chaiml-gy-exp88-dpo-exp_39253

developer_uid: bogoconic1

submission_id: chaiml-gy-exp88-dpo-exp_39253_v1

model_name: chaiml-gy-exp88-dpo-exp_39253_v1

model_group: ChaiML/gy-exp88-dpo-exp8

status: torndown

timestamp: 2025-07-05T08:36:21+00:00

num_battles: 8281

num_wins: 4393

celo_rating: 1308.54

family_friendly_score: 0.47740000000000005

family_friendly_standard_error: 0.007063840881560117

submission_type: basic

model_repo: ChaiML/gy-exp88-dpo-exp86ep8s2-exp72data-ep2

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.525314649341584, 'latency_mean': 1.9034966146945953, 'latency_p50': 1.8901900053024292, 'latency_p90': 2.112890601158142}, {'batch_size': 3, 'throughput': 1.0551886005243645, 'latency_mean': 2.833886501789093, 'latency_p50': 2.8323557376861572, 'latency_p90': 3.144317603111267}, {'batch_size': 5, 'throughput': 1.3523494796854607, 'latency_mean': 3.670794714689255, 'latency_p50': 3.6915005445480347, 'latency_p90': 4.101327681541443}, {'batch_size': 6, 'throughput': 1.4497133064451169, 'latency_mean': 4.108171640634537, 'latency_p50': 4.089532494544983, 'latency_p90': 4.539438676834107}, {'batch_size': 8, 'throughput': 1.5822316569139723, 'latency_mean': 5.022010912895203, 'latency_p50': 5.045639157295227, 'latency_p90': 5.614240765571594}, {'batch_size': 10, 'throughput': 1.671137765070543, 'latency_mean': 5.9118556702137, 'latency_p50': 5.861211538314819, 'latency_p90': 6.732330965995788}]

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

display_name: chaiml-gy-exp88-dpo-exp_39253_v1

is_internal_developer: True

language_model: ChaiML/gy-exp88-dpo-exp86ep8s2-exp72data-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.37

us_pacific_date: 2025-07-05

win_ratio: 0.5304914865354425

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-exp88-dpo-exp-39253-v1-mkmlizer
Waiting for job on chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer to finish
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: Downloaded to shared memory in 76.923s
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: Checking if ChaiML/gy-exp88-dpo-exp86ep8s2-exp72data-ep2 already exists in ChaiML
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3ihfcnq8, device:0
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: quantized model in 49.527s
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: Processed model ChaiML/gy-exp88-dpo-exp86ep8s2-exp72data-ep2 in 126.451s
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp88-dpo-exp-39253-v1/nvidia
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp88-dpo-exp-39253-v1/nvidia/config.json
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp88-dpo-exp-39253-v1/nvidia/special_tokens_map.json
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp88-dpo-exp-39253-v1/nvidia/tokenizer_config.json
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp88-dpo-exp-39253-v1/nvidia/tokenizer.json
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp88-dpo-exp-39253-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp88-dpo-exp-39253-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 37.67it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 29.30it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 31.20it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 27.15it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 30.83it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 27.71it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:09, 33.75it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:16, 20.04it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.57it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 22.88it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:12, 26.14it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:13, 23.03it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:10, 28.18it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.60it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.47it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.75it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 19.87it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 25.14it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.46it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 24.70it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:11, 24.59it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 19.41it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:10, 26.26it/s]
Loading 0:  28%|██▊       | 102/363 [00:04<00:10, 24.12it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.03it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 24.83it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:10, 22.73it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.73it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 24.52it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 28.73it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 26.80it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 27.24it/s]
Loading 0:  38%|███▊      | 139/363 [00:05<00:08, 26.76it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:08, 25.74it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 31.09it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:09, 21.70it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:10, 20.02it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 21.28it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:09, 21.75it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 25.11it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 22.55it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:07, 26.17it/s]
Loading 0:  48%|████▊     | 175/363 [00:07<00:07, 26.40it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:07, 26.22it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:06, 27.02it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 23.99it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 21.90it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.00it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:07, 23.30it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:06, 23.30it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:13,  1.19s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<02:38,  1.01it/s]
Loading 0:  57%|█████▋    | 208/363 [00:23<01:34,  1.64it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:12,  2.10it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:53,  2.76it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:36,  3.95it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:28,  5.00it/s]
Loading 0:  62%|██████▏   | 224/363 [00:24<00:23,  5.86it/s]
Loading 0:  63%|██████▎   | 228/363 [00:24<00:16,  8.26it/s]
Loading 0:  64%|██████▎   | 231/363 [00:24<00:13,  9.58it/s]
Loading 0:  65%|██████▌   | 237/363 [00:24<00:08, 14.19it/s]
Loading 0:  66%|██████▌   | 240/363 [00:24<00:08, 14.80it/s]
Loading 0:  67%|██████▋   | 244/363 [00:24<00:06, 18.22it/s]
Loading 0:  68%|██████▊   | 247/363 [00:24<00:05, 19.58it/s]
Loading 0:  69%|██████▉   | 250/363 [00:25<00:05, 20.17it/s]
Loading 0:  70%|███████   | 255/363 [00:25<00:04, 23.64it/s]
Loading 0:  71%|███████   | 258/363 [00:25<00:04, 21.77it/s]
Loading 0:  73%|███████▎  | 264/363 [00:25<00:03, 29.09it/s]
Loading 0:  74%|███████▍  | 268/363 [00:25<00:04, 21.20it/s]
Loading 0:  75%|███████▍  | 271/363 [00:26<00:04, 19.06it/s]
Loading 0:  75%|███████▌  | 274/363 [00:26<00:04, 20.19it/s]
Loading 0:  76%|███████▋  | 277/363 [00:26<00:04, 21.06it/s]
Loading 0:  78%|███████▊  | 282/363 [00:26<00:03, 24.68it/s]
Loading 0:  79%|███████▊  | 285/363 [00:26<00:03, 21.97it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 27.03it/s]
Loading 0:  81%|████████  | 294/363 [00:26<00:02, 24.38it/s]
Loading 0:  82%|████████▏ | 299/363 [00:27<00:02, 26.58it/s]
Loading 0:  84%|████████▎ | 304/363 [00:27<00:02, 24.02it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 22.16it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 22.99it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 23.23it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 26.57it/s]
Loading 0:  88%|████████▊ | 321/363 [00:28<00:01, 23.34it/s]
Loading 0:  90%|█████████ | 327/363 [00:28<00:01, 28.59it/s]
Loading 0:  91%|█████████ | 330/363 [00:28<00:01, 25.39it/s]
Loading 0:  92%|█████████▏| 335/363 [00:28<00:00, 28.05it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:00, 26.58it/s]
Loading 0:  94%|█████████▍| 341/363 [00:29<00:01, 15.73it/s]
Loading 0:  96%|█████████▌| 347/363 [00:29<00:00, 21.23it/s]
Loading 0:  96%|█████████▋| 350/363 [00:29<00:00, 21.45it/s]
Loading 0:  98%|█████████▊| 355/363 [00:29<00:00, 24.72it/s]
Loading 0:  99%|█████████▊| 358/363 [00:29<00:00, 22.51it/s]
                                                            
Job chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer completed after 155.8s with status: succeeded
Stopping job with name chaiml-gy-exp88-dpo-exp-39253-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.62s
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-exp88-dpo-exp-39253-v1
Waiting for inference service chaiml-gy-exp88-dpo-exp-39253-v1 to be ready
Inference service chaiml-gy-exp88-dpo-exp-39253-v1 ready after 221.22263073921204s
Pipeline stage MKMLDeployer completed in 221.82s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4594240188598633s
Received healthy response to inference request in 1.8348674774169922s
Received healthy response to inference request in 1.8977129459381104s
Received healthy response to inference request in 2.109178066253662s
Received healthy response to inference request in 2.032555103302002s
5 requests
0 failed requests
5th percentile: 1.8474365711212157
10th percentile: 1.8600056648254395
20th percentile: 1.8851438522338868
30th percentile: 1.9246813774108886
40th percentile: 1.9786182403564454
50th percentile: 2.032555103302002
60th percentile: 2.063204288482666
70th percentile: 2.09385347366333
80th percentile: 2.1792272567749023
90th percentile: 2.319325637817383
95th percentile: 2.389374828338623
99th percentile: 2.4454141807556153
mean time: 2.066747522354126
Pipeline stage StressChecker completed in 11.63s
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 0.64s
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 0.63s
Shutdown handler de-registered
chaiml-gy-exp88-dpo-exp_39253_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp88-dpo-exp-39253-v1-profiler
Waiting for inference service chaiml-gy-exp88-dpo-exp-39253-v1-profiler to be ready
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 3161.80s
Shutdown handler de-registered
chaiml-gy-exp88-dpo-exp_39253_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp88-dpo-exp_39253_v1 status is now torndown due to DeploymentManager action