submission_id: zonemercy-vingt-deux-gfv_3432_v2
developer_uid: chai_backend_admin
best_of: 8
celo_rating: 1234.87
display_name: temp-8
family_friendly_score: 0.0
formatter: {'memory_template': 'Bot Name: {bot_name}\n####\n', 'prompt_template': '', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A6000': 1}
ineligible_reason: num_battles<5000
is_internal_developer: True
language_model: zonemercy/Vingt-Deux-gfv1v2ep2
latencies: [{'batch_size': 1, 'throughput': 0.38305995441226487, 'latency_mean': 2.6104589426517486, 'latency_p50': 2.6053626537323, 'latency_p90': 2.883561062812805}, {'batch_size': 2, 'throughput': 0.6071667286331621, 'latency_mean': 3.288931735754013, 'latency_p50': 3.2903023958206177, 'latency_p90': 3.6561081647872924}, {'batch_size': 3, 'throughput': 0.7653289796727545, 'latency_mean': 3.9144016873836516, 'latency_p50': 3.8768956661224365, 'latency_p90': 4.307798051834107}, {'batch_size': 4, 'throughput': 0.8857363587051064, 'latency_mean': 4.482188686132431, 'latency_p50': 4.486079573631287, 'latency_p90': 5.042812347412109}, {'batch_size': 5, 'throughput': 0.9819905543663499, 'latency_mean': 5.068827984333038, 'latency_p50': 5.076302528381348, 'latency_p90': 5.6718902587890625}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: zonemercy/Vingt-Deux-gfv
model_name: temp-8
model_num_parameters: 22247282688.0
model_repo: zonemercy/Vingt-Deux-gfv1v2ep2
model_size: 22B
num_battles: 3631
num_wins: 1734
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 0.72
timestamp: 2024-09-24T22:33:11+00:00
us_pacific_date: 2024-09-24
win_ratio: 0.4775543927292757
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 zonemercy-vingt-deux-gfv-3432-v2-mkmlizer
Waiting for job on zonemercy-vingt-deux-gfv-3432-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: ║ _____ __ __ ║
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: ║ /___/ ║
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: ║ ║
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: ║ Version: 0.10.1 ║
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: ║ https://mk1.ai ║
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: ║ ║
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: ║ The license key for the current software has been verified as ║
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: ║ belonging to: ║
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: ║ ║
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: ║ Chai Research Corp. ║
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: ║ ║
zonemercy-vingt-deux-gfv-3432-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
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
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
Failed to get response for submission blend_jopos_2024-09-20: ('http://mistralai-mistral-small-5341-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:49512->127.0.0.1:8080: read: connection reset by peer\n')
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: Downloaded to shared memory in 109.664s
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_d5jhlw2, device:0
zonemercy-vingt-deux-gfv-3432-v2-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
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
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: quantized model in 50.334s
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: Processed model zonemercy/Vingt-Deux-gfv1v2ep2 in 159.997s
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-3432-v2
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-3432-v2/special_tokens_map.json
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-3432-v2/config.json
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-3432-v2/tokenizer_config.json
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-3432-v2/tokenizer.json
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-3432-v2/flywheel_model.1.safetensors
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-3432-v2/flywheel_model.0.safetensors
zonemercy-vingt-deux-gfv-3432-v2-mkmlizer: Loading 0: 0%| | 0/507 [00:00<?, ?it/s] Loading 0: 1%| | 4/507 [00:00<00:14, 35.32it/s] Loading 0: 2%|▏ | 8/507 [00:00<00:17, 29.25it/s] Loading 0: 2%|▏ | 12/507 [00:00<00:17, 28.06it/s] Loading 0: 3%|▎ | 15/507 [00:00<00:20, 23.82it/s] Loading 0: 4%|▎ | 19/507 [00:00<00:17, 27.34it/s] Loading 0: 5%|▍ | 23/507 [00:00<00:16, 29.52it/s] Loading 0: 5%|▌ | 27/507 [00:01<00:26, 18.42it/s] Loading 0: 6%|▌ | 31/507 [00:01<00:22, 21.56it/s] Loading 0: 7%|▋ | 34/507 [00:01<00:21, 22.37it/s] Loading 0: 8%|▊ | 39/507 [00:01<00:18, 25.34it/s] Loading 0: 8%|▊ | 42/507 [00:01<00:19, 23.29it/s] Loading 0: 9%|▉ | 46/507 [00:01<00:17, 26.14it/s] Loading 0: 10%|▉ | 50/507 [00:01<00:15, 28.71it/s] Loading 0: 11%|█ | 54/507 [00:02<00:23, 19.28it/s] Loading 0: 11%|█▏ | 58/507 [00:02<00:20, 22.10it/s] Loading 0: 12%|█▏ | 61/507 [00:02<00:19, 22.73it/s] Loading 0: 13%|█▎ | 66/507 [00:02<00:17, 24.87it/s] Loading 0: 14%|█▎ | 69/507 [00:02<00:19, 22.74it/s] Loading 0: 14%|█▍ | 73/507 [00:03<00:16, 25.97it/s] Loading 0: 15%|█▌ | 77/507 [00:03<00:15, 28.25it/s] Loading 0: 16%|█▌ | 81/507 [00:03<00:21, 20.26it/s] Loading 0: 17%|█▋ | 84/507 [00:03<00:19, 21.25it/s] Loading 0: 17%|█▋ | 88/507 [00:03<00:18, 22.38it/s] Loading 0: 18%|█▊ | 92/507 [00:03<00:16, 25.69it/s] Loading 0: 19%|█▊ | 95/507 [00:04<00:18, 22.53it/s] Loading 0: 20%|█▉ | 99/507 [00:04<00:16, 25.20it/s] Loading 0: 20%|██ | 102/507 [00:04<00:16, 25.02it/s] Loading 0: 21%|██ | 105/507 [00:04<00:15, 25.98it/s] Loading 0: 21%|██▏ | 108/507 [00:04<00:22, 17.46it/s] Loading 0: 22%|██▏ | 112/507 [00:04<00:18, 21.01it/s] Loading 0: 23%|██▎ | 115/507 [00:04<00:18, 21.75it/s] Loading 0: 23%|██▎ | 118/507 [00:05<00:16, 23.41it/s] Loading 0: 24%|██▍ | 121/507 [00:05<00:16, 23.83it/s] Loading 0: 24%|██▍ | 124/507 [00:05<00:15, 24.22it/s] Loading 0: 25%|██▌ | 127/507 [00:05<00:15, 24.98it/s] Loading 0: 26%|██▌ | 131/507 [00:05<00:13, 27.68it/s] Loading 0: 26%|██▋ | 134/507 [00:05<00:18, 19.73it/s] Loading 0: 27%|██▋ | 137/507 [00:05<00:17, 21.34it/s] Loading 0: 28%|██▊ | 140/507 [00:06<00:20, 18.05it/s] Loading 0: 29%|██▊ | 145/507 [00:06<00:15, 23.98it/s] Loading 0: 29%|██▉ | 148/507 [00:06<00:14, 24.40it/s] Loading 0: 30%|██▉ | 151/507 [00:06<00:14, 24.63it/s] Loading 0: 31%|███ | 155/507 [00:06<00:14, 24.78it/s] Loading 0: 32%|███▏ | 160/507 [00:06<00:14, 23.36it/s] Loading 0: 32%|███▏ | 163/507 [00:07<00:16, 21.47it/s] Loading 0: 33%|███▎ | 166/507 [00:07<00:15, 22.49it/s] Loading 0: 33%|███▎ | 169/507 [00:07<00:14, 23.10it/s] Loading 0: 34%|███▍ | 172/507 [00:07<00:13, 24.60it/s] Loading 0: 35%|███▍ | 175/507 [00:07<00:13, 23.89it/s] Loading 0: 35%|███▌ | 178/507 [00:07<00:13, 23.59it/s] Loading 0: 36%|███▌ | 182/507 [00:07<00:13, 23.99it/s] Loading 0: 37%|███▋ | 186/507 [00:07<00:11, 27.45it/s] Loading 0: 37%|███▋ | 189/507 [00:08<00:17, 18.17it/s] Loading 0: 38%|███▊ | 193/507 [00:08<00:14, 21.69it/s] Loading 0: 39%|███▊ | 196/507 [00:08<00:13, 22.45it/s] Loading 0: 40%|███▉ | 201/507 [00:08<00:11, 25.56it/s] Loading 0: 40%|████ | 204/507 [00:08<00:12, 23.49it/s] Loading 0: 41%|████ | 208/507 [00:08<00:11, 26.39it/s] Loading 0: 42%|████▏ | 212/507 [00:08<00:10, 28.48it/s] Loading 0: 43%|████▎ | 216/507 [00:09<00:15, 19.33it/s] Loading 0: 43%|████▎ | 220/507 [00:09<00:12, 22.19it/s] Loading 0: 44%|████▍ | 223/507 [00:09<00:12, 22.71it/s] Loading 0: 45%|████▍ | 228/507 [00:09<00:11, 25.18it/s] Loading 0: 46%|████▌ | 231/507 [00:09<00:11, 23.23it/s] Loading 0: 46%|████▋ | 235/507 [00:09<00:10, 26.25it/s] Loading 0: 47%|████▋ | 239/507 [00:10<00:09, 28.92it/s] Loading 0: 48%|████▊ | 243/507 [00:10<00:13, 19.02it/s] Loading 0: 49%|████▊ | 247/507 [00:10<00:11, 21.85it/s] Loading 0: 49%|████▉ | 250/507 [00:10<00:11, 22.56it/s] Loading 0: 50%|█████ | 255/507 [00:10<00:10, 24.86it/s] Loading 0: 51%|█████ | 258/507 [00:11<00:11, 22.50it/s] Loading 0: 52%|█████▏ | 262/507 [00:11<00:09, 25.79it/s] Loading 0: 52%|█████▏ | 266/507 [00:11<00:08, 28.36it/s] Loading 0: 53%|█████▎ | 270/507 [00:11<00:12, 18.80it/s] Loading 0: 54%|█████▍ | 274/507 [00:11<00:10, 21.82it/s] Loading 0: 55%|█████▍ | 277/507 [00:11<00:10, 22.54it/s] Loading 0: 56%|█████▌ | 282/507 [00:12<00:09, 24.73it/s] Loading 0: 56%|█████▌ | 285/507 [00:12<00:09, 22.93it/s] Loading 0: 57%|█████▋ | 289/507 [00:12<00:08, 26.18it/s] Loading 0: 58%|█████▊ | 293/507 [00:12<00:07, 28.77it/s] Loading 0: 59%|█████▊ | 297/507 [00:12<00:11, 19.01it/s] Loading 0: 59%|█████▉ | 300/507 [00:27<04:12, 1.22s/it] Loading 0: 60%|█████▉ | 302/507 [00:27<03:27, 1.01s/it] Loading 0: 60%|██████ | 306/507 [00:27<02:14, 1.49it/s] Loading 0: 61%|██████ | 309/507 [00:27<01:38, 2.01it/s] Loading 0: 62%|██████▏ | 312/507 [00:27<01:12, 2.67it/s] Loading 0: 62%|██████▏ | 316/507 [00:27<00:48, 3.95it/s] Loading 0: 63%|██████▎ | 320/507 [00:28<00:33, 5.63it/s] Loading 0: 64%|██████▎ | 323/507 [00:28<00:28, 6.45it/s] Loading 0: 64%|██████▍ | 326/507 [00:28<00:22, 8.16it/s] Loading 0: 65%|██████▍ | 329/507 [00:28<00:19, 9.24it/s] Loading 0: 66%|██████▌ | 334/507 [00:28<00:12, 13.63it/s] Loading 0: 66%|██████▋ | 337/507 [00:28<00:10, 15.50it/s] Loading 0: 67%|██████▋ | 340/507 [00:28<00:09, 17.36it/s] Loading 0: 68%|██████▊ | 344/507 [00:29<00:08, 19.41it/s] Loading 0: 69%|██████▊ | 348/507 [00:29<00:06, 23.30it/s] Loading 0: 69%|██████▉ | 352/507 [00:29<00:08, 18.72it/s] Loading 0: 70%|███████ | 355/507 [00:29<00:07, 19.97it/s] Loading 0: 71%|███████ | 358/507 [00:29<00:07, 20.84it/s] Loading 0: 72%|███████▏ | 363/507 [00:29<00:06, 23.84it/s] Loading 0: 72%|███████▏ | 366/507 [00:30<00:06, 22.34it/s] Loading 0: 73%|███████▎ | 370/507 [00:30<00:05, 25.12it/s] Loading 0: 74%|███████▍ | 374/507 [00:30<00:04, 27.46it/s] Loading 0: 74%|███████▍ | 377/507 [00:30<00:06, 20.18it/s] Loading 0: 75%|███████▍ | 380/507 [00:30<00:05, 21.53it/s] Loading 0: 76%|███████▌ | 383/507 [00:30<00:06, 18.14it/s] Loading 0: 77%|███████▋ | 388/507 [00:31<00:05, 23.78it/s] Loading 0: 77%|███████▋ | 391/507 [00:31<00:04, 24.03it/s] Loading 0: 78%|███████▊ | 394/507 [00:31<00:04, 24.25it/s] Loading 0: 79%|███████▊ | 398/507 [00:31<00:04, 24.54it/s] Loading 0: 79%|███████▉ | 402/507 [00:31<00:03, 28.04it/s] Loading 0: 80%|████████ | 406/507 [00:31<00:05, 19.79it/s] Loading 0: 81%|████████ | 409/507 [00:32<00:04, 21.08it/s] Loading 0: 81%|████████▏ | 412/507 [00:32<00:04, 21.85it/s] Loading 0: 82%|████████▏ | 417/507 [00:32<00:03, 24.30it/s] Loading 0: 83%|████████▎ | 420/507 [00:32<00:03, 22.56it/s] Loading 0: 84%|████████▎ | 424/507 [00:32<00:03, 25.86it/s] Loading 0: 84%|████████▍ | 428/507 [00:32<00:02, 28.24it/s] Loading 0: 85%|████████▌ | 432/507 [00:33<00:04, 18.74it/s] Loading 0: 86%|████████▌ | 436/507 [00:33<00:03, 21.84it/s] Loading 0: 87%|████████▋ | 439/507 [00:33<00:03, 22.26it/s] Loading 0: 87%|████████▋ | 442/507 [00:33<00:02, 23.56it/s] Loading 0: 88%|████████▊ | 445/507 [00:33<00:02, 23.41it/s] Loading 0: 88%|████████▊ | 448/507 [00:33<00:02, 23.82it/s] Loading 0: 89%|████████▉ | 452/507 [00:33<00:02, 24.08it/s] Loading 0: 90%|████████▉ | 456/507 [00:33<00:01, 27.56it/s] Loading 0: 91%|█████████ | 459/507 [00:34<00:02, 18.20it/s] Loading 0: 91%|█████████▏| 463/507 [00:34<00:02, 21.50it/s] Loading 0: 92%|█████████▏| 466/507 [00:34<00:01, 22.43it/s] Loading 0: 93%|█████████▎| 471/507 [00:34<00:01, 25.45it/s] Loading 0: 93%|█████████▎| 474/507 [00:34<00:01, 23.46it/s] Loading 0: 94%|█████████▍| 478/507 [00:34<00:01, 26.37it/s] Loading 0: 95%|█████████▌| 482/507 [00:35<00:00, 28.88it/s] Loading 0: 96%|█████████▌| 486/507 [00:37<00:04, 4.95it/s] Loading 0: 96%|█████████▋| 489/507 [00:37<00:02, 6.22it/s] Loading 0: 97%|█████████▋| 492/507 [00:37<00:02, 7.28it/s] Loading 0: 98%|█████████▊| 497/507 [00:37<00:00, 10.81it/s] Loading 0: 99%|█████████▊| 500/507 [00:37<00:00, 12.48it/s] Loading 0: 99%|█████████▉| 503/507 [00:38<00:00, 14.20it/s] Loading 0: 100%|█████████▉| 506/507 [00:38<00:00, 16.43it/s]
Job zonemercy-vingt-deux-gfv-3432-v2-mkmlizer completed after 187.92s with status: succeeded
Stopping job with name zonemercy-vingt-deux-gfv-3432-v2-mkmlizer
Pipeline stage MKMLizer completed in 188.48s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-vingt-deux-gfv-3432-v2
Waiting for inference service zonemercy-vingt-deux-gfv-3432-v2 to be ready
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
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
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 zonemercy-vingt-deux-gfv-3432-v2 ready after 211.77982711791992s
Pipeline stage MKMLDeployer completed in 212.31s
run pipeline stage %s
Running pipeline stage StressChecker
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
Received healthy response to inference request in 3.0693414211273193s
Received healthy response to inference request in 2.6000518798828125s
Received healthy response to inference request in 3.1736502647399902s
Received healthy response to inference request in 2.4678494930267334s
Received healthy response to inference request in 3.428833484649658s
5 requests
0 failed requests
5th percentile: 2.4942899703979493
10th percentile: 2.520730447769165
20th percentile: 2.5736114025115966
30th percentile: 2.693909788131714
40th percentile: 2.881625604629517
50th percentile: 3.0693414211273193
60th percentile: 3.1110649585723875
70th percentile: 3.152788496017456
80th percentile: 3.2246869087219237
90th percentile: 3.326760196685791
95th percentile: 3.377796840667725
99th percentile: 3.4186261558532713
mean time: 2.947945308685303
Pipeline stage StressChecker completed in 16.43s
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 6.36s
Shutdown handler de-registered
zonemercy-vingt-deux-gfv_3432_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 0.15s
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 zonemercy-vingt-deux-gfv-3432-v2-profiler
Waiting for inference service zonemercy-vingt-deux-gfv-3432-v2-profiler to be ready
Inference service zonemercy-vingt-deux-gfv-3432-v2-profiler ready after 220.49249386787415s
Pipeline stage MKMLProfilerDeployer completed in 220.91s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-vingt-deux4834f6d749426e48b5027e67d2ef1e15-deplobvxj9:/code/chaiverse_profiler_1727217892 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-vingt-deux4834f6d749426e48b5027e67d2ef1e15-deplobvxj9 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727217892 && python profiles.py profile --best_of_n 8 --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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1727217892/summary.json'
kubectl exec -it zonemercy-vingt-deux4834f6d749426e48b5027e67d2ef1e15-deplobvxj9 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727217892/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1547.65s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-vingt-deux-gfv-3432-v2-profiler is running
Tearing down inference service zonemercy-vingt-deux-gfv-3432-v2-profiler
Service zonemercy-vingt-deux-gfv-3432-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.21s
Shutdown handler de-registered
zonemercy-vingt-deux-gfv_3432_v2 status is now inactive due to auto deactivation removed underperforming models
zonemercy-vingt-deux-v1-1e5_v14 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
zonemercy-vingt-deux-v1-_8973_v2 status is now torndown due to DeploymentManager action
zonemercy-vingt-deux-gfv_3432_v2 status is now torndown due to DeploymentManager action
zonemercy-vingt-deux-v1-1e5_v12 status is now torndown due to DeploymentManager action
zonemercy-vingt-deux-v2-1e5_v15 status is now torndown due to DeploymentManager action