Adamas23 commited on
Commit
c76b5a1
1 Parent(s): 673c41b

End of training

Browse files
README.md ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: calculator_model_test
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
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: 0.0162
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: 40
42
+
43
+ ### Training results
44
+
45
+ | Training Loss | Epoch | Step | Validation Loss |
46
+ |:-------------:|:-----:|:----:|:---------------:|
47
+ | 2.7671 | 1.0 | 6 | 2.1243 |
48
+ | 1.8409 | 2.0 | 12 | 1.5234 |
49
+ | 1.3096 | 3.0 | 18 | 1.0612 |
50
+ | 0.9557 | 4.0 | 24 | 0.8622 |
51
+ | 0.8499 | 5.0 | 30 | 0.7836 |
52
+ | 0.7285 | 6.0 | 36 | 0.6873 |
53
+ | 0.6464 | 7.0 | 42 | 0.5698 |
54
+ | 0.5513 | 8.0 | 48 | 0.5230 |
55
+ | 0.4906 | 9.0 | 54 | 0.4933 |
56
+ | 0.4817 | 10.0 | 60 | 0.4228 |
57
+ | 0.388 | 11.0 | 66 | 0.3776 |
58
+ | 0.3697 | 12.0 | 72 | 0.3796 |
59
+ | 0.3994 | 13.0 | 78 | 0.3245 |
60
+ | 0.3127 | 14.0 | 84 | 0.3145 |
61
+ | 0.3215 | 15.0 | 90 | 0.2752 |
62
+ | 0.2758 | 16.0 | 96 | 0.2400 |
63
+ | 0.2507 | 17.0 | 102 | 0.2158 |
64
+ | 0.217 | 18.0 | 108 | 0.2150 |
65
+ | 0.2223 | 19.0 | 114 | 0.1940 |
66
+ | 0.1746 | 20.0 | 120 | 0.1826 |
67
+ | 0.1625 | 21.0 | 126 | 0.1445 |
68
+ | 0.1386 | 22.0 | 132 | 0.1421 |
69
+ | 0.1432 | 23.0 | 138 | 0.1241 |
70
+ | 0.1329 | 24.0 | 144 | 0.1104 |
71
+ | 0.1413 | 25.0 | 150 | 0.0889 |
72
+ | 0.1093 | 26.0 | 156 | 0.0765 |
73
+ | 0.0869 | 27.0 | 162 | 0.0596 |
74
+ | 0.0677 | 28.0 | 168 | 0.0495 |
75
+ | 0.0646 | 29.0 | 174 | 0.0397 |
76
+ | 0.0539 | 30.0 | 180 | 0.0359 |
77
+ | 0.0502 | 31.0 | 186 | 0.0339 |
78
+ | 0.0399 | 32.0 | 192 | 0.0285 |
79
+ | 0.0453 | 33.0 | 198 | 0.0239 |
80
+ | 0.0351 | 34.0 | 204 | 0.0223 |
81
+ | 0.039 | 35.0 | 210 | 0.0199 |
82
+ | 0.0255 | 36.0 | 216 | 0.0195 |
83
+ | 0.0259 | 37.0 | 222 | 0.0177 |
84
+ | 0.0241 | 38.0 | 228 | 0.0168 |
85
+ | 0.0251 | 39.0 | 234 | 0.0163 |
86
+ | 0.0239 | 40.0 | 240 | 0.0162 |
87
+
88
+
89
+ ### Framework versions
90
+
91
+ - Transformers 4.38.1
92
+ - Pytorch 2.1.0+cu121
93
+ - Datasets 2.18.0
94
+ - 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": 34
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": 34
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": "4.38.1",
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": "4.38.1"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d8b3effa605654cc97228060a9f386e0549bc6153a1a73b1e30c69d69467952
3
+ size 31168616
runs/Mar06_11-36-48_39a26eb66d2d/events.out.tfevents.1709725009.39a26eb66d2d.252.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ffe36d887c8899890f5995a7be4d0e58488f03167c248cff6c0e43cff80f015
3
+ size 27997
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 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "99": 16,
116
+ "10": 17,
117
+ "98": 18,
118
+ "11": 19,
119
+ "12": 20,
120
+ "97": 21,
121
+ "13": 22,
122
+ "96": 23,
123
+ "95": 24,
124
+ "14": 25,
125
+ "94": 26,
126
+ "15": 27,
127
+ "93": 28,
128
+ "16": 29,
129
+ "92": 30,
130
+ "17": 31,
131
+ "91": 32,
132
+ "18": 33
133
+ },
134
+ "merges": [
135
+ "9 9",
136
+ "1 0",
137
+ "9 8",
138
+ "1 1",
139
+ "1 2",
140
+ "9 7",
141
+ "1 3",
142
+ "9 6",
143
+ "9 5",
144
+ "1 4",
145
+ "9 4",
146
+ "1 5",
147
+ "9 3",
148
+ "1 6",
149
+ "9 2",
150
+ "1 7",
151
+ "9 1",
152
+ "1 8"
153
+ ]
154
+ }
155
+ }
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 sha256:2927464d0a68791dc1fc35a7ce36cd8aa776a70ecf01c86a319312356a440785
3
+ size 5112