Yash-ed/tmp_trainer

1{2  "activation": "gelu",3  "architectures": [4    "DistilBertForSequenceClassification"5  ],6  "attention_dropout": 0.1,7  "bos_token_id": null,8  "dim": 768,9  "dropout": 0.1,10  "dtype": "float32",11  "eos_token_id": null,12  "hidden_dim": 3072,13  "id2label": {14    "0": "LABEL_0",15    "1": "LABEL_1",16    "2": "LABEL_2",17    "3": "LABEL_3",18    "4": "LABEL_4",19    "5": "LABEL_5"20  },21  "initializer_range": 0.02,22  "label2id": {23    "LABEL_0": 0,24    "LABEL_1": 1,25    "LABEL_2": 2,26    "LABEL_3": 3,27    "LABEL_4": 4,28    "LABEL_5": 529  },30  "max_position_embeddings": 512,31  "model_type": "distilbert",32  "n_heads": 12,33  "n_layers": 6,34  "pad_token_id": 0,35  "problem_type": "single_label_classification",36  "qa_dropout": 0.1,37  "seq_classif_dropout": 0.2,38  "sinusoidal_pos_embds": false,39  "tie_weights_": true,40  "tie_word_embeddings": true,41  "transformers_version": "5.0.0",42  "use_cache": false,43  "vocab_size": 3052244}45