developer_uid: bogoconic1
submission_id: chaiml-gy-exp118-dpo-ex_79766_v2
model_name: chaiml-gy-exp118-dpo-ex_79766_v2
model_group: ChaiML/gy-exp118-dpo-exp
status: torndown
timestamp: 2025-07-08T09:20:55+00:00
num_battles: 7049
num_wins: 3785
celo_rating: 1318.63
family_friendly_score: 0.4628
family_friendly_standard_error: 0.007051470201312631
submission_type: basic
model_repo: ChaiML/gy-exp118-dpo-exp72ep2s3-gy-datamix-v3-bo12-dpo-chs-rej-reward-gt0.7-diffgt0.01-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': 0.4819212665331508, 'latency_mean': 2.0748245894908903, 'latency_p50': 2.0711328983306885, 'latency_p90': 2.3274796485900877}, {'batch_size': 3, 'throughput': 0.9308628556022605, 'latency_mean': 3.2131300592422485, 'latency_p50': 3.233121871948242, 'latency_p90': 3.611577296257019}, {'batch_size': 5, 'throughput': 1.1849806731695514, 'latency_mean': 4.193730702400208, 'latency_p50': 4.200371980667114, 'latency_p90': 4.743435072898865}, {'batch_size': 6, 'throughput': 1.2337633298737811, 'latency_mean': 4.822197577953339, 'latency_p50': 4.803033351898193, 'latency_p90': 5.374915552139282}, {'batch_size': 8, 'throughput': 1.3491444801170724, 'latency_mean': 5.883503373861313, 'latency_p50': 5.9028555154800415, 'latency_p90': 6.628283834457397}, {'batch_size': 10, 'throughput': 1.4070079044194943, 'latency_mean': 7.008932420015335, 'latency_p50': 7.094894051551819, 'latency_p90': 7.992905902862549}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-gy-exp118-dpo-ex_79766_v2
is_internal_developer: False
language_model: ChaiML/gy-exp118-dpo-exp72ep2s3-gy-datamix-v3-bo12-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2
model_size: 24B
ranking_group: single
throughput_3p7s: 1.08
us_pacific_date: 2025-07-08
win_ratio: 0.5369555965385161
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-exp118-dpo-ex-79766-v2-mkmlizer
Waiting for job on chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer to finish
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ║                                                                     ║
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: Downloaded to shared memory in 68.142s
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: Checking if ChaiML/gy-exp118-dpo-exp72ep2s3-gy-datamix-v3-bo12-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2 already exists in ChaiML
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpd0b_we8e, device:0
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Retrying (%r) after connection broken by '%r': %s
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: quantized model in 50.398s
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: Processed model ChaiML/gy-exp118-dpo-exp72ep2s3-gy-datamix-v3-bo12-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2 in 118.541s
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp118-dpo-ex-79766-v2/nvidia
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp118-dpo-ex-79766-v2/nvidia/config.json
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp118-dpo-ex-79766-v2/nvidia/special_tokens_map.json
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp118-dpo-ex-79766-v2/nvidia/tokenizer_config.json
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp118-dpo-ex-79766-v2/nvidia/tokenizer.json
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp118-dpo-ex-79766-v2/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp118-dpo-ex-79766-v2/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 36.39it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 28.72it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.93it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:13, 26.56it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 30.78it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 27.41it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:09, 33.37it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:16, 19.86it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 22.39it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:14, 22.75it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 26.30it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:12, 25.13it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:11, 27.77it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:11, 26.02it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 26.82it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:13, 22.50it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:15, 19.12it/s]
Loading 0:  21%|██▏       | 78/363 [00:03<00:11, 24.07it/s]
Loading 0:  22%|██▏       | 81/363 [00:03<00:12, 21.88it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.19it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 25.12it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.13it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 26.53it/s]
Loading 0:  28%|██▊       | 102/363 [00:04<00:10, 23.99it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:12, 21.26it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 24.15it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:11, 22.04it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:09, 26.74it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:10, 23.98it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 28.63it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 26.46it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 28.38it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:09, 24.52it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 31.00it/s]
Loading 0:  42%|████▏     | 151/363 [00:06<00:09, 22.79it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 21.05it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 21.92it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:09, 21.66it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 25.03it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 22.37it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:06, 27.35it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:07, 24.04it/s]
Loading 0:  50%|████▉     | 181/363 [00:07<00:06, 27.29it/s]
Loading 0:  51%|█████     | 186/363 [00:07<00:06, 28.12it/s]
Loading 0:  52%|█████▏    | 189/363 [00:07<00:10, 16.92it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:08, 19.95it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:08, 20.58it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:07, 20.58it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<03:05,  1.15s/it]
Loading 0:  56%|█████▌    | 203/363 [00:23<02:34,  1.04it/s]
Loading 0:  57%|█████▋    | 208/363 [00:23<01:33,  1.65it/s]
Loading 0:  58%|█████▊    | 211/363 [00:23<01:11,  2.11it/s]
Loading 0:  59%|█████▉    | 214/363 [00:23<00:53,  2.77it/s]
Loading 0:  60%|██████    | 218/363 [00:24<00:36,  3.96it/s]
Loading 0:  61%|██████    | 221/363 [00:24<00:28,  4.99it/s]
Loading 0:  62%|██████▏   | 224/363 [00:24<00:23,  5.87it/s]
Loading 0:  63%|██████▎   | 228/363 [00:24<00:16,  8.27it/s]
Loading 0:  64%|██████▎   | 231/363 [00:24<00:14,  9.32it/s]
Loading 0:  65%|██████▍   | 235/363 [00:24<00:10, 12.50it/s]
Loading 0:  66%|██████▌   | 238/363 [00:24<00:08, 14.65it/s]
Loading 0:  66%|██████▋   | 241/363 [00:25<00:07, 16.49it/s]
Loading 0:  68%|██████▊   | 246/363 [00:25<00:05, 20.71it/s]
Loading 0:  69%|██████▊   | 249/363 [00:25<00:05, 20.02it/s]
Loading 0:  70%|███████   | 255/363 [00:25<00:04, 25.59it/s]
Loading 0:  71%|███████▏  | 259/363 [00:25<00:04, 24.49it/s]
Loading 0:  72%|███████▏  | 262/363 [00:25<00:03, 25.56it/s]
Loading 0:  74%|███████▎  | 267/363 [00:26<00:04, 22.93it/s]
Loading 0:  74%|███████▍  | 270/363 [00:26<00:04, 19.33it/s]
Loading 0:  75%|███████▌  | 274/363 [00:26<00:03, 22.49it/s]
Loading 0:  76%|███████▋  | 277/363 [00:26<00:03, 22.96it/s]
Loading 0:  78%|███████▊  | 282/363 [00:26<00:03, 25.65it/s]
Loading 0:  79%|███████▊  | 285/363 [00:26<00:03, 22.85it/s]
Loading 0:  80%|████████  | 291/363 [00:27<00:02, 27.68it/s]
Loading 0:  81%|████████  | 294/363 [00:27<00:02, 24.48it/s]
Loading 0:  82%|████████▏ | 299/363 [00:27<00:02, 26.88it/s]
Loading 0:  84%|████████▎ | 304/363 [00:27<00:02, 23.64it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 21.66it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 22.66it/s]
Loading 0:  86%|████████▌ | 313/363 [00:28<00:02, 23.24it/s]
Loading 0:  88%|████████▊ | 318/363 [00:28<00:01, 26.41it/s]
Loading 0:  88%|████████▊ | 321/363 [00:28<00:01, 23.83it/s]
Loading 0:  90%|█████████ | 327/363 [00:28<00:01, 29.22it/s]
Loading 0:  91%|█████████ | 331/363 [00:28<00:01, 26.75it/s]
Loading 0:  92%|█████████▏| 334/363 [00:28<00:01, 27.35it/s]
Loading 0:  93%|█████████▎| 337/363 [00:28<00:01, 22.72it/s]
Loading 0:  94%|█████████▎| 340/363 [00:29<00:00, 24.25it/s]
Loading 0:  94%|█████████▍| 343/363 [00:29<00:01, 14.05it/s]
Loading 0:  96%|█████████▌| 347/363 [00:29<00:00, 17.94it/s]
Loading 0:  96%|█████████▋| 350/363 [00:29<00:00, 18.65it/s]
Loading 0:  97%|█████████▋| 353/363 [00:29<00:00, 20.75it/s]
Loading 0:  98%|█████████▊| 356/363 [00:30<00:00, 22.47it/s]
Loading 0:  99%|█████████▉| 359/363 [00:30<00:00, 22.34it/s]
                                                            

Job chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer completed after 147.7s with status: succeeded
Stopping job with name chaiml-gy-exp118-dpo-ex-79766-v2-mkmlizer
Pipeline stage MKMLizer completed in 148.24s
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-exp118-dpo-ex-79766-v2
Waiting for inference service chaiml-gy-exp118-dpo-ex-79766-v2 to be ready
Inference service chaiml-gy-exp118-dpo-ex-79766-v2 ready after 190.94159984588623s
Pipeline stage MKMLDeployer completed in 191.49s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8827147483825684s
Received healthy response to inference request in 1.9861931800842285s
Received healthy response to inference request in 2.1285574436187744s
Received healthy response to inference request in 1.9389708042144775s
Received healthy response to inference request in 2.492750883102417s
5 requests
0 failed requests
5th percentile: 1.9484152793884277
10th percentile: 1.957859754562378
20th percentile: 1.9767487049102783
30th percentile: 2.014666032791138
40th percentile: 2.071611738204956
50th percentile: 2.1285574436187744
60th percentile: 2.2742348194122313
70th percentile: 2.4199121952056886
80th percentile: 2.5707436561584474
90th percentile: 2.7267292022705076
95th percentile: 2.804721975326538
99th percentile: 2.8671161937713623
mean time: 2.285837411880493
Pipeline stage StressChecker completed in 13.02s
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 0.69s
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 0.72s
Shutdown handler de-registered
chaiml-gy-exp118-dpo-ex_79766_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 3397.78s
Shutdown handler de-registered
chaiml-gy-exp118-dpo-ex_79766_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp118-dpo-ex_79766_v2 status is now torndown due to DeploymentManager action