chaiml-gy-exp140-dpo-ex_65459

developer_uid: bogoconic1

submission_id: chaiml-gy-exp140-dpo-ex_65459_v2

model_name: chaiml-gy-exp140-dpo-ex_65459_v2

model_group: ChaiML/gy-exp140-dpo-exp

status: torndown

timestamp: 2025-07-11T09:56:18+00:00

num_battles: 10017

num_wins: 5321

celo_rating: 1313.6

family_friendly_score: 0.5034000000000001

family_friendly_standard_error: 0.007070904326887757

submission_type: basic

model_repo: ChaiML/gy-exp140-dpo-exp54ep6s2-gy-datamix-v3-bo8-dpo-gt0.7-diffgt0.01-lpdifftop9k-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': 0.5171727250427763, 'latency_mean': 1.9334893119335175, 'latency_p50': 1.9573746919631958, 'latency_p90': 2.125835585594177}, {'batch_size': 3, 'throughput': 1.0584310501852359, 'latency_mean': 2.8252797722816467, 'latency_p50': 2.8184356689453125, 'latency_p90': 3.1168850898742675}, {'batch_size': 5, 'throughput': 1.343012911228649, 'latency_mean': 3.7005430352687836, 'latency_p50': 3.7171294689178467, 'latency_p90': 4.07606360912323}, {'batch_size': 6, 'throughput': 1.4498049441623244, 'latency_mean': 4.102972540855408, 'latency_p50': 4.075257658958435, 'latency_p90': 4.59350368976593}, {'batch_size': 8, 'throughput': 1.5809858772086949, 'latency_mean': 5.012829377651214, 'latency_p50': 5.01519238948822, 'latency_p90': 5.644212985038758}, {'batch_size': 10, 'throughput': 1.679890610920978, 'latency_mean': 5.88747838139534, 'latency_p50': 5.875955939292908, 'latency_p90': 6.664313220977784}]

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

display_name: chaiml-gy-exp140-dpo-ex_65459_v2

is_internal_developer: False

language_model: ChaiML/gy-exp140-dpo-exp54ep6s2-gy-datamix-v3-bo8-dpo-gt0.7-diffgt0.01-lpdifftop9k-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.35

us_pacific_date: 2025-07-11

win_ratio: 0.5311969651592293

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|>', '<|im_start|>', '\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-exp140-dpo-ex-65459-v2-mkmlizer
Waiting for job on chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer to finish
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: Downloaded to shared memory in 73.020s
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: Checking if ChaiML/gy-exp140-dpo-exp54ep6s2-gy-datamix-v3-bo8-dpo-gt0.7-diffgt0.01-lpdifftop9k-ep2 already exists in ChaiML
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0bex_d_1, device:0
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: quantized model in 59.999s
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: Processed model ChaiML/gy-exp140-dpo-exp54ep6s2-gy-datamix-v3-bo8-dpo-gt0.7-diffgt0.01-lpdifftop9k-ep2 in 133.019s
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp140-dpo-ex-65459-v2/nvidia
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp140-dpo-ex-65459-v2/nvidia/config.json
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp140-dpo-ex-65459-v2/nvidia/special_tokens_map.json
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp140-dpo-ex-65459-v2/nvidia/tokenizer_config.json
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp140-dpo-ex-65459-v2/nvidia/tokenizer.json
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp140-dpo-ex-65459-v2/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp140-dpo-ex-65459-v2/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 33.66it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:13, 26.35it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 27.48it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:15, 21.79it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:12, 28.26it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:14, 23.26it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:10, 30.94it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:16, 20.55it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:17, 18.90it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:16, 19.74it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:15, 20.36it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:14, 22.00it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:13, 22.63it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:14, 21.95it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:12, 24.91it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:14, 20.80it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:12, 24.44it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 26.53it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:16, 17.27it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:15, 18.04it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:14, 20.12it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:15, 17.94it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:12, 21.36it/s]
Loading 0:  25%|██▍       | 89/363 [00:04<00:12, 21.82it/s]
Loading 0:  25%|██▌       | 92/363 [00:04<00:16, 16.70it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:12, 21.96it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:11, 22.45it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:11, 22.21it/s]
Loading 0:  29%|██▉       | 107/363 [00:05<00:14, 17.68it/s]
Loading 0:  31%|███       | 111/363 [00:05<00:12, 20.93it/s]
Loading 0:  31%|███▏      | 114/363 [00:05<00:12, 19.26it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:10, 22.99it/s]
Loading 0:  33%|███▎      | 121/363 [00:05<00:10, 22.27it/s]
Loading 0:  34%|███▍      | 124/363 [00:05<00:10, 21.79it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:10, 23.56it/s]
Loading 0:  36%|███▌      | 130/363 [00:05<00:09, 23.67it/s]
Loading 0:  37%|███▋      | 133/363 [00:06<00:09, 23.11it/s]
Loading 0:  37%|███▋      | 136/363 [00:06<00:09, 24.25it/s]
Loading 0:  38%|███▊      | 139/363 [00:06<00:09, 24.50it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:09, 23.10it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:09, 23.99it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:07, 27.88it/s]
Loading 0:  42%|████▏     | 152/363 [00:07<00:12, 16.99it/s]
Loading 0:  43%|████▎     | 155/363 [00:07<00:11, 18.01it/s]
Loading 0:  44%|████▎     | 158/363 [00:07<00:13, 15.40it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:09, 20.80it/s]
Loading 0:  46%|████▌     | 166/363 [00:07<00:09, 21.28it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:09, 21.53it/s]
Loading 0:  48%|████▊     | 174/363 [00:08<00:07, 24.07it/s]
Loading 0:  49%|████▉     | 177/363 [00:08<00:08, 21.20it/s]
Loading 0:  50%|████▉     | 181/363 [00:08<00:07, 24.89it/s]
Loading 0:  51%|█████     | 186/363 [00:08<00:06, 26.63it/s]
Loading 0:  52%|█████▏    | 189/363 [00:08<00:10, 16.50it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 19.24it/s]
Loading 0:  54%|█████▍    | 196/363 [00:09<00:08, 19.33it/s]
Loading 0:  55%|█████▍    | 199/363 [00:09<00:07, 20.82it/s]
Loading 0:  55%|█████▌    | 200/363 [00:20<00:07, 20.82it/s]
Loading 0:  55%|█████▌    | 201/363 [00:27<04:59,  1.85s/it]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:54,  1.47s/it]
Loading 0:  57%|█████▋    | 208/363 [00:27<02:08,  1.21it/s]
Loading 0:  58%|█████▊    | 211/363 [00:27<01:34,  1.61it/s]
Loading 0:  59%|█████▉    | 214/363 [00:28<01:08,  2.18it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:49,  2.96it/s]
Loading 0:  61%|██████    | 220/363 [00:28<00:37,  3.84it/s]
Loading 0:  61%|██████▏   | 223/363 [00:28<00:27,  5.14it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:22,  6.03it/s]
Loading 0:  63%|██████▎   | 229/363 [00:28<00:17,  7.70it/s]
Loading 0:  64%|██████▎   | 231/363 [00:29<00:15,  8.43it/s]
Loading 0:  65%|██████▍   | 235/363 [00:29<00:10, 11.66it/s]
Loading 0:  66%|██████▌   | 238/363 [00:29<00:09, 13.47it/s]
Loading 0:  66%|██████▋   | 241/363 [00:29<00:08, 14.68it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:06, 17.00it/s]
Loading 0:  68%|██████▊   | 247/363 [00:29<00:06, 18.06it/s]
Loading 0:  69%|██████▉   | 250/363 [00:29<00:06, 18.59it/s]
Loading 0:  70%|██████▉   | 253/363 [00:30<00:05, 20.49it/s]
Loading 0:  71%|███████   | 256/363 [00:30<00:05, 20.78it/s]
Loading 0:  71%|███████▏  | 259/363 [00:30<00:05, 20.18it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:04, 22.10it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:03, 25.68it/s]
Loading 0:  74%|███████▍  | 269/363 [00:30<00:05, 16.08it/s]
Loading 0:  75%|███████▍  | 272/363 [00:31<00:05, 16.85it/s]
Loading 0:  76%|███████▌  | 275/363 [00:31<00:06, 14.19it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 19.43it/s]
Loading 0:  78%|███████▊  | 283/363 [00:31<00:04, 19.83it/s]
Loading 0:  79%|███████▉  | 286/363 [00:31<00:03, 19.92it/s]
Loading 0:  80%|███████▉  | 289/363 [00:31<00:03, 21.50it/s]
Loading 0:  80%|████████  | 292/363 [00:32<00:03, 21.53it/s]
Loading 0:  81%|████████▏ | 295/363 [00:32<00:03, 20.78it/s]
Loading 0:  82%|████████▏ | 298/363 [00:32<00:02, 22.68it/s]
Loading 0:  83%|████████▎ | 303/363 [00:32<00:02, 24.39it/s]
Loading 0:  84%|████████▍ | 306/363 [00:32<00:03, 14.39it/s]
Loading 0:  85%|████████▌ | 310/363 [00:33<00:03, 17.01it/s]
Loading 0:  86%|████████▌ | 313/363 [00:33<00:02, 17.08it/s]
Loading 0:  87%|████████▋ | 316/363 [00:33<00:02, 18.88it/s]
Loading 0:  88%|████████▊ | 319/363 [00:33<00:02, 19.58it/s]
Loading 0:  89%|████████▊ | 322/363 [00:33<00:02, 19.27it/s]
Loading 0:  90%|████████▉ | 325/363 [00:33<00:01, 21.19it/s]
Loading 0:  90%|█████████ | 328/363 [00:33<00:01, 21.13it/s]
Loading 0:  91%|█████████ | 331/363 [00:34<00:01, 20.36it/s]
Loading 0:  92%|█████████▏| 334/363 [00:34<00:01, 22.05it/s]
Loading 0:  93%|█████████▎| 337/363 [00:34<00:01, 18.43it/s]
Loading 0:  94%|█████████▎| 340/363 [00:34<00:01, 20.55it/s]
Loading 0:  94%|█████████▍| 343/363 [00:35<00:01, 11.13it/s]
Loading 0:  96%|█████████▌| 347/363 [00:35<00:01, 14.43it/s]
Loading 0:  96%|█████████▋| 350/363 [00:35<00:00, 15.58it/s]
Loading 0:  97%|█████████▋| 353/363 [00:35<00:00, 17.54it/s]
Loading 0:  98%|█████████▊| 356/363 [00:35<00:00, 18.82it/s]
Loading 0:  99%|█████████▉| 359/363 [00:35<00:00, 19.00it/s]
Loading 0: 100%|█████████▉| 362/363 [00:35<00:00, 21.07it/s]
                                                            
Job chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer completed after 166.64s with status: succeeded
Stopping job with name chaiml-gy-exp140-dpo-ex-65459-v2-mkmlizer
Pipeline stage MKMLizer completed in 167.16s
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-exp140-dpo-ex-65459-v2
Waiting for inference service chaiml-gy-exp140-dpo-ex-65459-v2 to be ready
Inference service chaiml-gy-exp140-dpo-ex-65459-v2 ready after 201.2726604938507s
Pipeline stage MKMLDeployer completed in 202.06s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2247872352600098s
Received healthy response to inference request in 2.1024081707000732s
Received healthy response to inference request in 2.465397834777832s
Received healthy response to inference request in 2.17258358001709s
Received healthy response to inference request in 2.062969446182251s
5 requests
0 failed requests
5th percentile: 2.0708571910858153
10th percentile: 2.0787449359893797
20th percentile: 2.094520425796509
30th percentile: 2.1164432525634767
40th percentile: 2.144513416290283
50th percentile: 2.17258358001709
60th percentile: 2.289709281921387
70th percentile: 2.4068349838256835
80th percentile: 2.6172757148742676
90th percentile: 2.9210314750671387
95th percentile: 3.072909355163574
99th percentile: 3.1944116592407226
mean time: 2.4056292533874513
Pipeline stage StressChecker completed in 13.76s
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 0.76s
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 0.87s
Shutdown handler de-registered
chaiml-gy-exp140-dpo-ex_65459_v2 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 0.12s
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-exp140-dpo-ex-65459-v2-profiler
Waiting for inference service chaiml-gy-exp140-dpo-ex-65459-v2-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 3047.69s
Shutdown handler de-registered
chaiml-gy-exp140-dpo-ex_65459_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp140-dpo-ex_65459_v2 status is now torndown due to DeploymentManager action