chaiml-gy-exp77-dpo-exp5_8904

developer_uid: bogoconic1

submission_id: chaiml-gy-exp77-dpo-exp5_8904_v1

model_name: chaiml-gy-exp77-dpo-exp5_8904_v1

model_group: ChaiML/gy-exp77-dpo-exp5

status: torndown

timestamp: 2025-07-04T04:59:26+00:00

num_battles: 8000

num_wins: 4147

celo_rating: 1303.68

family_friendly_score: 0.5700000000000001

family_friendly_standard_error: 0.007001428425685719

submission_type: basic

model_repo: ChaiML/gy-exp77-dpo-exp5sftdpos3-majib-0630-ep2

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.5864229133170059, 'latency_mean': 1.7051075768470765, 'latency_p50': 1.7014249563217163, 'latency_p90': 1.883823776245117}, {'batch_size': 3, 'throughput': 1.0633290714775672, 'latency_mean': 2.817714521884918, 'latency_p50': 2.8116955757141113, 'latency_p90': 3.052591323852539}, {'batch_size': 5, 'throughput': 1.2698748812029064, 'latency_mean': 3.9236261093616487, 'latency_p50': 3.9097023010253906, 'latency_p90': 4.359145712852478}, {'batch_size': 6, 'throughput': 1.3413133561630557, 'latency_mean': 4.443953640460968, 'latency_p50': 4.463857531547546, 'latency_p90': 4.950771784782409}, {'batch_size': 8, 'throughput': 1.4075870082242545, 'latency_mean': 5.646624879837036, 'latency_p50': 5.634705424308777, 'latency_p90': 6.401626491546631}, {'batch_size': 10, 'throughput': 1.4442337730355785, 'latency_mean': 6.873306031227112, 'latency_p50': 6.8836082220077515, 'latency_p90': 7.784071683883667}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: chaiml-gy-exp77-dpo-exp5_8904_v1

is_internal_developer: True

language_model: ChaiML/gy-exp77-dpo-exp5sftdpos3-majib-0630-ep2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.24

us_pacific_date: 2025-07-03

win_ratio: 0.518375

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-exp77-dpo-exp5-8904-v1-mkmlizer
Waiting for job on chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer to finish
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ║                                                                     ║
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: Downloaded to shared memory in 41.657s
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: Checking if ChaiML/gy-exp77-dpo-exp5sftdpos3-majib-0630-ep2 already exists in ChaiML
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpzsp1i1su, device:0
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: quantized model in 29.734s
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: Processed model ChaiML/gy-exp77-dpo-exp5sftdpos3-majib-0630-ep2 in 71.391s
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-gy-exp77-dpo-exp5-8904-v1/nvidia
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-gy-exp77-dpo-exp5-8904-v1/nvidia/config.json
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-gy-exp77-dpo-exp5-8904-v1/nvidia/special_tokens_map.json
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-gy-exp77-dpo-exp5-8904-v1/nvidia/tokenizer_config.json
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-gy-exp77-dpo-exp5-8904-v1/nvidia/tokenizer.json
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-gy-exp77-dpo-exp5-8904-v1/nvidia/flywheel_model.0.safetensors
chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.33it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.87it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 43.48it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 41.35it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 47.96it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 45.29it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 44.61it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 50.25it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 47.88it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 34.86it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 34.73it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 38.71it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:07, 40.81it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:07, 36.31it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 44.43it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:05, 45.71it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:06, 39.14it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 48.01it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 41.59it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:06, 39.68it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 43.90it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 43.85it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 44.47it/s]
Loading 0:  39%|███▉      | 141/363 [00:03<00:05, 42.68it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 31.30it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:07, 30.06it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 35.60it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 36.92it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 39.38it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 40.12it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 40.57it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 45.65it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:03, 44.02it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:03, 43.35it/s]
Loading 0:  56%|█████▌    | 202/363 [00:04<00:03, 47.92it/s]
Loading 0:  57%|█████▋    | 207/363 [00:04<00:03, 48.38it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:03, 40.13it/s]
Loading 0:  60%|██████    | 219/363 [00:05<00:03, 47.21it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:04, 30.93it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 32.89it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 39.70it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:02, 40.48it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 41.29it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 42.63it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:02, 35.59it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 43.75it/s]
Loading 0:  74%|███████▍  | 270/363 [00:06<00:02, 44.44it/s]
Loading 0:  76%|███████▌  | 275/363 [00:06<00:02, 37.30it/s]
Loading 0:  78%|███████▊  | 283/363 [00:06<00:01, 44.95it/s]
Loading 0:  80%|███████▉  | 289/363 [00:07<00:01, 43.35it/s]
Loading 0:  81%|████████  | 294/363 [00:07<00:01, 41.25it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 43.01it/s]
Loading 0:  84%|████████▎ | 304/363 [00:07<00:02, 24.51it/s]
Loading 0:  85%|████████▍ | 308/363 [00:07<00:02, 26.38it/s]
Loading 0:  86%|████████▌ | 312/363 [00:07<00:01, 26.51it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 36.02it/s]
Loading 0:  90%|████████▉ | 326/363 [00:08<00:00, 37.78it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 37.90it/s]
Loading 0:  93%|█████████▎| 338/363 [00:08<00:00, 43.72it/s]
Loading 0:  95%|█████████▍| 344/363 [00:08<00:00, 42.53it/s]
Loading 0:  96%|█████████▌| 349/363 [00:08<00:00, 41.61it/s]
Loading 0:  98%|█████████▊| 356/363 [00:08<00:00, 46.58it/s]
Loading 0:  99%|█████████▉| 361/363 [00:08<00:00, 45.65it/s]
                                                            
Job chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer completed after 147.0s with status: succeeded
Stopping job with name chaiml-gy-exp77-dpo-exp5-8904-v1-mkmlizer
Pipeline stage MKMLizer completed in 147.64s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-gy-exp77-dpo-exp5-8904-v1
Waiting for inference service chaiml-gy-exp77-dpo-exp5-8904-v1 to be ready
Inference service chaiml-gy-exp77-dpo-exp5-8904-v1 ready after 220.943439245224s
Pipeline stage MKMLDeployer completed in 221.59s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.353181838989258s
Received healthy response to inference request in 1.7533493041992188s
Received healthy response to inference request in 1.6661396026611328s
Received healthy response to inference request in 1.825368881225586s
Received healthy response to inference request in 1.7037084102630615s
5 requests
0 failed requests
5th percentile: 1.6736533641815186
10th percentile: 1.6811671257019043
20th percentile: 1.6961946487426758
30th percentile: 1.713636589050293
40th percentile: 1.733492946624756
50th percentile: 1.7533493041992188
60th percentile: 1.7821571350097656
70th percentile: 1.8109649658203124
80th percentile: 1.9309314727783204
90th percentile: 2.1420566558837892
95th percentile: 2.2476192474365235
99th percentile: 2.332069320678711
mean time: 1.8603496074676513
Pipeline stage StressChecker completed in 10.67s
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 0.98s
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 0.93s
Shutdown handler de-registered
chaiml-gy-exp77-dpo-exp5_8904_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2823.65s
Shutdown handler de-registered
chaiml-gy-exp77-dpo-exp5_8904_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-gy-exp77-dpo-exp5_8904_v1 status is now torndown due to DeploymentManager action