Running pipeline stage MKMLizer
Starting job with name cycy233-l3-ss-e-v2-c1-v2-mkmlizer
Waiting for job on cycy233-l3-ss-e-v2-c1-v2-mkmlizer to finish
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: ║ _____ __ __ ║
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: ║ /___/ ║
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: ║ ║
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: ║ Version: 0.9.9 ║
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: ║ ║
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: ║ belonging to: ║
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: ║ ║
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: ║ ║
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: Downloaded to shared memory in 21.671s
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjywr8lrz, device:0
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: quantized model in 26.997s
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: Processed model cycy233/L3-ss-e-v2-c1 in 48.669s
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-ss-e-v2-c1-v2
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-ss-e-v2-c1-v2/config.json
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-ss-e-v2-c1-v2/special_tokens_map.json
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-ss-e-v2-c1-v2/tokenizer_config.json
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-ss-e-v2-c1-v2/tokenizer.json
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-ss-e-v2-c1-v2/flywheel_model.0.safetensors
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cycy233-l3-ss-e-v2-c1-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 1%|▏ | 4/291 [00:00<00:08, 32.77it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:05, 51.80it/s]
Loading 0: 8%|▊ | 22/291 [00:00<00:04, 63.56it/s]
Loading 0: 11%|█ | 31/291 [00:00<00:04, 58.32it/s]
Loading 0: 14%|█▎ | 40/291 [00:00<00:04, 59.71it/s]
Loading 0: 17%|█▋ | 49/291 [00:00<00:03, 65.37it/s]
Loading 0: 20%|█▉ | 58/291 [00:00<00:03, 70.28it/s]
Loading 0: 23%|██▎ | 67/291 [00:01<00:03, 66.32it/s]
Loading 0: 26%|██▌ | 76/291 [00:01<00:03, 70.20it/s]
Loading 0: 29%|██▉ | 84/291 [00:02<00:10, 19.21it/s]
Loading 0: 31%|███ | 90/291 [00:02<00:09, 22.17it/s]
Loading 0: 33%|███▎ | 97/291 [00:02<00:07, 26.98it/s]
Loading 0: 36%|███▋ | 106/291 [00:02<00:05, 34.35it/s]
Loading 0: 40%|███▉ | 116/291 [00:02<00:03, 44.46it/s]
Loading 0: 43%|████▎ | 124/291 [00:02<00:03, 50.65it/s]
Loading 0: 46%|████▌ | 133/291 [00:03<00:02, 57.49it/s]
Loading 0: 49%|████▉ | 142/291 [00:03<00:02, 58.82it/s]
Loading 0: 52%|█████▏ | 151/291 [00:03<00:02, 61.37it/s]
Loading 0: 55%|█████▍ | 160/291 [00:03<00:01, 67.51it/s]
Loading 0: 58%|█████▊ | 169/291 [00:03<00:01, 71.94it/s]
Loading 0: 61%|██████ | 178/291 [00:03<00:01, 73.46it/s]
Loading 0: 64%|██████▍ | 187/291 [00:04<00:05, 19.97it/s]
Loading 0: 67%|██████▋ | 196/291 [00:04<00:03, 25.31it/s]
Loading 0: 70%|███████ | 205/291 [00:05<00:02, 31.21it/s]
Loading 0: 74%|███████▎ | 214/291 [00:05<00:02, 37.94it/s]
Loading 0: 77%|███████▋ | 223/291 [00:05<00:01, 45.29it/s]
Loading 0: 80%|███████▉ | 232/291 [00:05<00:01, 50.28it/s]
Loading 0: 83%|████████▎ | 241/291 [00:05<00:00, 54.37it/s]
Loading 0: 86%|████████▌ | 250/291 [00:05<00:00, 58.81it/s]
Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 64.70it/s]
Loading 0: 92%|█████████▏| 268/291 [00:05<00:00, 69.67it/s]
Loading 0: 95%|█████████▌| 277/291 [00:06<00:00, 72.52it/s]
Loading 0: 98%|█████████▊| 286/291 [00:06<00:00, 73.59it/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.
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: warnings.warn(
cycy233-l3-ss-e-v2-c1-v2-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.
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: warnings.warn(
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: Saving duration: 0.326s
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.712s
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-ss-e-v2-c1-v2_reward
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-ss-e-v2-c1-v2_reward/config.json
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-ss-e-v2-c1-v2_reward/special_tokens_map.json
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-ss-e-v2-c1-v2_reward/tokenizer_config.json
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-ss-e-v2-c1-v2_reward/merges.txt
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-ss-e-v2-c1-v2_reward/vocab.json
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-ss-e-v2-c1-v2_reward/tokenizer.json
cycy233-l3-ss-e-v2-c1-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-ss-e-v2-c1-v2_reward/reward.tensors
Job cycy233-l3-ss-e-v2-c1-v2-mkmlizer completed after 89.78s with status: succeeded
Stopping job with name cycy233-l3-ss-e-v2-c1-v2-mkmlizer
Pipeline stage MKMLizer completed in 91.75s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-ss-e-v2-c1-v2
Waiting for inference service cycy233-l3-ss-e-v2-c1-v2 to be ready
Inference service cycy233-l3-ss-e-v2-c1-v2 ready after 301.45145416259766s
Pipeline stage ISVCDeployer completed in 303.58s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.994616985321045s
Received healthy response to inference request in 1.1623141765594482s
Received healthy response to inference request in 1.1434659957885742s
Received healthy response to inference request in 1.117781639099121s
Received healthy response to inference request in 1.1832225322723389s
5 requests
0 failed requests
5th percentile: 1.1229185104370116
10th percentile: 1.1280553817749024
20th percentile: 1.1383291244506837
30th percentile: 1.147235631942749
40th percentile: 1.1547749042510986
50th percentile: 1.1623141765594482
60th percentile: 1.1706775188446046
70th percentile: 1.1790408611297607
80th percentile: 1.3455014228820803
90th percentile: 1.6700592041015625
95th percentile: 1.8323380947113035
99th percentile: 1.9621612071990966
mean time: 1.3202802658081054
Pipeline stage StressChecker completed in 7.36s
cycy233-l3-ss-e-v2-c1_v2 status is now deployed due to DeploymentManager action
cycy233-l3-ss-e-v2-c1_v2 status is now inactive due to auto deactivation removed underperforming models
cycy233-l3-ss-e-v2-c1_v2 status is now torndown due to DeploymentManager action