junhua024-chai-1-full-066126

developer_uid: junhua024

submission_id: junhua024-chai-1-full-066126_v69

model_name: junhua024-chai-1-full-066126_v69

model_group: junhua024/chai-1-full-06

status: torndown

timestamp: 2025-07-15T14:11:26+00:00

num_battles: 6395

num_wins: 3273

celo_rating: 1272.9

family_friendly_score: 0.5558000000000001

family_friendly_standard_error: 0.0070268963276826565

submission_type: basic

model_repo: junhua024/chai-1-full-066126

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': 0.5906003171707815, 'latency_mean': 1.693075466156006, 'latency_p50': 1.6901640892028809, 'latency_p90': 1.8717528343200684}, {'batch_size': 3, 'throughput': 1.0654334248220885, 'latency_mean': 2.8080253541469573, 'latency_p50': 2.789706587791443, 'latency_p90': 3.0786009073257445}, {'batch_size': 5, 'throughput': 1.2748102117583329, 'latency_mean': 3.9069506227970123, 'latency_p50': 3.9095423221588135, 'latency_p90': 4.4635350704193115}, {'batch_size': 6, 'throughput': 1.335705702523239, 'latency_mean': 4.474516806602478, 'latency_p50': 4.455368161201477, 'latency_p90': 4.987507581710815}, {'batch_size': 8, 'throughput': 1.3964479180516414, 'latency_mean': 5.685752371549606, 'latency_p50': 5.689723253250122, 'latency_p90': 6.446341276168823}, {'batch_size': 10, 'throughput': 1.4251546376507864, 'latency_mean': 6.958089431524277, 'latency_p50': 6.987901926040649, 'latency_p90': 7.83858551979065}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full-066126_v69

is_internal_developer: False

language_model: junhua024/chai-1-full-066126

model_size: 13B

ranking_group: single

throughput_3p7s: 1.25

us_pacific_date: 2025-07-15

win_ratio: 0.5118060985144645

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-1-full-066126-v69-mkmlizer
Waiting for job on junhua024-chai-1-full-066126-v69-mkmlizer to finish
junhua024-chai-1-full-066126-v69-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-066126-v69-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-066126-v69-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v69-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-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-066126-v69-mkmlizer: Downloaded to shared memory in 71.722s
junhua024-chai-1-full-066126-v69-mkmlizer: Checking if junhua024/chai-1-full-066126 already exists in ChaiML
junhua024-chai-1-full-066126-v69-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2jmp3oek, device:0
junhua024-chai-1-full-066126-v69-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-066126-v69-mkmlizer: quantized model in 31.334s
junhua024-chai-1-full-066126-v69-mkmlizer: Processed model junhua024/chai-1-full-066126 in 103.133s
junhua024-chai-1-full-066126-v69-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-066126-v69-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-066126-v69-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v69/nvidia
junhua024-chai-1-full-066126-v69-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v69/nvidia/config.json
junhua024-chai-1-full-066126-v69-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v69/nvidia/special_tokens_map.json
junhua024-chai-1-full-066126-v69-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v69/nvidia/tokenizer_config.json
junhua024-chai-1-full-066126-v69-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v69/nvidia/tokenizer.json
junhua024-chai-1-full-066126-v69-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v69/nvidia/flywheel_model.0.safetensors
junhua024-chai-1-full-066126-v69-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:26, 13.86it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:21, 17.00it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 29.29it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:11, 30.84it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 33.01it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 46.47it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:08, 37.17it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:08, 35.83it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 40.17it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:09, 33.70it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 32.57it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.57it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 33.18it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:08, 36.10it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 35.19it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 34.84it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:07, 39.02it/s]
Loading 0:  26%|██▌       | 93/363 [00:02<00:07, 37.67it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 33.44it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:07, 32.88it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:08, 30.54it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 38.45it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:08, 30.53it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 31.43it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:07, 33.56it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:07, 31.98it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:06, 35.37it/s]
Loading 0:  39%|███▉      | 141/363 [00:04<00:06, 34.27it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:07, 29.63it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 29.11it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 38.03it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 34.69it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 34.43it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 34.28it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:04, 39.28it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 32.49it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 30.24it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 32.68it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:05, 32.78it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 33.94it/s]
Loading 0:  57%|█████▋    | 206/363 [00:06<00:04, 34.22it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 35.52it/s]
Loading 0:  60%|██████    | 219/363 [00:06<00:03, 42.92it/s]
Loading 0:  62%|██████▏   | 224/363 [00:06<00:03, 37.33it/s]
Loading 0:  63%|██████▎   | 229/363 [00:06<00:03, 36.13it/s]
Loading 0:  65%|██████▍   | 235/363 [00:06<00:03, 37.28it/s]
Loading 0:  66%|██████▌   | 240/363 [00:06<00:03, 36.96it/s]
Loading 0:  67%|██████▋   | 244/363 [00:07<00:03, 35.41it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 35.03it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:02, 36.86it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 34.19it/s]
Loading 0:  72%|███████▏  | 263/363 [00:07<00:02, 37.38it/s]
Loading 0:  74%|███████▎  | 267/363 [00:07<00:02, 37.99it/s]
Loading 0:  75%|███████▍  | 271/363 [00:07<00:02, 34.06it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 32.60it/s]
Loading 0:  78%|███████▊  | 283/363 [00:08<00:01, 43.65it/s]
Loading 0:  79%|███████▉  | 288/363 [00:08<00:02, 33.20it/s]
Loading 0:  81%|████████  | 293/363 [00:08<00:02, 34.21it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 42.29it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:01, 35.15it/s]
Loading 0:  86%|████████▌ | 311/363 [00:08<00:01, 33.69it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 35.69it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 35.06it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 35.50it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 35.13it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 35.89it/s]
Loading 0:  95%|█████████▌| 345/363 [00:09<00:00, 43.35it/s]
Loading 0:  96%|█████████▋| 350/363 [00:10<00:00, 24.72it/s]
Loading 0:  98%|█████████▊| 354/363 [00:10<00:00, 26.70it/s]
Loading 0:  99%|█████████▊| 358/363 [00:10<00:00, 28.39it/s]
                                                            
Job junhua024-chai-1-full-066126-v69-mkmlizer completed after 130.01s with status: succeeded
Stopping job with name junhua024-chai-1-full-066126-v69-mkmlizer
Pipeline stage MKMLizer completed in 130.90s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-1-full-066126-v69
Waiting for inference service junhua024-chai-1-full-066126-v69 to be ready
Inference service junhua024-chai-1-full-066126-v69 ready after 251.07968187332153s
Pipeline stage MKMLDeployer completed in 251.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.020827054977417s
Received healthy response to inference request in 1.4915378093719482s
Received healthy response to inference request in 1.614732027053833s
Received healthy response to inference request in 1.5826261043548584s
Received healthy response to inference request in 2.399561882019043s
5 requests
0 failed requests
5th percentile: 1.5097554683685304
10th percentile: 1.5279731273651123
20th percentile: 1.5644084453582763
30th percentile: 1.5890472888946534
40th percentile: 1.6018896579742432
50th percentile: 1.614732027053833
60th percentile: 1.928663969039917
70th percentile: 2.242595911026001
80th percentile: 2.5238149166107178
90th percentile: 2.7723209857940674
95th percentile: 2.896574020385742
99th percentile: 2.995976448059082
mean time: 2.02185697555542
Pipeline stage StressChecker completed in 11.80s
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 0.85s
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 0.82s
Shutdown handler de-registered
junhua024-chai-1-full-066126_v69 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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service junhua024-chai-1-full-066126-v69-profiler
Waiting for inference service junhua024-chai-1-full-066126-v69-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 4075.22s
Shutdown handler de-registered
junhua024-chai-1-full-066126_v69 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-066126_v69 status is now torndown due to DeploymentManager action
junhua024-chai-1-full-066126_v69 status is now torndown due to DeploymentManager action