chaiml-gy-exp110-dpo-ex_25191

developer_uid: bogoconic1

submission_id: chaiml-gy-exp110-dpo-ex_25191_v1

model_name: chaiml-gy-exp110-dpo-ex_25191_v1

model_group: ChaiML/gy-exp110-dpo-exp

status: torndown

timestamp: 2025-07-07T15:53:06+00:00

num_battles: 8840

num_wins: 4742

celo_rating: 1316.94

family_friendly_score: 0.476

family_friendly_standard_error: 0.0070629172443120135

submission_type: basic

model_repo: ChaiML/gy-exp110-dpo-exp93ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5145500111157565, 'latency_mean': 1.9432585799694062, 'latency_p50': 1.9438685178756714, 'latency_p90': 2.153661584854126}, {'batch_size': 3, 'throughput': 1.045028659359804, 'latency_mean': 2.8655321729183196, 'latency_p50': 2.851451277732849, 'latency_p90': 3.16912636756897}, {'batch_size': 5, 'throughput': 1.3178020990959087, 'latency_mean': 3.7748059642314913, 'latency_p50': 3.7314889430999756, 'latency_p90': 4.1981371402740475}, {'batch_size': 6, 'throughput': 1.427107951787533, 'latency_mean': 4.186398969888687, 'latency_p50': 4.159856915473938, 'latency_p90': 4.722250938415527}, {'batch_size': 8, 'throughput': 1.5443409464283961, 'latency_mean': 5.140819110870361, 'latency_p50': 5.170194983482361, 'latency_p90': 5.749981021881103}, {'batch_size': 10, 'throughput': 1.6233426849259691, 'latency_mean': 6.105767203569412, 'latency_p50': 6.083551287651062, 'latency_p90': 6.893013620376587}]

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

display_name: chaiml-gy-exp110-dpo-ex_25191_v1

is_internal_developer: False

language_model: ChaiML/gy-exp110-dpo-exp93ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.31

us_pacific_date: 2025-07-07

win_ratio: 0.5364253393665158

generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_start|>', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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-gy-exp110-dpo-ex-25191-v1-mkmlizer
Waiting for job on chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer to finish
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: Downloaded to shared memory in 88.386s
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: Checking if ChaiML/gy-exp110-dpo-exp93ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2 already exists in ChaiML
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbcziph69, device:0
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: quantized model in 49.136s
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: Processed model ChaiML/gy-exp110-dpo-exp93ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2 in 137.523s
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp110-dpo-ex-25191-v1/nvidia/config.json
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp110-dpo-ex-25191-v1/nvidia/special_tokens_map.json
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp110-dpo-ex-25191-v1/nvidia/tokenizer_config.json
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp110-dpo-ex-25191-v1/nvidia/tokenizer.json
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp110-dpo-ex-25191-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 34.49it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 28.07it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.54it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:13, 25.91it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 29.52it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 26.01it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:10, 31.00it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:16, 19.68it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:17, 18.82it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:16, 20.11it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:15, 20.44it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:13, 23.93it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:14, 21.06it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:11, 26.10it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:13, 23.00it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 25.64it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:13, 22.20it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:15, 19.27it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 24.35it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 23.76it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 25.14it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:11, 24.85it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 19.87it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:10, 25.57it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:10, 25.88it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:10, 24.48it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:12, 20.33it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:10, 23.80it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:10, 23.81it/s]
Loading 0:  33%|███▎      | 120/363 [00:05<00:09, 27.00it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:09, 24.53it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:07, 29.57it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 27.64it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.23it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.37it/s]
Loading 0:  41%|████      | 148/363 [00:05<00:06, 35.04it/s]
Loading 0:  42%|████▏     | 152/363 [00:06<00:09, 23.40it/s]
Loading 0:  43%|████▎     | 156/363 [00:06<00:09, 22.75it/s]
Loading 0:  44%|████▍     | 159/363 [00:06<00:09, 21.39it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.18it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.56it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:06, 28.16it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:06, 26.80it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 27.09it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 22.00it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:08, 20.51it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 21.61it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 22.22it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:07, 22.22it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:04,  1.14s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:32,  1.05it/s]
Loading 0:  57%|█████▋    | 208/363 [00:23<01:32,  1.68it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:10,  2.14it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:52,  2.81it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:36,  4.01it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.09it/s]
Loading 0:  62%|██████▏   | 224/363 [00:24<00:23,  5.92it/s]
Loading 0:  63%|██████▎   | 228/363 [00:24<00:16,  8.33it/s]
Loading 0:  64%|██████▎   | 231/363 [00:24<00:13,  9.66it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 14.28it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:08, 15.01it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 20.16it/s]
Loading 0:  69%|██████▊   | 249/363 [00:25<00:05, 19.50it/s]
Loading 0:  70%|███████   | 255/363 [00:25<00:04, 24.76it/s]
Loading 0:  71%|███████▏  | 259/363 [00:25<00:04, 24.64it/s]
Loading 0:  73%|███████▎  | 265/363 [00:25<00:03, 31.19it/s]
Loading 0:  74%|███████▍  | 269/363 [00:25<00:04, 21.88it/s]
Loading 0:  75%|███████▍  | 272/363 [00:25<00:04, 22.49it/s]
Loading 0:  76%|███████▌  | 275/363 [00:26<00:04, 19.15it/s]
Loading 0:  78%|███████▊  | 282/363 [00:26<00:03, 26.01it/s]
Loading 0:  79%|███████▉  | 286/363 [00:26<00:03, 25.26it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 28.02it/s]
Loading 0:  81%|████████▏ | 295/363 [00:26<00:02, 26.67it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 27.08it/s]
Loading 0:  84%|████████▎ | 304/363 [00:27<00:02, 24.06it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 22.17it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 23.16it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 23.80it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 27.01it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 24.26it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 29.81it/s]
Loading 0:  91%|█████████ | 331/363 [00:28<00:01, 28.25it/s]
Loading 0:  92%|█████████▏| 335/363 [00:28<00:00, 28.65it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:00, 27.48it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 16.24it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 21.79it/s]
Loading 0:  96%|█████████▋| 350/363 [00:29<00:00, 22.21it/s]
Loading 0:  98%|█████████▊| 355/363 [00:29<00:00, 25.60it/s]
Loading 0:  99%|█████████▊| 358/363 [00:29<00:00, 23.49it/s]
                                                            
Job chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer completed after 167.36s with status: succeeded
Stopping job with name chaiml-gy-exp110-dpo-ex-25191-v1-mkmlizer
Pipeline stage MKMLizer completed in 167.87s
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-gy-exp110-dpo-ex-25191-v1
Waiting for inference service chaiml-gy-exp110-dpo-ex-25191-v1 to be ready
Inference service chaiml-gy-exp110-dpo-ex-25191-v1 ready after 201.08677434921265s
Pipeline stage MKMLDeployer completed in 201.52s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.635998487472534s
Received healthy response to inference request in 2.158273696899414s
Received healthy response to inference request in 2.223388910293579s
Received healthy response to inference request in 1.910973310470581s
5 requests
1 failed requests
5th percentile: 1.9604333877563476
10th percentile: 2.009893465042114
20th percentile: 2.1088136196136475
30th percentile: 2.171296739578247
40th percentile: 2.1973428249359133
50th percentile: 2.223388910293579
60th percentile: 2.388432741165161
70th percentile: 2.553476572036743
80th percentile: 6.14048652648926
90th percentile: 13.149462604522707
95th percentile: 16.653950643539424
99th percentile: 19.457541074752807
mean time: 5.817414617538452
%s, retrying in %s seconds...
Received healthy response to inference request in 1.9537551403045654s
Received healthy response to inference request in 2.3026952743530273s
Received healthy response to inference request in 2.098423957824707s
Received healthy response to inference request in 2.3102264404296875s
Received healthy response to inference request in 2.3532063961029053s
5 requests
0 failed requests
5th percentile: 1.9826889038085938
10th percentile: 2.011622667312622
20th percentile: 2.0694901943206787
30th percentile: 2.139278221130371
40th percentile: 2.220986747741699
50th percentile: 2.3026952743530273
60th percentile: 2.3057077407836912
70th percentile: 2.3087202072143556
80th percentile: 2.318822431564331
90th percentile: 2.336014413833618
95th percentile: 2.344610404968262
99th percentile: 2.3514871978759766
mean time: 2.2036614418029785
Pipeline stage StressChecker completed in 42.63s
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 0.68s
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 0.74s
Shutdown handler de-registered
chaiml-gy-exp110-dpo-ex_25191_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 3729.04s
Shutdown handler de-registered
chaiml-gy-exp110-dpo-ex_25191_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp110-dpo-ex_25191_v1 status is now torndown due to DeploymentManager action