Running pipeline stage MKMLizer
Starting job with name chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer
Waiting for job on chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer to finish
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: ║ _____ __ __ ║
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: ║ /___/ ║
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: ║ Version: 0.8.14 ║
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: ║ https://mk1.ai ║
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: ║ belonging to: ║
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: ║ Chai Research Corp. ║
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: ║ ║
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: Downloaded to shared memory in 24.834s
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: creating bucket guanaco-mkml-models
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v11
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v11/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v11/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v11/config.json
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v11/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-sao10k-l3-rp-v3-3-v11/flywheel_model.0.safetensors
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: warnings.warn(
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer:
Downloading shards: 0%| | 0/2 [00:00<?, ?it/s]
Downloading shards: 50%|█████ | 1/2 [00:07<00:07, 7.06s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.18s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00, 4.61s/it]
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer:
Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.62it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.63it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.41it/s]
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: Saving duration: 2.253s
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.993s
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: creating bucket guanaco-reward-models
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v11_reward
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v11_reward/merges.txt
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v11_reward/config.json
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v11_reward/tokenizer_config.json
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v11_reward/special_tokens_map.json
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v11_reward/vocab.json
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v11_reward/tokenizer.json
chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-sao10k-l3-rp-v3-3-v11_reward/reward.tensors
Job chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer completed after 94.88s with status: succeeded
Stopping job with name chaiml-sao10k-l3-rp-v3-3-v11-mkmlizer
Pipeline stage MKMLizer completed in 95.86s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-sao10k-l3-rp-v3-3-v11
Waiting for inference service chaiml-sao10k-l3-rp-v3-3-v11 to be ready
Inference service chaiml-sao10k-l3-rp-v3-3-v11 ready after 40.21169424057007s
Pipeline stage ISVCDeployer completed in 47.21s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0368921756744385s
Received healthy response to inference request in 1.2330131530761719s
Received healthy response to inference request in 1.2458500862121582s
Received healthy response to inference request in 1.235764980316162s
Received healthy response to inference request in 1.236177921295166s
5 requests
0 failed requests
5th percentile: 1.23356351852417
10th percentile: 1.234113883972168
20th percentile: 1.235214614868164
30th percentile: 1.235847568511963
40th percentile: 1.2360127449035645
50th percentile: 1.236177921295166
60th percentile: 1.240046787261963
70th percentile: 1.2439156532287599
80th percentile: 1.4040585041046143
90th percentile: 1.7204753398895265
95th percentile: 1.8786837577819824
99th percentile: 2.0052504920959473
mean time: 1.3975396633148194
Pipeline stage StressChecker completed in 7.73s
chaiml-sao10k-l3-rp-v3-3_v11 status is now deployed due to DeploymentManager action
chaiml-sao10k-l3-rp-v3-3_v11 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-sao10k-l3-rp-v3-3_v11
Running pipeline stage ISVCDeleter
Checking if service chaiml-sao10k-l3-rp-v3-3-v11 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.35s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v11/config.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v11/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v11/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v11/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v11/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-sao10k-l3-rp-v3-3-v11_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v11_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v11_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v11_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v11_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v11_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-sao10k-l3-rp-v3-3-v11_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.20s
chaiml-sao10k-l3-rp-v3-3_v11 status is now torndown due to DeploymentManager action