chaiml-gy-exp120-dpo-ex_31713

developer_uid: bogoconic1

submission_id: chaiml-gy-exp120-dpo-ex_31713_v7

model_name: chaiml-gy-exp120-dpo-ex_31713_v7

model_group: ChaiML/gy-exp120-dpo-exp

status: torndown

timestamp: 2025-07-13T19:00:49+00:00

num_battles: 10877

num_wins: 5779

celo_rating: 1318.26

family_friendly_score: 0.46240000000000003

family_friendly_standard_error: 0.007051045879867752

submission_type: basic

model_repo: ChaiML/gy-exp120-dpo-exp72ep2s3-gy-datamix-v3-bo8-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': 0.517900095601145, 'latency_mean': 1.9307757604122162, 'latency_p50': 1.9391783475875854, 'latency_p90': 2.1270668745040893}, {'batch_size': 3, 'throughput': 1.052754501049547, 'latency_mean': 2.8430941426753997, 'latency_p50': 2.8458313941955566, 'latency_p90': 3.1230515241622925}, {'batch_size': 5, 'throughput': 1.3358642463325334, 'latency_mean': 3.712523194551468, 'latency_p50': 3.7058898210525513, 'latency_p90': 4.071402168273925}, {'batch_size': 6, 'throughput': 1.4483387291263297, 'latency_mean': 4.11242835521698, 'latency_p50': 4.109073877334595, 'latency_p90': 4.5644749164581295}, {'batch_size': 8, 'throughput': 1.5671761945449414, 'latency_mean': 5.060099700689316, 'latency_p50': 5.092768669128418, 'latency_p90': 5.610519742965698}, {'batch_size': 10, 'throughput': 1.6642075391434041, 'latency_mean': 5.956377894878387, 'latency_p50': 5.939265012741089, 'latency_p90': 6.735802006721496}]

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

display_name: chaiml-gy-exp120-dpo-ex_31713_v7

is_internal_developer: False

language_model: ChaiML/gy-exp120-dpo-exp72ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-13

win_ratio: 0.5313045876620391

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-exp120-dpo-ex-31713-v7-mkmlizer
Waiting for job on chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer to finish
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║                                                                     ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║                                                                     ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║                                                                     ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║                                                                     ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ║                                                                     ║
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: Downloaded to shared memory in 57.735s
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: Checking if ChaiML/gy-exp120-dpo-exp72ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2 already exists in ChaiML
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp60csu_m1, device:0
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: quantized model in 50.919s
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: Processed model ChaiML/gy-exp120-dpo-exp72ep2s3-gy-datamix-v3-bo8-dpo-chs-rej-reward-gt0.7-diffgt0.01-ep2 in 108.654s
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp120-dpo-ex-31713-v7/nvidia
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp120-dpo-ex-31713-v7/nvidia/config.json
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp120-dpo-ex-31713-v7/nvidia/special_tokens_map.json
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp120-dpo-ex-31713-v7/nvidia/tokenizer_config.json
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp120-dpo-ex-31713-v7/nvidia/tokenizer.json
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp120-dpo-ex-31713-v7/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp120-dpo-ex-31713-v7/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 37.28it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:12, 28.38it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 27.39it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:15, 23.12it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:11, 30.92it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:12, 27.22it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:12, 27.35it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:11, 27.95it/s]
Loading 0:  10%|▉         | 35/363 [00:01<00:18, 17.85it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:17, 18.48it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:20, 15.53it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:15, 20.48it/s]
Loading 0:  13%|█▎        | 49/363 [00:02<00:14, 21.80it/s]
Loading 0:  14%|█▍        | 52/363 [00:02<00:14, 20.78it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:14, 21.77it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:13, 22.75it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:13, 21.91it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:12, 23.16it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:11, 25.34it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:16, 17.41it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:16, 17.92it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:14, 20.18it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:13, 20.11it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:12, 21.88it/s]
Loading 0:  25%|██▍       | 89/363 [00:04<00:12, 22.17it/s]
Loading 0:  25%|██▌       | 92/363 [00:04<00:15, 17.77it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:11, 23.79it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:10, 24.09it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:10, 24.29it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:12, 20.95it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 24.46it/s]
Loading 0:  31%|███▏      | 114/363 [00:05<00:11, 22.29it/s]
Loading 0:  33%|███▎      | 120/363 [00:05<00:08, 27.67it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:09, 24.29it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 29.06it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 26.62it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 27.96it/s]
Loading 0:  39%|███▉      | 141/363 [00:06<00:09, 23.54it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:08, 26.62it/s]
Loading 0:  41%|████▏     | 150/363 [00:06<00:09, 22.50it/s]
Loading 0:  42%|████▏     | 153/363 [00:06<00:11, 18.98it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:09, 21.96it/s]
Loading 0:  44%|████▍     | 160/363 [00:07<00:09, 21.78it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:09, 22.20it/s]
Loading 0:  46%|████▌     | 166/363 [00:07<00:08, 22.36it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:08, 22.25it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:07, 25.02it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:08, 22.28it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:07, 24.93it/s]
Loading 0:  51%|█████     | 186/363 [00:08<00:06, 27.98it/s]
Loading 0:  52%|█████▏    | 189/363 [00:08<00:09, 17.70it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 20.96it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:07, 21.26it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:07, 21.26it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<03:09,  1.17s/it]
Loading 0:  56%|█████▌    | 203/363 [00:24<02:37,  1.02it/s]
Loading 0:  57%|█████▋    | 208/363 [00:24<01:34,  1.63it/s]
Loading 0:  58%|█████▊    | 211/363 [00:24<01:12,  2.10it/s]
Loading 0:  59%|█████▉    | 214/363 [00:24<00:54,  2.75it/s]
Loading 0:  60%|██████    | 218/363 [00:24<00:37,  3.92it/s]
Loading 0:  61%|██████    | 221/363 [00:24<00:28,  5.00it/s]
Loading 0:  62%|██████▏   | 224/363 [00:25<00:23,  5.96it/s]
Loading 0:  63%|██████▎   | 228/363 [00:25<00:16,  8.39it/s]
Loading 0:  64%|██████▎   | 231/363 [00:25<00:13,  9.71it/s]
Loading 0:  65%|██████▌   | 237/363 [00:25<00:08, 14.41it/s]
Loading 0:  66%|██████▌   | 240/363 [00:25<00:08, 14.72it/s]
Loading 0:  68%|██████▊   | 246/363 [00:25<00:06, 19.44it/s]
Loading 0:  69%|██████▊   | 249/363 [00:26<00:06, 18.86it/s]
Loading 0:  70%|███████   | 255/363 [00:26<00:04, 23.63it/s]
Loading 0:  71%|███████   | 258/363 [00:26<00:04, 21.64it/s]
Loading 0:  72%|███████▏  | 263/363 [00:26<00:03, 26.59it/s]
Loading 0:  74%|███████▎  | 267/363 [00:26<00:04, 21.93it/s]
Loading 0:  74%|███████▍  | 270/363 [00:26<00:04, 18.76it/s]
Loading 0:  75%|███████▌  | 274/363 [00:27<00:04, 21.88it/s]
Loading 0:  76%|███████▋  | 277/363 [00:27<00:03, 21.99it/s]
Loading 0:  78%|███████▊  | 282/363 [00:27<00:03, 24.97it/s]
Loading 0:  79%|███████▊  | 285/363 [00:27<00:03, 22.63it/s]
Loading 0:  80%|████████  | 291/363 [00:27<00:02, 26.96it/s]
Loading 0:  81%|████████  | 294/363 [00:27<00:02, 23.90it/s]
Loading 0:  82%|████████▏ | 299/363 [00:28<00:02, 25.80it/s]
Loading 0:  84%|████████▎ | 304/363 [00:28<00:02, 22.70it/s]
Loading 0:  85%|████████▍ | 307/363 [00:28<00:02, 21.08it/s]
Loading 0:  85%|████████▌ | 310/363 [00:28<00:02, 22.12it/s]
Loading 0:  86%|████████▌ | 313/363 [00:28<00:02, 22.37it/s]
Loading 0:  88%|████████▊ | 318/363 [00:28<00:01, 25.25it/s]
Loading 0:  88%|████████▊ | 321/363 [00:29<00:01, 22.77it/s]
Loading 0:  90%|█████████ | 327/363 [00:29<00:01, 27.50it/s]
Loading 0:  91%|█████████ | 330/363 [00:29<00:01, 24.37it/s]
Loading 0:  92%|█████████▏| 335/363 [00:29<00:01, 26.41it/s]
Loading 0:  93%|█████████▎| 338/363 [00:29<00:00, 25.11it/s]
Loading 0:  94%|█████████▍| 341/363 [00:30<00:01, 15.02it/s]
Loading 0:  95%|█████████▌| 346/363 [00:30<00:00, 20.29it/s]
Loading 0:  96%|█████████▌| 349/363 [00:30<00:00, 19.34it/s]
Loading 0:  97%|█████████▋| 353/363 [00:30<00:00, 22.60it/s]
Loading 0:  98%|█████████▊| 356/363 [00:30<00:00, 24.09it/s]
Loading 0:  99%|█████████▉| 359/363 [00:30<00:00, 23.69it/s]
                                                            
Job chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer completed after 147.06s with status: succeeded
Stopping job with name chaiml-gy-exp120-dpo-ex-31713-v7-mkmlizer
Pipeline stage MKMLizer completed in 147.60s
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-exp120-dpo-ex-31713-v7
Waiting for inference service chaiml-gy-exp120-dpo-ex-31713-v7 to be ready
Inference service chaiml-gy-exp120-dpo-ex-31713-v7 ready after 210.94744968414307s
Pipeline stage MKMLDeployer completed in 211.49s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5021519660949707s
Received healthy response to inference request in 1.8880770206451416s
Received healthy response to inference request in 2.0916049480438232s
Received healthy response to inference request in 2.1872594356536865s
Received healthy response to inference request in 1.9929001331329346s
5 requests
0 failed requests
5th percentile: 1.9090416431427002
10th percentile: 1.9300062656402588
20th percentile: 1.971935510635376
30th percentile: 2.012641096115112
40th percentile: 2.052123022079468
50th percentile: 2.0916049480438232
60th percentile: 2.1298667430877685
70th percentile: 2.1681285381317137
80th percentile: 2.2502379417419434
90th percentile: 2.376194953918457
95th percentile: 2.439173460006714
99th percentile: 2.4895562648773195
mean time: 2.1323987007141114
Pipeline stage StressChecker completed in 12.42s
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 0.71s
Shutdown handler de-registered
chaiml-gy-exp120-dpo-ex_31713_v7 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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp120-dpo-ex-31713-v7-profiler
Waiting for inference service chaiml-gy-exp120-dpo-ex-31713-v7-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
%s, retrying in %s seconds...
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 6785.64s
Shutdown handler de-registered
chaiml-gy-exp120-dpo-ex_31713_v7 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp120-dpo-ex_31713_v7 status is now torndown due to DeploymentManager action