junhua024-chai-1-full-066126

developer_uid: junhua024

submission_id: junhua024-chai-1-full-066126_v18

model_name: junhua024-chai-1-full-066126_v18

model_group: junhua024/chai-1-full-06

status: torndown

timestamp: 2025-07-14T06:56:15+00:00

num_battles: 7298

num_wins: 3415

celo_rating: 1276.21

family_friendly_score: 0.5528

family_friendly_standard_error: 0.007031531269929758

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': 0.5978082927638431, 'latency_mean': 1.6726661920547485, 'latency_p50': 1.6811573505401611, 'latency_p90': 1.8439273834228516}, {'batch_size': 3, 'throughput': 1.088776059127168, 'latency_mean': 2.748883526325226, 'latency_p50': 2.746289372444153, 'latency_p90': 3.0014807701110837}, {'batch_size': 5, 'throughput': 1.3092716877504844, 'latency_mean': 3.7991374802589415, 'latency_p50': 3.8378450870513916, 'latency_p90': 4.234020924568176}, {'batch_size': 6, 'throughput': 1.3727498085575836, 'latency_mean': 4.3375804960727695, 'latency_p50': 4.396425247192383, 'latency_p90': 4.8073115110397335}, {'batch_size': 8, 'throughput': 1.4496202824850781, 'latency_mean': 5.475539493560791, 'latency_p50': 5.473596811294556, 'latency_p90': 6.144902682304382}, {'batch_size': 10, 'throughput': 1.4825361268866337, 'latency_mean': 6.683070821762085, 'latency_p50': 6.657780289649963, 'latency_p90': 7.427653741836548}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full-066126_v18

is_internal_developer: False

language_model: junhua024/chai-1-full-066126

model_size: 13B

ranking_group: single

throughput_3p7s: 1.3

us_pacific_date: 2025-07-13

win_ratio: 0.4679364209372431

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 8, '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-v18-mkmlizer
Waiting for job on junhua024-chai-1-full-066126-v18-mkmlizer to finish
junhua024-chai-1-full-066126-v18-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-066126-v18-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-066126-v18-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v18-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-066126-v18-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-v18-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-v18-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-v18-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-v18-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-v18-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-v18-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-v18-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-v18-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-v18-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-v18-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-v18-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-v18-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-v18-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-v18-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-v18-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-v18-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-v18-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-v18-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-v18-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-v18-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-v18-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-v18-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-v18-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-v18-mkmlizer: Downloaded to shared memory in 84.000s
junhua024-chai-1-full-066126-v18-mkmlizer: Checking if junhua024/chai-1-full-066126 already exists in ChaiML
junhua024-chai-1-full-066126-v18-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjzykyojp, device:0
junhua024-chai-1-full-066126-v18-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-066126-v18-mkmlizer: quantized model in 39.523s
junhua024-chai-1-full-066126-v18-mkmlizer: Processed model junhua024/chai-1-full-066126 in 123.614s
junhua024-chai-1-full-066126-v18-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-066126-v18-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-066126-v18-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v18/nvidia
junhua024-chai-1-full-066126-v18-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v18/nvidia/config.json
junhua024-chai-1-full-066126-v18-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v18/nvidia/special_tokens_map.json
junhua024-chai-1-full-066126-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v18/nvidia/tokenizer_config.json
junhua024-chai-1-full-066126-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v18/nvidia/tokenizer.json
junhua024-chai-1-full-066126-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v18/nvidia/flywheel_model.0.safetensors
junhua024-chai-1-full-066126-v18-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:26, 13.81it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:23, 15.54it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:12, 29.04it/s]
Loading 0:   4%|▍         | 15/363 [00:00<00:11, 30.52it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:13, 24.85it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:13, 24.44it/s]
Loading 0:   8%|▊         | 29/363 [00:01<00:10, 31.25it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:11, 29.66it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 29.72it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:11, 27.89it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:09, 34.72it/s]
Loading 0:  14%|█▍        | 52/363 [00:01<00:10, 29.53it/s]
Loading 0:  15%|█▌        | 56/363 [00:01<00:10, 30.23it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 27.92it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:10, 27.45it/s]
Loading 0:  19%|█▊        | 68/363 [00:02<00:11, 25.19it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:09, 31.53it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:08, 32.28it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:10, 27.67it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:09, 29.21it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:09, 29.68it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 30.59it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:08, 30.57it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:09, 28.52it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:06, 37.08it/s]
Loading 0:  32%|███▏      | 117/363 [00:04<00:09, 26.67it/s]
Loading 0:  34%|███▎      | 122/363 [00:04<00:08, 28.02it/s]
Loading 0:  35%|███▌      | 128/363 [00:04<00:08, 29.05it/s]
Loading 0:  36%|███▋      | 132/363 [00:04<00:08, 28.42it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:07, 31.69it/s]
Loading 0:  39%|███▉      | 141/363 [00:04<00:06, 32.01it/s]
Loading 0:  40%|███▉      | 145/363 [00:05<00:07, 27.89it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:07, 27.19it/s]
Loading 0:  43%|████▎     | 155/363 [00:05<00:06, 32.95it/s]
Loading 0:  44%|████▍     | 160/363 [00:05<00:06, 30.88it/s]
Loading 0:  45%|████▌     | 164/363 [00:05<00:06, 30.10it/s]
Loading 0:  46%|████▋     | 168/363 [00:05<00:06, 28.45it/s]
Loading 0:  48%|████▊     | 175/363 [00:05<00:05, 36.82it/s]
Loading 0:  50%|████▉     | 180/363 [00:06<00:06, 26.27it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:06, 27.53it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.47it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:05, 29.34it/s]
Loading 0:  55%|█████▌    | 200/363 [00:06<00:04, 32.78it/s]
Loading 0:  56%|█████▌    | 204/363 [00:06<00:04, 33.16it/s]
Loading 0:  57%|█████▋    | 208/363 [00:07<00:05, 29.37it/s]
Loading 0:  58%|█████▊    | 212/363 [00:07<00:05, 28.52it/s]
Loading 0:  60%|██████    | 218/363 [00:07<00:04, 34.49it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:04, 32.79it/s]
Loading 0:  63%|██████▎   | 227/363 [00:07<00:04, 32.26it/s]
Loading 0:  64%|██████▎   | 231/363 [00:07<00:04, 30.31it/s]
Loading 0:  66%|██████▌   | 238/363 [00:07<00:03, 39.00it/s]
Loading 0:  67%|██████▋   | 243/363 [00:08<00:04, 28.52it/s]
Loading 0:  68%|██████▊   | 248/363 [00:08<00:03, 30.46it/s]
Loading 0:  70%|██████▉   | 254/363 [00:08<00:03, 31.22it/s]
Loading 0:  71%|███████   | 258/363 [00:08<00:03, 30.46it/s]
Loading 0:  72%|███████▏  | 263/363 [00:08<00:02, 33.40it/s]
Loading 0:  74%|███████▎  | 267/363 [00:08<00:02, 33.76it/s]
Loading 0:  75%|███████▍  | 271/363 [00:09<00:03, 28.93it/s]
Loading 0:  76%|███████▌  | 275/363 [00:09<00:03, 27.79it/s]
Loading 0:  77%|███████▋  | 281/363 [00:09<00:02, 33.18it/s]
Loading 0:  79%|███████▉  | 286/363 [00:09<00:02, 30.25it/s]
Loading 0:  80%|███████▉  | 290/363 [00:09<00:02, 29.89it/s]
Loading 0:  81%|████████  | 294/363 [00:09<00:02, 27.61it/s]
Loading 0:  82%|████████▏ | 299/363 [00:09<00:01, 32.22it/s]
Loading 0:  83%|████████▎ | 303/363 [00:10<00:02, 28.06it/s]
Loading 0:  85%|████████▍ | 307/363 [00:10<00:02, 27.19it/s]
Loading 0:  86%|████████▌ | 311/363 [00:10<00:01, 26.93it/s]
Loading 0:  87%|████████▋ | 317/363 [00:10<00:01, 28.07it/s]
Loading 0:  88%|████████▊ | 320/363 [00:10<00:01, 24.71it/s]
Loading 0:  90%|████████▉ | 325/363 [00:10<00:01, 29.23it/s]
Loading 0:  91%|█████████ | 329/363 [00:11<00:01, 29.08it/s]
Loading 0:  92%|█████████▏| 333/363 [00:11<00:01, 24.54it/s]
Loading 0:  93%|█████████▎| 338/363 [00:11<00:00, 26.28it/s]
Loading 0:  94%|█████████▍| 343/363 [00:11<00:00, 30.98it/s]
Loading 0:  96%|█████████▌| 348/363 [00:11<00:00, 33.64it/s]
Loading 0:  97%|█████████▋| 352/363 [00:12<00:00, 17.03it/s]
Loading 0:  98%|█████████▊| 357/363 [00:12<00:00, 20.47it/s]
                                                            
Job junhua024-chai-1-full-066126-v18-mkmlizer completed after 148.37s with status: succeeded
Stopping job with name junhua024-chai-1-full-066126-v18-mkmlizer
Pipeline stage MKMLizer completed in 149.06s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-1-full-066126-v18
Waiting for inference service junhua024-chai-1-full-066126-v18 to be ready
Inference service junhua024-chai-1-full-066126-v18 ready after 230.9994797706604s
Pipeline stage MKMLDeployer completed in 231.57s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5190258026123047s
Received healthy response to inference request in 1.6479110717773438s
Received healthy response to inference request in 1.786057472229004s
Received healthy response to inference request in 1.916013240814209s
Received healthy response to inference request in 1.5210785865783691s
5 requests
0 failed requests
5th percentile: 1.546445083618164
10th percentile: 1.571811580657959
20th percentile: 1.6225445747375489
30th percentile: 1.6755403518676757
40th percentile: 1.7307989120483398
50th percentile: 1.786057472229004
60th percentile: 1.8380397796630858
70th percentile: 1.890022087097168
80th percentile: 2.036615753173828
90th percentile: 2.2778207778930666
95th percentile: 2.3984232902526856
99th percentile: 2.4949053001403807
mean time: 1.8780172348022461
Pipeline stage StressChecker completed in 11.25s
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 0.75s
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 0.88s
Shutdown handler de-registered
junhua024-chai-1-full-066126_v18 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5735.48s
Shutdown handler de-registered
junhua024-chai-1-full-066126_v18 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-066126_v18 status is now torndown due to DeploymentManager action