developer_uid: junhua024
submission_id: junhua024-chai-1-full-002_v31
model_name: junhua024-chai-1-full-002_v31
model_group: junhua024/chai_1-full_00
status: torndown
timestamp: 2025-06-29T11:15:29+00:00
num_battles: 8069
num_wins: 3648
celo_rating: 1244.76
family_friendly_score: 0.5982000000000001
family_friendly_standard_error: 0.0069333507051064424
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': 0.5939881822734561, 'latency_mean': 1.6833610260486602, 'latency_p50': 1.6788873672485352, 'latency_p90': 1.8578989028930664}, {'batch_size': 3, 'throughput': 1.0794086454708178, 'latency_mean': 2.7672242450714113, 'latency_p50': 2.75453519821167, 'latency_p90': 3.0627368927001952}, {'batch_size': 5, 'throughput': 1.2930954564480175, 'latency_mean': 3.8456638860702514, 'latency_p50': 3.8502883911132812, 'latency_p90': 4.240335512161255}, {'batch_size': 6, 'throughput': 1.3602858933385875, 'latency_mean': 4.389772518873214, 'latency_p50': 4.418136119842529, 'latency_p90': 4.973739075660705}, {'batch_size': 8, 'throughput': 1.4095126727579728, 'latency_mean': 5.638348997831344, 'latency_p50': 5.668090343475342, 'latency_p90': 6.30636773109436}, {'batch_size': 10, 'throughput': 1.4561349106683974, 'latency_mean': 6.807092700004578, 'latency_p50': 6.780392646789551, 'latency_p90': 7.6194373846054075}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: junhua024-chai-1-full-002_v31
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: 0.452100632048581
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': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '{memory}\n You are a humble conversationalist; every sentence you utter should make the other person think you’re capable of being quite dumb.', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{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-v31-mkmlizer
Waiting for job on junhua024-chai-1-full-002-v31-mkmlizer to finish
junhua024-chai-1-full-002-v31-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-002-v31-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v31-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-002-v31-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-002-v31-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-002-v31-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-002-v31-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-002-v31-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-002-v31-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-002-v31-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-002-v31-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v31-mkmlizer: ║  Version: 0.29.3                                                    ║
junhua024-chai-1-full-002-v31-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-002-v31-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-002-v31-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-002-v31-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v31-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-002-v31-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-002-v31-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v31-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-002-v31-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-002-v31-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-002-v31-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-002-v31-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-002-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-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-v31-mkmlizer: Downloaded to shared memory in 74.704s
junhua024-chai-1-full-002-v31-mkmlizer: Checking if junhua024/chai_1-full_002 already exists in ChaiML
junhua024-chai-1-full-002-v31-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnk_glc_y, device:0
junhua024-chai-1-full-002-v31-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-002-v31-mkmlizer: quantized model in 31.423s
junhua024-chai-1-full-002-v31-mkmlizer: Processed model junhua024/chai_1-full_002 in 106.230s
junhua024-chai-1-full-002-v31-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-002-v31-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-002-v31-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-002-v31
junhua024-chai-1-full-002-v31-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v31/config.json
junhua024-chai-1-full-002-v31-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v31/special_tokens_map.json
junhua024-chai-1-full-002-v31-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v31/tokenizer_config.json
junhua024-chai-1-full-002-v31-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v31/tokenizer.json
junhua024-chai-1-full-002-v31-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-002-v31/flywheel_model.0.safetensors
Job junhua024-chai-1-full-002-v31-mkmlizer completed after 137.96s with status: succeeded
Stopping job with name junhua024-chai-1-full-002-v31-mkmlizer
Pipeline stage MKMLizer completed in 138.51s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-1-full-002-v31
Waiting for inference service junhua024-chai-1-full-002-v31 to be ready
Failed to get response for submission junhua024-chai-1-full-002_v30: HTTPConnectionPool(host='junhua024-chai-1-full-002-v30-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Unable to record family friendly update due to error: Invalid JSON input: Expecting value: line 1 column 43 (char 42)
Failed to get response for submission junhua024-chai-1-full-002_v29: ('http://junhua024-chai-1-full-002-v29-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:40624->127.0.0.1:8080: read: connection reset by peer\n')
Inference service junhua024-chai-1-full-002-v31 ready after 371.5703778266907s
Pipeline stage MKMLDeployer completed in 372.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1991565227508545s
Received healthy response to inference request in 1.7598636150360107s
Received healthy response to inference request in 1.9411933422088623s
Received healthy response to inference request in 1.850940227508545s
Received healthy response to inference request in 2.0836946964263916s
5 requests
0 failed requests
5th percentile: 1.7780789375305175
10th percentile: 1.7962942600250245
20th percentile: 1.8327249050140382
30th percentile: 1.8689908504486084
40th percentile: 1.9050920963287354
50th percentile: 1.9411933422088623
60th percentile: 1.998193883895874
70th percentile: 2.0551944255828856
80th percentile: 2.1067870616912843
90th percentile: 2.152971792221069
95th percentile: 2.176064157485962
99th percentile: 2.194538049697876
mean time: 1.9669696807861328
Pipeline stage StressChecker completed in 11.26s
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 0.77s
Shutdown handler de-registered
junhua024-chai-1-full-002_v31 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service junhua024-chai-1-full-002-v31-profiler
Waiting for inference service junhua024-chai-1-full-002-v31-profiler to be ready
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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2386.99s
Shutdown handler de-registered
junhua024-chai-1-full-002_v31 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-002_v31 status is now torndown due to DeploymentManager action