Hugging Face's logo

laplasian
/
calculator_model_test

Text2Text Generation
Transformers
TensorBoard
Safetensors
encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
laplasian commited on
Commit
2e9c582
•
1 Parent(s): 9ca2a1a

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_10-20-42_4150c2fa2709/events.out.tfevents.1709547643.4150c2fa2709.151.1 +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: 0.8124
17
 
18
  ## Model description
19
 
@@ -44,46 +44,46 @@ The following hyperparameters were used during training:
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
- | 3.3916 | 1.0 | 6 | 2.7549 |
48
- | 2.4048 | 2.0 | 12 | 1.9876 |
49
- | 1.8591 | 3.0 | 18 | 1.8948 |
50
- | 1.6663 | 4.0 | 24 | 1.6188 |
51
- | 1.586 | 5.0 | 30 | 1.5494 |
52
- | 1.5053 | 6.0 | 36 | 1.6146 |
53
- | 1.5878 | 7.0 | 42 | 1.5655 |
54
- | 1.5183 | 8.0 | 48 | 1.5487 |
55
- | 1.5695 | 9.0 | 54 | 1.5368 |
56
- | 1.5206 | 10.0 | 60 | 1.5189 |
57
- | 1.4748 | 11.0 | 66 | 1.5096 |
58
- | 1.4616 | 12.0 | 72 | 1.4969 |
59
- | 1.4502 | 13.0 | 78 | 1.4454 |
60
- | 1.4039 | 14.0 | 84 | 1.4019 |
61
- | 1.3864 | 15.0 | 90 | 1.3711 |
62
- | 1.3878 | 16.0 | 96 | 1.3687 |
63
- | 1.3034 | 17.0 | 102 | 1.2939 |
64
- | 1.2768 | 18.0 | 108 | 1.3036 |
65
- | 1.2649 | 19.0 | 114 | 1.2028 |
66
- | 1.26 | 20.0 | 120 | 1.1679 |
67
- | 1.198 | 21.0 | 126 | 1.2472 |
68
- | 1.1989 | 22.0 | 132 | 1.2993 |
69
- | 1.2132 | 23.0 | 138 | 1.0975 |
70
- | 1.1436 | 24.0 | 144 | 1.0720 |
71
- | 1.0686 | 25.0 | 150 | 1.1057 |
72
- | 1.0627 | 26.0 | 156 | 1.0181 |
73
- | 1.0 | 27.0 | 162 | 0.9821 |
74
- | 1.0395 | 28.0 | 168 | 0.9878 |
75
- | 0.9847 | 29.0 | 174 | 0.9409 |
76
- | 0.9655 | 30.0 | 180 | 0.9396 |
77
- | 0.9791 | 31.0 | 186 | 0.9019 |
78
- | 0.9318 | 32.0 | 192 | 0.8818 |
79
- | 0.9103 | 33.0 | 198 | 0.8827 |
80
- | 0.9049 | 34.0 | 204 | 0.8853 |
81
- | 0.9553 | 35.0 | 210 | 0.8960 |
82
- | 0.8924 | 36.0 | 216 | 0.8598 |
83
- | 0.9028 | 37.0 | 222 | 0.8312 |
84
- | 0.8601 | 38.0 | 228 | 0.8177 |
85
- | 0.8744 | 39.0 | 234 | 0.8153 |
86
- | 0.8442 | 40.0 | 240 | 0.8124 |
87
 
88
 
89
  ### 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: 0.0824
17
 
18
  ## Model description
19
 
 
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
+ | 2.9085 | 1.0 | 6 | 2.2339 |
48
+ | 1.9955 | 2.0 | 12 | 1.7507 |
49
+ | 1.5891 | 3.0 | 18 | 1.3630 |
50
+ | 1.221 | 4.0 | 24 | 1.0757 |
51
+ | 1.0321 | 5.0 | 30 | 0.9606 |
52
+ | 0.9056 | 6.0 | 36 | 0.8336 |
53
+ | 0.8119 | 7.0 | 42 | 0.7754 |
54
+ | 0.7251 | 8.0 | 48 | 0.7105 |
55
+ | 0.679 | 9.0 | 54 | 0.6689 |
56
+ | 0.6367 | 10.0 | 60 | 0.6193 |
57
+ | 0.5903 | 11.0 | 66 | 0.5498 |
58
+ | 0.5423 | 12.0 | 72 | 0.5078 |
59
+ | 0.5121 | 13.0 | 78 | 0.5079 |
60
+ | 0.4916 | 14.0 | 84 | 0.4614 |
61
+ | 0.4659 | 15.0 | 90 | 0.4271 |
62
+ | 0.4173 | 16.0 | 96 | 0.4071 |
63
+ | 0.3995 | 17.0 | 102 | 0.3885 |
64
+ | 0.3809 | 18.0 | 108 | 0.3586 |
65
+ | 0.3564 | 19.0 | 114 | 0.3231 |
66
+ | 0.3277 | 20.0 | 120 | 0.3317 |
67
+ | 0.3156 | 21.0 | 126 | 0.3146 |
68
+ | 0.3124 | 22.0 | 132 | 0.3063 |
69
+ | 0.2829 | 23.0 | 138 | 0.2604 |
70
+ | 0.2624 | 24.0 | 144 | 0.2385 |
71
+ | 0.2431 | 25.0 | 150 | 0.2421 |
72
+ | 0.23 | 26.0 | 156 | 0.1983 |
73
+ | 0.1995 | 27.0 | 162 | 0.1716 |
74
+ | 0.1857 | 28.0 | 168 | 0.1565 |
75
+ | 0.1654 | 29.0 | 174 | 0.1325 |
76
+ | 0.1477 | 30.0 | 180 | 0.1246 |
77
+ | 0.1489 | 31.0 | 186 | 0.1188 |
78
+ | 0.1352 | 32.0 | 192 | 0.1075 |
79
+ | 0.1232 | 33.0 | 198 | 0.1017 |
80
+ | 0.1205 | 34.0 | 204 | 0.0963 |
81
+ | 0.1125 | 35.0 | 210 | 0.0912 |
82
+ | 0.1149 | 36.0 | 216 | 0.0903 |
83
+ | 0.1081 | 37.0 | 222 | 0.0903 |
84
+ | 0.1069 | 38.0 | 228 | 0.0851 |
85
+ | 0.1046 | 39.0 | 234 | 0.0828 |
86
+ | 0.0996 | 40.0 | 240 | 0.0824 |
87
 
88
 
89
  ### 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 sha256:1316881e46b841dd1dd96b1112a88973a59bcc977ade6cb8a0b25e5e14c81baf
3
- size 31205552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:716d0e4c438984cf9fea3426de4859717ce10523a52ecf70917298bff07b5a65
3
+ size 31207604
runs/Mar04_10-20-42_4150c2fa2709/events.out.tfevents.1709547643.4150c2fa2709.151.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eab08d7befd138c78327bc3fe299aeb13650df35f56517211ea807e75a9e77a6
3
+ size 27997
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
- "19": 34,
134
  "90": 35,
135
- "20": 36,
136
- "89": 37,
137
- "21": 38,
138
- "88": 39,
139
- "22": 40,
140
  "87": 41,
141
- "23": 42,
142
- "86": 43,
143
- "85": 44,
144
- "24": 45,
145
- "25": 46,
146
- "84": 47,
147
- "26": 48,
148
  "83": 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",
@@ -166,24 +167,24 @@
166
  "1 6",
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
- "2 2",
178
  "8 7",
 
179
  "2 3",
180
  "8 6",
181
  "8 5",
182
  "2 4",
183
  "2 5",
184
  "8 4",
185
- "2 6",
186
  "8 3",
 
187
  "2 7",
188
  "8 2"
189
  ]
 
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",
187
+ "2 6",
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 sha256:0f8ecf8c900da182f6d948b82c28f1c64da66e2e05376f01450376eee7382376
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdaf4cbde81c5fb1296780d605b465e1ad53cb014fa08dae4ab07a15be520994
3
  size 5112