{
  "_name_or_path": "liuyanchen1015/FLAN-T5_GLUE_finetuning_lr3e-4",
  "adapters": {
    "adapters": {
      "been_done": "9076f36a74755ac4",
      "dey_it": "9076f36a74755ac4",
      "drop_aux": "9076f36a74755ac4",
      "got": "9076f36a74755ac4",
      "lexical": "9076f36a74755ac4",
      "negative_concord": "9076f36a74755ac4",
      "negative_inversion": "9076f36a74755ac4",
      "null_genetive": "9076f36a74755ac4",
      "null_relcl": "9076f36a74755ac4",
      "uninflect": "9076f36a74755ac4"
    },
    "config_map": {
      "9076f36a74755ac4": {
        "adapter_residual_before_ln": false,
        "cross_adapter": false,
        "factorized_phm_W": true,
        "factorized_phm_rule": false,
        "hypercomplex_nonlinearity": "glorot-uniform",
        "init_weights": "bert",
        "inv_adapter": null,
        "inv_adapter_reduction_factor": null,
        "is_parallel": false,
        "learn_phm": true,
        "leave_out": [],
        "ln_after": false,
        "ln_before": false,
        "mh_adapter": false,
        "non_linearity": "relu",
        "original_ln_after": true,
        "original_ln_before": true,
        "output_adapter": true,
        "phm_bias": true,
        "phm_c_init": "normal",
        "phm_dim": 4,
        "phm_init_range": 0.0001,
        "phm_layer": false,
        "phm_rank": 1,
        "reduction_factor": 16,
        "residual_before_ln": true,
        "scaling": 1.0,
        "shared_W_phm": false,
        "shared_phm_rule": true,
        "use_gating": false
      }
    },
    "fusion_config_map": {},
    "fusions": {
      "been_done,dey_it,drop_aux,got,lexical,negative_concord,negative_inversion,null_genetive,null_relcl,uninflect": "dynamic"
    }
  },
  "architectures": [
    "T5ForConditionalGeneration"
  ],
  "d_ff": 2048,
  "d_kv": 64,
  "d_model": 768,
  "decoder_start_token_id": 0,
  "dense_act_fn": "gelu_new",
  "dropout_rate": 0.1,
  "eos_token_id": 1,
  "feed_forward_proj": "gated-gelu",
  "initializer_factor": 1.0,
  "is_encoder_decoder": true,
  "is_gated_act": true,
  "layer_norm_epsilon": 1e-06,
  "model_type": "t5",
  "n_positions": 512,
  "num_decoder_layers": 12,
  "num_heads": 12,
  "num_layers": 12,
  "output_past": true,
  "pad_token_id": 0,
  "relative_attention_max_distance": 128,
  "relative_attention_num_buckets": 32,
  "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: "
    }
  },
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.26.1",
  "use_cache": true,
  "vocab_size": 32128
}