chaiml-icld-v3-dpo-cosine

developer_uid: chai_backend_admin

submission_id: chaiml-icld-v3-dpo-cosine_v1

model_name: training123

model_group: ChaiML/icld-v3-dpo_cosin

status: inactive

timestamp: 2025-11-24T01:43:37+00:00

num_battles: 6438

num_wins: 3259

celo_rating: 1304.64

family_friendly_score: 0.0

family_friendly_standard_error: 0.0

submission_type: basic

model_repo: ChaiML/icld-v3-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': 0.44995529547731117, 'latency_mean': 2.222340468168259, 'latency_p50': 2.2366862297058105, 'latency_p90': 2.448746132850647}, {'batch_size': 2, 'throughput': 0.6660974561267241, 'latency_mean': 2.9915626454353332, 'latency_p50': 2.995200276374817, 'latency_p90': 3.2602413177490233}, {'batch_size': 3, 'throughput': 0.8222913956688085, 'latency_mean': 3.6426565396785735, 'latency_p50': 3.6416351795196533, 'latency_p90': 3.936667037010193}, {'batch_size': 4, 'throughput': 0.9301990760406126, 'latency_mean': 4.28884881734848, 'latency_p50': 4.277732014656067, 'latency_p90': 4.850818920135498}, {'batch_size': 5, 'throughput': 0.9962206829809629, 'latency_mean': 5.009940637350082, 'latency_p50': 5.03518283367157, 'latency_p90': 5.613891124725342}]

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

display_name: training123

is_internal_developer: True

language_model: ChaiML/icld-v3-dpo_cosine

model_size: 24B

ranking_group: single

throughput_3p7s: 0.83

us_pacific_date: 2025-11-23

win_ratio: 0.5062131096613856

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': ['User:', 'You:', '</s>', '\n'], '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-cosine-v1-mkmlizer
Waiting for job on chaiml-icld-v3-dpo-cosine-v1-mkmlizer to finish
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ║                                                                     ║
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: Downloaded to shared memory in 94.917s
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: Checking if ChaiML/icld-v3-dpo_cosine already exists in ChaiML
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp5yssfkk5, device:0
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: quantized model in 47.838s
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: Processed model ChaiML/icld-v3-dpo_cosine in 142.755s
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-icld-v3-dpo-cosine-v1/nvidia
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-icld-v3-dpo-cosine-v1/nvidia/config.json
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-icld-v3-dpo-cosine-v1/nvidia/special_tokens_map.json
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-icld-v3-dpo-cosine-v1/nvidia/tokenizer_config.json
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-icld-v3-dpo-cosine-v1/nvidia/tokenizer.json
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-icld-v3-dpo-cosine-v1/nvidia/flywheel_model.1.safetensors
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-icld-v3-dpo-cosine-v1/nvidia/flywheel_model.0.safetensors
chaiml-icld-v3-dpo-cosine-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 37.83it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:11, 30.31it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:10, 33.42it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:11, 30.25it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:09, 35.04it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:10, 31.74it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:08, 38.85it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:14, 21.92it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 24.57it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.82it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 28.18it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:11, 27.19it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:10, 30.21it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:10, 28.29it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 29.30it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:11, 25.75it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:13, 21.59it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:10, 26.69it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:10, 26.27it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:09, 28.03it/s]
Loading 0:  25%|██▍       | 90/363 [00:03<00:11, 23.23it/s]
Loading 0:  26%|██▌       | 93/363 [00:03<00:12, 22.29it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 27.41it/s]
Loading 0:  28%|██▊       | 102/363 [00:03<00:10, 25.24it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.91it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 26.00it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 23.51it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.79it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:14, 17.05it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:11, 20.31it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:18, 12.78it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:15, 14.24it/s]
Loading 0:  38%|███▊      | 139/363 [00:05<00:13, 16.16it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:12, 17.98it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:08, 25.09it/s]
Loading 0:  42%|████▏     | 153/363 [00:06<00:11, 17.85it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 20.80it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:09, 22.15it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 25.78it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:07, 25.81it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:06, 28.98it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:06, 27.75it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:07, 25.94it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:06, 29.41it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:08, 20.79it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:07, 22.03it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 23.30it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 23.30it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<02:58,  1.10s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:27,  1.08it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:28,  1.74it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:08,  2.21it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:51,  2.92it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:34,  4.18it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:26,  5.35it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:21,  6.38it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.38it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 11.04it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 15.03it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:07, 15.93it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 21.56it/s]
Loading 0:  69%|██████▉   | 250/363 [00:24<00:05, 22.60it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 26.00it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:03, 26.01it/s]
Loading 0:  73%|███████▎  | 266/363 [00:24<00:03, 32.07it/s]
Loading 0:  74%|███████▍  | 270/363 [00:25<00:04, 20.98it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:03, 23.57it/s]
Loading 0:  77%|███████▋  | 278/363 [00:25<00:03, 25.22it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:02, 27.23it/s]
Loading 0:  79%|███████▉  | 286/363 [00:25<00:02, 26.65it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 29.69it/s]
Loading 0:  81%|████████▏ | 295/363 [00:26<00:02, 28.61it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 29.18it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 26.16it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 20.00it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 21.41it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 22.72it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 26.53it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 24.63it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 29.92it/s]
Loading 0:  91%|█████████ | 331/363 [00:27<00:01, 28.70it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 29.23it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 28.04it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 16.44it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 21.92it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 22.53it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 26.27it/s]
Loading 0:  99%|█████████▉| 359/363 [00:28<00:00, 26.24it/s]
                                                            
Job chaiml-icld-v3-dpo-cosine-v1-mkmlizer completed after 217.24s with status: succeeded
Stopping job with name chaiml-icld-v3-dpo-cosine-v1-mkmlizer
Pipeline stage MKMLizer completed in 218.20s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-icld-v3-dpo-cosine-v1
Waiting for inference service chaiml-icld-v3-dpo-cosine-v1 to be ready
Inference service chaiml-icld-v3-dpo-cosine-v1 ready after 150.72242856025696s
Pipeline stage MKMLDeployer completed in 151.47s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.285562753677368s
Received healthy response to inference request in 1.7985055446624756s
Received healthy response to inference request in 2.090120553970337s
Received healthy response to inference request in 2.3411881923675537s
Received healthy response to inference request in 1.884566068649292s
5 requests
0 failed requests
5th percentile: 1.8157176494598388
10th percentile: 1.832929754257202
20th percentile: 1.8673539638519288
30th percentile: 1.9256769657135009
40th percentile: 2.007898759841919
50th percentile: 2.090120553970337
60th percentile: 2.1682974338531493
70th percentile: 2.2464743137359617
80th percentile: 2.2966878414154053
90th percentile: 2.3189380168914795
95th percentile: 2.3300631046295166
99th percentile: 2.338963174819946
mean time: 2.079988622665405
Pipeline stage StressChecker completed in 11.89s
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 0.98s
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 0.66s
Shutdown handler de-registered
chaiml-icld-v3-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
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 5109.25s
Shutdown handler de-registered