Hugging Face's logo

gum123
/
calculator_model_test

Text2Text Generation
Transformers
TensorBoard
Safetensors
encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
gum123 commited on
Commit
d649c0a
•
1 Parent(s): bca0a58

End of training

Browse files
Files changed (6) hide show
  1. README.md +41 -41
  2. config.json +2 -2
  3. model.safetensors +2 -2
  4. runs/Mar04_10-20-52_987e769f7287/events.out.tfevents.1709547652.987e769f7287.502.1 +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: 0.5972
17
 
18
  ## Model description
19
 
@@ -45,46 +45,46 @@ The following hyperparameters were used during training:
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | 3.7046 | 1.0 | 6 | 3.1566 |
49
- | 2.7296 | 2.0 | 12 | 2.2354 |
50
- | 1.97 | 3.0 | 18 | 1.7402 |
51
- | 1.6522 | 4.0 | 24 | 1.6050 |
52
- | 1.5915 | 5.0 | 30 | 1.5117 |
53
- | 1.497 | 6.0 | 36 | 1.4859 |
54
- | 1.4994 | 7.0 | 42 | 1.4515 |
55
- | 1.4372 | 8.0 | 48 | 1.4207 |
56
- | 1.4099 | 9.0 | 54 | 1.3809 |
57
- | 1.37 | 10.0 | 60 | 1.3981 |
58
- | 1.3361 | 11.0 | 66 | 1.2905 |
59
- | 1.2942 | 12.0 | 72 | 1.2986 |
60
- | 1.2437 | 13.0 | 78 | 1.2145 |
61
- | 1.18 | 14.0 | 84 | 1.1069 |
62
- | 1.0947 | 15.0 | 90 | 1.0619 |
63
- | 1.0435 | 16.0 | 96 | 0.9873 |
64
- | 0.9961 | 17.0 | 102 | 0.9470 |
65
- | 0.9408 | 18.0 | 108 | 0.9126 |
66
- | 0.9119 | 19.0 | 114 | 0.9238 |
67
- | 0.9158 | 20.0 | 120 | 0.8937 |
68
- | 0.8981 | 21.0 | 126 | 0.8486 |
69
- | 0.862 | 22.0 | 132 | 0.8756 |
70
- | 0.8577 | 23.0 | 138 | 0.8344 |
71
- | 0.8243 | 24.0 | 144 | 0.8168 |
72
- | 0.8018 | 25.0 | 150 | 0.7711 |
73
- | 0.7861 | 26.0 | 156 | 0.7986 |
74
- | 0.7838 | 27.0 | 162 | 0.7765 |
75
- | 0.7753 | 28.0 | 168 | 0.7504 |
76
- | 0.7602 | 29.0 | 174 | 0.7205 |
77
- | 0.7215 | 30.0 | 180 | 0.7216 |
78
- | 0.7148 | 31.0 | 186 | 0.6973 |
79
- | 0.7082 | 32.0 | 192 | 0.6753 |
80
- | 0.7017 | 33.0 | 198 | 0.6480 |
81
- | 0.6784 | 34.0 | 204 | 0.6394 |
82
- | 0.6702 | 35.0 | 210 | 0.6333 |
83
- | 0.6663 | 36.0 | 216 | 0.6221 |
84
- | 0.6415 | 37.0 | 222 | 0.6133 |
85
- | 0.6377 | 38.0 | 228 | 0.6065 |
86
- | 0.6291 | 39.0 | 234 | 0.6049 |
87
- | 0.6288 | 40.0 | 240 | 0.5972 |
88
 
89
 
90
  ### 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: 0.1417
17
 
18
  ## Model description
19
 
 
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
+ | 2.9571 | 1.0 | 6 | 2.2956 |
49
+ | 2.0465 | 2.0 | 12 | 1.7293 |
50
+ | 1.5363 | 3.0 | 18 | 1.2901 |
51
+ | 1.2139 | 4.0 | 24 | 1.0866 |
52
+ | 1.0369 | 5.0 | 30 | 0.9429 |
53
+ | 0.9144 | 6.0 | 36 | 0.8284 |
54
+ | 0.8202 | 7.0 | 42 | 0.7701 |
55
+ | 0.7591 | 8.0 | 48 | 0.7184 |
56
+ | 0.7075 | 9.0 | 54 | 0.6474 |
57
+ | 0.6481 | 10.0 | 60 | 0.6074 |
58
+ | 0.611 | 11.0 | 66 | 0.5786 |
59
+ | 0.5714 | 12.0 | 72 | 0.5192 |
60
+ | 0.5412 | 13.0 | 78 | 0.4924 |
61
+ | 0.5092 | 14.0 | 84 | 0.5077 |
62
+ | 0.5118 | 15.0 | 90 | 0.4989 |
63
+ | 0.4982 | 16.0 | 96 | 0.4349 |
64
+ | 0.4512 | 17.0 | 102 | 0.4090 |
65
+ | 0.4176 | 18.0 | 108 | 0.3868 |
66
+ | 0.395 | 19.0 | 114 | 0.3586 |
67
+ | 0.3754 | 20.0 | 120 | 0.3666 |
68
+ | 0.3561 | 21.0 | 126 | 0.3182 |
69
+ | 0.3284 | 22.0 | 132 | 0.2906 |
70
+ | 0.3123 | 23.0 | 138 | 0.2981 |
71
+ | 0.3026 | 24.0 | 144 | 0.2740 |
72
+ | 0.2809 | 25.0 | 150 | 0.2448 |
73
+ | 0.2669 | 26.0 | 156 | 0.2321 |
74
+ | 0.257 | 27.0 | 162 | 0.2179 |
75
+ | 0.2349 | 28.0 | 168 | 0.2110 |
76
+ | 0.2205 | 29.0 | 174 | 0.1969 |
77
+ | 0.2142 | 30.0 | 180 | 0.1894 |
78
+ | 0.2116 | 31.0 | 186 | 0.1819 |
79
+ | 0.195 | 32.0 | 192 | 0.1747 |
80
+ | 0.1884 | 33.0 | 198 | 0.1668 |
81
+ | 0.1819 | 34.0 | 204 | 0.1615 |
82
+ | 0.1741 | 35.0 | 210 | 0.1541 |
83
+ | 0.172 | 36.0 | 216 | 0.1524 |
84
+ | 0.1726 | 37.0 | 222 | 0.1471 |
85
+ | 0.1555 | 38.0 | 228 | 0.1458 |
86
+ | 0.1606 | 39.0 | 234 | 0.1430 |
87
+ | 0.1604 | 40.0 | 240 | 0.1417 |
88
 
89
 
90
  ### 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 sha256:9eac9568032de2353e7afc4f6f8f5d2e1848d85b29492cda36c36b04f968e5e8
3
- size 31205552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20adbf651b3249c3a50b9a2faa1eb49f74f3190f9ebed2ea62b13f2ddd8ecad3
3
+ size 31207604
runs/Mar04_10-20-52_987e769f7287/events.out.tfevents.1709547652.987e769f7287.502.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ead38571a6e417f1e74a464fe96259523464eaa883a883ab43d325d734dfad4
3
+ size 27996
tokenizer.json CHANGED
@@ -112,48 +112,49 @@
112
  "7": 13,
113
  "8": 14,
114
  "9": 15,
115
- "99": 16,
116
  "10": 17,
117
- "11": 18,
118
  "98": 19,
119
- "97": 20,
120
- "12": 21,
121
- "96": 22,
122
- "13": 23,
123
- "95": 24,
124
- "14": 25,
125
- "94": 26,
126
- "15": 27,
127
- "93": 28,
128
- "16": 29,
129
- "17": 30,
130
- "92": 31,
131
- "91": 32,
132
  "18": 33,
133
- "90": 34,
134
- "19": 35,
135
- "89": 36,
136
  "20": 37,
137
- "21": 38,
138
- "88": 39,
139
- "22": 40,
140
  "87": 41,
141
- "86": 42,
142
  "23": 43,
143
- "24": 44,
144
  "85": 45,
145
- "25": 46,
146
- "84": 47,
147
- "83": 48,
148
- "26": 49,
149
- "27": 50,
150
- "82": 51
 
151
  },
152
  "merges": [
153
- "9 9",
154
  "1 0",
155
- "1 1",
156
  "9 8",
 
157
  "9 7",
158
  "1 2",
159
  "9 6",
@@ -166,20 +167,20 @@
166
  "1 6",
167
  "1 7",
168
  "9 2",
169
- "9 1",
170
  "1 8",
 
171
  "9 0",
172
  "1 9",
173
- "8 9",
174
  "2 0",
 
175
  "2 1",
176
  "8 8",
177
- "2 2",
178
  "8 7",
179
- "8 6",
180
  "2 3",
181
- "2 4",
182
  "8 5",
 
183
  "2 5",
184
  "8 4",
185
  "8 3",
 
112
  "7": 13,
113
  "8": 14,
114
  "9": 15,
115
+ "=": 16,
116
  "10": 17,
117
+ "99": 18,
118
  "98": 19,
119
+ "11": 20,
120
+ "97": 21,
121
+ "12": 22,
122
+ "96": 23,
123
+ "13": 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
  "18": 33,
133
+ "91": 34,
134
+ "90": 35,
135
+ "19": 36,
136
  "20": 37,
137
+ "89": 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
+ "25": 47,
147
+ "84": 48,
148
+ "83": 49,
149
+ "26": 50,
150
+ "27": 51,
151
+ "82": 52
152
  },
153
  "merges": [
 
154
  "1 0",
155
+ "9 9",
156
  "9 8",
157
+ "1 1",
158
  "9 7",
159
  "1 2",
160
  "9 6",
 
167
  "1 6",
168
  "1 7",
169
  "9 2",
 
170
  "1 8",
171
+ "9 1",
172
  "9 0",
173
  "1 9",
 
174
  "2 0",
175
+ "8 9",
176
  "2 1",
177
  "8 8",
 
178
  "8 7",
179
+ "2 2",
180
  "2 3",
181
+ "8 6",
182
  "8 5",
183
+ "2 4",
184
  "2 5",
185
  "8 4",
186
  "8 3",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fedc787b6585fe2f23741e21340cab6af289ea7ab373c0de387fd4de169db266
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4845741ab1a3479bc072df5105c0b7150f8aee2c76da05c97488950d259a6c8a
3
  size 5112