config.json

{
  "_name_or_path": "roberta-base",
  "accelerator": null,
  "accumulate_grad_batches": null,
  "add_context": true,
  "add_cross_attention": true,
  "amp_backend": null,
  "amp_level": null,
  "architectures": [
    "RobertaForContextualSequenceClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
  "auto_lr_find": false,
  "auto_scale_batch_size": false,
  "auto_select_gpus": null,
  "batch_size": 32,
  "benchmark": null,
  "binary_clf": false,
  "bos_token_id": 0,
  "check_val_every_n_epoch": 1,
  "checkpoint": "planning_models/classifier/f2012rua/checkpoints/epoch=7-step=53400.ckpt",
  "ckpt_metric": "val_macro_f1",
  "classifier_dropout": null,
  "context_dir": "context/complex/train",
  "context_doc_id": "pair_id",
  "context_window": 13,
  "default_root_dir": null,
  "detect_anomaly": false,
  "devices": "2",
  "doc_pos_embeds": false,
  "enable_checkpointing": true,
  "enable_model_summary": true,
  "enable_progress_bar": true,
  "eos_token_id": 2,
  "fast_dev_run": false,
  "gpus": null,
  "gradient_clip_algorithm": null,
  "gradient_clip_val": null,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2",
    "3": "LABEL_3"
  },
  "inference_mode": true,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "ipus": null,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2,
    "LABEL_3": 3
  },
  "layer_norm_eps": 1e-05,
  "learning_rate": 1e-05,
  "left_z_only": false,
  "limit_predict_batches": null,
  "limit_test_batches": null,
  "limit_train_batches": null,
  "limit_val_batches": null,
  "log_class_acc": false,
  "log_every_n_steps": 50,
  "logger": true,
  "lr_scheduler": false,
  "max_epochs": 10,
  "max_length": 128,
  "max_position_embeddings": 514,
  "max_samples": -1,
  "max_steps": -1,
  "max_time": null,
  "min_epochs": null,
  "min_steps": null,
  "model_type": "context-roberta",
  "move_metrics_to_cpu": false,
  "multiple_trainloader_mode": "max_size_cycle",
  "name": "dyn-init",
  "no_context_pos": false,
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "num_nodes": 1,
  "num_processes": null,
  "num_sanity_val_steps": 2,
  "overfit_batches": 0.0,
  "pad_token_id": 1,
  "plugins": null,
  "position_embedding_type": "absolute",
  "precision": 32,
  "profiler": null,
  "project": "planning_models",
  "reading_lvl": null,
  "regression": false,
  "reload_dataloaders_every_n_epochs": 0,
  "replace_sampler_ddp": true,
  "resume_from_checkpoint": null,
  "save_dir": null,
  "simple_context_dir": "context/simple/train",
  "simple_context_doc_id": "pair_id",
  "src_lvl": null,
  "strategy": null,
  "sync_batchnorm": false,
  "torch_dtype": "float32",
  "tpu_cores": null,
  "track_grad_norm": -1,
  "train_check_interval": 0.2,
  "train_file": "data/wikiauto_sents_train.csv",
  "train_split": 0.9,
  "train_workers": 8,
  "transformers_version": "4.29.1",
  "type_vocab_size": 1,
  "upsample_classes": false,
  "use_cache": true,
  "val_check_interval": null,
  "val_file": "data/wikiauto_sents_valid.csv",
  "val_split": 0.05,
  "val_workers": 8,
  "vocab_size": 50274,
  "wandb_id": null,
  "x_col": "complex",
  "y_col": "label"
}