Hugging Face's logo

ludziej
/
calculator_model_test

Text2Text Generation
Transformers
TensorBoard
Safetensors
encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ludziej commited on
Commit
df9d7c7
•
1 Parent(s): 41ae318

End of training

Browse files
Files changed (5) hide show
  1. README.md +52 -52
  2. model.safetensors +1 -1
  3. runs/Feb28_19-08-48_3897ec21fae5/events.out.tfevents.1709147328.3897ec21fae5.100515.0 +3 -0
  4. tokenizer.json +21 -21
  5. training_args.bin +1 -1
README.md CHANGED
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.8456
17
 
18
  ## Model description
19
 
@@ -32,7 +32,7 @@ More information needed
32
  ### Training hyperparameters
33
 
34
  The following hyperparameters were used during training:
35
- - learning_rate: 0.0001
36
  - train_batch_size: 512
37
  - eval_batch_size: 512
38
  - seed: 42
@@ -44,56 +44,56 @@ The following hyperparameters were used during training:
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
- | 3.5829 | 1.0 | 6 | 3.1864 |
48
- | 3.0602 | 2.0 | 12 | 2.8642 |
49
- | 2.7987 | 3.0 | 18 | 2.6521 |
50
- | 2.6074 | 4.0 | 24 | 2.5190 |
51
- | 2.5114 | 5.0 | 30 | 2.4076 |
52
- | 2.3968 | 6.0 | 36 | 2.3019 |
53
- | 2.2612 | 7.0 | 42 | 2.2065 |
54
- | 2.1937 | 8.0 | 48 | 2.1258 |
55
- | 2.1043 | 9.0 | 54 | 2.0391 |
56
- | 2.0193 | 10.0 | 60 | 1.9546 |
57
- | 1.9518 | 11.0 | 66 | 1.8654 |
58
- | 1.8505 | 12.0 | 72 | 1.7672 |
59
- | 1.7482 | 13.0 | 78 | 1.6792 |
60
- | 1.695 | 14.0 | 84 | 1.6032 |
61
- | 1.6015 | 15.0 | 90 | 1.5389 |
62
- | 1.5568 | 16.0 | 96 | 1.4837 |
63
- | 1.4888 | 17.0 | 102 | 1.4349 |
64
- | 1.4429 | 18.0 | 108 | 1.3923 |
65
- | 1.392 | 19.0 | 114 | 1.3534 |
66
- | 1.3448 | 20.0 | 120 | 1.3181 |
67
- | 1.306 | 21.0 | 126 | 1.2881 |
68
- | 1.2845 | 22.0 | 132 | 1.2568 |
69
- | 1.2813 | 23.0 | 138 | 1.2262 |
70
- | 1.2479 | 24.0 | 144 | 1.1989 |
71
- | 1.2164 | 25.0 | 150 | 1.1719 |
72
- | 1.2116 | 26.0 | 156 | 1.1514 |
73
- | 1.1514 | 27.0 | 162 | 1.1247 |
74
- | 1.1571 | 28.0 | 168 | 1.1012 |
75
- | 1.1334 | 29.0 | 174 | 1.0781 |
76
- | 1.1193 | 30.0 | 180 | 1.0559 |
77
- | 1.0721 | 31.0 | 186 | 1.0307 |
78
- | 1.041 | 32.0 | 192 | 1.0095 |
79
- | 1.02 | 33.0 | 198 | 0.9873 |
80
- | 1.0145 | 34.0 | 204 | 0.9694 |
81
- | 0.9817 | 35.0 | 210 | 0.9526 |
82
- | 0.9905 | 36.0 | 216 | 0.9391 |
83
- | 0.9691 | 37.0 | 222 | 0.9243 |
84
- | 0.9294 | 38.0 | 228 | 0.9117 |
85
- | 0.9265 | 39.0 | 234 | 0.8995 |
86
- | 0.9165 | 40.0 | 240 | 0.8897 |
87
- | 0.9059 | 41.0 | 246 | 0.8805 |
88
- | 0.8916 | 42.0 | 252 | 0.8727 |
89
- | 0.8632 | 43.0 | 258 | 0.8659 |
90
- | 0.8767 | 44.0 | 264 | 0.8608 |
91
- | 0.8878 | 45.0 | 270 | 0.8564 |
92
- | 0.8914 | 46.0 | 276 | 0.8522 |
93
- | 0.8632 | 47.0 | 282 | 0.8491 |
94
- | 0.8638 | 48.0 | 288 | 0.8469 |
95
- | 0.843 | 49.0 | 294 | 0.8460 |
96
- | 0.8565 | 50.0 | 300 | 0.8456 |
97
 
98
 
99
  ### Framework versions
 
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: 0.1435
17
 
18
  ## Model description
19
 
 
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
 
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
+ | 3.0221 | 1.0 | 6 | 2.2896 |
48
+ | 2.055 | 2.0 | 12 | 1.7915 |
49
+ | 1.6422 | 3.0 | 18 | 1.4365 |
50
+ | 1.2892 | 4.0 | 24 | 1.1407 |
51
+ | 1.0661 | 5.0 | 30 | 0.9557 |
52
+ | 0.9138 | 6.0 | 36 | 0.8362 |
53
+ | 0.8297 | 7.0 | 42 | 0.7370 |
54
+ | 0.7493 | 8.0 | 48 | 0.6858 |
55
+ | 0.7285 | 9.0 | 54 | 0.6761 |
56
+ | 0.6576 | 10.0 | 60 | 0.6179 |
57
+ | 0.6126 | 11.0 | 66 | 0.5748 |
58
+ | 0.57 | 12.0 | 72 | 0.5858 |
59
+ | 0.5453 | 13.0 | 78 | 0.5193 |
60
+ | 0.5309 | 14.0 | 84 | 0.5104 |
61
+ | 0.5394 | 15.0 | 90 | 0.5115 |
62
+ | 0.5024 | 16.0 | 96 | 0.4763 |
63
+ | 0.4642 | 17.0 | 102 | 0.4389 |
64
+ | 0.4478 | 18.0 | 108 | 0.4080 |
65
+ | 0.424 | 19.0 | 114 | 0.3999 |
66
+ | 0.4152 | 20.0 | 120 | 0.3876 |
67
+ | 0.3966 | 21.0 | 126 | 0.3982 |
68
+ | 0.3971 | 22.0 | 132 | 0.3669 |
69
+ | 0.369 | 23.0 | 138 | 0.3579 |
70
+ | 0.3584 | 24.0 | 144 | 0.3336 |
71
+ | 0.3577 | 25.0 | 150 | 0.3271 |
72
+ | 0.3279 | 26.0 | 156 | 0.3005 |
73
+ | 0.315 | 27.0 | 162 | 0.2841 |
74
+ | 0.3104 | 28.0 | 168 | 0.3149 |
75
+ | 0.3129 | 29.0 | 174 | 0.2906 |
76
+ | 0.2906 | 30.0 | 180 | 0.2925 |
77
+ | 0.2778 | 31.0 | 186 | 0.2644 |
78
+ | 0.276 | 32.0 | 192 | 0.2512 |
79
+ | 0.2685 | 33.0 | 198 | 0.2494 |
80
+ | 0.2524 | 34.0 | 204 | 0.2305 |
81
+ | 0.2488 | 35.0 | 210 | 0.2199 |
82
+ | 0.2411 | 36.0 | 216 | 0.2099 |
83
+ | 0.2167 | 37.0 | 222 | 0.2022 |
84
+ | 0.2175 | 38.0 | 228 | 0.1934 |
85
+ | 0.2113 | 39.0 | 234 | 0.1841 |
86
+ | 0.1923 | 40.0 | 240 | 0.1751 |
87
+ | 0.1908 | 41.0 | 246 | 0.1732 |
88
+ | 0.1857 | 42.0 | 252 | 0.1669 |
89
+ | 0.1858 | 43.0 | 258 | 0.1598 |
90
+ | 0.184 | 44.0 | 264 | 0.1600 |
91
+ | 0.1772 | 45.0 | 270 | 0.1519 |
92
+ | 0.1774 | 46.0 | 276 | 0.1533 |
93
+ | 0.1669 | 47.0 | 282 | 0.1490 |
94
+ | 0.1719 | 48.0 | 288 | 0.1454 |
95
+ | 0.1631 | 49.0 | 294 | 0.1447 |
96
+ | 0.1575 | 50.0 | 300 | 0.1435 |
97
 
98
 
99
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b103a0dbe09a82ff9b450dbdf4929fdc609afd639929df124571985170d7e93d
3
  size 31207604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3382b69e49d0bc15a1e3bc46509ee1eb1762c00de4b8752ca63872576a787056
3
  size 31207604
runs/Feb28_19-08-48_3897ec21fae5/events.out.tfevents.1709147328.3897ec21fae5.100515.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:353cb5fe7ab012805145dbb1489c65eecb94e22c708ca4c3a1b717a072d26ec1
3
+ size 29926
tokenizer.json CHANGED
@@ -117,14 +117,14 @@
117
  "10": 18,
118
  "11": 19,
119
  "98": 20,
120
- "12": 21,
121
- "97": 22,
122
- "13": 23,
123
- "96": 24,
124
  "95": 25,
125
  "14": 26,
126
- "94": 27,
127
- "15": 28,
128
  "93": 29,
129
  "16": 30,
130
  "17": 31,
@@ -133,18 +133,18 @@
133
  "18": 34,
134
  "19": 35,
135
  "90": 36,
136
- "20": 37,
137
- "89": 38,
138
- "21": 39,
139
- "88": 40,
140
  "22": 41,
141
  "87": 42,
142
- "86": 43,
143
- "23": 44,
144
  "24": 45,
145
  "85": 46,
146
- "84": 47,
147
- "25": 48,
148
  "26": 49,
149
  "83": 50,
150
  "27": 51,
@@ -155,14 +155,14 @@
155
  "1 0",
156
  "1 1",
157
  "9 8",
158
- "1 2",
159
  "9 7",
160
- "1 3",
161
  "9 6",
 
162
  "9 5",
163
  "1 4",
164
- "9 4",
165
  "1 5",
 
166
  "9 3",
167
  "1 6",
168
  "1 7",
@@ -171,18 +171,18 @@
171
  "1 8",
172
  "1 9",
173
  "9 0",
174
- "2 0",
175
  "8 9",
176
- "2 1",
177
  "8 8",
 
178
  "2 2",
179
  "8 7",
180
- "8 6",
181
  "2 3",
 
182
  "2 4",
183
  "8 5",
184
- "8 4",
185
  "2 5",
 
186
  "2 6",
187
  "8 3",
188
  "2 7",
 
117
  "10": 18,
118
  "11": 19,
119
  "98": 20,
120
+ "97": 21,
121
+ "12": 22,
122
+ "96": 23,
123
+ "13": 24,
124
  "95": 25,
125
  "14": 26,
126
+ "15": 27,
127
+ "94": 28,
128
  "93": 29,
129
  "16": 30,
130
  "17": 31,
 
133
  "18": 34,
134
  "19": 35,
135
  "90": 36,
136
+ "89": 37,
137
+ "20": 38,
138
+ "88": 39,
139
+ "21": 40,
140
  "22": 41,
141
  "87": 42,
142
+ "23": 43,
143
+ "86": 44,
144
  "24": 45,
145
  "85": 46,
146
+ "25": 47,
147
+ "84": 48,
148
  "26": 49,
149
  "83": 50,
150
  "27": 51,
 
155
  "1 0",
156
  "1 1",
157
  "9 8",
 
158
  "9 7",
159
+ "1 2",
160
  "9 6",
161
+ "1 3",
162
  "9 5",
163
  "1 4",
 
164
  "1 5",
165
+ "9 4",
166
  "9 3",
167
  "1 6",
168
  "1 7",
 
171
  "1 8",
172
  "1 9",
173
  "9 0",
 
174
  "8 9",
175
+ "2 0",
176
  "8 8",
177
+ "2 1",
178
  "2 2",
179
  "8 7",
 
180
  "2 3",
181
+ "8 6",
182
  "2 4",
183
  "8 5",
 
184
  "2 5",
185
+ "8 4",
186
  "2 6",
187
  "8 3",
188
  "2 7",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ee85665cc15713b5bd783ba232635c4e5e7bf8fde3048c9b9cdd845325cdd67
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92373650ff57d5cbc6bac5a4d68bf78863a8e67ac3450e8e14ef9c02d0ebeb53
3
  size 4920