config.json
| 1 | { |
| 2 | "_name_or_path": "../data/models/xlmr-3l-v3_lc0.1-mix2", |
| 3 | "architectures": [ |
| 4 | "SubwordXLMForTokenClassification" |
| 5 | ], |
| 6 | "attention_probs_dropout_prob": 0.1, |
| 7 | "base_model": "xlm-roberta-base", |
| 8 | "bos_token_id": 0, |
| 9 | "classifier_dropout": null, |
| 10 | "eos_token_id": 2, |
| 11 | "hidden_act": "gelu", |
| 12 | "hidden_dropout_prob": 0.1, |
| 13 | "hidden_size": 768, |
| 14 | "id2label": { |
| 15 | "0": "LABEL_0" |
| 16 | }, |
| 17 | "initializer_range": 0.02, |
| 18 | "intermediate_size": 3072, |
| 19 | "label2id": { |
| 20 | "LABEL_0": 0 |
| 21 | }, |
| 22 | "layer_norm_eps": 1e-05, |
| 23 | "lookahead": null, |
| 24 | "lookahead_split_layers": null, |
| 25 | "max_position_embeddings": 514, |
| 26 | "mixture_name": "xlm-token", |
| 27 | "model_type": "xlm-token", |
| 28 | "num_attention_heads": 12, |
| 29 | "num_hidden_layers": 3, |
| 30 | "output_past": true, |
| 31 | "pad_token_id": 1, |
| 32 | "position_embedding_type": "absolute", |
| 33 | "torch_dtype": "float32", |
| 34 | "transformers_version": "4.39.1", |
| 35 | "type_vocab_size": 1, |
| 36 | "use_cache": true, |
| 37 | "vocab_size": 250002, |
| 38 | "wandb_run_id": "xhbvy7b0" |
| 39 | } |
| 40 | |