junhua024-chai-1-full_94469

developer_uid: junhua024

submission_id: junhua024-chai-1-full_94469_v104

model_name: junhua024-chai-1-full_94469_v104

model_group: junhua024/chai-1-full-06

status: torndown

timestamp: 2025-07-16T06:45:18+00:00

num_battles: 8900

num_wins: 4311

celo_rating: 1279.84

family_friendly_score: 0.5508

family_friendly_standard_error: 0.007034477379308288

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': 0.596920112616458, 'latency_mean': 1.6751477861404418, 'latency_p50': 1.6938285827636719, 'latency_p90': 1.8382471799850464}, {'batch_size': 3, 'throughput': 1.0744202469815776, 'latency_mean': 2.7765669310092926, 'latency_p50': 2.7733190059661865, 'latency_p90': 3.081818866729736}, {'batch_size': 5, 'throughput': 1.2959735923578632, 'latency_mean': 3.8355772733688354, 'latency_p50': 3.850031614303589, 'latency_p90': 4.292092370986938}, {'batch_size': 6, 'throughput': 1.3660109494679933, 'latency_mean': 4.353869014978409, 'latency_p50': 4.3732264041900635, 'latency_p90': 4.845833349227905}, {'batch_size': 8, 'throughput': 1.4215370104567313, 'latency_mean': 5.588427531719208, 'latency_p50': 5.563969969749451, 'latency_p90': 6.264142036437988}, {'batch_size': 10, 'throughput': 1.4555754404036794, 'latency_mean': 6.818851922750473, 'latency_p50': 6.821886777877808, 'latency_p90': 7.605036020278931}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full_94469_v104

is_internal_developer: False

language_model: junhua024/chai-1-full-066126

model_size: 13B

ranking_group: single

throughput_3p7s: 1.28

us_pacific_date: 2025-07-15

win_ratio: 0.4843820224719101

generation_params: {'temperature': 1.2, '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-94469-v104-mkmlizer
Waiting for job on junhua024-chai-1-full-94469-v104-mkmlizer to finish
junhua024-chai-1-full-94469-v104-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-94469-v104-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-94469-v104-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-94469-v104-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-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-94469-v104-mkmlizer: Downloaded to shared memory in 77.090s
junhua024-chai-1-full-94469-v104-mkmlizer: Checking if junhua024/chai-1-full-066126 already exists in ChaiML
junhua024-chai-1-full-94469-v104-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphl8rf2ms, device:0
junhua024-chai-1-full-94469-v104-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-94469-v104-mkmlizer: quantized model in 33.720s
junhua024-chai-1-full-94469-v104-mkmlizer: Processed model junhua024/chai-1-full-066126 in 110.884s
junhua024-chai-1-full-94469-v104-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-94469-v104/nvidia/flywheel_model.0.safetensors
junhua024-chai-1-full-94469-v104-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:26, 13.42it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:23, 15.29it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:13, 26.02it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:12, 28.07it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:11, 30.24it/s]
Loading 0:   8%|▊         | 29/363 [00:00<00:09, 35.53it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:09, 33.03it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 32.39it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:10, 30.49it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 37.17it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:10, 28.95it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 31.43it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:09, 33.07it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:09, 31.58it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:08, 34.91it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 33.79it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 33.65it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:08, 33.97it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 30.64it/s]
Loading 0:  26%|██▋       | 96/363 [00:03<00:07, 34.22it/s]
Loading 0:  28%|██▊       | 100/363 [00:03<00:09, 26.84it/s]
Loading 0:  29%|██▊       | 104/363 [00:03<00:09, 26.88it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 36.57it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:08, 29.52it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 31.53it/s]
Loading 0:  35%|███▌      | 128/363 [00:04<00:07, 32.46it/s]
Loading 0:  36%|███▋      | 132/363 [00:04<00:07, 29.71it/s]
Loading 0:  38%|███▊      | 137/363 [00:04<00:06, 32.51it/s]
Loading 0:  39%|███▉      | 141/363 [00:04<00:06, 32.35it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:07, 27.86it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 27.45it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 36.36it/s]
Loading 0:  44%|████▍     | 161/363 [00:05<00:06, 32.53it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.98it/s]
Loading 0:  47%|████▋     | 169/363 [00:05<00:06, 32.26it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:05, 35.75it/s]
Loading 0:  50%|████▉     | 180/363 [00:05<00:06, 26.43it/s]
Loading 0:  51%|█████     | 185/363 [00:06<00:06, 27.67it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 30.24it/s]
Loading 0:  54%|█████▎    | 195/363 [00:06<00:05, 30.29it/s]
Loading 0:  55%|█████▌    | 200/363 [00:06<00:04, 34.22it/s]
Loading 0:  56%|█████▌    | 204/363 [00:06<00:04, 35.33it/s]
Loading 0:  57%|█████▋    | 208/363 [00:06<00:04, 31.36it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:05, 29.54it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:04, 35.75it/s]
Loading 0:  61%|██████▏   | 223/363 [00:07<00:04, 33.39it/s]
Loading 0:  63%|██████▎   | 227/363 [00:07<00:04, 33.02it/s]
Loading 0:  64%|██████▎   | 231/363 [00:07<00:04, 30.51it/s]
Loading 0:  66%|██████▌   | 239/363 [00:07<00:03, 37.52it/s]
Loading 0:  67%|██████▋   | 243/363 [00:07<00:03, 30.08it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 31.79it/s]
Loading 0:  70%|██████▉   | 254/363 [00:08<00:03, 33.48it/s]
Loading 0:  71%|███████   | 258/363 [00:08<00:03, 31.81it/s]
Loading 0:  72%|███████▏  | 263/363 [00:08<00:02, 35.46it/s]
Loading 0:  74%|███████▎  | 267/363 [00:08<00:02, 34.80it/s]
Loading 0:  75%|███████▍  | 271/363 [00:08<00:03, 27.41it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:03, 27.25it/s]
Loading 0:  78%|███████▊  | 283/363 [00:08<00:02, 38.06it/s]
Loading 0:  79%|███████▉  | 288/363 [00:09<00:02, 29.41it/s]
Loading 0:  81%|████████  | 293/363 [00:09<00:02, 31.04it/s]
Loading 0:  83%|████████▎ | 301/363 [00:09<00:01, 40.87it/s]
Loading 0:  84%|████████▍ | 306/363 [00:09<00:01, 30.36it/s]
Loading 0:  86%|████████▌ | 311/363 [00:09<00:01, 30.56it/s]
Loading 0:  87%|████████▋ | 317/363 [00:10<00:01, 31.91it/s]
Loading 0:  88%|████████▊ | 321/363 [00:10<00:01, 30.97it/s]
Loading 0:  90%|█████████ | 327/363 [00:10<00:01, 31.85it/s]
Loading 0:  91%|█████████▏| 332/363 [00:10<00:00, 32.08it/s]
Loading 0:  93%|█████████▎| 338/363 [00:10<00:00, 32.82it/s]
Loading 0:  95%|█████████▍| 344/363 [00:10<00:00, 37.89it/s]
Loading 0:  96%|█████████▌| 349/363 [00:11<00:00, 25.78it/s]
Loading 0:  97%|█████████▋| 353/363 [00:11<00:00, 21.65it/s]
Loading 0:  98%|█████████▊| 357/363 [00:11<00:00, 22.51it/s]
                                                            
Job junhua024-chai-1-full-94469-v104-mkmlizer completed after 145.47s with status: succeeded
Stopping job with name junhua024-chai-1-full-94469-v104-mkmlizer
Pipeline stage MKMLizer completed in 146.17s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-1-full-94469-v104
Waiting for inference service junhua024-chai-1-full-94469-v104 to be ready
Failed to get response for submission blend_fader_2025-07-10: ('http://chaiml-exp-grpo-cp312-9-36146-v7-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:46676->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission junhua024-chai-1-full_94469_v103: HTTPConnectionPool(host='junhua024-chai-1-full-94469-v103-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-1-full-94469-v104 ready after 252.18130445480347s
Pipeline stage MKMLDeployer completed in 253.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.237654209136963s
Received healthy response to inference request in 1.737051248550415s
Received healthy response to inference request in 1.5964784622192383s
Received healthy response to inference request in 1.7193279266357422s
Received healthy response to inference request in 1.62858247756958s
5 requests
0 failed requests
5th percentile: 1.6028992652893066
10th percentile: 1.609320068359375
20th percentile: 1.6221616744995118
30th percentile: 1.6467315673828125
40th percentile: 1.6830297470092774
50th percentile: 1.7193279266357422
60th percentile: 1.7264172554016113
70th percentile: 1.7335065841674804
80th percentile: 1.8371718406677247
90th percentile: 2.0374130249023437
95th percentile: 2.137533617019653
99th percentile: 2.217630090713501
mean time: 1.7838188648223876
Pipeline stage StressChecker completed in 10.74s
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 1.02s
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 0.68s
Shutdown handler de-registered
junhua024-chai-1-full_94469_v104 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4207.91s
Shutdown handler de-registered
junhua024-chai-1-full_94469_v104 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full_94469_v104 status is now torndown due to DeploymentManager action
junhua024-chai-1-full_94469_v104 status is now torndown due to DeploymentManager action