55 lines
2.9 KiB
JSON
55 lines
2.9 KiB
JSON
{
|
|
"_comment": "Example configuration for transfer learning adaptation.",
|
|
"model_name": "bert-base-uncased",
|
|
"_comment": "Pre-trained model to adapt. Choose from Hugging Face model hub.",
|
|
"dataset_name": "glue",
|
|
"_comment": "Dataset to fine-tune on. Choose from Hugging Face datasets or specify a local path.",
|
|
"dataset_subset": "mrpc",
|
|
"_comment": "Specific subset of the dataset to use (if applicable).",
|
|
"train_file": null,
|
|
"_comment": "Optional path to a custom training data file. Overrides dataset_name and dataset_subset if provided.",
|
|
"validation_file": null,
|
|
"_comment": "Optional path to a custom validation data file. Overrides dataset_name and dataset_subset if provided.",
|
|
"output_dir": "./adapted_model",
|
|
"_comment": "Directory to save the adapted model and training logs.",
|
|
"num_epochs": 3,
|
|
"_comment": "Number of training epochs.",
|
|
"learning_rate": 2e-5,
|
|
"_comment": "Learning rate for the AdamW optimizer.",
|
|
"batch_size": 32,
|
|
"_comment": "Batch size for training and evaluation.",
|
|
"weight_decay": 0.01,
|
|
"_comment": "Weight decay for regularization.",
|
|
"seed": 42,
|
|
"_comment": "Random seed for reproducibility.",
|
|
"max_length": 128,
|
|
"_comment": "Maximum sequence length for input tokens. Truncate or pad sequences as needed.",
|
|
"task_name": "text_classification",
|
|
"_comment": "Type of task for which the model is being adapted. Options: text_classification, token_classification, question_answering, sequence_to_sequence.",
|
|
"metric": "accuracy",
|
|
"_comment": "Primary metric to evaluate performance. Options depend on the task. Common examples: accuracy, f1, rouge, bleu.",
|
|
"gradient_accumulation_steps": 1,
|
|
"_comment": "Number of steps to accumulate gradients before performing a backward/update pass.",
|
|
"fp16": true,
|
|
"_comment": "Whether to use 16-bit floating point precision (Mixed Precision Training).",
|
|
"evaluation_strategy": "epoch",
|
|
"_comment": "Evaluation strategy to adopt during training. Options: steps, epoch",
|
|
"save_strategy": "epoch",
|
|
"_comment": "Save strategy to adopt during training. Options: steps, epoch",
|
|
"logging_steps": 100,
|
|
"_comment": "Log every X updates steps.",
|
|
"push_to_hub": false,
|
|
"_comment": "Whether to push the adapted model to the Hugging Face Hub.",
|
|
"hub_model_id": null,
|
|
"_comment": "The name of the repository to keep in sync with the local adapted model. It can be a path to an existing repository on the Hub or a new one. Overrides the repository id in the Trainer's config.",
|
|
"hub_token": null,
|
|
"_comment": "The token to use when pushing the adapted model to the Hub.",
|
|
"device": "cuda",
|
|
"_comment": "Device (cpu, cuda) on which the code should be run.",
|
|
"tokenizer_name": null,
|
|
"_comment": "Optional tokenizer name to use. If not provided, the tokenizer associated with the model_name will be used.",
|
|
"do_train": true,
|
|
"_comment": "Whether to perform training.",
|
|
"do_eval": true,
|
|
"_comment": "Whether to perform evaluation."
|
|
} |