junhua024-chai-16-full-qkv_72

developer_uid: junhua024
submission_id: junhua024-chai-16-full-qkv_72_v8
model_name: junhua024-chai-16-full-qkv_72_v8
model_group: junhua024/chai_16_full_q
status: torndown
timestamp: 2025-07-23T17:32:02+00:00
num_battles: 6804
num_wins: 3460
celo_rating: 1271.8
family_friendly_score: 0.5528
family_friendly_standard_error: 0.007031531269929758
submission_type: basic
model_repo: junhua024/chai_16_full_qkv100_o106_ffn106_1624
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': 0.6545622267173512, 'latency_mean': 1.5276175463199615, 'latency_p50': 1.5283091068267822, 'latency_p90': 1.6759776592254638}, {'batch_size': 3, 'throughput': 1.1055754660841741, 'latency_mean': 2.703230562210083, 'latency_p50': 2.677608013153076, 'latency_p90': 3.006815052032471}, {'batch_size': 5, 'throughput': 1.269588875289472, 'latency_mean': 3.922960455417633, 'latency_p50': 3.9647985696792603, 'latency_p90': 4.341478228569031}, {'batch_size': 6, 'throughput': 1.3344398030278628, 'latency_mean': 4.471659319400787, 'latency_p50': 4.430467844009399, 'latency_p90': 5.068899703025818}, {'batch_size': 8, 'throughput': 1.3954718596628892, 'latency_mean': 5.694669280052185, 'latency_p50': 5.7038596868515015, 'latency_p90': 6.3947797298431395}, {'batch_size': 10, 'throughput': 1.413467465605224, 'latency_mean': 7.014903748035431, 'latency_p50': 7.0273823738098145, 'latency_p90': 7.850557494163513}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: junhua024-chai-16-full-qkv_72_v8
is_internal_developer: False
language_model: junhua024/chai_16_full_qkv100_o106_ffn106_1624
model_size: 13B
ranking_group: single
throughput_3p7s: 1.25
us_pacific_date: 2025-07-23
win_ratio: 0.5085243974132863
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-16-full-qkv-72-v8-mkmlizer
Waiting for job on junhua024-chai-16-full-qkv-72-v8-mkmlizer to finish
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-qkv-72-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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_fihal_2025-07-23: HTTPConnectionPool(host='guanaco-model-mesh.k2.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-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-16-full-qkv-72-v8-mkmlizer: Downloaded to shared memory in 82.912s
junhua024-chai-16-full-qkv-72-v8-mkmlizer: Checking if junhua024/chai_16_full_qkv100_o106_ffn106_1624 already exists in ChaiML
junhua024-chai-16-full-qkv-72-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpsd118rdd, device:0
junhua024-chai-16-full-qkv-72-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_fihal_2025-07-23: HTTPConnectionPool(host='guanaco-model-mesh.k2.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-16-full-qkv-72-v8-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-16-full-qkv-72-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-16-full-qkv-72-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v8/nvidia
junhua024-chai-16-full-qkv-72-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v8/nvidia/config.json
junhua024-chai-16-full-qkv-72-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v8/nvidia/special_tokens_map.json
junhua024-chai-16-full-qkv-72-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v8/nvidia/tokenizer_config.json
junhua024-chai-16-full-qkv-72-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v8/nvidia/tokenizer.json
junhua024-chai-16-full-qkv-72-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-16-full-qkv-72-v8/nvidia/flywheel_model.0.safetensors
junhua024-chai-16-full-qkv-72-v8-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:20, 17.75it/s]
Loading 0:   1%|          | 4/363 [00:02<03:33,  1.68it/s]
Loading 0:   1%|▏         | 5/363 [00:03<04:22,  1.37it/s]
Loading 0:   2%|▏         | 8/363 [00:03<02:18,  2.56it/s]
Loading 0:   2%|▏         | 9/363 [00:03<02:15,  2.60it/s]
Loading 0:   3%|▎         | 10/363 [00:03<01:56,  3.03it/s]
Loading 0:   3%|▎         | 11/363 [00:04<02:50,  2.06it/s]
Loading 0:   3%|▎         | 12/363 [00:05<03:39,  1.60it/s]
Loading 0:   4%|▍         | 14/363 [00:06<02:30,  2.32it/s]
Loading 0:   4%|▍         | 15/363 [00:06<02:17,  2.53it/s]
Loading 0:   4%|▍         | 16/363 [00:06<01:55,  2.99it/s]
Loading 0:   5%|▍         | 18/363 [00:07<02:23,  2.41it/s]
Loading 0:   6%|▌         | 21/363 [00:08<02:06,  2.70it/s]
Loading 0:   6%|▌         | 22/363 [00:09<02:43,  2.09it/s]
Loading 0:   6%|▋         | 23/363 [00:10<03:25,  1.66it/s]
Loading 0:   7%|▋         | 26/363 [00:11<02:05,  2.68it/s]
Loading 0:   7%|▋         | 27/363 [00:11<02:00,  2.80it/s]
Loading 0:   8%|▊         | 28/363 [00:11<01:44,  3.21it/s]
Loading 0:   8%|▊         | 29/363 [00:12<02:33,  2.18it/s]
Loading 0:   9%|▊         | 31/363 [00:12<01:54,  2.89it/s]
Loading 0:   9%|▉         | 32/363 [00:13<01:49,  3.02it/s]
Loading 0:   9%|▉         | 33/363 [00:13<01:34,  3.50it/s]
Loading 0:  10%|▉         | 35/363 [00:14<02:04,  2.63it/s]
Loading 0:  10%|▉         | 36/363 [00:15<02:51,  1.90it/s]
Loading 0:  11%|█         | 39/363 [00:16<02:17,  2.35it/s]
Loading 0:  11%|█         | 40/363 [00:17<02:49,  1.90it/s]
Loading 0:  11%|█▏        | 41/363 [00:18<03:24,  1.57it/s]
Loading 0:  12%|█▏        | 44/363 [00:18<02:02,  2.60it/s]
Loading 0:  12%|█▏        | 45/363 [00:18<01:55,  2.74it/s]
Loading 0:  13%|█▎        | 46/363 [00:19<01:39,  3.18it/s]
Loading 0:  13%|█▎        | 48/363 [00:19<01:22,  3.83it/s]
Loading 0:  13%|█▎        | 49/363 [00:19<01:23,  3.78it/s]
Loading 0:  14%|█▍        | 50/363 [00:19<01:14,  4.23it/s]
Loading 0:  14%|█▍        | 52/363 [00:20<01:48,  2.87it/s]
Loading 0:  15%|█▍        | 53/363 [00:21<02:30,  2.06it/s]
Loading 0:  15%|█▍        | 54/363 [00:22<03:09,  1.63it/s]
Loading 0:  16%|█▌        | 57/363 [00:23<02:22,  2.15it/s]
Loading 0:  16%|█▌        | 58/363 [00:24<02:50,  1.78it/s]
Loading 0:  16%|█▋        | 59/363 [00:25<03:21,  1.51it/s]
Loading 0:  17%|█▋        | 62/363 [00:26<02:00,  2.51it/s]
Loading 0:  17%|█▋        | 63/363 [00:26<01:52,  2.66it/s]
Loading 0:  18%|█▊        | 64/363 [00:26<01:37,  3.07it/s]
Loading 0:  18%|█▊        | 66/363 [00:27<01:58,  2.51it/s]
Loading 0:  18%|█▊        | 67/363 [00:28<02:32,  1.94it/s]
Loading 0:  19%|█▊        | 68/363 [00:29<03:07,  1.58it/s]
Loading 0:  20%|█▉        | 71/363 [00:29<01:49,  2.67it/s]
Loading 0:  20%|█▉        | 72/363 [00:30<01:43,  2.81it/s]
Loading 0:  20%|██        | 73/363 [00:30<01:29,  3.24it/s]
Loading 0:  20%|██        | 74/363 [00:31<02:13,  2.16it/s]
Loading 0:  21%|██        | 75/363 [00:32<02:55,  1.64it/s]
Loading 0:  21%|██        | 77/363 [00:32<02:01,  2.35it/s]
Loading 0:  21%|██▏       | 78/363 [00:32<01:51,  2.56it/s]
Loading 0:  22%|██▏       | 79/363 [00:33<01:32,  3.07it/s]
Loading 0:  22%|██▏       | 80/363 [00:34<02:24,  1.96it/s]
Loading 0:  23%|██▎       | 82/363 [00:34<01:42,  2.75it/s]
Loading 0:  23%|██▎       | 83/363 [00:34<01:36,  2.91it/s]
Loading 0:  23%|██▎       | 84/363 [00:34<01:20,  3.45it/s]
Loading 0:  24%|██▎       | 86/363 [00:35<01:42,  2.70it/s]
Loading 0:  25%|██▍       | 89/363 [00:36<01:35,  2.87it/s]
Loading 0:  25%|██▍       | 90/363 [00:37<02:05,  2.18it/s]
Loading 0:  25%|██▌       | 91/363 [00:38<02:37,  1.73it/s]
Loading 0:  26%|██▌       | 94/363 [00:39<01:36,  2.78it/s]
Loading 0:  26%|██▌       | 95/363 [00:39<01:32,  2.90it/s]
Loading 0:  26%|██▋       | 96/363 [00:39<01:19,  3.34it/s]
Loading 0:  27%|██▋       | 98/363 [00:40<01:41,  2.61it/s]
Loading 0:  27%|██▋       | 99/363 [00:41<02:17,  1.92it/s]
Loading 0:  28%|██▊       | 102/363 [00:42<01:51,  2.34it/s]
Loading 0:  28%|██▊       | 103/363 [00:43<02:16,  1.90it/s]
Loading 0:  29%|██▊       | 104/363 [00:44<02:43,  1.58it/s]
Loading 0:  29%|██▉       | 107/363 [00:44<01:39,  2.58it/s]
Loading 0:  30%|██▉       | 108/363 [00:45<01:33,  2.73it/s]
Loading 0:  30%|███       | 109/363 [00:45<01:20,  3.16it/s]
Loading 0:  31%|███       | 111/363 [00:45<01:05,  3.83it/s]
Loading 0:  31%|███       | 112/363 [00:45<01:06,  3.79it/s]
Loading 0:  31%|███       | 113/363 [00:46<00:57,  4.32it/s]
Loading 0:  32%|███▏      | 115/363 [00:47<01:25,  2.90it/s]
Loading 0:  32%|███▏      | 116/363 [00:48<01:58,  2.08it/s]
Loading 0:  32%|███▏      | 117/363 [00:49<02:29,  1.64it/s]
Loading 0:  33%|███▎      | 120/363 [00:49<01:51,  2.17it/s]
Loading 0:  33%|███▎      | 121/363 [00:50<02:14,  1.79it/s]
Loading 0:  34%|███▎      | 122/363 [00:51<02:39,  1.51it/s]
Loading 0:  34%|███▍      | 125/363 [00:52<01:34,  2.52it/s]
Loading 0:  35%|███▍      | 126/363 [00:52<01:28,  2.66it/s]
Loading 0:  35%|███▍      | 127/363 [00:52<01:16,  3.10it/s]
Loading 0:  36%|███▌      | 129/363 [00:53<01:32,  2.52it/s]
Loading 0:  36%|███▌      | 130/363 [00:54<01:59,  1.94it/s]
Loading 0:  36%|███▌      | 131/363 [00:55<02:27,  1.58it/s]
Loading 0:  37%|███▋      | 134/363 [00:56<01:25,  2.67it/s]
Loading 0:  37%|███▋      | 135/363 [00:56<01:21,  2.81it/s]
Loading 0:  37%|███▋      | 136/363 [00:56<01:09,  3.26it/s]
Loading 0:  38%|███▊      | 137/363 [00:57<01:43,  2.18it/s]
Loading 0:  38%|███▊      | 138/363 [00:58<02:15,  1.66it/s]
Loading 0:  39%|███▊      | 140/363 [00:58<01:33,  2.38it/s]
Loading 0:  39%|███▉      | 141/363 [00:59<01:25,  2.58it/s]
Loading 0:  39%|███▉      | 142/363 [00:59<01:11,  3.08it/s]
Loading 0:  40%|███▉      | 144/363 [01:00<01:28,  2.47it/s]
Loading 0:  40%|████      | 147/363 [01:01<01:19,  2.73it/s]
Loading 0:  41%|████      | 148/363 [01:02<01:42,  2.09it/s]
Loading 0:  41%|████      | 149/363 [01:03<02:06,  1.69it/s]
Loading 0:  42%|████▏     | 152/363 [01:03<01:17,  2.72it/s]
Loading 0:  42%|████▏     | 153/363 [01:03<01:13,  2.85it/s]
Loading 0:  42%|████▏     | 154/363 [01:03<01:03,  3.27it/s]
Loading 0:  43%|████▎     | 155/363 [01:04<01:34,  2.20it/s]
Loading 0:  43%|████▎     | 157/363 [01:05<01:10,  2.92it/s]
Loading 0:  44%|████▎     | 158/363 [01:05<01:07,  3.06it/s]
Loading 0:  44%|████▍     | 159/363 [01:05<00:56,  3.58it/s]
Loading 0:  44%|████▍     | 161/363 [01:06<01:16,  2.63it/s]
Loading 0:  45%|████▍     | 162/363 [01:07<01:45,  1.90it/s]
Loading 0:  45%|████▌     | 165/363 [01:08<01:24,  2.35it/s]
Loading 0:  46%|████▌     | 166/363 [01:09<01:43,  1.90it/s]
Loading 0:  46%|████▌     | 167/363 [01:10<02:03,  1.58it/s]
Loading 0:  47%|████▋     | 170/363 [01:11<01:14,  2.60it/s]
Loading 0:  47%|████▋     | 171/363 [01:11<01:09,  2.74it/s]
Loading 0:  47%|████▋     | 172/363 [01:11<01:00,  3.15it/s]
Loading 0:  48%|████▊     | 174/363 [01:11<00:49,  3.79it/s]
Loading 0:  48%|████▊     | 175/363 [01:12<00:49,  3.76it/s]
Loading 0:  48%|████▊     | 176/363 [01:12<00:44,  4.24it/s]
Loading 0:  49%|████▉     | 178/363 [01:13<01:04,  2.85it/s]
Loading 0:  49%|████▉     | 179/363 [01:14<01:28,  2.07it/s]
Loading 0:  50%|████▉     | 180/363 [01:15<01:52,  1.63it/s]
Loading 0:  50%|█████     | 183/363 [01:16<01:23,  2.15it/s]
Loading 0:  51%|█████     | 184/363 [01:17<01:39,  1.79it/s]
Loading 0:  51%|█████     | 185/363 [01:18<01:57,  1.51it/s]
Loading 0:  52%|█████▏    | 188/363 [01:18<01:09,  2.52it/s]
Loading 0:  52%|█████▏    | 189/363 [01:18<01:05,  2.68it/s]
Loading 0:  52%|█████▏    | 190/363 [01:18<00:55,  3.10it/s]
Loading 0:  53%|█████▎    | 192/363 [01:19<01:07,  2.53it/s]
Loading 0:  53%|█████▎    | 193/363 [01:20<01:26,  1.96it/s]
Loading 0:  53%|█████▎    | 194/363 [01:21<01:46,  1.59it/s]
Loading 0:  54%|█████▍    | 197/363 [01:22<01:01,  2.69it/s]
Loading 0:  55%|█████▍    | 198/363 [01:22<00:58,  2.83it/s]
Loading 0:  55%|█████▍    | 199/363 [01:22<00:50,  3.25it/s]
Loading 0:  55%|█████▌    | 200/363 [01:23<01:14,  2.18it/s]
Loading 0:  55%|█████▌    | 201/363 [01:24<01:37,  1.67it/s]
Loading 0:  56%|█████▌    | 203/363 [01:24<01:07,  2.38it/s]
Loading 0:  56%|█████▌    | 204/363 [01:25<01:01,  2.59it/s]
Loading 0:  56%|█████▋    | 205/363 [01:25<00:51,  3.09it/s]
Loading 0:  57%|█████▋    | 207/363 [01:26<01:02,  2.48it/s]
Loading 0:  58%|█████▊    | 210/363 [01:27<00:55,  2.75it/s]
Loading 0:  58%|█████▊    | 211/363 [01:28<01:11,  2.12it/s]
Loading 0:  58%|█████▊    | 212/363 [01:29<01:28,  1.70it/s]
Loading 0:  59%|█████▉    | 215/363 [01:29<00:53,  2.74it/s]
Loading 0:  60%|█████▉    | 216/363 [01:29<00:51,  2.87it/s]
Loading 0:  60%|█████▉    | 217/363 [01:30<00:44,  3.28it/s]
Loading 0:  60%|██████    | 218/363 [01:31<01:05,  2.21it/s]
Loading 0:  61%|██████    | 220/363 [01:31<00:48,  2.94it/s]
Loading 0:  61%|██████    | 221/363 [01:31<00:46,  3.07it/s]
Loading 0:  61%|██████    | 222/363 [01:31<00:39,  3.55it/s]
Loading 0:  62%|██████▏   | 224/363 [01:32<00:52,  2.63it/s]
Loading 0:  62%|██████▏   | 225/363 [01:33<01:12,  1.90it/s]
Loading 0:  63%|██████▎   | 228/363 [01:34<00:57,  2.36it/s]
Loading 0:  63%|██████▎   | 229/363 [01:35<01:10,  1.91it/s]
Loading 0:  63%|██████▎   | 230/363 [01:36<01:23,  1.59it/s]
Loading 0:  64%|██████▍   | 233/363 [01:37<00:49,  2.62it/s]
Loading 0:  64%|██████▍   | 234/363 [01:37<00:46,  2.77it/s]
Loading 0:  65%|██████▍   | 235/363 [01:37<00:40,  3.20it/s]
Loading 0:  65%|██████▌   | 237/363 [01:37<00:32,  3.86it/s]
Loading 0:  66%|██████▌   | 238/363 [01:38<00:32,  3.81it/s]
Loading 0:  66%|██████▌   | 239/363 [01:38<00:28,  4.31it/s]
Loading 0:  66%|██████▋   | 241/363 [01:39<00:41,  2.91it/s]
Loading 0:  67%|██████▋   | 242/363 [01:40<00:57,  2.10it/s]
Loading 0:  67%|██████▋   | 243/363 [01:41<01:12,  1.65it/s]
Loading 0:  68%|██████▊   | 246/363 [01:42<00:53,  2.18it/s]
Loading 0:  68%|██████▊   | 247/363 [01:43<01:04,  1.80it/s]
Loading 0:  68%|██████▊   | 248/363 [01:44<01:15,  1.51it/s]
Loading 0:  69%|██████▉   | 251/363 [01:44<00:44,  2.53it/s]
Loading 0:  69%|██████▉   | 252/363 [01:44<00:41,  2.68it/s]
Loading 0:  70%|██████▉   | 253/363 [01:44<00:35,  3.12it/s]
Loading 0:  70%|███████   | 255/363 [01:45<00:42,  2.56it/s]
Loading 0:  71%|███████   | 256/363 [01:46<00:54,  1.97it/s]
Loading 0:  71%|███████   | 257/363 [01:47<01:05,  1.61it/s]
Loading 0:  72%|███████▏  | 260/363 [01:48<00:37,  2.72it/s]
Loading 0:  72%|███████▏  | 261/363 [01:48<00:35,  2.86it/s]
Loading 0:  72%|███████▏  | 262/363 [01:48<00:30,  3.30it/s]
Loading 0:  72%|███████▏  | 263/363 [01:49<00:45,  2.20it/s]
Loading 0:  73%|███████▎  | 264/363 [01:50<00:58,  1.69it/s]
Loading 0:  73%|███████▎  | 266/363 [01:50<00:40,  2.41it/s]
Loading 0:  74%|███████▎  | 267/363 [01:51<00:36,  2.61it/s]
Loading 0:  74%|███████▍  | 268/363 [01:51<00:30,  3.11it/s]
Loading 0:  74%|███████▍  | 270/363 [01:52<00:37,  2.49it/s]
Loading 0:  75%|███████▌  | 273/363 [01:53<00:32,  2.76it/s]
Loading 0:  75%|███████▌  | 274/363 [01:54<00:42,  2.12it/s]
Loading 0:  76%|███████▌  | 275/363 [01:55<00:51,  1.71it/s]
Loading 0:  77%|███████▋  | 278/363 [01:55<00:30,  2.76it/s]
Loading 0:  77%|███████▋  | 279/363 [01:55<00:29,  2.89it/s]
Loading 0:  77%|███████▋  | 280/363 [01:56<00:25,  3.31it/s]
Loading 0:  77%|███████▋  | 281/363 [01:57<00:36,  2.23it/s]
Loading 0:  78%|███████▊  | 283/363 [01:57<00:27,  2.96it/s]
Loading 0:  78%|███████▊  | 284/363 [01:57<00:25,  3.09it/s]
Loading 0:  79%|███████▊  | 285/363 [01:57<00:21,  3.62it/s]
Loading 0:  79%|███████▉  | 287/363 [01:58<00:28,  2.68it/s]
Loading 0:  79%|███████▉  | 288/363 [01:59<00:38,  1.94it/s]
Loading 0:  80%|████████  | 291/363 [02:00<00:30,  2.39it/s]
Loading 0:  80%|████████  | 292/363 [02:01<00:36,  1.93it/s]
Loading 0:  81%|████████  | 293/363 [02:02<00:43,  1.60it/s]
Loading 0:  82%|████████▏ | 296/363 [02:03<00:25,  2.63it/s]
Loading 0:  82%|████████▏ | 297/363 [02:03<00:23,  2.77it/s]
Loading 0:  82%|████████▏ | 298/363 [02:03<00:20,  3.15it/s]
Loading 0:  83%|████████▎ | 300/363 [02:03<00:16,  3.78it/s]
Loading 0:  83%|████████▎ | 301/363 [02:04<00:16,  3.73it/s]
Loading 0:  83%|████████▎ | 302/363 [02:04<00:14,  4.23it/s]
Loading 0:  84%|████████▎ | 304/363 [02:05<00:20,  2.88it/s]
Loading 0:  84%|████████▍ | 305/363 [02:06<00:27,  2.08it/s]
Loading 0:  84%|████████▍ | 306/363 [02:07<00:34,  1.65it/s]
Loading 0:  85%|████████▌ | 309/363 [02:08<00:24,  2.18it/s]
Loading 0:  85%|████████▌ | 310/363 [02:09<00:29,  1.80it/s]
Loading 0:  86%|████████▌ | 311/363 [02:10<00:34,  1.52it/s]
Loading 0:  87%|████████▋ | 314/363 [02:10<00:19,  2.54it/s]
Loading 0:  87%|████████▋ | 315/363 [02:10<00:17,  2.69it/s]
Loading 0:  87%|████████▋ | 316/363 [02:10<00:15,  3.12it/s]
Loading 0:  88%|████████▊ | 318/363 [02:11<00:17,  2.55it/s]
Loading 0:  88%|████████▊ | 319/363 [02:12<00:22,  1.97it/s]
Loading 0:  88%|████████▊ | 320/363 [02:13<00:26,  1.60it/s]
Loading 0:  89%|████████▉ | 323/363 [02:14<00:14,  2.70it/s]
Loading 0:  89%|████████▉ | 324/363 [02:14<00:13,  2.84it/s]
Loading 0:  90%|████████▉ | 325/363 [02:14<00:11,  3.28it/s]
Loading 0:  90%|████████▉ | 326/363 [02:15<00:16,  2.19it/s]
Loading 0:  90%|█████████ | 327/363 [02:16<00:21,  1.67it/s]
Loading 0:  91%|█████████ | 329/363 [02:16<00:14,  2.39it/s]
Loading 0:  91%|█████████ | 330/363 [02:17<00:12,  2.60it/s]
Loading 0:  91%|█████████ | 331/363 [02:17<00:10,  3.10it/s]
Loading 0:  92%|█████████▏| 333/363 [02:18<00:12,  2.49it/s]
Loading 0:  93%|█████████▎| 336/363 [02:19<00:09,  2.77it/s]
Loading 0:  93%|█████████▎| 337/363 [02:20<00:12,  2.14it/s]
Loading 0:  93%|█████████▎| 338/363 [02:21<00:14,  1.71it/s]
Loading 0:  94%|█████████▍| 341/363 [02:21<00:07,  2.76it/s]
Loading 0:  94%|█████████▍| 342/363 [02:21<00:07,  2.89it/s]
Loading 0:  94%|█████████▍| 343/363 [02:22<00:06,  3.29it/s]
Loading 0:  95%|█████████▍| 344/363 [02:22<00:08,  2.21it/s]
Loading 0:  95%|█████████▌| 346/363 [02:23<00:05,  2.94it/s]
Loading 0:  96%|█████████▌| 347/363 [02:23<00:05,  3.06it/s]
Loading 0:  96%|█████████▌| 348/363 [02:23<00:04,  3.56it/s]
Loading 0:  96%|█████████▌| 349/363 [02:23<00:03,  3.64it/s]
Loading 0:  96%|█████████▋| 350/363 [02:24<00:02,  4.37it/s]
Loading 0:  97%|█████████▋| 351/363 [02:25<00:05,  2.32it/s]
Loading 0:  97%|█████████▋| 352/363 [02:26<00:06,  1.67it/s]
Loading 0:  98%|█████████▊| 355/363 [02:27<00:03,  2.23it/s]
Loading 0:  98%|█████████▊| 356/363 [02:27<00:03,  1.81it/s]
Loading 0:  98%|█████████▊| 357/363 [02:28<00:03,  1.52it/s]
Loading 0:  99%|█████████▉| 360/363 [02:29<00:01,  2.57it/s]
Loading 0:  99%|█████████▉| 361/363 [02:29<00:00,  2.73it/s]
Loading 0: 100%|█████████▉| 362/363 [02:29<00:00,  3.16it/s]
                                                            
Job junhua024-chai-16-full-qkv-72-v8-mkmlizer completed after 273.81s with status: succeeded
Stopping job with name junhua024-chai-16-full-qkv-72-v8-mkmlizer
Pipeline stage MKMLizer completed in 275.32s
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-16-full-qkv-72-v8
Waiting for inference service junhua024-chai-16-full-qkv-72-v8 to be ready
Inference service junhua024-chai-16-full-qkv-72-v8 ready after 181.11388564109802s
Pipeline stage MKMLDeployer completed in 181.89s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.65232515335083s
Received healthy response to inference request in 1.6975231170654297s
Received healthy response to inference request in 1.8965482711791992s
Received healthy response to inference request in 1.446584701538086s
Received healthy response to inference request in 1.5055038928985596s
5 requests
0 failed requests
5th percentile: 1.4583685398101807
10th percentile: 1.4701523780822754
20th percentile: 1.4937200546264648
30th percentile: 1.5439077377319337
40th percentile: 1.6207154273986817
50th percentile: 1.6975231170654297
60th percentile: 1.7771331787109375
70th percentile: 1.8567432403564452
80th percentile: 2.447703647613526
90th percentile: 3.550014400482178
95th percentile: 4.101169776916503
99th percentile: 4.542094078063965
mean time: 2.2396970272064207
Pipeline stage StressChecker completed in 12.58s
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 0.83s
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 0.72s
Shutdown handler de-registered
junhua024-chai-16-full-qkv_72_v8 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 3321.85s
Shutdown handler de-registered
junhua024-chai-16-full-qkv_72_v8 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-16-full-qkv_72_v8 status is now torndown due to DeploymentManager action