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
d847a74
•
1 Parent(s): df9d7c7

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_19-58-25_3897ec21fae5/events.out.tfevents.1709150306.3897ec21fae5.112417.0 +3 -0
  5. tokenizer.json +36 -37
  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: 0.1435
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
- | 3.0221 | 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
 
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: 0.5850
17
 
18
  ## Model description
19
 
 
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
+ | 3.396 | 1.0 | 6 | 2.7406 |
48
+ | 2.3939 | 2.0 | 12 | 1.9948 |
49
+ | 1.7939 | 3.0 | 18 | 1.6558 |
50
+ | 1.5985 | 4.0 | 24 | 1.6015 |
51
+ | 1.6024 | 5.0 | 30 | 1.5540 |
52
+ | 1.5383 | 6.0 | 36 | 1.5356 |
53
+ | 1.4729 | 7.0 | 42 | 1.5437 |
54
+ | 1.4981 | 8.0 | 48 | 1.4425 |
55
+ | 1.3622 | 9.0 | 54 | 1.4418 |
56
+ | 1.3585 | 10.0 | 60 | 1.3501 |
57
+ | 1.2883 | 11.0 | 66 | 1.2932 |
58
+ | 1.2361 | 12.0 | 72 | 1.3210 |
59
+ | 1.2274 | 13.0 | 78 | 1.2883 |
60
+ | 1.2667 | 14.0 | 84 | 1.2169 |
61
+ | 1.1679 | 15.0 | 90 | 1.1638 |
62
+ | 1.1237 | 16.0 | 96 | 1.1617 |
63
+ | 1.144 | 17.0 | 102 | 1.0919 |
64
+ | 1.0771 | 18.0 | 108 | 1.0928 |
65
+ | 1.059 | 19.0 | 114 | 1.0184 |
66
+ | 1.0024 | 20.0 | 120 | 0.9676 |
67
+ | 0.9949 | 21.0 | 126 | 0.9555 |
68
+ | 0.986 | 22.0 | 132 | 1.0286 |
69
+ | 1.0278 | 23.0 | 138 | 0.9337 |
70
+ | 0.9413 | 24.0 | 144 | 0.9162 |
71
+ | 0.912 | 25.0 | 150 | 0.9396 |
72
+ | 0.9621 | 26.0 | 156 | 0.8786 |
73
+ | 0.9102 | 27.0 | 162 | 0.8947 |
74
+ | 0.9384 | 28.0 | 168 | 0.8820 |
75
+ | 0.868 | 29.0 | 174 | 0.8468 |
76
+ | 0.8512 | 30.0 | 180 | 0.8478 |
77
+ | 0.8302 | 31.0 | 186 | 0.8099 |
78
+ | 0.8327 | 32.0 | 192 | 0.7622 |
79
+ | 0.8193 | 33.0 | 198 | 0.7596 |
80
+ | 0.7834 | 34.0 | 204 | 0.7329 |
81
+ | 0.7608 | 35.0 | 210 | 0.7229 |
82
+ | 0.7686 | 36.0 | 216 | 0.7257 |
83
+ | 0.7262 | 37.0 | 222 | 0.6940 |
84
+ | 0.7342 | 38.0 | 228 | 0.7117 |
85
+ | 0.7209 | 39.0 | 234 | 0.6646 |
86
+ | 0.7099 | 40.0 | 240 | 0.6530 |
87
+ | 0.6908 | 41.0 | 246 | 0.6397 |
88
+ | 0.6895 | 42.0 | 252 | 0.6356 |
89
+ | 0.6761 | 43.0 | 258 | 0.6202 |
90
+ | 0.668 | 44.0 | 264 | 0.6174 |
91
+ | 0.6735 | 45.0 | 270 | 0.6074 |
92
+ | 0.6502 | 46.0 | 276 | 0.6019 |
93
+ | 0.6427 | 47.0 | 282 | 0.5953 |
94
+ | 0.6326 | 48.0 | 288 | 0.5904 |
95
+ | 0.6467 | 49.0 | 294 | 0.5872 |
96
+ | 0.6307 | 50.0 | 300 | 0.5850 |
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": 53
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": 53
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": 52
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": 52
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 sha256:3382b69e49d0bc15a1e3bc46509ee1eb1762c00de4b8752ca63872576a787056
3
- size 31207604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6dd0c10a93bc861dfdb78a028c4f50ca6a5ec612bb363bbe7288196804c2809
3
+ size 31205552
runs/Feb28_19-58-25_3897ec21fae5/events.out.tfevents.1709150306.3897ec21fae5.112417.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc68afa9ce9448c7ac50be9b177c13e7e3ae130988291c7d10994b33f57c8bd1
3
+ size 29926
tokenizer.json CHANGED
@@ -112,73 +112,72 @@
112
  "7": 13,
113
  "8": 14,
114
  "9": 15,
115
- "=": 16,
116
  "99": 17,
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,
131
- "92": 32,
132
- "91": 33,
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,
151
- "82": 52
152
  },
153
  "merges": [
154
- "9 9",
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",
169
  "9 2",
170
  "9 1",
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",
 
112
  "7": 13,
113
  "8": 14,
114
  "9": 15,
115
+ "10": 16,
116
  "99": 17,
117
+ "11": 18,
118
+ "98": 19,
119
+ "12": 20,
120
  "97": 21,
121
+ "13": 22,
122
  "96": 23,
123
+ "14": 24,
124
  "95": 25,
125
+ "94": 26,
126
  "15": 27,
127
+ "16": 28,
128
  "93": 29,
129
+ "17": 30,
130
+ "92": 31,
131
+ "91": 32,
132
+ "18": 33,
133
+ "19": 34,
134
+ "90": 35,
135
+ "20": 36,
136
  "89": 37,
137
+ "21": 38,
138
  "88": 39,
139
+ "87": 40,
140
  "22": 41,
141
+ "86": 42,
142
  "23": 43,
143
+ "24": 44,
144
+ "85": 45,
145
+ "25": 46,
146
+ "84": 47,
147
+ "26": 48,
148
+ "83": 49,
149
+ "27": 50,
150
+ "82": 51
 
151
  },
152
  "merges": [
 
153
  "1 0",
154
+ "9 9",
155
  "1 1",
156
  "9 8",
 
157
  "1 2",
158
+ "9 7",
159
  "1 3",
160
+ "9 6",
161
  "1 4",
162
+ "9 5",
163
  "9 4",
164
+ "1 5",
165
  "1 6",
166
+ "9 3",
167
  "1 7",
168
  "9 2",
169
  "9 1",
170
  "1 8",
171
  "1 9",
172
  "9 0",
 
173
  "2 0",
174
+ "8 9",
175
  "2 1",
176
+ "8 8",
177
  "8 7",
178
+ "2 2",
179
  "8 6",
180
+ "2 3",
181
  "2 4",
182
  "8 5",
183
  "2 5",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92373650ff57d5cbc6bac5a4d68bf78863a8e67ac3450e8e14ef9c02d0ebeb53
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4842f4a0fd629ccc59cab7f2313be44d4264afb1d3e03281108215f6061469f3
3
  size 4920