Commit 
							
							路
						
						7f64672
	
1
								Parent(s):
							
							29594d2
								
adding model distilled on mlqa
Browse files- config.json +33 -0
 - pytorch_model.bin +3 -0
 - special_tokens_map.json +9 -0
 - tokenizer.json +0 -0
 - tokenizer_config.json +23 -0
 - train_metrics.json +192 -0
 - validation_metrics.json +230 -0
 
    	
        config.json
    ADDED
    
    | 
         @@ -0,0 +1,33 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "_name_or_path": "josecannete/albert-base-spanish-4",
         
     | 
| 3 | 
         
            +
              "architectures": [
         
     | 
| 4 | 
         
            +
                "AlbertForQuestionAnswering"
         
     | 
| 5 | 
         
            +
              ],
         
     | 
| 6 | 
         
            +
              "attention_probs_dropout_prob": 0,
         
     | 
| 7 | 
         
            +
              "bos_token_id": 2,
         
     | 
| 8 | 
         
            +
              "classifier_dropout_prob": 0.1,
         
     | 
| 9 | 
         
            +
              "down_scale_factor": 1,
         
     | 
| 10 | 
         
            +
              "embedding_size": 128,
         
     | 
| 11 | 
         
            +
              "eos_token_id": 3,
         
     | 
| 12 | 
         
            +
              "gap_size": 0,
         
     | 
| 13 | 
         
            +
              "hidden_act": "gelu",
         
     | 
| 14 | 
         
            +
              "hidden_dropout_prob": 0,
         
     | 
| 15 | 
         
            +
              "hidden_size": 768,
         
     | 
| 16 | 
         
            +
              "initializer_range": 0.02,
         
     | 
| 17 | 
         
            +
              "inner_group_num": 1,
         
     | 
| 18 | 
         
            +
              "intermediate_size": 3072,
         
     | 
| 19 | 
         
            +
              "layer_norm_eps": 1e-12,
         
     | 
| 20 | 
         
            +
              "max_position_embeddings": 512,
         
     | 
| 21 | 
         
            +
              "model_type": "albert",
         
     | 
| 22 | 
         
            +
              "net_structure_type": 0,
         
     | 
| 23 | 
         
            +
              "num_attention_heads": 12,
         
     | 
| 24 | 
         
            +
              "num_hidden_groups": 1,
         
     | 
| 25 | 
         
            +
              "num_hidden_layers": 4,
         
     | 
| 26 | 
         
            +
              "num_memory_blocks": 0,
         
     | 
| 27 | 
         
            +
              "pad_token_id": 0,
         
     | 
| 28 | 
         
            +
              "position_embedding_type": "absolute",
         
     | 
| 29 | 
         
            +
              "torch_dtype": "float32",
         
     | 
| 30 | 
         
            +
              "transformers_version": "4.25.1",
         
     | 
| 31 | 
         
            +
              "type_vocab_size": 2,
         
     | 
| 32 | 
         
            +
              "vocab_size": 31000
         
     | 
| 33 | 
         
            +
            }
         
     | 
    	
        pytorch_model.bin
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:0dbe5b68e2c45dc205b56ca4e70c99d04bd318b5b787c4f3171e156c080b8051
         
     | 
| 3 | 
         
            +
            size 44903231
         
     | 
    	
        special_tokens_map.json
    ADDED
    
    | 
         @@ -0,0 +1,9 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "bos_token": "[CLS]",
         
     | 
| 3 | 
         
            +
              "cls_token": "[CLS]",
         
     | 
| 4 | 
         
            +
              "eos_token": "[SEP]",
         
     | 
| 5 | 
         
            +
              "mask_token": "[MASK]",
         
     | 
| 6 | 
         
            +
              "pad_token": "<pad>",
         
     | 
| 7 | 
         
            +
              "sep_token": "[SEP]",
         
     | 
| 8 | 
         
            +
              "unk_token": "<unk>"
         
     | 
| 9 | 
         
            +
            }
         
     | 
    	
        tokenizer.json
    ADDED
    
    | 
         The diff for this file is too large to render. 
		See raw diff 
     | 
| 
         | 
    	
        tokenizer_config.json
    ADDED
    
    | 
         @@ -0,0 +1,23 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "bos_token": "[CLS]",
         
     | 
| 3 | 
         
            +
              "cls_token": "[CLS]",
         
     | 
| 4 | 
         
            +
              "do_lower_case": true,
         
     | 
| 5 | 
         
            +
              "eos_token": "[SEP]",
         
     | 
| 6 | 
         
            +
              "keep_accents": true,
         
     | 
| 7 | 
         
            +
              "mask_token": {
         
     | 
| 8 | 
         
            +
                "__type": "AddedToken",
         
     | 
| 9 | 
         
            +
                "content": "[MASK]",
         
     | 
| 10 | 
         
            +
                "lstrip": true,
         
     | 
| 11 | 
         
            +
                "normalized": true,
         
     | 
| 12 | 
         
            +
                "rstrip": false,
         
     | 
| 13 | 
         
            +
                "single_word": false
         
     | 
| 14 | 
         
            +
              },
         
     | 
| 15 | 
         
            +
              "model_max_length": 512,
         
     | 
| 16 | 
         
            +
              "name_or_path": "josecannete/albert-base-spanish-4",
         
     | 
| 17 | 
         
            +
              "pad_token": "<pad>",
         
     | 
| 18 | 
         
            +
              "remove_space": true,
         
     | 
| 19 | 
         
            +
              "sep_token": "[SEP]",
         
     | 
| 20 | 
         
            +
              "special_tokens_map_file": null,
         
     | 
| 21 | 
         
            +
              "tokenizer_class": "AlbertTokenizer",
         
     | 
| 22 | 
         
            +
              "unk_token": "<unk>"
         
     | 
| 23 | 
         
            +
            }
         
     | 
    	
        train_metrics.json
    ADDED
    
    | 
         @@ -0,0 +1,192 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            [
         
     | 
| 2 | 
         
            +
                {
         
     | 
| 3 | 
         
            +
                    "kd_train_loss": 0.9267110703099266,
         
     | 
| 4 | 
         
            +
                    "ce_train_loss": 2.2553009721142003,
         
     | 
| 5 | 
         
            +
                    "epoch": 1
         
     | 
| 6 | 
         
            +
                },
         
     | 
| 7 | 
         
            +
                {
         
     | 
| 8 | 
         
            +
                    "kd_train_loss": 0.437324966422325,
         
     | 
| 9 | 
         
            +
                    "ce_train_loss": 1.75392818311556,
         
     | 
| 10 | 
         
            +
                    "epoch": 2
         
     | 
| 11 | 
         
            +
                },
         
     | 
| 12 | 
         
            +
                {
         
     | 
| 13 | 
         
            +
                    "kd_train_loss": 0.25564840695271246,
         
     | 
| 14 | 
         
            +
                    "ce_train_loss": 1.549681672491046,
         
     | 
| 15 | 
         
            +
                    "epoch": 3
         
     | 
| 16 | 
         
            +
                },
         
     | 
| 17 | 
         
            +
                {
         
     | 
| 18 | 
         
            +
                    "kd_train_loss": 0.19114146709720883,
         
     | 
| 19 | 
         
            +
                    "ce_train_loss": 1.467941019872809,
         
     | 
| 20 | 
         
            +
                    "epoch": 4
         
     | 
| 21 | 
         
            +
                },
         
     | 
| 22 | 
         
            +
                {
         
     | 
| 23 | 
         
            +
                    "kd_train_loss": 0.16233224118606057,
         
     | 
| 24 | 
         
            +
                    "ce_train_loss": 1.43373512829177,
         
     | 
| 25 | 
         
            +
                    "epoch": 5
         
     | 
| 26 | 
         
            +
                },
         
     | 
| 27 | 
         
            +
                {
         
     | 
| 28 | 
         
            +
                    "kd_train_loss": 0.1377103858840066,
         
     | 
| 29 | 
         
            +
                    "ce_train_loss": 1.4005313754917956,
         
     | 
| 30 | 
         
            +
                    "epoch": 6
         
     | 
| 31 | 
         
            +
                },
         
     | 
| 32 | 
         
            +
                {
         
     | 
| 33 | 
         
            +
                    "kd_train_loss": 0.12142761922582973,
         
     | 
| 34 | 
         
            +
                    "ce_train_loss": 1.3796487985090269,
         
     | 
| 35 | 
         
            +
                    "epoch": 7
         
     | 
| 36 | 
         
            +
                },
         
     | 
| 37 | 
         
            +
                {
         
     | 
| 38 | 
         
            +
                    "kd_train_loss": 0.10911479878325715,
         
     | 
| 39 | 
         
            +
                    "ce_train_loss": 1.364345971253916,
         
     | 
| 40 | 
         
            +
                    "epoch": 8
         
     | 
| 41 | 
         
            +
                },
         
     | 
| 42 | 
         
            +
                {
         
     | 
| 43 | 
         
            +
                    "kd_train_loss": 0.10162057526938077,
         
     | 
| 44 | 
         
            +
                    "ce_train_loss": 1.35470530912222,
         
     | 
| 45 | 
         
            +
                    "epoch": 9
         
     | 
| 46 | 
         
            +
                },
         
     | 
| 47 | 
         
            +
                {
         
     | 
| 48 | 
         
            +
                    "kd_train_loss": 0.09173406713692267,
         
     | 
| 49 | 
         
            +
                    "ce_train_loss": 1.34008420633322,
         
     | 
| 50 | 
         
            +
                    "epoch": 10
         
     | 
| 51 | 
         
            +
                },
         
     | 
| 52 | 
         
            +
                {
         
     | 
| 53 | 
         
            +
                    "kd_train_loss": 0.08481045791462632,
         
     | 
| 54 | 
         
            +
                    "ce_train_loss": 1.331363442719029,
         
     | 
| 55 | 
         
            +
                    "epoch": 11
         
     | 
| 56 | 
         
            +
                },
         
     | 
| 57 | 
         
            +
                {
         
     | 
| 58 | 
         
            +
                    "kd_train_loss": 0.07994053070887122,
         
     | 
| 59 | 
         
            +
                    "ce_train_loss": 1.3250762583195745,
         
     | 
| 60 | 
         
            +
                    "epoch": 12
         
     | 
| 61 | 
         
            +
                },
         
     | 
| 62 | 
         
            +
                {
         
     | 
| 63 | 
         
            +
                    "kd_train_loss": 0.07311130602374406,
         
     | 
| 64 | 
         
            +
                    "ce_train_loss": 1.3166886057736626,
         
     | 
| 65 | 
         
            +
                    "epoch": 13
         
     | 
| 66 | 
         
            +
                },
         
     | 
| 67 | 
         
            +
                {
         
     | 
| 68 | 
         
            +
                    "kd_train_loss": 0.06744800969400819,
         
     | 
| 69 | 
         
            +
                    "ce_train_loss": 1.3090809386685223,
         
     | 
| 70 | 
         
            +
                    "epoch": 14
         
     | 
| 71 | 
         
            +
                },
         
     | 
| 72 | 
         
            +
                {
         
     | 
| 73 | 
         
            +
                    "kd_train_loss": 0.0634845183372486,
         
     | 
| 74 | 
         
            +
                    "ce_train_loss": 1.3027143190358639,
         
     | 
| 75 | 
         
            +
                    "epoch": 15
         
     | 
| 76 | 
         
            +
                },
         
     | 
| 77 | 
         
            +
                {
         
     | 
| 78 | 
         
            +
                    "kd_train_loss": 0.059948685925253556,
         
     | 
| 79 | 
         
            +
                    "ce_train_loss": 1.2982534907311085,
         
     | 
| 80 | 
         
            +
                    "epoch": 16
         
     | 
| 81 | 
         
            +
                },
         
     | 
| 82 | 
         
            +
                {
         
     | 
| 83 | 
         
            +
                    "kd_train_loss": 0.05605776371058318,
         
     | 
| 84 | 
         
            +
                    "ce_train_loss": 1.294342599036818,
         
     | 
| 85 | 
         
            +
                    "epoch": 17
         
     | 
| 86 | 
         
            +
                },
         
     | 
| 87 | 
         
            +
                {
         
     | 
| 88 | 
         
            +
                    "kd_train_loss": 0.05173261831380247,
         
     | 
| 89 | 
         
            +
                    "ce_train_loss": 1.2884771879167178,
         
     | 
| 90 | 
         
            +
                    "epoch": 18
         
     | 
| 91 | 
         
            +
                },
         
     | 
| 92 | 
         
            +
                {
         
     | 
| 93 | 
         
            +
                    "kd_train_loss": 0.0496412553909414,
         
     | 
| 94 | 
         
            +
                    "ce_train_loss": 1.2861254281558194,
         
     | 
| 95 | 
         
            +
                    "epoch": 19
         
     | 
| 96 | 
         
            +
                },
         
     | 
| 97 | 
         
            +
                {
         
     | 
| 98 | 
         
            +
                    "kd_train_loss": 0.04744180476558645,
         
     | 
| 99 | 
         
            +
                    "ce_train_loss": 1.282894245670442,
         
     | 
| 100 | 
         
            +
                    "epoch": 20
         
     | 
| 101 | 
         
            +
                },
         
     | 
| 102 | 
         
            +
                {
         
     | 
| 103 | 
         
            +
                    "kd_train_loss": 0.04444942316904211,
         
     | 
| 104 | 
         
            +
                    "ce_train_loss": 1.28070035802138,
         
     | 
| 105 | 
         
            +
                    "epoch": 21
         
     | 
| 106 | 
         
            +
                },
         
     | 
| 107 | 
         
            +
                {
         
     | 
| 108 | 
         
            +
                    "kd_train_loss": 0.041973895603821365,
         
     | 
| 109 | 
         
            +
                    "ce_train_loss": 1.27674570335881,
         
     | 
| 110 | 
         
            +
                    "epoch": 22
         
     | 
| 111 | 
         
            +
                },
         
     | 
| 112 | 
         
            +
                {
         
     | 
| 113 | 
         
            +
                    "kd_train_loss": 0.040531559972875025,
         
     | 
| 114 | 
         
            +
                    "ce_train_loss": 1.275717901502934,
         
     | 
| 115 | 
         
            +
                    "epoch": 23
         
     | 
| 116 | 
         
            +
                },
         
     | 
| 117 | 
         
            +
                {
         
     | 
| 118 | 
         
            +
                    "kd_train_loss": 0.038666574527971904,
         
     | 
| 119 | 
         
            +
                    "ce_train_loss": 1.272625279166414,
         
     | 
| 120 | 
         
            +
                    "epoch": 24
         
     | 
| 121 | 
         
            +
                },
         
     | 
| 122 | 
         
            +
                {
         
     | 
| 123 | 
         
            +
                    "kd_train_loss": 0.036579677870675675,
         
     | 
| 124 | 
         
            +
                    "ce_train_loss": 1.2708269421908416,
         
     | 
| 125 | 
         
            +
                    "epoch": 25
         
     | 
| 126 | 
         
            +
                },
         
     | 
| 127 | 
         
            +
                {
         
     | 
| 128 | 
         
            +
                    "kd_train_loss": 0.03472885877018851,
         
     | 
| 129 | 
         
            +
                    "ce_train_loss": 1.267079499905126,
         
     | 
| 130 | 
         
            +
                    "epoch": 26
         
     | 
| 131 | 
         
            +
                },
         
     | 
| 132 | 
         
            +
                {
         
     | 
| 133 | 
         
            +
                    "kd_train_loss": 0.03300567091074616,
         
     | 
| 134 | 
         
            +
                    "ce_train_loss": 1.265107855630497,
         
     | 
| 135 | 
         
            +
                    "epoch": 27
         
     | 
| 136 | 
         
            +
                },
         
     | 
| 137 | 
         
            +
                {
         
     | 
| 138 | 
         
            +
                    "kd_train_loss": 0.031267707465856755,
         
     | 
| 139 | 
         
            +
                    "ce_train_loss": 1.263978869895961,
         
     | 
| 140 | 
         
            +
                    "epoch": 28
         
     | 
| 141 | 
         
            +
                },
         
     | 
| 142 | 
         
            +
                {
         
     | 
| 143 | 
         
            +
                    "kd_train_loss": 0.02948023329343028,
         
     | 
| 144 | 
         
            +
                    "ce_train_loss": 1.2610492245907534,
         
     | 
| 145 | 
         
            +
                    "epoch": 29
         
     | 
| 146 | 
         
            +
                },
         
     | 
| 147 | 
         
            +
                {
         
     | 
| 148 | 
         
            +
                    "kd_train_loss": 0.028111331475519707,
         
     | 
| 149 | 
         
            +
                    "ce_train_loss": 1.2602382712617852,
         
     | 
| 150 | 
         
            +
                    "epoch": 30
         
     | 
| 151 | 
         
            +
                },
         
     | 
| 152 | 
         
            +
                {
         
     | 
| 153 | 
         
            +
                    "kd_train_loss": 0.026608478986394655,
         
     | 
| 154 | 
         
            +
                    "ce_train_loss": 1.2580400243320227,
         
     | 
| 155 | 
         
            +
                    "epoch": 31
         
     | 
| 156 | 
         
            +
                },
         
     | 
| 157 | 
         
            +
                {
         
     | 
| 158 | 
         
            +
                    "kd_train_loss": 0.0248751914831327,
         
     | 
| 159 | 
         
            +
                    "ce_train_loss": 1.2560983723202257,
         
     | 
| 160 | 
         
            +
                    "epoch": 32
         
     | 
| 161 | 
         
            +
                },
         
     | 
| 162 | 
         
            +
                {
         
     | 
| 163 | 
         
            +
                    "kd_train_loss": 0.023646128705622146,
         
     | 
| 164 | 
         
            +
                    "ce_train_loss": 1.2534775997824903,
         
     | 
| 165 | 
         
            +
                    "epoch": 33
         
     | 
| 166 | 
         
            +
                },
         
     | 
| 167 | 
         
            +
                {
         
     | 
| 168 | 
         
            +
                    "kd_train_loss": 0.02271544611893031,
         
     | 
| 169 | 
         
            +
                    "ce_train_loss": 1.2530935516091686,
         
     | 
| 170 | 
         
            +
                    "epoch": 34
         
     | 
| 171 | 
         
            +
                },
         
     | 
| 172 | 
         
            +
                {
         
     | 
| 173 | 
         
            +
                    "kd_train_loss": 0.021936021171748313,
         
     | 
| 174 | 
         
            +
                    "ce_train_loss": 1.2515547741509376,
         
     | 
| 175 | 
         
            +
                    "epoch": 35
         
     | 
| 176 | 
         
            +
                },
         
     | 
| 177 | 
         
            +
                {
         
     | 
| 178 | 
         
            +
                    "kd_train_loss": 0.021128209527009924,
         
     | 
| 179 | 
         
            +
                    "ce_train_loss": 1.2513876314494912,
         
     | 
| 180 | 
         
            +
                    "epoch": 36
         
     | 
| 181 | 
         
            +
                },
         
     | 
| 182 | 
         
            +
                {
         
     | 
| 183 | 
         
            +
                    "kd_train_loss": 0.019934771938535472,
         
     | 
| 184 | 
         
            +
                    "ce_train_loss": 1.2498082426243802,
         
     | 
| 185 | 
         
            +
                    "epoch": 37
         
     | 
| 186 | 
         
            +
                },
         
     | 
| 187 | 
         
            +
                {
         
     | 
| 188 | 
         
            +
                    "kd_train_loss": 0.018994240464449558,
         
     | 
| 189 | 
         
            +
                    "ce_train_loss": 1.2493383634257669,
         
     | 
| 190 | 
         
            +
                    "epoch": 38
         
     | 
| 191 | 
         
            +
                }
         
     | 
| 192 | 
         
            +
            ]
         
     | 
    	
        validation_metrics.json
    ADDED
    
    | 
         @@ -0,0 +1,230 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            [
         
     | 
| 2 | 
         
            +
                {
         
     | 
| 3 | 
         
            +
                    "exact_match": 37.2,
         
     | 
| 4 | 
         
            +
                    "f1": 59.57842060282067,
         
     | 
| 5 | 
         
            +
                    "validation_loss": 2.41743141412735,
         
     | 
| 6 | 
         
            +
                    "epoch": 1
         
     | 
| 7 | 
         
            +
                },
         
     | 
| 8 | 
         
            +
                {
         
     | 
| 9 | 
         
            +
                    "exact_match": 35.0,
         
     | 
| 10 | 
         
            +
                    "f1": 59.76357784672174,
         
     | 
| 11 | 
         
            +
                    "validation_loss": 2.4413123428821564,
         
     | 
| 12 | 
         
            +
                    "epoch": 2
         
     | 
| 13 | 
         
            +
                },
         
     | 
| 14 | 
         
            +
                {
         
     | 
| 15 | 
         
            +
                    "exact_match": 37.2,
         
     | 
| 16 | 
         
            +
                    "f1": 60.33021590001654,
         
     | 
| 17 | 
         
            +
                    "validation_loss": 2.419440597295761,
         
     | 
| 18 | 
         
            +
                    "epoch": 3
         
     | 
| 19 | 
         
            +
                },
         
     | 
| 20 | 
         
            +
                {
         
     | 
| 21 | 
         
            +
                    "exact_match": 37.0,
         
     | 
| 22 | 
         
            +
                    "f1": 60.876613790878174,
         
     | 
| 23 | 
         
            +
                    "validation_loss": 2.393815279006958,
         
     | 
| 24 | 
         
            +
                    "epoch": 4
         
     | 
| 25 | 
         
            +
                },
         
     | 
| 26 | 
         
            +
                {
         
     | 
| 27 | 
         
            +
                    "exact_match": 38.6,
         
     | 
| 28 | 
         
            +
                    "f1": 62.11650390602729,
         
     | 
| 29 | 
         
            +
                    "validation_loss": 2.279040962457657,
         
     | 
| 30 | 
         
            +
                    "epoch": 5
         
     | 
| 31 | 
         
            +
                },
         
     | 
| 32 | 
         
            +
                {
         
     | 
| 33 | 
         
            +
                    "exact_match": 36.2,
         
     | 
| 34 | 
         
            +
                    "f1": 60.24461119706418,
         
     | 
| 35 | 
         
            +
                    "validation_loss": 2.313094735145569,
         
     | 
| 36 | 
         
            +
                    "epoch": 6
         
     | 
| 37 | 
         
            +
                },
         
     | 
| 38 | 
         
            +
                {
         
     | 
| 39 | 
         
            +
                    "exact_match": 39.4,
         
     | 
| 40 | 
         
            +
                    "f1": 62.563444650375324,
         
     | 
| 41 | 
         
            +
                    "validation_loss": 2.3069529682397842,
         
     | 
| 42 | 
         
            +
                    "epoch": 7
         
     | 
| 43 | 
         
            +
                },
         
     | 
| 44 | 
         
            +
                {
         
     | 
| 45 | 
         
            +
                    "exact_match": 38.0,
         
     | 
| 46 | 
         
            +
                    "f1": 61.676504733167725,
         
     | 
| 47 | 
         
            +
                    "validation_loss": 2.2878972589969635,
         
     | 
| 48 | 
         
            +
                    "epoch": 8
         
     | 
| 49 | 
         
            +
                },
         
     | 
| 50 | 
         
            +
                {
         
     | 
| 51 | 
         
            +
                    "exact_match": 39.8,
         
     | 
| 52 | 
         
            +
                    "f1": 63.639278114254296,
         
     | 
| 53 | 
         
            +
                    "validation_loss": 2.2642438858747482,
         
     | 
| 54 | 
         
            +
                    "epoch": 9
         
     | 
| 55 | 
         
            +
                },
         
     | 
| 56 | 
         
            +
                {
         
     | 
| 57 | 
         
            +
                    "exact_match": 38.6,
         
     | 
| 58 | 
         
            +
                    "f1": 62.84171569640027,
         
     | 
| 59 | 
         
            +
                    "validation_loss": 2.236086845397949,
         
     | 
| 60 | 
         
            +
                    "epoch": 10
         
     | 
| 61 | 
         
            +
                },
         
     | 
| 62 | 
         
            +
                {
         
     | 
| 63 | 
         
            +
                    "exact_match": 39.2,
         
     | 
| 64 | 
         
            +
                    "f1": 61.88612229562657,
         
     | 
| 65 | 
         
            +
                    "validation_loss": 2.2972750663757324,
         
     | 
| 66 | 
         
            +
                    "epoch": 11
         
     | 
| 67 | 
         
            +
                },
         
     | 
| 68 | 
         
            +
                {
         
     | 
| 69 | 
         
            +
                    "exact_match": 40.0,
         
     | 
| 70 | 
         
            +
                    "f1": 63.41957204484483,
         
     | 
| 71 | 
         
            +
                    "validation_loss": 2.2380547374486923,
         
     | 
| 72 | 
         
            +
                    "epoch": 12
         
     | 
| 73 | 
         
            +
                },
         
     | 
| 74 | 
         
            +
                {
         
     | 
| 75 | 
         
            +
                    "exact_match": 38.8,
         
     | 
| 76 | 
         
            +
                    "f1": 63.0855328431726,
         
     | 
| 77 | 
         
            +
                    "validation_loss": 2.2377340495586395,
         
     | 
| 78 | 
         
            +
                    "epoch": 13
         
     | 
| 79 | 
         
            +
                },
         
     | 
| 80 | 
         
            +
                {
         
     | 
| 81 | 
         
            +
                    "exact_match": 38.6,
         
     | 
| 82 | 
         
            +
                    "f1": 63.128146216898976,
         
     | 
| 83 | 
         
            +
                    "validation_loss": 2.2086049765348434,
         
     | 
| 84 | 
         
            +
                    "epoch": 14
         
     | 
| 85 | 
         
            +
                },
         
     | 
| 86 | 
         
            +
                {
         
     | 
| 87 | 
         
            +
                    "exact_match": 40.0,
         
     | 
| 88 | 
         
            +
                    "f1": 64.54242193361432,
         
     | 
| 89 | 
         
            +
                    "validation_loss": 2.2143527567386627,
         
     | 
| 90 | 
         
            +
                    "epoch": 15
         
     | 
| 91 | 
         
            +
                },
         
     | 
| 92 | 
         
            +
                {
         
     | 
| 93 | 
         
            +
                    "exact_match": 40.0,
         
     | 
| 94 | 
         
            +
                    "f1": 63.278631848762295,
         
     | 
| 95 | 
         
            +
                    "validation_loss": 2.2167883813381195,
         
     | 
| 96 | 
         
            +
                    "epoch": 16
         
     | 
| 97 | 
         
            +
                },
         
     | 
| 98 | 
         
            +
                {
         
     | 
| 99 | 
         
            +
                    "exact_match": 40.2,
         
     | 
| 100 | 
         
            +
                    "f1": 64.27562472854457,
         
     | 
| 101 | 
         
            +
                    "validation_loss": 2.2080784142017365,
         
     | 
| 102 | 
         
            +
                    "epoch": 17
         
     | 
| 103 | 
         
            +
                },
         
     | 
| 104 | 
         
            +
                {
         
     | 
| 105 | 
         
            +
                    "exact_match": 40.0,
         
     | 
| 106 | 
         
            +
                    "f1": 64.15211177156412,
         
     | 
| 107 | 
         
            +
                    "validation_loss": 2.23178893327713,
         
     | 
| 108 | 
         
            +
                    "epoch": 18
         
     | 
| 109 | 
         
            +
                },
         
     | 
| 110 | 
         
            +
                {
         
     | 
| 111 | 
         
            +
                    "exact_match": 39.6,
         
     | 
| 112 | 
         
            +
                    "f1": 63.7482440053434,
         
     | 
| 113 | 
         
            +
                    "validation_loss": 2.216603860259056,
         
     | 
| 114 | 
         
            +
                    "epoch": 19
         
     | 
| 115 | 
         
            +
                },
         
     | 
| 116 | 
         
            +
                {
         
     | 
| 117 | 
         
            +
                    "exact_match": 39.0,
         
     | 
| 118 | 
         
            +
                    "f1": 62.873221029732164,
         
     | 
| 119 | 
         
            +
                    "validation_loss": 2.2428862750530243,
         
     | 
| 120 | 
         
            +
                    "epoch": 20
         
     | 
| 121 | 
         
            +
                },
         
     | 
| 122 | 
         
            +
                {
         
     | 
| 123 | 
         
            +
                    "exact_match": 38.6,
         
     | 
| 124 | 
         
            +
                    "f1": 63.0879279178262,
         
     | 
| 125 | 
         
            +
                    "validation_loss": 2.206653445959091,
         
     | 
| 126 | 
         
            +
                    "epoch": 21
         
     | 
| 127 | 
         
            +
                },
         
     | 
| 128 | 
         
            +
                {
         
     | 
| 129 | 
         
            +
                    "exact_match": 41.0,
         
     | 
| 130 | 
         
            +
                    "f1": 64.54332732301185,
         
     | 
| 131 | 
         
            +
                    "validation_loss": 2.2194953709840775,
         
     | 
| 132 | 
         
            +
                    "epoch": 22
         
     | 
| 133 | 
         
            +
                },
         
     | 
| 134 | 
         
            +
                {
         
     | 
| 135 | 
         
            +
                    "exact_match": 40.6,
         
     | 
| 136 | 
         
            +
                    "f1": 63.80289079581061,
         
     | 
| 137 | 
         
            +
                    "validation_loss": 2.203217476606369,
         
     | 
| 138 | 
         
            +
                    "epoch": 23
         
     | 
| 139 | 
         
            +
                },
         
     | 
| 140 | 
         
            +
                {
         
     | 
| 141 | 
         
            +
                    "exact_match": 40.0,
         
     | 
| 142 | 
         
            +
                    "f1": 63.404288028303924,
         
     | 
| 143 | 
         
            +
                    "validation_loss": 2.215685695409775,
         
     | 
| 144 | 
         
            +
                    "epoch": 24
         
     | 
| 145 | 
         
            +
                },
         
     | 
| 146 | 
         
            +
                {
         
     | 
| 147 | 
         
            +
                    "exact_match": 38.8,
         
     | 
| 148 | 
         
            +
                    "f1": 62.93220915086903,
         
     | 
| 149 | 
         
            +
                    "validation_loss": 2.2293421030044556,
         
     | 
| 150 | 
         
            +
                    "epoch": 25
         
     | 
| 151 | 
         
            +
                },
         
     | 
| 152 | 
         
            +
                {
         
     | 
| 153 | 
         
            +
                    "exact_match": 39.6,
         
     | 
| 154 | 
         
            +
                    "f1": 63.04610033996446,
         
     | 
| 155 | 
         
            +
                    "validation_loss": 2.1999125480651855,
         
     | 
| 156 | 
         
            +
                    "epoch": 26
         
     | 
| 157 | 
         
            +
                },
         
     | 
| 158 | 
         
            +
                {
         
     | 
| 159 | 
         
            +
                    "exact_match": 38.8,
         
     | 
| 160 | 
         
            +
                    "f1": 63.37994688557569,
         
     | 
| 161 | 
         
            +
                    "validation_loss": 2.19596266746521,
         
     | 
| 162 | 
         
            +
                    "epoch": 27
         
     | 
| 163 | 
         
            +
                },
         
     | 
| 164 | 
         
            +
                {
         
     | 
| 165 | 
         
            +
                    "exact_match": 39.8,
         
     | 
| 166 | 
         
            +
                    "f1": 63.36716124332587,
         
     | 
| 167 | 
         
            +
                    "validation_loss": 2.207815259695053,
         
     | 
| 168 | 
         
            +
                    "epoch": 28
         
     | 
| 169 | 
         
            +
                },
         
     | 
| 170 | 
         
            +
                {
         
     | 
| 171 | 
         
            +
                    "exact_match": 39.0,
         
     | 
| 172 | 
         
            +
                    "f1": 63.20235070703525,
         
     | 
| 173 | 
         
            +
                    "validation_loss": 2.2127343714237213,
         
     | 
| 174 | 
         
            +
                    "epoch": 29
         
     | 
| 175 | 
         
            +
                },
         
     | 
| 176 | 
         
            +
                {
         
     | 
| 177 | 
         
            +
                    "exact_match": 39.8,
         
     | 
| 178 | 
         
            +
                    "f1": 64.53722000128786,
         
     | 
| 179 | 
         
            +
                    "validation_loss": 2.2037834227085114,
         
     | 
| 180 | 
         
            +
                    "epoch": 30
         
     | 
| 181 | 
         
            +
                },
         
     | 
| 182 | 
         
            +
                {
         
     | 
| 183 | 
         
            +
                    "exact_match": 39.0,
         
     | 
| 184 | 
         
            +
                    "f1": 63.89482166971992,
         
     | 
| 185 | 
         
            +
                    "validation_loss": 2.202571988105774,
         
     | 
| 186 | 
         
            +
                    "epoch": 31
         
     | 
| 187 | 
         
            +
                },
         
     | 
| 188 | 
         
            +
                {
         
     | 
| 189 | 
         
            +
                    "exact_match": 39.6,
         
     | 
| 190 | 
         
            +
                    "f1": 63.50426623795006,
         
     | 
| 191 | 
         
            +
                    "validation_loss": 2.2169955670833588,
         
     | 
| 192 | 
         
            +
                    "epoch": 32
         
     | 
| 193 | 
         
            +
                },
         
     | 
| 194 | 
         
            +
                {
         
     | 
| 195 | 
         
            +
                    "exact_match": 39.2,
         
     | 
| 196 | 
         
            +
                    "f1": 63.413569332959725,
         
     | 
| 197 | 
         
            +
                    "validation_loss": 2.2177259027957916,
         
     | 
| 198 | 
         
            +
                    "epoch": 33
         
     | 
| 199 | 
         
            +
                },
         
     | 
| 200 | 
         
            +
                {
         
     | 
| 201 | 
         
            +
                    "exact_match": 40.2,
         
     | 
| 202 | 
         
            +
                    "f1": 64.15148141858079,
         
     | 
| 203 | 
         
            +
                    "validation_loss": 2.2170828878879547,
         
     | 
| 204 | 
         
            +
                    "epoch": 34
         
     | 
| 205 | 
         
            +
                },
         
     | 
| 206 | 
         
            +
                {
         
     | 
| 207 | 
         
            +
                    "exact_match": 39.2,
         
     | 
| 208 | 
         
            +
                    "f1": 63.379632141043025,
         
     | 
| 209 | 
         
            +
                    "validation_loss": 2.221564292907715,
         
     | 
| 210 | 
         
            +
                    "epoch": 35
         
     | 
| 211 | 
         
            +
                },
         
     | 
| 212 | 
         
            +
                {
         
     | 
| 213 | 
         
            +
                    "exact_match": 38.6,
         
     | 
| 214 | 
         
            +
                    "f1": 63.822407502125486,
         
     | 
| 215 | 
         
            +
                    "validation_loss": 2.2223614752292633,
         
     | 
| 216 | 
         
            +
                    "epoch": 36
         
     | 
| 217 | 
         
            +
                },
         
     | 
| 218 | 
         
            +
                {
         
     | 
| 219 | 
         
            +
                    "exact_match": 38.4,
         
     | 
| 220 | 
         
            +
                    "f1": 63.25330786310625,
         
     | 
| 221 | 
         
            +
                    "validation_loss": 2.2186082154512405,
         
     | 
| 222 | 
         
            +
                    "epoch": 37
         
     | 
| 223 | 
         
            +
                },
         
     | 
| 224 | 
         
            +
                {
         
     | 
| 225 | 
         
            +
                    "exact_match": 39.4,
         
     | 
| 226 | 
         
            +
                    "f1": 63.81577942649743,
         
     | 
| 227 | 
         
            +
                    "validation_loss": 2.2130299359560013,
         
     | 
| 228 | 
         
            +
                    "epoch": 38
         
     | 
| 229 | 
         
            +
                }
         
     | 
| 230 | 
         
            +
            ]
         
     |