{ "_name_or_path": "trained_models/t5_10ep-joint-qanom_15.12.21", "architectures": [ "T5ForConditionalGeneration" ], "batch_size": 12, "d_ff": 2048, "d_kv": 64, "d_model": 512, "decoder_start_token_id": 0, "description": "duplicating qanom training data ", "dropout_rate": 0.1, "eos_token_id": 1, "feed_forward_proj": "relu", "fp16": true, "gradient_checkpointing": false, "initializer_factor": 1.0, "is_encoder_decoder": true, "layer_norm_epsilon": 1e-06, "model_type": "t5", "n_positions": 512, "num_decoder_layers": 6, "num_heads": 8, "num_layers": 6, "output_past": true, "overwrite_output_dir": true, "pad_token_id": 0, "preprocess_input_func": "input_predicate_marker", "preprocessing_kwargs": { "batch_size": 12, "description": "duplicating qanom training data ", "fp16": true, "model_type": "t5", "overwrite_output_dir": true, "preprocess_input_func": "input_predicate_marker", "source_prefix": "", "test_dataset": "qanom", "train_dataset": "joint_qanom", "train_epochs": 5, "use_bilateral_predicate_marker": true, "wandb_run_name": "2021-12-16--00:13:35_5ep_t5_joint_qanom_factor=14" }, "relative_attention_num_buckets": 32, "source_prefix": "", "task_specific_params": { "summarization": { "early_stopping": true, "length_penalty": 2.0, "max_length": 200, "min_length": 30, "no_repeat_ngram_size": 3, "num_beams": 4, "prefix": "summarize: " }, "translation_en_to_de": { "early_stopping": true, "max_length": 300, "num_beams": 4, "prefix": "translate English to German: " }, "translation_en_to_fr": { "early_stopping": true, "max_length": 300, "num_beams": 4, "prefix": "translate English to French: " }, "translation_en_to_ro": { "early_stopping": true, "max_length": 300, "num_beams": 4, "prefix": "translate English to Romanian: " } }, "test_dataset": "qanom", "torch_dtype": "float32", "train_dataset": "joint_qanom", "train_epochs": 5, "transformers_version": "4.14.1", "use_bilateral_predicate_marker": true, "use_cache": true, "vocab_size": 32101, "wandb_run_name": "2021-12-16--00:13:35_5ep_t5_joint_qanom_factor=14" }