junhua024-chai-06-full-_34362

developer_uid: junhua024

submission_id: junhua024-chai-06-full-_34362_v1

model_name: junhua024-chai-06-full-_34362_v1

model_group: junhua024/chai_06_full_0

status: torndown

timestamp: 2025-07-18T22:01:27+00:00

num_battles: 7383

num_wins: 3512

celo_rating: 1272.34

family_friendly_score: 0.554

family_friendly_standard_error: 0.007029708386554879

submission_type: basic

model_repo: junhua024/chai_06_full_021028_0106

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6026977833790889, 'latency_mean': 1.6590233433246613, 'latency_p50': 1.656174898147583, 'latency_p90': 1.83889319896698}, {'batch_size': 3, 'throughput': 1.0908094063737155, 'latency_mean': 2.7432548666000365, 'latency_p50': 2.7473729848861694, 'latency_p90': 3.0043614864349366}, {'batch_size': 5, 'throughput': 1.3103875751469911, 'latency_mean': 3.7939962828159333, 'latency_p50': 3.795132279396057, 'latency_p90': 4.223613953590393}, {'batch_size': 6, 'throughput': 1.3793686835869086, 'latency_mean': 4.325014578104019, 'latency_p50': 4.3215227127075195, 'latency_p90': 4.857065486907959}, {'batch_size': 8, 'throughput': 1.447421636995834, 'latency_mean': 5.49041345000267, 'latency_p50': 5.488845348358154, 'latency_p90': 6.146841192245483}, {'batch_size': 10, 'throughput': 1.4763119821038058, 'latency_mean': 6.7271548891067505, 'latency_p50': 6.742769718170166, 'latency_p90': 7.524650049209595}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-06-full-_34362_v1

is_internal_developer: False

language_model: junhua024/chai_06_full_021028_0106

model_size: 13B

ranking_group: single

throughput_3p7s: 1.3

us_pacific_date: 2025-07-18

win_ratio: 0.47568738994988485

generation_params: {'temperature': 1.0, 'top_p': 0.88, 'min_p': 0.0, 'top_k': 10, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, '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': 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 junhua024-chai-06-full-34362-v1-mkmlizer
Waiting for job on junhua024-chai-06-full-34362-v1-mkmlizer to finish
junhua024-chai-06-full-34362-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-06-full-34362-v1-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-06-full-34362-v1-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-34362-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
Failed to get response for submission chaiml-exp-grpo-cp312-_36146_v12: HTTPConnectionPool(host='chaiml-exp-grpo-cp312-36146-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
Failed to get response for submission chaiml-20250611-retune-_1558_v12: HTTPConnectionPool(host='chaiml-20250611-retune-1558-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
Failed to get response for submission chaiml-exp-grpo-cp312-_36146_v12: HTTPConnectionPool(host='chaiml-exp-grpo-cp312-36146-v12-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-06-full-34362-v1-mkmlizer: Downloaded to shared memory in 163.677s
junhua024-chai-06-full-34362-v1-mkmlizer: Checking if junhua024/chai_06_full_021028_0106 already exists in ChaiML
junhua024-chai-06-full-34362-v1-mkmlizer: Creating repo ChaiML/chai_06_full_021028_0106 and uploading /tmp/tmpr56j8mia to it
Failed to get response for submission chaiml-mistral31-24b-s_69496_v19: HTTPConnectionPool(host='chaiml-mistral31-24b-s-69496-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-06-full-34362-v1-mkmlizer: 
  0%|          | 0/26 [00:00<?, ?it/s]
  4%|▍         | 1/26 [00:02<00:54,  2.18s/it]
  8%|▊         | 2/26 [00:03<00:40,  1.70s/it]
 12%|█▏        | 3/26 [00:04<00:35,  1.53s/it]
 15%|█▌        | 4/26 [00:06<00:32,  1.47s/it]
 19%|█▉        | 5/26 [00:07<00:31,  1.51s/it]
 23%|██▎       | 6/26 [00:09<00:29,  1.48s/it]
 27%|██▋       | 7/26 [00:12<00:39,  2.08s/it]
 31%|███       | 8/26 [00:13<00:33,  1.85s/it]
 35%|███▍      | 9/26 [00:15<00:29,  1.72s/it]
 38%|███▊      | 10/26 [00:17<00:27,  1.72s/it]
 42%|████▏     | 11/26 [00:18<00:25,  1.68s/it]
 46%|████▌     | 12/26 [00:20<00:22,  1.58s/it]
 50%|█████     | 13/26 [00:21<00:19,  1.50s/it]
 54%|█████▍    | 14/26 [00:22<00:17,  1.46s/it]
 58%|█████▊    | 15/26 [00:24<00:17,  1.63s/it]
 62%|██████▏   | 16/26 [00:26<00:16,  1.64s/it]
 65%|██████▌   | 17/26 [00:27<00:14,  1.59s/it]
 69%|██████▉   | 18/26 [00:29<00:12,  1.51s/it]
 73%|███████▎  | 19/26 [00:30<00:10,  1.45s/it]
 77%|███████▋  | 20/26 [00:31<00:08,  1.42s/it]
 81%|████████  | 21/26 [00:35<00:10,  2.16s/it]
 85%|████████▍ | 22/26 [00:39<00:10,  2.54s/it]
 88%|████████▊ | 23/26 [00:40<00:06,  2.22s/it]
 92%|█████████▏| 24/26 [00:42<00:03,  1.99s/it]
 96%|█████████▌| 25/26 [00:44<00:02,  2.17s/it]
100%|██████████| 26/26 [00:45<00:00,  1.86s/it]
100%|██████████| 26/26 [00:45<00:00,  1.76s/it]
junhua024-chai-06-full-34362-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpr56j8mia, device:0
junhua024-chai-06-full-34362-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-06-full-34362-v1-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-06-full-34362-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-06-full-34362-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-06-full-34362-v1/nvidia
junhua024-chai-06-full-34362-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-06-full-34362-v1/nvidia/config.json
junhua024-chai-06-full-34362-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-06-full-34362-v1/nvidia/special_tokens_map.json
junhua024-chai-06-full-34362-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-06-full-34362-v1/nvidia/tokenizer_config.json
junhua024-chai-06-full-34362-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-06-full-34362-v1/nvidia/tokenizer.json
junhua024-chai-06-full-34362-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-06-full-34362-v1/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-06-full-34362-v1-mkmlizer completed after 297.64s with status: succeeded
Stopping job with name junhua024-chai-06-full-34362-v1-mkmlizer
Pipeline stage MKMLizer completed in 298.43s
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 junhua024-chai-06-full-34362-v1
Waiting for inference service junhua024-chai-06-full-34362-v1 to be ready
Failed to get response for submission chaiml-mistral31-24b-s_69496_v19: HTTPConnectionPool(host='chaiml-mistral31-24b-s-69496-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-mistral31-24b-s_69496_v19: HTTPConnectionPool(host='chaiml-mistral31-24b-s-69496-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-nis-8b-v1-llama3_48598_v5: HTTPConnectionPool(host='chaiml-nis-8b-v1-llama3-48598-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-06-full-34362-v1 ready after 331.66493797302246s
Pipeline stage MKMLDeployer completed in 332.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.580303907394409s
Received healthy response to inference request in 1.6647720336914062s
Received healthy response to inference request in 1.7688777446746826s
Received healthy response to inference request in 2.260693073272705s
Received healthy response to inference request in 1.758969783782959s
5 requests
0 failed requests
5th percentile: 1.6836115837097168
10th percentile: 1.7024511337280273
20th percentile: 1.7401302337646485
30th percentile: 1.7609513759613038
40th percentile: 1.7649145603179932
50th percentile: 1.7688777446746826
60th percentile: 1.9656038761138916
70th percentile: 2.1623300075531007
80th percentile: 2.324615240097046
90th percentile: 2.4524595737457275
95th percentile: 2.5163817405700684
99th percentile: 2.567519474029541
mean time: 2.0067233085632323
Pipeline stage StressChecker completed in 11.58s
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 1.11s
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 1.00s
Shutdown handler de-registered
junhua024-chai-06-full-_34362_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service junhua024-chai-06-full-34362-v1-profiler
Waiting for inference service junhua024-chai-06-full-34362-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 3393.69s
Shutdown handler de-registered
junhua024-chai-06-full-_34362_v1 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-06-full-_34362_v1 status is now torndown due to DeploymentManager action
junhua024-chai-06-full-_34362_v1 status is now torndown due to DeploymentManager action