$ docker build --target production -f .pipeline/training/tone_check/retrain/blubber.yaml -t retrain:slim . $ pwd # ml-pipelines/training/tone_check $ docker run --rm \ -v $(pwd)/data:/srv/edit_check/training/tone_check/data \ -v $(pwd)/base_model:/srv/edit_check/training/tone_check/base_model \ -v $(pwd)/output:/srv/edit_check/training/tone_check/output \ retrain:slim # Output INFO:root: -- Welcome to Tonecheck Retraining Job -- INFO:root:DEVICE: cpu >>>> STARTED!!! Generating train split: 3000 examples [00:00, 78989.27 examples/s] INFO:root:train_dataset['train'][10]: {'input': 'en[SEP]Peacock_Detection[SEP]they operate in several international markets . the company was founded in 1980 and has grown steadily since . this organization focuses on delivering quality services . he worked in finance and operations for over a decade . they operate in several international markets . this organization focuses on delivering quality services . the company was founded in 1980 and has grown steadily since . employees undergo regular training programs . he worked in finance and operations for over a decade . employees undergo regular training programs . the report was submitted for review . he worked in finance and operations for over a decade . the company was founded in 1980 and has grown steadily since . they operate in several international markets . employees undergo regular training programs . they operate in several international markets . employees undergo regular training programs . the company was founded in 1980 and has grown steadily since . he worked in finance and operations for over a decade . the system was updated to meet new regulatory requirements . the report was submitted for review . this organization focuses on delivering quality services . the company was founded in 1980 and has grown steadily since . this organization focuses on delivering quality services . they operate in several international markets . the report was submitted for review . the system was updated to meet new regulatory requirements . they operate in several international markets . they operate in several international markets . they operate in several international markets .', 'label': 0} INFO:root:tokenizer loaded DatasetDict({ train: Dataset({ features: ['input', 'label'], num_rows: 2700 }) test: Dataset({ features: ['input', 'label'], num_rows: 300 }) }) Map: 100%|██████████| 2700/2700 [00:00<00:00, 7525.25 examples/s] Map: 100%|██████████| 300/300 [00:00<00:00, 7653.61 examples/s] Filter: 100%|██████████| 2700/2700 [00:00<00:00, 6217.11 examples/s] Filter: 100%|██████████| 300/300 [00:00<00:00, 5845.64 examples/s] INFO:root:model is loaded: BertForSequenceClassification( (bert): BertModel( (embeddings): BertEmbeddings( (word_embeddings): Embedding(119547, 768, padding_idx=0) (position_embeddings): Embedding(512, 768) (token_type_embeddings): Embedding(2, 768) (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) (encoder): BertEncoder( (layer): ModuleList( (0-11): 12 x BertLayer( (attention): BertAttention( (self): BertSdpaSelfAttention( (query): Linear(in_features=768, out_features=768, bias=True) (key): Linear(in_features=768, out_features=768, bias=True) (value): Linear(in_features=768, out_features=768, bias=True) (dropout): Dropout(p=0.1, inplace=False) ) (output): BertSelfOutput( (dense): Linear(in_features=768, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) (intermediate): BertIntermediate( (dense): Linear(in_features=768, out_features=3072, bias=True) (intermediate_act_fn): GELUActivation() ) (output): BertOutput( (dense): Linear(in_features=3072, out_features=768, bias=True) (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) (dropout): Dropout(p=0.1, inplace=False) ) ) ) ) (pooler): BertPooler( (dense): Linear(in_features=768, out_features=768, bias=True) (activation): Tanh() ) ) (dropout): Dropout(p=0.1, inplace=False) (classifier): Linear(in_features=768, out_features=2, bias=True) ) INFO:root:Start training 0%| | 0/20 [00:00