chaiml-gy-exp100-dpo-exp_9121

developer_uid: bogoconic1

submission_id: chaiml-gy-exp100-dpo-exp_9121_v1

model_name: chaiml-gy-exp100-dpo-exp_9121_v1

model_group: ChaiML/gy-exp100-dpo-exp

status: torndown

timestamp: 2025-07-06T17:17:56+00:00

num_battles: 8914

num_wins: 4661

celo_rating: 1308.21

family_friendly_score: 0.501

family_friendly_standard_error: 0.00707105366971571

submission_type: basic

model_repo: ChaiML/gy-exp100-dpo-exp95ep2s2-grok-payloads-0705-swap-rm512-win-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': 0.5209939066166955, 'latency_mean': 1.9193109321594237, 'latency_p50': 1.910531997680664, 'latency_p90': 2.1272736310958864}, {'batch_size': 3, 'throughput': 1.0490050706102627, 'latency_mean': 2.849391839504242, 'latency_p50': 2.8299994468688965, 'latency_p90': 3.194890284538269}, {'batch_size': 5, 'throughput': 1.3476614253730554, 'latency_mean': 3.692037727832794, 'latency_p50': 3.6858071088790894, 'latency_p90': 4.037902307510376}, {'batch_size': 6, 'throughput': 1.431704006198945, 'latency_mean': 4.159603198766709, 'latency_p50': 4.152015566825867, 'latency_p90': 4.626369333267212}, {'batch_size': 8, 'throughput': 1.554290294128211, 'latency_mean': 5.111285688877106, 'latency_p50': 5.098500490188599, 'latency_p90': 5.681616115570068}, {'batch_size': 10, 'throughput': 1.647028709421039, 'latency_mean': 6.0141673231124875, 'latency_p50': 6.04339337348938, 'latency_p90': 6.790475225448608}]

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

display_name: chaiml-gy-exp100-dpo-exp_9121_v1

is_internal_developer: False

language_model: ChaiML/gy-exp100-dpo-exp95ep2s2-grok-payloads-0705-swap-rm512-win-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.36

us_pacific_date: 2025-07-06

win_ratio: 0.5228853488893875

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-exp100-dpo-exp-9121-v1-mkmlizer
Waiting for job on chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer to finish
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: Downloaded to shared memory in 96.818s
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: Checking if ChaiML/gy-exp100-dpo-exp95ep2s2-grok-payloads-0705-swap-rm512-win-ep2 already exists in ChaiML
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpwz9ciyxv, device:0
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: quantized model in 66.381s
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: Processed model ChaiML/gy-exp100-dpo-exp95ep2s2-grok-payloads-0705-swap-rm512-win-ep2 in 163.200s
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp100-dpo-exp-9121-v1/nvidia
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp100-dpo-exp-9121-v1/nvidia/config.json
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp100-dpo-exp-9121-v1/nvidia/special_tokens_map.json
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp100-dpo-exp-9121-v1/nvidia/tokenizer_config.json
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp100-dpo-exp-9121-v1/nvidia/tokenizer.json
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp100-dpo-exp-9121-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp100-dpo-exp-9121-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:13, 27.31it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:17, 19.82it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:15, 22.93it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:15, 23.18it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:16, 21.58it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:14, 23.72it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:14, 24.05it/s]
Loading 0:   7%|▋         | 25/363 [00:01<00:15, 21.60it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:14, 23.43it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:12, 26.27it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:20, 16.14it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:19, 17.01it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:23, 13.61it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:16, 18.95it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:16, 19.61it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:16, 19.15it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:14, 20.70it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:14, 21.40it/s]
Loading 0:  17%|█▋        | 61/363 [00:03<00:14, 20.87it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:13, 22.31it/s]
Loading 0:  19%|█▊        | 68/363 [00:03<00:11, 26.24it/s]
Loading 0:  20%|█▉        | 71/363 [00:03<00:18, 15.51it/s]
Loading 0:  20%|██        | 74/363 [00:03<00:19, 14.85it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:15, 18.49it/s]
Loading 0:  22%|██▏       | 81/363 [00:04<00:16, 16.62it/s]
Loading 0:  23%|██▎       | 84/363 [00:04<00:14, 18.71it/s]
Loading 0:  24%|██▍       | 87/363 [00:04<00:16, 16.38it/s]
Loading 0:  25%|██▌       | 91/363 [00:04<00:14, 19.23it/s]
Loading 0:  26%|██▌       | 94/363 [00:04<00:13, 19.37it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:12, 20.59it/s]
Loading 0:  28%|██▊       | 100/363 [00:05<00:12, 20.74it/s]
Loading 0:  28%|██▊       | 103/363 [00:05<00:13, 19.98it/s]
Loading 0:  29%|██▉       | 106/363 [00:05<00:11, 21.74it/s]
Loading 0:  30%|███       | 109/363 [00:05<00:15, 16.49it/s]
Loading 0:  31%|███       | 112/363 [00:05<00:13, 18.10it/s]
Loading 0:  32%|███▏      | 115/363 [00:05<00:13, 18.36it/s]
Loading 0:  33%|███▎      | 118/363 [00:06<00:12, 20.29it/s]
Loading 0:  33%|███▎      | 121/363 [00:06<00:11, 21.08it/s]
Loading 0:  34%|███▍      | 124/363 [00:06<00:11, 19.97it/s]
Loading 0:  35%|███▍      | 127/363 [00:06<00:10, 21.78it/s]
Loading 0:  36%|███▌      | 130/363 [00:06<00:10, 22.08it/s]
Loading 0:  37%|███▋      | 133/363 [00:06<00:10, 21.26it/s]
Loading 0:  37%|███▋      | 136/363 [00:06<00:10, 22.64it/s]
Loading 0:  38%|███▊      | 139/363 [00:06<00:10, 22.09it/s]
Loading 0:  39%|███▉      | 142/363 [00:07<00:10, 20.64it/s]
Loading 0:  40%|███▉      | 145/363 [00:07<00:09, 21.87it/s]
Loading 0:  41%|████      | 149/363 [00:07<00:08, 24.94it/s]
Loading 0:  42%|████▏     | 152/363 [00:07<00:13, 15.62it/s]
Loading 0:  43%|████▎     | 155/363 [00:07<00:12, 16.49it/s]
Loading 0:  43%|████▎     | 157/363 [00:08<00:12, 16.29it/s]
Loading 0:  44%|████▍     | 159/363 [00:08<00:13, 15.30it/s]
Loading 0:  45%|████▍     | 163/363 [00:08<00:10, 19.02it/s]
Loading 0:  46%|████▌     | 166/363 [00:08<00:09, 19.85it/s]
Loading 0:  47%|████▋     | 169/363 [00:08<00:10, 19.12it/s]
Loading 0:  47%|████▋     | 172/363 [00:08<00:09, 20.95it/s]
Loading 0:  48%|████▊     | 175/363 [00:08<00:09, 20.83it/s]
Loading 0:  49%|████▉     | 178/363 [00:09<00:09, 19.98it/s]
Loading 0:  50%|████▉     | 181/363 [00:09<00:08, 20.98it/s]
Loading 0:  51%|█████     | 186/363 [00:09<00:07, 23.06it/s]
Loading 0:  52%|█████▏    | 189/363 [00:09<00:12, 13.46it/s]
Loading 0:  53%|█████▎    | 193/363 [00:10<00:10, 16.28it/s]
Loading 0:  54%|█████▍    | 196/363 [00:10<00:09, 16.82it/s]
Loading 0:  55%|█████▍    | 199/363 [00:10<00:08, 18.88it/s]
Loading 0:  55%|█████▌    | 201/363 [00:29<00:08, 18.88it/s]
Loading 0:  56%|█████▌    | 202/363 [00:30<05:04,  1.89s/it]
Loading 0:  56%|█████▌    | 203/363 [00:30<04:30,  1.69s/it]
Loading 0:  57%|█████▋    | 208/363 [00:30<02:24,  1.07it/s]
Loading 0:  58%|█████▊    | 211/363 [00:30<01:44,  1.45it/s]
Loading 0:  59%|█████▊    | 213/363 [00:30<01:23,  1.79it/s]
Loading 0:  60%|█████▉    | 217/363 [00:30<00:52,  2.77it/s]
Loading 0:  61%|██████    | 220/363 [00:31<00:39,  3.59it/s]
Loading 0:  61%|██████▏   | 223/363 [00:31<00:29,  4.80it/s]
Loading 0:  62%|██████▏   | 226/363 [00:31<00:23,  5.71it/s]
Loading 0:  63%|██████▎   | 229/363 [00:31<00:18,  7.38it/s]
Loading 0:  64%|██████▍   | 232/363 [00:31<00:14,  9.11it/s]
Loading 0:  65%|██████▍   | 235/363 [00:31<00:11, 11.43it/s]
Loading 0:  66%|██████▌   | 238/363 [00:32<00:09, 13.33it/s]
Loading 0:  66%|██████▋   | 241/363 [00:32<00:08, 14.82it/s]
Loading 0:  67%|██████▋   | 244/363 [00:32<00:06, 17.04it/s]
Loading 0:  68%|██████▊   | 247/363 [00:32<00:06, 18.15it/s]
Loading 0:  69%|██████▉   | 250/363 [00:32<00:06, 17.68it/s]
Loading 0:  70%|██████▉   | 253/363 [00:32<00:05, 19.90it/s]
Loading 0:  71%|███████   | 256/363 [00:32<00:05, 20.48it/s]
Loading 0:  71%|███████▏  | 259/363 [00:33<00:05, 20.12it/s]
Loading 0:  72%|███████▏  | 262/363 [00:33<00:04, 22.20it/s]
Loading 0:  73%|███████▎  | 266/363 [00:33<00:03, 25.86it/s]
Loading 0:  74%|███████▍  | 269/363 [00:33<00:05, 16.99it/s]
Loading 0:  75%|███████▍  | 272/363 [00:33<00:05, 18.17it/s]
Loading 0:  76%|███████▌  | 275/363 [00:34<00:05, 14.99it/s]
Loading 0:  77%|███████▋  | 280/363 [00:34<00:04, 20.52it/s]
Loading 0:  78%|███████▊  | 283/363 [00:34<00:03, 21.35it/s]
Loading 0:  79%|███████▉  | 286/363 [00:34<00:03, 20.91it/s]
Loading 0:  80%|███████▉  | 289/363 [00:34<00:03, 22.72it/s]
Loading 0:  80%|████████  | 292/363 [00:34<00:03, 22.85it/s]
Loading 0:  81%|████████▏ | 295/363 [00:34<00:03, 22.05it/s]
Loading 0:  82%|████████▏ | 298/363 [00:34<00:02, 23.52it/s]
Loading 0:  83%|████████▎ | 303/363 [00:35<00:02, 24.62it/s]
Loading 0:  84%|████████▍ | 306/363 [00:35<00:03, 14.89it/s]
Loading 0:  85%|████████▌ | 310/363 [00:35<00:02, 17.68it/s]
Loading 0:  86%|████████▌ | 313/363 [00:35<00:02, 17.94it/s]
Loading 0:  87%|████████▋ | 316/363 [00:35<00:02, 19.25it/s]
Loading 0:  88%|████████▊ | 319/363 [00:36<00:02, 19.87it/s]
Loading 0:  89%|████████▊ | 322/363 [00:36<00:02, 19.90it/s]
Loading 0:  90%|████████▉ | 325/363 [00:36<00:01, 21.35it/s]
Loading 0:  90%|█████████ | 328/363 [00:36<00:01, 21.66it/s]
Loading 0:  91%|█████████ | 331/363 [00:36<00:01, 20.69it/s]
Loading 0:  92%|█████████▏| 334/363 [00:36<00:01, 22.07it/s]
Loading 0:  93%|█████████▎| 337/363 [00:36<00:01, 17.82it/s]
Loading 0:  94%|█████████▎| 340/363 [00:37<00:01, 19.76it/s]
Loading 0:  94%|█████████▍| 343/363 [00:37<00:01, 11.21it/s]
Loading 0:  96%|█████████▌| 347/363 [00:37<00:01, 14.74it/s]
Loading 0:  96%|█████████▋| 350/363 [00:37<00:00, 15.98it/s]
Loading 0:  97%|█████████▋| 353/363 [00:38<00:00, 17.87it/s]
Loading 0:  98%|█████████▊| 356/363 [00:38<00:00, 19.40it/s]
Loading 0:  99%|█████████▉| 359/363 [00:38<00:00, 19.46it/s]
Loading 0: 100%|█████████▉| 362/363 [00:38<00:00, 21.37it/s]
                                                            
Job chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer completed after 208.45s with status: succeeded
Stopping job with name chaiml-gy-exp100-dpo-exp-9121-v1-mkmlizer
Pipeline stage MKMLizer completed in 209.36s
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-exp100-dpo-exp-9121-v1
Waiting for inference service chaiml-gy-exp100-dpo-exp-9121-v1 to be ready
Inference service chaiml-gy-exp100-dpo-exp-9121-v1 ready after 211.3307967185974s
Pipeline stage MKMLDeployer completed in 211.76s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7103281021118164s
Received healthy response to inference request in 2.2281816005706787s
Received healthy response to inference request in 2.3728528022766113s
Received healthy response to inference request in 1.963423252105713s
Received healthy response to inference request in 2.256289482116699s
5 requests
0 failed requests
5th percentile: 2.016374921798706
10th percentile: 2.0693265914916994
20th percentile: 2.1752299308776855
30th percentile: 2.2338031768798827
40th percentile: 2.245046329498291
50th percentile: 2.256289482116699
60th percentile: 2.3029148101806642
70th percentile: 2.349540138244629
80th percentile: 2.4403478622436525
90th percentile: 2.5753379821777345
95th percentile: 2.642833042144775
99th percentile: 2.696829090118408
mean time: 2.3062150478363037
Pipeline stage StressChecker completed in 13.49s
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 0.66s
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 0.73s
Shutdown handler de-registered
chaiml-gy-exp100-dpo-exp_9121_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 3402.53s
Shutdown handler de-registered
chaiml-gy-exp100-dpo-exp_9121_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp100-dpo-exp_9121_v1 status is now torndown due to DeploymentManager action