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
41ae318
•
1 Parent(s): 1c83c91

End of training

Browse files
Files changed (6) hide show
  1. README.md +51 -51
  2. config.json +2 -2
  3. model.safetensors +2 -2
  4. runs/Feb28_18-32-24_3897ec21fae5/events.out.tfevents.1709145145.3897ec21fae5.91861.0 +3 -0
  5. tokenizer.json +37 -36
  6. 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: 1.0813
17
 
18
  ## Model description
19
 
@@ -44,56 +44,56 @@ The following hyperparameters were used during training:
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
- | 3.8078 | 1.0 | 6 | 3.6115 |
48
- | 3.5402 | 2.0 | 12 | 3.4403 |
49
- | 3.3905 | 3.0 | 18 | 3.3023 |
50
- | 3.2601 | 4.0 | 24 | 3.1757 |
51
- | 3.1298 | 5.0 | 30 | 3.0465 |
52
- | 2.9919 | 6.0 | 36 | 2.9159 |
53
- | 2.8647 | 7.0 | 42 | 2.7868 |
54
- | 2.7503 | 8.0 | 48 | 2.6616 |
55
- | 2.6207 | 9.0 | 54 | 2.5386 |
56
- | 2.4973 | 10.0 | 60 | 2.4256 |
57
- | 2.3944 | 11.0 | 66 | 2.3203 |
58
- | 2.2924 | 12.0 | 72 | 2.2263 |
59
- | 2.2061 | 13.0 | 78 | 2.1487 |
60
- | 2.117 | 14.0 | 84 | 2.0624 |
61
- | 2.044 | 15.0 | 90 | 1.9910 |
62
- | 1.9718 | 16.0 | 96 | 1.9239 |
63
- | 1.9093 | 17.0 | 102 | 1.8786 |
64
- | 1.8542 | 18.0 | 108 | 1.8129 |
65
- | 1.8085 | 19.0 | 114 | 1.7692 |
66
- | 1.7653 | 20.0 | 120 | 1.7316 |
67
- | 1.7103 | 21.0 | 126 | 1.6790 |
68
- | 1.6757 | 22.0 | 132 | 1.6199 |
69
- | 1.6089 | 23.0 | 138 | 1.5592 |
70
- | 1.5391 | 24.0 | 144 | 1.5067 |
71
- | 1.4987 | 25.0 | 150 | 1.4640 |
72
- | 1.4535 | 26.0 | 156 | 1.4296 |
73
- | 1.4285 | 27.0 | 162 | 1.3858 |
74
- | 1.3828 | 28.0 | 168 | 1.3493 |
75
- | 1.3468 | 29.0 | 174 | 1.3184 |
76
- | 1.3265 | 30.0 | 180 | 1.2910 |
77
- | 1.2953 | 31.0 | 186 | 1.2636 |
78
- | 1.2804 | 32.0 | 192 | 1.2402 |
79
- | 1.2522 | 33.0 | 198 | 1.2223 |
80
- | 1.2375 | 34.0 | 204 | 1.2094 |
81
- | 1.219 | 35.0 | 210 | 1.1914 |
82
- | 1.2133 | 36.0 | 216 | 1.1762 |
83
- | 1.19 | 37.0 | 222 | 1.1606 |
84
- | 1.1839 | 38.0 | 228 | 1.1532 |
85
- | 1.1737 | 39.0 | 234 | 1.1380 |
86
- | 1.1635 | 40.0 | 240 | 1.1267 |
87
- | 1.1496 | 41.0 | 246 | 1.1219 |
88
- | 1.1514 | 42.0 | 252 | 1.1104 |
89
- | 1.1285 | 43.0 | 258 | 1.1056 |
90
- | 1.1367 | 44.0 | 264 | 1.0976 |
91
- | 1.1232 | 45.0 | 270 | 1.0949 |
92
- | 1.1185 | 46.0 | 276 | 1.0896 |
93
- | 1.1155 | 47.0 | 282 | 1.0836 |
94
- | 1.1053 | 48.0 | 288 | 1.0834 |
95
- | 1.1071 | 49.0 | 294 | 1.0823 |
96
- | 1.1132 | 50.0 | 300 | 1.0813 |
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: 0.8456
17
 
18
  ## Model description
19
 
 
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
config.json CHANGED
@@ -78,7 +78,7 @@
78
  "typical_p": 1.0,
79
  "use_bfloat16": false,
80
  "use_cache": true,
81
- "vocab_size": 52
82
  },
83
  "decoder_start_token_id": 2,
84
  "encoder": {
@@ -157,7 +157,7 @@
157
  "typical_p": 1.0,
158
  "use_bfloat16": false,
159
  "use_cache": true,
160
- "vocab_size": 52
161
  },
162
  "eos_token_id": 0,
163
  "is_encoder_decoder": true,
 
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": {
 
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,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da4f203a50465bbaf1babcff0cb9459252480321b46aa69609402a6d6f466c22
3
- size 31205552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b103a0dbe09a82ff9b450dbdf4929fdc609afd639929df124571985170d7e93d
3
+ size 31207604
runs/Feb28_18-32-24_3897ec21fae5/events.out.tfevents.1709145145.3897ec21fae5.91861.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:364def6cd24d7f154ab304ac352dcb5e71382b3d87842e0e684fd36a16f2c138
3
+ size 29928
tokenizer.json CHANGED
@@ -112,78 +112,79 @@
112
  "7": 13,
113
  "8": 14,
114
  "9": 15,
115
- "10": 16,
116
  "99": 17,
117
- "98": 18,
118
  "11": 19,
119
- "97": 20,
120
  "12": 21,
121
- "96": 22,
122
  "13": 23,
123
- "95": 24,
124
- "14": 25,
125
- "15": 26,
126
  "94": 27,
127
- "93": 28,
128
- "16": 29,
129
- "17": 30,
130
- "92": 31,
131
- "18": 32,
132
  "91": 33,
133
- "90": 34,
134
  "19": 35,
135
- "20": 36,
136
- "89": 37,
137
- "21": 38,
138
- "88": 39,
139
- "87": 40,
140
  "22": 41,
141
- "23": 42,
142
  "86": 43,
143
- "85": 44,
144
  "24": 45,
145
- "25": 46,
146
  "84": 47,
147
- "83": 48,
148
  "26": 49,
149
- "27": 50,
150
- "82": 51
 
151
  },
152
  "merges": [
153
- "1 0",
154
  "9 9",
155
- "9 8",
156
  "1 1",
157
- "9 7",
158
  "1 2",
159
- "9 6",
160
  "1 3",
 
161
  "9 5",
162
  "1 4",
163
- "1 5",
164
  "9 4",
 
165
  "9 3",
166
  "1 6",
167
  "1 7",
168
  "9 2",
169
- "1 8",
170
  "9 1",
171
- "9 0",
172
  "1 9",
 
173
  "2 0",
174
  "8 9",
175
  "2 1",
176
  "8 8",
177
- "8 7",
178
  "2 2",
179
- "2 3",
180
  "8 6",
181
- "8 5",
182
  "2 4",
183
- "2 5",
184
  "8 4",
185
- "8 3",
186
  "2 6",
 
187
  "2 7",
188
  "8 2"
189
  ]
 
112
  "7": 13,
113
  "8": 14,
114
  "9": 15,
115
+ "=": 16,
116
  "99": 17,
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,
131
+ "92": 32,
132
  "91": 33,
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,
151
+ "82": 52
152
  },
153
  "merges": [
 
154
  "9 9",
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",
169
  "9 2",
 
170
  "9 1",
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",
189
  "8 2"
190
  ]
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d67f255dd0132ad0e26dff40d45f3b9dccbb9a1d04a4e4d270f7a3e6fa02c0ec
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ee85665cc15713b5bd783ba232635c4e5e7bf8fde3048c9b9cdd845325cdd67
3
  size 4920