developer_uid: bogoconic1
submission_id: chaiml-gy-exp88-dpo-exp_49090_v2
model_name: chaiml-gy-exp88-dpo-exp_49090_v2
model_group: ChaiML/gy-exp88-dpo-exp8
status: torndown
timestamp: 2025-07-05T11:42:14+00:00
num_battles: 7173
num_wins: 3829
celo_rating: 1312.05
family_friendly_score: 0.46719999999999995
family_friendly_standard_error: 0.007055836732804976
submission_type: basic
model_repo: ChaiML/gy-exp88-dpo-exp86ep8s2-exp72data-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': 0.5148043280790763, 'latency_mean': 1.942389690876007, 'latency_p50': 1.9500901699066162, 'latency_p90': 2.1483815193176268}, {'batch_size': 3, 'throughput': 1.0516463037312274, 'latency_mean': 2.838793137073517, 'latency_p50': 2.8298861980438232, 'latency_p90': 3.163463807106018}, {'batch_size': 5, 'throughput': 1.330939064782254, 'latency_mean': 3.7382723438739776, 'latency_p50': 3.7505486011505127, 'latency_p90': 4.222241616249084}, {'batch_size': 6, 'throughput': 1.442149010747684, 'latency_mean': 4.128385961055756, 'latency_p50': 4.126497030258179, 'latency_p90': 4.617316389083863}, {'batch_size': 8, 'throughput': 1.5663634468071315, 'latency_mean': 5.064655820131302, 'latency_p50': 5.020089864730835, 'latency_p90': 5.74309389591217}, {'batch_size': 10, 'throughput': 1.6576718894149929, 'latency_mean': 5.997451000213623, 'latency_p50': 5.9998732805252075, 'latency_p90': 6.813562512397766}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-gy-exp88-dpo-exp_49090_v2
is_internal_developer: True
language_model: ChaiML/gy-exp88-dpo-exp86ep8s2-exp72data-ep1
model_size: 24B
ranking_group: single
throughput_3p7s: 1.33
us_pacific_date: 2025-07-05
win_ratio: 0.53380733305451
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-49090-v2-mkmlizer
Waiting for job on chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer to finish
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: Downloaded to shared memory in 62.786s
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: Checking if ChaiML/gy-exp88-dpo-exp86ep8s2-exp72data-ep1 already exists in ChaiML
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnyyco2_z, device:0
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: quantized model in 50.875s
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: Processed model ChaiML/gy-exp88-dpo-exp86ep8s2-exp72data-ep1 in 113.662s
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp88-dpo-exp-49090-v2/nvidia
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp88-dpo-exp-49090-v2/nvidia/config.json
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp88-dpo-exp-49090-v2/nvidia/special_tokens_map.json
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp88-dpo-exp-49090-v2/nvidia/tokenizer_config.json
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp88-dpo-exp-49090-v2/nvidia/tokenizer.json
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp88-dpo-exp-49090-v2/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp88-dpo-exp-49090-v2/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 32.79it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:13, 25.81it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 28.24it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:14, 23.78it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 28.92it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:13, 24.76it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:10, 31.96it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 21.95it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:15, 20.59it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 21.72it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:14, 22.08it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:13, 23.66it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:12, 24.66it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:13, 23.29it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:12, 24.72it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:12, 24.76it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:12, 23.98it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:11, 25.18it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 27.55it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:15, 18.33it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:15, 19.10it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:13, 21.04it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:15, 18.64it/s]
Loading 0:  23%|██▎       | 84/363 [00:03<00:13, 20.40it/s]
Loading 0:  24%|██▍       | 87/363 [00:03<00:14, 18.84it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:12, 21.52it/s]
Loading 0:  26%|██▌       | 94/363 [00:04<00:12, 21.39it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:11, 22.65it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:10, 24.07it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:11, 22.93it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:10, 24.02it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:14, 17.81it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:12, 20.16it/s]
Loading 0:  32%|███▏      | 115/363 [00:05<00:12, 20.34it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:11, 22.19it/s]
Loading 0:  33%|███▎      | 121/363 [00:05<00:10, 23.77it/s]
Loading 0:  34%|███▍      | 124/363 [00:05<00:10, 22.67it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 26.37it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:10, 22.45it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 25.81it/s]
Loading 0:  38%|███▊      | 139/363 [00:06<00:08, 26.61it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:08, 25.64it/s]
Loading 0:  40%|████      | 147/363 [00:06<00:06, 31.01it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:09, 21.54it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:10, 20.44it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 21.81it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 22.56it/s]
Loading 0:  45%|████▌     | 165/363 [00:07<00:07, 26.30it/s]
Loading 0:  46%|████▋     | 168/363 [00:07<00:08, 23.56it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:06, 28.21it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:07, 24.25it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 26.54it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:06, 26.94it/s]
Loading 0:  52%|█████▏    | 189/363 [00:08<00:10, 16.05it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 19.03it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:08, 19.24it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:08, 19.96it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:08, 19.96it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<04:12,  1.56s/it]
Loading 0:  56%|█████▌    | 203/363 [00:24<03:17,  1.23s/it]
Loading 0:  57%|█████▋    | 208/363 [00:24<01:48,  1.43it/s]
Loading 0:  58%|█████▊    | 211/363 [00:24<01:20,  1.89it/s]
Loading 0:  59%|█████▉    | 214/363 [00:24<00:58,  2.55it/s]
Loading 0:  60%|██████    | 218/363 [00:24<00:38,  3.73it/s]
Loading 0:  61%|██████    | 221/363 [00:24<00:29,  4.82it/s]
Loading 0:  62%|██████▏   | 224/363 [00:25<00:24,  5.74it/s]
Loading 0:  63%|██████▎   | 228/363 [00:25<00:16,  8.17it/s]
Loading 0:  64%|██████▎   | 231/363 [00:25<00:13,  9.57it/s]
Loading 0:  65%|██████▌   | 237/363 [00:25<00:08, 14.44it/s]
Loading 0:  66%|██████▌   | 240/363 [00:25<00:08, 15.17it/s]
Loading 0:  68%|██████▊   | 246/363 [00:25<00:05, 20.57it/s]
Loading 0:  69%|██████▉   | 250/363 [00:26<00:05, 20.99it/s]
Loading 0:  70%|███████   | 255/363 [00:26<00:04, 24.41it/s]
Loading 0:  71%|███████▏  | 259/363 [00:26<00:04, 23.53it/s]
Loading 0:  73%|███████▎  | 264/363 [00:26<00:03, 28.08it/s]
Loading 0:  74%|███████▍  | 268/363 [00:26<00:04, 21.41it/s]
Loading 0:  75%|███████▍  | 271/363 [00:27<00:04, 20.21it/s]
Loading 0:  75%|███████▌  | 274/363 [00:27<00:04, 21.57it/s]
Loading 0:  76%|███████▋  | 277/363 [00:27<00:03, 22.20it/s]
Loading 0:  78%|███████▊  | 282/363 [00:27<00:03, 25.83it/s]
Loading 0:  79%|███████▊  | 285/363 [00:27<00:03, 22.58it/s]
Loading 0:  80%|███████▉  | 289/363 [00:27<00:02, 25.61it/s]
Loading 0:  80%|████████  | 292/363 [00:27<00:02, 25.11it/s]
Loading 0:  81%|████████▏ | 295/363 [00:27<00:02, 24.83it/s]
Loading 0:  82%|████████▏ | 299/363 [00:28<00:02, 25.16it/s]
Loading 0:  84%|████████▎ | 304/363 [00:28<00:02, 21.54it/s]
Loading 0:  85%|████████▍ | 307/363 [00:28<00:02, 20.09it/s]
Loading 0:  85%|████████▌ | 310/363 [00:28<00:02, 21.39it/s]
Loading 0:  86%|████████▌ | 313/363 [00:28<00:02, 21.58it/s]
Loading 0:  87%|████████▋ | 316/363 [00:28<00:02, 23.31it/s]
Loading 0:  88%|████████▊ | 320/363 [00:29<00:02, 20.57it/s]
Loading 0:  90%|████████▉ | 326/363 [00:29<00:01, 28.54it/s]
Loading 0:  91%|█████████ | 330/363 [00:29<00:01, 24.12it/s]
Loading 0:  92%|█████████▏| 335/363 [00:29<00:01, 26.98it/s]
Loading 0:  93%|█████████▎| 339/363 [00:29<00:00, 26.39it/s]
Loading 0:  94%|█████████▍| 342/363 [00:30<00:01, 15.28it/s]
Loading 0:  95%|█████████▌| 346/363 [00:30<00:00, 18.78it/s]
Loading 0:  96%|█████████▌| 349/363 [00:30<00:00, 18.25it/s]
Loading 0:  98%|█████████▊| 355/363 [00:30<00:00, 23.72it/s]
Loading 0:  99%|█████████▊| 358/363 [00:30<00:00, 21.77it/s]
Loading 0: 100%|█████████▉| 362/363 [00:30<00:00, 24.90it/s]
                                                            

Job chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer completed after 145.57s with status: succeeded
Stopping job with name chaiml-gy-exp88-dpo-exp-49090-v2-mkmlizer
Pipeline stage MKMLizer completed in 146.32s
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-exp88-dpo-exp-49090-v2
Waiting for inference service chaiml-gy-exp88-dpo-exp-49090-v2 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service chaiml-gy-exp88-dpo-exp-49090-v2 ready after 231.24139642715454s
Pipeline stage MKMLDeployer completed in 231.83s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9830687046051025s
Received healthy response to inference request in 1.9497172832489014s
Received healthy response to inference request in 1.8930106163024902s
Received healthy response to inference request in 2.4356400966644287s
Received healthy response to inference request in 2.399662733078003s
5 requests
0 failed requests
5th percentile: 1.9043519496917725
10th percentile: 1.9156932830810547
20th percentile: 1.9383759498596191
30th percentile: 2.0397063732147216
40th percentile: 2.2196845531463625
50th percentile: 2.399662733078003
60th percentile: 2.4140536785125732
70th percentile: 2.4284446239471436
80th percentile: 2.5451258182525636
90th percentile: 2.764097261428833
95th percentile: 2.8735829830169677
99th percentile: 2.9611715602874757
mean time: 2.332219886779785
Pipeline stage StressChecker completed in 13.15s
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 0.83s
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 0.80s
Shutdown handler de-registered
chaiml-gy-exp88-dpo-exp_49090_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 3123.76s
Shutdown handler de-registered
chaiml-gy-exp88-dpo-exp_49090_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp88-dpo-exp_49090_v2 status is now torndown due to DeploymentManager action