developer_uid: junhua024
submission_id: junhua024-chai-06-full-_59231_v1
model_name: junhua024-chai-06-full-_59231_v1
model_group: junhua024/chai_06_full_0
status: torndown
timestamp: 2025-07-17T18:32:39+00:00
num_battles: 8423
num_wins: 4097
celo_rating: 1272.38
family_friendly_score: 0.5636
family_friendly_standard_error: 0.007013630158484265
submission_type: basic
model_repo: junhua024/chai_06_full_02108_2024
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': 0.5969051173036909, 'latency_mean': 1.6751317632198335, 'latency_p50': 1.6787824630737305, 'latency_p90': 1.8525033712387085}, {'batch_size': 3, 'throughput': 1.0749753384212921, 'latency_mean': 2.7768236196041105, 'latency_p50': 2.7728337049484253, 'latency_p90': 3.0196540355682373}, {'batch_size': 5, 'throughput': 1.2944591338070295, 'latency_mean': 3.8396532213687897, 'latency_p50': 3.8443734645843506, 'latency_p90': 4.3096318483352665}, {'batch_size': 6, 'throughput': 1.3534954165702564, 'latency_mean': 4.401589410305023, 'latency_p50': 4.371663212776184, 'latency_p90': 4.920353841781616}, {'batch_size': 8, 'throughput': 1.4167476042736584, 'latency_mean': 5.601269283294678, 'latency_p50': 5.598566055297852, 'latency_p90': 6.24450569152832}, {'batch_size': 10, 'throughput': 1.4448941185886097, 'latency_mean': 6.864503706693649, 'latency_p50': 6.914478302001953, 'latency_p90': 7.658665037155151}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: junhua024-chai-06-full-_59231_v1
is_internal_developer: False
language_model: junhua024/chai_06_full_02108_2024
model_size: 13B
ranking_group: single
throughput_3p7s: 1.28
us_pacific_date: 2025-07-17
win_ratio: 0.4864062685503977
generation_params: {'temperature': 1.0, '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-06-full-59231-v1-mkmlizer
Waiting for job on junhua024-chai-06-full-59231-v1-mkmlizer to finish
junhua024-chai-06-full-59231-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-06-full-59231-v1-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-06-full-59231-v1-mkmlizer: ║                                                                     ║
junhua024-chai-06-full-59231-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-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-06-full-59231-v1-mkmlizer: Downloaded to shared memory in 128.628s
junhua024-chai-06-full-59231-v1-mkmlizer: Checking if junhua024/chai_06_full_02108_2024 already exists in ChaiML
junhua024-chai-06-full-59231-v1-mkmlizer: Creating repo ChaiML/chai_06_full_02108_2024 and uploading /tmp/tmpu0mzk2c3 to it
Failed to get response for submission junhua024-chai-06-full-_60967_v6: HTTPConnectionPool(host='junhua024-chai-06-full-60967-v6-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-06-full-59231-v1-mkmlizer: 
  0%|          | 0/26 [00:00<?, ?it/s]
  4%|▍         | 1/26 [00:01<00:46,  1.86s/it]
  8%|▊         | 2/26 [00:04<00:56,  2.36s/it]
 12%|█▏        | 3/26 [00:06<00:54,  2.38s/it]
 15%|█▌        | 4/26 [00:09<00:49,  2.26s/it]
 19%|█▉        | 5/26 [00:11<00:45,  2.18s/it]
 23%|██▎       | 6/26 [00:13<00:44,  2.23s/it]
 27%|██▋       | 7/26 [00:14<00:38,  2.00s/it]
 31%|███       | 8/26 [00:17<00:39,  2.20s/it]
 35%|███▍      | 9/26 [00:19<00:33,  1.99s/it]
 38%|███▊      | 10/26 [00:20<00:29,  1.85s/it]
 42%|████▏     | 11/26 [00:22<00:26,  1.76s/it]
 46%|████▌     | 12/26 [00:24<00:25,  1.83s/it]
 50%|█████     | 13/26 [00:25<00:22,  1.75s/it]
 54%|█████▍    | 14/26 [00:32<00:37,  3.13s/it]
 58%|█████▊    | 15/26 [00:33<00:30,  2.75s/it]
 62%|██████▏   | 16/26 [00:35<00:25,  2.53s/it]
 65%|██████▌   | 17/26 [00:37<00:20,  2.28s/it]
 69%|██████▉   | 18/26 [00:39<00:16,  2.02s/it]
 73%|███████▎  | 19/26 [00:40<00:13,  1.89s/it]
 77%|███████▋  | 20/26 [00:42<00:10,  1.76s/it]
 81%|████████  | 21/26 [00:44<00:09,  1.86s/it]
 85%|████████▍ | 22/26 [00:46<00:07,  1.90s/it]
 88%|████████▊ | 23/26 [00:48<00:05,  1.89s/it]
 92%|█████████▏| 24/26 [00:50<00:04,  2.19s/it]
 96%|█████████▌| 25/26 [00:57<00:03,  3.36s/it]
100%|██████████| 26/26 [00:58<00:00,  2.70s/it]
100%|██████████| 26/26 [00:58<00:00,  2.24s/it]
junhua024-chai-06-full-59231-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpu0mzk2c3, device:0
junhua024-chai-06-full-59231-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-06-full-59231-v1-mkmlizer: quantized model in 31.816s
junhua024-chai-06-full-59231-v1-mkmlizer: Processed model junhua024/chai_06_full_02108_2024 in 245.062s
junhua024-chai-06-full-59231-v1-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-06-full-59231-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-06-full-59231-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-06-full-59231-v1/nvidia
junhua024-chai-06-full-59231-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-06-full-59231-v1/nvidia/config.json
junhua024-chai-06-full-59231-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-06-full-59231-v1/nvidia/special_tokens_map.json
junhua024-chai-06-full-59231-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-06-full-59231-v1/nvidia/tokenizer_config.json
junhua024-chai-06-full-59231-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-06-full-59231-v1/nvidia/tokenizer.json
Job junhua024-chai-06-full-59231-v1-mkmlizer completed after 274.13s with status: succeeded
Stopping job with name junhua024-chai-06-full-59231-v1-mkmlizer
Pipeline stage MKMLizer completed in 274.68s
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-06-full-59231-v1
Waiting for inference service junhua024-chai-06-full-59231-v1 to be ready
Failed to get response for submission blend_fader_2025-07-10: HTTPConnectionPool(host='chaiml-anthropic-40k-2-11629-v13-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7d15e455dd10>: Failed to establish a new connection: [Errno -3] Temporary failure in name resolution'))
Inference service junhua024-chai-06-full-59231-v1 ready after 302.11886715888977s
Pipeline stage MKMLDeployer completed in 303.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.696744680404663s
Received healthy response to inference request in 1.770409107208252s
Received healthy response to inference request in 1.867875576019287s
Received healthy response to inference request in 1.7434191703796387s
Received healthy response to inference request in 1.7177915573120117s
5 requests
0 failed requests
5th percentile: 1.722917079925537
10th percentile: 1.7280426025390625
20th percentile: 1.7382936477661133
30th percentile: 1.7488171577453613
40th percentile: 1.7596131324768067
50th percentile: 1.770409107208252
60th percentile: 1.809395694732666
70th percentile: 1.8483822822570801
80th percentile: 2.0336493968963625
90th percentile: 2.365197038650513
95th percentile: 2.5309708595275877
99th percentile: 2.663589916229248
mean time: 1.9592480182647705
Pipeline stage StressChecker completed in 11.53s
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 0.80s
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 0.86s
Shutdown handler de-registered
junhua024-chai-06-full-_59231_v1 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 4723.23s
Shutdown handler de-registered
junhua024-chai-06-full-_59231_v1 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-06-full-_59231_v1 status is now torndown due to DeploymentManager action
junhua024-chai-06-full-_59231_v1 status is now torndown due to DeploymentManager action