Hugging Face's logo

wtd
/
calculator_model_test

Transformers
Safetensors
encoder-decoder
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
wtd commited on
Commit
1d78c48
·
verified ·
1 Parent(s): 4f5676a

End of training

Browse files
Files changed (7) hide show
  1. README.md +95 -0
  2. config.json +94 -0
  3. generation_config.json +12 -0
  4. model.safetensors +3 -0
  5. tokenizer.json +300 -0
  6. tokenizer_config.json +8 -0
  7. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: calculator_model_test
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # calculator_model_test
14
+
15
+ This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.5500
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 0.001
37
+ - train_batch_size: 512
38
+ - eval_batch_size: 512
39
+ - seed: 42
40
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 40
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:----:|:---------------:|
48
+ | 3.4851 | 1.0 | 5 | 2.9408 |
49
+ | 2.5835 | 2.0 | 10 | 2.1787 |
50
+ | 1.9668 | 3.0 | 15 | 1.7919 |
51
+ | 1.7209 | 4.0 | 20 | 1.6411 |
52
+ | 1.5973 | 5.0 | 25 | 1.5588 |
53
+ | 1.5383 | 6.0 | 30 | 1.4900 |
54
+ | 1.4628 | 7.0 | 35 | 1.4556 |
55
+ | 1.4427 | 8.0 | 40 | 1.4175 |
56
+ | 1.3979 | 9.0 | 45 | 1.3629 |
57
+ | 1.3421 | 10.0 | 50 | 1.2893 |
58
+ | 1.2395 | 11.0 | 55 | 1.1524 |
59
+ | 1.1789 | 12.0 | 60 | 1.1692 |
60
+ | 1.1266 | 13.0 | 65 | 1.0435 |
61
+ | 1.0469 | 14.0 | 70 | 0.9994 |
62
+ | 1.0149 | 15.0 | 75 | 1.0576 |
63
+ | 1.0010 | 16.0 | 80 | 0.9336 |
64
+ | 0.9451 | 17.0 | 85 | 0.8939 |
65
+ | 0.9079 | 18.0 | 90 | 0.8588 |
66
+ | 0.8922 | 19.0 | 95 | 0.8718 |
67
+ | 0.8619 | 20.0 | 100 | 0.8359 |
68
+ | 0.8458 | 21.0 | 105 | 0.7859 |
69
+ | 0.8284 | 22.0 | 110 | 0.7901 |
70
+ | 0.8187 | 23.0 | 115 | 0.7792 |
71
+ | 0.7879 | 24.0 | 120 | 0.7507 |
72
+ | 0.7589 | 25.0 | 125 | 0.7389 |
73
+ | 0.7497 | 26.0 | 130 | 0.7087 |
74
+ | 0.7263 | 27.0 | 135 | 0.6955 |
75
+ | 0.7082 | 28.0 | 140 | 0.6706 |
76
+ | 0.6982 | 29.0 | 145 | 0.6740 |
77
+ | 0.6815 | 30.0 | 150 | 0.6415 |
78
+ | 0.6655 | 31.0 | 155 | 0.6237 |
79
+ | 0.6555 | 32.0 | 160 | 0.6191 |
80
+ | 0.6435 | 33.0 | 165 | 0.6018 |
81
+ | 0.6303 | 34.0 | 170 | 0.5913 |
82
+ | 0.6235 | 35.0 | 175 | 0.5822 |
83
+ | 0.6098 | 36.0 | 180 | 0.5722 |
84
+ | 0.6044 | 37.0 | 185 | 0.5670 |
85
+ | 0.5995 | 38.0 | 190 | 0.5563 |
86
+ | 0.5915 | 39.0 | 195 | 0.5555 |
87
+ | 0.5864 | 40.0 | 200 | 0.5500 |
88
+
89
+
90
+ ### Framework versions
91
+
92
+ - Transformers 5.0.0
93
+ - Pytorch 2.10.0+cpu
94
+ - Datasets 4.0.0
95
+ - Tokenizers 0.22.2
config.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token_id": null,
11
+ "chunk_size_feed_forward": 0,
12
+ "classifier_dropout": null,
13
+ "dtype": null,
14
+ "eos_token_id": null,
15
+ "hidden_act": "gelu",
16
+ "hidden_dropout_prob": 0.1,
17
+ "hidden_size": 256,
18
+ "id2label": {
19
+ "0": "LABEL_0",
20
+ "1": "LABEL_1"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 1024,
24
+ "is_decoder": true,
25
+ "is_encoder_decoder": false,
26
+ "label2id": {
27
+ "LABEL_0": 0,
28
+ "LABEL_1": 1
29
+ },
30
+ "layer_norm_eps": 1e-12,
31
+ "max_position_embeddings": 512,
32
+ "model_type": "bert",
33
+ "num_attention_heads": 4,
34
+ "num_hidden_layers": 4,
35
+ "output_attentions": false,
36
+ "output_hidden_states": false,
37
+ "pad_token_id": 0,
38
+ "problem_type": null,
39
+ "return_dict": true,
40
+ "tie_word_embeddings": true,
41
+ "type_vocab_size": 2,
42
+ "use_cache": true,
43
+ "vocab_size": 52
44
+ },
45
+ "decoder_start_token_id": 2,
46
+ "dtype": "float32",
47
+ "encoder": {
48
+ "_name_or_path": "",
49
+ "add_cross_attention": false,
50
+ "architectures": null,
51
+ "attention_probs_dropout_prob": 0.1,
52
+ "bos_token_id": null,
53
+ "chunk_size_feed_forward": 0,
54
+ "classifier_dropout": null,
55
+ "dtype": null,
56
+ "eos_token_id": null,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout_prob": 0.1,
59
+ "hidden_size": 256,
60
+ "id2label": {
61
+ "0": "LABEL_0",
62
+ "1": "LABEL_1"
63
+ },
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 1024,
66
+ "is_decoder": false,
67
+ "is_encoder_decoder": false,
68
+ "label2id": {
69
+ "LABEL_0": 0,
70
+ "LABEL_1": 1
71
+ },
72
+ "layer_norm_eps": 1e-12,
73
+ "max_position_embeddings": 512,
74
+ "model_type": "bert",
75
+ "num_attention_heads": 4,
76
+ "num_hidden_layers": 4,
77
+ "output_attentions": false,
78
+ "output_hidden_states": false,
79
+ "pad_token_id": 0,
80
+ "problem_type": null,
81
+ "return_dict": true,
82
+ "tie_word_embeddings": true,
83
+ "type_vocab_size": 2,
84
+ "use_cache": true,
85
+ "vocab_size": 52
86
+ },
87
+ "eos_token_id": 0,
88
+ "is_encoder_decoder": true,
89
+ "model_type": "encoder-decoder",
90
+ "pad_token_id": 3,
91
+ "transformers_version": "5.0.0",
92
+ "unk_token_id": null,
93
+ "use_cache": false
94
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 2,
4
+ "eos_token_id": [
5
+ 0
6
+ ],
7
+ "output_attentions": false,
8
+ "output_hidden_states": false,
9
+ "pad_token_id": 3,
10
+ "transformers_version": "5.0.0",
11
+ "use_cache": true
12
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:953334a2882f1b73612ab6395f352673190781e4f503bb027afc517c6ee080c8
3
+ size 31205552
tokenizer.json ADDED
@@ -0,0 +1,300 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "ignore_merges": false,
99
+ "vocab": {
100
+ "[EOS]": 0,
101
+ "[UNK]": 1,
102
+ "[CLS]": 2,
103
+ "[PAD]": 3,
104
+ "+": 4,
105
+ "-": 5,
106
+ "0": 6,
107
+ "1": 7,
108
+ "2": 8,
109
+ "3": 9,
110
+ "4": 10,
111
+ "5": 11,
112
+ "6": 12,
113
+ "7": 13,
114
+ "8": 14,
115
+ "9": 15,
116
+ "10": 16,
117
+ "99": 17,
118
+ "11": 18,
119
+ "98": 19,
120
+ "97": 20,
121
+ "12": 21,
122
+ "96": 22,
123
+ "13": 23,
124
+ "95": 24,
125
+ "14": 25,
126
+ "15": 26,
127
+ "94": 27,
128
+ "93": 28,
129
+ "16": 29,
130
+ "17": 30,
131
+ "92": 31,
132
+ "18": 32,
133
+ "91": 33,
134
+ "19": 34,
135
+ "90": 35,
136
+ "20": 36,
137
+ "89": 37,
138
+ "88": 38,
139
+ "21": 39,
140
+ "22": 40,
141
+ "87": 41,
142
+ "86": 42,
143
+ "23": 43,
144
+ "24": 44,
145
+ "25": 45,
146
+ "84": 46,
147
+ "85": 47,
148
+ "26": 48,
149
+ "83": 49,
150
+ "27": 50,
151
+ "82": 51
152
+ },
153
+ "merges": [
154
+ [
155
+ "1",
156
+ "0"
157
+ ],
158
+ [
159
+ "9",
160
+ "9"
161
+ ],
162
+ [
163
+ "1",
164
+ "1"
165
+ ],
166
+ [
167
+ "9",
168
+ "8"
169
+ ],
170
+ [
171
+ "9",
172
+ "7"
173
+ ],
174
+ [
175
+ "1",
176
+ "2"
177
+ ],
178
+ [
179
+ "9",
180
+ "6"
181
+ ],
182
+ [
183
+ "1",
184
+ "3"
185
+ ],
186
+ [
187
+ "9",
188
+ "5"
189
+ ],
190
+ [
191
+ "1",
192
+ "4"
193
+ ],
194
+ [
195
+ "1",
196
+ "5"
197
+ ],
198
+ [
199
+ "9",
200
+ "4"
201
+ ],
202
+ [
203
+ "9",
204
+ "3"
205
+ ],
206
+ [
207
+ "1",
208
+ "6"
209
+ ],
210
+ [
211
+ "1",
212
+ "7"
213
+ ],
214
+ [
215
+ "9",
216
+ "2"
217
+ ],
218
+ [
219
+ "1",
220
+ "8"
221
+ ],
222
+ [
223
+ "9",
224
+ "1"
225
+ ],
226
+ [
227
+ "1",
228
+ "9"
229
+ ],
230
+ [
231
+ "9",
232
+ "0"
233
+ ],
234
+ [
235
+ "2",
236
+ "0"
237
+ ],
238
+ [
239
+ "8",
240
+ "9"
241
+ ],
242
+ [
243
+ "8",
244
+ "8"
245
+ ],
246
+ [
247
+ "2",
248
+ "1"
249
+ ],
250
+ [
251
+ "2",
252
+ "2"
253
+ ],
254
+ [
255
+ "8",
256
+ "7"
257
+ ],
258
+ [
259
+ "8",
260
+ "6"
261
+ ],
262
+ [
263
+ "2",
264
+ "3"
265
+ ],
266
+ [
267
+ "2",
268
+ "4"
269
+ ],
270
+ [
271
+ "2",
272
+ "5"
273
+ ],
274
+ [
275
+ "8",
276
+ "4"
277
+ ],
278
+ [
279
+ "8",
280
+ "5"
281
+ ],
282
+ [
283
+ "2",
284
+ "6"
285
+ ],
286
+ [
287
+ "8",
288
+ "3"
289
+ ],
290
+ [
291
+ "2",
292
+ "7"
293
+ ],
294
+ [
295
+ "8",
296
+ "2"
297
+ ]
298
+ ]
299
+ }
300
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[EOS]",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "pad_token": "[PAD]",
7
+ "tokenizer_class": "TokenizersBackend"
8
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0d03dc40fda592f09c806514aa895333bb76b63d79d79a67d73d2dd95f0c956
3
+ size 5329