albertwang8192-2025-07-11-5

developer_uid: RandomForest1024

submission_id: albertwang8192-2025-07-11-5_v1

model_name: 2025-07-11_5

model_group: AlbertWang8192/2025-07-1

status: torndown

timestamp: 2025-07-11T21:35:07+00:00

num_battles: 8807

num_wins: 4142

celo_rating: 1268.46

family_friendly_score: 0.5232

family_friendly_standard_error: 0.007063451847361883

submission_type: basic

model_repo: AlbertWang8192/2025-07-11_5

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': 0.5908981935953174, 'latency_mean': 1.6921833276748657, 'latency_p50': 1.6820231676101685, 'latency_p90': 1.877629280090332}, {'batch_size': 3, 'throughput': 1.0663030441928854, 'latency_mean': 2.809950326681137, 'latency_p50': 2.813484311103821, 'latency_p90': 3.138035225868225}, {'batch_size': 5, 'throughput': 1.2661564524609195, 'latency_mean': 3.934350620508194, 'latency_p50': 3.9296035766601562, 'latency_p90': 4.412841439247131}, {'batch_size': 6, 'throughput': 1.3174560043363714, 'latency_mean': 4.531021665334702, 'latency_p50': 4.563483715057373, 'latency_p90': 5.0699995994567875}, {'batch_size': 8, 'throughput': 1.3870000324221654, 'latency_mean': 5.715959098339081, 'latency_p50': 5.754398941993713, 'latency_p90': 6.406875681877136}, {'batch_size': 10, 'throughput': 1.426341924007222, 'latency_mean': 6.959036229848862, 'latency_p50': 7.035190939903259, 'latency_p90': 7.788039040565491}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: 2025-07-11_5

is_internal_developer: False

language_model: AlbertWang8192/2025-07-11_5

model_size: 13B

ranking_group: single

throughput_3p7s: 1.24

us_pacific_date: 2025-07-11

win_ratio: 0.4703077097763143

generation_params: {'temperature': 0.6, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['\n', '<|im_end|>', '<|im_start|>'], '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': True}

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 albertwang8192-2025-07-11-5-v1-mkmlizer
Waiting for job on albertwang8192-2025-07-11-5-v1-mkmlizer to finish
albertwang8192-2025-07-11-5-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
albertwang8192-2025-07-11-5-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║  https://mk1.ai                                                     ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║  belonging to:                                                      ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║  Chai Research Corp.                                                ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ║                                                                     ║
albertwang8192-2025-07-11-5-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
albertwang8192-2025-07-11-5-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`
albertwang8192-2025-07-11-5-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`
albertwang8192-2025-07-11-5-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`
albertwang8192-2025-07-11-5-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`
albertwang8192-2025-07-11-5-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 blend_fader_2025-07-10: HTTPConnectionPool(host='chaiml-mistral32-deepse-89261-v4-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 0x72659c5fca10>, 'Connection to chaiml-mistral32-deepse-89261-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))
albertwang8192-2025-07-11-5-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`
albertwang8192-2025-07-11-5-v1-mkmlizer: Downloaded to shared memory in 53.632s
albertwang8192-2025-07-11-5-v1-mkmlizer: Checking if AlbertWang8192/2025-07-11_5 already exists in ChaiML
albertwang8192-2025-07-11-5-v1-mkmlizer: Creating repo ChaiML/2025-07-11_5 and uploading /tmp/tmps21_s91y to it
albertwang8192-2025-07-11-5-v1-mkmlizer: 
  0%|          | 0/6 [00:00<?, ?it/s]
 17%|█▋        | 1/6 [00:03<00:17,  3.53s/it]
 33%|███▎      | 2/6 [00:07<00:14,  3.58s/it]
 50%|█████     | 3/6 [00:15<00:17,  5.69s/it]
 67%|██████▋   | 4/6 [00:18<00:09,  4.88s/it]
 83%|████████▎ | 5/6 [00:24<00:05,  5.17s/it]
100%|██████████| 6/6 [00:25<00:00,  3.78s/it]
100%|██████████| 6/6 [00:25<00:00,  4.30s/it]
albertwang8192-2025-07-11-5-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmps21_s91y, device:0
albertwang8192-2025-07-11-5-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
albertwang8192-2025-07-11-5-v1-mkmlizer: quantized model in 30.579s
albertwang8192-2025-07-11-5-v1-mkmlizer: Processed model AlbertWang8192/2025-07-11_5 in 135.072s
albertwang8192-2025-07-11-5-v1-mkmlizer: creating bucket guanaco-mkml-models
albertwang8192-2025-07-11-5-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
albertwang8192-2025-07-11-5-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/albertwang8192-2025-07-11-5-v1/nvidia
albertwang8192-2025-07-11-5-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/albertwang8192-2025-07-11-5-v1/nvidia/config.json
albertwang8192-2025-07-11-5-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/albertwang8192-2025-07-11-5-v1/nvidia/special_tokens_map.json
albertwang8192-2025-07-11-5-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/albertwang8192-2025-07-11-5-v1/nvidia/tokenizer_config.json
albertwang8192-2025-07-11-5-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/albertwang8192-2025-07-11-5-v1/nvidia/flywheel_model.0.safetensors
albertwang8192-2025-07-11-5-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.48it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 49.77it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 43.46it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 42.11it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 47.82it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.15it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.19it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 48.03it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:07, 43.77it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 32.56it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 32.18it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 38.35it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:07, 40.43it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 34.35it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 41.03it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 41.37it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 42.57it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:05, 44.37it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:06, 41.76it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 42.26it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:06, 40.44it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 42.47it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 42.54it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 41.66it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 42.19it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:08, 25.75it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:08, 26.56it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:06, 34.22it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.19it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.16it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 39.60it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 34.12it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 41.30it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 41.58it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 41.42it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 42.89it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 36.02it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 42.87it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 42.58it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 44.08it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:05, 26.93it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 29.33it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 36.49it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 37.51it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 38.90it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 41.01it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 34.83it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 41.89it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 41.57it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 41.02it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 42.76it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 36.26it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 42.63it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 42.47it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 44.13it/s]
Loading 0:  84%|████████▍ | 306/363 [00:08<00:02, 23.35it/s]
Loading 0:  85%|████████▌ | 310/363 [00:08<00:02, 24.69it/s]
Loading 0:  87%|████████▋ | 314/363 [00:08<00:01, 26.90it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 32.58it/s]
Loading 0:  90%|████████▉ | 326/363 [00:08<00:01, 34.34it/s]
Loading 0:  91%|█████████ | 330/363 [00:08<00:00, 33.83it/s]
Loading 0:  93%|█████████▎| 338/363 [00:08<00:00, 42.54it/s]
Loading 0:  95%|█████████▍| 344/363 [00:09<00:00, 40.86it/s]
Loading 0:  96%|█████████▌| 349/363 [00:09<00:00, 40.75it/s]
Loading 0:  98%|█████████▊| 356/363 [00:09<00:00, 45.62it/s]
Loading 0:  99%|█████████▉| 361/363 [00:09<00:00, 46.20it/s]
                                                            
Job albertwang8192-2025-07-11-5-v1-mkmlizer completed after 157.01s with status: succeeded
Stopping job with name albertwang8192-2025-07-11-5-v1-mkmlizer
Pipeline stage MKMLizer completed in 157.55s
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 albertwang8192-2025-07-11-5-v1
Waiting for inference service albertwang8192-2025-07-11-5-v1 to be ready
Inference service albertwang8192-2025-07-11-5-v1 ready after 210.8735213279724s
Pipeline stage MKMLDeployer completed in 211.40s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.256892442703247s
Received healthy response to inference request in 1.6439282894134521s
Received healthy response to inference request in 1.709949254989624s
Received healthy response to inference request in 1.6136679649353027s
Received healthy response to inference request in 1.5405445098876953s
5 requests
0 failed requests
5th percentile: 1.5551692008972169
10th percentile: 1.5697938919067382
20th percentile: 1.5990432739257812
30th percentile: 1.6197200298309327
40th percentile: 1.6318241596221923
50th percentile: 1.6439282894134521
60th percentile: 1.6703366756439209
70th percentile: 1.6967450618743896
80th percentile: 1.8193378925323487
90th percentile: 2.0381151676177978
95th percentile: 2.147503805160522
99th percentile: 2.235014715194702
mean time: 1.7529964923858643
Pipeline stage StressChecker completed in 9.91s
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 0.68s
Shutdown handler de-registered
albertwang8192-2025-07-11-5_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 5826.92s
Shutdown handler de-registered
albertwang8192-2025-07-11-5_v1 status is now inactive due to auto deactivation removed underperforming models
albertwang8192-2025-07-11-5_v1 status is now torndown due to DeploymentManager action