Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer to finish
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: Downloaded to shared memory in 33.604s
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 79.42it/s]
Loading 0: 64%|██████▍ | 187/291 [00:02<00:01, 95.62it/s]
Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 136.64it/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-4472-v1-mkmlizer: quantized model in 23.506s
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.5.2 in 57.110s
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-4472-v1
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-4472-v1/config.json
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-4472-v1/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-4472-v1/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-4472-v1/tokenizer.json
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-4472-v1/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-d-4472-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-4472-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-4472-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-4472-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-4472-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-4472-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-4472-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-4472-v1-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-4472-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-4472-v1-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: Saving duration: 0.401s
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.200s
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: creating bucket guanaco-reward-models
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-4472-v1_reward
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-4472-v1_reward/config.json
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-4472-v1_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-4472-v1_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-4472-v1_reward/vocab.json
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-4472-v1_reward/merges.txt
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-4472-v1_reward/tokenizer.json
cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-4472-v1_reward/reward.tensors
Job cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer completed after 143.06s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-d-4472-v1-mkmlizer
Pipeline stage MKMLizer completed in 144.01s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-d-4472-v1
Waiting for inference service cgato-thesalt-rp-l3-8b-d-4472-v1 to be ready
Inference service cgato-thesalt-rp-l3-8b-d-4472-v1 ready after 40.234224796295166s
Pipeline stage ISVCDeployer completed in 47.13s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.109563112258911s
Received healthy response to inference request in 1.309114933013916s
Received healthy response to inference request in 1.410142421722412s
Received healthy response to inference request in 1.4104435443878174s
Received healthy response to inference request in 1.2615907192230225s
5 requests
0 failed requests
5th percentile: 1.2710955619812012
10th percentile: 1.28060040473938
20th percentile: 1.2996100902557373
30th percentile: 1.3293204307556152
40th percentile: 1.3697314262390137
50th percentile: 1.410142421722412
60th percentile: 1.4102628707885743
70th percentile: 1.4103833198547364
80th percentile: 1.5502674579620361
90th percentile: 1.8299152851104736
95th percentile: 1.9697391986846924
99th percentile: 2.081598329544067
mean time: 1.5001709461212158
Pipeline stage StressChecker completed in 8.19s
cgato-thesalt-rp-l3-8b-d_4472_v1 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-d_4472_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-thesalt-rp-l3-8b-d_4472_v1
Running pipeline stage ISVCDeleter
Checking if service cgato-thesalt-rp-l3-8b-d-4472-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 5.71s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-thesalt-rp-l3-8b-d-4472-v1/config.json from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-d-4472-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-d-4472-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-d-4472-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-d-4472-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-thesalt-rp-l3-8b-d-4472-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-4472-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-4472-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-4472-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-4472-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-4472-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-4472-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.39s
cgato-thesalt-rp-l3-8b-d_4472_v1 status is now torndown due to DeploymentManager action