junhua024-chai-1-full-002

developer_uid: junhua024

submission_id: junhua024-chai-1-full-002_v9

model_name: junhua024-chai-1-full-002_v9

model_group: junhua024/chai_1-full_00

status: torndown

timestamp: 2025-06-29T03:46:17+00:00

num_battles: 5667

num_wins: 2645

celo_rating: 1258.69

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': 0.5969576152399048, 'latency_mean': 1.6749778079986573, 'latency_p50': 1.6701958179473877, 'latency_p90': 1.8551365375518798}, {'batch_size': 3, 'throughput': 1.0817567644496466, 'latency_mean': 2.7653515625, 'latency_p50': 2.7500020265579224, 'latency_p90': 3.029690480232239}, {'batch_size': 5, 'throughput': 1.283421482683746, 'latency_mean': 3.8713659942150116, 'latency_p50': 3.8947054147720337, 'latency_p90': 4.40159375667572}, {'batch_size': 6, 'throughput': 1.3468529003156098, 'latency_mean': 4.434689830541611, 'latency_p50': 4.468114972114563, 'latency_p90': 4.9586440324783325}, {'batch_size': 8, 'throughput': 1.4106487767751557, 'latency_mean': 5.639026492834091, 'latency_p50': 5.669715523719788, 'latency_p90': 6.320115923881531}, {'batch_size': 10, 'throughput': 1.4485014862701344, 'latency_mean': 6.852112987041473, 'latency_p50': 6.84601628780365, 'latency_p90': 7.806209874153137}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full-002_v9

is_internal_developer: False

language_model: junhua024/chai_1-full_002

model_size: 13B

ranking_group: single

throughput_3p7s: 1.27

us_pacific_date: 2025-06-28

win_ratio: 0.46673725074995587

generation_params: {'temperature': 1.0, '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-v9-mkmlizer
Waiting for job on junhua024-chai-1-full-002-v9-mkmlizer to finish
junhua024-chai-1-full-002-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-002-v9-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v9-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-002-v9-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-002-v9-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-002-v9-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-002-v9-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-002-v9-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-002-v9-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-002-v9-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-002-v9-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v9-mkmlizer: ║  Version: 0.29.3                                                    ║
junhua024-chai-1-full-002-v9-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-002-v9-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-002-v9-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-002-v9-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v9-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-002-v9-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-002-v9-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v9-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-002-v9-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-002-v9-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-002-v9-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission junhua024-chai-1-full-06_v1: HTTPConnectionPool(host='junhua024-chai-1-full-06-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-1-full-002-v9-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-v9-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-v9-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 junhua024-chai-1-full-06_v1: HTTPConnectionPool(host='junhua024-chai-1-full-06-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-1-full-002-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-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-v9-mkmlizer: Downloaded to shared memory in 82.666s
junhua024-chai-1-full-002-v9-mkmlizer: Checking if junhua024/chai_1-full_002 already exists in ChaiML
junhua024-chai-1-full-002-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7bv525v_, device:0
junhua024-chai-1-full-002-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-002-v9-mkmlizer: quantized model in 31.159s
junhua024-chai-1-full-002-v9-mkmlizer: Processed model junhua024/chai_1-full_002 in 113.914s
junhua024-chai-1-full-002-v9-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-002-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-002-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-002-v9
junhua024-chai-1-full-002-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v9/config.json
junhua024-chai-1-full-002-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v9/special_tokens_map.json
junhua024-chai-1-full-002-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v9/tokenizer_config.json
junhua024-chai-1-full-002-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v9/tokenizer.json
junhua024-chai-1-full-002-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-002-v9/flywheel_model.0.safetensors
junhua024-chai-1-full-002-v9-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:22, 16.09it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:19, 18.13it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 29.02it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:11, 30.26it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.99it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 43.99it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:10, 30.99it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:10, 31.90it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 39.43it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:08, 34.24it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 33.77it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 35.09it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 34.22it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:07, 37.66it/s]
Loading 0:  21%|██▏       | 78/363 [00:02<00:07, 38.02it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 33.01it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 39.64it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 38.80it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:08, 29.49it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:08, 30.97it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 38.84it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 34.22it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 33.55it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 34.19it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 33.56it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 33.62it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 33.28it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 34.60it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:05, 39.76it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 37.26it/s]
Loading 0:  45%|████▌     | 164/363 [00:04<00:05, 36.89it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:05, 33.91it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:04, 39.70it/s]
Loading 0:  50%|████▉     | 180/363 [00:05<00:05, 32.42it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 34.19it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:04, 35.49it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:04, 34.57it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 34.57it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:04, 33.85it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 34.96it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:03, 40.25it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:03, 36.47it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:03, 35.90it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:03, 33.28it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:03, 39.30it/s]
Loading 0:  67%|██████▋   | 243/363 [00:07<00:03, 32.08it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 34.03it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 35.41it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 34.28it/s]
Loading 0:  72%|███████▏  | 263/363 [00:07<00:02, 37.74it/s]
Loading 0:  74%|███████▎  | 267/363 [00:07<00:02, 38.15it/s]
Loading 0:  75%|███████▍  | 271/363 [00:07<00:02, 33.04it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 30.96it/s]
Loading 0:  77%|███████▋  | 281/363 [00:08<00:02, 36.50it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 34.65it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:02, 35.09it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:02, 33.23it/s]
Loading 0:  83%|████████▎ | 301/363 [00:08<00:01, 41.95it/s]
Loading 0:  84%|████████▍ | 306/363 [00:08<00:01, 30.72it/s]
Loading 0:  86%|████████▌ | 311/363 [00:08<00:01, 32.93it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 34.53it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 33.45it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 33.96it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 33.61it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 34.84it/s]
Loading 0:  95%|█████████▍| 344/363 [00:09<00:00, 39.68it/s]
Loading 0:  96%|█████████▌| 349/363 [00:10<00:00, 26.24it/s]
Loading 0:  97%|█████████▋| 353/363 [00:10<00:00, 24.38it/s]
Loading 0:  98%|█████████▊| 357/363 [00:10<00:00, 26.15it/s]
                                                            
Job junhua024-chai-1-full-002-v9-mkmlizer completed after 138.89s with status: succeeded
Stopping job with name junhua024-chai-1-full-002-v9-mkmlizer
Pipeline stage MKMLizer completed in 139.50s
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-v9
Waiting for inference service junhua024-chai-1-full-002-v9 to be ready
Inference service junhua024-chai-1-full-002-v9 ready after 170.89895820617676s
Pipeline stage MKMLDeployer completed in 171.46s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5189247131347656s
Received healthy response to inference request in 1.7994368076324463s
Received healthy response to inference request in 1.6946370601654053s
Received healthy response to inference request in 1.5440030097961426s
Received healthy response to inference request in 1.60335373878479s
5 requests
0 failed requests
5th percentile: 1.555873155593872
10th percentile: 1.5677433013916016
20th percentile: 1.5914835929870605
30th percentile: 1.621610403060913
40th percentile: 1.6581237316131592
50th percentile: 1.6946370601654053
60th percentile: 1.7365569591522216
70th percentile: 1.778476858139038
80th percentile: 1.9433343887329102
90th percentile: 2.231129550933838
95th percentile: 2.3750271320343015
99th percentile: 2.4901451969146726
mean time: 1.83207106590271
Pipeline stage StressChecker completed in 10.76s
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 0.77s
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 0.87s
Shutdown handler de-registered
junhua024-chai-1-full-002_v9 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3110.43s
Shutdown handler de-registered
junhua024-chai-1-full-002_v9 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-002_v9 status is now torndown due to DeploymentManager action