developer_uid: junhua024
submission_id: junhua024-chai-1-full-066126_v84
model_name: junhua024-chai-1-full-066126_v84
model_group: junhua024/chai-1-full-06
status: torndown
timestamp: 2025-07-15T19:10:16+00:00
num_battles: 8918
num_wins: 4373
celo_rating: 1283.04
family_friendly_score: 0.5548
family_friendly_standard_error: 0.007028470103799261
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': 0.6033961947570184, 'latency_mean': 1.6571342062950134, 'latency_p50': 1.6394718885421753, 'latency_p90': 1.8416138410568237}, {'batch_size': 3, 'throughput': 1.0621011115292947, 'latency_mean': 2.810752645730972, 'latency_p50': 2.8188838958740234, 'latency_p90': 3.123464488983154}, {'batch_size': 5, 'throughput': 1.2852381121038536, 'latency_mean': 3.8719751369953155, 'latency_p50': 3.892444372177124, 'latency_p90': 4.364796233177185}, {'batch_size': 6, 'throughput': 1.3434834898839405, 'latency_mean': 4.439151210784912, 'latency_p50': 4.4177786111831665, 'latency_p90': 4.993555164337158}, {'batch_size': 8, 'throughput': 1.411510041192628, 'latency_mean': 5.62842138171196, 'latency_p50': 5.615530729293823, 'latency_p90': 6.316859126091003}, {'batch_size': 10, 'throughput': 1.4220206738208516, 'latency_mean': 6.9839601075649265, 'latency_p50': 7.031026363372803, 'latency_p90': 7.746408820152283}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: junhua024-chai-1-full-066126_v84
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: 0.4903565821933169
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': '{memory} What nuanced feelings lie behind these words?', '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-066126-v84-mkmlizer
Waiting for job on junhua024-chai-1-full-066126-v84-mkmlizer to finish
junhua024-chai-1-full-066126-v84-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-066126-v84-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-066126-v84-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-066126-v84-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-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-066126-v84-mkmlizer: Downloaded to shared memory in 77.032s
junhua024-chai-1-full-066126-v84-mkmlizer: Checking if junhua024/chai-1-full-066126 already exists in ChaiML
junhua024-chai-1-full-066126-v84-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplzppazyl, device:0
junhua024-chai-1-full-066126-v84-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-066126-v84-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-066126-v84-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-066126-v84-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v84/nvidia
junhua024-chai-1-full-066126-v84-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v84/nvidia/config.json
junhua024-chai-1-full-066126-v84-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v84/nvidia/special_tokens_map.json
junhua024-chai-1-full-066126-v84-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v84/nvidia/tokenizer_config.json
junhua024-chai-1-full-066126-v84-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-066126-v84/nvidia/tokenizer.json
Job junhua024-chai-1-full-066126-v84-mkmlizer completed after 137.73s with status: succeeded
Stopping job with name junhua024-chai-1-full-066126-v84-mkmlizer
Pipeline stage MKMLizer completed in 138.30s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-1-full-066126-v84
Waiting for inference service junhua024-chai-1-full-066126-v84 to be ready
Failed to get response for submission junhua024-chai-1-full-066126_v80: ('http://junhua024-chai-1-full-066126-v80-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:53774->127.0.0.1:8080: read: connection reset by peer\n')
Inference service junhua024-chai-1-full-066126-v84 ready after 251.6670081615448s
Pipeline stage MKMLDeployer completed in 252.11s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
{"detail":"HTTPConnectionPool(host='junhua024-chai-1-full-066126-v84-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7a02b41b5310>, 'Connection to junhua024-chai-1-full-066126-v84-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))"}
Received unhealthy response to inference request!
Received healthy response to inference request in 2.519170045852661s
Received healthy response to inference request in 2.3974826335906982s
Received healthy response to inference request in 1.9896876811981201s
5 requests
2 failed requests
5th percentile: 2.0712466716766356
10th percentile: 2.1528056621551515
20th percentile: 2.315923643112183
30th percentile: 2.421820116043091
40th percentile: 2.470495080947876
50th percentile: 2.519170045852661
60th percentile: 6.422295999526977
70th percentile: 10.325421953201293
80th percentile: 13.848935699462892
90th percentile: 16.99283723831177
95th percentile: 18.564788007736205
99th percentile: 19.822348623275758
mean time: 7.864012813568115
%s, retrying in %s seconds...
Received healthy response to inference request in 1.5372271537780762s
Received healthy response to inference request in 1.699265956878662s
Received healthy response to inference request in 1.7253086566925049s
Received healthy response to inference request in 1.6171960830688477s
Received healthy response to inference request in 1.9287021160125732s
5 requests
0 failed requests
5th percentile: 1.5532209396362304
10th percentile: 1.5692147254943847
20th percentile: 1.6012022972106934
30th percentile: 1.6336100578308106
40th percentile: 1.6664380073547362
50th percentile: 1.699265956878662
60th percentile: 1.7096830368041993
70th percentile: 1.7201001167297363
80th percentile: 1.7659873485565185
90th percentile: 1.847344732284546
95th percentile: 1.8880234241485596
99th percentile: 1.9205663776397706
mean time: 1.7015399932861328
Pipeline stage StressChecker completed in 50.56s
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 0.68s
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 0.84s
Shutdown handler de-registered
junhua024-chai-1-full-066126_v84 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 8216.69s
Shutdown handler de-registered
junhua024-chai-1-full-066126_v84 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-066126_v84 status is now torndown due to DeploymentManager action
junhua024-chai-1-full-066126_v84 status is now torndown due to DeploymentManager action