developer_uid: junhua024
submission_id: junhua024-chai-1-full-00220_v1
model_name: junhua024-chai-1-full-00220_v1
model_group: junhua024/chai_1-full_00
status: torndown
timestamp: 2025-06-28T16:44:24+00:00
num_battles: 8180
num_wins: 3784
celo_rating: 1253.29
family_friendly_score: 0.5922000000000001
family_friendly_standard_error: 0.006949808054903387
submission_type: basic
model_repo: junhua024/chai_1-full_00220
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': 0.6076026425806389, 'latency_mean': 1.6457036864757537, 'latency_p50': 1.6452045440673828, 'latency_p90': 1.8023613929748534}, {'batch_size': 3, 'throughput': 1.0870428792794484, 'latency_mean': 2.7429034161567687, 'latency_p50': 2.731065273284912, 'latency_p90': 2.9869595527648927}, {'batch_size': 5, 'throughput': 1.3107482712017744, 'latency_mean': 3.806087779998779, 'latency_p50': 3.796548366546631, 'latency_p90': 4.236751222610474}, {'batch_size': 6, 'throughput': 1.368154577631663, 'latency_mean': 4.3518861591815945, 'latency_p50': 4.333468437194824, 'latency_p90': 4.8395007133483885}, {'batch_size': 8, 'throughput': 1.4344059813745589, 'latency_mean': 5.5267582809925075, 'latency_p50': 5.562810897827148, 'latency_p90': 6.171759057044983}, {'batch_size': 10, 'throughput': 1.4742960828604155, 'latency_mean': 6.731411496400833, 'latency_p50': 6.765092611312866, 'latency_p90': 7.733507513999939}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: junhua024-chai-1-full-00220_v1
is_internal_developer: False
language_model: junhua024/chai_1-full_00220
model_size: 13B
ranking_group: single
throughput_3p7s: 1.3
us_pacific_date: 2025-06-28
win_ratio: 0.4625916870415648
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, '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': "{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-00220-v1-mkmlizer
Waiting for job on junhua024-chai-1-full-00220-v1-mkmlizer to finish
junhua024-chai-1-full-00220-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-1-full-00220-v1-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-1-full-00220-v1-mkmlizer: ║                                                                     ║
junhua024-chai-1-full-00220-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-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-1-full-00220-v1-mkmlizer: Downloaded to shared memory in 140.641s
junhua024-chai-1-full-00220-v1-mkmlizer: Checking if junhua024/chai_1-full_00220 already exists in ChaiML
junhua024-chai-1-full-00220-v1-mkmlizer: Creating repo ChaiML/chai_1-full_00220 and uploading /tmp/tmpom3p3n2k to it
junhua024-chai-1-full-00220-v1-mkmlizer: 
  0%|          | 0/26 [00:00<?, ?it/s]
  4%|▍         | 1/26 [00:01<00:36,  1.47s/it]
  8%|▊         | 2/26 [00:02<00:34,  1.44s/it]
 12%|█▏        | 3/26 [00:06<00:58,  2.53s/it]
 15%|█▌        | 4/26 [00:08<00:46,  2.12s/it]
 19%|█▉        | 5/26 [00:09<00:39,  1.87s/it]
 23%|██▎       | 6/26 [00:11<00:34,  1.72s/it]
 27%|██▋       | 7/26 [00:12<00:30,  1.61s/it]
 31%|███       | 8/26 [00:18<00:55,  3.06s/it]
 35%|███▍      | 9/26 [00:20<00:43,  2.57s/it]
 38%|███▊      | 10/26 [00:22<00:38,  2.43s/it]
 42%|████▏     | 11/26 [00:23<00:32,  2.15s/it]
 46%|████▌     | 12/26 [00:25<00:26,  1.92s/it]
 50%|█████     | 13/26 [00:26<00:23,  1.80s/it]
 54%|█████▍    | 14/26 [00:28<00:20,  1.71s/it]
 58%|█████▊    | 15/26 [00:29<00:17,  1.63s/it]
 62%|██████▏   | 16/26 [00:31<00:16,  1.63s/it]
 65%|██████▌   | 17/26 [00:37<00:27,  3.01s/it]
 69%|██████▉   | 18/26 [00:38<00:20,  2.51s/it]
 73%|███████▎  | 19/26 [00:41<00:18,  2.68s/it]
 77%|███████▋  | 20/26 [00:44<00:15,  2.57s/it]
 81%|████████  | 21/26 [00:45<00:11,  2.27s/it]
 85%|████████▍ | 22/26 [00:47<00:08,  2.05s/it]
 88%|████████▊ | 23/26 [00:48<00:05,  1.87s/it]
 92%|█████████▏| 24/26 [00:50<00:03,  1.75s/it]
 96%|█████████▌| 25/26 [00:51<00:01,  1.65s/it]
100%|██████████| 26/26 [00:52<00:00,  1.55s/it]
100%|██████████| 26/26 [00:52<00:00,  2.04s/it]
junhua024-chai-1-full-00220-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpom3p3n2k, device:0
junhua024-chai-1-full-00220-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-00220-v1-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-00220-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-00220-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-00220-v1
junhua024-chai-1-full-00220-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-00220-v1/config.json
junhua024-chai-1-full-00220-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-00220-v1/special_tokens_map.json
junhua024-chai-1-full-00220-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-00220-v1/tokenizer_config.json
junhua024-chai-1-full-00220-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-00220-v1/tokenizer.json
junhua024-chai-1-full-00220-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-00220-v1/flywheel_model.0.safetensors
Job junhua024-chai-1-full-00220-v1-mkmlizer completed after 280.66s with status: succeeded
Stopping job with name junhua024-chai-1-full-00220-v1-mkmlizer
Pipeline stage MKMLizer completed in 281.23s
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-1-full-00220-v1
Waiting for inference service junhua024-chai-1-full-00220-v1 to be ready
Inference service junhua024-chai-1-full-00220-v1 ready after 170.57239055633545s
Pipeline stage MKMLDeployer completed in 171.17s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3599042892456055s
Received healthy response to inference request in 1.5284521579742432s
Received healthy response to inference request in 1.976794719696045s
Received healthy response to inference request in 1.5189402103424072s
Received healthy response to inference request in 1.4378180503845215s
5 requests
0 failed requests
5th percentile: 1.4540424823760987
10th percentile: 1.4702669143676759
20th percentile: 1.50271577835083
30th percentile: 1.5208425998687745
40th percentile: 1.5246473789215087
50th percentile: 1.5284521579742432
60th percentile: 1.7077891826629639
70th percentile: 1.8871262073516846
80th percentile: 2.053416633605957
90th percentile: 2.2066604614257814
95th percentile: 2.2832823753356934
99th percentile: 2.3445799064636232
mean time: 1.7643818855285645
Pipeline stage StressChecker completed in 10.54s
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 0.77s
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 1.13s
Shutdown handler de-registered
junhua024-chai-1-full-00220_v1 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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service junhua024-chai-1-full-00220-v1-profiler
Waiting for inference service junhua024-chai-1-full-00220-v1-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 5610.96s
Shutdown handler de-registered
junhua024-chai-1-full-00220_v1 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-00220_v1 status is now torndown due to DeploymentManager action