Training in progress, epoch 1
Browse files- config.json +57 -0
- model.safetensors +3 -0
- runs/Mar18_10-05-52_Jays-MacBook-Pro.local/events.out.tfevents.1710727654.Jays-MacBook-Pro.local.1513.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
    	
        config.json
    ADDED
    
    | @@ -0,0 +1,57 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_name_or_path": "dslim/bert-base-NER",
         | 
| 3 | 
            +
              "_num_labels": 9,
         | 
| 4 | 
            +
              "architectures": [
         | 
| 5 | 
            +
                "BertForTokenClassification"
         | 
| 6 | 
            +
              ],
         | 
| 7 | 
            +
              "attention_probs_dropout_prob": 0.1,
         | 
| 8 | 
            +
              "classifier_dropout": null,
         | 
| 9 | 
            +
              "hidden_act": "gelu",
         | 
| 10 | 
            +
              "hidden_dropout_prob": 0.1,
         | 
| 11 | 
            +
              "hidden_size": 768,
         | 
| 12 | 
            +
              "id2label": {
         | 
| 13 | 
            +
                "0": "O",
         | 
| 14 | 
            +
                "1": "B-corporation",
         | 
| 15 | 
            +
                "2": "I-corporation",
         | 
| 16 | 
            +
                "3": "B-creative-work",
         | 
| 17 | 
            +
                "4": "I-creative-work",
         | 
| 18 | 
            +
                "5": "B-group",
         | 
| 19 | 
            +
                "6": "I-group",
         | 
| 20 | 
            +
                "7": "B-location",
         | 
| 21 | 
            +
                "8": "I-location",
         | 
| 22 | 
            +
                "9": "B-person",
         | 
| 23 | 
            +
                "10": "I-person",
         | 
| 24 | 
            +
                "11": "B-product",
         | 
| 25 | 
            +
                "12": "I-product"
         | 
| 26 | 
            +
              },
         | 
| 27 | 
            +
              "initializer_range": 0.02,
         | 
| 28 | 
            +
              "intermediate_size": 3072,
         | 
| 29 | 
            +
              "label2id": {
         | 
| 30 | 
            +
                "B-corporation": 1,
         | 
| 31 | 
            +
                "B-creative-work": 3,
         | 
| 32 | 
            +
                "B-group": 5,
         | 
| 33 | 
            +
                "B-location": 7,
         | 
| 34 | 
            +
                "B-person": 9,
         | 
| 35 | 
            +
                "B-product": 11,
         | 
| 36 | 
            +
                "I-corporation": 2,
         | 
| 37 | 
            +
                "I-creative-work": 4,
         | 
| 38 | 
            +
                "I-group": 6,
         | 
| 39 | 
            +
                "I-location": 8,
         | 
| 40 | 
            +
                "I-person": 10,
         | 
| 41 | 
            +
                "I-product": 12,
         | 
| 42 | 
            +
                "O": 0
         | 
| 43 | 
            +
              },
         | 
| 44 | 
            +
              "layer_norm_eps": 1e-12,
         | 
| 45 | 
            +
              "max_position_embeddings": 512,
         | 
| 46 | 
            +
              "model_type": "bert",
         | 
| 47 | 
            +
              "num_attention_heads": 12,
         | 
| 48 | 
            +
              "num_hidden_layers": 12,
         | 
| 49 | 
            +
              "output_past": true,
         | 
| 50 | 
            +
              "pad_token_id": 0,
         | 
| 51 | 
            +
              "position_embedding_type": "absolute",
         | 
| 52 | 
            +
              "torch_dtype": "float32",
         | 
| 53 | 
            +
              "transformers_version": "4.38.2",
         | 
| 54 | 
            +
              "type_vocab_size": 2,
         | 
| 55 | 
            +
              "use_cache": true,
         | 
| 56 | 
            +
              "vocab_size": 28996
         | 
| 57 | 
            +
            }
         | 
    	
        model.safetensors
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:ce43a89c34aef2dac74654c8d73c96443edc17b9f0e486105c7188829aa9aca2
         | 
| 3 | 
            +
            size 430942044
         | 
    	
        runs/Mar18_10-05-52_Jays-MacBook-Pro.local/events.out.tfevents.1710727654.Jays-MacBook-Pro.local.1513.1
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:0dfc3acbe7eb9e4a2dc7ca07d630bcebfb7011ced484b6217a26803e0f5a6ce0
         | 
| 3 | 
            +
            size 5704
         | 
    	
        special_tokens_map.json
    ADDED
    
    | @@ -0,0 +1,7 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "cls_token": "[CLS]",
         | 
| 3 | 
            +
              "mask_token": "[MASK]",
         | 
| 4 | 
            +
              "pad_token": "[PAD]",
         | 
| 5 | 
            +
              "sep_token": "[SEP]",
         | 
| 6 | 
            +
              "unk_token": "[UNK]"
         | 
| 7 | 
            +
            }
         | 
    	
        tokenizer.json
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  | 
    	
        tokenizer_config.json
    ADDED
    
    | @@ -0,0 +1,58 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "added_tokens_decoder": {
         | 
| 3 | 
            +
                "0": {
         | 
| 4 | 
            +
                  "content": "[PAD]",
         | 
| 5 | 
            +
                  "lstrip": false,
         | 
| 6 | 
            +
                  "normalized": false,
         | 
| 7 | 
            +
                  "rstrip": false,
         | 
| 8 | 
            +
                  "single_word": false,
         | 
| 9 | 
            +
                  "special": true
         | 
| 10 | 
            +
                },
         | 
| 11 | 
            +
                "100": {
         | 
| 12 | 
            +
                  "content": "[UNK]",
         | 
| 13 | 
            +
                  "lstrip": false,
         | 
| 14 | 
            +
                  "normalized": false,
         | 
| 15 | 
            +
                  "rstrip": false,
         | 
| 16 | 
            +
                  "single_word": false,
         | 
| 17 | 
            +
                  "special": true
         | 
| 18 | 
            +
                },
         | 
| 19 | 
            +
                "101": {
         | 
| 20 | 
            +
                  "content": "[CLS]",
         | 
| 21 | 
            +
                  "lstrip": false,
         | 
| 22 | 
            +
                  "normalized": false,
         | 
| 23 | 
            +
                  "rstrip": false,
         | 
| 24 | 
            +
                  "single_word": false,
         | 
| 25 | 
            +
                  "special": true
         | 
| 26 | 
            +
                },
         | 
| 27 | 
            +
                "102": {
         | 
| 28 | 
            +
                  "content": "[SEP]",
         | 
| 29 | 
            +
                  "lstrip": false,
         | 
| 30 | 
            +
                  "normalized": false,
         | 
| 31 | 
            +
                  "rstrip": false,
         | 
| 32 | 
            +
                  "single_word": false,
         | 
| 33 | 
            +
                  "special": true
         | 
| 34 | 
            +
                },
         | 
| 35 | 
            +
                "103": {
         | 
| 36 | 
            +
                  "content": "[MASK]",
         | 
| 37 | 
            +
                  "lstrip": false,
         | 
| 38 | 
            +
                  "normalized": false,
         | 
| 39 | 
            +
                  "rstrip": false,
         | 
| 40 | 
            +
                  "single_word": false,
         | 
| 41 | 
            +
                  "special": true
         | 
| 42 | 
            +
                }
         | 
| 43 | 
            +
              },
         | 
| 44 | 
            +
              "clean_up_tokenization_spaces": true,
         | 
| 45 | 
            +
              "cls_token": "[CLS]",
         | 
| 46 | 
            +
              "do_basic_tokenize": true,
         | 
| 47 | 
            +
              "do_lower_case": false,
         | 
| 48 | 
            +
              "mask_token": "[MASK]",
         | 
| 49 | 
            +
              "max_len": 512,
         | 
| 50 | 
            +
              "model_max_length": 512,
         | 
| 51 | 
            +
              "never_split": null,
         | 
| 52 | 
            +
              "pad_token": "[PAD]",
         | 
| 53 | 
            +
              "sep_token": "[SEP]",
         | 
| 54 | 
            +
              "strip_accents": null,
         | 
| 55 | 
            +
              "tokenize_chinese_chars": true,
         | 
| 56 | 
            +
              "tokenizer_class": "BertTokenizer",
         | 
| 57 | 
            +
              "unk_token": "[UNK]"
         | 
| 58 | 
            +
            }
         | 
    	
        training_args.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:a712cdcf2a18013976c9644d38669bc244b6b47bfe871fcc10bcf5efefe75d94
         | 
| 3 | 
            +
            size 4920
         | 
    	
        vocab.txt
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  |