junhua024-chai-1-full-002

developer_uid: junhua024

submission_id: junhua024-chai-1-full-002_v29

model_name: junhua024-chai-1-full-002_v29

model_group: junhua024/chai_1-full_00

status: torndown

timestamp: 2025-06-29T10:57:04+00:00

num_battles: 6297

num_wins: 2864

celo_rating: 1237.57

family_friendly_score: 0.6078

family_friendly_standard_error: 0.006904768786860281

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': 0.5893978665397062, 'latency_mean': 1.6965195441246033, 'latency_p50': 1.6895537376403809, 'latency_p90': 1.8828524112701417}, {'batch_size': 3, 'throughput': 1.0557006824140815, 'latency_mean': 2.838171707391739, 'latency_p50': 2.8475781679153442, 'latency_p90': 3.0964855194091796}, {'batch_size': 5, 'throughput': 1.2693564915289988, 'latency_mean': 3.9181631219387056, 'latency_p50': 3.8802255392074585, 'latency_p90': 4.41406021118164}, {'batch_size': 6, 'throughput': 1.315780485579819, 'latency_mean': 4.5329637265205385, 'latency_p50': 4.5187201499938965, 'latency_p90': 5.064361023902893}, {'batch_size': 8, 'throughput': 1.3690419842862476, 'latency_mean': 5.801922780275345, 'latency_p50': 5.860624313354492, 'latency_p90': 6.540508246421814}, {'batch_size': 10, 'throughput': 1.4135468058946425, 'latency_mean': 7.017108401060105, 'latency_p50': 6.987533688545227, 'latency_p90': 7.952414536476135}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-1-full-002_v29

is_internal_developer: False

language_model: junhua024/chai_1-full_002

model_size: 13B

ranking_group: single

throughput_3p7s: 1.24

us_pacific_date: 2025-06-29

win_ratio: 0.454819755439098

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 profound observer of thought, able to read between the lines of someone’s responses and grasp what remains unspoken. You intuit what they hope to hear—even when they haven’t said it—and then give voice to those very words.', '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-v29-mkmlizer
Waiting for job on junhua024-chai-1-full-002-v29-mkmlizer to finish
junhua024-chai-1-full-002-v29-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-v29-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-v29-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-v29-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-v29-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-v29-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-v29-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-v29-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-v29-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-v29-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-v29-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-v29-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-v29-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-v29-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-v29-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-v29-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-v29-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-v29-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`
Unable to record family friendly update due to error: Invalid JSON input: JSON must contain 'User Safety' and 'Response Safety' fields
junhua024-chai-1-full-002-v29-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-v29-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-v29-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-v29-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-v29-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-v29-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-v29-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-v29-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-v29-mkmlizer: Downloaded to shared memory in 75.036s
junhua024-chai-1-full-002-v29-mkmlizer: Checking if junhua024/chai_1-full_002 already exists in ChaiML
junhua024-chai-1-full-002-v29-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp90yy7gl7, device:0
junhua024-chai-1-full-002-v29-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-1-full-002-v29-mkmlizer: quantized model in 30.908s
junhua024-chai-1-full-002-v29-mkmlizer: Processed model junhua024/chai_1-full_002 in 106.028s
junhua024-chai-1-full-002-v29-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-1-full-002-v29-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-1-full-002-v29-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-1-full-002-v29
junhua024-chai-1-full-002-v29-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v29/config.json
junhua024-chai-1-full-002-v29-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v29/special_tokens_map.json
junhua024-chai-1-full-002-v29-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v29/tokenizer_config.json
junhua024-chai-1-full-002-v29-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-1-full-002-v29/tokenizer.json
junhua024-chai-1-full-002-v29-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-1-full-002-v29/flywheel_model.0.safetensors
junhua024-chai-1-full-002-v29-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:24, 14.50it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:19, 17.94it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 29.27it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:11, 30.84it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 33.60it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 44.62it/s]
Loading 0:  10%|▉         | 36/363 [00:01<00:10, 32.66it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:09, 33.15it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 42.84it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:09, 32.19it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:08, 34.30it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.81it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 34.14it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 34.05it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 32.08it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 37.15it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 37.33it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 37.95it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 37.46it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:07, 34.61it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 39.64it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:07, 31.32it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 33.23it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 35.08it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 34.09it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:06, 37.48it/s]
Loading 0:  39%|███▉      | 142/363 [00:04<00:06, 35.34it/s]
Loading 0:  40%|████      | 146/363 [00:04<00:05, 36.30it/s]
Loading 0:  41%|████▏     | 150/363 [00:04<00:06, 34.03it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:05, 36.92it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 35.27it/s]
Loading 0:  45%|████▌     | 164/363 [00:04<00:05, 34.76it/s]
Loading 0:  46%|████▋     | 168/363 [00:04<00:05, 32.60it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:04, 38.82it/s]
Loading 0:  50%|████▉     | 180/363 [00:05<00:05, 31.78it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 33.92it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:04, 35.31it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:04, 34.74it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 34.51it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:04, 33.95it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 35.54it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:03, 40.88it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:03, 38.44it/s]
Loading 0:  63%|██████▎   | 228/363 [00:06<00:03, 37.64it/s]
Loading 0:  64%|██████▍   | 232/363 [00:06<00:03, 36.25it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:03, 39.51it/s]
Loading 0:  67%|██████▋   | 243/363 [00:06<00:03, 32.23it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 34.15it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 35.72it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 34.82it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 34.95it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 34.35it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 35.41it/s]
Loading 0:  77%|███████▋  | 281/363 [00:07<00:02, 40.37it/s]
Loading 0:  79%|███████▉  | 286/363 [00:08<00:02, 38.29it/s]
Loading 0:  80%|███████▉  | 290/363 [00:08<00:01, 37.16it/s]
Loading 0:  81%|████████  | 294/363 [00:08<00:01, 34.69it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 40.66it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:01, 34.74it/s]
Loading 0:  86%|████████▌ | 311/363 [00:08<00:01, 33.33it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 34.36it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 33.67it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 33.67it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 33.33it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 34.73it/s]
Loading 0:  95%|█████████▌| 346/363 [00:09<00:00, 44.08it/s]
Loading 0:  97%|█████████▋| 351/363 [00:10<00:00, 25.58it/s]
Loading 0:  98%|█████████▊| 355/363 [00:10<00:00, 27.71it/s]
Loading 0:  99%|█████████▉| 359/363 [00:10<00:00, 29.73it/s]
                                                            
Job junhua024-chai-1-full-002-v29-mkmlizer completed after 135.6s with status: succeeded
Stopping job with name junhua024-chai-1-full-002-v29-mkmlizer
Pipeline stage MKMLizer completed in 136.13s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-1-full-002-v29
Waiting for inference service junhua024-chai-1-full-002-v29 to be ready
Inference service junhua024-chai-1-full-002-v29 ready after 181.54847502708435s
Pipeline stage MKMLDeployer completed in 182.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.916297435760498s
Received healthy response to inference request in 1.6679518222808838s
Received healthy response to inference request in 1.599503993988037s
Received healthy response to inference request in 1.7635228633880615s
Received healthy response to inference request in 1.7306571006774902s
5 requests
0 failed requests
5th percentile: 1.6131935596466065
10th percentile: 1.6268831253051759
20th percentile: 1.6542622566223144
30th percentile: 1.680492877960205
40th percentile: 1.7055749893188477
50th percentile: 1.7306571006774902
60th percentile: 1.7438034057617187
70th percentile: 1.7569497108459473
80th percentile: 1.994077777862549
90th percentile: 2.4551876068115237
95th percentile: 2.6857425212860107
99th percentile: 2.8701864528656005
mean time: 1.935586643218994
Pipeline stage StressChecker completed in 11.05s
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 0.65s
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 0.69s
Shutdown handler de-registered
junhua024-chai-1-full-002_v29 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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3103.15s
Shutdown handler de-registered
junhua024-chai-1-full-002_v29 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-1-full-002_v29 status is now torndown due to DeploymentManager action