amank
Made change to cleaning code, modified number of warmpu step, getting eval samples from validation split
7839b8e
| { | |
| // Use IntelliSense to learn about possible attributes. | |
| // Hover to view descriptions of existing attributes. | |
| // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387 | |
| "version": "0.2.0", | |
| "configurations": [ | |
| { | |
| "name": "Python: StreamingFile", | |
| "type": "python", | |
| "request": "launch", | |
| "program": "${file}", | |
| "args": [ | |
| "--output_dir","roberta_mc4_sentence_piece", | |
| "--model_type","roberta", | |
| "--config_name","roberta_mc4_sentence_piece", | |
| "--tokenizer_name","roberta_mc4_sentence_piece", | |
| "--dataset_name","mc4", | |
| "--dataset_config_name","hi", | |
| "--max_seq_length","256", | |
| "--per_device_train_batch_size","16", | |
| "--per_device_eval_batch_size","16", | |
| "--learning_rate","3e-4", | |
| "--warmup_steps","1000", | |
| "--overwrite_output_dir", | |
| "--adam_beta1","0.9", | |
| "--adam_beta2","0.98", | |
| "--num_train_steps","10000", | |
| "--num_eval_samples","5000", | |
| "--preprocessing_num_workers", "90", | |
| "--logging_steps","250", | |
| "--eval_steps","1000" | |
| ], | |
| "console": "integratedTerminal" | |
| }, | |
| { | |
| "name": "Python: Current File", | |
| "type": "python", | |
| "request": "launch", | |
| "program": "${file}", | |
| "console": "integratedTerminal" | |
| } | |
| ] | |
| } |