Hugging Face's logo

FrogInTheFog
/
calculator_model_test

Text2Text Generation
Transformers
TensorBoard
Safetensors
encoder-decoder
Generated from Trainer
Model card Files Metrics Community
FrogInTheFog commited on
Commit
af68764
·
verified ·
1 Parent(s): ffbaf2a

End of training

Browse files
Files changed (6) hide show
  1. README.md +42 -42
  2. config.json +2 -2
  3. model.safetensors +2 -2
  4. runs/Mar16_12-59-48_83faed59bb9a/events.out.tfevents.1710593988.83faed59bb9a.5192.0 +3 -0
  5. tokenizer.json +25 -23
  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: 0.1669
17
 
18
  ## Model description
19
 
@@ -44,51 +44,51 @@ The following hyperparameters were used during training:
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
- | 2.9295 | 1.0 | 6 | 2.2361 |
48
- | 2.0194 | 2.0 | 12 | 1.7202 |
49
- | 1.5748 | 3.0 | 18 | 1.3398 |
50
- | 1.2632 | 4.0 | 24 | 1.1425 |
51
- | 1.0983 | 5.0 | 30 | 0.9739 |
52
- | 0.9349 | 6.0 | 36 | 0.8281 |
53
- | 0.822 | 7.0 | 42 | 0.8311 |
54
- | 0.7876 | 8.0 | 48 | 0.7384 |
55
- | 0.7133 | 9.0 | 54 | 0.6575 |
56
- | 0.6574 | 10.0 | 60 | 0.6079 |
57
- | 0.5991 | 11.0 | 66 | 0.5648 |
58
- | 0.581 | 12.0 | 72 | 0.5233 |
59
- | 0.5475 | 13.0 | 78 | 0.5250 |
60
- | 0.5322 | 14.0 | 84 | 0.4741 |
61
- | 0.4975 | 15.0 | 90 | 0.4556 |
62
- | 0.4775 | 16.0 | 96 | 0.4322 |
63
- | 0.4436 | 17.0 | 102 | 0.4330 |
64
- | 0.4374 | 18.0 | 108 | 0.4130 |
65
- | 0.4231 | 19.0 | 114 | 0.3923 |
66
- | 0.4003 | 20.0 | 120 | 0.3696 |
67
- | 0.3734 | 21.0 | 126 | 0.3544 |
68
- | 0.3703 | 22.0 | 132 | 0.3490 |
69
- | 0.3603 | 23.0 | 138 | 0.3219 |
70
- | 0.3442 | 24.0 | 144 | 0.3091 |
71
- | 0.3151 | 25.0 | 150 | 0.2807 |
72
- | 0.2983 | 26.0 | 156 | 0.2681 |
73
- | 0.2833 | 27.0 | 162 | 0.2545 |
74
- | 0.2679 | 28.0 | 168 | 0.2419 |
75
- | 0.2625 | 29.0 | 174 | 0.2267 |
76
- | 0.2511 | 30.0 | 180 | 0.2158 |
77
- | 0.242 | 31.0 | 186 | 0.2167 |
78
- | 0.2227 | 32.0 | 192 | 0.2067 |
79
- | 0.2249 | 33.0 | 198 | 0.1975 |
80
- | 0.2198 | 34.0 | 204 | 0.1897 |
81
- | 0.2049 | 35.0 | 210 | 0.1827 |
82
- | 0.2019 | 36.0 | 216 | 0.1774 |
83
- | 0.2019 | 37.0 | 222 | 0.1768 |
84
- | 0.1874 | 38.0 | 228 | 0.1701 |
85
- | 0.1852 | 39.0 | 234 | 0.1684 |
86
- | 0.1875 | 40.0 | 240 | 0.1669 |
87
 
88
 
89
  ### Framework versions
90
 
91
  - Transformers 4.39.0.dev0
92
- - Pytorch 2.1.0+cu121
93
  - Datasets 2.18.0
94
  - Tokenizers 0.15.2
 
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: 0.0886
17
 
18
  ## Model description
19
 
 
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
+ | 2.9371 | 1.0 | 6 | 2.2809 |
48
+ | 2.0329 | 2.0 | 12 | 1.7417 |
49
+ | 1.5558 | 3.0 | 18 | 1.3281 |
50
+ | 1.2296 | 4.0 | 24 | 1.1153 |
51
+ | 1.0568 | 5.0 | 30 | 0.9804 |
52
+ | 0.935 | 6.0 | 36 | 0.8776 |
53
+ | 0.8432 | 7.0 | 42 | 0.7807 |
54
+ | 0.7598 | 8.0 | 48 | 0.7081 |
55
+ | 0.6977 | 9.0 | 54 | 0.6922 |
56
+ | 0.6587 | 10.0 | 60 | 0.6535 |
57
+ | 0.6083 | 11.0 | 66 | 0.5866 |
58
+ | 0.5913 | 12.0 | 72 | 0.5483 |
59
+ | 0.5361 | 13.0 | 78 | 0.4847 |
60
+ | 0.4944 | 14.0 | 84 | 0.4919 |
61
+ | 0.4768 | 15.0 | 90 | 0.4696 |
62
+ | 0.4375 | 16.0 | 96 | 0.4223 |
63
+ | 0.4205 | 17.0 | 102 | 0.3673 |
64
+ | 0.379 | 18.0 | 108 | 0.3210 |
65
+ | 0.3334 | 19.0 | 114 | 0.2762 |
66
+ | 0.3065 | 20.0 | 120 | 0.2556 |
67
+ | 0.2759 | 21.0 | 126 | 0.2456 |
68
+ | 0.2589 | 22.0 | 132 | 0.2186 |
69
+ | 0.2374 | 23.0 | 138 | 0.2009 |
70
+ | 0.2248 | 24.0 | 144 | 0.1943 |
71
+ | 0.2182 | 25.0 | 150 | 0.1972 |
72
+ | 0.2181 | 26.0 | 156 | 0.1695 |
73
+ | 0.1999 | 27.0 | 162 | 0.1829 |
74
+ | 0.2048 | 28.0 | 168 | 0.1786 |
75
+ | 0.1865 | 29.0 | 174 | 0.1371 |
76
+ | 0.1667 | 30.0 | 180 | 0.1323 |
77
+ | 0.161 | 31.0 | 186 | 0.1301 |
78
+ | 0.1442 | 32.0 | 192 | 0.1162 |
79
+ | 0.1365 | 33.0 | 198 | 0.1111 |
80
+ | 0.1298 | 34.0 | 204 | 0.1054 |
81
+ | 0.1295 | 35.0 | 210 | 0.1001 |
82
+ | 0.1223 | 36.0 | 216 | 0.0974 |
83
+ | 0.1222 | 37.0 | 222 | 0.0939 |
84
+ | 0.1227 | 38.0 | 228 | 0.0921 |
85
+ | 0.1198 | 39.0 | 234 | 0.0895 |
86
+ | 0.1139 | 40.0 | 240 | 0.0886 |
87
 
88
 
89
  ### Framework versions
90
 
91
  - Transformers 4.39.0.dev0
92
+ - Pytorch 2.2.1+cu121
93
  - Datasets 2.18.0
94
  - Tokenizers 0.15.2
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 sha256:62b34c6d0d83f290d5bf53a10d4db30cdb72c20b2c37734f085fe798196f91bc
3
- size 31205552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:036a0dca403e01d5994de5b8ddacb9ff4cc0b1b9c088e5891d2475e994ab27df
3
+ size 31207604
runs/Mar16_12-59-48_83faed59bb9a/events.out.tfevents.1710593988.83faed59bb9a.5192.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f00e750b1cd8d5413dffa722c9c2a1b3ae433eb1cf4f07c24b7ac53a48f1d70
3
+ size 28002
tokenizer.json CHANGED
@@ -113,78 +113,80 @@
113
  "8": 14,
114
  "9": 15,
115
  "=": 16,
116
- "99": 17,
117
- "10": 18,
118
- "98": 19,
119
- "11": 20,
120
  "97": 21,
121
  "12": 22,
122
  "13": 23,
123
  "96": 24,
124
  "14": 25,
125
  "95": 26,
126
- "15": 27,
127
- "94": 28,
128
  "93": 29,
129
  "16": 30,
130
- "17": 31,
131
- "92": 32,
132
  "18": 33,
133
  "91": 34,
134
- "19": 35,
135
- "90": 36,
136
  "89": 37,
137
  "20": 38,
138
  "21": 39,
139
  "88": 40,
140
  "87": 41,
141
  "22": 42,
142
- "23": 43,
143
- "86": 44,
144
  "85": 45,
145
  "24": 46,
146
- "84": 47,
147
- "25": 48,
148
  "26": 49,
149
  "83": 50,
150
- "27": 51
 
151
  },
152
  "merges": [
153
- "9 9",
154
  "1 0",
155
- "9 8",
156
  "1 1",
 
157
  "9 7",
158
  "1 2",
159
  "1 3",
160
  "9 6",
161
  "1 4",
162
  "9 5",
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
- "1 9",
172
  "9 0",
 
173
  "8 9",
174
  "2 0",
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
- "8 4",
184
  "2 5",
 
185
  "2 6",
186
  "8 3",
187
- "2 7"
 
188
  ]
189
  }
190
  }
 
113
  "8": 14,
114
  "9": 15,
115
  "=": 16,
116
+ "10": 17,
117
+ "99": 18,
118
+ "11": 19,
119
+ "98": 20,
120
  "97": 21,
121
  "12": 22,
122
  "13": 23,
123
  "96": 24,
124
  "14": 25,
125
  "95": 26,
126
+ "94": 27,
127
+ "15": 28,
128
  "93": 29,
129
  "16": 30,
130
+ "92": 31,
131
+ "17": 32,
132
  "18": 33,
133
  "91": 34,
134
+ "90": 35,
135
+ "19": 36,
136
  "89": 37,
137
  "20": 38,
138
  "21": 39,
139
  "88": 40,
140
  "87": 41,
141
  "22": 42,
142
+ "86": 43,
143
+ "23": 44,
144
  "85": 45,
145
  "24": 46,
146
+ "25": 47,
147
+ "84": 48,
148
  "26": 49,
149
  "83": 50,
150
+ "27": 51,
151
+ "82": 52
152
  },
153
  "merges": [
 
154
  "1 0",
155
+ "9 9",
156
  "1 1",
157
+ "9 8",
158
  "9 7",
159
  "1 2",
160
  "1 3",
161
  "9 6",
162
  "1 4",
163
  "9 5",
 
164
  "9 4",
165
+ "1 5",
166
  "9 3",
167
  "1 6",
 
168
  "9 2",
169
+ "1 7",
170
  "1 8",
171
  "9 1",
 
172
  "9 0",
173
+ "1 9",
174
  "8 9",
175
  "2 0",
176
  "2 1",
177
  "8 8",
178
  "8 7",
179
  "2 2",
 
180
  "8 6",
181
+ "2 3",
182
  "8 5",
183
  "2 4",
 
184
  "2 5",
185
+ "8 4",
186
  "2 6",
187
  "8 3",
188
+ "2 7",
189
+ "8 2"
190
  ]
191
  }
192
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ee497ef9b8eebcdab0ca76dc0a587a912a428b75caf3ef0a83430ce1408f050
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:845a264c5883bb341f7bc3050bf1b8f5934599fbd3443492f28c880f5f344157
3
  size 5112