Running pipeline stage MKMLizer
Starting job with name cgato-l3-thespice-8b-sto-5210-v8-mkmlizer
Waiting for job on cgato-l3-thespice-8b-sto-5210-v8-mkmlizer to finish
Job cgato-l3-thespice-8b-sto-5210-v8-mkmlizer completed after 10.45s with status: failed
Stopping job with name cgato-l3-thespice-8b-sto-5210-v8-mkmlizer
%s, retrying in %s seconds...
Starting job with name cgato-l3-thespice-8b-sto-5210-v8-mkmlizer
Waiting for job on cgato-l3-thespice-8b-sto-5210-v8-mkmlizer to finish
cgato-l3-thespice-8b-sto-5210-v8-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-sto-5210-v8-mkmlizer: warnings.warn(warning_message, FutureWarning)
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: Downloaded to shared memory in 19.438s
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: quantizing model to /dev/shm/model_cache
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer:
Loading 0: 0%| | 0/291 [00:00<?, ?it/s]
Loading 0: 29%|██▊ | 83/291 [00:01<00:02, 82.96it/s]
Loading 0: 64%|██████▍ | 187/291 [00:01<00:01, 97.39it/s]
Loading 0: 99%|█████████▊| 287/291 [00:02<00:00, 140.16it/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: quantized model in 18.861s
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: Processed model cgato/L3-TheSpice-8b-Stoic-Silence-4 in 39.316s
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: creating bucket guanaco-mkml-models
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-l3-thespice-8b-sto-5210-v8
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-sto-5210-v8/config.json
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-sto-5210-v8/special_tokens_map.json
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-l3-thespice-8b-sto-5210-v8/tokenizer_config.json
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-l3-thespice-8b-sto-5210-v8/flywheel_model.0.safetensors
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
cgato-l3-thespice-8b-sto-5210-v8-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-sto-5210-v8-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-sto-5210-v8-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-sto-5210-v8-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-sto-5210-v8-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-l3-thespice-8b-sto-5210-v8-mkmlizer: warnings.warn(
cgato-l3-thespice-8b-sto-5210-v8-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-sto-5210-v8-mkmlizer: return self.fget.__get__(instance, owner)()
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: Saving duration: 0.309s
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 6.474s
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: creating bucket guanaco-reward-models
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cgato-l3-thespice-8b-sto-5210-v8_reward
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-sto-5210-v8_reward/config.json
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cgato-l3-thespice-8b-sto-5210-v8_reward/special_tokens_map.json
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cgato-l3-thespice-8b-sto-5210-v8_reward/tokenizer_config.json
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cgato-l3-thespice-8b-sto-5210-v8_reward/merges.txt
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cgato-l3-thespice-8b-sto-5210-v8_reward/vocab.json
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cgato-l3-thespice-8b-sto-5210-v8_reward/tokenizer.json
cgato-l3-thespice-8b-sto-5210-v8-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cgato-l3-thespice-8b-sto-5210-v8_reward/reward.tensors
Job cgato-l3-thespice-8b-sto-5210-v8-mkmlizer completed after 105.4s with status: succeeded
Stopping job with name cgato-l3-thespice-8b-sto-5210-v8-mkmlizer
Pipeline stage MKMLizer completed in 119.39s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service cgato-l3-thespice-8b-sto-5210-v8
Waiting for inference service cgato-l3-thespice-8b-sto-5210-v8 to be ready
Inference service cgato-l3-thespice-8b-sto-5210-v8 ready after 40.3084671497345s
Pipeline stage ISVCDeployer completed in 47.52s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.040752410888672s
Received healthy response to inference request in 1.121830940246582s
Received healthy response to inference request in 1.13631010055542s
Received healthy response to inference request in 1.1369750499725342s
Received healthy response to inference request in 1.1468908786773682s
5 requests
0 failed requests
5th percentile: 1.1247267723083496
10th percentile: 1.1276226043701172
20th percentile: 1.1334142684936523
30th percentile: 1.1364430904388427
40th percentile: 1.1367090702056886
50th percentile: 1.1369750499725342
60th percentile: 1.1409413814544678
70th percentile: 1.1449077129364014
80th percentile: 1.325663185119629
90th percentile: 1.6832077980041504
95th percentile: 1.861980104446411
99th percentile: 2.0049979496002197
mean time: 1.3165518760681152
Pipeline stage StressChecker completed in 7.22s
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-sto_5210_v8 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
cgato-l3-thespice-8b-sto_5210_v8 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cgato-l3-thespice-8b-sto_5210_v8
Running pipeline stage ISVCDeleter
Checking if service cgato-l3-thespice-8b-sto-5210-v8 is running
Tearing down inference service cgato-l3-thespice-8b-sto-5210-v8
Toredown service cgato-l3-thespice-8b-sto-5210-v8
Pipeline stage ISVCDeleter completed in 4.58s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-sto-5210-v8/config.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-sto-5210-v8/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-sto-5210-v8/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-sto-5210-v8/tokenizer.json from bucket guanaco-mkml-models
Deleting key cgato-l3-thespice-8b-sto-5210-v8/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cgato-l3-thespice-8b-sto-5210-v8_reward/config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-sto-5210-v8_reward/merges.txt from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-sto-5210-v8_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-sto-5210-v8_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-sto-5210-v8_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-sto-5210-v8_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cgato-l3-thespice-8b-sto-5210-v8_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.23s
cgato-l3-thespice-8b-sto_5210_v8 status is now torndown due to DeploymentManager action