Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer to finish
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: Downloaded to shared memory in 43.713s
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 4%|▍ | 13/291 [00:00<00:02, 112.88it/s]
Loading 0: 9%|▉ | 27/291 [00:00<00:02, 123.61it/s]
Loading 0: 14%|█▎ | 40/291 [00:00<00:02, 121.81it/s]
Loading 0: 19%|█▊ | 54/291 [00:00<00:01, 127.94it/s]
Loading 0: 23%|██▎ | 67/291 [00:00<00:01, 125.73it/s]
Loading 0: 28%|██▊ | 81/291 [00:00<00:01, 130.08it/s]
Loading 0: 33%|███▎ | 95/291 [00:01<00:03, 65.18it/s]
Loading 0: 38%|███▊ | 111/291 [00:01<00:02, 81.37it/s]
Loading 0: 42%|████▏ | 123/291 [00:01<00:01, 87.97it/s]
Loading 0: 47%|████▋ | 138/291 [00:01<00:01, 101.64it/s]
Loading 0: 52%|█████▏ | 151/291 [00:01<00:01, 106.43it/s]
Loading 0: 57%|█████▋ | 166/291 [00:01<00:01, 113.29it/s]
Loading 0: 62%|██████▏ | 180/291 [00:01<00:00, 119.33it/s]
Loading 0: 66%|██████▋ | 193/291 [00:02<00:01, 71.39it/s]
Loading 0: 71%|███████ | 207/291 [00:02<00:01, 83.54it/s]
Loading 0: 76%|███████▌ | 220/291 [00:02<00:00, 91.90it/s]
Loading 0: 81%|████████▏ | 237/291 [00:02<00:00, 105.77it/s]
Loading 0: 86%|████████▌ | 250/291 [00:02<00:00, 110.43it/s]
Loading 0: 91%|█████████ | 265/291 [00:02<00:00, 116.21it/s]
Loading 0: 97%|█████████▋| 281/291 [00:02<00:00, 122.47it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: quantized model in 24.088s
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.9.2 in 67.801s
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-3610-v1
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-3610-v1/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-3610-v1/config.json
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-3610-v1/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-3610-v1/tokenizer.json
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-3610-v1/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-d-3610-v1-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.
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-3610-v1-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`.
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-3610-v1-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.
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-3610-v1-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.
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: Saving duration: 0.418s
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 8.099s
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-3610-v1_reward
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-3610-v1_reward/config.json
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-3610-v1_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-3610-v1_reward/merges.txt
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-3610-v1_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-3610-v1_reward/vocab.json
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-3610-v1_reward/tokenizer.json
cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-3610-v1_reward/reward.tensors
Job cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer completed after 95.57s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-d-3610-v1-mkmlizer
Pipeline stage MKMLizer completed in 96.45s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-d-3610-v1
Waiting for inference service cgato-thesalt-rp-l3-8b-d-3610-v1 to be ready
Inference service cgato-thesalt-rp-l3-8b-d-3610-v1 ready after 40.44243502616882s
Pipeline stage ISVCDeployer completed in 47.23s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0015082359313965s
Received healthy response to inference request in 1.2842347621917725s
Received healthy response to inference request in 1.2756273746490479s
Received healthy response to inference request in 1.2627336978912354s
Received healthy response to inference request in 1.2405025959014893s
5 requests
0 failed requests
5th percentile: 1.2449488162994384
10th percentile: 1.2493950366973876
20th percentile: 1.2582874774932862
30th percentile: 1.2653124332427979
40th percentile: 1.2704699039459229
50th percentile: 1.2756273746490479
60th percentile: 1.2790703296661377
70th percentile: 1.2825132846832275
80th percentile: 1.4276894569396974
90th percentile: 1.714598846435547
95th percentile: 1.8580535411834715
99th percentile: 1.9728172969818114
mean time: 1.4129213333129882
Pipeline stage StressChecker completed in 7.76s
cgato-thesalt-rp-l3-8b-d_3610_v1 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-d_3610_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-thesalt-rp-l3-8b-d_3610_v1
Running pipeline stage ISVCDeleter
Checking if service cgato-thesalt-rp-l3-8b-d-3610-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 7.23s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-thesalt-rp-l3-8b-d-3610-v1/config.json from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-d-3610-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-d-3610-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-d-3610-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-d-3610-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-thesalt-rp-l3-8b-d-3610-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-3610-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-3610-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-3610-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-3610-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-3610-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-3610-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.36s
cgato-thesalt-rp-l3-8b-d_3610_v1 status is now torndown due to DeploymentManager action