chaiml-gy-exp74-dpo-exp3_7789

developer_uid: bogoconic1

submission_id: chaiml-gy-exp74-dpo-exp3_7789_v1

model_name: chaiml-gy-exp74-dpo-exp3_7789_v1

model_group: ChaiML/gy-exp74-dpo-exp3

status: torndown

timestamp: 2025-07-03T18:06:33+00:00

num_battles: 7598

num_wins: 4062

celo_rating: 1310.73

family_friendly_score: 0.5034000000000001

family_friendly_standard_error: 0.007070904326887757

submission_type: basic

model_repo: ChaiML/gy-exp74-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-rm-win-safe-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': 0.513120713389177, 'latency_mean': 1.9487309014797212, 'latency_p50': 1.9498484134674072, 'latency_p90': 2.1627797842025758}, {'batch_size': 3, 'throughput': 1.0523107587446374, 'latency_mean': 2.837892974615097, 'latency_p50': 2.8512580394744873, 'latency_p90': 3.1722288370132445}, {'batch_size': 5, 'throughput': 1.334327431719196, 'latency_mean': 3.720466684103012, 'latency_p50': 3.7437373399734497, 'latency_p90': 4.2236061811447145}, {'batch_size': 6, 'throughput': 1.4503241634624182, 'latency_mean': 4.11489768743515, 'latency_p50': 4.137680292129517, 'latency_p90': 4.584279942512512}, {'batch_size': 8, 'throughput': 1.563242622697685, 'latency_mean': 5.068775277137757, 'latency_p50': 5.117465496063232, 'latency_p90': 5.6481360912323}, {'batch_size': 10, 'throughput': 1.656929883776077, 'latency_mean': 5.984796751737594, 'latency_p50': 6.01969850063324, 'latency_p90': 6.73526177406311}]

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

display_name: chaiml-gy-exp74-dpo-exp3_7789_v1

is_internal_developer: False

language_model: ChaiML/gy-exp74-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-rm-win-safe-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-03

win_ratio: 0.5346143722032114

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-exp74-dpo-exp3-7789-v1-mkmlizer
Waiting for job on chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer to finish
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: Downloaded to shared memory in 78.912s
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: Checking if ChaiML/gy-exp74-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-rm-win-safe-ep2 already exists in ChaiML
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphi50uty5, device:0
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: quantized model in 47.880s
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: Processed model ChaiML/gy-exp74-dpo-exp32ep8s2-pref-grok3-sub-nis-majib-30jun-rm-win-safe-ep2 in 126.794s
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp74-dpo-exp3-7789-v1/nvidia/config.json
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp74-dpo-exp3-7789-v1/nvidia/special_tokens_map.json
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp74-dpo-exp3-7789-v1/nvidia/tokenizer_config.json
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp74-dpo-exp3-7789-v1/nvidia/tokenizer.json
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp74-dpo-exp3-7789-v1/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp74-dpo-exp3-7789-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.10it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:09, 36.32it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 33.07it/s]
Loading 0:   6%|▌         | 21/363 [00:00<00:10, 33.79it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:11, 30.18it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 35.27it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:15, 21.24it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:13, 24.01it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:12, 25.28it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:11, 27.05it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:12, 25.55it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:11, 27.70it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:12, 24.84it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.81it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:12, 23.89it/s]
Loading 0:  20%|██        | 73/363 [00:02<00:14, 20.54it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:11, 25.42it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.81it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:10, 26.46it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:10, 26.60it/s]
Loading 0:  25%|██▌       | 92/363 [00:03<00:12, 21.43it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:09, 28.52it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:09, 27.07it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:11, 22.24it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:09, 25.22it/s]
Loading 0:  32%|███▏      | 115/363 [00:04<00:09, 25.21it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:08, 27.87it/s]
Loading 0:  34%|███▍      | 123/363 [00:04<00:09, 25.06it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 29.56it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:08, 28.00it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:07, 29.73it/s]
Loading 0:  39%|███▉      | 142/363 [00:05<00:07, 27.99it/s]
Loading 0:  40%|████      | 147/363 [00:05<00:06, 32.43it/s]
Loading 0:  42%|████▏     | 151/363 [00:05<00:09, 23.48it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:09, 22.10it/s]
Loading 0:  43%|████▎     | 157/363 [00:06<00:08, 23.13it/s]
Loading 0:  44%|████▍     | 160/363 [00:06<00:08, 23.64it/s]
Loading 0:  45%|████▌     | 165/363 [00:06<00:07, 26.41it/s]
Loading 0:  46%|████▋     | 168/363 [00:06<00:08, 24.17it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:06, 28.85it/s]
Loading 0:  49%|████▉     | 177/363 [00:06<00:07, 25.60it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:06, 27.93it/s]
Loading 0:  52%|█████▏    | 187/363 [00:07<00:07, 24.59it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 23.03it/s]
Loading 0:  53%|█████▎    | 193/363 [00:07<00:07, 23.96it/s]
Loading 0:  54%|█████▍    | 196/363 [00:07<00:06, 24.44it/s]
Loading 0:  55%|█████▌    | 200/363 [00:21<00:06, 24.44it/s]
Loading 0:  55%|█████▌    | 201/363 [00:21<02:59,  1.11s/it]
Loading 0:  56%|█████▌    | 203/363 [00:22<02:28,  1.08it/s]
Loading 0:  57%|█████▋    | 208/363 [00:22<01:29,  1.73it/s]
Loading 0:  58%|█████▊    | 211/363 [00:22<01:08,  2.20it/s]
Loading 0:  59%|█████▉    | 214/363 [00:22<00:51,  2.90it/s]
Loading 0:  60%|██████    | 218/363 [00:22<00:35,  4.12it/s]
Loading 0:  61%|██████    | 221/363 [00:22<00:27,  5.25it/s]
Loading 0:  62%|██████▏   | 224/363 [00:23<00:22,  6.22it/s]
Loading 0:  63%|██████▎   | 229/363 [00:23<00:14,  9.20it/s]
Loading 0:  64%|██████▍   | 232/363 [00:23<00:11, 10.97it/s]
Loading 0:  65%|██████▌   | 237/363 [00:23<00:08, 14.80it/s]
Loading 0:  66%|██████▌   | 240/363 [00:23<00:07, 15.57it/s]
Loading 0:  68%|██████▊   | 246/363 [00:23<00:05, 20.80it/s]
Loading 0:  69%|██████▊   | 249/363 [00:23<00:05, 20.33it/s]
Loading 0:  70%|███████   | 255/363 [00:24<00:04, 25.24it/s]
Loading 0:  71%|███████▏  | 259/363 [00:24<00:04, 24.68it/s]
Loading 0:  73%|███████▎  | 264/363 [00:24<00:03, 29.01it/s]
Loading 0:  74%|███████▍  | 268/363 [00:24<00:04, 22.02it/s]
Loading 0:  75%|███████▍  | 271/363 [00:24<00:04, 21.15it/s]
Loading 0:  75%|███████▌  | 274/363 [00:24<00:03, 22.56it/s]
Loading 0:  76%|███████▋  | 277/363 [00:25<00:03, 22.76it/s]
Loading 0:  78%|███████▊  | 282/363 [00:25<00:03, 25.71it/s]
Loading 0:  79%|███████▊  | 285/363 [00:25<00:03, 23.53it/s]
Loading 0:  80%|████████  | 291/363 [00:25<00:02, 28.65it/s]
Loading 0:  81%|████████  | 294/363 [00:25<00:02, 25.07it/s]
Loading 0:  82%|████████▏ | 299/363 [00:25<00:02, 27.50it/s]
Loading 0:  84%|████████▎ | 304/363 [00:26<00:02, 24.46it/s]
Loading 0:  85%|████████▍ | 307/363 [00:26<00:02, 22.83it/s]
Loading 0:  85%|████████▌ | 310/363 [00:26<00:02, 23.93it/s]
Loading 0:  86%|████████▌ | 313/363 [00:26<00:02, 24.02it/s]
Loading 0:  88%|████████▊ | 318/363 [00:26<00:01, 26.92it/s]
Loading 0:  88%|████████▊ | 321/363 [00:26<00:01, 24.07it/s]
Loading 0:  90%|█████████ | 327/363 [00:26<00:01, 28.63it/s]
Loading 0:  91%|█████████ | 330/363 [00:27<00:01, 25.89it/s]
Loading 0:  92%|█████████▏| 335/363 [00:27<00:00, 28.21it/s]
Loading 0:  93%|█████████▎| 338/363 [00:27<00:00, 26.75it/s]
Loading 0:  94%|█████████▍| 341/363 [00:27<00:01, 16.07it/s]
Loading 0:  96%|█████████▌| 347/363 [00:27<00:00, 21.69it/s]
Loading 0:  96%|█████████▋| 350/363 [00:28<00:00, 22.28it/s]
Loading 0:  97%|█████████▋| 353/363 [00:28<00:00, 23.72it/s]
Loading 0:  98%|█████████▊| 357/363 [00:28<00:00, 21.83it/s]
                                                            
Job chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer completed after 156.42s with status: succeeded
Stopping job with name chaiml-gy-exp74-dpo-exp3-7789-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.97s
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-exp74-dpo-exp3-7789-v1
Waiting for inference service chaiml-gy-exp74-dpo-exp3-7789-v1 to be ready
Inference service chaiml-gy-exp74-dpo-exp3-7789-v1 ready after 211.51967120170593s
Pipeline stage MKMLDeployer completed in 212.27s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.835742473602295s
Received healthy response to inference request in 2.17854905128479s
Received healthy response to inference request in 1.9825084209442139s
Received healthy response to inference request in 2.226051092147827s
5 requests
1 failed requests
5th percentile: 2.0217165470123293
10th percentile: 2.0609246730804442
20th percentile: 2.1393409252166746
30th percentile: 2.1880494594573974
40th percentile: 2.2070502758026125
50th percentile: 2.226051092147827
60th percentile: 2.4699276447296143
70th percentile: 2.713804197311401
80th percentile: 6.295281076431277
90th percentile: 13.214358282089236
95th percentile: 16.67389688491821
99th percentile: 19.441527767181395
mean time: 5.871257305145264
%s, retrying in %s seconds...
Received healthy response to inference request in 2.1550004482269287s
Received healthy response to inference request in 2.0253820419311523s
Received healthy response to inference request in 2.0615217685699463s
Received healthy response to inference request in 2.2549972534179688s
Received healthy response to inference request in 2.26886248588562s
5 requests
0 failed requests
5th percentile: 2.032609987258911
10th percentile: 2.03983793258667
20th percentile: 2.0542938232421877
30th percentile: 2.0802175045013427
40th percentile: 2.117608976364136
50th percentile: 2.1550004482269287
60th percentile: 2.194999170303345
70th percentile: 2.2349978923797607
80th percentile: 2.257770299911499
90th percentile: 2.2633163928985596
95th percentile: 2.26608943939209
99th percentile: 2.2683078765869142
mean time: 2.1531527996063233
Pipeline stage StressChecker completed in 43.21s
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 0.75s
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-exp74-dpo-exp3_7789_v1 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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-gy-exp74-dpo-exp3-7789-v1-profiler
Waiting for inference service chaiml-gy-exp74-dpo-exp3-7789-v1-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3343.09s
Shutdown handler de-registered
chaiml-gy-exp74-dpo-exp3_7789_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp74-dpo-exp3_7789_v1 status is now torndown due to DeploymentManager action