Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer to finish
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: ║ Version: 0.9.6 ║
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: Downloaded to shared memory in 61.548s
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnjjyss2y, device:0
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:11, 25.43it/s]
Loading 0: 4%|▍ | 12/291 [00:00<00:07, 39.49it/s]
Loading 0: 6%|▌ | 17/291 [00:00<00:07, 36.68it/s]
Loading 0: 7%|▋ | 21/291 [00:00<00:07, 35.01it/s]
Loading 0: 9%|▊ | 25/291 [00:00<00:07, 33.58it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:06, 40.62it/s]
Loading 0: 12%|█▏ | 36/291 [00:01<00:10, 23.27it/s]
Loading 0: 14%|█▍ | 41/291 [00:01<00:09, 25.54it/s]
Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 33.15it/s]
Loading 0: 18%|█▊ | 53/291 [00:01<00:06, 34.02it/s]
Loading 0: 20%|█▉ | 58/291 [00:01<00:06, 34.80it/s]
Loading 0: 21%|██▏ | 62/291 [00:01<00:06, 35.87it/s]
Loading 0: 23%|██▎ | 67/291 [00:02<00:06, 36.52it/s]
Loading 0: 25%|██▍ | 72/291 [00:02<00:05, 39.06it/s]
Loading 0: 26%|██▋ | 77/291 [00:02<00:06, 34.25it/s]
Loading 0: 28%|██▊ | 81/291 [00:02<00:08, 25.53it/s]
Loading 0: 29%|██▉ | 85/291 [00:02<00:07, 26.54it/s]
Loading 0: 31%|███ | 90/291 [00:02<00:06, 30.97it/s]
Loading 0: 32%|███▏ | 94/291 [00:02<00:06, 31.07it/s]
Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 33.92it/s]
Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 33.31it/s]
Loading 0: 37%|███▋ | 108/291 [00:03<00:04, 36.65it/s]
Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 34.91it/s]
Loading 0: 40%|███▉ | 116/291 [00:03<00:04, 35.50it/s]
Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 39.73it/s]
Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 37.20it/s]
Loading 0: 46%|████▌ | 133/291 [00:04<00:04, 31.79it/s]
Loading 0: 47%|████▋ | 137/291 [00:04<00:04, 32.00it/s]
Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 29.83it/s]
Loading 0: 51%|█████ | 147/291 [00:04<00:04, 34.73it/s]
Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 33.93it/s]
Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 36.32it/s]
Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 34.65it/s]
Loading 0: 57%|█████▋ | 165/291 [00:04<00:03, 37.15it/s]
Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 35.55it/s]
Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 38.02it/s]
Loading 0: 61%|██████ | 178/291 [00:05<00:03, 35.26it/s]
Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 40.84it/s]
Loading 0: 65%|██████▍ | 189/291 [00:05<00:04, 24.46it/s]
Loading 0: 67%|██████▋ | 194/291 [00:05<00:03, 26.12it/s]
Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 32.26it/s]
Loading 0: 70%|███████ | 205/291 [00:06<00:02, 31.32it/s]
Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 33.63it/s]
Loading 0: 74%|███████▎ | 214/291 [00:06<00:02, 32.65it/s]
Loading 0: 75%|███████▌ | 219/291 [00:06<00:02, 34.89it/s]
Loading 0: 77%|███████▋ | 223/291 [00:06<00:02, 33.84it/s]
Loading 0: 78%|███████▊ | 227/291 [00:06<00:01, 34.15it/s]
Loading 0: 79%|███████▉ | 231/291 [00:06<00:01, 34.38it/s]
Loading 0: 81%|████████ | 235/291 [00:07<00:02, 26.07it/s]
Loading 0: 82%|████████▏ | 239/291 [00:07<00:01, 26.05it/s]
Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 33.08it/s]
Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 31.69it/s]
Loading 0: 88%|████████▊ | 255/291 [00:07<00:01, 33.98it/s]
Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 32.57it/s]
Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 33.44it/s]
Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 32.00it/s]
Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 33.88it/s]
Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 32.87it/s]
Loading 0: 97%|█████████▋| 281/291 [00:08<00:00, 32.26it/s]
Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.52it/s]
Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.13it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: quantized model in 29.221s
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: Processed model BBChicago/Brt-8B-L3_v1.9_with_dpo_lora_s5600 in 90.769s
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-9-1812-v1
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-9-1812-v1/config.json
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-9-1812-v1/special_tokens_map.json
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-9-1812-v1/tokenizer_config.json
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-9-1812-v1/tokenizer.json
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-9-1812-v1/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: Saving duration: 1.390s
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 10.484s
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-9-1812-v1_reward
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-9-1812-v1_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-9-1812-v1_reward/config.json
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-9-1812-v1_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-9-1812-v1_reward/merges.txt
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-9-1812-v1_reward/vocab.json
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-9-1812-v1_reward/tokenizer.json
bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-9-1812-v1_reward/reward.tensors
Job bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer completed after 135.87s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-9-1812-v1-mkmlizer
Pipeline stage MKMLizer completed in 136.87s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v1-9-1812-v1
Waiting for inference service bbchicago-brt-8b-l3-v1-9-1812-v1 to be ready
Inference service bbchicago-brt-8b-l3-v1-9-1812-v1 ready after 60.59494113922119s
Pipeline stage ISVCDeployer completed in 62.21s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2692034244537354s
Received healthy response to inference request in 1.4036178588867188s
Received healthy response to inference request in 1.4025516510009766s
Received healthy response to inference request in 1.4002270698547363s
Received healthy response to inference request in 1.3988609313964844s
5 requests
0 failed requests
5th percentile: 1.3991341590881348
10th percentile: 1.3994073867797852
20th percentile: 1.399953842163086
30th percentile: 1.4006919860839844
40th percentile: 1.4016218185424805
50th percentile: 1.4025516510009766
60th percentile: 1.4029781341552734
70th percentile: 1.4034046173095702
80th percentile: 1.5767349720001222
90th percentile: 1.9229691982269288
95th percentile: 2.096086311340332
99th percentile: 2.2345800018310547
mean time: 1.5748921871185302
Pipeline stage StressChecker completed in 8.60s
bbchicago-brt-8b-l3-v1-9_1812_v1 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v1-9_1812_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-brt-8b-l3-v1-9_1812_v1
Running pipeline stage ISVCDeleter
Checking if service bbchicago-brt-8b-l3-v1-9-1812-v1 is running
Tearing down inference service bbchicago-brt-8b-l3-v1-9-1812-v1
Service bbchicago-brt-8b-l3-v1-9-1812-v1 has been torndown
Pipeline stage ISVCDeleter completed in 5.34s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-9-1812-v1/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-9-1812-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-9-1812-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-9-1812-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-9-1812-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-9-1812-v1_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-9-1812-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-9-1812-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-9-1812-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-9-1812-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-9-1812-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-9-1812-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.47s
bbchicago-brt-8b-l3-v1-9_1812_v1 status is now torndown due to DeploymentManager action