Marcin1304 commited on
Commit
2fe1818
1 Parent(s): 5d49caf

End of training

Browse files
README.md ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: calculator_model_test_third_version
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # calculator_model_test_third_version
13
+
14
+ This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 0.2789
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 0.001
36
+ - train_batch_size: 512
37
+ - eval_batch_size: 512
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 100
42
+
43
+ ### Training results
44
+
45
+ | Training Loss | Epoch | Step | Validation Loss |
46
+ |:-------------:|:-----:|:----:|:---------------:|
47
+ | 3.4163 | 1.0 | 6 | 2.7578 |
48
+ | 2.3764 | 2.0 | 12 | 1.9673 |
49
+ | 1.794 | 3.0 | 18 | 1.6871 |
50
+ | 1.682 | 4.0 | 24 | 1.6571 |
51
+ | 1.6127 | 5.0 | 30 | 1.5569 |
52
+ | 1.5398 | 6.0 | 36 | 1.5012 |
53
+ | 1.5125 | 7.0 | 42 | 1.5110 |
54
+ | 1.521 | 8.0 | 48 | 1.4432 |
55
+ | 1.4421 | 9.0 | 54 | 1.3939 |
56
+ | 1.3958 | 10.0 | 60 | 1.3717 |
57
+ | 1.3615 | 11.0 | 66 | 1.2885 |
58
+ | 1.2466 | 12.0 | 72 | 1.2391 |
59
+ | 1.2277 | 13.0 | 78 | 1.1908 |
60
+ | 1.1821 | 14.0 | 84 | 1.2211 |
61
+ | 1.1512 | 15.0 | 90 | 1.1313 |
62
+ | 1.1268 | 16.0 | 96 | 1.0571 |
63
+ | 1.0752 | 17.0 | 102 | 1.0546 |
64
+ | 1.0988 | 18.0 | 108 | 1.0526 |
65
+ | 1.0499 | 19.0 | 114 | 1.0063 |
66
+ | 0.9957 | 20.0 | 120 | 0.9662 |
67
+ | 1.0018 | 21.0 | 126 | 0.9062 |
68
+ | 0.9747 | 22.0 | 132 | 0.9273 |
69
+ | 0.9545 | 23.0 | 138 | 1.0973 |
70
+ | 1.0842 | 24.0 | 144 | 1.1854 |
71
+ | 1.0838 | 25.0 | 150 | 1.0031 |
72
+ | 0.9812 | 26.0 | 156 | 1.0129 |
73
+ | 1.0154 | 27.0 | 162 | 0.9693 |
74
+ | 0.9441 | 28.0 | 168 | 0.8257 |
75
+ | 0.863 | 29.0 | 174 | 0.8138 |
76
+ | 0.8591 | 30.0 | 180 | 0.8746 |
77
+ | 0.8913 | 31.0 | 186 | 0.8592 |
78
+ | 0.8719 | 32.0 | 192 | 0.7773 |
79
+ | 0.8187 | 33.0 | 198 | 0.7999 |
80
+ | 0.8013 | 34.0 | 204 | 0.7491 |
81
+ | 0.7976 | 35.0 | 210 | 0.7171 |
82
+ | 0.8033 | 36.0 | 216 | 0.7610 |
83
+ | 0.7785 | 37.0 | 222 | 0.8047 |
84
+ | 0.8141 | 38.0 | 228 | 0.7245 |
85
+ | 0.7726 | 39.0 | 234 | 0.6725 |
86
+ | 0.7832 | 40.0 | 240 | 0.8410 |
87
+ | 0.8625 | 41.0 | 246 | 0.7093 |
88
+ | 0.7307 | 42.0 | 252 | 0.6675 |
89
+ | 0.6832 | 43.0 | 258 | 0.6891 |
90
+ | 0.7126 | 44.0 | 264 | 0.7927 |
91
+ | 0.7808 | 45.0 | 270 | 0.7757 |
92
+ | 0.8031 | 46.0 | 276 | 0.6749 |
93
+ | 0.728 | 47.0 | 282 | 0.7299 |
94
+ | 0.741 | 48.0 | 288 | 0.6062 |
95
+ | 0.6772 | 49.0 | 294 | 0.6449 |
96
+ | 0.6505 | 50.0 | 300 | 0.6041 |
97
+ | 0.6315 | 51.0 | 306 | 0.5769 |
98
+ | 0.6339 | 52.0 | 312 | 0.6003 |
99
+ | 0.6388 | 53.0 | 318 | 0.6115 |
100
+ | 0.6436 | 54.0 | 324 | 0.5778 |
101
+ | 0.5993 | 55.0 | 330 | 0.5777 |
102
+ | 0.5936 | 56.0 | 336 | 0.5614 |
103
+ | 0.5873 | 57.0 | 342 | 0.5445 |
104
+ | 0.5819 | 58.0 | 348 | 0.5437 |
105
+ | 0.5523 | 59.0 | 354 | 0.4961 |
106
+ | 0.5527 | 60.0 | 360 | 0.4939 |
107
+ | 0.5622 | 61.0 | 366 | 0.4922 |
108
+ | 0.5603 | 62.0 | 372 | 0.5252 |
109
+ | 0.612 | 63.0 | 378 | 0.5024 |
110
+ | 0.6284 | 64.0 | 384 | 0.5152 |
111
+ | 0.573 | 65.0 | 390 | 0.5300 |
112
+ | 0.5407 | 66.0 | 396 | 0.4879 |
113
+ | 0.5266 | 67.0 | 402 | 0.4813 |
114
+ | 0.526 | 68.0 | 408 | 0.4341 |
115
+ | 0.5306 | 69.0 | 414 | 0.4817 |
116
+ | 0.5108 | 70.0 | 420 | 0.4127 |
117
+ | 0.5079 | 71.0 | 426 | 0.5083 |
118
+ | 0.5237 | 72.0 | 432 | 0.4423 |
119
+ | 0.5049 | 73.0 | 438 | 0.4948 |
120
+ | 0.491 | 74.0 | 444 | 0.4121 |
121
+ | 0.484 | 75.0 | 450 | 0.4047 |
122
+ | 0.4668 | 76.0 | 456 | 0.4041 |
123
+ | 0.4669 | 77.0 | 462 | 0.3987 |
124
+ | 0.4524 | 78.0 | 468 | 0.4115 |
125
+ | 0.4604 | 79.0 | 474 | 0.3926 |
126
+ | 0.4536 | 80.0 | 480 | 0.3970 |
127
+ | 0.4747 | 81.0 | 486 | 0.3674 |
128
+ | 0.4417 | 82.0 | 492 | 0.3905 |
129
+ | 0.458 | 83.0 | 498 | 0.4045 |
130
+ | 0.4393 | 84.0 | 504 | 0.3889 |
131
+ | 0.431 | 85.0 | 510 | 0.3427 |
132
+ | 0.4076 | 86.0 | 516 | 0.3621 |
133
+ | 0.4239 | 87.0 | 522 | 0.3368 |
134
+ | 0.4089 | 88.0 | 528 | 0.3353 |
135
+ | 0.3936 | 89.0 | 534 | 0.3253 |
136
+ | 0.3899 | 90.0 | 540 | 0.3173 |
137
+ | 0.3792 | 91.0 | 546 | 0.3065 |
138
+ | 0.3774 | 92.0 | 552 | 0.3060 |
139
+ | 0.3677 | 93.0 | 558 | 0.3063 |
140
+ | 0.3655 | 94.0 | 564 | 0.2909 |
141
+ | 0.3608 | 95.0 | 570 | 0.2944 |
142
+ | 0.3561 | 96.0 | 576 | 0.2842 |
143
+ | 0.3593 | 97.0 | 582 | 0.2906 |
144
+ | 0.357 | 98.0 | 588 | 0.2800 |
145
+ | 0.3558 | 99.0 | 594 | 0.2751 |
146
+ | 0.3456 | 100.0 | 600 | 0.2789 |
147
+
148
+
149
+ ### Framework versions
150
+
151
+ - Transformers 4.38.2
152
+ - Pytorch 2.1.0+cu121
153
+ - Datasets 2.18.0
154
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "",
7
+ "add_cross_attention": true,
8
+ "architectures": null,
9
+ "attention_probs_dropout_prob": 0.1,
10
+ "bad_words_ids": null,
11
+ "begin_suppress_tokens": null,
12
+ "bos_token_id": null,
13
+ "chunk_size_feed_forward": 0,
14
+ "classifier_dropout": null,
15
+ "cross_attention_hidden_size": null,
16
+ "decoder_start_token_id": null,
17
+ "diversity_penalty": 0.0,
18
+ "do_sample": false,
19
+ "early_stopping": false,
20
+ "encoder_no_repeat_ngram_size": 0,
21
+ "eos_token_id": null,
22
+ "exponential_decay_length_penalty": null,
23
+ "finetuning_task": null,
24
+ "forced_bos_token_id": null,
25
+ "forced_eos_token_id": null,
26
+ "hidden_act": "gelu",
27
+ "hidden_dropout_prob": 0.1,
28
+ "hidden_size": 256,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 1024,
35
+ "is_decoder": true,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "layer_norm_eps": 1e-12,
42
+ "length_penalty": 1.0,
43
+ "max_length": 20,
44
+ "max_position_embeddings": 512,
45
+ "min_length": 0,
46
+ "model_type": "bert",
47
+ "no_repeat_ngram_size": 0,
48
+ "num_attention_heads": 4,
49
+ "num_beam_groups": 1,
50
+ "num_beams": 1,
51
+ "num_hidden_layers": 4,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
55
+ "output_scores": false,
56
+ "pad_token_id": 0,
57
+ "position_embedding_type": "absolute",
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "pruned_heads": {},
61
+ "remove_invalid_values": false,
62
+ "repetition_penalty": 1.0,
63
+ "return_dict": true,
64
+ "return_dict_in_generate": false,
65
+ "sep_token_id": null,
66
+ "suppress_tokens": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tf_legacy_loss": false,
70
+ "tie_encoder_decoder": false,
71
+ "tie_word_embeddings": true,
72
+ "tokenizer_class": null,
73
+ "top_k": 50,
74
+ "top_p": 1.0,
75
+ "torch_dtype": null,
76
+ "torchscript": false,
77
+ "type_vocab_size": 2,
78
+ "typical_p": 1.0,
79
+ "use_bfloat16": false,
80
+ "use_cache": true,
81
+ "vocab_size": 53
82
+ },
83
+ "decoder_start_token_id": 2,
84
+ "encoder": {
85
+ "_name_or_path": "",
86
+ "add_cross_attention": false,
87
+ "architectures": null,
88
+ "attention_probs_dropout_prob": 0.1,
89
+ "bad_words_ids": null,
90
+ "begin_suppress_tokens": null,
91
+ "bos_token_id": null,
92
+ "chunk_size_feed_forward": 0,
93
+ "classifier_dropout": null,
94
+ "cross_attention_hidden_size": null,
95
+ "decoder_start_token_id": null,
96
+ "diversity_penalty": 0.0,
97
+ "do_sample": false,
98
+ "early_stopping": false,
99
+ "encoder_no_repeat_ngram_size": 0,
100
+ "eos_token_id": null,
101
+ "exponential_decay_length_penalty": null,
102
+ "finetuning_task": null,
103
+ "forced_bos_token_id": null,
104
+ "forced_eos_token_id": null,
105
+ "hidden_act": "gelu",
106
+ "hidden_dropout_prob": 0.1,
107
+ "hidden_size": 256,
108
+ "id2label": {
109
+ "0": "LABEL_0",
110
+ "1": "LABEL_1"
111
+ },
112
+ "initializer_range": 0.02,
113
+ "intermediate_size": 1024,
114
+ "is_decoder": false,
115
+ "is_encoder_decoder": false,
116
+ "label2id": {
117
+ "LABEL_0": 0,
118
+ "LABEL_1": 1
119
+ },
120
+ "layer_norm_eps": 1e-12,
121
+ "length_penalty": 1.0,
122
+ "max_length": 20,
123
+ "max_position_embeddings": 512,
124
+ "min_length": 0,
125
+ "model_type": "bert",
126
+ "no_repeat_ngram_size": 0,
127
+ "num_attention_heads": 4,
128
+ "num_beam_groups": 1,
129
+ "num_beams": 1,
130
+ "num_hidden_layers": 4,
131
+ "num_return_sequences": 1,
132
+ "output_attentions": false,
133
+ "output_hidden_states": false,
134
+ "output_scores": false,
135
+ "pad_token_id": 0,
136
+ "position_embedding_type": "absolute",
137
+ "prefix": null,
138
+ "problem_type": null,
139
+ "pruned_heads": {},
140
+ "remove_invalid_values": false,
141
+ "repetition_penalty": 1.0,
142
+ "return_dict": true,
143
+ "return_dict_in_generate": false,
144
+ "sep_token_id": null,
145
+ "suppress_tokens": null,
146
+ "task_specific_params": null,
147
+ "temperature": 1.0,
148
+ "tf_legacy_loss": false,
149
+ "tie_encoder_decoder": false,
150
+ "tie_word_embeddings": true,
151
+ "tokenizer_class": null,
152
+ "top_k": 50,
153
+ "top_p": 1.0,
154
+ "torch_dtype": null,
155
+ "torchscript": false,
156
+ "type_vocab_size": 2,
157
+ "typical_p": 1.0,
158
+ "use_bfloat16": false,
159
+ "use_cache": true,
160
+ "vocab_size": 53
161
+ },
162
+ "eos_token_id": 0,
163
+ "is_encoder_decoder": true,
164
+ "model_type": "encoder-decoder",
165
+ "pad_token_id": 3,
166
+ "torch_dtype": "float32",
167
+ "transformers_version": "4.38.2",
168
+ "unk_token_id": null
169
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 2,
4
+ "eos_token_id": 0,
5
+ "pad_token_id": 3,
6
+ "transformers_version": "4.38.2"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bdb0dc8431840aa72a57b8454a7ca5f498bd4b4a53dd39467139fb43d163e40
3
+ size 31207604
runs/Mar10_16-55-27_d0c17e360eb0/events.out.tfevents.1710089728.d0c17e360eb0.144.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a60c9e6ed671345f1e01fbfa34aa0966302906462d2efbf262baddaec0fd1e6
3
+ size 56960
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "[EOS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[EOS]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[UNK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[CLS]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[PAD]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ }
42
+ ],
43
+ "normalizer": null,
44
+ "pre_tokenizer": {
45
+ "type": "Whitespace"
46
+ },
47
+ "post_processor": {
48
+ "type": "TemplateProcessing",
49
+ "single": [
50
+ {
51
+ "Sequence": {
52
+ "id": "A",
53
+ "type_id": 0
54
+ }
55
+ },
56
+ {
57
+ "SpecialToken": {
58
+ "id": "[EOS]",
59
+ "type_id": 0
60
+ }
61
+ }
62
+ ],
63
+ "pair": [
64
+ {
65
+ "Sequence": {
66
+ "id": "A",
67
+ "type_id": 0
68
+ }
69
+ },
70
+ {
71
+ "Sequence": {
72
+ "id": "B",
73
+ "type_id": 1
74
+ }
75
+ }
76
+ ],
77
+ "special_tokens": {
78
+ "[EOS]": {
79
+ "id": "[EOS]",
80
+ "ids": [
81
+ 0
82
+ ],
83
+ "tokens": [
84
+ "[EOS]"
85
+ ]
86
+ }
87
+ }
88
+ },
89
+ "decoder": null,
90
+ "model": {
91
+ "type": "BPE",
92
+ "dropout": null,
93
+ "unk_token": "[UNK]",
94
+ "continuing_subword_prefix": null,
95
+ "end_of_word_suffix": null,
96
+ "fuse_unk": false,
97
+ "byte_fallback": false,
98
+ "vocab": {
99
+ "[EOS]": 0,
100
+ "[UNK]": 1,
101
+ "[CLS]": 2,
102
+ "[PAD]": 3,
103
+ "+": 4,
104
+ "-": 5,
105
+ "0": 6,
106
+ "1": 7,
107
+ "2": 8,
108
+ "3": 9,
109
+ "4": 10,
110
+ "5": 11,
111
+ "6": 12,
112
+ "7": 13,
113
+ "8": 14,
114
+ "9": 15,
115
+ "=": 16,
116
+ "99": 17,
117
+ "10": 18,
118
+ "98": 19,
119
+ "11": 20,
120
+ "97": 21,
121
+ "12": 22,
122
+ "96": 23,
123
+ "13": 24,
124
+ "95": 25,
125
+ "14": 26,
126
+ "94": 27,
127
+ "15": 28,
128
+ "93": 29,
129
+ "16": 30,
130
+ "17": 31,
131
+ "92": 32,
132
+ "18": 33,
133
+ "91": 34,
134
+ "90": 35,
135
+ "19": 36,
136
+ "20": 37,
137
+ "89": 38,
138
+ "21": 39,
139
+ "88": 40,
140
+ "87": 41,
141
+ "22": 42,
142
+ "23": 43,
143
+ "86": 44,
144
+ "85": 45,
145
+ "24": 46,
146
+ "25": 47,
147
+ "84": 48,
148
+ "83": 49,
149
+ "26": 50,
150
+ "27": 51,
151
+ "82": 52
152
+ },
153
+ "merges": [
154
+ "9 9",
155
+ "1 0",
156
+ "9 8",
157
+ "1 1",
158
+ "9 7",
159
+ "1 2",
160
+ "9 6",
161
+ "1 3",
162
+ "9 5",
163
+ "1 4",
164
+ "9 4",
165
+ "1 5",
166
+ "9 3",
167
+ "1 6",
168
+ "1 7",
169
+ "9 2",
170
+ "1 8",
171
+ "9 1",
172
+ "9 0",
173
+ "1 9",
174
+ "2 0",
175
+ "8 9",
176
+ "2 1",
177
+ "8 8",
178
+ "8 7",
179
+ "2 2",
180
+ "2 3",
181
+ "8 6",
182
+ "8 5",
183
+ "2 4",
184
+ "2 5",
185
+ "8 4",
186
+ "8 3",
187
+ "2 6",
188
+ "2 7",
189
+ "8 2"
190
+ ]
191
+ }
192
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[EOS]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "clean_up_tokenization_spaces": true,
37
+ "cls_token": "[CLS]",
38
+ "eos_token": "[EOS]",
39
+ "model_max_length": 1000000000000000019884624838656,
40
+ "pad_token": "[PAD]",
41
+ "tokenizer_class": "PreTrainedTokenizerFast"
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4631492100d117e0b8cefb155bacc828297245e2baa79f6d038daa078369387
3
+ size 5112