2024-02-27 15:10:59,120 - INFO: Problem Type: text_causal_classification_modeling 2024-02-27 15:10:59,120 - INFO: Global random seed: 550978 2024-02-27 15:10:59,120 - INFO: Preparing the data... 2024-02-27 15:10:59,120 - INFO: Setting up automatic validation split... 2024-02-27 15:10:59,161 - INFO: Preparing train and validation data 2024-02-27 15:10:59,161 - INFO: Loading train dataset... 2024-02-27 15:10:59,884 - INFO: Loading validation dataset... 2024-02-27 15:11:00,030 - INFO: Number of observations in train dataset: 10800 2024-02-27 15:11:00,030 - INFO: Number of observations in validation dataset: 1200 2024-02-27 15:11:00,338 - WARNING: WARNING: You are currently loading Falcon using legacy code contained in the model repository. Falcon has now been fully ported into the Hugging Face transformers library. For the most up-to-date and high-performance version of the Falcon model code, please update to the latest version of transformers and then load the model without the trust_remote_code=True argument. 2024-02-27 15:11:00,476 - WARNING: PAD token id not matching between config and tokenizer. Overwriting with tokenizer id. 2024-02-27 15:11:00,483 - INFO: Using bfloat16 for backbone 2024-02-27 15:11:00,483 - INFO: Loading tiiuae/falcon-7b. This may take a while. 2024-02-27 15:11:48,531 - INFO: Loaded tiiuae/falcon-7b. 2024-02-27 15:11:48,533 - WARNING: PAD token id not matching between generation config and tokenizer. Overwriting with tokenizer id. 2024-02-27 15:11:48,533 - INFO: Lora module names: ['query_key_value', 'dense', 'dense_h_to_4h', 'dense_4h_to_h'] 2024-02-27 15:11:48,673 - INFO: Enough space available for saving model weights.Required space: 13632.81MB, Available space: 991138.32MB. 2024-02-27 15:11:48,818 - INFO: Training Epoch: 1 / 15 2024-02-27 15:11:48,818 - INFO: train loss: 0%| | 0/1350 [00:00 0.79197 to /app/output 2024-02-27 15:29:52,269 - INFO: Training Epoch: 2 / 15 2024-02-27 15:29:52,270 - INFO: train loss: 0%| | 0/1350 [00:00 0.97231 to /app/output 2024-02-27 15:47:55,634 - INFO: Training Epoch: 3 / 15 2024-02-27 15:47:55,634 - INFO: train loss: 0%| | 0/1350 [00:00 0.97734 to /app/output 2024-02-27 16:06:01,990 - INFO: Training Epoch: 4 / 15 2024-02-27 16:06:01,990 - INFO: train loss: 0%| | 0/1350 [00:00 0.97797 to /app/output 2024-02-27 16:24:10,405 - INFO: Training Epoch: 5 / 15 2024-02-27 16:24:10,405 - INFO: train loss: 0%| | 0/1350 [00:00 0.98081 to /app/output 2024-02-27 17:00:10,151 - INFO: Training Epoch: 7 / 15 2024-02-27 17:00:10,151 - INFO: train loss: 0%| | 0/1350 [00:00 0.98454 to /app/output 2024-02-27 17:36:16,570 - INFO: Training Epoch: 9 / 15 2024-02-27 17:36:16,571 - INFO: train loss: 0%| | 0/1350 [00:00 0.98495 to /app/output 2024-02-27 18:12:32,189 - INFO: Training Epoch: 11 / 15 2024-02-27 18:12:32,190 - INFO: train loss: 0%| | 0/1350 [00:00