junhua024-chai-1-full_94469

developer_uid: junhua024

submission_id: junhua024-chai-1-full_94469_v101

model_name: junhua024-chai-1-full_94469_v101

model_group: junhua024/chai-1-full-06

status: torndown

timestamp: 2025-07-16T04:09:11+00:00

num_battles: 7386

num_wins: 3495

celo_rating: 1263.67

family_friendly_score: 0.5648

family_friendly_standard_error: 0.007011432949119602

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': 0.5939882596632319, 'latency_mean': 1.6833476042747497, 'latency_p50': 1.6736277341842651, 'latency_p90': 1.8544448614120483}, {'batch_size': 3, 'throughput': 1.070390227709692, 'latency_mean': 2.7940105211734774, 'latency_p50': 2.8054826259613037, 'latency_p90': 3.069709038734436}, {'batch_size': 5, 'throughput': 1.2816131574229717, 'latency_mean': 3.8730752885341646, 'latency_p50': 3.8839378356933594, 'latency_p90': 4.3343956708908085}, {'batch_size': 6, 'throughput': 1.3412205219501314, 'latency_mean': 4.44295417189598, 'latency_p50': 4.399943113327026, 'latency_p90': 5.012401747703552}, {'batch_size': 8, 'throughput': 1.4052150965802865, 'latency_mean': 5.660150725841522, 'latency_p50': 5.676993489265442, 'latency_p90': 6.293896460533142}, {'batch_size': 10, 'throughput': 1.4336423106487013, 'latency_mean': 6.916106736660003, 'latency_p50': 6.916937708854675, 'latency_p90': 7.8535367250442505}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full_94469_v101

is_internal_developer: False

language_model: junhua024/chai-1-full-066126

model_size: 13B

ranking_group: single

throughput_3p7s: 1.26

us_pacific_date: 2025-07-15

win_ratio: 0.4731925264012998

generation_params: {'temperature': 1.0, 'top_p': 0.4, '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-v101-mkmlizer
Waiting for job on junhua024-chai-1-full-94469-v101-mkmlizer to finish
junhua024-chai-1-full-94469-v101-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-94469-v101-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-94469-v101-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-94469-v101-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-94469-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-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-v101-mkmlizer: Downloaded to shared memory in 77.621s
junhua024-chai-1-full-94469-v101-mkmlizer: Checking if junhua024/chai-1-full-066126 already exists in ChaiML
junhua024-chai-1-full-94469-v101-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkkrxp28s, device:0
junhua024-chai-1-full-94469-v101-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-94469-v101-mkmlizer: quantized model in 31.758s
junhua024-chai-1-full-94469-v101-mkmlizer: Processed model junhua024/chai-1-full-066126 in 109.462s
junhua024-chai-1-full-94469-v101-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-94469-v101-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-94469-v101-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-94469-v101/nvidia
junhua024-chai-1-full-94469-v101-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-94469-v101/nvidia/config.json
junhua024-chai-1-full-94469-v101-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-94469-v101/nvidia/special_tokens_map.json
junhua024-chai-1-full-94469-v101-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-94469-v101/nvidia/tokenizer_config.json
junhua024-chai-1-full-94469-v101-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-94469-v101/nvidia/flywheel_model.0.safetensors
junhua024-chai-1-full-94469-v101-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:24, 14.48it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:20, 17.11it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:13, 26.71it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:12, 27.57it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:11, 30.30it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:08, 41.44it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:10, 31.00it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:10, 32.19it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 40.23it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:09, 33.80it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 32.53it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:08, 34.36it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 33.45it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:09, 31.75it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:08, 33.08it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:08, 31.16it/s]
Loading 0:  24%|██▍       | 87/363 [00:02<00:08, 32.02it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:09, 29.58it/s]
Loading 0:  27%|██▋       | 97/363 [00:03<00:08, 31.76it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:08, 31.92it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:08, 29.92it/s]
Loading 0:  31%|███       | 112/363 [00:03<00:06, 38.93it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:08, 28.35it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:08, 29.42it/s]
Loading 0:  35%|███▌      | 128/363 [00:04<00:07, 32.02it/s]
Loading 0:  36%|███▋      | 132/363 [00:04<00:07, 31.30it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 32.53it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 32.71it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 33.14it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:04, 42.44it/s]
Loading 0:  45%|████▍     | 162/363 [00:05<00:06, 32.72it/s]
Loading 0:  46%|████▌     | 167/363 [00:05<00:05, 33.54it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:04, 41.60it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 34.78it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 32.94it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 34.39it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:05, 33.27it/s]
Loading 0:  55%|█████▌    | 201/363 [00:06<00:04, 33.39it/s]
Loading 0:  57%|█████▋    | 206/363 [00:06<00:04, 33.02it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 34.04it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:03, 39.10it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:03, 37.17it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:03, 36.59it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:03, 34.28it/s]
Loading 0:  66%|██████▌   | 239/363 [00:07<00:03, 41.29it/s]
Loading 0:  67%|██████▋   | 244/363 [00:07<00:03, 34.92it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 34.54it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:02, 36.35it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 34.97it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 35.40it/s]
Loading 0:  74%|███████▍  | 269/363 [00:08<00:02, 34.91it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:02, 35.71it/s]
Loading 0:  78%|███████▊  | 282/363 [00:08<00:01, 43.11it/s]
Loading 0:  79%|███████▉  | 287/363 [00:08<00:01, 38.23it/s]
Loading 0:  80%|████████  | 292/363 [00:08<00:01, 37.41it/s]
Loading 0:  82%|████████▏ | 296/363 [00:08<00:01, 36.14it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 37.55it/s]
Loading 0:  84%|████████▍ | 306/363 [00:09<00:01, 30.00it/s]
Loading 0:  86%|████████▌ | 311/363 [00:09<00:01, 32.02it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 34.25it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 33.28it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 33.85it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 33.50it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 34.56it/s]
Loading 0:  95%|█████████▍| 344/363 [00:10<00:00, 39.63it/s]
Loading 0:  96%|█████████▌| 349/363 [00:10<00:00, 26.78it/s]
Loading 0:  97%|█████████▋| 353/363 [00:10<00:00, 24.42it/s]
Loading 0:  98%|█████████▊| 357/363 [00:10<00:00, 26.15it/s]
                                                            
Job junhua024-chai-1-full-94469-v101-mkmlizer completed after 130.6s with status: succeeded
Stopping job with name junhua024-chai-1-full-94469-v101-mkmlizer
Pipeline stage MKMLizer completed in 131.40s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-1-full-94469-v101
Waiting for inference service junhua024-chai-1-full-94469-v101 to be ready
Inference service junhua024-chai-1-full-94469-v101 ready after 271.45731830596924s
Pipeline stage MKMLDeployer completed in 272.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2823867797851562s
Received healthy response to inference request in 1.5861492156982422s
Received healthy response to inference request in 1.5103504657745361s
Received healthy response to inference request in 1.7863807678222656s
Received healthy response to inference request in 1.6139922142028809s
5 requests
0 failed requests
5th percentile: 1.5255102157592773
10th percentile: 1.5406699657440186
20th percentile: 1.570989465713501
30th percentile: 1.59171781539917
40th percentile: 1.6028550148010254
50th percentile: 1.6139922142028809
60th percentile: 1.6829476356506348
70th percentile: 1.7519030570983887
80th percentile: 1.8855819702148438
90th percentile: 2.083984375
95th percentile: 2.183185577392578
99th percentile: 2.2625465393066406
mean time: 1.7558518886566161
Pipeline stage StressChecker completed in 10.23s
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 0.78s
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 1.01s
Shutdown handler de-registered
junhua024-chai-1-full_94469_v101 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 3066.54s
Shutdown handler de-registered
junhua024-chai-1-full_94469_v101 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full_94469_v101 status is now torndown due to DeploymentManager action
junhua024-chai-1-full_94469_v101 status is now torndown due to DeploymentManager action