developer_uid: chai_backend_admin
submission_id: chaiml-ca18-v1-1-dpo-cosine_v1
model_name: training123
model_group: ChaiML/ca18-v1-1-dpo_cos
status: torndown
timestamp: 2025-11-18T11:41:22+00:00
num_battles: 6113
num_wins: 3156
celo_rating: 1296.4
family_friendly_score: 0.507
family_friendly_standard_error: 0.007070374813261317
submission_type: basic
model_repo: ChaiML/ca18-v1-1-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': 0.6841232880753825, 'latency_mean': 1.4615998446941376, 'latency_p50': 1.4507249593734741, 'latency_p90': 1.61453275680542}, {'batch_size': 3, 'throughput': 1.2738256870475306, 'latency_mean': 2.3464299762248992, 'latency_p50': 2.3651920557022095, 'latency_p90': 2.5817554712295534}, {'batch_size': 5, 'throughput': 1.5688015149394932, 'latency_mean': 3.1729887413978575, 'latency_p50': 3.164022922515869, 'latency_p90': 3.6125547170639036}, {'batch_size': 6, 'throughput': 1.6581470382454553, 'latency_mean': 3.6000134992599486, 'latency_p50': 3.6193881034851074, 'latency_p90': 4.011175489425659}, {'batch_size': 8, 'throughput': 1.7796516727758274, 'latency_mean': 4.471601915359497, 'latency_p50': 4.4735400676727295, 'latency_p90': 5.070699143409729}, {'batch_size': 10, 'throughput': 1.832991341780154, 'latency_mean': 5.410948777198792, 'latency_p50': 5.446178317070007, 'latency_p90': 6.117558598518372}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: training123
is_internal_developer: True
language_model: ChaiML/ca18-v1-1-dpo_cosine
model_size: 13B
ranking_group: single
throughput_3p7s: 1.68
us_pacific_date: 2025-11-15
win_ratio: 0.5162767871748732
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>', 'You:', 'User:', '\n'], '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-v1-1-dpo-cosine-v1-mkmlizer
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
Waiting for job on chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer to finish
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: Downloaded to shared memory in 39.302s
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: Checking if ChaiML/ca18-v1-1-dpo_cosine already exists in ChaiML
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0ouzx58c, device:0
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: quantized model in 25.611s
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: Processed model ChaiML/ca18-v1-1-dpo_cosine in 64.914s
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v1-1-dpo-cosine-v1/nvidia
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v1-1-dpo-cosine-v1/nvidia/config.json
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v1-1-dpo-cosine-v1/nvidia/special_tokens_map.json
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v1-1-dpo-cosine-v1/nvidia/tokenizer_config.json
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v1-1-dpo-cosine-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 34.86it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 49.35it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:06, 53.81it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:05, 56.28it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:05, 57.73it/s]
Loading 0:  14%|█▍        | 50/363 [00:00<00:05, 58.43it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:04, 64.49it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:06, 48.38it/s]
Loading 0:  20%|██        | 73/363 [00:01<00:06, 45.96it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:05, 49.10it/s]
Loading 0:  25%|██▌       | 91/363 [00:01<00:05, 51.24it/s]
Loading 0:  27%|██▋       | 99/363 [00:01<00:04, 56.70it/s]
Loading 0:  29%|██▉       | 105/363 [00:01<00:04, 54.65it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:04, 58.24it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:04, 53.14it/s]
Loading 0:  35%|███▍      | 127/363 [00:02<00:04, 52.25it/s]
Loading 0:  37%|███▋      | 136/363 [00:02<00:04, 53.61it/s]
Loading 0:  39%|███▉      | 142/363 [00:02<00:04, 46.76it/s]
Loading 0:  40%|████      | 147/363 [00:02<00:04, 45.57it/s]
Loading 0:  42%|████▏     | 153/363 [00:02<00:04, 48.77it/s]
Loading 0:  44%|████▍     | 159/363 [00:03<00:04, 46.01it/s]
Loading 0:  46%|████▌     | 167/363 [00:03<00:04, 47.01it/s]
Loading 0:  48%|████▊     | 175/363 [00:03<00:03, 53.66it/s]
Loading 0:  50%|████▉     | 181/363 [00:03<00:03, 51.45it/s]
Loading 0:  52%|█████▏    | 187/363 [00:03<00:03, 52.37it/s]
Loading 0:  53%|█████▎    | 194/363 [00:03<00:03, 49.41it/s]
Loading 0:  56%|█████▌    | 203/363 [00:03<00:03, 51.61it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 57.96it/s]
Loading 0:  60%|██████    | 218/363 [00:04<00:02, 55.19it/s]
Loading 0:  62%|██████▏   | 224/363 [00:04<00:03, 45.52it/s]
Loading 0:  63%|██████▎   | 229/363 [00:04<00:02, 45.07it/s]
Loading 0:  65%|██████▍   | 235/363 [00:04<00:02, 44.93it/s]
Loading 0:  66%|██████▌   | 240/363 [00:04<00:02, 45.66it/s]
Loading 0:  68%|██████▊   | 247/363 [00:04<00:02, 51.49it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 40.88it/s]
Loading 0:  71%|███████   | 258/363 [00:05<00:02, 41.88it/s]
Loading 0:  73%|███████▎  | 266/363 [00:05<00:02, 44.38it/s]
Loading 0:  75%|███████▌  | 274/363 [00:05<00:01, 52.38it/s]
Loading 0:  77%|███████▋  | 280/363 [00:05<00:01, 50.41it/s]
Loading 0:  79%|███████▉  | 286/363 [00:05<00:01, 52.20it/s]
Loading 0:  81%|████████  | 293/363 [00:05<00:01, 49.80it/s]
Loading 0:  83%|████████▎ | 303/363 [00:05<00:01, 56.53it/s]
Loading 0:  85%|████████▌ | 309/363 [00:06<00:01, 34.01it/s]
Loading 0:  87%|████████▋ | 314/363 [00:06<00:01, 35.27it/s]
Loading 0:  88%|████████▊ | 321/363 [00:06<00:01, 38.11it/s]
Loading 0:  91%|█████████ | 330/363 [00:06<00:00, 43.71it/s]
Loading 0:  93%|█████████▎| 339/363 [00:06<00:00, 47.18it/s]
Loading 0:  96%|█████████▌| 348/363 [00:07<00:00, 50.14it/s]
Loading 0:  98%|█████████▊| 357/363 [00:07<00:00, 51.59it/s]
                                                            

Job chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer completed after 103.74s with status: succeeded
Stopping job with name chaiml-ca18-v1-1-dpo-cosine-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.75s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ca18-v1-1-dpo-cosine-v1
Waiting for inference service chaiml-ca18-v1-1-dpo-cosine-v1 to be ready
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-v1-1-dpo-cosine-v1 ready after 171.15546202659607s
Pipeline stage MKMLDeployer completed in 171.86s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.511230707168579s
Received healthy response to inference request in 1.5110626220703125s
Received healthy response to inference request in 1.3669631481170654s
Received healthy response to inference request in 1.3020148277282715s
Received healthy response to inference request in 1.304603099822998s
5 requests
0 failed requests
5th percentile: 1.3025324821472168
10th percentile: 1.3030501365661622
20th percentile: 1.3040854454040527
30th percentile: 1.3170751094818116
40th percentile: 1.3420191287994385
50th percentile: 1.3669631481170654
60th percentile: 1.4246029376983642
70th percentile: 1.482242727279663
80th percentile: 1.5110962390899658
90th percentile: 1.5111634731292725
95th percentile: 1.5111970901489258
99th percentile: 1.5112239837646484
mean time: 1.3991748809814453
Pipeline stage StressChecker completed in 8.66s
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 0.65s
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 0.82s
Shutdown handler de-registered
chaiml-ca18-v1-1-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 0.08s
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-v1-1-dpo-cosine-v1-profiler
Waiting for inference service chaiml-ca18-v1-1-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 2779.36s
Shutdown handler de-registered
chaiml-ca18-v1-1-dpo-cosine_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v1-1-dpo-cosine_v1 status is now torndown due to DeploymentManager action