developer_uid: junhua024
submission_id: junhua024-chai-02-full-0109_v1
model_name: junhua024-chai-02-full-0109_v1
model_group: junhua024/chai_02_full_0
status: torndown
timestamp: 2025-07-22T15:41:49+00:00
num_battles: 6707
num_wins: 3365
celo_rating: 1273.88
family_friendly_score: 0.534
family_friendly_standard_error: 0.00705470056061914
submission_type: basic
model_repo: junhua024/chai_02_full_0109
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': 0.6632926426597178, 'latency_mean': 1.5075166761875152, 'latency_p50': 1.4977020025253296, 'latency_p90': 1.660514497756958}, {'batch_size': 3, 'throughput': 1.127319457134287, 'latency_mean': 2.6532330143451692, 'latency_p50': 2.642151713371277, 'latency_p90': 2.921956205368042}, {'batch_size': 5, 'throughput': 1.3028763525314397, 'latency_mean': 3.8327723371982576, 'latency_p50': 3.805778980255127, 'latency_p90': 4.2747070550918576}, {'batch_size': 6, 'throughput': 1.3551220585298607, 'latency_mean': 4.410521464347839, 'latency_p50': 4.42721962928772, 'latency_p90': 4.9428870677948}, {'batch_size': 8, 'throughput': 1.4240810649334799, 'latency_mean': 5.586836421489716, 'latency_p50': 5.564739465713501, 'latency_p90': 6.280158066749573}, {'batch_size': 10, 'throughput': 1.4476764262410038, 'latency_mean': 6.845855467319488, 'latency_p50': 6.810719966888428, 'latency_p90': 7.810128092765808}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: junhua024-chai-02-full-0109_v1
is_internal_developer: False
language_model: junhua024/chai_02_full_0109
model_size: 13B
ranking_group: single
throughput_3p7s: 1.29
us_pacific_date: 2025-07-22
win_ratio: 0.5017146265096168
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-02-full-0109-v1-mkmlizer
Waiting for job on junhua024-chai-02-full-0109-v1-mkmlizer to finish
junhua024-chai-02-full-0109-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-02-full-0109-v1-mkmlizer: ║ ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ Version: 0.29.15 ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ https://mk1.ai ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ The license key for the current software has been verified as ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ belonging to: ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ Chai Research Corp. ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
junhua024-chai-02-full-0109-v1-mkmlizer: ║ ║
junhua024-chai-02-full-0109-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-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 chaiml-llama-8b-nis-retu_8225_v2: HTTPConnectionPool(host='chaiml-llama-8b-nis-retu-8225-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-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 chaiml-llama-8b-nis-retu_8225_v2: HTTPConnectionPool(host='chaiml-llama-8b-nis-retu-8225-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-02-full-0109-v1-mkmlizer: 0%| | 0/26 [00:00<?, ?it/s] 4%|▍ | 1/26 [00:01<00:46, 1.86s/it] 8%|▊ | 2/26 [00:03<00:42, 1.76s/it] 12%|█▏ | 3/26 [00:05<00:37, 1.64s/it] 15%|█▌ | 4/26 [00:06<00:35, 1.62s/it] 19%|█▉ | 5/26 [00:08<00:33, 1.61s/it] 23%|██▎ | 6/26 [00:09<00:31, 1.58s/it] 27%|██▋ | 7/26 [00:12<00:38, 2.05s/it] 31%|███ | 8/26 [00:14<00:37, 2.10s/it] 35%|███▍ | 9/26 [00:18<00:40, 2.40s/it] 38%|███▊ | 10/26 [00:19<00:34, 2.17s/it] 42%|████▏ | 11/26 [00:21<00:29, 1.96s/it] 46%|████▌ | 12/26 [00:23<00:27, 1.95s/it] 50%|█████ | 13/26 [00:24<00:24, 1.88s/it] 54%|█████▍ | 14/26 [00:26<00:21, 1.83s/it] 58%|█████▊ | 15/26 [00:27<00:18, 1.72s/it] 62%|██████▏ | 16/26 [00:29<00:16, 1.67s/it] 65%|██████▌ | 17/26 [00:31<00:15, 1.77s/it] 69%|██████▉ | 18/26 [00:33<00:13, 1.72s/it] 73%|███████▎ | 19/26 [00:35<00:13, 1.96s/it] 77%|███████▋ | 20/26 [00:37<00:10, 1.80s/it] 81%|████████ | 21/26 [00:38<00:09, 1.81s/it] 85%|████████▍ | 22/26 [00:40<00:07, 1.82s/it] 88%|████████▊ | 23/26 [00:42<00:05, 1.74s/it] 92%|█████████▏| 24/26 [00:43<00:03, 1.68s/it] 96%|█████████▌| 25/26 [00:45<00:01, 1.66s/it] 100%|██████████| 26/26 [00:46<00:00, 1.51s/it] 100%|██████████| 26/26 [00:46<00:00, 1.79s/it]
junhua024-chai-02-full-0109-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpmehhwuhe, device:0
junhua024-chai-02-full-0109-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
junhua024-chai-02-full-0109-v1-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-02-full-0109-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-02-full-0109-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-02-full-0109-v1/nvidia
junhua024-chai-02-full-0109-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-02-full-0109-v1/nvidia/config.json
junhua024-chai-02-full-0109-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-02-full-0109-v1/nvidia/special_tokens_map.json
junhua024-chai-02-full-0109-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-02-full-0109-v1/nvidia/tokenizer_config.json
junhua024-chai-02-full-0109-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-02-full-0109-v1/nvidia/tokenizer.json
junhua024-chai-02-full-0109-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-02-full-0109-v1/nvidia/flywheel_model.0.safetensors
junhua024-chai-02-full-0109-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 2/363 [00:00<00:24, 14.89it/s] Loading 0: 1%| | 4/363 [00:02<03:33, 1.68it/s] Loading 0: 1%|▏ | 5/363 [00:03<04:20, 1.38it/s] Loading 0: 2%|▏ | 8/363 [00:03<02:17, 2.58it/s] Loading 0: 2%|▏ | 9/363 [00:03<02:12, 2.68it/s] Loading 0: 3%|▎ | 10/363 [00:03<01:53, 3.11it/s] Loading 0: 3%|▎ | 11/363 [00:04<02:48, 2.08it/s] Loading 0: 3%|▎ | 12/363 [00:05<03:38, 1.60it/s] Loading 0: 4%|▍ | 14/363 [00:06<02:31, 2.31it/s] Loading 0: 4%|▍ | 15/363 [00:06<02:17, 2.52it/s] Loading 0: 4%|▍ | 16/363 [00:06<01:55, 3.01it/s] Loading 0: 5%|▍ | 18/363 [00:07<02:21, 2.43it/s] Loading 0: 6%|▌ | 21/363 [00:08<02:06, 2.70it/s] Loading 0: 6%|▌ | 22/363 [00:09<02:43, 2.08it/s] Loading 0: 6%|▋ | 23/363 [00:10<03:21, 1.69it/s] Loading 0: 7%|▋ | 26/363 [00:11<02:03, 2.73it/s] Loading 0: 7%|▋ | 27/363 [00:11<01:57, 2.86it/s] Loading 0: 8%|▊ | 28/363 [00:11<01:42, 3.26it/s] Loading 0: 8%|▊ | 29/363 [00:12<02:32, 2.19it/s] Loading 0: 9%|▊ | 31/363 [00:12<01:53, 2.92it/s] Loading 0: 9%|▉ | 32/363 [00:13<01:48, 3.05it/s] Loading 0: 9%|▉ | 33/363 [00:13<01:32, 3.56it/s] Loading 0: 10%|▉ | 35/363 [00:14<02:03, 2.66it/s] Loading 0: 10%|▉ | 36/363 [00:15<02:50, 1.91it/s] Loading 0: 11%|█ | 39/363 [00:16<02:17, 2.36it/s] Loading 0: 11%|█ | 40/363 [00:17<02:50, 1.90it/s] Loading 0: 11%|█▏ | 41/363 [00:18<03:25, 1.56it/s] Loading 0: 12%|█▏ | 44/363 [00:18<02:04, 2.56it/s] Loading 0: 12%|█▏ | 45/363 [00:18<01:57, 2.70it/s] Loading 0: 13%|█▎ | 46/363 [00:18<01:41, 3.11it/s] Loading 0: 13%|█▎ | 48/363 [00:19<01:23, 3.75it/s] Loading 0: 13%|█▎ | 49/363 [00:19<01:24, 3.71it/s] Loading 0: 14%|█▍ | 50/363 [00:19<01:14, 4.19it/s] Loading 0: 14%|█▍ | 52/363 [00:20<01:49, 2.84it/s] Loading 0: 15%|█▍ | 53/363 [00:21<02:31, 2.05it/s] Loading 0: 15%|█▍ | 54/363 [00:22<03:12, 1.61it/s] Loading 0: 16%|█▌ | 57/363 [00:23<02:24, 2.12it/s] Loading 0: 16%|█▌ | 58/363 [00:24<02:53, 1.76it/s] Loading 0: 16%|█▋ | 59/363 [00:25<03:24, 1.49it/s] Loading 0: 17%|█▋ | 62/363 [00:26<02:01, 2.49it/s] Loading 0: 17%|█▋ | 63/363 [00:26<01:53, 2.63it/s] Loading 0: 18%|█▊ | 64/363 [00:26<01:38, 3.04it/s] Loading 0: 18%|█▊ | 66/363 [00:27<01:59, 2.48it/s] Loading 0: 18%|█▊ | 67/363 [00:28<02:34, 1.91it/s] Loading 0: 19%|█▊ | 68/363 [00:29<03:10, 1.55it/s] Loading 0: 20%|█▉ | 71/363 [00:29<01:51, 2.61it/s] Loading 0: 20%|█▉ | 72/363 [00:30<01:45, 2.76it/s] Loading 0: 20%|██ | 73/363 [00:30<01:31, 3.17it/s] Loading 0: 20%|██ | 74/363 [00:31<02:15, 2.14it/s] Loading 0: 21%|██ | 75/363 [00:32<02:56, 1.64it/s] Loading 0: 21%|██ | 77/363 [00:32<02:02, 2.34it/s] Loading 0: 21%|██▏ | 78/363 [00:33<01:52, 2.54it/s] Loading 0: 22%|██▏ | 79/363 [00:33<01:33, 3.03it/s] Loading 0: 22%|██▏ | 80/363 [00:34<02:26, 1.93it/s] Loading 0: 23%|██▎ | 82/363 [00:34<01:44, 2.70it/s] Loading 0: 23%|██▎ | 83/363 [00:34<01:37, 2.86it/s] Loading 0: 23%|██▎ | 84/363 [00:34<01:23, 3.35it/s] Loading 0: 24%|██▎ | 86/363 [00:35<01:44, 2.65it/s] Loading 0: 25%|██▍ | 89/363 [00:36<01:36, 2.83it/s] Loading 0: 25%|██▍ | 90/363 [00:37<02:07, 2.14it/s] Loading 0: 25%|██▌ | 91/363 [00:38<02:39, 1.71it/s] Loading 0: 26%|██▌ | 94/363 [00:39<01:38, 2.74it/s] Loading 0: 26%|██▌ | 95/363 [00:39<01:33, 2.86it/s] Loading 0: 26%|██▋ | 96/363 [00:39<01:22, 3.25it/s] Loading 0: 27%|██▋ | 98/363 [00:40<01:43, 2.55it/s] Loading 0: 27%|██▋ | 99/363 [00:41<02:20, 1.88it/s] Loading 0: 28%|██▊ | 102/363 [00:42<01:53, 2.31it/s] Loading 0: 28%|██▊ | 103/363 [00:43<02:18, 1.88it/s] Loading 0: 29%|██▊ | 104/363 [00:44<02:45, 1.57it/s] Loading 0: 29%|██▉ | 107/363 [00:45<01:40, 2.55it/s] Loading 0: 30%|██▉ | 108/363 [00:45<01:34, 2.69it/s] Loading 0: 30%|███ | 109/363 [00:45<01:22, 3.09it/s] Loading 0: 31%|███ | 111/363 [00:45<01:07, 3.73it/s] Loading 0: 31%|███ | 112/363 [00:46<01:07, 3.71it/s] Loading 0: 31%|███ | 113/363 [00:46<00:59, 4.18it/s] Loading 0: 32%|███▏ | 115/363 [00:47<01:27, 2.83it/s] Loading 0: 32%|███▏ | 116/363 [00:48<02:00, 2.04it/s] Loading 0: 32%|███▏ | 117/363 [00:49<02:33, 1.61it/s] Loading 0: 33%|███▎ | 120/363 [00:50<01:54, 2.12it/s] Loading 0: 33%|███▎ | 121/363 [00:51<02:17, 1.75it/s] Loading 0: 34%|███▎ | 122/363 [00:52<02:42, 1.49it/s] Loading 0: 34%|███▍ | 125/363 [00:52<01:35, 2.48it/s] Loading 0: 35%|███▍ | 126/363 [00:53<01:30, 2.63it/s] Loading 0: 35%|███▍ | 127/363 [00:53<01:17, 3.05it/s] Loading 0: 36%|███▌ | 129/363 [00:54<01:33, 2.49it/s] Loading 0: 36%|███▌ | 130/363 [00:55<02:01, 1.92it/s] Loading 0: 36%|███▌ | 131/363 [00:56<02:29, 1.55it/s] Loading 0: 37%|███▋ | 134/363 [00:56<01:27, 2.63it/s] Loading 0: 37%|███▋ | 135/363 [00:56<01:22, 2.77it/s] Loading 0: 37%|███▋ | 136/363 [00:57<01:11, 3.20it/s] Loading 0: 38%|███▊ | 137/363 [00:57<01:45, 2.14it/s] Loading 0: 38%|███▊ | 138/363 [00:59<02:17, 1.64it/s] Loading 0: 39%|███▊ | 140/363 [00:59<01:35, 2.34it/s] Loading 0: 39%|███▉ | 141/363 [00:59<01:27, 2.53it/s] Loading 0: 39%|███▉ | 142/363 [00:59<01:14, 2.98it/s] Loading 0: 40%|███▉ | 144/363 [01:00<01:30, 2.41it/s] Loading 0: 40%|████ | 147/363 [01:01<01:20, 2.68it/s] Loading 0: 41%|████ | 148/363 [01:02<01:43, 2.08it/s] Loading 0: 41%|████ | 149/363 [01:03<02:07, 1.68it/s] Loading 0: 42%|████▏ | 152/363 [01:04<01:17, 2.71it/s] Loading 0: 42%|████▏ | 153/363 [01:04<01:13, 2.84it/s] Loading 0: 42%|████▏ | 154/363 [01:04<01:04, 3.25it/s] Loading 0: 43%|████▎ | 155/363 [01:05<01:35, 2.17it/s] Loading 0: 43%|████▎ | 157/363 [01:05<01:11, 2.89it/s] Loading 0: 44%|████▎ | 158/363 [01:06<01:07, 3.02it/s] Loading 0: 44%|████▍ | 159/363 [01:06<00:58, 3.51it/s] Loading 0: 44%|████▍ | 161/363 [01:07<01:17, 2.62it/s] Loading 0: 45%|████▍ | 162/363 [01:08<01:46, 1.89it/s] Loading 0: 45%|████▌ | 165/363 [01:09<01:25, 2.33it/s] Loading 0: 46%|████▌ | 166/363 [01:10<01:45, 1.87it/s] Loading 0: 46%|████▌ | 167/363 [01:11<02:07, 1.54it/s] Loading 0: 47%|████▋ | 170/363 [01:11<01:15, 2.54it/s] Loading 0: 47%|████▋ | 171/363 [01:12<01:11, 2.68it/s] Loading 0: 47%|████▋ | 172/363 [01:12<01:02, 3.08it/s] Loading 0: 48%|████▊ | 174/363 [01:12<00:50, 3.73it/s] Loading 0: 48%|████▊ | 175/363 [01:12<00:50, 3.74it/s] Loading 0: 48%|████▊ | 176/363 [01:12<00:44, 4.22it/s] Loading 0: 49%|████▉ | 178/363 [01:14<01:05, 2.82it/s] Loading 0: 49%|████▉ | 179/363 [01:14<01:29, 2.04it/s] Loading 0: 50%|████▉ | 180/363 [01:16<01:53, 1.61it/s] Loading 0: 50%|█████ | 183/363 [01:16<01:24, 2.14it/s] Loading 0: 51%|█████ | 184/363 [01:17<01:41, 1.77it/s] Loading 0: 51%|█████ | 185/363 [01:18<01:58, 1.50it/s] Loading 0: 52%|█████▏ | 188/363 [01:19<01:10, 2.49it/s] Loading 0: 52%|█████▏ | 189/363 [01:19<01:05, 2.65it/s] Loading 0: 52%|█████▏ | 190/363 [01:19<00:56, 3.06it/s] Loading 0: 53%|█████▎ | 192/363 [01:20<01:08, 2.50it/s] Loading 0: 53%|█████▎ | 193/363 [01:21<01:28, 1.93it/s] Loading 0: 53%|█████▎ | 194/363 [01:22<01:48, 1.56it/s] Loading 0: 54%|█████▍ | 197/363 [01:23<01:02, 2.66it/s] Loading 0: 55%|█████▍ | 198/363 [01:23<00:59, 2.80it/s] Loading 0: 55%|█████▍ | 199/363 [01:23<00:50, 3.24it/s] Loading 0: 55%|█████▌ | 200/363 [01:24<01:15, 2.17it/s] Loading 0: 55%|█████▌ | 201/363 [01:25<01:37, 1.65it/s] Loading 0: 56%|█████▌ | 203/363 [01:25<01:07, 2.37it/s] Loading 0: 56%|█████▌ | 204/363 [01:26<01:01, 2.57it/s] Loading 0: 56%|█████▋ | 205/363 [01:26<00:51, 3.06it/s] Loading 0: 57%|█████▋ | 207/363 [01:27<01:03, 2.44it/s] Loading 0: 58%|█████▊ | 210/363 [01:28<00:56, 2.72it/s] Loading 0: 58%|█████▊ | 211/363 [01:29<01:12, 2.09it/s] Loading 0: 58%|█████▊ | 212/363 [01:30<01:29, 1.69it/s] Loading 0: 59%|█████▉ | 215/363 [01:30<00:54, 2.73it/s] Loading 0: 60%|█████▉ | 216/363 [01:30<00:51, 2.85it/s] Loading 0: 60%|█████▉ | 217/363 [01:31<00:45, 3.22it/s] Loading 0: 60%|██████ | 218/363 [01:32<01:07, 2.15it/s] Loading 0: 61%|██████ | 220/363 [01:32<00:50, 2.85it/s] Loading 0: 61%|██████ | 221/363 [01:32<00:47, 2.99it/s] Loading 0: 61%|██████ | 222/363 [01:32<00:40, 3.46it/s] Loading 0: 62%|██████▏ | 224/363 [01:33<00:53, 2.62it/s] Loading 0: 62%|██████▏ | 225/363 [01:34<01:12, 1.89it/s] Loading 0: 63%|██████▎ | 228/363 [01:35<00:57, 2.35it/s] Loading 0: 63%|██████▎ | 229/363 [01:36<01:10, 1.90it/s] Loading 0: 63%|██████▎ | 230/363 [01:37<01:24, 1.58it/s] Loading 0: 64%|██████▍ | 233/363 [01:38<00:50, 2.60it/s] Loading 0: 64%|██████▍ | 234/363 [01:38<00:47, 2.74it/s] Loading 0: 65%|██████▍ | 235/363 [01:38<00:40, 3.16it/s] Loading 0: 65%|██████▌ | 237/363 [01:38<00:32, 3.82it/s] Loading 0: 66%|██████▌ | 238/363 [01:39<00:33, 3.77it/s] Loading 0: 66%|██████▌ | 239/363 [01:39<00:29, 4.28it/s] Loading 0: 66%|██████▋ | 241/363 [01:40<00:42, 2.88it/s] Loading 0: 67%|██████▋ | 242/363 [01:41<00:58, 2.08it/s] Loading 0: 67%|██████▋ | 243/363 [01:42<01:14, 1.62it/s] Loading 0: 68%|██████▊ | 246/363 [01:43<00:54, 2.14it/s] Loading 0: 68%|██████▊ | 247/363 [01:44<01:05, 1.78it/s] Loading 0: 68%|██████▊ | 248/363 [01:45<01:16, 1.50it/s] Loading 0: 69%|██████▉ | 251/363 [01:45<00:44, 2.50it/s] Loading 0: 69%|██████▉ | 252/363 [01:45<00:41, 2.66it/s] Loading 0: 70%|██████▉ | 253/363 [01:46<00:35, 3.07it/s] Loading 0: 70%|███████ | 255/363 [01:47<00:42, 2.51it/s] Loading 0: 71%|███████ | 256/363 [01:48<00:55, 1.94it/s] Loading 0: 71%|███████ | 257/363 [01:49<01:07, 1.58it/s] Loading 0: 72%|███████▏ | 260/363 [01:49<00:38, 2.67it/s] Loading 0: 72%|███████▏ | 261/363 [01:49<00:36, 2.81it/s] Loading 0: 72%|███████▏ | 262/363 [01:49<00:31, 3.24it/s] Loading 0: 72%|███████▏ | 263/363 [01:50<00:46, 2.17it/s] Loading 0: 73%|███████▎ | 264/363 [01:51<00:59, 1.65it/s] Loading 0: 73%|███████▎ | 266/363 [01:52<00:41, 2.36it/s] Loading 0: 74%|███████▎ | 267/363 [01:52<00:37, 2.55it/s] Loading 0: 74%|███████▍ | 268/363 [01:52<00:31, 3.04it/s] Loading 0: 74%|███████▍ | 270/363 [01:53<00:38, 2.43it/s] Loading 0: 75%|███████▌ | 273/363 [01:54<00:33, 2.71it/s] Loading 0: 75%|███████▌ | 274/363 [01:55<00:42, 2.09it/s] Loading 0: 76%|███████▌ | 275/363 [01:56<00:52, 1.69it/s] Loading 0: 77%|███████▋ | 278/363 [01:56<00:31, 2.72it/s] Loading 0: 77%|███████▋ | 279/363 [01:57<00:29, 2.85it/s] Loading 0: 77%|███████▋ | 280/363 [01:57<00:25, 3.28it/s] Loading 0: 77%|███████▋ | 281/363 [01:58<00:37, 2.21it/s] Loading 0: 78%|███████▊ | 283/363 [01:58<00:27, 2.94it/s] Loading 0: 78%|███████▊ | 284/363 [01:58<00:25, 3.06it/s] Loading 0: 79%|███████▊ | 285/363 [01:59<00:21, 3.57it/s] Loading 0: 79%|███████▉ | 287/363 [02:00<00:28, 2.66it/s] Loading 0: 79%|███████▉ | 288/363 [02:01<00:39, 1.91it/s] Loading 0: 80%|████████ | 291/363 [02:02<00:30, 2.36it/s] Loading 0: 80%|████████ | 292/363 [02:03<00:37, 1.91it/s] Loading 0: 81%|████████ | 293/363 [02:04<00:44, 1.58it/s] Loading 0: 82%|████████▏ | 296/363 [02:04<00:25, 2.59it/s] Loading 0: 82%|████████▏ | 297/363 [02:04<00:24, 2.73it/s] Loading 0: 82%|████████▏ | 298/363 [02:04<00:20, 3.14it/s] Loading 0: 83%|████████▎ | 300/363 [02:05<00:16, 3.79it/s] Loading 0: 83%|████████▎ | 301/363 [02:05<00:16, 3.74it/s] Loading 0: 83%|████████▎ | 302/363 [02:05<00:14, 4.22it/s] Loading 0: 84%|████████▎ | 304/363 [02:06<00:20, 2.88it/s] Loading 0: 84%|████████▍ | 305/363 [02:07<00:27, 2.08it/s] Loading 0: 84%|████████▍ | 306/363 [02:08<00:34, 1.64it/s] Loading 0: 85%|████████▌ | 309/363 [02:09<00:24, 2.17it/s] Loading 0: 85%|████████▌ | 310/363 [02:10<00:29, 1.80it/s] Loading 0: 86%|████████▌ | 311/363 [02:11<00:34, 1.52it/s] Loading 0: 87%|████████▋ | 314/363 [02:11<00:19, 2.52it/s] Loading 0: 87%|████████▋ | 315/363 [02:12<00:17, 2.68it/s] Loading 0: 87%|████████▋ | 316/363 [02:12<00:15, 3.09it/s] Loading 0: 88%|████████▊ | 318/363 [02:13<00:17, 2.52it/s] Loading 0: 88%|████████▊ | 319/363 [02:14<00:22, 1.93it/s] Loading 0: 88%|████████▊ | 320/363 [02:15<00:27, 1.56it/s] Loading 0: 89%|████████▉ | 323/363 [02:15<00:15, 2.65it/s] Loading 0: 89%|████████▉ | 324/363 [02:15<00:13, 2.79it/s] Loading 0: 90%|████████▉ | 325/363 [02:16<00:11, 3.22it/s] Loading 0: 90%|████████▉ | 326/363 [02:17<00:17, 2.16it/s] Loading 0: 90%|█████████ | 327/363 [02:18<00:21, 1.65it/s] Loading 0: 91%|█████████ | 329/363 [02:18<00:14, 2.36it/s] Loading 0: 91%|█████████ | 330/363 [02:18<00:12, 2.56it/s] Loading 0: 91%|█████████ | 331/363 [02:18<00:10, 3.05it/s] Loading 0: 92%|█████████▏| 333/363 [02:19<00:12, 2.45it/s] Loading 0: 93%|█████████▎| 336/363 [02:20<00:09, 2.73it/s] Loading 0: 93%|█████████▎| 337/363 [02:21<00:12, 2.11it/s] Loading 0: 93%|█████████▎| 338/363 [02:22<00:14, 1.70it/s] Loading 0: 94%|█████████▍| 341/363 [02:23<00:08, 2.74it/s] Loading 0: 94%|█████████▍| 342/363 [02:23<00:07, 2.86it/s] Loading 0: 94%|█████████▍| 343/363 [02:23<00:06, 3.24it/s] Loading 0: 95%|█████████▍| 344/363 [02:24<00:08, 2.18it/s] Loading 0: 95%|█████████▌| 346/363 [02:24<00:05, 2.90it/s] Loading 0: 96%|█████████▌| 347/363 [02:25<00:05, 3.02it/s] Loading 0: 96%|█████████▌| 348/363 [02:25<00:04, 3.51it/s] Loading 0: 96%|█████████▌| 349/363 [02:25<00:03, 3.53it/s] Loading 0: 96%|█████████▋| 350/363 [02:25<00:03, 4.21it/s] Loading 0: 97%|█████████▋| 351/363 [02:26<00:05, 2.28it/s] Loading 0: 97%|█████████▋| 352/363 [02:27<00:06, 1.66it/s] Loading 0: 98%|█████████▊| 355/363 [02:28<00:03, 2.21it/s] Loading 0: 98%|█████████▊| 356/363 [02:29<00:03, 1.80it/s] Loading 0: 98%|█████████▊| 357/363 [02:30<00:03, 1.50it/s] Loading 0: 99%|█████████▉| 360/363 [02:31<00:01, 2.55it/s] Loading 0: 99%|█████████▉| 361/363 [02:31<00:00, 2.70it/s] Loading 0: 100%|█████████▉| 362/363 [02:31<00:00, 3.10it/s]
Job junhua024-chai-02-full-0109-v1-mkmlizer completed after 403.45s with status: succeeded
Stopping job with name junhua024-chai-02-full-0109-v1-mkmlizer
Pipeline stage MKMLizer completed in 404.00s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-02-full-0109-v1
Waiting for inference service junhua024-chai-02-full-0109-v1 to be ready
Failed to get response for submission chaiml-llama-8b-nis-retu_8225_v2: HTTPConnectionPool(host='chaiml-llama-8b-nis-retu-8225-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-llama-8b-nis-retu_8225_v2: HTTPConnectionPool(host='chaiml-llama-8b-nis-retu-8225-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-02-full-0109-v1 ready after 322.053484916687s
Pipeline stage MKMLDeployer completed in 322.73s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.489794969558716s
Received healthy response to inference request in 1.8235619068145752s
Received healthy response to inference request in 1.824357032775879s
Received healthy response to inference request in 1.933547019958496s
5 requests
1 failed requests
5th percentile: 1.823720932006836
10th percentile: 1.8238799571990967
20th percentile: 1.8241980075836182
30th percentile: 1.8461950302124024
40th percentile: 1.8898710250854491
50th percentile: 1.933547019958496
60th percentile: 2.156046199798584
70th percentile: 2.378545379638672
80th percentile: 6.040745735168461
90th percentile: 13.142647266387941
95th percentile: 16.693598031997677
99th percentile: 19.534358644485472
mean time: 5.663161945343018
%s, retrying in %s seconds...
Received healthy response to inference request in 1.5083868503570557s
Received healthy response to inference request in 1.6406376361846924s
Received healthy response to inference request in 1.5345635414123535s
Received healthy response to inference request in 1.5313701629638672s
Received healthy response to inference request in 1.6956450939178467s
5 requests
0 failed requests
5th percentile: 1.512983512878418
10th percentile: 1.5175801753997802
20th percentile: 1.526773500442505
30th percentile: 1.5320088386535644
40th percentile: 1.533286190032959
50th percentile: 1.5345635414123535
60th percentile: 1.576993179321289
70th percentile: 1.6194228172302245
80th percentile: 1.6516391277313232
90th percentile: 1.673642110824585
95th percentile: 1.684643602371216
99th percentile: 1.6934447956085206
mean time: 1.582120656967163
Pipeline stage StressChecker completed in 39.28s
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 1.00s
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
junhua024-chai-02-full-0109_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 2704.43s
Shutdown handler de-registered
junhua024-chai-02-full-0109_v1 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-02-full-0109_v1 status is now torndown due to DeploymentManager action