chaiml-ca18-v2-1-dpo-cosine

developer_uid: chai_backend_admin

submission_id: chaiml-ca18-v2-1-dpo-cosine_v1

model_name: training123

model_group: ChaiML/ca18-v2-1-dpo_cos

status: torndown

timestamp: 2025-11-19T21:21:15+00:00

num_battles: 5317

num_wins: 2804

celo_rating: 1306.86

family_friendly_score: 0.511

family_friendly_standard_error: 0.007069356406349874

submission_type: basic

model_repo: ChaiML/ca18-v2-1-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': 0.5659266240084223, 'latency_mean': 1.7668871593475342, 'latency_p50': 1.4713650941848755, 'latency_p90': 1.680059242248535}, {'batch_size': 3, 'throughput': 1.2927580280904343, 'latency_mean': 2.315737179517746, 'latency_p50': 2.318277955055237, 'latency_p90': 2.543325638771057}, {'batch_size': 5, 'throughput': 1.5789776524542871, 'latency_mean': 3.158768718242645, 'latency_p50': 3.1645838022232056, 'latency_p90': 3.512084722518921}, {'batch_size': 6, 'throughput': 1.6698110405162803, 'latency_mean': 3.5702319288253785, 'latency_p50': 3.568612575531006, 'latency_p90': 3.9977799892425536}, {'batch_size': 8, 'throughput': 1.7952845944656266, 'latency_mean': 4.4102126455307005, 'latency_p50': 4.428151607513428, 'latency_p90': 4.9281927108764645}, {'batch_size': 10, 'throughput': 1.8646393137251853, 'latency_mean': 5.309639745950699, 'latency_p50': 5.35203492641449, 'latency_p90': 6.009781408309936}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ca18-v2-1-dpo_cosine

model_size: 13B

ranking_group: single

throughput_3p7s: 1.71

us_pacific_date: 2025-11-16

win_ratio: 0.5273650554824149

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', 'You:', '</s>', '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
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
run pipeline %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
Connection pool is full, discarding connection: %s. Connection pool size: %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer
Waiting for job on chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer to finish
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: Downloaded to shared memory in 22.578s
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: Checking if ChaiML/ca18-v2-1-dpo_cosine already exists in ChaiML
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5ju65zfn, device:0
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: quantized model in 25.707s
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: Processed model ChaiML/ca18-v2-1-dpo_cosine in 48.285s
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v2-1-dpo-cosine-v1/nvidia
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v2-1-dpo-cosine-v1/nvidia/config.json
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v2-1-dpo-cosine-v1/nvidia/special_tokens_map.json
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v2-1-dpo-cosine-v1/nvidia/tokenizer_config.json
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v2-1-dpo-cosine-v1/nvidia/tokenizer.json
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v2-1-dpo-cosine-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 34.47it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 48.68it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:06, 53.36it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:05, 55.49it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:05, 55.67it/s]
Loading 0:  14%|█▍        | 50/363 [00:00<00:05, 56.55it/s]
Loading 0:  17%|█▋        | 60/363 [00:01<00:04, 62.58it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:06, 47.31it/s]
Loading 0:  20%|██        | 73/363 [00:01<00:06, 45.43it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:05, 48.73it/s]
Loading 0:  25%|██▌       | 91/363 [00:01<00:05, 50.79it/s]
Loading 0:  27%|██▋       | 99/363 [00:01<00:04, 56.20it/s]
Loading 0:  29%|██▉       | 105/363 [00:01<00:04, 54.22it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:04, 56.86it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:04, 49.57it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 56.34it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:04, 53.76it/s]
Loading 0:  38%|███▊      | 138/363 [00:02<00:04, 54.39it/s]
Loading 0:  40%|███▉      | 144/363 [00:02<00:05, 38.42it/s]
Loading 0:  41%|████      | 149/363 [00:02<00:05, 40.27it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:04, 48.95it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 48.61it/s]
Loading 0:  47%|████▋     | 169/363 [00:03<00:03, 50.00it/s]
Loading 0:  48%|████▊     | 175/363 [00:03<00:03, 52.52it/s]
Loading 0:  50%|████▉     | 181/363 [00:03<00:03, 51.00it/s]
Loading 0:  52%|█████▏    | 187/363 [00:03<00:03, 52.21it/s]
Loading 0:  53%|█████▎    | 194/363 [00:03<00:03, 48.97it/s]
Loading 0:  56%|█████▌    | 202/363 [00:03<00:02, 55.89it/s]
Loading 0:  57%|█████▋    | 208/363 [00:04<00:02, 53.00it/s]
Loading 0:  59%|█████▉    | 214/363 [00:04<00:02, 53.64it/s]
Loading 0:  61%|██████    | 222/363 [00:04<00:02, 54.62it/s]
Loading 0:  63%|██████▎   | 228/363 [00:04<00:03, 39.66it/s]
Loading 0:  65%|██████▍   | 235/363 [00:04<00:03, 41.96it/s]
Loading 0:  66%|██████▌   | 240/363 [00:04<00:02, 42.79it/s]
Loading 0:  68%|██████▊   | 247/363 [00:04<00:02, 48.49it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 47.80it/s]
Loading 0:  71%|███████▏  | 259/363 [00:05<00:02, 49.88it/s]
Loading 0:  73%|███████▎  | 266/363 [00:05<00:02, 47.94it/s]
Loading 0:  75%|███████▌  | 274/363 [00:05<00:01, 55.17it/s]
Loading 0:  77%|███████▋  | 280/363 [00:05<00:01, 52.87it/s]
Loading 0:  79%|███████▉  | 286/363 [00:05<00:01, 52.43it/s]
Loading 0:  81%|████████  | 293/363 [00:05<00:01, 48.84it/s]
Loading 0:  83%|████████▎ | 303/363 [00:05<00:01, 55.45it/s]
Loading 0:  85%|████████▌ | 309/363 [00:06<00:01, 33.26it/s]
Loading 0:  87%|████████▋ | 314/363 [00:06<00:01, 34.75it/s]
Loading 0:  88%|████████▊ | 321/363 [00:06<00:01, 37.51it/s]
Loading 0:  91%|█████████ | 330/363 [00:06<00:00, 43.10it/s]
Loading 0:  93%|█████████▎| 339/363 [00:06<00:00, 46.96it/s]
Loading 0:  96%|█████████▌| 348/363 [00:07<00:00, 49.53it/s]
Loading 0:  98%|█████████▊| 357/363 [00:07<00:00, 51.39it/s]
                                                            
Job chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer completed after 183.48s with status: succeeded
Stopping job with name chaiml-ca18-v2-1-dpo-cosine-v1-mkmlizer
Pipeline stage MKMLizer completed in 184.01s
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-v2-1-dpo-cosine-v1
Waiting for inference service chaiml-ca18-v2-1-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-v2-1-dpo-cosine-v1 ready after 171.0278398990631s
Pipeline stage MKMLDeployer completed in 171.59s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8294880390167236s
Received healthy response to inference request in 1.4620757102966309s
Received healthy response to inference request in 1.2632865905761719s
Received healthy response to inference request in 1.2920820713043213s
Received healthy response to inference request in 1.5168020725250244s
5 requests
0 failed requests
5th percentile: 1.2690456867218018
10th percentile: 1.2748047828674316
20th percentile: 1.2863229751586913
30th percentile: 1.3260807991027832
40th percentile: 1.394078254699707
50th percentile: 1.4620757102966309
60th percentile: 1.4839662551879882
70th percentile: 1.5058568000793457
80th percentile: 1.5793392658233643
90th percentile: 1.704413652420044
95th percentile: 1.7669508457183838
99th percentile: 1.8169806003570557
mean time: 1.4727468967437745
Pipeline stage StressChecker completed in 8.68s
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 0.68s
Shutdown handler de-registered
chaiml-ca18-v2-1-dpo-cosine_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2480.99s
Shutdown handler de-registered
chaiml-ca18-v2-1-dpo-cosine_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v2-1-dpo-cosine_v1 status is now torndown due to DeploymentManager action