junhua024-chai-1-full-002

developer_uid: junhua024

submission_id: junhua024-chai-1-full-002_v14

model_name: junhua024-chai-1-full-002_v14

model_group: junhua024/chai_1-full_00

status: torndown

timestamp: 2025-06-29T06:07:22+00:00

num_battles: 7129

num_wins: 3261

celo_rating: 1248.89

family_friendly_score: 0.5926

family_friendly_standard_error: 0.0069487443470025575

submission_type: basic

model_repo: junhua024/chai_1-full_002

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': 0.5963347038883573, 'latency_mean': 1.6767308473587037, 'latency_p50': 1.6944410800933838, 'latency_p90': 1.8595525026321411}, {'batch_size': 3, 'throughput': 1.0780995804724312, 'latency_mean': 2.7703035569190977, 'latency_p50': 2.780582904815674, 'latency_p90': 3.0414844036102293}, {'batch_size': 5, 'throughput': 1.2940229748819683, 'latency_mean': 3.8460143291950226, 'latency_p50': 3.863340735435486, 'latency_p90': 4.214499402046203}, {'batch_size': 6, 'throughput': 1.3512311383021138, 'latency_mean': 4.411747305393219, 'latency_p50': 4.403534173965454, 'latency_p90': 4.926880884170532}, {'batch_size': 8, 'throughput': 1.4290422633335333, 'latency_mean': 5.545675842761994, 'latency_p50': 5.558962821960449, 'latency_p90': 6.186202645301819}, {'batch_size': 10, 'throughput': 1.4575728085167599, 'latency_mean': 6.811213531494141, 'latency_p50': 6.796043753623962, 'latency_p90': 7.8059741973876955}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full-002_v14

is_internal_developer: False

language_model: junhua024/chai_1-full_002

model_size: 13B

ranking_group: single

throughput_3p7s: 1.28

us_pacific_date: 2025-06-28

win_ratio: 0.45742740917379715

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.2, 'top_k': 40, '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-1-full-002-v14-mkmlizer
Waiting for job on junhua024-chai-1-full-002-v14-mkmlizer to finish
junhua024-chai-1-full-002-v14-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-002-v14-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v14-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-002-v14-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-002-v14-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-002-v14-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-002-v14-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-002-v14-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-002-v14-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-002-v14-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-002-v14-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v14-mkmlizer: ║  Version: 0.29.3                                                    ║
junhua024-chai-1-full-002-v14-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-002-v14-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-002-v14-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-002-v14-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v14-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-002-v14-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-002-v14-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v14-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-002-v14-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-002-v14-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-002-v14-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v14-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-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-1-full-002-v14-mkmlizer: Downloaded to shared memory in 78.276s
junhua024-chai-1-full-002-v14-mkmlizer: Checking if junhua024/chai_1-full_002 already exists in ChaiML
junhua024-chai-1-full-002-v14-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqdbb2_sp, device:0
junhua024-chai-1-full-002-v14-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-002-v14-mkmlizer: quantized model in 30.714s
junhua024-chai-1-full-002-v14-mkmlizer: Processed model junhua024/chai_1-full_002 in 109.067s
junhua024-chai-1-full-002-v14-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-002-v14-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-002-v14-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-002-v14
junhua024-chai-1-full-002-v14-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v14/config.json
junhua024-chai-1-full-002-v14-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v14/special_tokens_map.json
junhua024-chai-1-full-002-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v14/tokenizer_config.json
junhua024-chai-1-full-002-v14-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v14/tokenizer.json
junhua024-chai-1-full-002-v14-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-002-v14/flywheel_model.0.safetensors
junhua024-chai-1-full-002-v14-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:21, 16.87it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:18, 19.44it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.61it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 32.07it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 34.40it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 45.67it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:09, 33.58it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:09, 33.89it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 41.50it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:08, 35.70it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:08, 34.94it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 35.83it/s]
Loading 0:  19%|█▉        | 69/363 [00:01<00:08, 34.74it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:07, 38.19it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:07, 35.96it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:07, 35.81it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:07, 36.62it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 34.64it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 36.23it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:07, 36.19it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:07, 33.60it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 39.76it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:07, 31.70it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 33.37it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 34.46it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 33.58it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 33.50it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 33.36it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 34.59it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:04, 42.03it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 37.79it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.17it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 39.92it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:04, 39.43it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 34.32it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 33.78it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:04, 35.61it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:04, 34.67it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 34.84it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:04, 34.15it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 34.59it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:03, 39.27it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:03, 37.59it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:03, 37.44it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:03, 34.66it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:03, 40.74it/s]
Loading 0:  67%|██████▋   | 244/363 [00:06<00:03, 35.04it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 34.46it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 36.03it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:02, 35.09it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 34.59it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 34.11it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 34.85it/s]
Loading 0:  77%|███████▋  | 281/363 [00:07<00:02, 40.10it/s]
Loading 0:  79%|███████▉  | 286/363 [00:07<00:02, 38.04it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:01, 37.52it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:01, 35.01it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 40.40it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:01, 34.65it/s]
Loading 0:  86%|████████▌ | 311/363 [00:08<00:01, 33.83it/s]
Loading 0:  87%|████████▋ | 317/363 [00:08<00:01, 35.70it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 34.67it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 34.32it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 33.63it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 34.71it/s]
Loading 0:  95%|█████████▍| 344/363 [00:09<00:00, 39.33it/s]
Loading 0:  96%|█████████▌| 349/363 [00:09<00:00, 27.01it/s]
Loading 0:  97%|█████████▋| 353/363 [00:10<00:00, 24.95it/s]
Loading 0:  98%|█████████▊| 357/363 [00:10<00:00, 26.64it/s]
                                                            
Job junhua024-chai-1-full-002-v14-mkmlizer completed after 136.9s with status: succeeded
Stopping job with name junhua024-chai-1-full-002-v14-mkmlizer
Pipeline stage MKMLizer completed in 137.46s
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-1-full-002-v14
Waiting for inference service junhua024-chai-1-full-002-v14 to be ready
Inference service junhua024-chai-1-full-002-v14 ready after 170.58027243614197s
Pipeline stage MKMLDeployer completed in 171.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1997644901275635s
Received healthy response to inference request in 1.5510711669921875s
Received healthy response to inference request in 1.5885083675384521s
Received healthy response to inference request in 1.4644477367401123s
Received healthy response to inference request in 1.5210199356079102s
5 requests
0 failed requests
5th percentile: 1.475762176513672
10th percentile: 1.4870766162872315
20th percentile: 1.5097054958343505
30th percentile: 1.5270301818847656
40th percentile: 1.5390506744384767
50th percentile: 1.5510711669921875
60th percentile: 1.5660460472106934
70th percentile: 1.5810209274291993
80th percentile: 1.7107595920562746
90th percentile: 1.955262041091919
95th percentile: 2.077513265609741
99th percentile: 2.175314245223999
mean time: 1.6649623394012452
Pipeline stage StressChecker completed in 9.87s
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 0.70s
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
junhua024-chai-1-full-002_v14 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 0.17s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service junhua024-chai-1-full-002-v14-profiler
Waiting for inference service junhua024-chai-1-full-002-v14-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5463.82s
Shutdown handler de-registered
junhua024-chai-1-full-002_v14 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-002_v14 status is now torndown due to DeploymentManager action