chaiml-ca18-v1-6-dpo

developer_uid: chai_backend_admin

submission_id: chaiml-ca18-v1-6-dpo_v1

model_name: training123

model_group: ChaiML/ca18-v1-6-dpo

status: torndown

timestamp: 2025-11-19T10:21:16+00:00

num_battles: 5596

num_wins: 2948

celo_rating: 1302.62

family_friendly_score: 0.5025999999999999

family_friendly_standard_error: 0.007070972210382389

submission_type: basic

model_repo: ChaiML/ca18-v1-6-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': 0.6800168654008913, 'latency_mean': 1.4704278385639191, 'latency_p50': 1.465857982635498, 'latency_p90': 1.6216028690338136}, {'batch_size': 3, 'throughput': 1.2781942541598124, 'latency_mean': 2.3459701144695284, 'latency_p50': 2.3450090885162354, 'latency_p90': 2.604892635345459}, {'batch_size': 5, 'throughput': 1.5444368880697543, 'latency_mean': 3.2189166831970213, 'latency_p50': 3.2192859649658203, 'latency_p90': 3.668123745918274}, {'batch_size': 6, 'throughput': 1.6299578244588977, 'latency_mean': 3.65900505900383, 'latency_p50': 3.6605693101882935, 'latency_p90': 4.15814516544342}, {'batch_size': 8, 'throughput': 1.7573228124391538, 'latency_mean': 4.516605831384659, 'latency_p50': 4.523874878883362, 'latency_p90': 5.182298088073731}, {'batch_size': 10, 'throughput': 1.8264088266231289, 'latency_mean': 5.428027091026306, 'latency_p50': 5.457186460494995, 'latency_p90': 6.1381385087966915}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ca18-v1-6-dpo

model_size: 13B

ranking_group: single

throughput_3p7s: 1.65

us_pacific_date: 2025-11-16

win_ratio: 0.5268048606147248

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

Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-ca18-v1-6-dpo-v1-mkmlizer
Waiting for job on chaiml-ca18-v1-6-dpo-v1-mkmlizer to finish
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-6-dpo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v1-6-dpo-v1-mkmlizer: Downloaded to shared memory in 26.703s
chaiml-ca18-v1-6-dpo-v1-mkmlizer: Checking if ChaiML/ca18-v1-6-dpo already exists in ChaiML
chaiml-ca18-v1-6-dpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpi_2k5xib, device:0
chaiml-ca18-v1-6-dpo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v1-6-dpo-v1-mkmlizer: quantized model in 26.285s
chaiml-ca18-v1-6-dpo-v1-mkmlizer: Processed model ChaiML/ca18-v1-6-dpo in 52.989s
chaiml-ca18-v1-6-dpo-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v1-6-dpo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v1-6-dpo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v1-6-dpo-v1/nvidia
chaiml-ca18-v1-6-dpo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v1-6-dpo-v1/nvidia/config.json
chaiml-ca18-v1-6-dpo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v1-6-dpo-v1/nvidia/special_tokens_map.json
chaiml-ca18-v1-6-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v1-6-dpo-v1/nvidia/tokenizer_config.json
chaiml-ca18-v1-6-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v1-6-dpo-v1/nvidia/tokenizer.json
chaiml-ca18-v1-6-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v1-6-dpo-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v1-6-dpo-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 33.31it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 47.15it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:06, 51.85it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 53.14it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:05, 54.79it/s]
Loading 0:  14%|█▍        | 50/363 [00:00<00:05, 56.06it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:04, 61.22it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:06, 44.72it/s]
Loading 0:  20%|██        | 73/363 [00:01<00:06, 43.26it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:05, 50.56it/s]
Loading 0:  24%|██▍       | 87/363 [00:01<00:05, 49.43it/s]
Loading 0:  26%|██▌       | 93/363 [00:01<00:05, 50.26it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:05, 48.21it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:04, 54.65it/s]
Loading 0:  32%|███▏      | 116/363 [00:02<00:04, 53.09it/s]
Loading 0:  34%|███▍      | 123/363 [00:02<00:04, 51.42it/s]
Loading 0:  36%|███▌      | 129/363 [00:02<00:04, 51.89it/s]
Loading 0:  37%|███▋      | 135/363 [00:02<00:04, 53.71it/s]
Loading 0:  39%|███▉      | 141/363 [00:02<00:05, 41.41it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:07, 27.27it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:07, 27.05it/s]
Loading 0:  42%|████▏     | 154/363 [00:03<00:07, 29.22it/s]
Loading 0:  44%|████▎     | 158/363 [00:03<00:07, 28.74it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:05, 38.09it/s]
Loading 0:  47%|████▋     | 172/363 [00:03<00:04, 40.17it/s]
Loading 0:  49%|████▉     | 177/363 [00:03<00:04, 42.16it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 48.87it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:03, 47.72it/s]
Loading 0:  54%|█████▍    | 196/363 [00:04<00:03, 49.68it/s]
Loading 0:  56%|█████▌    | 203/363 [00:04<00:03, 47.67it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 55.17it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:02, 52.55it/s]
Loading 0:  61%|██████▏   | 223/363 [00:04<00:03, 43.49it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 43.34it/s]
Loading 0:  64%|██████▍   | 233/363 [00:05<00:02, 44.89it/s]
Loading 0:  66%|██████▌   | 239/363 [00:05<00:02, 42.21it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 50.41it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 48.93it/s]
Loading 0:  71%|███████▏  | 259/363 [00:05<00:02, 50.15it/s]
Loading 0:  73%|███████▎  | 266/363 [00:05<00:02, 47.05it/s]
Loading 0:  75%|███████▌  | 274/363 [00:05<00:01, 53.49it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 51.40it/s]
Loading 0:  79%|███████▉  | 286/363 [00:06<00:01, 51.86it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 53.91it/s]
Loading 0:  82%|████████▏ | 298/363 [00:06<00:01, 50.24it/s]
Loading 0:  84%|████████▎ | 304/363 [00:06<00:01, 30.56it/s]
Loading 0:  85%|████████▌ | 309/363 [00:06<00:01, 33.94it/s]
Loading 0:  87%|████████▋ | 314/363 [00:07<00:01, 35.06it/s]
Loading 0:  88%|████████▊ | 321/363 [00:07<00:01, 38.21it/s]
Loading 0:  91%|█████████ | 330/363 [00:07<00:00, 43.54it/s]
Loading 0:  93%|█████████▎| 339/363 [00:07<00:00, 46.86it/s]
Loading 0:  96%|█████████▌| 348/363 [00:07<00:00, 49.60it/s]
Loading 0:  98%|█████████▊| 357/363 [00:07<00:00, 51.31it/s]
                                                            
Job chaiml-ca18-v1-6-dpo-v1-mkmlizer completed after 83.18s with status: succeeded
Stopping job with name chaiml-ca18-v1-6-dpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 83.72s
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-v1-6-dpo-v1
Waiting for inference service chaiml-ca18-v1-6-dpo-v1 to be ready
Unable to record family friendly update due to error: Invalid JSON input: Expecting value: line 1 column 1 (char 0)
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', '')
Inference service chaiml-ca18-v1-6-dpo-v1 ready after 170.72469115257263s
Pipeline stage MKMLDeployer completed in 171.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.7099127769470215s
Received healthy response to inference request in 1.0889520645141602s
Received healthy response to inference request in 1.3328838348388672s
Received healthy response to inference request in 1.4508724212646484s
Received healthy response to inference request in 1.2603867053985596s
5 requests
0 failed requests
5th percentile: 1.12323899269104
10th percentile: 1.1575259208679198
20th percentile: 1.2260997772216797
30th percentile: 1.274886131286621
40th percentile: 1.3038849830627441
50th percentile: 1.3328838348388672
60th percentile: 1.3800792694091797
70th percentile: 1.4272747039794922
80th percentile: 1.502680492401123
90th percentile: 1.6062966346740724
95th percentile: 1.658104705810547
99th percentile: 1.6995511627197266
mean time: 1.3686015605926514
Pipeline stage StressChecker completed in 8.42s
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 0.67s
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 0.67s
Shutdown handler de-registered
chaiml-ca18-v1-6-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 2537.08s
Shutdown handler de-registered
chaiml-ca18-v1-6-dpo_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v1-6-dpo_v1 status is now torndown due to DeploymentManager action