developer_uid: junhua024
submission_id: junhua024-chai-16-full-_74386_v1
model_name: junhua024-chai-16-full-_74386_v1
model_group: junhua024/chai_16_full_1
status: torndown
timestamp: 2025-07-19T14:13:16+00:00
num_battles: 7058
num_wins: 3564
celo_rating: 1275.66
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: junhua024/chai_16_full_102_o_ffn_1925
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': 0.5952954837569333, 'latency_mean': 1.6796945822238922, 'latency_p50': 1.6767817735671997, 'latency_p90': 1.8605375051498414}, {'batch_size': 3, 'throughput': 1.051743675784397, 'latency_mean': 2.8494730579853056, 'latency_p50': 2.849293351173401, 'latency_p90': 3.115987205505371}, {'batch_size': 5, 'throughput': 1.2723263400043265, 'latency_mean': 3.9095641696453094, 'latency_p50': 3.897208571434021, 'latency_p90': 4.345053100585938}, {'batch_size': 6, 'throughput': 1.3340740056293683, 'latency_mean': 4.4715655374526975, 'latency_p50': 4.48758327960968, 'latency_p90': 4.97797200679779}, {'batch_size': 8, 'throughput': 1.3869331466322867, 'latency_mean': 5.723298933506012, 'latency_p50': 5.739246726036072, 'latency_p90': 6.438833022117615}, {'batch_size': 10, 'throughput': 1.4300955574701635, 'latency_mean': 6.944422036409378, 'latency_p50': 6.936695694923401, 'latency_p90': 7.80252480506897}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: junhua024-chai-16-full-_74386_v1
is_internal_developer: False
language_model: junhua024/chai_16_full_102_o_ffn_1925
model_size: 13B
ranking_group: single
throughput_3p7s: 1.24
us_pacific_date: 2025-07-19
win_ratio: 0.5049589118730519
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-16-full-74386-v1-mkmlizer
Waiting for job on junhua024-chai-16-full-74386-v1-mkmlizer to finish
junhua024-chai-16-full-74386-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-16-full-74386-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-16-full-74386-v1-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-74386-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-16-full-74386-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-16-full-74386-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-16-full-74386-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-16-full-74386-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-16-full-74386-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-16-full-74386-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-16-full-74386-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-16-full-74386-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-16-full-74386-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`
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-16-full-74386-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-16-full-74386-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-16-full-74386-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-16-full-74386-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-16-full-74386-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-16-full-74386-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-16-full-74386-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-16-full-74386-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-16-full-74386-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`
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-16-full-74386-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-16-full-74386-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-16-full-74386-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-16-full-74386-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-16-full-74386-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-16-full-74386-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-16-full-74386-v1-mkmlizer: Downloaded to shared memory in 130.739s
junhua024-chai-16-full-74386-v1-mkmlizer: Checking if junhua024/chai_16_full_102_o_ffn_1925 already exists in ChaiML
junhua024-chai-16-full-74386-v1-mkmlizer: Creating repo ChaiML/chai_16_full_102_o_ffn_1925 and uploading /tmp/tmp40kz3t89 to it
Failed to get response for submission junhua024-chai-16-full-_68541_v3: HTTPConnectionPool(host='junhua024-chai-16-full-68541-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-16-full-74386-v1-mkmlizer: 
  0%|          | 0/26 [00:00<?, ?it/s]
  4%|▍         | 1/26 [00:01<00:37,  1.49s/it]
  8%|▊         | 2/26 [00:03<00:47,  1.97s/it]
 12%|█▏        | 3/26 [00:06<00:55,  2.39s/it]
 15%|█▌        | 4/26 [00:09<00:55,  2.54s/it]
 19%|█▉        | 5/26 [00:11<00:46,  2.21s/it]
 23%|██▎       | 6/26 [00:12<00:38,  1.92s/it]
 27%|██▋       | 7/26 [00:13<00:33,  1.77s/it]
 31%|███       | 8/26 [00:15<00:32,  1.82s/it]
 35%|███▍      | 9/26 [00:17<00:30,  1.79s/it]
 38%|███▊      | 10/26 [00:18<00:26,  1.65s/it]
 42%|████▏     | 11/26 [00:20<00:24,  1.61s/it]
 46%|████▌     | 12/26 [00:21<00:21,  1.52s/it]
 50%|█████     | 13/26 [00:24<00:23,  1.79s/it]
 54%|█████▍    | 14/26 [00:25<00:20,  1.71s/it]
 58%|█████▊    | 15/26 [00:27<00:18,  1.66s/it]
 62%|██████▏   | 16/26 [00:28<00:16,  1.64s/it]
 65%|██████▌   | 17/26 [00:30<00:16,  1.78s/it]
 69%|██████▉   | 18/26 [00:35<00:20,  2.51s/it]
 73%|███████▎  | 19/26 [00:36<00:15,  2.23s/it]
 77%|███████▋  | 20/26 [00:38<00:11,  1.99s/it]
 81%|████████  | 21/26 [00:39<00:09,  1.81s/it]
 85%|████████▍ | 22/26 [00:41<00:06,  1.74s/it]
 88%|████████▊ | 23/26 [00:42<00:05,  1.75s/it]
 92%|█████████▏| 24/26 [00:44<00:03,  1.84s/it]
 96%|█████████▌| 25/26 [00:47<00:01,  1.99s/it]
100%|██████████| 26/26 [00:48<00:00,  1.76s/it]
100%|██████████| 26/26 [00:48<00:00,  1.86s/it]
junhua024-chai-16-full-74386-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp40kz3t89, device:0
junhua024-chai-16-full-74386-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-16-full-74386-v1-mkmlizer: quantized model in 31.229s
junhua024-chai-16-full-74386-v1-mkmlizer: Processed model junhua024/chai_16_full_102_o_ffn_1925 in 236.876s
junhua024-chai-16-full-74386-v1-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-16-full-74386-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-16-full-74386-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-16-full-74386-v1/nvidia
junhua024-chai-16-full-74386-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-16-full-74386-v1/nvidia/config.json
junhua024-chai-16-full-74386-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-16-full-74386-v1/nvidia/special_tokens_map.json
junhua024-chai-16-full-74386-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-16-full-74386-v1/nvidia/tokenizer_config.json
junhua024-chai-16-full-74386-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-16-full-74386-v1/nvidia/tokenizer.json
Job junhua024-chai-16-full-74386-v1-mkmlizer completed after 264.19s with status: succeeded
Stopping job with name junhua024-chai-16-full-74386-v1-mkmlizer
Pipeline stage MKMLizer completed in 265.03s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-16-full-74386-v1
Waiting for inference service junhua024-chai-16-full-74386-v1 to be ready
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-16-full-74386-v1 ready after 331.5200283527374s
Pipeline stage MKMLDeployer completed in 332.14s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8741025924682617s
Received healthy response to inference request in 1.797795295715332s
Received healthy response to inference request in 2.092193365097046s
Received healthy response to inference request in 2.085369348526001s
Received healthy response to inference request in 1.796851396560669s
5 requests
0 failed requests
5th percentile: 1.7970401763916015
10th percentile: 1.797228956222534
20th percentile: 1.7976065158843995
30th percentile: 1.8553101062774657
40th percentile: 1.9703397274017334
50th percentile: 2.085369348526001
60th percentile: 2.088098955154419
70th percentile: 2.090828561782837
80th percentile: 2.248575210571289
90th percentile: 2.5613389015197754
95th percentile: 2.7177207469940186
99th percentile: 2.842826223373413
mean time: 2.129262399673462
Pipeline stage StressChecker completed in 12.48s
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 0.70s
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 0.78s
Shutdown handler de-registered
junhua024-chai-16-full-_74386_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
junhua024-chai-16-full-_74386_v1 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-16-full-_74386_v1 status is now torndown due to DeploymentManager action