chaiml-gy-exp111-dpo-ex_16835

developer_uid: bogoconic1

submission_id: chaiml-gy-exp111-dpo-ex_16835_v1

model_name: chaiml-gy-exp111-dpo-ex_16835_v1

model_group: ChaiML/gy-exp111-dpo-exp

status: torndown

timestamp: 2025-07-07T17:17:13+00:00

num_battles: 9504

num_wins: 5135

celo_rating: 1318.15

family_friendly_score: 0.45799999999999996

family_friendly_standard_error: 0.0070460769226570324

submission_type: basic

model_repo: ChaiML/gy-exp111-dpo-exp72ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep1

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': 0.5163680838134713, 'latency_mean': 1.93650203704834, 'latency_p50': 1.919917345046997, 'latency_p90': 2.1443895578384398}, {'batch_size': 3, 'throughput': 1.0291637600694605, 'latency_mean': 2.906980423927307, 'latency_p50': 2.90494167804718, 'latency_p90': 3.214022397994995}, {'batch_size': 5, 'throughput': 1.297167193112711, 'latency_mean': 3.8403334367275237, 'latency_p50': 3.8613994121551514, 'latency_p90': 4.316982960700988}, {'batch_size': 6, 'throughput': 1.4036505652480844, 'latency_mean': 4.24342078089714, 'latency_p50': 4.227039456367493, 'latency_p90': 4.7505357503890995}, {'batch_size': 8, 'throughput': 1.5176048324619484, 'latency_mean': 5.2220492482185366, 'latency_p50': 5.227501749992371, 'latency_p90': 5.832494688034058}, {'batch_size': 10, 'throughput': 1.6123531187275555, 'latency_mean': 6.156641305685043, 'latency_p50': 6.1548566818237305, 'latency_p90': 6.950976300239563}]

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

display_name: chaiml-gy-exp111-dpo-ex_16835_v1

is_internal_developer: False

language_model: ChaiML/gy-exp111-dpo-exp72ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep1

model_size: 24B

ranking_group: single

throughput_3p7s: 1.27

us_pacific_date: 2025-07-07

win_ratio: 0.5402988215488216

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': ['<|im_start|>', '<|im_end|>', '\n'], '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-exp111-dpo-ex-16835-v1-mkmlizer
Waiting for job on chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer to finish
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: Downloaded to shared memory in 78.640s
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: Checking if ChaiML/gy-exp111-dpo-exp72ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep1 already exists in ChaiML
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpm49ec61z, device:0
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: quantized model in 49.203s
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: Processed model ChaiML/gy-exp111-dpo-exp72ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep1 in 127.843s
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp111-dpo-ex-16835-v1/nvidia
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp111-dpo-ex-16835-v1/nvidia/tokenizer_config.json
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp111-dpo-ex-16835-v1/nvidia/tokenizer.json
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp111-dpo-ex-16835-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp111-dpo-ex-16835-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 32.66it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:13, 26.52it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 28.55it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:14, 23.85it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 28.84it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:13, 24.72it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:10, 31.85it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 22.18it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:15, 20.69it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.03it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:14, 21.82it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:12, 24.96it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:13, 22.67it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:11, 27.26it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:12, 24.23it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 26.59it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.34it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:14, 19.94it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:11, 24.95it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:12, 22.17it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:12, 23.24it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:12, 21.47it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:11, 24.65it/s]
Loading 0:  26%|██▌       | 94/363 [00:03<00:10, 24.63it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:10, 25.63it/s]
Loading 0:  28%|██▊       | 101/363 [00:04<00:11, 22.65it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.26it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:09, 25.48it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 22.80it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.80it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:09, 24.98it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:07, 30.68it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 28.40it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 30.83it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.26it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 31.99it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:09, 22.63it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 21.29it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 22.38it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 22.82it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.22it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 23.64it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.10it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:07, 24.39it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 26.92it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 22.93it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:08, 21.59it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.58it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.00it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:07, 23.00it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:06,  1.15s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:33,  1.04it/s]
Loading 0:  57%|█████▋    | 208/363 [00:23<01:32,  1.68it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:11,  2.14it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:52,  2.82it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:35,  4.04it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.16it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.15it/s]
Loading 0:  63%|██████▎   | 228/363 [00:24<00:15,  8.65it/s]
Loading 0:  64%|██████▎   | 231/363 [00:24<00:13,  9.94it/s]
Loading 0:  65%|██████▍   | 235/363 [00:24<00:09, 13.26it/s]
Loading 0:  66%|██████▌   | 239/363 [00:24<00:08, 14.58it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 21.66it/s]
Loading 0:  69%|██████▉   | 250/363 [00:24<00:05, 21.98it/s]
Loading 0:  70%|███████   | 255/363 [00:25<00:04, 25.09it/s]
Loading 0:  71%|███████▏  | 259/363 [00:25<00:04, 23.88it/s]
Loading 0:  72%|███████▏  | 263/363 [00:25<00:03, 26.87it/s]
Loading 0:  74%|███████▎  | 267/363 [00:25<00:04, 21.88it/s]
Loading 0:  74%|███████▍  | 270/363 [00:25<00:04, 19.13it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:03, 22.50it/s]
Loading 0:  76%|███████▋  | 277/363 [00:26<00:03, 22.98it/s]
Loading 0:  78%|███████▊  | 282/363 [00:26<00:03, 26.22it/s]
Loading 0:  79%|███████▊  | 285/363 [00:26<00:03, 23.77it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 28.31it/s]
Loading 0:  81%|████████  | 294/363 [00:26<00:02, 25.02it/s]
Loading 0:  82%|████████▏ | 298/363 [00:26<00:02, 28.19it/s]
Loading 0:  83%|████████▎ | 303/363 [00:26<00:01, 30.67it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 21.04it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 22.16it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 22.69it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 26.40it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 23.47it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 28.50it/s]
Loading 0:  91%|█████████ | 331/363 [00:28<00:01, 26.83it/s]
Loading 0:  92%|█████████▏| 335/363 [00:28<00:01, 27.58it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:00, 25.70it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 15.22it/s]
Loading 0:  96%|█████████▌| 347/363 [00:28<00:00, 20.68it/s]
Loading 0:  96%|█████████▋| 350/363 [00:29<00:00, 21.41it/s]
Loading 0:  98%|█████████▊| 355/363 [00:29<00:00, 24.69it/s]
Loading 0:  99%|█████████▊| 358/363 [00:29<00:00, 22.68it/s]
                                                            
Job chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer completed after 157.36s with status: succeeded
Stopping job with name chaiml-gy-exp111-dpo-ex-16835-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.88s
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-gy-exp111-dpo-ex-16835-v1
Waiting for inference service chaiml-gy-exp111-dpo-ex-16835-v1 to be ready
Inference service chaiml-gy-exp111-dpo-ex-16835-v1 ready after 190.70200490951538s
Pipeline stage MKMLDeployer completed in 191.27s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.3664567470550537s
Received healthy response to inference request in 2.132636785507202s
Received healthy response to inference request in 2.3006694316864014s
Received healthy response to inference request in 2.3098697662353516s
Received healthy response to inference request in 2.231401205062866s
5 requests
0 failed requests
5th percentile: 2.152389669418335
10th percentile: 2.1721425533294676
20th percentile: 2.2116483211517335
30th percentile: 2.2452548503875733
40th percentile: 2.272962141036987
50th percentile: 2.3006694316864014
60th percentile: 2.3043495655059814
70th percentile: 2.3080296993255613
80th percentile: 2.521187162399292
90th percentile: 2.943821954727173
95th percentile: 3.155139350891113
99th percentile: 3.3241932678222654
mean time: 2.468206787109375
Pipeline stage StressChecker completed in 13.94s
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 0.89s
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 0.67s
Shutdown handler de-registered
chaiml-gy-exp111-dpo-ex_16835_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 3253.04s
Shutdown handler de-registered
chaiml-gy-exp111-dpo-ex_16835_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp111-dpo-ex_16835_v1 status is now torndown due to DeploymentManager action