chaiml-ca18-v1-2-dpo-cosine

developer_uid: chai_backend_admin

submission_id: chaiml-ca18-v1-2-dpo-cosine_v1

model_name: training123

model_group: ChaiML/ca18-v1-2-dpo_cos

status: torndown

timestamp: 2025-11-18T11:51:15+00:00

num_battles: 6128

num_wins: 3263

celo_rating: 1318.97

family_friendly_score: 0.5052

family_friendly_standard_error: 0.007070685398177464

submission_type: basic

model_repo: ChaiML/ca18-v1-2-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': 0.6894673208389096, 'latency_mean': 1.4502979302406311, 'latency_p50': 1.43244469165802, 'latency_p90': 1.5911721467971802}, {'batch_size': 3, 'throughput': 1.283967804547954, 'latency_mean': 2.33121205329895, 'latency_p50': 2.3370450735092163, 'latency_p90': 2.545377254486084}, {'batch_size': 5, 'throughput': 1.5603159450213233, 'latency_mean': 3.1860946547985076, 'latency_p50': 3.177484154701233, 'latency_p90': 3.605475330352783}, {'batch_size': 6, 'throughput': 1.665118709456142, 'latency_mean': 3.581375774145126, 'latency_p50': 3.5833194255828857, 'latency_p90': 4.051030850410461}, {'batch_size': 8, 'throughput': 1.797720966631023, 'latency_mean': 4.432082271575927, 'latency_p50': 4.42715048789978, 'latency_p90': 5.058031392097473}, {'batch_size': 10, 'throughput': 1.8521990915215663, 'latency_mean': 5.3482394587993625, 'latency_p50': 5.382451772689819, 'latency_p90': 6.0213255167007445}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ca18-v1-2-dpo_cosine

model_size: 13B

ranking_group: single

throughput_3p7s: 1.7

us_pacific_date: 2025-11-15

win_ratio: 0.5324738903394256

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:', '\n', '</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
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer
Waiting for job on chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer to finish
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: Downloaded to shared memory in 27.681s
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: Checking if ChaiML/ca18-v1-2-dpo_cosine already exists in ChaiML
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprs4fvs53, device:0
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v1-2-dpo-cosine-v1/nvidia
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v1-2-dpo-cosine-v1/nvidia/config.json
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v1-2-dpo-cosine-v1/nvidia/special_tokens_map.json
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v1-2-dpo-cosine-v1/nvidia/tokenizer_config.json
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v1-2-dpo-cosine-v1/nvidia/tokenizer.json
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v1-2-dpo-cosine-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 33.47it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:07, 45.57it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:06, 49.62it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:06, 52.45it/s]
Loading 0:  11%|█▏        | 41/363 [00:00<00:06, 53.61it/s]
Loading 0:  14%|█▍        | 50/363 [00:00<00:05, 54.72it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:05, 57.93it/s]
Loading 0:  17%|█▋        | 63/363 [00:01<00:07, 42.39it/s]
Loading 0:  19%|█▉        | 69/363 [00:01<00:06, 42.90it/s]
Loading 0:  21%|██        | 75/363 [00:01<00:06, 46.06it/s]
Loading 0:  23%|██▎       | 82/363 [00:01<00:06, 45.56it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 53.13it/s]
Loading 0:  26%|██▋       | 96/363 [00:01<00:05, 51.02it/s]
Loading 0:  28%|██▊       | 102/363 [00:02<00:04, 52.72it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:04, 55.54it/s]
Loading 0:  32%|███▏      | 116/363 [00:02<00:04, 54.82it/s]
Loading 0:  34%|███▍      | 123/363 [00:02<00:04, 52.58it/s]
Loading 0:  36%|███▌      | 129/363 [00:02<00:04, 52.38it/s]
Loading 0:  37%|███▋      | 136/363 [00:02<00:04, 49.08it/s]
Loading 0:  39%|███▉      | 142/363 [00:02<00:05, 43.12it/s]
Loading 0:  40%|████      | 147/363 [00:03<00:05, 42.98it/s]
Loading 0:  42%|████▏     | 154/363 [00:03<00:04, 44.45it/s]
Loading 0:  44%|████▍     | 159/363 [00:03<00:04, 45.44it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:03, 51.04it/s]
Loading 0:  47%|████▋     | 172/363 [00:03<00:03, 49.74it/s]
Loading 0:  49%|████▉     | 178/363 [00:03<00:03, 51.47it/s]
Loading 0:  51%|█████     | 185/363 [00:03<00:03, 49.03it/s]
Loading 0:  53%|█████▎    | 193/363 [00:03<00:03, 56.02it/s]
Loading 0:  55%|█████▍    | 199/363 [00:03<00:03, 53.16it/s]
Loading 0:  56%|█████▋    | 205/363 [00:04<00:02, 53.47it/s]
Loading 0:  58%|█████▊    | 212/363 [00:04<00:03, 50.04it/s]
Loading 0:  61%|██████    | 222/363 [00:04<00:02, 56.00it/s]
Loading 0:  63%|██████▎   | 228/363 [00:04<00:03, 42.59it/s]
Loading 0:  64%|██████▍   | 234/363 [00:04<00:02, 45.78it/s]
Loading 0:  66%|██████▌   | 240/363 [00:04<00:02, 43.91it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 49.40it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 48.44it/s]
Loading 0:  71%|███████▏  | 259/363 [00:05<00:02, 49.91it/s]
Loading 0:  73%|███████▎  | 266/363 [00:05<00:02, 47.84it/s]
Loading 0:  75%|███████▌  | 274/363 [00:05<00:01, 55.00it/s]
Loading 0:  77%|███████▋  | 280/363 [00:05<00:01, 52.48it/s]
Loading 0:  79%|███████▉  | 286/363 [00:05<00:01, 53.21it/s]
Loading 0:  81%|████████  | 293/363 [00:05<00:01, 49.43it/s]
Loading 0:  83%|████████▎ | 303/363 [00:06<00:01, 55.18it/s]
Loading 0:  85%|████████▌ | 309/363 [00:06<00:01, 33.12it/s]
Loading 0:  87%|████████▋ | 314/363 [00:06<00:01, 34.63it/s]
Loading 0:  88%|████████▊ | 321/363 [00:06<00:01, 37.41it/s]
Loading 0:  91%|█████████ | 330/363 [00:06<00:00, 42.96it/s]
Loading 0:  93%|█████████▎| 339/363 [00:07<00:00, 46.37it/s]
Loading 0:  96%|█████████▌| 347/363 [00:07<00:00, 53.02it/s]
Loading 0:  97%|█████████▋| 353/363 [00:07<00:00, 51.61it/s]
Loading 0:  99%|█████████▉| 359/363 [00:07<00:00, 52.37it/s]
                                                            
Job chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer completed after 104.17s with status: succeeded
Stopping job with name chaiml-ca18-v1-2-dpo-cosine-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.69s
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-v1-2-dpo-cosine-v1
Waiting for inference service chaiml-ca18-v1-2-dpo-cosine-v1 to be ready
Inference service chaiml-ca18-v1-2-dpo-cosine-v1 ready after 171.0282220840454s
Pipeline stage MKMLDeployer completed in 171.49s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.781599521636963s
Received healthy response to inference request in 1.2486622333526611s
Received healthy response to inference request in 1.2638463973999023s
Received healthy response to inference request in 1.4284603595733643s
Received healthy response to inference request in 1.3193979263305664s
5 requests
0 failed requests
5th percentile: 1.2516990661621095
10th percentile: 1.2547358989715576
20th percentile: 1.260809564590454
30th percentile: 1.2749567031860352
40th percentile: 1.2971773147583008
50th percentile: 1.3193979263305664
60th percentile: 1.3630228996276856
70th percentile: 1.4066478729248046
80th percentile: 1.4990881919860841
90th percentile: 1.6403438568115234
95th percentile: 1.710971689224243
99th percentile: 1.767473955154419
mean time: 1.4083932876586913
Pipeline stage StressChecker completed in 8.57s
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 0.79s
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-v1-2-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 2647.77s
Shutdown handler de-registered
chaiml-ca18-v1-2-dpo-cosine_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v1-2-dpo-cosine_v1 status is now torndown due to DeploymentManager action