chaiml-gy-exp122-dpo-ex_18452

developer_uid: bogoconic1

submission_id: chaiml-gy-exp122-dpo-ex_18452_v1

model_name: chaiml-gy-exp122-dpo-ex_18452_v1

model_group: ChaiML/gy-exp122-dpo-exp

status: torndown

timestamp: 2025-07-08T10:31:54+00:00

num_battles: 7582

num_wins: 4096

celo_rating: 1319.62

family_friendly_score: 0.49160000000000004

family_friendly_standard_error: 0.007070069872356284

submission_type: basic

model_repo: ChaiML/gy-exp122-dpo-exp32ep8s2-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': 0.48543965714694615, 'latency_mean': 2.059738700389862, 'latency_p50': 2.05822491645813, 'latency_p90': 2.2985398530960084}, {'batch_size': 3, 'throughput': 1.0094157257518448, 'latency_mean': 2.9645792305469514, 'latency_p50': 2.980051636695862, 'latency_p90': 3.268887662887573}, {'batch_size': 5, 'throughput': 1.1854703993385634, 'latency_mean': 4.184987142086029, 'latency_p50': 4.188815236091614, 'latency_p90': 4.677776145935058}, {'batch_size': 6, 'throughput': 1.3861826301193882, 'latency_mean': 4.2965969264507295, 'latency_p50': 4.2882304191589355, 'latency_p90': 4.864107012748718}, {'batch_size': 8, 'throughput': 1.494013836924383, 'latency_mean': 5.300136038064957, 'latency_p50': 5.2890976667404175, 'latency_p90': 5.936911296844483}, {'batch_size': 10, 'throughput': 1.4770927270478786, 'latency_mean': 6.698590446710586, 'latency_p50': 6.712616324424744, 'latency_p90': 7.59481418132782}]

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

display_name: chaiml-gy-exp122-dpo-ex_18452_v1

is_internal_developer: False

language_model: ChaiML/gy-exp122-dpo-exp32ep8s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.14

us_pacific_date: 2025-07-08

win_ratio: 0.5402268530730678

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_end|>', '\n', '<|im_start|>'], '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-exp122-dpo-ex-18452-v1-mkmlizer
Waiting for job on chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer to finish
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: Downloaded to shared memory in 75.993s
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: Checking if ChaiML/gy-exp122-dpo-exp32ep8s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2 already exists in ChaiML
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplrrmpwg4, device:0
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: quantized model in 49.285s
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: Processed model ChaiML/gy-exp122-dpo-exp32ep8s2-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2 in 125.278s
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp122-dpo-ex-18452-v1/nvidia
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp122-dpo-ex-18452-v1/nvidia/config.json
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp122-dpo-ex-18452-v1/nvidia/special_tokens_map.json
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp122-dpo-ex-18452-v1/nvidia/tokenizer_config.json
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp122-dpo-ex-18452-v1/nvidia/tokenizer.json
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp122-dpo-ex-18452-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp122-dpo-ex-18452-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 34.94it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 27.93it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.33it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:13, 26.31it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 30.28it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 26.94it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:09, 34.38it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:16, 20.21it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:15, 20.85it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:18, 17.63it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:12, 24.96it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:12, 24.33it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:11, 27.43it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.22it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 26.42it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 22.70it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:14, 19.54it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 24.81it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.26it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.19it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 25.73it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.24it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 27.43it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:10, 25.23it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:12, 19.90it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:11, 22.85it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:12, 20.66it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:09, 25.35it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:10, 22.86it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 27.36it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:09, 23.94it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 27.66it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:09, 24.51it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 31.06it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:09, 22.25it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:10, 20.86it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 21.84it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:09, 22.32it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 25.26it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 22.27it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:06, 27.17it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:07, 24.08it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 26.93it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 23.86it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.16it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.08it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 23.40it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 23.40it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:06,  1.15s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<02:34,  1.04it/s]
Loading 0:  57%|█████▋    | 208/363 [00:23<01:32,  1.67it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:10,  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,  5.17it/s]
Loading 0:  62%|██████▏   | 224/363 [00:24<00:22,  6.18it/s]
Loading 0:  63%|██████▎   | 228/363 [00:24<00:15,  8.70it/s]
Loading 0:  64%|██████▎   | 231/363 [00:24<00:13, 10.07it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 15.09it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:07, 15.70it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 20.89it/s]
Loading 0:  69%|██████▉   | 250/363 [00:24<00:05, 21.72it/s]
Loading 0:  70%|███████   | 255/363 [00:25<00:04, 24.78it/s]
Loading 0:  71%|███████▏  | 259/363 [00:25<00:04, 24.30it/s]
Loading 0:  73%|███████▎  | 265/363 [00:25<00:03, 31.10it/s]
Loading 0:  74%|███████▍  | 269/363 [00:25<00:04, 21.78it/s]
Loading 0:  75%|███████▍  | 272/363 [00:25<00:04, 22.47it/s]
Loading 0:  76%|███████▌  | 275/363 [00:26<00:04, 18.78it/s]
Loading 0:  78%|███████▊  | 282/363 [00:26<00:03, 25.45it/s]
Loading 0:  79%|███████▉  | 286/363 [00:26<00:03, 24.70it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 27.20it/s]
Loading 0:  81%|████████▏ | 295/363 [00:26<00:02, 25.79it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 26.08it/s]
Loading 0:  83%|████████▎ | 303/363 [00:26<00:02, 28.93it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 19.57it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 20.75it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 21.55it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 24.50it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 22.65it/s]
Loading 0:  90%|█████████ | 327/363 [00:28<00:01, 27.79it/s]
Loading 0:  91%|█████████ | 330/363 [00:28<00:01, 24.17it/s]
Loading 0:  92%|█████████▏| 335/363 [00:28<00:01, 26.88it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:01, 24.96it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 15.06it/s]
Loading 0:  96%|█████████▌| 347/363 [00:29<00:00, 20.36it/s]
Loading 0:  96%|█████████▋| 350/363 [00:29<00:00, 21.17it/s]
Loading 0:  98%|█████████▊| 355/363 [00:29<00:00, 25.09it/s]
Loading 0:  99%|█████████▊| 358/363 [00:29<00:00, 23.29it/s]
                                                            
Job chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer completed after 156.48s with status: succeeded
Stopping job with name chaiml-gy-exp122-dpo-ex-18452-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.36s
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-gy-exp122-dpo-ex-18452-v1
Waiting for inference service chaiml-gy-exp122-dpo-ex-18452-v1 to be ready
Inference service chaiml-gy-exp122-dpo-ex-18452-v1 ready after 191.70844888687134s
Pipeline stage MKMLDeployer completed in 192.81s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6841814517974854s
Received healthy response to inference request in 2.5168416500091553s
Received healthy response to inference request in 2.195603132247925s
Received healthy response to inference request in 2.2989537715911865s
Received healthy response to inference request in 2.335451602935791s
5 requests
0 failed requests
5th percentile: 2.2162732601165773
10th percentile: 2.2369433879852294
20th percentile: 2.278283643722534
30th percentile: 2.3062533378601073
40th percentile: 2.3208524703979494
50th percentile: 2.335451602935791
60th percentile: 2.4080076217651367
70th percentile: 2.4805636405944824
80th percentile: 2.5503096103668215
90th percentile: 2.6172455310821534
95th percentile: 2.650713491439819
99th percentile: 2.677487859725952
mean time: 2.4062063217163088
Pipeline stage StressChecker completed in 13.39s
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 0.85s
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 1.30s
Shutdown handler de-registered
chaiml-gy-exp122-dpo-ex_18452_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5662.97s
Shutdown handler de-registered
chaiml-gy-exp122-dpo-ex_18452_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp122-dpo-ex_18452_v1 status is now torndown due to DeploymentManager action