sao10k-hina-7x

developer_uid: sao10k
submission_id: sao10k-hina-7x_v2
model_name: Hina-70
model_group: Sao10K/Hina-7X
status: torndown
timestamp: 2024-09-07T23:59:44+00:00
num_battles: 15470
num_wins: 7480
celo_rating: 1229.77
family_friendly_score: 0.0
submission_type: basic
model_repo: Sao10K/Hina-7X
model_architecture: LlamaForCausalLM
model_num_parameters: 70553706496.0
best_of: 4
max_input_tokens: 512
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.25437257421624426, 'latency_mean': 3.9311865973472595, 'latency_p50': 3.9192473888397217, 'latency_p90': 4.393234181404114}, {'batch_size': 2, 'throughput': 0.42050094452414416, 'latency_mean': 4.7507052266597745, 'latency_p50': 4.7927281856536865, 'latency_p90': 5.2019453048706055}, {'batch_size': 3, 'throughput': 0.5802589821073247, 'latency_mean': 5.149143658876419, 'latency_p50': 5.15314519405365, 'latency_p90': 5.625476336479187}, {'batch_size': 5, 'throughput': 0.8078123692187896, 'latency_mean': 6.154181975126266, 'latency_p50': 6.118534088134766, 'latency_p90': 7.05156831741333}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: Hina-70
is_internal_developer: False
language_model: Sao10K/Hina-7X
model_size: 71B
ranking_group: single
us_pacific_date: 2024-09-07
win_ratio: 0.4835164835164835
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}
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}
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-hina-7x-v2-mkmlizer
Waiting for job on sao10k-hina-7x-v2-mkmlizer to finish
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-hina-7x-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
sao10k-hina-7x-v2-mkmlizer: ║     _____            __           __                                ║
sao10k-hina-7x-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
sao10k-hina-7x-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
sao10k-hina-7x-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
sao10k-hina-7x-v2-mkmlizer: ║       /___/                                                         ║
sao10k-hina-7x-v2-mkmlizer: ║                                                                     ║
sao10k-hina-7x-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
sao10k-hina-7x-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
sao10k-hina-7x-v2-mkmlizer: ║  https://mk1.ai                                                     ║
sao10k-hina-7x-v2-mkmlizer: ║                                                                     ║
sao10k-hina-7x-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
sao10k-hina-7x-v2-mkmlizer: ║  belonging to:                                                      ║
sao10k-hina-7x-v2-mkmlizer: ║                                                                     ║
sao10k-hina-7x-v2-mkmlizer: ║  Chai Research Corp.                                                ║
sao10k-hina-7x-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
sao10k-hina-7x-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
sao10k-hina-7x-v2-mkmlizer: ║                                                                     ║
sao10k-hina-7x-v2-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
Failed to get response for submission blend_katim_2024-08-22: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:49756->127.0.0.1:8080: read: connection reset by peer\n')
sao10k-hina-7x-v2-mkmlizer: Downloaded to shared memory in 133.492s
sao10k-hina-7x-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpibf2d_nm, device:0
sao10k-hina-7x-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
sao10k-hina-7x-v2-mkmlizer: quantized model in 135.065s
sao10k-hina-7x-v2-mkmlizer: Processed model Sao10K/Hina-7X in 268.557s
sao10k-hina-7x-v2-mkmlizer: creating bucket guanaco-mkml-models
sao10k-hina-7x-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
sao10k-hina-7x-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/sao10k-hina-7x-v2
sao10k-hina-7x-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/sao10k-hina-7x-v2/config.json
sao10k-hina-7x-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/sao10k-hina-7x-v2/special_tokens_map.json
sao10k-hina-7x-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/sao10k-hina-7x-v2/tokenizer_config.json
sao10k-hina-7x-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/sao10k-hina-7x-v2/tokenizer.json
sao10k-hina-7x-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.5.safetensors s3://guanaco-mkml-models/sao10k-hina-7x-v2/flywheel_model.5.safetensors
sao10k-hina-7x-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/sao10k-hina-7x-v2/flywheel_model.0.safetensors
sao10k-hina-7x-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/sao10k-hina-7x-v2/flywheel_model.2.safetensors
sao10k-hina-7x-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/sao10k-hina-7x-v2/flywheel_model.3.safetensors
sao10k-hina-7x-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.4.safetensors s3://guanaco-mkml-models/sao10k-hina-7x-v2/flywheel_model.4.safetensors
sao10k-hina-7x-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/sao10k-hina-7x-v2/flywheel_model.1.safetensors
sao10k-hina-7x-v2-mkmlizer: 
Loading 0:   0%|          | 0/723 [00:00<?, ?it/s]
Loading 0:   0%|          | 2/723 [00:09<57:04,  4.75s/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<03:18,  3.57it/s]
Loading 0:   3%|▎         | 21/723 [00:10<01:59,  5.89it/s]
Loading 0:   3%|▎         | 25/723 [00:10<01:34,  7.38it/s]
Loading 0:   4%|▍         | 29/723 [00:10<01:10,  9.89it/s]
Loading 0:   4%|▍         | 32/723 [00:11<01:18,  8.80it/s]
Loading 0:   5%|▍         | 35/723 [00:11<01:06, 10.40it/s]
Loading 0:   5%|▌         | 38/723 [00:11<00:55, 12.45it/s]
Loading 0:   6%|▌         | 41/723 [00:11<00:48, 14.09it/s]
Loading 0:   6%|▌         | 44/723 [00:11<00:43, 15.53it/s]
Loading 0:   7%|▋         | 47/723 [00:11<00:37, 17.81it/s]
Loading 0:   7%|▋         | 50/723 [00:11<00:35, 18.90it/s]
Loading 0:   7%|▋         | 53/723 [00:11<00:33, 19.73it/s]
Loading 0:   8%|▊         | 56/723 [00:12<00:32, 20.56it/s]
Loading 0:   8%|▊         | 59/723 [00:12<00:31, 20.93it/s]
Loading 0:   9%|▊         | 62/723 [00:12<00:31, 21.13it/s]
Loading 0:   9%|▉         | 65/723 [00:12<00:29, 22.22it/s]
Loading 0:   9%|▉         | 68/723 [00:12<00:29, 22.03it/s]
Loading 0:  10%|▉         | 71/723 [00:12<00:29, 21.95it/s]
Loading 0:  10%|█         | 74/723 [00:12<00:27, 23.39it/s]
Loading 0:  11%|█         | 77/723 [00:13<00:28, 22.89it/s]
Loading 0:  11%|█         | 80/723 [00:13<00:28, 22.62it/s]
Loading 0:  11%|█▏        | 83/723 [00:13<00:26, 23.97it/s]
Loading 0:  12%|█▏        | 86/723 [00:13<00:44, 14.39it/s]
Loading 0:  12%|█▏        | 88/723 [00:13<00:44, 14.31it/s]
Loading 0:  13%|█▎        | 92/723 [00:13<00:34, 18.46it/s]
Loading 0:  13%|█▎        | 95/723 [00:14<00:32, 19.40it/s]
Loading 0:  14%|█▎        | 98/723 [00:14<00:30, 20.24it/s]
Loading 0:  14%|█▍        | 101/723 [00:14<00:28, 21.59it/s]
Loading 0:  14%|█▍        | 104/723 [00:14<00:28, 21.69it/s]
Loading 0:  15%|█▍        | 107/723 [00:14<00:28, 21.93it/s]
Loading 0:  15%|█▌        | 110/723 [00:14<00:26, 23.28it/s]
Loading 0:  16%|█▌        | 113/723 [00:29<15:18,  1.51s/it]
Loading 0:  16%|█▌        | 114/723 [00:29<13:34,  1.34s/it]
Loading 0:  16%|█▋        | 118/723 [00:29<08:02,  1.25it/s]
Loading 0:  17%|█▋        | 121/723 [00:30<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<01:35,  6.18it/s]
Loading 0:  19%|█▉        | 137/723 [00:31<01:30,  6.48it/s]
Loading 0:  19%|█▉        | 140/723 [00:31<01:12,  8.00it/s]
Loading 0:  20%|█▉        | 142/723 [00:31<01:04,  8.96it/s]
Loading 0:  20%|██        | 146/723 [00:31<00:46, 12.49it/s]
Loading 0:  21%|██        | 149/723 [00:31<00:40, 14.14it/s]
Loading 0:  21%|██        | 152/723 [00:31<00:35, 15.87it/s]
Loading 0:  21%|██▏       | 155/723 [00:31<00:31, 17.86it/s]
Loading 0:  22%|██▏       | 158/723 [00:32<00:30, 18.26it/s]
Loading 0:  22%|██▏       | 161/723 [00:32<00:29, 19.32it/s]
Loading 0:  23%|██▎       | 164/723 [00:32<00:27, 20.25it/s]
Loading 0:  23%|██▎       | 167/723 [00:32<00:27, 20.12it/s]
Loading 0:  24%|██▎       | 170/723 [00:32<00:26, 20.71it/s]
Loading 0:  24%|██▍       | 173/723 [00:32<00:25, 21.81it/s]
Loading 0:  24%|██▍       | 176/723 [00:32<00:26, 21.03it/s]
Loading 0:  25%|██▍       | 179/723 [00:32<00:25, 21.40it/s]
Loading 0:  25%|██▌       | 182/723 [00:33<00:23, 22.85it/s]
Loading 0:  26%|██▌       | 185/723 [00:33<00:24, 21.89it/s]
Loading 0:  26%|██▌       | 188/723 [00:33<00:39, 13.54it/s]
Loading 0:  26%|██▋       | 191/723 [00:33<00:33, 15.83it/s]
Loading 0:  27%|██▋       | 194/723 [00:33<00:31, 16.78it/s]
Loading 0:  27%|██▋       | 197/723 [00:34<00:29, 18.07it/s]
Loading 0:  28%|██▊       | 200/723 [00:34<00:25, 20.19it/s]
Loading 0:  28%|██▊       | 203/723 [00:34<00:25, 20.10it/s]
Loading 0:  28%|██▊       | 206/723 [00:34<00:24, 20.74it/s]
Loading 0:  29%|██▉       | 209/723 [00:34<00:22, 22.51it/s]
Loading 0:  29%|██▉       | 212/723 [00:34<00:23, 21.58it/s]
Loading 0:  30%|██▉       | 215/723 [00:34<00:23, 21.76it/s]
Loading 0:  30%|███       | 218/723 [00:34<00:22, 22.58it/s]
Loading 0:  31%|███       | 221/723 [00:35<00:23, 21.64it/s]
Loading 0:  31%|███       | 224/723 [00:35<00:23, 21.53it/s]
Loading 0:  31%|███▏      | 227/723 [00:35<00:22, 22.53it/s]
Loading 0:  32%|███▏      | 230/723 [00:35<00:22, 21.80it/s]
Loading 0:  32%|███▏      | 233/723 [00:35<00:22, 22.11it/s]
Loading 0:  33%|███▎      | 236/723 [00:35<00:20, 23.31it/s]
Loading 0:  33%|███▎      | 239/723 [00:36<00:34, 13.96it/s]
Loading 0:  33%|███▎      | 241/723 [00:36<00:33, 14.35it/s]
Loading 0:  34%|███▍      | 245/723 [00:36<00:26, 18.02it/s]
Loading 0:  34%|███▍      | 248/723 [00:36<00:25, 18.55it/s]
Loading 0:  34%|███▍      | 248/723 [00:51<00:25, 18.55it/s]
Loading 0:  34%|███▍      | 249/723 [00:51<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<02:04,  3.68it/s]
Loading 0:  37%|███▋      | 269/723 [00:52<01:34,  4.80it/s]
Loading 0:  38%|███▊      | 272/723 [00:52<01:11,  6.30it/s]
Loading 0:  38%|███▊      | 275/723 [00:52<00:57,  7.83it/s]
Loading 0:  38%|███▊      | 278/723 [00:52<00:46,  9.61it/s]
Loading 0:  39%|███▉      | 281/723 [00:52<00:37, 11.90it/s]
Loading 0:  39%|███▉      | 284/723 [00:52<00:32, 13.51it/s]
Loading 0:  40%|███▉      | 287/723 [00:52<00:29, 15.00it/s]
Loading 0:  40%|████      | 290/723 [00:53<00:25, 17.11it/s]
Loading 0:  41%|████      | 293/723 [00:53<00:35, 12.14it/s]
Loading 0:  41%|████      | 295/723 [00:53<00:33, 12.65it/s]
Loading 0:  41%|████▏     | 299/723 [00:53<00:25, 16.70it/s]
Loading 0:  42%|████▏     | 302/723 [00:53<00:24, 17.52it/s]
Loading 0:  42%|████▏     | 305/723 [00:53<00:22, 18.81it/s]
Loading 0:  43%|████▎     | 308/723 [00:54<00:19, 20.75it/s]
Loading 0:  43%|████▎     | 311/723 [00:54<00:20, 20.45it/s]
Loading 0:  43%|████▎     | 314/723 [00:54<00:19, 20.95it/s]
Loading 0:  44%|████▍     | 317/723 [00:54<00:18, 22.14it/s]
Loading 0:  44%|████▍     | 320/723 [00:54<00:18, 21.38it/s]
Loading 0:  45%|████▍     | 323/723 [00:54<00:18, 21.70it/s]
Loading 0:  45%|████▌     | 326/723 [00:54<00:17, 23.14it/s]
Loading 0:  46%|████▌     | 329/723 [00:55<00:17, 21.93it/s]
Loading 0:  46%|████▌     | 332/723 [00:55<00:17, 22.00it/s]
Loading 0:  46%|████▋     | 335/723 [00:55<00:17, 22.78it/s]
Loading 0:  47%|████▋     | 338/723 [00:55<00:17, 21.93it/s]
Loading 0:  47%|████▋     | 341/723 [00:55<00:17, 21.66it/s]
Loading 0:  48%|████▊     | 344/723 [00:55<00:27, 13.96it/s]
Loading 0:  48%|████▊     | 347/723 [00:56<00:24, 15.33it/s]
Loading 0:  48%|████▊     | 349/723 [00:56<00:24, 15.27it/s]
Loading 0:  49%|████▉     | 353/723 [00:56<00:19, 19.26it/s]
Loading 0:  49%|████▉     | 356/723 [00:56<00:18, 19.42it/s]
Loading 0:  50%|████▉     | 359/723 [00:56<00:17, 20.27it/s]
Loading 0:  50%|█████     | 362/723 [00:56<00:16, 21.93it/s]
Loading 0:  50%|█████     | 365/723 [00:56<00:17, 21.03it/s]
Loading 0:  51%|█████     | 368/723 [00:57<00:16, 21.50it/s]
Loading 0:  51%|█████▏    | 371/723 [00:57<00:15, 22.98it/s]
Loading 0:  52%|█████▏    | 374/723 [00:57<00:16, 21.64it/s]
Loading 0:  52%|█████▏    | 377/723 [00:57<00:15, 21.90it/s]
Loading 0:  53%|█████▎    | 380/723 [00:57<00:14, 22.90it/s]
Loading 0:  53%|█████▎    | 383/723 [00:57<00:15, 21.65it/s]
Loading 0:  53%|█████▎    | 383/723 [01:11<00:15, 21.65it/s]
Loading 0:  53%|█████▎    | 384/723 [01:12<10:19,  1.83s/it]
Loading 0:  54%|█████▎    | 388/723 [01:12<06:02,  1.08s/it]
Loading 0:  54%|█████▍    | 391/723 [01:12<04:15,  1.30it/s]
Loading 0:  54%|█████▍    | 394/723 [01:12<03:12,  1.71it/s]
Loading 0:  55%|█████▌    | 398/723 [01:13<02:03,  2.63it/s]
Loading 0:  55%|█████▌    | 401/723 [01:13<01:32,  3.49it/s]
Loading 0:  56%|█████▌    | 404/723 [01:13<01:09,  4.61it/s]
Loading 0:  56%|█████▋    | 407/723 [01:13<00:51,  6.10it/s]
Loading 0:  57%|█████▋    | 410/723 [01:13<00:40,  7.66it/s]
Loading 0:  57%|█████▋    | 413/723 [01:13<00:32,  9.50it/s]
Loading 0:  58%|█████▊    | 416/723 [01:13<00:26, 11.72it/s]
Loading 0:  58%|█████▊    | 419/723 [01:13<00:22, 13.31it/s]
Loading 0:  58%|█████▊    | 422/723 [01:14<00:20, 14.89it/s]
Loading 0:  59%|█████▉    | 425/723 [01:14<00:17, 17.18it/s]
Loading 0:  59%|█████▉    | 428/723 [01:14<00:16, 17.81it/s]
Loading 0:  60%|█████▉    | 431/723 [01:14<00:15, 18.36it/s]
Loading 0:  60%|██████    | 434/723 [01:14<00:14, 20.39it/s]
Loading 0:  60%|██████    | 437/723 [01:14<00:14, 20.19it/s]
Loading 0:  61%|██████    | 440/723 [01:14<00:13, 20.96it/s]
Loading 0:  61%|██████▏   | 443/723 [01:15<00:12, 22.62it/s]
Loading 0:  62%|██████▏   | 446/723 [01:15<00:20, 13.81it/s]
Loading 0:  62%|██████▏   | 448/723 [01:15<00:19, 14.02it/s]
Loading 0:  63%|██████▎   | 452/723 [01:15<00:15, 18.04it/s]
Loading 0:  63%|██████▎   | 455/723 [01:15<00:14, 18.56it/s]
Loading 0:  63%|██████▎   | 458/723 [01:16<00:13, 19.56it/s]
Loading 0:  64%|██████▍   | 461/723 [01:16<00:12, 21.25it/s]
Loading 0:  64%|██████▍   | 464/723 [01:16<00:12, 20.71it/s]
Loading 0:  65%|██████▍   | 467/723 [01:16<00:12, 20.77it/s]
Loading 0:  65%|██████▌   | 470/723 [01:16<00:11, 22.20it/s]
Loading 0:  65%|██████▌   | 473/723 [01:16<00:11, 21.52it/s]
Loading 0:  66%|██████▌   | 476/723 [01:16<00:12, 20.57it/s]
Loading 0:  66%|██████▋   | 479/723 [01:16<00:11, 21.86it/s]
Loading 0:  67%|██████▋   | 482/723 [01:17<00:11, 21.07it/s]
Loading 0:  67%|██████▋   | 485/723 [01:17<00:11, 21.51it/s]
Loading 0:  67%|██████▋   | 488/723 [01:17<00:10, 22.99it/s]
Loading 0:  68%|██████▊   | 491/723 [01:17<00:10, 21.84it/s]
Loading 0:  68%|██████▊   | 494/723 [01:17<00:10, 22.23it/s]
Loading 0:  69%|██████▊   | 497/723 [01:17<00:09, 23.40it/s]
Loading 0:  69%|██████▉   | 500/723 [01:18<00:15, 14.04it/s]
Loading 0:  69%|██████▉   | 502/723 [01:18<00:15, 14.48it/s]
Loading 0:  70%|██████▉   | 506/723 [01:18<00:11, 18.42it/s]
Loading 0:  70%|███████   | 509/723 [01:18<00:11, 19.17it/s]
Loading 0:  71%|███████   | 512/723 [01:18<00:10, 19.52it/s]
Loading 0:  71%|███████   | 515/723 [01:18<00:09, 21.33it/s]
Loading 0:  72%|███████▏  | 518/723 [01:18<00:09, 21.04it/s]
Loading 0:  72%|███████▏  | 518/723 [01:32<00:09, 21.04it/s]
Loading 0:  72%|███████▏  | 519/723 [01:32<05:55,  1.74s/it]
Loading 0:  72%|███████▏  | 523/723 [01:32<03:27,  1.04s/it]
Loading 0:  73%|███████▎  | 526/723 [01:33<02:25,  1.35it/s]
Loading 0:  73%|███████▎  | 529/723 [01:33<01:43,  1.87it/s]
Loading 0:  74%|███████▎  | 533/723 [01:33<01:06,  2.87it/s]
Loading 0:  74%|███████▍  | 536/723 [01:33<00:49,  3.79it/s]
Loading 0:  75%|███████▍  | 539/723 [01:33<00:36,  4.98it/s]
Loading 0:  75%|███████▍  | 542/723 [01:33<00:27,  6.54it/s]
Loading 0:  75%|███████▌  | 545/723 [01:33<00:21,  8.15it/s]
Loading 0:  76%|███████▌  | 548/723 [01:34<00:17, 10.04it/s]
Loading 0:  76%|███████▌  | 551/723 [01:34<00:18,  9.36it/s]
Loading 0:  77%|███████▋  | 554/723 [01:34<00:15, 11.17it/s]
Loading 0:  77%|███████▋  | 556/723 [01:34<00:14, 11.81it/s]
Loading 0:  77%|███████▋  | 560/723 [01:34<00:10, 15.62it/s]
Loading 0:  78%|███████▊  | 563/723 [01:34<00:09, 16.70it/s]
Loading 0:  78%|███████▊  | 566/723 [01:35<00:08, 18.09it/s]
Loading 0:  79%|███████▊  | 569/723 [01:35<00:07, 19.82it/s]
Loading 0:  79%|███████▉  | 572/723 [01:35<00:07, 20.03it/s]
Loading 0:  80%|███████▉  | 575/723 [01:35<00:07, 20.42it/s]
Loading 0:  80%|███████▉  | 578/723 [01:35<00:06, 22.05it/s]
Loading 0:  80%|████████  | 581/723 [01:35<00:06, 21.40it/s]
Loading 0:  81%|████████  | 584/723 [01:35<00:06, 21.83it/s]
Loading 0:  81%|████████  | 587/723 [01:36<00:06, 22.60it/s]
Loading 0:  82%|████████▏ | 590/723 [01:36<00:06, 21.86it/s]
Loading 0:  82%|████████▏ | 593/723 [01:36<00:05, 21.82it/s]
Loading 0:  82%|████████▏ | 596/723 [01:36<00:05, 22.68it/s]
Loading 0:  83%|████████▎ | 599/723 [01:36<00:05, 22.09it/s]
Loading 0:  83%|████████▎ | 602/723 [01:36<00:08, 13.76it/s]
Loading 0:  84%|████████▎ | 605/723 [01:37<00:07, 16.27it/s]
Loading 0:  84%|████████▍ | 608/723 [01:37<00:06, 17.23it/s]
Loading 0:  85%|████████▍ | 611/723 [01:37<00:06, 18.64it/s]
Loading 0:  85%|████████▍ | 614/723 [01:37<00:05, 20.77it/s]
Loading 0:  85%|████████▌ | 617/723 [01:37<00:05, 20.68it/s]
Loading 0:  86%|████████▌ | 620/723 [01:37<00:04, 21.15it/s]
Loading 0:  86%|████████▌ | 623/723 [01:37<00:04, 22.17it/s]
Loading 0:  87%|████████▋ | 626/723 [01:38<00:04, 21.55it/s]
Loading 0:  87%|████████▋ | 629/723 [01:38<00:04, 21.86it/s]
Loading 0:  87%|████████▋ | 632/723 [01:38<00:03, 23.27it/s]
Loading 0:  88%|████████▊ | 635/723 [01:38<00:03, 22.09it/s]
Loading 0:  88%|████████▊ | 638/723 [01:38<00:03, 22.35it/s]
Loading 0:  89%|████████▊ | 641/723 [01:38<00:03, 23.66it/s]
Loading 0:  89%|████████▉ | 644/723 [01:38<00:03, 22.52it/s]
Loading 0:  89%|████████▉ | 647/723 [01:38<00:03, 22.31it/s]
Loading 0:  90%|████████▉ | 650/723 [01:39<00:03, 23.70it/s]
Loading 0:  90%|█████████ | 653/723 [01:39<00:04, 14.15it/s]
Loading 0:  90%|█████████ | 653/723 [01:53<00:04, 14.15it/s]
Loading 0:  90%|█████████ | 654/723 [01:53<02:04,  1.81s/it]
Loading 0:  91%|█████████ | 658/723 [01:53<01:09,  1.07s/it]
Loading 0:  91%|█████████▏| 661/723 [01:53<00:47,  1.31it/s]
Loading 0:  92%|█████████▏| 663/723 [01:53<00:36,  1.64it/s]
Loading 0:  92%|█████████▏| 668/723 [01:54<00:19,  2.87it/s]
Loading 0:  93%|█████████▎| 671/723 [01:54<00:13,  3.77it/s]
Loading 0:  93%|█████████▎| 674/723 [01:54<00:09,  4.94it/s]
Loading 0:  94%|█████████▎| 677/723 [01:54<00:07,  6.45it/s]
Loading 0:  94%|█████████▍| 680/723 [01:54<00:05,  8.04it/s]
Loading 0:  94%|█████████▍| 683/723 [01:54<00:04,  9.81it/s]
Loading 0:  95%|█████████▍| 686/723 [01:54<00:03, 11.94it/s]
Loading 0:  95%|█████████▌| 689/723 [01:55<00:02, 13.64it/s]
Loading 0:  96%|█████████▌| 692/723 [01:55<00:02, 15.08it/s]
Loading 0:  96%|█████████▌| 695/723 [01:55<00:01, 16.92it/s]
Loading 0:  97%|█████████▋| 698/723 [01:55<00:01, 17.61it/s]
Loading 0:  97%|█████████▋| 701/723 [01:55<00:01, 18.89it/s]
Loading 0:  97%|█████████▋| 704/723 [01:55<00:00, 20.90it/s]
Loading 0:  98%|█████████▊| 707/723 [01:56<00:01, 13.66it/s]
Loading 0:  98%|█████████▊| 709/723 [01:56<00:00, 14.18it/s]
Loading 0:  99%|█████████▊| 713/723 [01:56<00:00, 18.29it/s]
Loading 0:  99%|█████████▉| 716/723 [01:56<00:00, 19.19it/s]
Loading 0:  99%|█████████▉| 719/723 [01:56<00:00, 20.14it/s]
Loading 0: 100%|█████████▉| 722/723 [01:56<00:00, 21.48it/s]
                                                            
Job sao10k-hina-7x-v2-mkmlizer completed after 316.01s with status: succeeded
Stopping job with name sao10k-hina-7x-v2-mkmlizer
Pipeline stage MKMLizer completed in 317.10s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service sao10k-hina-7x-v2
Failed to get response for submission blend_susol_2024-08-22: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:39832->127.0.0.1:8080: read: connection reset by peer\n')
Waiting for inference service sao10k-hina-7x-v2 to be ready
Failed to get response for submission blend_sehof_2024-08-22: ('http://chaiml-llama-8b-pairwis-8189-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:48808->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
Inference service sao10k-hina-7x-v2 ready after 141.08491730690002s
Pipeline stage MKMLDeployer completed in 142.23s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.886085033416748s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 4.66861891746521s
Received healthy response to inference request in 5.165406703948975s
Received healthy response to inference request in 4.456876993179321s
Received healthy response to inference request in 4.224022626876831s
5 requests
0 failed requests
5th percentile: 4.270593500137329
10th percentile: 4.317164373397827
20th percentile: 4.410306119918824
30th percentile: 4.499225378036499
40th percentile: 4.5839221477508545
50th percentile: 4.66861891746521
60th percentile: 4.867334032058716
70th percentile: 5.0660491466522215
80th percentile: 5.3095423698425295
90th percentile: 5.597813701629638
95th percentile: 5.741949367523193
99th percentile: 5.857257900238037
mean time: 4.880202054977417
%s, retrying in %s seconds...
Received healthy response to inference request in 4.295407295227051s
Received healthy response to inference request in 4.541724681854248s
Received healthy response to inference request in 3.9559857845306396s
Received healthy response to inference request in 4.279115200042725s
Received healthy response to inference request in 4.20076584815979s
5 requests
0 failed requests
5th percentile: 4.004941797256469
10th percentile: 4.0538978099823
20th percentile: 4.15180983543396
30th percentile: 4.216435718536377
40th percentile: 4.247775459289551
50th percentile: 4.279115200042725
60th percentile: 4.285632038116455
70th percentile: 4.292148876190185
80th percentile: 4.34467077255249
90th percentile: 4.443197727203369
95th percentile: 4.492461204528809
99th percentile: 4.53187198638916
mean time: 4.254599761962891
Pipeline stage StressChecker completed in 47.96s
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 5.88s
Shutdown handler de-registered
sao10k-hina-7x_v2 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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service sao10k-hina-7x-v2-profiler
Waiting for inference service sao10k-hina-7x-v2-profiler to be ready
Inference service sao10k-hina-7x-v2-profiler ready after 150.37161922454834s
Pipeline stage MKMLProfilerDeployer completed in 150.77s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/sao10k-hina-7x-v2-profiler-predictor-00001-deployment-5dd9glbmz:/code/chaiverse_profiler_1725754290 --namespace tenant-chaiml-guanaco
kubectl exec -it sao10k-hina-7x-v2-profiler-predictor-00001-deployment-5dd9glbmz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725754290 && 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_1725754290/summary.json'
kubectl exec -it sao10k-hina-7x-v2-profiler-predictor-00001-deployment-5dd9glbmz --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725754290/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1864.35s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service sao10k-hina-7x-v2-profiler is running
Tearing down inference service sao10k-hina-7x-v2-profiler
Service sao10k-hina-7x-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.69s
Shutdown handler de-registered
sao10k-hina-7x_v2 status is now inactive due to auto deactivation removed underperforming models
sao10k-hina-7x_v2 status is now torndown due to DeploymentManager action