junhua024-chai-16-full-_18823

developer_uid: junhua024
submission_id: junhua024-chai-16-full-_18823_v3
model_name: junhua024-chai-16-full-_18823_v3
model_group: junhua024/chai_16_full_1
status: torndown
timestamp: 2025-07-20T04:42:27+00:00
num_battles: 6679
num_wins: 3373
celo_rating: 1282.59
family_friendly_score: 0.5571999999999999
family_friendly_standard_error: 0.007024644617345421
submission_type: basic
model_repo: junhua024/chai_16_full_106_qkv098_o_ffn_1925
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': 0.5903963734171254, 'latency_mean': 1.693654248714447, 'latency_p50': 1.699108362197876, 'latency_p90': 1.8507358074188232}, {'batch_size': 3, 'throughput': 1.076673069014407, 'latency_mean': 2.7753502357006075, 'latency_p50': 2.7710235118865967, 'latency_p90': 3.0365459442138674}, {'batch_size': 5, 'throughput': 1.2908371764796247, 'latency_mean': 3.854773166179657, 'latency_p50': 3.8899070024490356, 'latency_p90': 4.299937176704407}, {'batch_size': 6, 'throughput': 1.3602938144919607, 'latency_mean': 4.386775733232498, 'latency_p50': 4.396584630012512, 'latency_p90': 4.939549088478088}, {'batch_size': 8, 'throughput': 1.4184481709219927, 'latency_mean': 5.603083477020264, 'latency_p50': 5.643506050109863, 'latency_p90': 6.2555938243865965}, {'batch_size': 10, 'throughput': 1.44067905404567, 'latency_mean': 6.867846665382385, 'latency_p50': 6.96156907081604, 'latency_p90': 7.68802285194397}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: junhua024-chai-16-full-_18823_v3
is_internal_developer: False
language_model: junhua024/chai_16_full_106_qkv098_o_ffn_1925
model_size: 13B
ranking_group: single
throughput_3p7s: 1.27
us_pacific_date: 2025-07-19
win_ratio: 0.5050157209163049
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': "{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-18823-v3-mkmlizer
Waiting for job on junhua024-chai-16-full-18823-v3-mkmlizer to finish
junhua024-chai-16-full-18823-v2-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-18823-v2-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-18823-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-16-full-18823-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-18823-v2-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-18823-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-16-full-18823-v2-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-18823-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-16-full-18823-v2-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-18823-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-16-full-18823-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-16-full-18823-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-16-full-18823-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-16-full-18823-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-16-full-18823-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-16-full-18823-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-18823-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-16-full-18823-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-16-full-18823-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-16-full-18823-v3-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-16-full-18823-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-18823-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-16-full-18823-v3-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-16-full-18823-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-18823-v3-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-16-full-18823-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-16-full-18823-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-16-full-18823-v3-mkmlizer: ║                                                                     ║
junhua024-chai-16-full-18823-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-16-full-18823-v2-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-18823-v2-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-18823-v2-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-18823-v3-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-18823-v3-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-18823-v3-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-18823-v2-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-18823-v2-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-18823-v2-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-18823-v3-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-18823-v3-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-18823-v3-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-18823-v2-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-18823-v2-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-18823-v3-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-18823-v3-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-18823-v3-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-18823-v2-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-18823-v2-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-18823-v2-mkmlizer: Downloaded to shared memory in 109.006s
junhua024-chai-16-full-18823-v2-mkmlizer: Checking if junhua024/chai_16_full_106_qkv098_o_ffn_1925 already exists in ChaiML
junhua024-chai-16-full-18823-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprvhffpem, device:0
junhua024-chai-16-full-18823-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-16-full-18823-v3-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-18823-v3-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-18823-v3-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-18823-v3-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-18823-v3-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-18823-v3-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-18823-v3-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-18823-v3-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-18823-v3-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 junhua024-chai-16-full-_63690_v4: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-16-full-_63690_v1: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-16-full-18823-v2-mkmlizer: quantized model in 31.279s
junhua024-chai-16-full-18823-v2-mkmlizer: Processed model junhua024/chai_16_full_106_qkv098_o_ffn_1925 in 140.371s
junhua024-chai-16-full-18823-v2-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-16-full-18823-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-16-full-18823-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-16-full-18823-v2/nvidia
junhua024-chai-16-full-18823-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-16-full-18823-v2/nvidia/config.json
junhua024-chai-16-full-18823-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-16-full-18823-v2/nvidia/special_tokens_map.json
junhua024-chai-16-full-18823-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-16-full-18823-v2/nvidia/tokenizer_config.json
junhua024-chai-16-full-18823-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-16-full-18823-v2/nvidia/tokenizer.json
junhua024-chai-16-full-18823-v3-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-18823-v3-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-18823-v3-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-18823-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-16-full-18823-v2/nvidia/flywheel_model.0.safetensors
junhua024-chai-16-full-18823-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:23, 15.17it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:20, 17.82it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:11, 30.14it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:10, 32.04it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 33.43it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 46.95it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:09, 35.90it/s]
Loading 0:  12%|█▏        | 43/363 [00:01<00:09, 35.28it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:07, 39.49it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:09, 32.77it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 32.46it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:08, 34.59it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 33.29it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 34.03it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 32.77it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 37.96it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 37.06it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 37.69it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:07, 36.61it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:07, 33.97it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 39.24it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:07, 31.43it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 32.70it/s]
Loading 0:  35%|███▌      | 128/363 [00:03<00:06, 34.38it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:06, 33.30it/s]
Loading 0:  38%|███▊      | 138/363 [00:04<00:06, 33.90it/s]
Loading 0:  39%|███▉      | 143/363 [00:04<00:06, 34.04it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:06, 33.87it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 41.36it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.91it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 36.54it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 35.46it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:04, 39.93it/s]
Loading 0:  50%|████▉     | 181/363 [00:05<00:05, 33.52it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 31.83it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 33.72it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:05, 32.45it/s]
Loading 0:  55%|█████▌    | 200/363 [00:05<00:04, 35.92it/s]
Loading 0:  56%|█████▋    | 205/363 [00:05<00:04, 34.60it/s]
Loading 0:  58%|█████▊    | 209/363 [00:06<00:04, 35.85it/s]
Loading 0:  59%|█████▊    | 213/363 [00:06<00:04, 32.94it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:03, 36.64it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:04, 34.97it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:03, 35.07it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 32.53it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:03, 39.95it/s]
Loading 0:  67%|██████▋   | 244/363 [00:07<00:03, 33.63it/s]
Loading 0:  68%|██████▊   | 248/363 [00:07<00:03, 32.90it/s]
Loading 0:  70%|██████▉   | 254/363 [00:07<00:03, 34.88it/s]
Loading 0:  71%|███████   | 258/363 [00:07<00:03, 33.52it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 33.20it/s]
Loading 0:  74%|███████▍  | 269/363 [00:07<00:02, 33.58it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 34.03it/s]
Loading 0:  78%|███████▊  | 282/363 [00:08<00:01, 41.67it/s]
Loading 0:  79%|███████▉  | 287/363 [00:08<00:02, 37.37it/s]
Loading 0:  80%|████████  | 292/363 [00:08<00:01, 36.86it/s]
Loading 0:  82%|████████▏ | 298/363 [00:08<00:01, 37.70it/s]
Loading 0:  83%|████████▎ | 303/363 [00:08<00:01, 36.88it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:01, 35.55it/s]
Loading 0:  86%|████████▌ | 311/363 [00:08<00:01, 34.40it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 35.91it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 34.75it/s]
Loading 0:  90%|█████████ | 327/363 [00:09<00:01, 35.38it/s]
Loading 0:  91%|█████████▏| 332/363 [00:09<00:00, 34.94it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 35.56it/s]
Loading 0:  95%|█████████▌| 345/363 [00:09<00:00, 43.12it/s]
Loading 0:  96%|█████████▋| 350/363 [00:10<00:00, 24.49it/s]
Loading 0:  98%|█████████▊| 354/363 [00:10<00:00, 26.81it/s]
Loading 0:  99%|█████████▊| 358/363 [00:10<00:00, 28.23it/s]
                                                            
Job junhua024-chai-16-full-18823-v2-mkmlizer completed after 163.04s with status: succeeded
Stopping job with name junhua024-chai-16-full-18823-v2-mkmlizer
Pipeline stage MKMLizer completed in 163.72s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.25s
junhua024-chai-16-full-18823-v3-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`
run pipeline stage %s
junhua024-chai-16-full-18823-v3-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`
Running pipeline stage MKMLDeployer
junhua024-chai-16-full-18823-v3-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`
Creating inference service junhua024-chai-16-full-18823-v2
Waiting for inference service junhua024-chai-16-full-18823-v2 to be ready
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-16-full-_63690_v1: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-16-full-18823-v3-mkmlizer: Downloaded to shared memory in 91.169s
junhua024-chai-16-full-18823-v3-mkmlizer: Checking if junhua024/chai_16_full_106_qkv098_o_ffn_1925 already exists in ChaiML
junhua024-chai-16-full-18823-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpgx97z9n1, device:0
junhua024-chai-16-full-18823-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-16-full-18823-v3-mkmlizer: quantized model in 32.407s
junhua024-chai-16-full-18823-v3-mkmlizer: Processed model junhua024/chai_16_full_106_qkv098_o_ffn_1925 in 123.662s
junhua024-chai-16-full-18823-v3-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-16-full-18823-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-16-full-18823-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-16-full-18823-v3/nvidia
junhua024-chai-16-full-18823-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-16-full-18823-v3/nvidia/config.json
junhua024-chai-16-full-18823-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-16-full-18823-v3/nvidia/special_tokens_map.json
junhua024-chai-16-full-18823-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-16-full-18823-v3/nvidia/tokenizer_config.json
junhua024-chai-16-full-18823-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-16-full-18823-v3/nvidia/tokenizer.json
junhua024-chai-16-full-18823-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-16-full-18823-v3/nvidia/flywheel_model.0.safetensors
junhua024-chai-16-full-18823-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:00<00:23, 15.25it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:20, 17.85it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:12, 28.71it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:11, 29.50it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:11, 30.07it/s]
Loading 0:   8%|▊         | 29/363 [00:00<00:09, 35.18it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:10, 31.46it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 31.69it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:10, 29.90it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:08, 36.50it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:10, 30.12it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:09, 33.03it/s]
Loading 0:  18%|█▊        | 65/363 [00:02<00:08, 35.48it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:08, 34.62it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:08, 35.14it/s]
Loading 0:  22%|██▏       | 80/363 [00:02<00:08, 33.58it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 38.72it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 37.14it/s]
Loading 0:  27%|██▋       | 97/363 [00:02<00:07, 37.71it/s]
Loading 0:  28%|██▊       | 101/363 [00:03<00:07, 37.15it/s]
Loading 0:  29%|██▉       | 105/363 [00:03<00:07, 34.33it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 40.91it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:07, 34.06it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:07, 31.65it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:06, 34.77it/s]
Loading 0:  36%|███▌      | 131/363 [00:04<00:08, 25.87it/s]
Loading 0:  37%|███▋      | 136/363 [00:04<00:07, 30.17it/s]
Loading 0:  39%|███▊      | 140/363 [00:04<00:07, 29.69it/s]
Loading 0:  40%|███▉      | 144/363 [00:04<00:08, 26.08it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 28.57it/s]
Loading 0:  43%|████▎     | 155/363 [00:04<00:06, 34.56it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 33.85it/s]
Loading 0:  45%|████▌     | 164/363 [00:05<00:06, 33.06it/s]
Loading 0:  46%|████▋     | 168/363 [00:05<00:06, 31.29it/s]
Loading 0:  48%|████▊     | 176/363 [00:05<00:04, 38.22it/s]
Loading 0:  50%|████▉     | 180/363 [00:05<00:05, 30.50it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:05, 32.32it/s]
Loading 0:  53%|█████▎    | 191/363 [00:05<00:05, 34.00it/s]
Loading 0:  54%|█████▎    | 195/363 [00:05<00:05, 32.68it/s]
Loading 0:  55%|█████▌    | 201/363 [00:06<00:04, 32.52it/s]
Loading 0:  57%|█████▋    | 206/363 [00:06<00:04, 31.71it/s]
Loading 0:  58%|█████▊    | 212/363 [00:06<00:04, 31.97it/s]
Loading 0:  60%|█████▉    | 217/363 [00:06<00:04, 35.56it/s]
Loading 0:  61%|██████    | 222/363 [00:06<00:03, 37.06it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:04, 29.37it/s]
Loading 0:  63%|██████▎   | 230/363 [00:07<00:04, 28.62it/s]
Loading 0:  65%|██████▌   | 237/363 [00:07<00:03, 36.76it/s]
Loading 0:  67%|██████▋   | 242/363 [00:07<00:03, 32.09it/s]
Loading 0:  68%|██████▊   | 246/363 [00:07<00:03, 33.43it/s]
Loading 0:  69%|██████▉   | 251/363 [00:07<00:03, 36.77it/s]
Loading 0:  70%|███████   | 255/363 [00:07<00:03, 31.03it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:03, 32.79it/s]
Loading 0:  73%|███████▎  | 264/363 [00:08<00:03, 32.72it/s]
Loading 0:  74%|███████▍  | 269/363 [00:08<00:02, 33.60it/s]
Loading 0:  76%|███████▌  | 275/363 [00:08<00:02, 34.66it/s]
Loading 0:  78%|███████▊  | 283/363 [00:08<00:01, 44.42it/s]
Loading 0:  79%|███████▉  | 288/363 [00:08<00:02, 33.74it/s]
Loading 0:  81%|████████  | 293/363 [00:08<00:02, 34.65it/s]
Loading 0:  83%|████████▎ | 302/363 [00:09<00:01, 42.95it/s]
Loading 0:  85%|████████▍ | 307/363 [00:09<00:01, 36.84it/s]
Loading 0:  86%|████████▌ | 312/363 [00:09<00:01, 36.34it/s]
Loading 0:  87%|████████▋ | 317/363 [00:09<00:01, 35.19it/s]
Loading 0:  88%|████████▊ | 321/363 [00:09<00:01, 32.89it/s]
Loading 0:  90%|████████▉ | 325/363 [00:09<00:01, 34.00it/s]
Loading 0:  91%|█████████ | 329/363 [00:09<00:01, 31.99it/s]
Loading 0:  92%|█████████▏| 333/363 [00:10<00:01, 26.54it/s]
Loading 0:  93%|█████████▎| 338/363 [00:10<00:00, 28.19it/s]
Loading 0:  95%|█████████▍| 344/363 [00:10<00:00, 34.09it/s]
Loading 0:  96%|█████████▌| 349/363 [00:10<00:00, 23.32it/s]
Loading 0:  97%|█████████▋| 352/363 [00:10<00:00, 20.82it/s]
Loading 0:  98%|█████████▊| 357/363 [00:11<00:00, 25.08it/s]
                                                            
Job junhua024-chai-16-full-18823-v3-mkmlizer completed after 155.21s with status: succeeded
Stopping job with name junhua024-chai-16-full-18823-v3-mkmlizer
Pipeline stage MKMLizer completed in 156.18s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.26s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-16-full-18823-v3
Waiting for inference service junhua024-chai-16-full-18823-v3 to be ready
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-16-full-_63690_v3: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-16-full-_63690_v4: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-16-full-_63690_v3: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-16-full-_63690_v4: HTTPConnectionPool(host='junhua024-chai-16-full-63690-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-16-full-18823-v2 ready after 322.1953456401825s
Pipeline stage MKMLDeployer completed in 323.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.832700490951538s
Received healthy response to inference request in 2.1161487102508545s
Received healthy response to inference request in 1.7979621887207031s
Received healthy response to inference request in 1.8546652793884277s
Received healthy response to inference request in 1.7680416107177734s
5 requests
0 failed requests
5th percentile: 1.7740257263183594
10th percentile: 1.7800098419189454
20th percentile: 1.7919780731201171
30th percentile: 1.809302806854248
40th percentile: 1.831984043121338
50th percentile: 1.8546652793884277
60th percentile: 1.9592586517333985
70th percentile: 2.0638520240783693
80th percentile: 2.2594590663909915
90th percentile: 2.5460797786712646
95th percentile: 2.689390134811401
99th percentile: 2.804038419723511
mean time: 2.0739036560058595
Pipeline stage StressChecker completed in 13.76s
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 1.06s
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 0.99s
Shutdown handler de-registered
junhua024-chai-16-full-_18823_v2 status is now deployed due to DeploymentManager action
Inference service junhua024-chai-16-full-18823-v3 ready after 341.6417875289917s
Pipeline stage MKMLDeployer completed in 342.44s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.1337087154388428s
Received healthy response to inference request in 1.8576579093933105s
Received healthy response to inference request in 1.6224067211151123s
Received healthy response to inference request in 1.8245618343353271s
Received healthy response to inference request in 1.6776351928710938s
5 requests
0 failed requests
5th percentile: 1.6334524154663086
10th percentile: 1.6444981098175049
20th percentile: 1.6665894985198975
30th percentile: 1.7070205211639404
40th percentile: 1.7657911777496338
50th percentile: 1.8245618343353271
60th percentile: 1.8378002643585205
70th percentile: 1.8510386943817139
80th percentile: 2.112868070602417
90th percentile: 2.62328839302063
95th percentile: 2.8784985542297363
99th percentile: 3.0826666831970213
mean time: 2.0231940746307373
Pipeline stage StressChecker completed in 12.90s
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 0.79s
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 0.80s
Shutdown handler de-registered
junhua024-chai-16-full-_18823_v3 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 2687.22s
Shutdown handler de-registered
junhua024-chai-16-full-_18823_v3 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-16-full-_18823_v3 status is now torndown due to DeploymentManager action