chaiml-gy-exp63-dpo-exp_33117

developer_uid: bogoconic1

submission_id: chaiml-gy-exp63-dpo-exp_33117_v2

model_name: chaiml-gy-exp63-dpo-exp_33117_v2

model_group: ChaiML/gy-exp63-dpo-exp3

status: torndown

timestamp: 2025-07-02T22:06:16+00:00

num_battles: 8266

num_wins: 4361

celo_rating: 1306.56

family_friendly_score: 0.503

family_friendly_standard_error: 0.007070940531499328

submission_type: basic

model_repo: ChaiML/gy-exp63-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-ep1

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5260654828763889, 'latency_mean': 1.9008059418201446, 'latency_p50': 1.8997912406921387, 'latency_p90': 2.110244870185852}, {'batch_size': 3, 'throughput': 1.0413305431355386, 'latency_mean': 2.872450981140137, 'latency_p50': 2.897805690765381, 'latency_p90': 3.134694242477417}, {'batch_size': 5, 'throughput': 1.3210259800551944, 'latency_mean': 3.7501874709129335, 'latency_p50': 3.7762694358825684, 'latency_p90': 4.173889994621277}, {'batch_size': 6, 'throughput': 1.4308715860431556, 'latency_mean': 4.177957037687301, 'latency_p50': 4.196407914161682, 'latency_p90': 4.694726991653442}, {'batch_size': 8, 'throughput': 1.5524629236522574, 'latency_mean': 5.100446702241897, 'latency_p50': 5.090936779975891, 'latency_p90': 5.730449771881103}, {'batch_size': 10, 'throughput': 1.6460943012982343, 'latency_mean': 6.011096559762954, 'latency_p50': 6.058378100395203, 'latency_p90': 6.711791944503784}]

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

display_name: chaiml-gy-exp63-dpo-exp_33117_v2

is_internal_developer: True

language_model: ChaiML/gy-exp63-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-ep1

model_size: 24B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2025-07-02

win_ratio: 0.527582869586257

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-exp63-dpo-exp-33117-v2-mkmlizer
Waiting for job on chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer to finish
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║  Version: 0.29.8                                                    ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: Downloaded to shared memory in 69.159s
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: Checking if ChaiML/gy-exp63-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-ep1 already exists in ChaiML
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8inz0waa, device:0
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: quantized model in 48.020s
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: Processed model ChaiML/gy-exp63-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-ep1 in 117.180s
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp63-dpo-exp-33117-v2/nvidia
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp63-dpo-exp-33117-v2/nvidia/config.json
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp63-dpo-exp-33117-v2/nvidia/special_tokens_map.json
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp63-dpo-exp-33117-v2/nvidia/tokenizer_config.json
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp63-dpo-exp-33117-v2/nvidia/tokenizer.json
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp63-dpo-exp-33117-v2/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp63-dpo-exp-33117-v2/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 33.59it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:13, 27.10it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 29.88it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:13, 26.62it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 29.32it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:13, 24.63it/s]
Loading 0:   8%|▊         | 29/363 [00:01<00:11, 30.35it/s]
Loading 0:   9%|▉         | 33/363 [00:01<00:14, 23.38it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:16, 19.57it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.71it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 22.95it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 26.85it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:12, 24.36it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 27.71it/s]
Loading 0:  16%|█▋        | 59/363 [00:02<00:13, 22.71it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.31it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:13, 22.51it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:14, 19.53it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 24.97it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.33it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.45it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.72it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.14it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 29.15it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:09, 27.62it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:10, 23.36it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 25.99it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.29it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 28.81it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 27.53it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:07, 31.43it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 28.60it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 31.59it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 28.79it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 33.03it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:08, 24.43it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 22.54it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 23.50it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.88it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 27.98it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:07, 25.06it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 30.19it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:06, 27.75it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 28.17it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:06, 25.60it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 22.87it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.67it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.07it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 24.07it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:05,  1.14s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:33,  1.05it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:32,  1.68it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:10,  2.15it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:52,  2.83it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:35,  4.05it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.15it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.15it/s]
Loading 0:  63%|██████▎   | 228/363 [00:23<00:15,  8.66it/s]
Loading 0:  64%|██████▎   | 231/363 [00:23<00:13, 10.06it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 15.20it/s]
Loading 0:  66%|██████▋   | 241/363 [00:24<00:07, 16.85it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 21.15it/s]
Loading 0:  69%|██████▉   | 250/363 [00:24<00:05, 21.90it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 25.81it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 25.18it/s]
Loading 0:  73%|███████▎  | 265/363 [00:24<00:03, 31.89it/s]
Loading 0:  74%|███████▍  | 269/363 [00:25<00:04, 22.53it/s]
Loading 0:  75%|███████▌  | 273/363 [00:25<00:04, 22.37it/s]
Loading 0:  76%|███████▌  | 276/363 [00:25<00:04, 21.46it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 26.77it/s]
Loading 0:  79%|███████▉  | 286/363 [00:25<00:02, 25.83it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 28.63it/s]
Loading 0:  81%|████████▏ | 295/363 [00:26<00:02, 27.23it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 27.72it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 24.98it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 22.49it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.36it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 23.54it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 27.71it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 24.70it/s]
Loading 0:  90%|█████████ | 327/363 [00:27<00:01, 30.51it/s]
Loading 0:  91%|█████████ | 331/363 [00:27<00:01, 28.54it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 30.17it/s]
Loading 0:  93%|█████████▎| 339/363 [00:27<00:00, 30.21it/s]
Loading 0:  94%|█████████▍| 343/363 [00:28<00:01, 17.52it/s]
Loading 0:  96%|█████████▌| 348/363 [00:28<00:00, 19.18it/s]
Loading 0:  98%|█████████▊| 355/363 [00:28<00:00, 26.49it/s]
Loading 0:  99%|█████████▉| 359/363 [00:28<00:00, 25.80it/s]
                                                            
Job chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer completed after 146.16s with status: succeeded
Stopping job with name chaiml-gy-exp63-dpo-exp-33117-v2-mkmlizer
Pipeline stage MKMLizer completed in 146.66s
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-exp63-dpo-exp-33117-v2
Waiting for inference service chaiml-gy-exp63-dpo-exp-33117-v2 to be ready
Inference service chaiml-gy-exp63-dpo-exp-33117-v2 ready after 220.94537472724915s
Pipeline stage MKMLDeployer completed in 221.48s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7489819526672363s
Received healthy response to inference request in 2.087883949279785s
Received healthy response to inference request in 2.1407761573791504s
Received healthy response to inference request in 2.193995714187622s
Received healthy response to inference request in 2.0180580615997314s
5 requests
0 failed requests
5th percentile: 2.032023239135742
10th percentile: 2.045988416671753
20th percentile: 2.0739187717437746
30th percentile: 2.098462390899658
40th percentile: 2.119619274139404
50th percentile: 2.1407761573791504
60th percentile: 2.162063980102539
70th percentile: 2.1833518028259276
80th percentile: 2.304992961883545
90th percentile: 2.5269874572753905
95th percentile: 2.637984704971313
99th percentile: 2.7267825031280517
mean time: 2.237939167022705
Pipeline stage StressChecker completed in 12.54s
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 0.70s
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 0.70s
Shutdown handler de-registered
chaiml-gy-exp63-dpo-exp_33117_v2 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 3163.06s
Shutdown handler de-registered
chaiml-gy-exp63-dpo-exp_33117_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp63-dpo-exp_33117_v2 status is now torndown due to DeploymentManager action