Running pipeline stage MKMLizer
Starting job with name cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer
Waiting for job on cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer to finish
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: ║ _____ __ __ ║
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: ║ /___/ ║
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: ║ Version: 0.8.14 ║
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: ║ https://mk1.ai ║
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: ║ belonging to: ║
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: ║ Chai Research Corp. ║
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: ║ ║
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: Downloaded to shared memory in 45.729s
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 5%|▍ | 14/291 [00:00<00:02, 136.31it/s]
Loading 0: 11%|█ | 32/291 [00:00<00:01, 150.30it/s]
Loading 0: 17%|█▋ | 50/291 [00:00<00:01, 156.37it/s]
Loading 0: 23%|██▎ | 68/291 [00:00<00:01, 159.33it/s]
Loading 0: 29%|██▉ | 84/291 [00:00<00:02, 87.55it/s]
Loading 0: 35%|███▌ | 102/291 [00:00<00:01, 104.64it/s]
Loading 0: 41%|████ | 120/291 [00:01<00:01, 118.33it/s]
Loading 0: 46%|████▋ | 135/291 [00:01<00:01, 123.12it/s]
Loading 0: 52%|█████▏ | 150/291 [00:01<00:01, 129.78it/s]
Loading 0: 57%|█████▋ | 167/291 [00:01<00:00, 137.49it/s]
Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 93.99it/s]
Loading 0: 69%|██████▉ | 202/291 [00:01<00:00, 101.89it/s]
Loading 0: 76%|███████▌ | 220/291 [00:01<00:00, 116.05it/s]
Loading 0: 82%|████████▏ | 238/291 [00:01<00:00, 127.31it/s]
Loading 0: 88%|████████▊ | 256/291 [00:02<00:00, 137.17it/s]
Loading 0: 94%|█████████▍| 274/291 [00:02<00:00, 144.77it/s]
Loading 0: 100%|█████████▉| 290/291 [00:07<00:00, 10.09it/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-2881-v5-mkmlizer: quantized model in 22.796s
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: Processed model cgato/TheSalt-RP-L3-8b-DPO-v0.3.2-e0.4.2 in 68.525s
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: creating bucket guanaco-mkml-models
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v5
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v5/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v5/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v5/config.json
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v5/tokenizer.json
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-thesalt-rp-l3-8b-d-2881-v5/flywheel_model.0.safetensors
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-thesalt-rp-l3-8b-d-2881-v5-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-2881-v5-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2881-v5-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-2881-v5-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2881-v5-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-2881-v5-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2881-v5-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-2881-v5-mkmlizer: warnings.warn(
cgato-thesalt-rp-l3-8b-d-2881-v5-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-2881-v5-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: creating bucket guanaco-reward-models
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
Connection pool is full, discarding connection: %s
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v5_reward
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v5_reward/config.json
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v5_reward/tokenizer_config.json
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v5_reward/special_tokens_map.json
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v5_reward/merges.txt
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v5_reward/vocab.json
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v5_reward/tokenizer.json
cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-thesalt-rp-l3-8b-d-2881-v5_reward/reward.tensors
Job cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer completed after 114.65s with status: succeeded
Stopping job with name cgato-thesalt-rp-l3-8b-d-2881-v5-mkmlizer
Pipeline stage MKMLizer completed in 115.43s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service cgato-thesalt-rp-l3-8b-d-2881-v5
Waiting for inference service cgato-thesalt-rp-l3-8b-d-2881-v5 to be ready
Inference service cgato-thesalt-rp-l3-8b-d-2881-v5 ready after 110.58431911468506s
Pipeline stage ISVCDeployer completed in 117.07s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.978546142578125s
Received healthy response to inference request in 1.2974154949188232s
Received healthy response to inference request in 1.2727077007293701s
Received healthy response to inference request in 1.2534351348876953s
Received healthy response to inference request in 1.2493691444396973s
5 requests
0 failed requests
5th percentile: 1.2501823425292968
10th percentile: 1.2509955406188964
20th percentile: 1.2526219367980957
30th percentile: 1.2572896480560303
40th percentile: 1.2649986743927002
50th percentile: 1.2727077007293701
60th percentile: 1.2825908184051513
70th percentile: 1.2924739360809325
80th percentile: 1.4336416244506838
90th percentile: 1.7060938835144044
95th percentile: 1.8423200130462645
99th percentile: 1.951300916671753
mean time: 1.4102947235107421
Pipeline stage StressChecker completed in 7.75s
cgato-thesalt-rp-l3-8b-d_2881_v5 status is now deployed due to DeploymentManager action
cgato-thesalt-rp-l3-8b-d_2881_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-thesalt-rp-l3-8b-d_2881_v5
Running pipeline stage ISVCDeleter
Checking if service cgato-thesalt-rp-l3-8b-d-2881-v5 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.63s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-thesalt-rp-l3-8b-d-2881-v5/config.json from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-d-2881-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-d-2881-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-d-2881-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-thesalt-rp-l3-8b-d-2881-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-thesalt-rp-l3-8b-d-2881-v5_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-2881-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-2881-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-2881-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-2881-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-2881-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-thesalt-rp-l3-8b-d-2881-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.49s
cgato-thesalt-rp-l3-8b-d_2881_v5 status is now torndown due to DeploymentManager action