junhua024-chai-1-full-002

developer_uid: junhua024

submission_id: junhua024-chai-1-full-002_v20

model_name: junhua024-chai-1-full-002_v20

model_group: junhua024/chai_1-full_00

status: torndown

timestamp: 2025-06-29T07:42:07+00:00

num_battles: 7166

num_wins: 3302

celo_rating: 1253.56

family_friendly_score: 0.5811999999999999

family_friendly_standard_error: 0.006977199438170017

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': 0.5937685010107008, 'latency_mean': 1.6840420830249787, 'latency_p50': 1.6843100786209106, 'latency_p90': 1.8509771823883057}, {'batch_size': 3, 'throughput': 1.0739501861446588, 'latency_mean': 2.7747109544277193, 'latency_p50': 2.762614607810974, 'latency_p90': 3.0601620435714723}, {'batch_size': 5, 'throughput': 1.296943529435607, 'latency_mean': 3.84090301156044, 'latency_p50': 3.841854453086853, 'latency_p90': 4.282146763801575}, {'batch_size': 6, 'throughput': 1.354012884267876, 'latency_mean': 4.399568222761154, 'latency_p50': 4.35114598274231, 'latency_p90': 4.894116830825805}, {'batch_size': 8, 'throughput': 1.4296623789197989, 'latency_mean': 5.554517447948456, 'latency_p50': 5.5584471225738525, 'latency_p90': 6.297706246376038}, {'batch_size': 10, 'throughput': 1.4562964086837071, 'latency_mean': 6.81234699010849, 'latency_p50': 6.872462034225464, 'latency_p90': 7.643368935585022}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full-002_v20

is_internal_developer: False

language_model: junhua024/chai_1-full_002

model_size: 13B

ranking_group: single

throughput_3p7s: 1.28

us_pacific_date: 2025-06-29

win_ratio: 0.46078704995813563

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': ['<|im_start|>', '\n', '<|im_end|>'], '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-v20-mkmlizer
Waiting for job on junhua024-chai-1-full-002-v20-mkmlizer to finish
junhua024-chai-1-full-002-v20-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-002-v20-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v20-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-002-v20-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-002-v20-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-002-v20-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-002-v20-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-002-v20-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-002-v20-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-002-v20-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-002-v20-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v20-mkmlizer: ║  Version: 0.29.3                                                    ║
junhua024-chai-1-full-002-v20-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-002-v20-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-002-v20-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-002-v20-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v20-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-002-v20-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-002-v20-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v20-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-002-v20-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-002-v20-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-002-v20-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v20-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-002-v20-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-v20-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-v20-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-v20-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-v20-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-v20-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-v20-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-v20-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-v20-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-v20-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-v20-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-v20-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-v20-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-v20-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-v20-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-v20-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-v20-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-v20-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`
Connection pool is full, discarding connection: %s. Connection pool size: %s
junhua024-chai-1-full-002-v20-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-v20-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-v20-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-v20-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-v20-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-v20-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-v20-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-v20-mkmlizer: Downloaded to shared memory in 73.712s
junhua024-chai-1-full-002-v20-mkmlizer: Checking if junhua024/chai_1-full_002 already exists in ChaiML
junhua024-chai-1-full-002-v20-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgo0zu5d_, device:0
junhua024-chai-1-full-002-v20-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-002-v20-mkmlizer: quantized model in 30.711s
junhua024-chai-1-full-002-v20-mkmlizer: Processed model junhua024/chai_1-full_002 in 104.503s
junhua024-chai-1-full-002-v20-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-002-v20-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-002-v20-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-002-v20
junhua024-chai-1-full-002-v20-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v20/config.json
junhua024-chai-1-full-002-v20-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v20/special_tokens_map.json
junhua024-chai-1-full-002-v20-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v20/tokenizer_config.json
junhua024-chai-1-full-002-v20-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-002-v20/flywheel_model.0.safetensors
junhua024-chai-1-full-002-v20-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:21, 16.64it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:19, 18.65it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.03it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:11, 31.37it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 34.00it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 45.54it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:09, 33.09it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:09, 33.97it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 41.78it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:08, 36.21it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:08, 34.34it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 35.42it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 34.49it/s]
Loading 0:  20%|██        | 74/363 [00:02<00:07, 37.33it/s]
Loading 0:  22%|██▏       | 79/363 [00:02<00:07, 35.53it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:07, 36.02it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 40.49it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 40.78it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:08, 31.43it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:07, 32.90it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 41.01it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 35.35it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:06, 34.60it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 36.17it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 34.55it/s]
Loading 0:  38%|███▊      | 138/363 [00:03<00:06, 34.28it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 33.84it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 34.90it/s]
Loading 0:  43%|████▎     | 157/363 [00:04<00:04, 44.05it/s]
Loading 0:  45%|████▍     | 162/363 [00:04<00:05, 33.97it/s]
Loading 0:  46%|████▌     | 167/363 [00:04<00:05, 34.20it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:04, 41.11it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 35.87it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 34.77it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:04, 36.11it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:04, 35.14it/s]
Loading 0:  55%|█████▌    | 200/363 [00:05<00:04, 38.15it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:04, 38.17it/s]
Loading 0:  57%|█████▋    | 208/363 [00:05<00:04, 33.59it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 32.34it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:03, 37.97it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:03, 35.03it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 33.57it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 31.85it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:03, 38.68it/s]
Loading 0:  67%|██████▋   | 243/363 [00:06<00:03, 31.91it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 33.99it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 35.79it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 34.47it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 34.09it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 33.30it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 34.34it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 43.61it/s]
Loading 0:  79%|███████▉  | 288/363 [00:08<00:02, 33.76it/s]
Loading 0:  81%|████████  | 293/363 [00:08<00:02, 33.66it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 40.40it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:01, 34.45it/s]
Loading 0:  86%|████████▌ | 311/363 [00:08<00:01, 33.50it/s]
Loading 0:  87%|████████▋ | 317/363 [00:08<00:01, 35.11it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 34.56it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 34.34it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 33.72it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 35.25it/s]
Loading 0:  95%|█████████▍| 344/363 [00:09<00:00, 40.17it/s]
Loading 0:  96%|█████████▌| 349/363 [00:09<00:00, 27.52it/s]
Loading 0:  97%|█████████▋| 353/363 [00:10<00:00, 25.47it/s]
Loading 0:  98%|█████████▊| 357/363 [00:10<00:00, 27.18it/s]
                                                            
Job junhua024-chai-1-full-002-v20-mkmlizer completed after 128.53s with status: succeeded
Stopping job with name junhua024-chai-1-full-002-v20-mkmlizer
Pipeline stage MKMLizer completed in 129.30s
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-v20
Waiting for inference service junhua024-chai-1-full-002-v20 to be ready
Inference service junhua024-chai-1-full-002-v20 ready after 180.94763660430908s
Pipeline stage MKMLDeployer completed in 182.13s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4078307151794434s
Received healthy response to inference request in 1.8295936584472656s
Received healthy response to inference request in 1.8498387336730957s
Received healthy response to inference request in 1.4502649307250977s
Received healthy response to inference request in 1.8738594055175781s
5 requests
0 failed requests
5th percentile: 1.5261306762695312
10th percentile: 1.6019964218139648
20th percentile: 1.753727912902832
30th percentile: 1.8336426734924316
40th percentile: 1.8417407035827638
50th percentile: 1.8498387336730957
60th percentile: 1.8594470024108887
70th percentile: 1.8690552711486816
80th percentile: 1.9806536674499513
90th percentile: 2.1942421913146974
95th percentile: 2.3010364532470704
99th percentile: 2.386471862792969
mean time: 1.882277488708496
Pipeline stage StressChecker completed in 11.07s
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 0.72s
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 0.75s
Shutdown handler de-registered
junhua024-chai-1-full-002_v20 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 3229.05s
Shutdown handler de-registered
junhua024-chai-1-full-002_v20 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-002_v20 status is now torndown due to DeploymentManager action