chaiml-ca18-v2-2-dpo-lr_37662

developer_uid: chai_backend_admin

submission_id: chaiml-ca18-v2-2-dpo-lr_37662_v1

model_name: training123

model_group: ChaiML/ca18-v2-2-dpo_lr1

status: torndown

timestamp: 2025-11-20T06:41:15+00:00

num_battles: 5916

num_wins: 3179

celo_rating: 1314.74

family_friendly_score: 0.5076

family_friendly_standard_error: 0.007070250914925157

submission_type: basic

model_repo: ChaiML/ca18-v2-2-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': 0.691690865468774, 'latency_mean': 1.4456098127365111, 'latency_p50': 1.4427045583724976, 'latency_p90': 1.5963626861572267}, {'batch_size': 3, 'throughput': 1.2948440566221309, 'latency_mean': 2.3093816244602206, 'latency_p50': 2.316222310066223, 'latency_p90': 2.5101797342300416}, {'batch_size': 5, 'throughput': 1.5788792467185326, 'latency_mean': 3.151321370601654, 'latency_p50': 3.1938798427581787, 'latency_p90': 3.5061233282089233}, {'batch_size': 6, 'throughput': 1.6881167494683125, 'latency_mean': 3.543130621910095, 'latency_p50': 3.5383654832839966, 'latency_p90': 3.954147958755493}, {'batch_size': 8, 'throughput': 1.8001761602649087, 'latency_mean': 4.4145280873775485, 'latency_p50': 4.446905612945557, 'latency_p90': 4.978570365905762}, {'batch_size': 10, 'throughput': 1.8732007324666544, 'latency_mean': 5.288592215776443, 'latency_p50': 5.293752074241638, 'latency_p90': 5.960961532592774}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ca18-v2-2-dpo_lr15-b025

model_size: 13B

ranking_group: single

throughput_3p7s: 1.72

us_pacific_date: 2025-11-16

win_ratio: 0.5373563218390804

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:', 'User:', '\n', '</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-v2-2-dpo-lr-37662-v1-mkmlizer
Waiting for job on chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer to finish
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: Downloaded to shared memory in 60.067s
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: Checking if ChaiML/ca18-v2-2-dpo_lr15-b025 already exists in ChaiML
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdazg348t, device:0
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: quantized model in 26.344s
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: Processed model ChaiML/ca18-v2-2-dpo_lr15-b025 in 86.411s
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v2-2-dpo-lr-37662-v1/nvidia
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v2-2-dpo-lr-37662-v1/nvidia/config.json
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v2-2-dpo-lr-37662-v1/nvidia/special_tokens_map.json
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v2-2-dpo-lr-37662-v1/nvidia/tokenizer_config.json
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v2-2-dpo-lr-37662-v1/nvidia/tokenizer.json
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v2-2-dpo-lr-37662-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 33.48it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 46.50it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:06, 50.81it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 52.66it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:05, 53.86it/s]
Loading 0:  14%|█▍        | 50/363 [00:00<00:05, 54.38it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:05, 59.94it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:06, 45.52it/s]
Loading 0:  20%|██        | 73/363 [00:01<00:06, 43.28it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:05, 50.63it/s]
Loading 0:  24%|██▍       | 87/363 [00:01<00:05, 49.46it/s]
Loading 0:  26%|██▌       | 93/363 [00:01<00:05, 51.15it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:05, 48.50it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:04, 54.68it/s]
Loading 0:  32%|███▏      | 116/363 [00:02<00:04, 54.38it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:04, 55.65it/s]
Loading 0:  35%|███▌      | 128/363 [00:02<00:04, 49.52it/s]
Loading 0:  37%|███▋      | 135/363 [00:02<00:04, 52.64it/s]
Loading 0:  39%|███▉      | 141/363 [00:02<00:04, 49.93it/s]
Loading 0:  40%|████      | 147/363 [00:03<00:05, 37.99it/s]
Loading 0:  42%|████▏     | 152/363 [00:03<00:05, 39.84it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:04, 41.71it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 42.57it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 43.71it/s]
Loading 0:  48%|████▊     | 175/363 [00:03<00:03, 49.22it/s]
Loading 0:  50%|████▉     | 181/363 [00:03<00:03, 48.55it/s]
Loading 0:  51%|█████     | 186/363 [00:03<00:03, 47.44it/s]
Loading 0:  53%|█████▎    | 193/363 [00:03<00:03, 52.86it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 50.15it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:03, 50.61it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 53.00it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:02, 50.88it/s]
Loading 0:  61%|██████▏   | 223/363 [00:04<00:03, 40.70it/s]
Loading 0:  63%|██████▎   | 228/363 [00:04<00:03, 40.97it/s]
Loading 0:  64%|██████▍   | 233/363 [00:04<00:03, 42.98it/s]
Loading 0:  66%|██████▌   | 239/363 [00:05<00:03, 40.47it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 49.10it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 47.51it/s]
Loading 0:  71%|███████   | 258/363 [00:05<00:02, 46.93it/s]
Loading 0:  73%|███████▎  | 265/363 [00:05<00:01, 51.93it/s]
Loading 0:  75%|███████▍  | 271/363 [00:05<00:01, 49.46it/s]
Loading 0:  76%|███████▋  | 277/363 [00:05<00:01, 50.31it/s]
Loading 0:  78%|███████▊  | 283/363 [00:05<00:01, 52.68it/s]
Loading 0:  80%|███████▉  | 289/363 [00:05<00:01, 48.45it/s]
Loading 0:  81%|████████  | 294/363 [00:06<00:01, 46.86it/s]
Loading 0:  83%|████████▎ | 303/363 [00:06<00:01, 51.84it/s]
Loading 0:  85%|████████▌ | 309/363 [00:06<00:01, 30.56it/s]
Loading 0:  87%|████████▋ | 314/363 [00:06<00:01, 32.11it/s]
Loading 0:  88%|████████▊ | 321/363 [00:06<00:01, 34.92it/s]
Loading 0:  91%|█████████ | 330/363 [00:07<00:00, 40.83it/s]
Loading 0:  93%|█████████▎| 338/363 [00:07<00:00, 48.41it/s]
Loading 0:  95%|█████████▍| 344/363 [00:07<00:00, 48.05it/s]
Loading 0:  96%|█████████▋| 350/363 [00:07<00:00, 49.93it/s]
Loading 0:  98%|█████████▊| 357/363 [00:07<00:00, 48.41it/s]
                                                            
Job chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer completed after 174.68s with status: succeeded
Stopping job with name chaiml-ca18-v2-2-dpo-lr-37662-v1-mkmlizer
Pipeline stage MKMLizer completed in 175.15s
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-v2-2-dpo-lr-37662-v1
Waiting for inference service chaiml-ca18-v2-2-dpo-lr-37662-v1 to be ready
Inference service chaiml-ca18-v2-2-dpo-lr-37662-v1 ready after 170.6943416595459s
Pipeline stage MKMLDeployer completed in 171.23s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9270751476287842s
Received healthy response to inference request in 1.4207251071929932s
Received healthy response to inference request in 1.6516609191894531s
Received healthy response to inference request in 1.7718608379364014s
Received healthy response to inference request in 1.4945766925811768s
5 requests
0 failed requests
5th percentile: 1.43549542427063
10th percentile: 1.4502657413482667
20th percentile: 1.47980637550354
30th percentile: 1.525993537902832
40th percentile: 1.5888272285461427
50th percentile: 1.6516609191894531
60th percentile: 1.6997408866882324
70th percentile: 1.7478208541870117
80th percentile: 1.802903699874878
90th percentile: 1.864989423751831
95th percentile: 1.8960322856903076
99th percentile: 1.920866575241089
mean time: 1.6531797409057618
Pipeline stage StressChecker completed in 18.64s
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 0.68s
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 0.65s
Shutdown handler de-registered
chaiml-ca18-v2-2-dpo-lr_37662_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-v2-2-dpo-lr-37662-v1-profiler
Waiting for inference service chaiml-ca18-v2-2-dpo-lr-37662-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 2622.08s
Shutdown handler de-registered
chaiml-ca18-v2-2-dpo-lr_37662_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v2-2-dpo-lr_37662_v1 status is now torndown due to DeploymentManager action