chaiml-icld-v2-dpo-cosineb025

developer_uid: chai_backend_admin

submission_id: chaiml-icld-v2-dpo-cosineb025_v1

model_name: training123

model_group: ChaiML/icld-v2-dpo_cosin

status: inactive

timestamp: 2025-11-23T12:06:53+00:00

num_battles: 7174

num_wins: 3689

celo_rating: 1304.61

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/icld-v2-dpo_cosineb025

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 2048

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.38035197069285803, 'latency_mean': 2.629041364192963, 'latency_p50': 2.6414575576782227, 'latency_p90': 2.865526580810547}, {'batch_size': 2, 'throughput': 0.5780200530348982, 'latency_mean': 3.4526409769058226, 'latency_p50': 3.4575120210647583, 'latency_p90': 3.783003640174866}, {'batch_size': 3, 'throughput': 0.712994250796409, 'latency_mean': 4.203490288257599, 'latency_p50': 4.212367296218872, 'latency_p90': 4.764248037338256}, {'batch_size': 4, 'throughput': 0.8086104065297425, 'latency_mean': 4.931765018701554, 'latency_p50': 4.942420244216919, 'latency_p90': 5.5036579132080075}, {'batch_size': 5, 'throughput': 0.8674055519138698, 'latency_mean': 5.748834638595581, 'latency_p50': 5.777377367019653, 'latency_p90': 6.577936744689941}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/icld-v2-dpo_cosineb025

model_size: 24B

ranking_group: single

throughput_3p7s: 0.63

us_pacific_date: 2025-11-23

win_ratio: 0.514218009478673

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', 'User:', '</s>'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', '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-icld-v2-dpo-cosineb025-v1-mkmlizer
Waiting for job on chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer to finish
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║                                                                     ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║                                                                     ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║                                                                     ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║                                                                     ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ║                                                                     ║
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: Downloaded to shared memory in 53.624s
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: Checking if ChaiML/icld-v2-dpo_cosineb025 already exists in ChaiML
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplgnkz8iw, device:0
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: quantized model in 42.824s
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: Processed model ChaiML/icld-v2-dpo_cosineb025 in 96.448s
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-icld-v2-dpo-cosineb025-v1/nvidia
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-icld-v2-dpo-cosineb025-v1/nvidia/tokenizer.json
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-icld-v2-dpo-cosineb025-v1/nvidia/flywheel_model.1.safetensors
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-icld-v2-dpo-cosineb025-v1/nvidia/flywheel_model.0.safetensors
chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.52it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 39.52it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 37.93it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 37.64it/s]
Loading 0:   8%|▊         | 28/363 [00:00<00:08, 39.19it/s]
Loading 0:   9%|▉         | 33/363 [00:00<00:10, 32.47it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.26it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:15, 20.91it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 28.51it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 28.58it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:09, 32.48it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:09, 30.31it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 31.95it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 28.74it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 25.36it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.38it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:09, 30.85it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:10, 27.40it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:09, 27.31it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 34.68it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:07, 32.72it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 27.86it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 30.41it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:07, 31.16it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.09it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 26.12it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 32.40it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.33it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 34.30it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.23it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 38.95it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 26.79it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.86it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.95it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.67it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.91it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.31it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 33.13it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 30.59it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.13it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.31it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:14,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:55,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.10it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.66it/s]
Loading 0:  59%|█████▉    | 215/363 [00:20<00:39,  3.71it/s]
Loading 0:  60%|██████    | 219/363 [00:20<00:29,  4.95it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:20,  6.92it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:14,  9.50it/s]
Loading 0:  64%|██████▍   | 233/363 [00:20<00:11, 11.66it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:08, 14.55it/s]
Loading 0:  66%|██████▋   | 241/363 [00:20<00:07, 17.07it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 21.63it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 23.17it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 27.66it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 28.03it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 35.26it/s]
Loading 0:  75%|███████▍  | 271/363 [00:21<00:03, 25.80it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.33it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.43it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.67it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.82it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 32.08it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 33.01it/s]
Loading 0:  84%|████████▎ | 304/363 [00:22<00:01, 29.73it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 29.37it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.18it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.88it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.78it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 34.24it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 32.36it/s]
Loading 0:  92%|█████████▏| 335/363 [00:23<00:00, 32.70it/s]
Loading 0:  93%|█████████▎| 339/363 [00:23<00:00, 33.12it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.24it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 22.13it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.84it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 29.64it/s]
                                                            
Job chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer completed after 164.85s with status: succeeded
Stopping job with name chaiml-icld-v2-dpo-cosineb025-v1-mkmlizer
Pipeline stage MKMLizer completed in 165.36s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.41s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-icld-v2-dpo-cosineb025-v1
Waiting for inference service chaiml-icld-v2-dpo-cosineb025-v1 to be ready
Inference service chaiml-icld-v2-dpo-cosineb025-v1 ready after 150.67071843147278s
Pipeline stage MKMLDeployer completed in 159.77s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3764476776123047s
Received healthy response to inference request in 2.654778003692627s
Received healthy response to inference request in 2.146775484085083s
Received healthy response to inference request in 2.2174227237701416s
Received healthy response to inference request in 2.254443407058716s
5 requests
0 failed requests
5th percentile: 2.1609049320220945
10th percentile: 2.1750343799591065
20th percentile: 2.20329327583313
30th percentile: 2.2248268604278563
40th percentile: 2.239635133743286
50th percentile: 2.254443407058716
60th percentile: 2.303245115280151
70th percentile: 2.352046823501587
80th percentile: 2.4321137428283692
90th percentile: 2.543445873260498
95th percentile: 2.5991119384765624
99th percentile: 2.643644790649414
mean time: 2.3299734592437744
Pipeline stage StressChecker completed in 13.22s
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 0.62s
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-icld-v2-dpo-cosineb025_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-icld-v2-dpo-cosineb025-v1-profiler
Waiting for inference service chaiml-icld-v2-dpo-cosineb025-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4987.63s
Shutdown handler de-registered