dahe827's picture
End of training
7affa90 verified
{
"_name_or_path": "kiddothe2b/longformer-base-4096",
"architectures": [
"LongformerForSequenceClassification"
],
"attention_mode": "longformer",
"attention_probs_dropout_prob": 0.1,
"attention_window": [
128,
128,
128,
128,
128,
128,
128,
128,
128,
128,
128,
128
],
"bos_token_id": 0,
"classifier_dropout": null,
"cls_token_id": 0,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "capacity expansion",
"1": "legal action",
"2": "market expansion",
"3": "merger & acquisition and finance investments",
"4": "outsourcing and alliance",
"5": "product introductions and improvements"
},
"ignore_attention_mask": false,
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"capacity expansion": 0,
"legal action": 1,
"market expansion": 2,
"merger & acquisition and finance investments": 3,
"outsourcing and alliance": 4,
"product introductions and improvements": 5
},
"layer_norm_eps": 1e-05,
"max_position_embeddings": 4099,
"max_sentence_length": 128,
"max_sentence_size": 128,
"max_sentences": 8,
"model_max_length": 4096,
"model_type": "longformer",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"onnx_export": false,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"problem_type": "multi_label_classification",
"sep_token_id": 2,
"torch_dtype": "float32",
"transformers_version": "4.41.1",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 50265
}