chaiml-icld-v4-dpo-cosine

developer_uid: chai_backend_admin

submission_id: chaiml-icld-v4-dpo-cosine_v1

model_name: training123

model_group: ChaiML/icld-v4-dpo_cosin

status: inactive

timestamp: 2025-11-24T05:46:35+00:00

num_battles: 5623

num_wins: 2825

celo_rating: 1298.46

family_friendly_score: 0.5267999999999999

family_friendly_standard_error: 0.007060903058391327

submission_type: basic

model_repo: ChaiML/icld-v4-dpo_cosine

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': 0.379532431529315, 'latency_mean': 2.634721853733063, 'latency_p50': 2.6224559545516968, 'latency_p90': 2.8791138172149657}, {'batch_size': 2, 'throughput': 0.5756268321373127, 'latency_mean': 3.466679563522339, 'latency_p50': 3.4558966159820557, 'latency_p90': 3.7967240810394287}, {'batch_size': 3, 'throughput': 0.7142498991640024, 'latency_mean': 4.181150592565537, 'latency_p50': 4.216424345970154, 'latency_p90': 4.505104899406433}, {'batch_size': 4, 'throughput': 0.8036608270658192, 'latency_mean': 4.962969062328338, 'latency_p50': 4.985458016395569, 'latency_p90': 5.50748724937439}, {'batch_size': 5, 'throughput': 0.8734035542207818, 'latency_mean': 5.69882120013237, 'latency_p50': 5.7172335386276245, 'latency_p90': 6.514757871627808}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/icld-v4-dpo_cosine

model_size: 24B

ranking_group: single

throughput_3p7s: 0.63

us_pacific_date: 2025-11-23

win_ratio: 0.5024008536368486

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>', '\n', 'You:', 'User:'], '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-v4-dpo-cosine-v1-mkmlizer
Waiting for job on chaiml-icld-v4-dpo-cosine-v1-mkmlizer to finish
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: Downloaded to shared memory in 65.576s
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: Checking if ChaiML/icld-v4-dpo_cosine already exists in ChaiML
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplw4jwui0, device:0
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: quantized model in 47.188s
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: Processed model ChaiML/icld-v4-dpo_cosine in 112.764s
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-icld-v4-dpo-cosine-v1/nvidia
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-icld-v4-dpo-cosine-v1/nvidia/config.json
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-icld-v4-dpo-cosine-v1/nvidia/tokenizer_config.json
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-icld-v4-dpo-cosine-v1/nvidia/special_tokens_map.json
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-icld-v4-dpo-cosine-v1/nvidia/tokenizer.json
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-icld-v4-dpo-cosine-v1/nvidia/flywheel_model.1.safetensors
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-icld-v4-dpo-cosine-v1/nvidia/flywheel_model.0.safetensors
chaiml-icld-v4-dpo-cosine-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.27it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 30.93it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 33.48it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:11, 29.85it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 34.17it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 30.03it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 36.81it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 21.95it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 24.56it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 26.07it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 28.00it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 26.92it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 30.08it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 28.45it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 29.03it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.62it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.52it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.87it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:10, 26.07it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:09, 27.81it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:09, 27.56it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.77it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 29.14it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.69it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:11, 23.18it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 25.94it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.53it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.61it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 25.78it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 30.68it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 28.41it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 27.42it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:08, 25.02it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.24it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:08, 25.07it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:08, 23.24it/s]
Loading 0:  43%|████▎     | 157/363 [00:05<00:08, 24.16it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:08, 24.40it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 28.07it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:07, 25.49it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.38it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 28.14it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.68it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:06, 26.40it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.95it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:06, 24.67it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.93it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.93it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<03:01,  1.12s/it]
Loading 0:  56%|█████▌    | 203/363 [00:21<02:29,  1.07it/s]
Loading 0:  57%|█████▋    | 208/363 [00:21<01:30,  1.72it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:09,  2.19it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.88it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.11it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:27,  5.25it/s]
Loading 0:  62%|██████▏   | 224/363 [00:22<00:21,  6.34it/s]
Loading 0:  63%|██████▎   | 229/363 [00:22<00:14,  9.34it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.06it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.02it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.86it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 21.41it/s]
Loading 0:  69%|██████▉   | 250/363 [00:23<00:05, 22.12it/s]
Loading 0:  70%|███████   | 255/363 [00:23<00:04, 25.51it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 23.61it/s]
Loading 0:  73%|███████▎  | 265/363 [00:24<00:03, 30.34it/s]
Loading 0:  74%|███████▍  | 269/363 [00:24<00:04, 22.80it/s]
Loading 0:  75%|███████▍  | 272/363 [00:24<00:03, 23.40it/s]
Loading 0:  76%|███████▌  | 275/363 [00:24<00:04, 19.00it/s]
Loading 0:  78%|███████▊  | 282/363 [00:24<00:03, 25.99it/s]
Loading 0:  79%|███████▉  | 286/363 [00:25<00:03, 25.17it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 28.11it/s]
Loading 0:  81%|████████▏ | 295/363 [00:25<00:02, 27.06it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.77it/s]
Loading 0:  84%|████████▎ | 304/363 [00:25<00:02, 25.82it/s]
Loading 0:  85%|████████▍ | 307/363 [00:25<00:02, 23.52it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 24.39it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 24.51it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 27.64it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 24.57it/s]
Loading 0:  90%|████████▉ | 325/363 [00:26<00:01, 25.53it/s]
Loading 0:  90%|█████████ | 328/363 [00:26<00:01, 26.05it/s]
Loading 0:  91%|█████████ | 331/363 [00:26<00:01, 25.85it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:01, 26.47it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 25.87it/s]
Loading 0:  94%|█████████▍| 341/363 [00:27<00:01, 15.47it/s]
Loading 0:  96%|█████████▌| 347/363 [00:27<00:00, 21.32it/s]
Loading 0:  96%|█████████▋| 350/363 [00:27<00:00, 21.93it/s]
Loading 0:  98%|█████████▊| 355/363 [00:27<00:00, 25.45it/s]
Loading 0:  99%|█████████▊| 358/363 [00:28<00:00, 23.29it/s]
                                                            
Job chaiml-icld-v4-dpo-cosine-v1-mkmlizer completed after 154.95s with status: succeeded
Stopping job with name chaiml-icld-v4-dpo-cosine-v1-mkmlizer
Pipeline stage MKMLizer completed in 155.65s
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-icld-v4-dpo-cosine-v1
Waiting for inference service chaiml-icld-v4-dpo-cosine-v1 to be ready
Failed to get response for submission chaiml-icld-v2-dpo-b025_v3: HTTPConnectionPool(host='chaiml-icld-v2-dpo-b025-v3-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-icld-v4-dpo-cosine-v1 ready after 151.20485854148865s
Pipeline stage MKMLDeployer completed in 151.80s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3741042613983154s
Received healthy response to inference request in 2.392961025238037s
Received healthy response to inference request in 2.351259708404541s
Received healthy response to inference request in 2.157916307449341s
Received healthy response to inference request in 2.2795217037200928s
5 requests
0 failed requests
5th percentile: 2.182237386703491
10th percentile: 2.2065584659576416
20th percentile: 2.2552006244659424
30th percentile: 2.2938693046569822
40th percentile: 2.3225645065307616
50th percentile: 2.351259708404541
60th percentile: 2.360397529602051
70th percentile: 2.3695353507995605
80th percentile: 2.3778756141662596
90th percentile: 2.3854183197021483
95th percentile: 2.389189672470093
99th percentile: 2.392206754684448
mean time: 2.3111526012420653
Pipeline stage StressChecker completed in 12.87s
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 0.69s
Shutdown handler de-registered
chaiml-icld-v4-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 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-icld-v4-dpo-cosine-v1-profiler
Waiting for inference service chaiml-icld-v4-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 2809.97s
Shutdown handler de-registered
chaiml-icld-v4-dpo-cosine_v1 status is now inactive due to auto deactivation removed underperforming models