chaiml-gy-exp129-dpo-ex_61642

developer_uid: bogoconic1

submission_id: chaiml-gy-exp129-dpo-ex_61642_v4

model_name: chaiml-gy-exp129-dpo-ex_61642_v4

model_group: ChaiML/gy-exp129-dpo-exp

status: torndown

timestamp: 2025-07-09T14:11:24+00:00

num_battles: 8518

num_wins: 4606

celo_rating: 1317.87

family_friendly_score: 0.5

family_friendly_standard_error: 0.007071067811865475

submission_type: basic

model_repo: ChaiML/gy-exp129-dpo-exp54ep6s2-maxlen1024-exp122data-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': 0.5265307336369619, 'latency_mean': 1.8991035056114196, 'latency_p50': 1.9034841060638428, 'latency_p90': 2.1107629537582397}, {'batch_size': 3, 'throughput': 1.0473958598074102, 'latency_mean': 2.847051508426666, 'latency_p50': 2.8483986854553223, 'latency_p90': 3.141447329521179}, {'batch_size': 5, 'throughput': 1.3247522414749122, 'latency_mean': 3.7608506762981415, 'latency_p50': 3.776221513748169, 'latency_p90': 4.155805993080139}, {'batch_size': 6, 'throughput': 1.4270398049940722, 'latency_mean': 4.167341057062149, 'latency_p50': 4.16418719291687, 'latency_p90': 4.679568219184875}, {'batch_size': 8, 'throughput': 1.5663071173139647, 'latency_mean': 5.06557968378067, 'latency_p50': 5.064581274986267, 'latency_p90': 5.679891037940979}, {'batch_size': 10, 'throughput': 1.6473959563347205, 'latency_mean': 6.004349707365036, 'latency_p50': 6.011641263961792, 'latency_p90': 6.687836337089538}]

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

display_name: chaiml-gy-exp129-dpo-ex_61642_v4

is_internal_developer: False

language_model: ChaiML/gy-exp129-dpo-exp54ep6s2-maxlen1024-exp122data-ep2

model_size: 24B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2025-07-09

win_ratio: 0.540737262268138

generation_params: {'temperature': 0.7, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_start|>', '<|im_end|>', '\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': False}

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-exp129-dpo-ex-61642-v4-mkmlizer
Waiting for job on chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer to finish
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║                                                                     ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║                                                                     ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║                                                                     ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║                                                                     ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ║                                                                     ║
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: Downloaded to shared memory in 63.093s
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: Checking if ChaiML/gy-exp129-dpo-exp54ep6s2-maxlen1024-exp122data-ep2 already exists in ChaiML
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpghj7szpx, device:0
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: quantized model in 51.409s
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: Processed model ChaiML/gy-exp129-dpo-exp54ep6s2-maxlen1024-exp122data-ep2 in 114.502s
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp129-dpo-ex-61642-v4/nvidia
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp129-dpo-ex-61642-v4/nvidia/config.json
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp129-dpo-ex-61642-v4/nvidia/special_tokens_map.json
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp129-dpo-ex-61642-v4/nvidia/tokenizer_config.json
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp129-dpo-ex-61642-v4/nvidia/tokenizer.json
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-gy-exp129-dpo-ex-61642-v4/nvidia/flywheel_model.1.safetensors
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp129-dpo-ex-61642-v4/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:10, 33.68it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:13, 26.96it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 27.02it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:15, 22.05it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:12, 26.52it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:12, 26.41it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:13, 24.87it/s]
Loading 0:   8%|▊         | 30/363 [00:01<00:10, 30.84it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:16, 19.61it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:17, 18.75it/s]
Loading 0:  11%|█         | 40/363 [00:01<00:16, 19.87it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:15, 20.71it/s]
Loading 0:  13%|█▎        | 48/363 [00:02<00:13, 24.15it/s]
Loading 0:  14%|█▍        | 51/363 [00:02<00:14, 21.60it/s]
Loading 0:  16%|█▌        | 57/363 [00:02<00:11, 26.83it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:12, 23.65it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:11, 25.37it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:10, 27.42it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:15, 19.01it/s]
Loading 0:  21%|██        | 75/363 [00:03<00:14, 19.64it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:12, 22.02it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:13, 21.53it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 23.96it/s]
Loading 0:  25%|██▍       | 89/363 [00:03<00:11, 23.89it/s]
Loading 0:  25%|██▌       | 92/363 [00:04<00:14, 18.91it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:10, 24.75it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:10, 25.05it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:10, 24.31it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:12, 19.73it/s]
Loading 0:  31%|███       | 111/363 [00:04<00:10, 23.19it/s]
Loading 0:  31%|███▏      | 114/363 [00:04<00:11, 21.19it/s]
Loading 0:  33%|███▎      | 120/363 [00:05<00:09, 25.71it/s]
Loading 0:  34%|███▍      | 123/363 [00:05<00:10, 22.25it/s]
Loading 0:  36%|███▌      | 129/363 [00:05<00:08, 26.39it/s]
Loading 0:  36%|███▋      | 132/363 [00:05<00:10, 23.01it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:08, 25.71it/s]
Loading 0:  38%|███▊      | 139/363 [00:05<00:08, 25.16it/s]
Loading 0:  39%|███▉      | 142/363 [00:06<00:09, 24.01it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:08, 25.05it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:07, 28.23it/s]
Loading 0:  42%|████▏     | 152/363 [00:06<00:11, 18.13it/s]
Loading 0:  43%|████▎     | 155/363 [00:06<00:10, 19.05it/s]
Loading 0:  44%|████▎     | 158/363 [00:07<00:12, 16.29it/s]
Loading 0:  45%|████▌     | 165/363 [00:07<00:08, 22.57it/s]
Loading 0:  46%|████▋     | 168/363 [00:07<00:09, 20.11it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:07, 24.58it/s]
Loading 0:  49%|████▉     | 177/363 [00:07<00:08, 22.22it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:07, 24.94it/s]
Loading 0:  52%|█████▏    | 187/363 [00:08<00:08, 21.35it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:08, 19.52it/s]
Loading 0:  53%|█████▎    | 193/363 [00:08<00:08, 20.36it/s]
Loading 0:  54%|█████▍    | 196/363 [00:08<00:08, 20.83it/s]
Loading 0:  55%|█████▌    | 200/363 [00:23<00:07, 20.83it/s]
Loading 0:  55%|█████▌    | 201/363 [00:23<03:11,  1.18s/it]
Loading 0:  56%|█████▌    | 203/363 [00:24<02:39,  1.01it/s]
Loading 0:  57%|█████▋    | 208/363 [00:24<01:35,  1.62it/s]
Loading 0:  58%|█████▊    | 211/363 [00:24<01:13,  2.07it/s]
Loading 0:  59%|█████▉    | 214/363 [00:24<00:54,  2.72it/s]
Loading 0:  60%|██████    | 218/363 [00:24<00:37,  3.90it/s]
Loading 0:  61%|██████    | 221/363 [00:24<00:28,  4.94it/s]
Loading 0:  62%|██████▏   | 224/363 [00:25<00:24,  5.77it/s]
Loading 0:  63%|██████▎   | 228/363 [00:25<00:16,  8.12it/s]
Loading 0:  64%|██████▎   | 231/363 [00:25<00:14,  9.37it/s]
Loading 0:  65%|██████▌   | 237/363 [00:25<00:09, 13.89it/s]
Loading 0:  66%|██████▌   | 240/363 [00:25<00:08, 14.44it/s]
Loading 0:  67%|██████▋   | 244/363 [00:25<00:06, 18.02it/s]
Loading 0:  68%|██████▊   | 247/363 [00:26<00:05, 19.49it/s]
Loading 0:  69%|██████▉   | 250/363 [00:26<00:05, 20.32it/s]
Loading 0:  70%|███████   | 255/363 [00:26<00:04, 23.45it/s]
Loading 0:  71%|███████   | 258/363 [00:26<00:05, 19.49it/s]
Loading 0:  72%|███████▏  | 262/363 [00:26<00:04, 21.46it/s]
Loading 0:  73%|███████▎  | 266/363 [00:26<00:03, 24.94it/s]
Loading 0:  74%|███████▍  | 269/363 [00:27<00:05, 17.86it/s]
Loading 0:  75%|███████▍  | 272/363 [00:27<00:04, 18.78it/s]
Loading 0:  76%|███████▌  | 275/363 [00:27<00:05, 15.87it/s]
Loading 0:  77%|███████▋  | 280/363 [00:27<00:03, 20.85it/s]
Loading 0:  78%|███████▊  | 283/363 [00:27<00:03, 21.54it/s]
Loading 0:  79%|███████▉  | 286/363 [00:27<00:03, 21.49it/s]
Loading 0:  80%|████████  | 291/363 [00:28<00:02, 24.23it/s]
Loading 0:  81%|████████  | 294/363 [00:28<00:03, 21.67it/s]
Loading 0:  82%|████████▏ | 298/363 [00:28<00:02, 24.94it/s]
Loading 0:  83%|████████▎ | 303/363 [00:28<00:02, 26.66it/s]
Loading 0:  84%|████████▍ | 306/363 [00:28<00:03, 16.60it/s]
Loading 0:  85%|████████▌ | 310/363 [00:29<00:02, 19.83it/s]
Loading 0:  86%|████████▌ | 313/363 [00:29<00:02, 20.34it/s]
Loading 0:  87%|████████▋ | 316/363 [00:29<00:02, 21.94it/s]
Loading 0:  88%|████████▊ | 319/363 [00:29<00:01, 22.81it/s]
Loading 0:  89%|████████▊ | 322/363 [00:29<00:01, 21.71it/s]
Loading 0:  90%|████████▉ | 325/363 [00:29<00:01, 23.53it/s]
Loading 0:  90%|█████████ | 328/363 [00:29<00:01, 24.47it/s]
Loading 0:  91%|█████████ | 331/363 [00:29<00:01, 23.80it/s]
Loading 0:  92%|█████████▏| 334/363 [00:30<00:01, 24.87it/s]
Loading 0:  93%|█████████▎| 337/363 [00:30<00:01, 21.07it/s]
Loading 0:  94%|█████████▍| 341/363 [00:30<00:01, 13.45it/s]
Loading 0:  95%|█████████▌| 346/363 [00:30<00:00, 18.79it/s]
Loading 0:  96%|█████████▌| 349/363 [00:31<00:00, 18.07it/s]
Loading 0:  97%|█████████▋| 353/363 [00:31<00:00, 21.51it/s]
Loading 0:  98%|█████████▊| 357/363 [00:31<00:00, 20.37it/s]
Loading 0: 100%|█████████▉| 362/363 [00:31<00:00, 25.69it/s]
                                                            
Job chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer completed after 156.27s with status: succeeded
Stopping job with name chaiml-gy-exp129-dpo-ex-61642-v4-mkmlizer
Pipeline stage MKMLizer completed in 157.37s
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-exp129-dpo-ex-61642-v4
Waiting for inference service chaiml-gy-exp129-dpo-ex-61642-v4 to be ready
Inference service chaiml-gy-exp129-dpo-ex-61642-v4 ready after 191.11212491989136s
Pipeline stage MKMLDeployer completed in 191.86s
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 3.4341812133789062s
Received healthy response to inference request in 2.3687376976013184s
Received healthy response to inference request in 1.9156250953674316s
Received healthy response to inference request in 2.3063323497772217s
5 requests
1 failed requests
5th percentile: 1.9937665462493896
10th percentile: 2.0719079971313477
20th percentile: 2.2281908988952637
30th percentile: 2.318813419342041
40th percentile: 2.3437755584716795
50th percentile: 2.3687376976013184
60th percentile: 2.7949151039123534
70th percentile: 3.2210925102233885
80th percentile: 6.777952480316165
90th percentile: 13.465495014190676
95th percentile: 16.809266281127925
99th percentile: 19.484283294677734
mean time: 6.035582780838013
%s, retrying in %s seconds...
Received healthy response to inference request in 2.082677125930786s
Received healthy response to inference request in 2.3456172943115234s
Received healthy response to inference request in 1.8098642826080322s
Received healthy response to inference request in 2.011409044265747s
Received healthy response to inference request in 2.233368158340454s
5 requests
0 failed requests
5th percentile: 1.8501732349395752
10th percentile: 1.8904821872711182
20th percentile: 1.971100091934204
30th percentile: 2.025662660598755
40th percentile: 2.0541698932647705
50th percentile: 2.082677125930786
60th percentile: 2.1429535388946532
70th percentile: 2.2032299518585203
80th percentile: 2.255817985534668
90th percentile: 2.3007176399230955
95th percentile: 2.3231674671173095
99th percentile: 2.341127328872681
mean time: 2.0965871810913086
Pipeline stage StressChecker completed in 43.62s
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 0.73s
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 0.99s
Shutdown handler de-registered
chaiml-gy-exp129-dpo-ex_61642_v4 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5090.93s
Shutdown handler de-registered
chaiml-gy-exp129-dpo-ex_61642_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp129-dpo-ex_61642_v4 status is now torndown due to DeploymentManager action