submission_id: sao10k-hanami-7x_v1
developer_uid: sao10k
best_of: 4
celo_rating: 1241.7
display_name: Hanami-70
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.2, 'top_p': 1.0, 'min_p': 0.2, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n\n', '<|eot_id|>', '\n\n{user_name}', '\nYou:', '<|end_header_id|>'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
is_internal_developer: False
language_model: Sao10K/Hanami-7X
latencies: [{'batch_size': 1, 'throughput': 0.25786800826999, 'latency_mean': 3.877898954153061, 'latency_p50': 3.9065483808517456, 'latency_p90': 4.3901550531387326}, {'batch_size': 2, 'throughput': 0.4253612573116705, 'latency_mean': 4.695802361965179, 'latency_p50': 4.703146696090698, 'latency_p90': 5.21333909034729}, {'batch_size': 3, 'throughput': 0.5835873095656545, 'latency_mean': 5.118059620857239, 'latency_p50': 5.145003080368042, 'latency_p90': 5.618739104270935}, {'batch_size': 5, 'throughput': 0.8228298060142376, 'latency_mean': 6.022669515609741, 'latency_p50': 5.977034330368042, 'latency_p90': 6.903988289833069}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Sao10K/Hanami-7X
model_name: Hanami-70
model_num_parameters: 70553706496.0
model_repo: Sao10K/Hanami-7X
model_size: 71B
num_battles: 13512
num_wins: 6772
ranking_group: single
status: torndown
submission_type: basic
timestamp: 2024-09-07T18:19:18+00:00
us_pacific_date: 2024-09-07
win_ratio: 0.5011841326228538
Download Preference Data
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 sao10k-hanami-7x-v1-mkmlizer
Waiting for job on sao10k-hanami-7x-v1-mkmlizer to finish
sao10k-hanami-7x-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-hanami-7x-v1-mkmlizer: ║ _____ __ __ ║
sao10k-hanami-7x-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
sao10k-hanami-7x-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
sao10k-hanami-7x-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
sao10k-hanami-7x-v1-mkmlizer: ║ /___/ ║
sao10k-hanami-7x-v1-mkmlizer: ║ ║
sao10k-hanami-7x-v1-mkmlizer: ║ Version: 0.10.1 ║
sao10k-hanami-7x-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
sao10k-hanami-7x-v1-mkmlizer: ║ https://mk1.ai ║
sao10k-hanami-7x-v1-mkmlizer: ║ ║
sao10k-hanami-7x-v1-mkmlizer: ║ The license key for the current software has been verified as ║
sao10k-hanami-7x-v1-mkmlizer: ║ belonging to: ║
sao10k-hanami-7x-v1-mkmlizer: ║ ║
sao10k-hanami-7x-v1-mkmlizer: ║ Chai Research Corp. ║
sao10k-hanami-7x-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
sao10k-hanami-7x-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
sao10k-hanami-7x-v1-mkmlizer: ║ ║
sao10k-hanami-7x-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
sao10k-hanami-7x-v1-mkmlizer: Downloaded to shared memory in 239.050s
sao10k-hanami-7x-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp31hl2j9w, device:0
sao10k-hanami-7x-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
sao10k-hanami-7x-v1-mkmlizer: quantized model in 135.228s
sao10k-hanami-7x-v1-mkmlizer: Processed model Sao10K/Hanami-7X in 374.279s
sao10k-hanami-7x-v1-mkmlizer: creating bucket guanaco-mkml-models
sao10k-hanami-7x-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-hanami-7x-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-hanami-7x-v1
sao10k-hanami-7x-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-hanami-7x-v1/config.json
sao10k-hanami-7x-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-hanami-7x-v1/special_tokens_map.json
sao10k-hanami-7x-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-hanami-7x-v1/tokenizer_config.json
sao10k-hanami-7x-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-hanami-7x-v1/tokenizer.json
sao10k-hanami-7x-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.5.safetensors s3://guanaco-mkml-models/sao10k-hanami-7x-v1/flywheel_model.5.safetensors
sao10k-hanami-7x-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/sao10k-hanami-7x-v1/flywheel_model.2.safetensors
sao10k-hanami-7x-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.4.safetensors s3://guanaco-mkml-models/sao10k-hanami-7x-v1/flywheel_model.4.safetensors
sao10k-hanami-7x-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-hanami-7x-v1/flywheel_model.0.safetensors
sao10k-hanami-7x-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/sao10k-hanami-7x-v1/flywheel_model.1.safetensors
sao10k-hanami-7x-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/sao10k-hanami-7x-v1/flywheel_model.3.safetensors
sao10k-hanami-7x-v1-mkmlizer: Loading 0: 0%| | 0/723 [00:00<?, ?it/s] Loading 0: 0%| | 2/723 [00:09<57:08, 4.76s/it] Loading 0: 1%| | 5/723 [00:09<18:27, 1.54s/it] Loading 0: 1%| | 7/723 [00:09<11:30, 1.04it/s] Loading 0: 2%|▏ | 13/723 [00:09<04:26, 2.66it/s] Loading 0: 2%|▏ | 16/723 [00:10<03:17, 3.58it/s] Loading 0: 3%|▎ | 20/723 [00:10<02:09, 5.41it/s] Loading 0: 3%|▎ | 23/723 [00:10<01:41, 6.91it/s] Loading 0: 4%|▎ | 26/723 [00:10<01:20, 8.64it/s] Loading 0: 4%|▍ | 29/723 [00:10<01:03, 10.86it/s] Loading 0: 4%|▍ | 32/723 [00:11<01:12, 9.47it/s] Loading 0: 5%|▍ | 35/723 [00:11<01:00, 11.45it/s] Loading 0: 5%|▌ | 38/723 [00:11<00:49, 13.85it/s] Loading 0: 6%|▌ | 41/723 [00:11<00:43, 15.78it/s] Loading 0: 6%|▌ | 44/723 [00:11<00:39, 17.38it/s] Loading 0: 7%|▋ | 47/723 [00:11<00:34, 19.57it/s] Loading 0: 7%|▋ | 50/723 [00:11<00:33, 20.29it/s] Loading 0: 7%|▋ | 53/723 [00:11<00:32, 20.89it/s] Loading 0: 8%|▊ | 56/723 [00:12<00:29, 22.34it/s] Loading 0: 8%|▊ | 59/723 [00:12<00:29, 22.26it/s] Loading 0: 9%|▊ | 62/723 [00:12<00:29, 22.24it/s] Loading 0: 9%|▉ | 65/723 [00:12<00:28, 23.45it/s] Loading 0: 9%|▉ | 68/723 [00:12<00:28, 23.03it/s] Loading 0: 10%|▉ | 71/723 [00:12<00:28, 22.53it/s] Loading 0: 10%|█ | 74/723 [00:12<00:27, 23.77it/s] Loading 0: 11%|█ | 77/723 [00:12<00:27, 23.62it/s] Loading 0: 11%|█ | 80/723 [00:13<00:27, 23.23it/s] Loading 0: 11%|█▏ | 83/723 [00:13<00:27, 23.50it/s] Loading 0: 12%|█▏ | 86/723 [00:13<00:42, 14.99it/s] Loading 0: 12%|█▏ | 88/723 [00:13<00:41, 15.22it/s] Loading 0: 13%|█▎ | 92/723 [00:13<00:32, 19.34it/s] Loading 0: 13%|█▎ | 95/723 [00:13<00:31, 20.03it/s] Loading 0: 14%|█▎ | 98/723 [00:14<00:30, 20.72it/s] Loading 0: 14%|█▍ | 101/723 [00:14<00:27, 22.37it/s] Loading 0: 14%|█▍ | 104/723 [00:14<00:27, 22.30it/s] Loading 0: 15%|█▍ | 107/723 [00:14<00:28, 21.99it/s] Loading 0: 15%|█▌ | 110/723 [00:14<00:26, 23.02it/s] Loading 0: 16%|█▌ | 113/723 [00:29<15:20, 1.51s/it] Loading 0: 16%|█▌ | 114/723 [00:29<13:35, 1.34s/it] Loading 0: 16%|█▋ | 118/723 [00:29<08:03, 1.25it/s] Loading 0: 17%|█▋ | 121/723 [00:29<05:45, 1.74it/s] Loading 0: 17%|█▋ | 123/723 [00:30<04:39, 2.15it/s] Loading 0: 18%|█▊ | 128/723 [00:30<02:39, 3.73it/s] Loading 0: 18%|█▊ | 131/723 [00:30<02:02, 4.83it/s] Loading 0: 19%|█▊ | 134/723 [00:30<01:34, 6.20it/s] Loading 0: 19%|█▉ | 137/723 [00:30<01:28, 6.66it/s] Loading 0: 19%|█▉ | 140/723 [00:31<01:10, 8.28it/s] Loading 0: 20%|█▉ | 142/723 [00:31<01:03, 9.18it/s] Loading 0: 20%|██ | 146/723 [00:31<00:45, 12.60it/s] Loading 0: 21%|██ | 149/723 [00:31<00:40, 14.21it/s] Loading 0: 21%|██ | 152/723 [00:31<00:36, 15.76it/s] Loading 0: 21%|██▏ | 155/723 [00:31<00:31, 17.80it/s] Loading 0: 22%|██▏ | 158/723 [00:31<00:30, 18.40it/s] Loading 0: 22%|██▏ | 161/723 [00:31<00:29, 19.35it/s] Loading 0: 23%|██▎ | 164/723 [00:32<00:26, 20.72it/s] Loading 0: 23%|██▎ | 167/723 [00:32<00:27, 20.54it/s] Loading 0: 24%|██▎ | 170/723 [00:32<00:26, 20.83it/s] Loading 0: 24%|██▍ | 173/723 [00:32<00:24, 22.09it/s] Loading 0: 24%|██▍ | 176/723 [00:32<00:25, 21.25it/s] Loading 0: 25%|██▍ | 179/723 [00:32<00:25, 21.13it/s] Loading 0: 25%|██▌ | 182/723 [00:32<00:23, 22.76it/s] Loading 0: 26%|██▌ | 185/723 [00:33<00:24, 21.87it/s] Loading 0: 26%|██▌ | 188/723 [00:33<00:38, 13.93it/s] Loading 0: 26%|██▋ | 191/723 [00:33<00:32, 16.19it/s] Loading 0: 27%|██▋ | 194/723 [00:33<00:30, 17.12it/s] Loading 0: 27%|██▋ | 197/723 [00:33<00:29, 18.07it/s] Loading 0: 28%|██▊ | 200/723 [00:33<00:26, 19.71it/s] Loading 0: 28%|██▊ | 203/723 [00:34<00:25, 20.08it/s] Loading 0: 28%|██▊ | 206/723 [00:34<00:27, 18.84it/s] Loading 0: 29%|██▉ | 209/723 [00:34<00:25, 20.55it/s] Loading 0: 29%|██▉ | 212/723 [00:34<00:24, 20.50it/s] Loading 0: 30%|██▉ | 215/723 [00:34<00:24, 20.92it/s] Loading 0: 30%|███ | 218/723 [00:34<00:22, 22.27it/s] Loading 0: 31%|███ | 221/723 [00:34<00:23, 21.70it/s] Loading 0: 31%|███ | 224/723 [00:35<00:22, 21.76it/s] Loading 0: 31%|███▏ | 227/723 [00:35<00:21, 23.10it/s] Loading 0: 32%|███▏ | 230/723 [00:35<00:22, 22.15it/s] Loading 0: 32%|███▏ | 233/723 [00:35<00:22, 22.07it/s] Loading 0: 33%|███▎ | 236/723 [00:35<00:21, 22.89it/s] Loading 0: 33%|███▎ | 239/723 [00:36<00:34, 14.07it/s] Loading 0: 33%|███▎ | 241/723 [00:36<00:33, 14.35it/s] Loading 0: 34%|███▍ | 245/723 [00:36<00:26, 18.09it/s] Loading 0: 34%|███▍ | 248/723 [00:36<00:25, 18.57it/s] Loading 0: 34%|███▍ | 248/723 [00:50<00:25, 18.57it/s] Loading 0: 34%|███▍ | 249/723 [00:50<14:28, 1.83s/it] Loading 0: 35%|███▍ | 253/723 [00:51<08:33, 1.09s/it] Loading 0: 35%|███▌ | 256/723 [00:51<06:04, 1.28it/s] Loading 0: 36%|███▌ | 258/723 [00:51<04:50, 1.60it/s] Loading 0: 36%|███▋ | 263/723 [00:51<02:44, 2.80it/s] Loading 0: 37%|███▋ | 266/723 [00:51<02:03, 3.69it/s] Loading 0: 37%|███▋ | 269/723 [00:51<01:34, 4.81it/s] Loading 0: 38%|███▊ | 272/723 [00:52<01:11, 6.27it/s] Loading 0: 38%|███▊ | 275/723 [00:52<00:56, 7.88it/s] Loading 0: 38%|███▊ | 278/723 [00:52<00:45, 9.77it/s] Loading 0: 39%|███▉ | 281/723 [00:52<00:36, 12.00it/s] Loading 0: 39%|███▉ | 284/723 [00:52<00:32, 13.71it/s] Loading 0: 40%|███▉ | 287/723 [00:52<00:28, 15.18it/s] Loading 0: 40%|████ | 290/723 [00:52<00:24, 17.43it/s] Loading 0: 41%|████ | 293/723 [00:53<00:33, 12.86it/s] Loading 0: 41%|████ | 295/723 [00:53<00:31, 13.49it/s] Loading 0: 41%|████▏ | 299/723 [00:53<00:24, 17.66it/s] Loading 0: 42%|████▏ | 302/723 [00:53<00:22, 18.46it/s] Loading 0: 42%|████▏ | 305/723 [00:53<00:21, 19.63it/s] Loading 0: 43%|████▎ | 308/723 [00:53<00:19, 21.31it/s] Loading 0: 43%|████▎ | 311/723 [00:53<00:19, 21.16it/s] Loading 0: 43%|████▎ | 314/723 [00:54<00:19, 20.97it/s] Loading 0: 44%|████▍ | 317/723 [00:54<00:18, 22.17it/s] Loading 0: 44%|████▍ | 320/723 [00:54<00:18, 21.50it/s] Loading 0: 45%|████▍ | 323/723 [00:54<00:18, 21.84it/s] Loading 0: 45%|████▌ | 326/723 [00:54<00:17, 22.82it/s] Loading 0: 46%|████▌ | 329/723 [00:54<00:17, 22.01it/s] Loading 0: 46%|████▌ | 332/723 [00:54<00:17, 21.82it/s] Loading 0: 46%|████▋ | 335/723 [00:55<00:16, 23.40it/s] Loading 0: 47%|████▋ | 338/723 [00:55<00:16, 22.66it/s] Loading 0: 47%|████▋ | 341/723 [00:55<00:16, 22.60it/s] Loading 0: 48%|████▊ | 344/723 [00:55<00:24, 15.21it/s] Loading 0: 48%|████▊ | 347/723 [00:55<00:22, 16.44it/s] Loading 0: 48%|████▊ | 349/723 [00:55<00:22, 16.29it/s] Loading 0: 49%|████▉ | 353/723 [00:56<00:18, 20.12it/s] Loading 0: 49%|████▉ | 356/723 [00:56<00:18, 20.01it/s] Loading 0: 50%|████▉ | 359/723 [00:56<00:17, 20.23it/s] Loading 0: 50%|█████ | 362/723 [00:56<00:16, 21.59it/s] Loading 0: 50%|█████ | 365/723 [00:56<00:16, 21.38it/s] Loading 0: 51%|█████ | 368/723 [00:56<00:16, 21.57it/s] Loading 0: 51%|█████▏ | 371/723 [00:56<00:15, 22.73it/s] Loading 0: 52%|█████▏ | 374/723 [00:57<00:15, 22.04it/s] Loading 0: 52%|█████▏ | 377/723 [00:57<00:15, 22.18it/s] Loading 0: 53%|█████▎ | 380/723 [00:57<00:14, 23.49it/s] Loading 0: 53%|█████▎ | 383/723 [00:57<00:15, 22.52it/s] Loading 0: 53%|█████▎ | 383/723 [01:11<00:15, 22.52it/s] Loading 0: 53%|█████▎ | 384/723 [01:11<10:17, 1.82s/it] Loading 0: 54%|█████▎ | 388/723 [01:11<06:01, 1.08s/it] Loading 0: 54%|█████▍ | 391/723 [01:12<04:14, 1.30it/s] Loading 0: 54%|█████▍ | 394/723 [01:12<03:10, 1.72it/s] Loading 0: 55%|█████▌ | 398/723 [01:12<02:02, 2.65it/s] Loading 0: 55%|█████▌ | 401/723 [01:12<01:31, 3.50it/s] Loading 0: 56%|█████▌ | 404/723 [01:12<01:08, 4.63it/s] Loading 0: 56%|█████▋ | 407/723 [01:13<00:51, 6.11it/s] Loading 0: 57%|█████▋ | 410/723 [01:13<00:40, 7.67it/s] Loading 0: 57%|█████▋ | 413/723 [01:13<00:32, 9.54it/s] Loading 0: 58%|█████▊ | 416/723 [01:13<00:25, 11.82it/s] Loading 0: 58%|█████▊ | 419/723 [01:13<00:22, 13.63it/s] Loading 0: 58%|█████▊ | 422/723 [01:13<00:19, 15.32it/s] Loading 0: 59%|█████▉ | 425/723 [01:13<00:17, 17.49it/s] Loading 0: 59%|█████▉ | 428/723 [01:13<00:16, 18.18it/s] Loading 0: 60%|█████▉ | 431/723 [01:14<00:15, 19.38it/s] Loading 0: 60%|██████ | 434/723 [01:14<00:13, 20.98it/s] Loading 0: 60%|██████ | 437/723 [01:14<00:13, 20.64it/s] Loading 0: 61%|██████ | 440/723 [01:14<00:13, 20.94it/s] Loading 0: 61%|██████▏ | 443/723 [01:14<00:12, 21.73it/s] Loading 0: 62%|██████▏ | 446/723 [01:15<00:19, 13.93it/s] Loading 0: 62%|██████▏ | 448/723 [01:15<00:19, 14.08it/s] Loading 0: 63%|██████▎ | 452/723 [01:15<00:15, 17.82it/s] Loading 0: 63%|██████▎ | 455/723 [01:15<00:14, 18.41it/s] Loading 0: 63%|██████▎ | 458/723 [01:15<00:14, 18.84it/s] Loading 0: 64%|██████▍ | 461/723 [01:15<00:12, 20.53it/s] Loading 0: 64%|██████▍ | 464/723 [01:15<00:12, 20.37it/s] Loading 0: 65%|██████▍ | 467/723 [01:15<00:12, 20.84it/s] Loading 0: 65%|██████▌ | 470/723 [01:16<00:11, 22.27it/s] Loading 0: 65%|██████▌ | 473/723 [01:16<00:11, 21.96it/s] Loading 0: 66%|██████▌ | 476/723 [01:16<00:11, 21.89it/s] Loading 0: 66%|██████▋ | 479/723 [01:16<00:10, 22.84it/s] Loading 0: 67%|██████▋ | 482/723 [01:16<00:10, 22.23it/s] Loading 0: 67%|██████▋ | 485/723 [01:16<00:10, 22.55it/s] Loading 0: 67%|██████▋ | 488/723 [01:16<00:09, 23.70it/s] Loading 0: 68%|██████▊ | 491/723 [01:17<00:10, 22.71it/s] Loading 0: 68%|██████▊ | 494/723 [01:17<00:10, 22.58it/s] Loading 0: 69%|██████▊ | 497/723 [01:17<00:09, 23.61it/s] Loading 0: 69%|██████▉ | 500/723 [01:17<00:14, 15.12it/s] Loading 0: 69%|██████▉ | 502/723 [01:17<00:14, 15.05it/s] Loading 0: 70%|██████▉ | 506/723 [01:17<00:11, 18.99it/s] Loading 0: 70%|███████ | 509/723 [01:18<00:11, 19.04it/s] Loading 0: 71%|███████ | 512/723 [01:18<00:10, 19.77it/s] Loading 0: 71%|███████ | 515/723 [01:18<00:09, 21.40it/s] Loading 0: 72%|███████▏ | 518/723 [01:18<00:09, 21.18it/s] Loading 0: 72%|███████▏ | 518/723 [01:32<00:09, 21.18it/s] Loading 0: 72%|███████▏ | 519/723 [01:32<06:06, 1.80s/it] Loading 0: 72%|███████▏ | 523/723 [01:32<03:33, 1.07s/it] Loading 0: 73%|███████▎ | 526/723 [01:32<02:29, 1.31it/s] Loading 0: 73%|███████▎ | 529/723 [01:33<01:46, 1.83it/s] Loading 0: 74%|███████▎ | 533/723 [01:33<01:07, 2.80it/s] Loading 0: 74%|███████▍ | 536/723 [01:33<00:50, 3.72it/s] Loading 0: 75%|███████▍ | 539/723 [01:33<00:37, 4.89it/s] Loading 0: 75%|███████▍ | 542/723 [01:33<00:28, 6.37it/s] Loading 0: 75%|███████▌ | 545/723 [01:33<00:22, 7.98it/s] Loading 0: 76%|███████▌ | 548/723 [01:33<00:17, 9.86it/s] Loading 0: 76%|███████▌ | 551/723 [01:34<00:18, 9.40it/s] Loading 0: 77%|███████▋ | 554/723 [01:34<00:15, 11.24it/s] Loading 0: 77%|███████▋ | 556/723 [01:34<00:13, 12.03it/s] Loading 0: 77%|███████▋ | 560/723 [01:34<00:10, 15.92it/s] Loading 0: 78%|███████▊ | 563/723 [01:34<00:09, 16.94it/s] Loading 0: 78%|███████▊ | 566/723 [01:34<00:08, 18.34it/s] Loading 0: 79%|███████▊ | 569/723 [01:35<00:07, 19.99it/s] Loading 0: 79%|███████▉ | 572/723 [01:35<00:07, 20.14it/s] Loading 0: 80%|███████▉ | 575/723 [01:35<00:07, 20.78it/s] Loading 0: 80%|███████▉ | 578/723 [01:35<00:06, 21.80it/s] Loading 0: 80%|████████ | 581/723 [01:35<00:06, 21.50it/s] Loading 0: 81%|████████ | 584/723 [01:35<00:06, 21.83it/s] Loading 0: 81%|████████ | 587/723 [01:35<00:05, 22.84it/s] Loading 0: 82%|████████▏ | 590/723 [01:36<00:05, 22.18it/s] Loading 0: 82%|████████▏ | 593/723 [01:36<00:05, 22.53it/s] Loading 0: 82%|████████▏ | 596/723 [01:36<00:05, 23.83it/s] Loading 0: 83%|████████▎ | 599/723 [01:36<00:05, 22.56it/s] Loading 0: 83%|████████▎ | 602/723 [01:36<00:08, 14.57it/s] Loading 0: 84%|████████▎ | 605/723 [01:36<00:07, 16.54it/s] Loading 0: 84%|████████▍ | 608/723 [01:37<00:06, 17.39it/s] Loading 0: 85%|████████▍ | 611/723 [01:37<00:06, 18.29it/s] Loading 0: 85%|████████▍ | 614/723 [01:37<00:05, 20.34it/s] Loading 0: 85%|████████▌ | 617/723 [01:37<00:05, 20.33it/s] Loading 0: 86%|████████▌ | 620/723 [01:37<00:04, 21.03it/s] Loading 0: 86%|████████▌ | 623/723 [01:37<00:04, 22.47it/s] Loading 0: 87%|████████▋ | 626/723 [01:37<00:04, 22.17it/s] Loading 0: 87%|████████▋ | 629/723 [01:37<00:04, 22.31it/s] Loading 0: 87%|████████▋ | 632/723 [01:38<00:03, 23.31it/s] Loading 0: 88%|████████▊ | 635/723 [01:38<00:03, 22.48it/s] Loading 0: 88%|████████▊ | 638/723 [01:38<00:03, 22.09it/s] Loading 0: 89%|████████▊ | 641/723 [01:38<00:03, 22.97it/s] Loading 0: 89%|████████▉ | 644/723 [01:38<00:03, 22.35it/s] Loading 0: 89%|████████▉ | 647/723 [01:38<00:03, 22.66it/s] Loading 0: 90%|████████▉ | 650/723 [01:38<00:03, 24.11it/s] Loading 0: 90%|█████████ | 653/723 [01:39<00:04, 14.92it/s] Loading 0: 90%|█████████ | 653/723 [01:53<00:04, 14.92it/s] Loading 0: 90%|█████████ | 654/723 [01:53<02:06, 1.83s/it] Loading 0: 91%|█████████ | 657/723 [01:53<01:19, 1.20s/it] Loading 0: 91%|█████████▏| 660/723 [01:53<00:51, 1.22it/s] Loading 0: 92%|█████████▏| 663/723 [01:54<00:35, 1.70it/s] Loading 0: 92%|█████████▏| 668/723 [01:54<00:18, 2.91it/s] Loading 0: 93%|█████████▎| 671/723 [01:54<00:13, 3.79it/s] Loading 0: 93%|█████████▎| 674/723 [01:54<00:09, 4.93it/s] Loading 0: 94%|█████████▎| 677/723 [01:54<00:07, 6.39it/s] Loading 0: 94%|█████████▍| 680/723 [01:54<00:05, 7.99it/s] Loading 0: 94%|█████████▍| 683/723 [01:54<00:04, 9.84it/s] Loading 0: 95%|█████████▍| 686/723 [01:54<00:03, 12.05it/s] Loading 0: 95%|█████████▌| 689/723 [01:55<00:02, 13.81it/s] Loading 0: 96%|█████████▌| 692/723 [01:55<00:01, 15.63it/s] Loading 0: 96%|█████████▌| 695/723 [01:55<00:01, 17.58it/s] Loading 0: 97%|█████████▋| 698/723 [01:55<00:01, 18.17it/s] Loading 0: 97%|█████████▋| 701/723 [01:55<00:01, 19.01it/s] Loading 0: 97%|█████████▋| 704/723 [01:55<00:00, 20.69it/s] Loading 0: 98%|█████████▊| 707/723 [01:56<00:01, 14.41it/s] Loading 0: 98%|█████████▊| 709/723 [01:56<00:00, 14.69it/s] Loading 0: 99%|█████████▊| 713/723 [01:56<00:00, 18.35it/s] Loading 0: 99%|█████████▉| 716/723 [01:56<00:00, 19.00it/s] Loading 0: 99%|█████████▉| 719/723 [01:56<00:00, 19.85it/s] Loading 0: 100%|█████████▉| 722/723 [01:56<00:00, 21.21it/s]
Job sao10k-hanami-7x-v1-mkmlizer completed after 422.26s with status: succeeded
Stopping job with name sao10k-hanami-7x-v1-mkmlizer
Pipeline stage MKMLizer completed in 423.57s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sao10k-hanami-7x-v1
Waiting for inference service sao10k-hanami-7x-v1 to be ready
Failed to get response for submission blend_jerun_2024-08-22: ('http://chaiml-lexical-nemo-v4-1k1e5-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:53922->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission chaiml-llama-8b-pairwis_8189_v19: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:36990->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission chaiml-llama-8b-pairwis_8189_v19: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:48220->127.0.0.1:8080: read: connection reset by peer\n')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service sao10k-hanami-7x-v1 ready after 150.95271968841553s
Pipeline stage MKMLDeployer completed in 152.12s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.340216398239136s
Received healthy response to inference request in 5.31818699836731s
Received healthy response to inference request in 5.011355400085449s
Received healthy response to inference request in 4.574952602386475s
Received healthy response to inference request in 4.904443740844727s
5 requests
0 failed requests
5th percentile: 4.640850830078125
10th percentile: 4.706749057769775
20th percentile: 4.838545513153076
30th percentile: 4.925826072692871
40th percentile: 4.96859073638916
50th percentile: 5.011355400085449
60th percentile: 5.134088039398193
70th percentile: 5.2568206787109375
80th percentile: 5.322592878341675
90th percentile: 5.3314046382904055
95th percentile: 5.33581051826477
99th percentile: 5.339335222244262
mean time: 5.029831027984619
%s, retrying in %s seconds...
Received healthy response to inference request in 4.222384452819824s
Received healthy response to inference request in 4.161991596221924s
Received healthy response to inference request in 4.326411247253418s
Received healthy response to inference request in 4.031514406204224s
Received healthy response to inference request in 3.4603946208953857s
5 requests
0 failed requests
5th percentile: 3.5746185779571533
10th percentile: 3.688842535018921
20th percentile: 3.917290449142456
30th percentile: 4.0576098442077635
40th percentile: 4.109800720214844
50th percentile: 4.161991596221924
60th percentile: 4.186148738861084
70th percentile: 4.210305881500244
80th percentile: 4.243189811706543
90th percentile: 4.2848005294799805
95th percentile: 4.305605888366699
99th percentile: 4.322250175476074
mean time: 4.040539264678955
Pipeline stage StressChecker completed in 47.70s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 4.11s
Shutdown handler de-registered
sao10k-hanami-7x_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.98s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sao10k-hanami-7x-v1-profiler
Waiting for inference service sao10k-hanami-7x-v1-profiler to be ready
Inference service sao10k-hanami-7x-v1-profiler ready after 150.3623776435852s
Pipeline stage MKMLProfilerDeployer completed in 150.81s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sao10k-hanami-7x-v1-profiler-predictor-00001-deployment-5bz5frd:/code/chaiverse_profiler_1725733985 --namespace tenant-chaiml-guanaco
kubectl exec -it sao10k-hanami-7x-v1-profiler-predictor-00001-deployment-5bz5frd --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725733985 && python profiles.py profile --best_of_n 4 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 512 --output_tokens 64 --summary /code/chaiverse_profiler_1725733985/summary.json'
kubectl exec -it sao10k-hanami-7x-v1-profiler-predictor-00001-deployment-5bz5frd --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725733985/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1841.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sao10k-hanami-7x-v1-profiler is running
Tearing down inference service sao10k-hanami-7x-v1-profiler
Service sao10k-hanami-7x-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.78s
Shutdown handler de-registered
sao10k-hanami-7x_v1 status is now inactive due to auto deactivation removed underperforming models
sao10k-hanami-7x_v1 status is now torndown due to DeploymentManager action
sao10k-hanami-7x_v1 status is now torndown due to DeploymentManager action