00:00<00:05, 57.61it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:04, 63.27it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:06, 46.53it/s]
Loading 0:  20%|██        | 73/363 [00:01<00:06, 44.84it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:06, 43.97it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 50.76it/s]
Loading 0:  26%|██▋       | 96/363 [00:01<00:05, 50.55it/s]
Loading 0:  28%|██▊       | 102/363 [00:01<00:05, 51.43it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:04, 53.95it/s]
Loading 0:  32%|███▏      | 116/363 [00:02<00:04, 54.72it/s]
Loading 0:  34%|███▍      | 123/363 [00:02<00:04, 52.85it/s]
Loading 0:  36%|███▌      | 129/363 [00:02<00:04, 53.98it/s]
Loading 0:  37%|███▋      | 136/363 [00:02<00:04, 50.20it/s]
Loading 0:  39%|███▉      | 142/363 [00:02<00:05, 43.02it/s]
Loading 0:  40%|████      | 147/363 [00:02<00:05, 42.35it/s]
Loading 0:  42%|████▏     | 153/363 [00:03<00:04, 46.14it/s]
Loading 0:  44%|████▎     | 158/363 [00:03<00:04, 41.98it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:03, 50.20it/s]
Loading 0:  47%|████▋     | 172/363 [00:03<00:03, 49.25it/s]
Loading 0:  49%|████▉     | 178/363 [00:03<00:03, 50.90it/s]
Loading 0:  51%|█████     | 185/363 [00:03<00:03, 48.83it/s]
Loading 0:  53%|█████▎    | 193/363 [00:03<00:03, 56.12it/s]
Loading 0:  55%|█████▍    | 199/363 [00:03<00:03, 53.86it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 54.33it/s]
Loading 0:  58%|█████▊    | 212/363 [00:04<00:02, 50.87it/s]
Loading 0:  61%|██████    | 222/363 [00:04<00:02, 56.97it/s]
Loading 0:  63%|██████▎   | 228/363 [00:04<00:03, 41.88it/s]
Loading 0:  64%|██████▍   | 234/363 [00:04<00:02, 45.30it/s]
Loading 0:  66%|██████▌   | 240/363 [00:04<00:02, 43.79it/s]
Loading 0:  68%|██████▊   | 247/363 [00:04<00:02, 49.44it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 49.01it/s]
Loading 0:  71%|███████▏  | 259/363 [00:05<00:02, 50.79it/s]
Loading 0:  73%|███████▎  | 266/363 [00:05<00:02, 48.04it/s]
Loading 0:  75%|███████▌  | 274/363 [00:05<00:01, 54.86it/s]
Loading 0:  77%|███████▋  | 280/363 [00:05<00:01, 52.60it/s]
Loading 0:  79%|███████▉  | 286/363 [00:05<00:01, 53.13it/s]
Loading 0:  81%|████████  | 293/363 [00:05<00:01, 49.45it/s]
Loading 0:  83%|████████▎ | 303/363 [00:05<00:01, 56.13it/s]
Loading 0:  85%|████████▌ | 309/363 [00:06<00:01, 33.36it/s]
Loading 0:  87%|████████▋ | 314/363 [00:06<00:01, 34.81it/s]
Loading 0:  88%|████████▊ | 321/363 [00:06<00:01, 37.27it/s]
Loading 0:  91%|█████████ | 330/363 [00:06<00:00, 42.98it/s]
Loading 0:  93%|█████████▎| 339/363 [00:06<00:00, 47.03it/s]
Loading 0:  96%|█████████▌| 348/363 [00:07<00:00, 49.92it/s]
Loading 0:  98%|█████████▊| 357/363 [00:07<00:00, 51.43it/s]
                                                            
Job chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer completed after 124.73s with status: succeeded
Stopping job with name chaiml-ca18-v1-9-dpo-cosine-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.21s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ca18-v1-9-dpo-cosine-v1
Waiting for inference service chaiml-ca18-v1-9-dpo-cosine-v1 to be ready
Inference service chaiml-ca18-v1-9-dpo-cosine-v1 ready after 150.54408192634583s
Pipeline stage MKMLDeployer completed in 151.07s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.757415533065796s
Received healthy response to inference request in 1.2413063049316406s
Received healthy response to inference request in 1.7132155895233154s
Received healthy response to inference request in 1.567296028137207s
Received healthy response to inference request in 1.2820281982421875s
5 requests
0 failed requests
5th percentile: 1.24945068359375
10th percentile: 1.2575950622558594
20th percentile: 1.2738838195800781
30th percentile: 1.3390817642211914
40th percentile: 1.4531888961791992
50th percentile: 1.567296028137207
60th percentile: 1.6256638526916505
70th percentile: 1.6840316772460937
80th percentile: 1.7220555782318114
90th percentile: 1.7397355556488037
95th percentile: 1.7485755443573
99th percentile: 1.7556475353240968
mean time: 1.5122523307800293
Pipeline stage StressChecker completed in 8.72s
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 0.66s
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-v1-9-dpo-cosine_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 0.07s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ca18-v1-9-dpo-cosine-v1-profiler
Waiting for inference service chaiml-ca18-v1-9-dpo-cosine-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 2466.46s
Shutdown handler de-registered
chaiml-ca18-v1-9-dpo-cosine_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v1-9-dpo-cosine_v1 status is now torndown due to DeploymentManager action