Running pipeline stage MKMLizer
Starting job with name bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer
Waiting for job on bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer to finish
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: ║ _____ __ __ ║
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: ║ /___/ ║
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: ║ Version: 0.9.7 ║
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: ║ https://mk1.ai ║
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: ║ belonging to: ║
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: ║ Chai Research Corp. ║
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: ║ ║
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: Downloaded to shared memory in 44.360s
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8fyfqr4l, device:0
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: quantized model in 29.636s
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: Processed model BBChicago/Brt-8B-L3_v1.7_with_dpo_lora_s2500 in 73.997s
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v34
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v34/config.json
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v34/special_tokens_map.json
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v34/tokenizer_config.json
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-brt-8b-l3-v1-4895-v34/flywheel_model.0.safetensors
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 2%|▏ | 5/291 [00:00<00:11, 25.73it/s]
Loading 0: 4%|▍ | 12/291 [00:00<00:07, 35.27it/s]
Loading 0: 5%|▌ | 16/291 [00:00<00:08, 32.97it/s]
Loading 0: 7%|▋ | 21/291 [00:00<00:07, 35.68it/s]
Loading 0: 9%|▊ | 25/291 [00:00<00:08, 33.21it/s]
Loading 0: 10%|█ | 30/291 [00:00<00:06, 37.62it/s]
Loading 0: 12%|█▏ | 34/291 [00:01<00:10, 24.60it/s]
Loading 0: 13%|█▎ | 38/291 [00:01<00:09, 25.94it/s]
Loading 0: 14%|█▍ | 42/291 [00:01<00:09, 25.17it/s]
Loading 0: 16%|█▋ | 48/291 [00:01<00:07, 30.54it/s]
Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 29.96it/s]
Loading 0: 20%|█▉ | 57/291 [00:01<00:07, 32.90it/s]
Loading 0: 21%|██ | 61/291 [00:01<00:07, 31.36it/s]
Loading 0: 23%|██▎ | 66/291 [00:02<00:06, 33.07it/s]
Loading 0: 24%|██▍ | 70/291 [00:02<00:07, 31.26it/s]
Loading 0: 25%|██▌ | 74/291 [00:02<00:07, 30.67it/s]
Loading 0: 27%|██▋ | 78/291 [00:02<00:07, 29.87it/s]
Loading 0: 28%|██▊ | 82/291 [00:02<00:09, 22.20it/s]
Loading 0: 29%|██▉ | 85/291 [00:02<00:08, 23.28it/s]
Loading 0: 31%|███ | 90/291 [00:03<00:07, 27.14it/s]
Loading 0: 32%|███▏ | 93/291 [00:03<00:07, 25.59it/s]
Loading 0: 34%|███▍ | 99/291 [00:03<00:06, 31.52it/s]
Loading 0: 35%|███▌ | 103/291 [00:03<00:06, 30.90it/s]
Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 34.44it/s]
Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 32.16it/s]
Loading 0: 40%|███▉ | 116/291 [00:03<00:05, 32.68it/s]
Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 37.03it/s]
Loading 0: 44%|████▎ | 127/291 [00:04<00:04, 34.74it/s]
Loading 0: 46%|████▌ | 133/291 [00:04<00:05, 30.15it/s]
Loading 0: 47%|████▋ | 137/291 [00:04<00:05, 29.41it/s]
Loading 0: 48%|████▊ | 141/291 [00:04<00:05, 27.18it/s]
Loading 0: 51%|█████ | 147/291 [00:04<00:04, 32.16it/s]
Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 31.27it/s]
Loading 0: 54%|█████▎ | 156/291 [00:05<00:03, 34.17it/s]
Loading 0: 55%|█████▍ | 160/291 [00:05<00:04, 32.31it/s]
Loading 0: 57%|█████▋ | 165/291 [00:05<00:03, 33.77it/s]
Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 31.55it/s]
Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 33.30it/s]
Loading 0: 61%|██████ | 178/291 [00:05<00:03, 31.62it/s]
Loading 0: 63%|██████▎ | 183/291 [00:05<00:03, 35.35it/s]
Loading 0: 64%|██████▍ | 187/291 [00:06<00:04, 24.80it/s]
Loading 0: 65%|██████▌ | 190/291 [00:06<00:04, 23.92it/s]
Loading 0: 67%|██████▋ | 194/291 [00:06<00:04, 23.72it/s]
Loading 0: 69%|██████▉ | 201/291 [00:06<00:02, 31.21it/s]
Loading 0: 70%|███████ | 205/291 [00:06<00:02, 30.31it/s]
Loading 0: 72%|███████▏ | 210/291 [00:06<00:02, 33.61it/s]
Loading 0: 74%|███████▎ | 214/291 [00:07<00:02, 32.28it/s]
Loading 0: 75%|███████▌ | 219/291 [00:07<00:02, 35.03it/s]
Loading 0: 77%|███████▋ | 223/291 [00:07<00:02, 33.54it/s]
Loading 0: 78%|███████▊ | 227/291 [00:07<00:01, 33.99it/s]
Loading 0: 79%|███████▉ | 231/291 [00:07<00:01, 33.79it/s]
Loading 0: 81%|████████ | 235/291 [00:07<00:02, 25.55it/s]
Loading 0: 82%|████████▏ | 239/291 [00:07<00:02, 24.81it/s]
Loading 0: 85%|████████▍ | 246/291 [00:08<00:01, 31.53it/s]
Loading 0: 86%|████████▌ | 250/291 [00:08<00:01, 30.78it/s]
Loading 0: 88%|████████▊ | 255/291 [00:08<00:01, 33.51it/s]
Loading 0: 89%|████████▉ | 259/291 [00:08<00:00, 32.33it/s]
Loading 0: 91%|█████████ | 264/291 [00:08<00:00, 34.74it/s]
Loading 0: 92%|█████████▏| 268/291 [00:08<00:00, 33.05it/s]
Loading 0: 94%|█████████▍| 273/291 [00:08<00:00, 35.68it/s]
Loading 0: 95%|█████████▌| 277/291 [00:08<00:00, 33.86it/s]
Loading 0: 97%|█████████▋| 281/291 [00:09<00:00, 34.10it/s]
Loading 0: 98%|█████████▊| 286/291 [00:14<00:01, 2.54it/s]
Loading 0: 99%|█████████▉| 289/291 [00:14<00:00, 3.16it/s]
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-4895-v34-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-v1-4895-v34-mkmlizer: warnings.warn(
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: Saving duration: 1.420s
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.231s
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: creating bucket guanaco-reward-models
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: Bucket 's3://guanaco-reward-models/' created
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v34_reward
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v34_reward/special_tokens_map.json
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v34_reward/config.json
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v34_reward/tokenizer_config.json
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v34_reward/merges.txt
bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/bbchicago-brt-8b-l3-v1-4895-v34_reward/reward.tensors
Job bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer completed after 116.21s with status: succeeded
Stopping job with name bbchicago-brt-8b-l3-v1-4895-v34-mkmlizer
Pipeline stage MKMLizer completed in 117.28s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service bbchicago-brt-8b-l3-v1-4895-v34
Waiting for inference service bbchicago-brt-8b-l3-v1-4895-v34 to be ready
Inference service bbchicago-brt-8b-l3-v1-4895-v34 ready after 111.03406119346619s
Pipeline stage ISVCDeployer completed in 113.14s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.272153854370117s
Received healthy response to inference request in 1.3794171810150146s
Received healthy response to inference request in 1.3904600143432617s
Received healthy response to inference request in 1.3976249694824219s
Received healthy response to inference request in 1.3887851238250732s
5 requests
0 failed requests
5th percentile: 1.3812907695770265
10th percentile: 1.383164358139038
20th percentile: 1.3869115352630614
30th percentile: 1.389120101928711
40th percentile: 1.3897900581359863
50th percentile: 1.3904600143432617
60th percentile: 1.3933259963989257
70th percentile: 1.3961919784545898
80th percentile: 1.5725307464599612
90th percentile: 1.922342300415039
95th percentile: 2.097248077392578
99th percentile: 2.2371726989746095
mean time: 1.5656882286071778
Pipeline stage StressChecker completed in 8.56s
bbchicago-brt-8b-l3-v1-_4895_v34 status is now deployed due to DeploymentManager action
bbchicago-brt-8b-l3-v1-_4895_v34 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of bbchicago-brt-8b-l3-v1-_4895_v34
Running pipeline stage ISVCDeleter
Checking if service bbchicago-brt-8b-l3-v1-4895-v34 is running
Tearing down inference service bbchicago-brt-8b-l3-v1-4895-v34
Service bbchicago-brt-8b-l3-v1-4895-v34 has been torndown
Pipeline stage ISVCDeleter completed in 4.35s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-4895-v34/config.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v34/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v34/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v34/tokenizer.json from bucket guanaco-mkml-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v34/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key bbchicago-brt-8b-l3-v1-4895-v34_reward/config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v34_reward/merges.txt from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v34_reward/reward.tensors from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v34_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v34_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v34_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key bbchicago-brt-8b-l3-v1-4895-v34_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.43s
bbchicago-brt-8b-l3-v1-_4895_v34 status is now torndown due to DeploymentManager action