chaiml-ua-v1-dpo-7b07-l_88277

developer_uid: chai_backend_admin

submission_id: chaiml-ua-v1-dpo-7b07-l_88277_v1

model_name: training123

model_group: ChaiML/ua-v1-dpo_7b07-lr

status: torndown

timestamp: 2025-11-08T08:51:29+00:00

num_battles: 6027

num_wins: 3055

celo_rating: 1296.86

family_friendly_score: 0.4992

family_friendly_standard_error: 0.007071058760892883

submission_type: basic

model_repo: ChaiML/ua-v1-dpo_7b07-lr2e6b01

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 2048

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.2661436674152611, 'latency_mean': 3.7572717130184174, 'latency_p50': 2.8732632398605347, 'latency_p90': 5.889773559570313}, {'batch_size': 2, 'throughput': 0.5735192505590729, 'latency_mean': 3.485443549156189, 'latency_p50': 3.4887025356292725, 'latency_p90': 3.7997806310653686}, {'batch_size': 3, 'throughput': 0.7081882323489403, 'latency_mean': 4.223344383239746, 'latency_p50': 4.197147011756897, 'latency_p90': 4.629953789710998}, {'batch_size': 4, 'throughput': 0.794390905165972, 'latency_mean': 5.024317893981934, 'latency_p50': 5.055651307106018, 'latency_p90': 5.460095357894897}, {'batch_size': 5, 'throughput': 0.8516045865913761, 'latency_mean': 5.835107910633087, 'latency_p50': 5.868100523948669, 'latency_p90': 6.659729671478272}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ua-v1-dpo_7b07-lr2e6b01

model_size: 24B

ranking_group: single

throughput_3p7s: 0.27

us_pacific_date: 2025-11-05

win_ratio: 0.506885681101709

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', '\n', 'User:', 'You:'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', '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-ua-v1-dpo-7b07-l-88277-v1-mkmlizer
Waiting for job on chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer to finish
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║                                                                     ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║                                                                     ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║                                                                     ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║                                                                     ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ║                                                                     ║
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: Downloaded to shared memory in 55.257s
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: Checking if ChaiML/ua-v1-dpo_7b07-lr2e6b01 already exists in ChaiML
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjqi4l4wn, device:0
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Retrying (%r) after connection broken by '%r': %s
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: quantized model in 42.212s
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: Processed model ChaiML/ua-v1-dpo_7b07-lr2e6b01 in 97.470s
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ua-v1-dpo-7b07-l-88277-v1/nvidia
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ua-v1-dpo-7b07-l-88277-v1/nvidia/config.json
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ua-v1-dpo-7b07-l-88277-v1/nvidia/special_tokens_map.json
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ua-v1-dpo-7b07-l-88277-v1/nvidia/tokenizer_config.json
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ua-v1-dpo-7b07-l-88277-v1/nvidia/tokenizer.json
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ua-v1-dpo-7b07-l-88277-v1/nvidia/flywheel_model.1.safetensors
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ua-v1-dpo-7b07-l-88277-v1/nvidia/flywheel_model.0.safetensors
chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:16, 21.63it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:08, 39.70it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:09, 36.03it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:09, 35.75it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:08, 39.21it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 41.75it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:12, 25.62it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:13, 24.11it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 31.76it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 30.68it/s]
Loading 0:  16%|█▌        | 57/363 [00:01<00:08, 34.19it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 31.06it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 32.41it/s]
Loading 0:  19%|█▉        | 70/363 [00:02<00:10, 28.59it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:11, 25.80it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:09, 29.80it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.22it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:09, 27.69it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 30.35it/s]
Loading 0:  26%|██▌       | 95/363 [00:03<00:08, 31.60it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:07, 33.50it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 31.33it/s]
Loading 0:  29%|██▉       | 107/363 [00:03<00:09, 26.18it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:08, 29.08it/s]
Loading 0:  32%|███▏      | 116/363 [00:03<00:08, 29.27it/s]
Loading 0:  33%|███▎      | 120/363 [00:03<00:07, 31.40it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:08, 28.62it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:07, 32.33it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:07, 31.27it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 34.57it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 32.33it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:05, 39.08it/s]
Loading 0:  42%|████▏     | 154/363 [00:05<00:07, 26.40it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.57it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.70it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 30.45it/s]
Loading 0:  48%|████▊     | 174/363 [00:05<00:05, 33.74it/s]
Loading 0:  49%|████▉     | 178/363 [00:05<00:05, 32.36it/s]
Loading 0:  50%|█████     | 182/363 [00:05<00:05, 32.89it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 30.09it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.15it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:06, 26.03it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:14,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:19<01:55,  1.39it/s]
Loading 0:  57%|█████▋    | 208/363 [00:19<01:13,  2.10it/s]
Loading 0:  58%|█████▊    | 211/363 [00:19<00:57,  2.65it/s]
Loading 0:  59%|█████▉    | 214/363 [00:20<00:44,  3.36it/s]
Loading 0:  60%|██████    | 218/363 [00:20<00:30,  4.68it/s]
Loading 0:  61%|██████    | 221/363 [00:20<00:24,  5.81it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:20,  6.72it/s]
Loading 0:  63%|██████▎   | 229/363 [00:20<00:13,  9.87it/s]
Loading 0:  64%|██████▍   | 232/363 [00:20<00:11, 11.74it/s]
Loading 0:  65%|██████▌   | 237/363 [00:20<00:07, 16.22it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:06, 18.53it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 23.21it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 24.59it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:03, 29.06it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 28.82it/s]
Loading 0:  73%|███████▎  | 266/363 [00:21<00:02, 35.86it/s]
Loading 0:  75%|███████▍  | 271/363 [00:22<00:03, 25.72it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 24.18it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 31.27it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 29.89it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.08it/s]
Loading 0:  81%|████████▏ | 295/363 [00:22<00:02, 31.56it/s]
Loading 0:  82%|████████▏ | 299/363 [00:22<00:01, 32.33it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:01, 29.90it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 29.03it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:01, 26.26it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.93it/s]
Loading 0:  89%|████████▊ | 322/363 [00:23<00:01, 30.99it/s]
Loading 0:  90%|█████████ | 327/363 [00:23<00:01, 34.32it/s]
Loading 0:  91%|█████████ | 331/363 [00:23<00:00, 32.44it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 33.23it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 34.04it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:00, 20.41it/s]
Loading 0:  96%|█████████▌| 348/363 [00:24<00:00, 21.88it/s]
Loading 0:  98%|█████████▊| 355/363 [00:24<00:00, 29.24it/s]
Loading 0:  99%|█████████▉| 359/363 [00:24<00:00, 29.14it/s]
                                                            
Job chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer completed after 164.99s with status: succeeded
Stopping job with name chaiml-ua-v1-dpo-7b07-l-88277-v1-mkmlizer
Pipeline stage MKMLizer completed in 165.59s
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-ua-v1-dpo-7b07-l-88277-v1
Waiting for inference service chaiml-ua-v1-dpo-7b07-l-88277-v1 to be ready
Inference service chaiml-ua-v1-dpo-7b07-l-88277-v1 ready after 140.8928964138031s
Pipeline stage MKMLDeployer completed in 141.50s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5894463062286377s
Received healthy response to inference request in 2.2655484676361084s
Received healthy response to inference request in 2.7637715339660645s
Received healthy response to inference request in 2.299532890319824s
Received healthy response to inference request in 2.2787837982177734s
5 requests
0 failed requests
5th percentile: 2.2681955337524413
10th percentile: 2.2708425998687742
20th percentile: 2.2761367321014405
30th percentile: 2.2829336166381835
40th percentile: 2.291233253479004
50th percentile: 2.299532890319824
60th percentile: 2.4154982566833496
70th percentile: 2.531463623046875
80th percentile: 2.624311351776123
90th percentile: 2.694041442871094
95th percentile: 2.728906488418579
99th percentile: 2.7567985248565674
mean time: 2.439416599273682
Pipeline stage StressChecker completed in 13.69s
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 0.94s
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 0.69s
Shutdown handler de-registered
chaiml-ua-v1-dpo-7b07-l_88277_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
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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-ua-v1-dpo-7b07-l-88277-v1-profiler
Waiting for inference service chaiml-ua-v1-dpo-7b07-l-88277-v1-profiler to be ready
Inference service chaiml-ua-v1-dpo-7b07-l-88277-v1-profiler ready after 231.8221297264099s
Pipeline stage MKMLProfilerDeployer completed in 232.58s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-ua-v1-dpo-7b04424ad84063dd453625e4d8fa0ce09b3-deplod2q6l:/code/chaiverse_profiler_1762328998 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-ua-v1-dpo-7b04424ad84063dd453625e4d8fa0ce09b3-deplod2q6l --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1762328998 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 64 --summary /code/chaiverse_profiler_1762328998/summary.json'
%s, retrying in %s seconds...
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-ua-v1-dpo-7b04424ad84063dd453625e4d8fa0ce09b3-deplod2q6l:/code/chaiverse_profiler_1762330272 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-ua-v1-dpo-7b04424ad84063dd453625e4d8fa0ce09b3-deplod2q6l --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1762330272 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 2048 --output_tokens 64 --summary /code/chaiverse_profiler_1762330272/summary.json'
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-ua-v1-dpo-7b04424ad84063dd453625e4d8fa0ce09b3-deplod2q6l --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1762330272/summary.json'
Pipeline stage MKMLProfilerRunner completed in 3151.67s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-ua-v1-dpo-7b07-l-88277-v1-profiler is running
Tearing down inference service chaiml-ua-v1-dpo-7b07-l-88277-v1-profiler
Service chaiml-ua-v1-dpo-7b07-l-88277-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 0.53s
Shutdown handler de-registered
chaiml-ua-v1-dpo-7b07-l_88277_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ua-v1-dpo-7b07-l_88277_v1 status is now torndown due to DeploymentManager action