Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-dpo-271-v2-mkmlizer
Waiting for job on cgato-l3-thespice-8b-dpo-271-v2-mkmlizer to finish
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: ║ _____ __ __ ║
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: ║ /___/ ║
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: ║ Version: 0.8.10 ║
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: ║ The license key for the current software has been verified as ║
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: ║ belonging to: ║
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: ║ Chai Research Corp. ║
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: ║ Expiration: 2024-07-15 23:59:59 ║
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: ║ ║
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: Downloaded to shared memory in 20.347s
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 79.21it/s]
Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 134.46it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: quantized model in 18.133s
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: Processed model cgato/L3-TheSpice-8b-DPO-v3.2-e3.1 in 39.499s
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-271-v2
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-271-v2/special_tokens_map.json
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-271-v2/tokenizer_config.json
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-271-v2/config.json
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-271-v2/tokenizer.json
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-dpo-271-v2/flywheel_model.0.safetensors
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-dpo-271-v2-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-l3-thespice-8b-dpo-271-v2-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: Saving duration: 0.228s
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.833s
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-271-v2_reward
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-271-v2_reward/special_tokens_map.json
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-271-v2_reward/tokenizer_config.json
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-271-v2_reward/config.json
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-271-v2_reward/vocab.json
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-271-v2_reward/merges.txt
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-271-v2_reward/tokenizer.json
cgato-l3-thespice-8b-dpo-271-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-dpo-271-v2_reward/reward.tensors
Job cgato-l3-thespice-8b-dpo-271-v2-mkmlizer completed after 73.13s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-dpo-271-v2-mkmlizer
Pipeline stage MKMLizer completed in 76.46s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-dpo-271-v2
Waiting for inference service cgato-l3-thespice-8b-dpo-271-v2 to be ready
Inference service cgato-l3-thespice-8b-dpo-271-v2 ready after 40.29054498672485s
Pipeline stage ISVCDeployer completed in 48.38s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2700891494750977s
Received healthy response to inference request in 1.2759876251220703s
Received healthy response to inference request in 1.2736830711364746s
Received healthy response to inference request in 1.2708585262298584s
Received healthy response to inference request in 1.2781891822814941s
5 requests
0 failed requests
5th percentile: 1.2714234352111817
10th percentile: 1.2719883441925048
20th percentile: 1.2731181621551513
30th percentile: 1.2741439819335938
40th percentile: 1.275065803527832
50th percentile: 1.2759876251220703
60th percentile: 1.2768682479858398
70th percentile: 1.2777488708496094
80th percentile: 1.476569175720215
90th percentile: 1.8733291625976562
95th percentile: 2.071709156036377
99th percentile: 2.2304131507873537
mean time: 1.473761510848999
Pipeline stage StressChecker completed in 8.00s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
cgato-l3-thespice-8b-dpo_271_v2 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-dpo_271_v2 status is now rejected due to its M-Eval score being less than the acceptable minimum 6.5 to serve to users. Please consider iterating on your model's ability to adhere to prompts to improve this score.