alexbeta80 commited on
Commit
e0b0544
·
verified ·
1 Parent(s): 23ba0d0

End of training

Browse files
README.md CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.8879
21
 
22
  ## Model description
23
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 9.0437 | 1.0 | 50 | 4.3564 |
52
- | 3.6792 | 2.0 | 100 | 2.1457 |
53
- | 2.4216 | 3.0 | 150 | 1.8879 |
54
 
55
 
56
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.3545
21
 
22
  ## Model description
23
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 1.853 | 1.0 | 100 | 0.5830 |
52
+ | 0.6005 | 2.0 | 200 | 0.3953 |
53
+ | 0.4386 | 3.0 | 300 | 0.3545 |
54
 
55
 
56
  ### Framework versions
added_tokens.json CHANGED
@@ -1,22 +1,18 @@
1
  {
2
  "</s>": 2,
3
- "</s_CODICI>": 57535,
4
- "</s_DATA>": 57527,
5
- "</s_FORNITORE>": 57532,
6
- "</s_NUMERO>": 57531,
7
- "</s_OGGETTI>": 57534,
8
- "</s_POSIZIONI>": 57528,
9
- "</s_QUANTITA>": 57529,
10
  "<mask>": 57521,
11
  "<pad>": 1,
12
  "<s>": 0,
 
13
  "<s_CODICI>": 57526,
14
- "<s_DATA>": 57525,
15
- "<s_FORNITORE>": 57530,
16
- "<s_NUMERO>": 57538,
17
- "<s_OGGETTI>": 57537,
18
- "<s_POSIZIONI>": 57533,
19
- "<s_QUANTITA>": 57536,
20
  "<s_iitcdip>": 57523,
21
  "<s_synthdog>": 57524,
22
  "<sep/>": 57522,
 
1
  {
2
  "</s>": 2,
3
+ "</s_CODICE>": 57529,
4
+ "</s_CODICI>": 57532,
5
+ "</s_POSIZIONE>": 57528,
6
+ "</s_POSIZIONI>": 57525,
7
+ "</s_QUANTITA>": 57530,
 
 
8
  "<mask>": 57521,
9
  "<pad>": 1,
10
  "<s>": 0,
11
+ "<s_CODICE>": 57534,
12
  "<s_CODICI>": 57526,
13
+ "<s_POSIZIONE>": 57527,
14
+ "<s_POSIZIONI>": 57531,
15
+ "<s_QUANTITA>": 57533,
 
 
 
16
  "<s_iitcdip>": 57523,
17
  "<s_synthdog>": 57524,
18
  "<sep/>": 57522,
config.json CHANGED
@@ -85,7 +85,7 @@
85
  "typical_p": 1.0,
86
  "use_bfloat16": false,
87
  "use_cache": true,
88
- "vocab_size": 57539
89
  },
90
  "decoder_start_token_id": 0,
91
  "encoder": {
 
85
  "typical_p": 1.0,
86
  "use_bfloat16": false,
87
  "use_cache": true,
88
+ "vocab_size": 57535
89
  },
90
  "decoder_start_token_id": 0,
91
  "encoder": {
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b6aebb4453933dfa8157ded0f7e7960339e0c8e89fd96cbeba31d257b809180
3
- size 809236694
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f77222446b5baa5d59ff3f66bff13f80238b34b9923329aa69cbd0e96d14cec
3
+ size 809220310
special_tokens_map.json CHANGED
@@ -2,22 +2,18 @@
2
  "additional_special_tokens": [
3
  "<s_iitcdip>",
4
  "<s_synthdog>",
5
- "<s_DATA>",
6
- "<s_CODICI>",
7
- "</s_DATA>",
8
  "</s_POSIZIONI>",
9
- "<s>",
10
  "</s>",
 
 
 
11
  "</s_QUANTITA>",
12
- "<s_FORNITORE>",
13
- "</s_NUMERO>",
14
- "</s_FORNITORE>",
15
  "<s_POSIZIONI>",
16
- "</s_OGGETTI>",
17
  "</s_CODICI>",
18
  "<s_QUANTITA>",
19
- "<s_OGGETTI>",
20
- "<s_NUMERO>"
21
  ],
22
  "bos_token": "<s>",
23
  "cls_token": "<s>",
 
2
  "additional_special_tokens": [
3
  "<s_iitcdip>",
4
  "<s_synthdog>",
 
 
 
5
  "</s_POSIZIONI>",
6
+ "<s_CODICI>",
7
  "</s>",
8
+ "<s_POSIZIONE>",
9
+ "</s_POSIZIONE>",
10
+ "</s_CODICE>",
11
  "</s_QUANTITA>",
 
 
 
12
  "<s_POSIZIONI>",
 
13
  "</s_CODICI>",
14
  "<s_QUANTITA>",
15
+ "<s_CODICE>",
16
+ "<s>"
17
  ],
18
  "bos_token": "<s>",
19
  "cls_token": "<s>",
tokenizer.json CHANGED
@@ -1,21 +1,7 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
- "padding": {
10
- "strategy": {
11
- "Fixed": 512
12
- },
13
- "direction": "Right",
14
- "pad_to_multiple_of": null,
15
- "pad_id": 1,
16
- "pad_type_id": 0,
17
- "pad_token": "<pad>"
18
- },
19
  "added_tokens": [
20
  {
21
  "id": 0,
@@ -91,7 +77,7 @@
91
  },
92
  {
93
  "id": 57525,
94
- "content": "<s_DATA>",
95
  "single_word": false,
96
  "lstrip": true,
97
  "rstrip": true,
@@ -109,7 +95,7 @@
109
  },
110
  {
111
  "id": 57527,
112
- "content": "</s_DATA>",
113
  "single_word": false,
114
  "lstrip": true,
115
  "rstrip": true,
@@ -118,7 +104,7 @@
118
  },
119
  {
120
  "id": 57528,
121
- "content": "</s_POSIZIONI>",
122
  "single_word": false,
123
  "lstrip": true,
124
  "rstrip": true,
@@ -127,7 +113,7 @@
127
  },
128
  {
129
  "id": 57529,
130
- "content": "</s_QUANTITA>",
131
  "single_word": false,
132
  "lstrip": true,
133
  "rstrip": true,
@@ -136,7 +122,7 @@
136
  },
137
  {
138
  "id": 57530,
139
- "content": "<s_FORNITORE>",
140
  "single_word": false,
141
  "lstrip": true,
142
  "rstrip": true,
@@ -145,24 +131,6 @@
145
  },
146
  {
147
  "id": 57531,
148
- "content": "</s_NUMERO>",
149
- "single_word": false,
150
- "lstrip": true,
151
- "rstrip": true,
152
- "normalized": false,
153
- "special": true
154
- },
155
- {
156
- "id": 57532,
157
- "content": "</s_FORNITORE>",
158
- "single_word": false,
159
- "lstrip": true,
160
- "rstrip": true,
161
- "normalized": false,
162
- "special": true
163
- },
164
- {
165
- "id": 57533,
166
  "content": "<s_POSIZIONI>",
167
  "single_word": false,
168
  "lstrip": true,
@@ -171,16 +139,7 @@
171
  "special": true
172
  },
173
  {
174
- "id": 57534,
175
- "content": "</s_OGGETTI>",
176
- "single_word": false,
177
- "lstrip": true,
178
- "rstrip": true,
179
- "normalized": false,
180
- "special": true
181
- },
182
- {
183
- "id": 57535,
184
  "content": "</s_CODICI>",
185
  "single_word": false,
186
  "lstrip": true,
@@ -189,7 +148,7 @@
189
  "special": true
190
  },
191
  {
192
- "id": 57536,
193
  "content": "<s_QUANTITA>",
194
  "single_word": false,
195
  "lstrip": true,
@@ -198,17 +157,8 @@
198
  "special": true
199
  },
200
  {
201
- "id": 57537,
202
- "content": "<s_OGGETTI>",
203
- "single_word": false,
204
- "lstrip": true,
205
- "rstrip": true,
206
- "normalized": false,
207
- "special": true
208
- },
209
- {
210
- "id": 57538,
211
- "content": "<s_NUMERO>",
212
  "single_word": false,
213
  "lstrip": true,
214
  "rstrip": true,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
 
77
  },
78
  {
79
  "id": 57525,
80
+ "content": "</s_POSIZIONI>",
81
  "single_word": false,
82
  "lstrip": true,
83
  "rstrip": true,
 
95
  },
96
  {
97
  "id": 57527,
98
+ "content": "<s_POSIZIONE>",
99
  "single_word": false,
100
  "lstrip": true,
101
  "rstrip": true,
 
104
  },
105
  {
106
  "id": 57528,
107
+ "content": "</s_POSIZIONE>",
108
  "single_word": false,
109
  "lstrip": true,
110
  "rstrip": true,
 
113
  },
114
  {
115
  "id": 57529,
116
+ "content": "</s_CODICE>",
117
  "single_word": false,
118
  "lstrip": true,
119
  "rstrip": true,
 
122
  },
123
  {
124
  "id": 57530,
125
+ "content": "</s_QUANTITA>",
126
  "single_word": false,
127
  "lstrip": true,
128
  "rstrip": true,
 
131
  },
132
  {
133
  "id": 57531,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  "content": "<s_POSIZIONI>",
135
  "single_word": false,
136
  "lstrip": true,
 
139
  "special": true
140
  },
141
  {
142
+ "id": 57532,
 
 
 
 
 
 
 
 
 
143
  "content": "</s_CODICI>",
144
  "single_word": false,
145
  "lstrip": true,
 
148
  "special": true
149
  },
150
  {
151
+ "id": 57533,
152
  "content": "<s_QUANTITA>",
153
  "single_word": false,
154
  "lstrip": true,
 
157
  "special": true
158
  },
159
  {
160
+ "id": 57534,
161
+ "content": "<s_CODICE>",
 
 
 
 
 
 
 
 
 
162
  "single_word": false,
163
  "lstrip": true,
164
  "rstrip": true,
tokenizer_config.json CHANGED
@@ -65,7 +65,7 @@
65
  "special": true
66
  },
67
  "57525": {
68
- "content": "<s_DATA>",
69
  "lstrip": true,
70
  "normalized": false,
71
  "rstrip": true,
@@ -81,7 +81,7 @@
81
  "special": true
82
  },
83
  "57527": {
84
- "content": "</s_DATA>",
85
  "lstrip": true,
86
  "normalized": false,
87
  "rstrip": true,
@@ -89,7 +89,7 @@
89
  "special": true
90
  },
91
  "57528": {
92
- "content": "</s_POSIZIONI>",
93
  "lstrip": true,
94
  "normalized": false,
95
  "rstrip": true,
@@ -97,7 +97,7 @@
97
  "special": true
98
  },
99
  "57529": {
100
- "content": "</s_QUANTITA>",
101
  "lstrip": true,
102
  "normalized": false,
103
  "rstrip": true,
@@ -105,7 +105,7 @@
105
  "special": true
106
  },
107
  "57530": {
108
- "content": "<s_FORNITORE>",
109
  "lstrip": true,
110
  "normalized": false,
111
  "rstrip": true,
@@ -113,22 +113,6 @@
113
  "special": true
114
  },
115
  "57531": {
116
- "content": "</s_NUMERO>",
117
- "lstrip": true,
118
- "normalized": false,
119
- "rstrip": true,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "57532": {
124
- "content": "</s_FORNITORE>",
125
- "lstrip": true,
126
- "normalized": false,
127
- "rstrip": true,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "57533": {
132
  "content": "<s_POSIZIONI>",
133
  "lstrip": true,
134
  "normalized": false,
@@ -136,15 +120,7 @@
136
  "single_word": false,
137
  "special": true
138
  },
139
- "57534": {
140
- "content": "</s_OGGETTI>",
141
- "lstrip": true,
142
- "normalized": false,
143
- "rstrip": true,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "57535": {
148
  "content": "</s_CODICI>",
149
  "lstrip": true,
150
  "normalized": false,
@@ -152,7 +128,7 @@
152
  "single_word": false,
153
  "special": true
154
  },
155
- "57536": {
156
  "content": "<s_QUANTITA>",
157
  "lstrip": true,
158
  "normalized": false,
@@ -160,16 +136,8 @@
160
  "single_word": false,
161
  "special": true
162
  },
163
- "57537": {
164
- "content": "<s_OGGETTI>",
165
- "lstrip": true,
166
- "normalized": false,
167
- "rstrip": true,
168
- "single_word": false,
169
- "special": true
170
- },
171
- "57538": {
172
- "content": "<s_NUMERO>",
173
  "lstrip": true,
174
  "normalized": false,
175
  "rstrip": true,
@@ -180,22 +148,18 @@
180
  "additional_special_tokens": [
181
  "<s_iitcdip>",
182
  "<s_synthdog>",
183
- "<s_DATA>",
184
- "<s_CODICI>",
185
- "</s_DATA>",
186
  "</s_POSIZIONI>",
187
- "<s>",
188
  "</s>",
 
 
 
189
  "</s_QUANTITA>",
190
- "<s_FORNITORE>",
191
- "</s_NUMERO>",
192
- "</s_FORNITORE>",
193
  "<s_POSIZIONI>",
194
- "</s_OGGETTI>",
195
  "</s_CODICI>",
196
  "<s_QUANTITA>",
197
- "<s_OGGETTI>",
198
- "<s_NUMERO>"
199
  ],
200
  "bos_token": "<s>",
201
  "clean_up_tokenization_spaces": true,
 
65
  "special": true
66
  },
67
  "57525": {
68
+ "content": "</s_POSIZIONI>",
69
  "lstrip": true,
70
  "normalized": false,
71
  "rstrip": true,
 
81
  "special": true
82
  },
83
  "57527": {
84
+ "content": "<s_POSIZIONE>",
85
  "lstrip": true,
86
  "normalized": false,
87
  "rstrip": true,
 
89
  "special": true
90
  },
91
  "57528": {
92
+ "content": "</s_POSIZIONE>",
93
  "lstrip": true,
94
  "normalized": false,
95
  "rstrip": true,
 
97
  "special": true
98
  },
99
  "57529": {
100
+ "content": "</s_CODICE>",
101
  "lstrip": true,
102
  "normalized": false,
103
  "rstrip": true,
 
105
  "special": true
106
  },
107
  "57530": {
108
+ "content": "</s_QUANTITA>",
109
  "lstrip": true,
110
  "normalized": false,
111
  "rstrip": true,
 
113
  "special": true
114
  },
115
  "57531": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
116
  "content": "<s_POSIZIONI>",
117
  "lstrip": true,
118
  "normalized": false,
 
120
  "single_word": false,
121
  "special": true
122
  },
123
+ "57532": {
 
 
 
 
 
 
 
 
124
  "content": "</s_CODICI>",
125
  "lstrip": true,
126
  "normalized": false,
 
128
  "single_word": false,
129
  "special": true
130
  },
131
+ "57533": {
132
  "content": "<s_QUANTITA>",
133
  "lstrip": true,
134
  "normalized": false,
 
136
  "single_word": false,
137
  "special": true
138
  },
139
+ "57534": {
140
+ "content": "<s_CODICE>",
 
 
 
 
 
 
 
 
141
  "lstrip": true,
142
  "normalized": false,
143
  "rstrip": true,
 
148
  "additional_special_tokens": [
149
  "<s_iitcdip>",
150
  "<s_synthdog>",
 
 
 
151
  "</s_POSIZIONI>",
152
+ "<s_CODICI>",
153
  "</s>",
154
+ "<s_POSIZIONE>",
155
+ "</s_POSIZIONE>",
156
+ "</s_CODICE>",
157
  "</s_QUANTITA>",
 
 
 
158
  "<s_POSIZIONI>",
 
159
  "</s_CODICI>",
160
  "<s_QUANTITA>",
161
+ "<s_CODICE>",
162
+ "<s>"
163
  ],
164
  "bos_token": "<s>",
165
  "clean_up_tokenization_spaces": true,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2a735dac94e68727f3a9b7e6cad599d4554366548680fba70beb659366f1135
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d66378bc8123f196b8ea02123a5a19a9dadb9f54daad125e8e98ce9d42886957
3
  size 4664