2024-08-07 19:01:43,343 - INFO: Calling run.. 2024-08-07 19:01:43,344 - INFO: Environment configuration: ConfigNLPCausalClassificationEnvironment(gpus=['0'], mixed_precision=False, compile_model=False, use_deepspeed=False, deepspeed_reduce_bucket_size=10000000.0, deepspeed_stage3_prefetch_bucket_size=10000000.0, deepspeed_stage3_param_persistence_threshold=10000000.0, deepspeed_offload_optimizer=False, deepspeed_stage3_max_live_parameters=10000000.0, deepspeed_stage3_max_reuse_distance=10000000.0, find_unused_parameters=False, trust_remote_code=False, huggingface_branch='main', number_of_workers=8, seed=-1, _seed=0, _distributed=False, _distributed_inference=True, _local_rank=0, _world_size=1, _curr_step=0, _curr_val_step=0, _rank=0, _device='cuda', _cpu_comm=None, _model_card_template='text_causal_classification_model_card_template.md', _summary_card_template='text_causal_classification_experiment_summary_card_template.md') 2024-08-07 19:01:43,344 - INFO: cfg.environment._distributed set to False 2024-08-07 19:01:43,345 - INFO: Problem Type: text_causal_classification_modeling 2024-08-07 19:01:43,345 - INFO: Global random seed: 288462 2024-08-07 19:01:43,345 - INFO: Preparing the data... 2024-08-07 19:01:43,346 - INFO: Setting up automatic validation split... 2024-08-07 19:01:43,381 - INFO: The dataframe has following columns: Index(['Description', 'category', 'sub_category', 'label'], dtype='object') 2024-08-07 19:01:43,387 - INFO: Preparing train and validation data, dataset config to be used: ConfigNLPCausalClassificationDataset(dataset_class=, personalize=False, chatbot_name='OI_AI', chatbot_author='openinnovation.ai', train_dataframe='/app/train_df.csv', validation_strategy='automatic', validation_dataframe='', validation_size=0.2, data_sample=1.0, data_sample_choice=('Train', 'Validation'), system_column='None', prompt_column=('Description',), answer_column='category', parent_id_column='None', text_system_start='', text_prompt_start='', text_answer_separator='', limit_chained_samples=False, add_eos_token_to_system=False, add_eos_token_to_prompt=False, add_eos_token_to_answer=False, mask_prompt_labels=True, _allowed_file_extensions=('csv', 'pq', 'parquet'), num_classes=10) 2024-08-07 19:01:43,387 - INFO: Loading train dataset... 2024-08-07 19:01:43,387 - INFO: Columns found: Index(['Description', 'category', 'sub_category', 'label'], dtype='object') 2024-08-07 19:01:44,557 - INFO: Loading validation dataset... 2024-08-07 19:01:44,706 - INFO: Number of observations in train dataset: 9600 2024-08-07 19:01:44,706 - INFO: Number of observations in validation dataset: 2400 2024-08-07 19:01:44,965 - WARNING: PAD token id not matching between config and tokenizer. Overwriting with tokenizer id. 2024-08-07 19:01:44,973 - INFO: Using float16 for backbone 2024-08-07 19:01:44,973 - INFO: Loading tiiuae/falcon-7b. This may take a while. 2024-08-07 19:03:58,808 - INFO: Loaded tiiuae/falcon-7b. 2024-08-07 19:03:58,810 - WARNING: PAD token id not matching between generation config and tokenizer. Overwriting with tokenizer id. 2024-08-07 19:03:58,810 - INFO: Lora module names: ['query_key_value', 'dense', 'dense_h_to_4h', 'dense_4h_to_h'] 2024-08-07 19:03:58,943 - INFO: Enough space available for saving model weights.Required space: 13632.81MB, Available space: 368261.23MB. 2024-08-07 19:03:58,947 - INFO: Optimizer AdamW has been provided with parameters {'weight_decay': 0.0, 'eps': 1e-08, 'betas': (0.8999999762, 0.9990000129), 'lr': 0.0001} 2024-08-07 19:03:59,367 - INFO: started process: 0, can_track: True, tracking_mode: TrackingMode.AFTER_EPOCH 2024-08-07 19:03:59,368 - INFO: Training Epoch: 1 / 10 2024-08-07 19:03:59,369 - INFO: train loss: 0%| | 0/300 [00:00