chaiml-icld-v3-dpo-cosineb025

developer_uid: chai_backend_admin

submission_id: chaiml-icld-v3-dpo-cosineb025_v2

model_name: training123

model_group: ChaiML/icld-v3-dpo_cosin

status: inactive

timestamp: 2025-11-24T02:36:51+00:00

num_battles: 6339

num_wins: 3155

celo_rating: 1298.64

family_friendly_score: 0.5352

family_friendly_standard_error: 0.007053523374881521

submission_type: basic

model_repo: ChaiML/icld-v3-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': 0.4491768517819594, 'latency_mean': 2.226196924448013, 'latency_p50': 2.2284427881240845, 'latency_p90': 2.4255263805389404}, {'batch_size': 3, 'throughput': 0.8340747265831907, 'latency_mean': 3.589502809047699, 'latency_p50': 3.5775710344314575, 'latency_p90': 3.913651084899902}, {'batch_size': 5, 'throughput': 0.9979051577500783, 'latency_mean': 4.978994669914246, 'latency_p50': 5.023048996925354, 'latency_p90': 5.508768367767334}, {'batch_size': 6, 'throughput': 1.057040938427162, 'latency_mean': 5.647702261209488, 'latency_p50': 5.634626269340515, 'latency_p90': 6.273872113227844}, {'batch_size': 10, 'throughput': 1.1633128256479917, 'latency_mean': 8.538270988464355, 'latency_p50': 8.57596230506897, 'latency_p90': 9.570735216140747}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/icld-v3-dpo_cosineb025

model_size: 24B

ranking_group: single

throughput_3p7s: 0.85

us_pacific_date: 2025-11-23

win_ratio: 0.4977125729610349

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-v3-dpo-cosineb025-v2-mkmlizer
Waiting for job on chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer to finish
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║                                                                     ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║                                                                     ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║                                                                     ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║                                                                     ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ║                                                                     ║
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: Downloaded to shared memory in 119.467s
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: Checking if ChaiML/icld-v3-dpo_cosineb025 already exists in ChaiML
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpihq3r6pr, device:0
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: quantized model in 47.218s
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: Processed model ChaiML/icld-v3-dpo_cosineb025 in 166.685s
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-icld-v3-dpo-cosineb025-v2/nvidia
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-icld-v3-dpo-cosineb025-v2/nvidia/config.json
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-icld-v3-dpo-cosineb025-v2/nvidia/special_tokens_map.json
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-icld-v3-dpo-cosineb025-v2/nvidia/tokenizer_config.json
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-icld-v3-dpo-cosineb025-v2/nvidia/tokenizer.json
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-icld-v3-dpo-cosineb025-v2/nvidia/flywheel_model.1.safetensors
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-icld-v3-dpo-cosineb025-v2/nvidia/flywheel_model.0.safetensors
chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 37.63it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 29.84it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 32.36it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 28.81it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 33.47it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 29.91it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 36.62it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 20.75it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 23.43it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.02it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.21it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.26it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 29.55it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 27.89it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 28.61it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 24.99it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 20.83it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.40it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.00it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:09, 27.82it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:09, 28.13it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 22.11it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 29.46it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 28.06it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 23.06it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 26.22it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 23.59it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.61it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 26.81it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.56it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 27.80it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.34it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.69it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 33.83it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:09, 21.50it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 24.05it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:08, 24.63it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 27.67it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:07, 26.59it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 29.40it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 27.74it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.23it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 25.18it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.12it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.98it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.51it/s]
Loading 0:  55%|█████▍    | 199/363 [00:07<00:06, 24.49it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.49it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<04:03,  1.50s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<03:09,  1.18s/it]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:43,  1.50it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:16,  1.98it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:55,  2.68it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:36,  3.94it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:27,  5.12it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.19it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.20it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 10.96it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.89it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.82it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.38it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 22.24it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 25.54it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 25.29it/s]
Loading 0:  73%|███████▎  | 266/363 [00:24<00:03, 31.12it/s]
Loading 0:  74%|███████▍  | 270/363 [00:24<00:04, 20.46it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 23.00it/s]
Loading 0:  76%|███████▋  | 277/363 [00:24<00:03, 23.75it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 26.68it/s]
Loading 0:  79%|███████▉  | 286/363 [00:25<00:02, 26.52it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 29.48it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 28.31it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 28.62it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 26.01it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 23.71it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 24.53it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:01, 25.30it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 28.59it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 25.74it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 31.00it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 29.38it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 29.68it/s]
Loading 0:  93%|█████████▎| 339/363 [00:27<00:00, 30.04it/s]
Loading 0:  94%|█████████▍| 343/363 [00:27<00:01, 17.71it/s]
Loading 0:  96%|█████████▌| 348/363 [00:27<00:00, 19.07it/s]
Loading 0:  98%|█████████▊| 355/363 [00:27<00:00, 25.46it/s]
Loading 0:  99%|█████████▉| 359/363 [00:28<00:00, 25.56it/s]
                                                            
Job chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer completed after 205.55s with status: succeeded
Stopping job with name chaiml-icld-v3-dpo-cosineb025-v2-mkmlizer
Pipeline stage MKMLizer completed in 206.42s
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-icld-v3-dpo-cosineb025-v2
Waiting for inference service chaiml-icld-v3-dpo-cosineb025-v2 to be ready
Inference service chaiml-icld-v3-dpo-cosineb025-v2 ready after 150.87340331077576s
Pipeline stage MKMLDeployer completed in 151.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1480484008789062s
Received healthy response to inference request in 2.037930727005005s
Received healthy response to inference request in 1.6939201354980469s
Received healthy response to inference request in 1.7558252811431885s
Received healthy response to inference request in 1.6957201957702637s
5 requests
0 failed requests
5th percentile: 1.6942801475524902
10th percentile: 1.6946401596069336
20th percentile: 1.6953601837158203
30th percentile: 1.7077412128448486
40th percentile: 1.7317832469940186
50th percentile: 1.7558252811431885
60th percentile: 1.8686674594879151
70th percentile: 1.9815096378326416
80th percentile: 2.0599542617797852
90th percentile: 2.1040013313293455
95th percentile: 2.126024866104126
99th percentile: 2.1436436939239503
mean time: 1.866288948059082
Pipeline stage StressChecker completed in 10.56s
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 0.80s
Shutdown handler de-registered
chaiml-icld-v3-dpo-cosineb025_v2 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 2864.51s
Shutdown handler de-registered
chaiml-icld-v3-dpo-cosineb025_v2 status is now inactive due to auto deactivation removed underperforming models