flanT5_large_FINAL_MT / config.json
rishavranaut's picture
Training in progress, step 2500
bff54cd verified
raw
history blame contribute delete
958 Bytes
{
"_name_or_path": "google/flan-t5-large",
"architectures": [
"T5ForSequenceClassification"
],
"classifier_dropout": 0.0,
"d_ff": 2816,
"d_kv": 64,
"d_model": 1024,
"decoder_start_token_id": 0,
"dense_act_fn": "gelu_new",
"dropout_rate": 0.1,
"eos_token_id": 1,
"feed_forward_proj": "gated-gelu",
"id2label": {
"0": "0",
"1": "1"
},
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"label2id": {
"0": 0,
"1": 1
},
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"n_positions": 512,
"num_decoder_layers": 24,
"num_heads": 16,
"num_layers": 24,
"output_past": true,
"pad_token_id": 0,
"problem_type": "single_label_classification",
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.44.2",
"use_cache": true,
"vocab_size": 32128
}