chaiml-gy-exp67-dpo-exp_18647

developer_uid: bogoconic1

submission_id: chaiml-gy-exp67-dpo-exp_18647_v1

model_name: chaiml-gy-exp67-dpo-exp_18647_v1

model_group: ChaiML/gy-exp67-dpo-exp3

status: torndown

timestamp: 2025-07-03T07:16:39+00:00

num_battles: 11539

num_wins: 6189

celo_rating: 1312.35

family_friendly_score: 0.5154000000000001

family_friendly_standard_error: 0.0070677130671809255

submission_type: basic

model_repo: ChaiML/gy-exp67-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-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': 0.5185030507684509, 'latency_mean': 1.9285055637359618, 'latency_p50': 1.9387856721878052, 'latency_p90': 2.1219462156295776}, {'batch_size': 3, 'throughput': 1.0509296660210068, 'latency_mean': 2.8464637529850005, 'latency_p50': 2.849704146385193, 'latency_p90': 3.103935146331787}, {'batch_size': 5, 'throughput': 1.3287601635795563, 'latency_mean': 3.738760133981705, 'latency_p50': 3.7222131490707397, 'latency_p90': 4.201488327980042}, {'batch_size': 6, 'throughput': 1.4340085856664906, 'latency_mean': 4.149384276866913, 'latency_p50': 4.147839903831482, 'latency_p90': 4.6286855936050415}, {'batch_size': 8, 'throughput': 1.565478553568917, 'latency_mean': 5.076047375202179, 'latency_p50': 5.082528829574585, 'latency_p90': 5.649502158164978}, {'batch_size': 10, 'throughput': 1.655469481153396, 'latency_mean': 5.993490419387817, 'latency_p50': 5.997284889221191, 'latency_p90': 6.754798936843872}]

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

display_name: chaiml-gy-exp67-dpo-exp_18647_v1

is_internal_developer: True

language_model: ChaiML/gy-exp67-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.33

us_pacific_date: 2025-07-03

win_ratio: 0.5363549701013953

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_end|>', '<|im_start|>'], '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-exp67-dpo-exp-18647-v1-mkmlizer
Waiting for job on chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer to finish
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: Downloaded to shared memory in 74.669s
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: Checking if ChaiML/gy-exp67-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-ep2 already exists in ChaiML
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpo84ozska, device:0
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: quantized model in 49.241s
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: Processed model ChaiML/gy-exp67-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-ep2 in 123.910s
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp67-dpo-exp-18647-v1/nvidia
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp67-dpo-exp-18647-v1/nvidia/config.json
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp67-dpo-exp-18647-v1/nvidia/special_tokens_map.json
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp67-dpo-exp-18647-v1/nvidia/tokenizer_config.json
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp67-dpo-exp-18647-v1/nvidia/tokenizer.json
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp67-dpo-exp-18647-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 38.29it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 29.48it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 31.59it/s]
Loading 0:   4%|▍         | 16/363 [00:00<00:12, 27.64it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 32.39it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 28.65it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 33.97it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:16, 20.39it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:14, 23.06it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:13, 23.21it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 26.47it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:12, 25.43it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:11, 27.80it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:12, 24.31it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:11, 26.78it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 24.21it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 19.94it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 24.91it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.02it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 25.40it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 24.99it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:13, 20.29it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 26.99it/s]
Loading 0:  28%|██▊       | 102/363 [00:04<00:11, 23.60it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:09, 26.33it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:12, 21.12it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:11, 22.73it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:11, 22.14it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:09, 25.37it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:10, 22.71it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:09, 25.92it/s]
Loading 0:  36%|███▌      | 130/363 [00:05<00:08, 25.96it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:09, 24.94it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 26.89it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:09, 23.43it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:08, 26.75it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:07, 29.74it/s]
Loading 0:  42%|████▏     | 153/363 [00:06<00:11, 18.12it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 21.32it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:09, 21.61it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:08, 23.29it/s]
Loading 0:  46%|████▌     | 166/363 [00:06<00:08, 24.41it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:08, 24.00it/s]
Loading 0:  47%|████▋     | 172/363 [00:06<00:07, 25.13it/s]
Loading 0:  48%|████▊     | 175/363 [00:07<00:07, 25.69it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:07, 24.29it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:07, 24.50it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 23.67it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:08, 21.54it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 22.53it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 22.97it/s]
Loading 0:  55%|█████▌    | 200/363 [00:22<00:07, 22.97it/s]
Loading 0:  55%|█████▌    | 201/363 [00:22<03:13,  1.20s/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,  2.77it/s]
Loading 0:  60%|██████    | 218/363 [00:23<00:36,  3.98it/s]
Loading 0:  61%|██████    | 221/363 [00:23<00:27,  5.07it/s]
Loading 0:  62%|██████▏   | 224/363 [00:24<00:22,  6.10it/s]
Loading 0:  63%|██████▎   | 228/363 [00:24<00:15,  8.60it/s]
Loading 0:  64%|██████▎   | 231/363 [00:24<00:13,  9.96it/s]
Loading 0:  65%|██████▍   | 235/363 [00:24<00:09, 13.35it/s]
Loading 0:  66%|██████▌   | 238/363 [00:24<00:08, 15.54it/s]
Loading 0:  66%|██████▋   | 241/363 [00:24<00:07, 17.09it/s]
Loading 0:  68%|██████▊   | 246/363 [00:24<00:05, 21.01it/s]
Loading 0:  69%|██████▊   | 249/363 [00:24<00:05, 20.16it/s]
Loading 0:  70%|███████   | 255/363 [00:25<00:04, 25.41it/s]
Loading 0:  71%|███████   | 258/363 [00:25<00:04, 22.88it/s]
Loading 0:  73%|███████▎  | 264/363 [00:25<00:03, 29.65it/s]
Loading 0:  74%|███████▍  | 268/363 [00:25<00:04, 22.84it/s]
Loading 0:  75%|███████▍  | 271/363 [00:25<00:04, 21.17it/s]
Loading 0:  75%|███████▌  | 274/363 [00:25<00:04, 22.21it/s]
Loading 0:  76%|███████▋  | 277/363 [00:26<00:03, 22.22it/s]
Loading 0:  78%|███████▊  | 282/363 [00:26<00:03, 25.33it/s]
Loading 0:  79%|███████▊  | 285/363 [00:26<00:03, 22.70it/s]
Loading 0:  80%|████████  | 291/363 [00:26<00:02, 27.41it/s]
Loading 0:  81%|████████  | 294/363 [00:26<00:02, 24.23it/s]
Loading 0:  82%|████████▏ | 299/363 [00:26<00:02, 26.49it/s]
Loading 0:  84%|████████▎ | 304/363 [00:27<00:02, 22.79it/s]
Loading 0:  85%|████████▍ | 307/363 [00:27<00:02, 21.18it/s]
Loading 0:  85%|████████▌ | 310/363 [00:27<00:02, 22.30it/s]
Loading 0:  86%|████████▌ | 313/363 [00:27<00:02, 22.73it/s]
Loading 0:  88%|████████▊ | 318/363 [00:27<00:01, 25.26it/s]
Loading 0:  88%|████████▊ | 321/363 [00:27<00:01, 22.69it/s]
Loading 0:  90%|█████████ | 327/363 [00:28<00:01, 27.77it/s]
Loading 0:  91%|█████████ | 330/363 [00:28<00:01, 24.83it/s]
Loading 0:  92%|█████████▏| 335/363 [00:28<00:01, 27.29it/s]
Loading 0:  93%|█████████▎| 338/363 [00:28<00:00, 26.20it/s]
Loading 0:  94%|█████████▍| 341/363 [00:28<00:01, 15.72it/s]
Loading 0:  96%|█████████▌| 347/363 [00:29<00:00, 21.10it/s]
Loading 0:  96%|█████████▋| 350/363 [00:29<00:00, 21.69it/s]
Loading 0:  98%|█████████▊| 355/363 [00:29<00:00, 25.00it/s]
Loading 0:  99%|█████████▊| 358/363 [00:29<00:00, 22.81it/s]
                                                            
Job chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer completed after 157.06s with status: succeeded
Stopping job with name chaiml-gy-exp67-dpo-exp-18647-v1-mkmlizer
Pipeline stage MKMLizer completed in 158.29s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp67-dpo-exp-18647-v1
Waiting for inference service chaiml-gy-exp67-dpo-exp-18647-v1 to be ready
Failed to get response for submission blend_nonab_2025-06-17: HTTPConnectionPool(host='guanaco-model-mesh.k2.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service chaiml-gy-exp67-dpo-exp-18647-v1 ready after 201.544353723526s
Pipeline stage MKMLDeployer completed in 202.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6363961696624756s
Received healthy response to inference request in 2.1765735149383545s
Received healthy response to inference request in 2.332472562789917s
Received healthy response to inference request in 2.1878716945648193s
Received healthy response to inference request in 1.9294497966766357s
5 requests
0 failed requests
5th percentile: 1.9788745403289796
10th percentile: 2.0282992839813234
20th percentile: 2.1271487712860107
30th percentile: 2.1788331508636474
40th percentile: 2.1833524227142336
50th percentile: 2.1878716945648193
60th percentile: 2.2457120418548584
70th percentile: 2.3035523891448975
80th percentile: 2.3932572841644286
90th percentile: 2.5148267269134523
95th percentile: 2.575611448287964
99th percentile: 2.6242392253875733
mean time: 2.2525527477264404
Pipeline stage StressChecker completed in 12.50s
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 0.68s
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 0.66s
Shutdown handler de-registered
chaiml-gy-exp67-dpo-exp_18647_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5329.15s
Shutdown handler de-registered
chaiml-gy-exp67-dpo-exp_18647_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp67-dpo-exp_18647_v1 status is now torndown due to DeploymentManager action