Hugging Face's logo

hiba2
/
results_mt5_xl-_wiki

Text2Text Generation
Transformers
TensorBoard
Safetensors
mt5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
hiba2 commited on
Commit
9c50feb
•
1 Parent(s): c00e95a

End of training

Browse files
Files changed (13) hide show
  1. .gitattributes +1 -0
  2. README.md +156 -0
  3. config.json +33 -0
  4. generation_config.json +6 -0
  5. model.safetensors +3 -0
  6. runs/Jun05_20-44-22_f2ba9c758eb2/events.out.tfevents.1717620353.f2ba9c758eb2.565.0 +3 -0
  7. runs/Jun05_20-44-22_f2ba9c758eb2/events.out.tfevents.1717620533.f2ba9c758eb2.565.1 +3 -0
  8. runs/Jun05_20-54-15_f2ba9c758eb2/events.out.tfevents.1717620948.f2ba9c758eb2.5544.0 +3 -0
  9. special_tokens_map.json +23 -0
  10. spiece.model +3 -0
  11. tokenizer.json +3 -0
  12. tokenizer_config.json +40 -0
  13. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/mt5-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - rouge
8
+ model-index:
9
+ - name: results_mt5_xl-_wiki
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # results_mt5_xl-_wiki
17
+
18
+ This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0048
21
+ - Rouge1: 0.1023
22
+ - Rouge2: 0.0125
23
+ - Rougel: 0.1022
24
+ - Rougelsum: 0.1019
25
+ - Gen Len: 18.9302
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 4e-05
45
+ - train_batch_size: 1
46
+ - eval_batch_size: 1
47
+ - seed: 42
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - lr_scheduler_warmup_steps: 250
51
+ - num_epochs: 10
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
56
+ |:-------------:|:------:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
57
+ | 9.7309 | 0.1081 | 500 | 8.7752 | 0.0 | 0.0 | 0.0 | 0.0 | 19.0 |
58
+ | 8.2303 | 0.2161 | 1000 | 7.2210 | 0.0 | 0.0 | 0.0 | 0.0 | 19.0 |
59
+ | 7.2363 | 0.3242 | 1500 | 6.7270 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
60
+ | 7.0589 | 0.4322 | 2000 | 6.3511 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
61
+ | 6.7392 | 0.5403 | 2500 | 6.2383 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
62
+ | 6.716 | 0.6484 | 3000 | 6.2242 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
63
+ | 6.5459 | 0.7564 | 3500 | 6.1235 | 0.0112 | 0.0 | 0.0112 | 0.0112 | 19.0 |
64
+ | 6.3342 | 0.8645 | 4000 | 6.0783 | 0.0738 | 0.0 | 0.0736 | 0.0732 | 12.6417 |
65
+ | 6.2404 | 0.9726 | 4500 | 6.0705 | 0.0738 | 0.0 | 0.0736 | 0.0732 | 15.3982 |
66
+ | 6.1405 | 1.0806 | 5000 | 6.0811 | 0.0112 | 0.0 | 0.0112 | 0.0112 | 19.0 |
67
+ | 6.0387 | 1.1887 | 5500 | 5.8715 | 0.0112 | 0.0 | 0.0112 | 0.0112 | 18.951 |
68
+ | 5.7348 | 1.2967 | 6000 | 5.2644 | 0.0392 | 0.0 | 0.0392 | 0.0394 | 0.4314 |
69
+ | 5.2214 | 1.4048 | 6500 | 4.8743 | 0.0184 | 0.0 | 0.0184 | 0.0184 | 9.9584 |
70
+ | 4.9215 | 1.5129 | 7000 | 4.4677 | 0.0359 | 0.0 | 0.036 | 0.036 | 19.0 |
71
+ | 4.6441 | 1.6209 | 7500 | 4.0154 | 0.0738 | 0.0 | 0.0736 | 0.0732 | 19.0 |
72
+ | 4.2095 | 1.7290 | 8000 | 3.4679 | 0.0238 | 0.0 | 0.0238 | 0.0238 | 7.9318 |
73
+ | 3.6038 | 1.8370 | 8500 | 2.7153 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
74
+ | 2.9711 | 1.9451 | 9000 | 1.9488 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
75
+ | 2.2376 | 2.0532 | 9500 | 1.1301 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
76
+ | 1.4721 | 2.1612 | 10000 | 0.5812 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
77
+ | 1.0658 | 2.2693 | 10500 | 0.3416 | 0.0746 | 0.0002 | 0.0743 | 0.0741 | 18.8022 |
78
+ | 0.6153 | 2.3774 | 11000 | 0.2139 | 0.0442 | 0.0 | 0.0441 | 0.0441 | 2.7739 |
79
+ | 0.4134 | 2.4854 | 11500 | 0.1454 | 0.0 | 0.0 | 0.0 | 0.0 | 0.01 |
80
+ | 0.31 | 2.5935 | 12000 | 0.1086 | 0.0831 | 0.002 | 0.0824 | 0.0822 | 18.6766 |
81
+ | 0.2423 | 2.7015 | 12500 | 0.0821 | 0.0852 | 0.0038 | 0.0848 | 0.0847 | 18.7947 |
82
+ | 0.1862 | 2.8096 | 13000 | 0.0670 | 0.078 | 0.001 | 0.0777 | 0.0778 | 18.8196 |
83
+ | 0.1596 | 2.9177 | 13500 | 0.0546 | 0.0875 | 0.0042 | 0.0872 | 0.0871 | 18.8279 |
84
+ | 0.13 | 3.0257 | 14000 | 0.0586 | 0.0861 | 0.0047 | 0.0858 | 0.0859 | 18.857 |
85
+ | 0.1055 | 3.1338 | 14500 | 0.0393 | 0.081 | 0.003 | 0.0808 | 0.0808 | 18.655 |
86
+ | 0.0896 | 3.2418 | 15000 | 0.0348 | 0.0832 | 0.0049 | 0.0828 | 0.0827 | 18.7091 |
87
+ | 0.0854 | 3.3499 | 15500 | 0.0310 | 0.0858 | 0.0062 | 0.0854 | 0.0853 | 18.6268 |
88
+ | 0.0717 | 3.4580 | 16000 | 0.0284 | 0.091 | 0.0084 | 0.0907 | 0.0908 | 18.803 |
89
+ | 0.065 | 3.5660 | 16500 | 0.0250 | 0.0887 | 0.0093 | 0.0885 | 0.0885 | 18.7805 |
90
+ | 0.0584 | 3.6741 | 17000 | 0.0229 | 0.089 | 0.0109 | 0.0888 | 0.089 | 18.5179 |
91
+ | 0.0511 | 3.7821 | 17500 | 0.0209 | 0.0874 | 0.0093 | 0.0872 | 0.0874 | 18.5154 |
92
+ | 0.0502 | 3.8902 | 18000 | 0.0189 | 0.091 | 0.0077 | 0.0909 | 0.0906 | 18.4372 |
93
+ | 0.0429 | 3.9983 | 18500 | 0.0172 | 0.0865 | 0.0075 | 0.0863 | 0.0862 | 18.8645 |
94
+ | 0.0412 | 4.1063 | 19000 | 0.0160 | 0.0911 | 0.008 | 0.0909 | 0.0907 | 18.5395 |
95
+ | 0.0419 | 4.2144 | 19500 | 0.0148 | 0.0913 | 0.0118 | 0.091 | 0.0913 | 18.8736 |
96
+ | 0.0353 | 4.3225 | 20000 | 0.0137 | 0.0974 | 0.0103 | 0.097 | 0.097 | 18.6874 |
97
+ | 0.0321 | 4.4305 | 20500 | 0.0128 | 0.0936 | 0.0128 | 0.0936 | 0.0934 | 18.5578 |
98
+ | 0.029 | 4.5386 | 21000 | 0.0120 | 0.0944 | 0.0128 | 0.094 | 0.0939 | 18.7415 |
99
+ | 0.0275 | 4.6466 | 21500 | 0.0117 | 0.0907 | 0.0134 | 0.0905 | 0.0907 | 18.7889 |
100
+ | 0.0265 | 4.7547 | 22000 | 0.0108 | 0.0902 | 0.008 | 0.0902 | 0.0899 | 18.5669 |
101
+ | 0.2825 | 4.8628 | 22500 | 1.2607 | 0.0958 | 0.0112 | 0.0957 | 0.0957 | 18.749 |
102
+ | 0.5612 | 4.9708 | 23000 | 0.1068 | 0.0956 | 0.0108 | 0.0955 | 0.0952 | 18.3699 |
103
+ | 0.029 | 5.0789 | 23500 | 0.0090 | 0.0941 | 0.0098 | 0.094 | 0.0939 | 18.3973 |
104
+ | 0.023 | 5.1869 | 24000 | 0.0085 | 0.0947 | 0.0099 | 0.0945 | 0.0942 | 18.414 |
105
+ | 0.0205 | 5.2950 | 24500 | 0.0085 | 0.1042 | 0.0105 | 0.1038 | 0.1039 | 18.4996 |
106
+ | 0.0222 | 5.4031 | 25000 | 0.0081 | 0.0916 | 0.0093 | 0.0916 | 0.0914 | 18.6517 |
107
+ | 0.0188 | 5.5111 | 25500 | 0.0078 | 0.0964 | 0.0114 | 0.0961 | 0.0961 | 18.2236 |
108
+ | 0.0205 | 5.6192 | 26000 | 0.0074 | 0.1077 | 0.0137 | 0.1077 | 0.1076 | 18.325 |
109
+ | 0.018 | 5.7273 | 26500 | 0.0071 | 0.1001 | 0.0112 | 0.1 | 0.0995 | 18.6575 |
110
+ | 0.0173 | 5.8353 | 27000 | 0.0068 | 0.095 | 0.0096 | 0.0949 | 0.0947 | 18.5669 |
111
+ | 0.0162 | 5.9434 | 27500 | 0.0066 | 0.0946 | 0.0091 | 0.0948 | 0.0944 | 18.4871 |
112
+ | 0.0145 | 6.0514 | 28000 | 0.0064 | 0.098 | 0.0112 | 0.0979 | 0.0979 | 18.6301 |
113
+ | 0.0154 | 6.1595 | 28500 | 0.0064 | 0.0953 | 0.0101 | 0.095 | 0.0952 | 18.4838 |
114
+ | 0.0149 | 6.2676 | 29000 | 0.0062 | 0.1013 | 0.0137 | 0.1011 | 0.1011 | 18.2577 |
115
+ | 0.014 | 6.3756 | 29500 | 0.0062 | 0.0964 | 0.0141 | 0.0961 | 0.0966 | 18.5195 |
116
+ | 0.0142 | 6.4837 | 30000 | 0.0060 | 0.1028 | 0.0143 | 0.1022 | 0.1025 | 18.5062 |
117
+ | 0.0138 | 6.5917 | 30500 | 0.0060 | 0.0998 | 0.0141 | 0.0993 | 0.0994 | 18.5794 |
118
+ | 0.0124 | 6.6998 | 31000 | 0.0059 | 0.0957 | 0.0113 | 0.0955 | 0.0957 | 18.4938 |
119
+ | 0.0119 | 6.8079 | 31500 | 0.0058 | 0.0968 | 0.0113 | 0.0963 | 0.0965 | 18.6401 |
120
+ | 0.0132 | 6.9159 | 32000 | 0.0057 | 0.0949 | 0.0104 | 0.0946 | 0.0947 | 18.5628 |
121
+ | 0.0129 | 7.0240 | 32500 | 0.0056 | 0.0952 | 0.0146 | 0.0947 | 0.0949 | 18.4406 |
122
+ | 0.0125 | 7.1321 | 33000 | 0.0055 | 0.0986 | 0.0127 | 0.0983 | 0.0983 | 18.5777 |
123
+ | 0.0107 | 7.2401 | 33500 | 0.0054 | 0.0985 | 0.0137 | 0.0979 | 0.0982 | 18.4264 |
124
+ | 0.0228 | 7.3482 | 34000 | 0.0054 | 0.0971 | 0.0113 | 0.0968 | 0.0969 | 18.744 |
125
+ | 0.011 | 7.4562 | 34500 | 0.0054 | 0.1089 | 0.0136 | 0.1088 | 0.1086 | 18.9069 |
126
+ | 0.0106 | 7.5643 | 35000 | 0.0054 | 0.1058 | 0.0133 | 0.1057 | 0.1055 | 18.7149 |
127
+ | 0.0102 | 7.6724 | 35500 | 0.0053 | 0.0957 | 0.0105 | 0.0954 | 0.0953 | 18.6342 |
128
+ | 0.0108 | 7.7804 | 36000 | 0.0052 | 0.1028 | 0.0131 | 0.1027 | 0.1024 | 18.9069 |
129
+ | 0.0106 | 7.8885 | 36500 | 0.0052 | 0.1075 | 0.0153 | 0.1074 | 0.1073 | 18.6841 |
130
+ | 0.0122 | 7.9965 | 37000 | 0.0051 | 0.0995 | 0.0106 | 0.0995 | 0.0993 | 18.7606 |
131
+ | 0.0097 | 8.1046 | 37500 | 0.0051 | 0.1128 | 0.0175 | 0.1125 | 0.1125 | 18.985 |
132
+ | 0.0098 | 8.2127 | 38000 | 0.0051 | 0.1006 | 0.0102 | 0.1003 | 0.1003 | 18.9701 |
133
+ | 0.0095 | 8.3207 | 38500 | 0.0050 | 0.1025 | 0.0105 | 0.1023 | 0.1021 | 18.7897 |
134
+ | 0.009 | 8.4288 | 39000 | 0.0050 | 0.1004 | 0.0088 | 0.1003 | 0.1002 | 18.7697 |
135
+ | 0.0095 | 8.5368 | 39500 | 0.0050 | 0.1023 | 0.0097 | 0.1023 | 0.1023 | 18.8238 |
136
+ | 0.0095 | 8.6449 | 40000 | 0.0050 | 0.0979 | 0.0091 | 0.0979 | 0.0977 | 18.8196 |
137
+ | 0.0092 | 8.7530 | 40500 | 0.0049 | 0.1011 | 0.01 | 0.1011 | 0.1009 | 18.926 |
138
+ | 0.0091 | 8.8610 | 41000 | 0.0049 | 0.1016 | 0.0103 | 0.1017 | 0.1015 | 18.9302 |
139
+ | 0.0091 | 8.9691 | 41500 | 0.0049 | 0.1016 | 0.0111 | 0.1013 | 0.1012 | 18.9302 |
140
+ | 0.0089 | 9.0772 | 42000 | 0.0049 | 0.1044 | 0.0113 | 0.1041 | 0.104 | 18.9302 |
141
+ | 0.0089 | 9.1852 | 42500 | 0.0049 | 0.1016 | 0.0111 | 0.1013 | 0.1012 | 18.9302 |
142
+ | 0.0089 | 9.2933 | 43000 | 0.0049 | 0.1031 | 0.0125 | 0.103 | 0.1027 | 18.9135 |
143
+ | 0.0088 | 9.4013 | 43500 | 0.0049 | 0.1009 | 0.0111 | 0.1007 | 0.1004 | 18.9302 |
144
+ | 0.0084 | 9.5094 | 44000 | 0.0049 | 0.1022 | 0.0114 | 0.1022 | 0.1019 | 18.9302 |
145
+ | 0.0087 | 9.6175 | 44500 | 0.0048 | 0.1031 | 0.0125 | 0.103 | 0.1027 | 18.9302 |
146
+ | 0.0082 | 9.7255 | 45000 | 0.0049 | 0.1015 | 0.0114 | 0.1014 | 0.1011 | 18.9302 |
147
+ | 0.0084 | 9.8336 | 45500 | 0.0048 | 0.1023 | 0.0125 | 0.1022 | 0.1019 | 18.9302 |
148
+ | 0.0081 | 9.9416 | 46000 | 0.0048 | 0.1023 | 0.0125 | 0.1022 | 0.1019 | 18.9302 |
149
+
150
+
151
+ ### Framework versions
152
+
153
+ - Transformers 4.42.0.dev0
154
+ - Pytorch 2.3.0+cu121
155
+ - Datasets 2.19.2
156
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-base",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "mt5",
20
+ "num_decoder_layers": 12,
21
+ "num_heads": 12,
22
+ "num_layers": 12,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "tokenizer_class": "T5Tokenizer",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.42.0.dev0",
31
+ "use_cache": true,
32
+ "vocab_size": 250112
33
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.42.0.dev0"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef0ef97ddb719fe2f22b339e6c60c7c686c7edbff00d8eff9411d796f79b2e40
3
+ size 2329601904
runs/Jun05_20-44-22_f2ba9c758eb2/events.out.tfevents.1717620353.f2ba9c758eb2.565.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26041f0d02869318d1ddfbda9d0ec72fab3ee6de39862693a2e9f7a23c446f34
3
+ size 5170
runs/Jun05_20-44-22_f2ba9c758eb2/events.out.tfevents.1717620533.f2ba9c758eb2.565.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5302e11f2aa3bfc17dd6b47edaa256819a212d9cc659c09ef7a49db8282bc16f
3
+ size 4184
runs/Jun05_20-54-15_f2ba9c758eb2/events.out.tfevents.1717620948.f2ba9c758eb2.5544.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3591e4c2339c0736ca76671054506611b1867aeae3db8832efbc162b9911cb6a
3
+ size 79371
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c75db174930c130a1b55e88f4ee57d5f706099adf12eb9c22bc9ef7c599da913
3
+ size 16330805
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [],
30
+ "clean_up_tokenization_spaces": true,
31
+ "eos_token": "</s>",
32
+ "extra_ids": 0,
33
+ "legacy": true,
34
+ "max_new_tokens": 512,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "<pad>",
37
+ "sp_model_kwargs": {},
38
+ "tokenizer_class": "T5Tokenizer",
39
+ "unk_token": "<unk>"
40
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:982a7ade757570e5612fcde4fe5a5d6d4f80abc845c6385a6ec7ede845e1e87c
3
+ size 5304