Hugging Face's logo

Marcin1304
/
calculator_model_test

Text2Text Generation
Transformers
TensorBoard
Safetensors
encoder-decoder
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
Marcin1304 commited on
Commit
dc780f8
•
1 Parent(s): 2809249

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/Mar10_16-27-55_d0c17e360eb0/events.out.tfevents.1710088076.d0c17e360eb0.144.0 +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: 0.8874
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
- | 3.3675 | 1.0 | 6 | 2.7074 |
48
- | 2.3683 | 2.0 | 12 | 1.9388 |
49
- | 1.8247 | 3.0 | 18 | 1.6651 |
50
- | 1.6383 | 4.0 | 24 | 1.5641 |
51
- | 1.5856 | 5.0 | 30 | 1.5378 |
52
- | 1.5526 | 6.0 | 36 | 1.5271 |
53
- | 1.5412 | 7.0 | 42 | 1.5342 |
54
- | 1.5522 | 8.0 | 48 | 1.5284 |
55
- | 1.5412 | 9.0 | 54 | 1.5417 |
56
- | 1.5399 | 10.0 | 60 | 1.5179 |
57
- | 1.5359 | 11.0 | 66 | 1.5177 |
58
- | 1.5109 | 12.0 | 72 | 1.5163 |
59
- | 1.5186 | 13.0 | 78 | 1.5135 |
60
- | 1.5322 | 14.0 | 84 | 1.5068 |
61
- | 1.5102 | 15.0 | 90 | 1.4860 |
62
- | 1.4963 | 16.0 | 96 | 1.4628 |
63
- | 1.4525 | 17.0 | 102 | 1.4343 |
64
- | 1.4217 | 18.0 | 108 | 1.4009 |
65
- | 1.3893 | 19.0 | 114 | 1.4014 |
66
- | 1.3816 | 20.0 | 120 | 1.3321 |
67
- | 1.3374 | 21.0 | 126 | 1.3043 |
68
- | 1.3131 | 22.0 | 132 | 1.3202 |
69
- | 1.3057 | 23.0 | 138 | 1.2499 |
70
- | 1.3516 | 24.0 | 144 | 1.2650 |
71
- | 1.2694 | 25.0 | 150 | 1.2313 |
72
- | 1.2187 | 26.0 | 156 | 1.1643 |
73
- | 1.1725 | 27.0 | 162 | 1.1295 |
74
- | 1.1283 | 28.0 | 168 | 1.0800 |
75
- | 1.0868 | 29.0 | 174 | 1.0535 |
76
- | 1.0771 | 30.0 | 180 | 1.0376 |
77
- | 1.0544 | 31.0 | 186 | 0.9880 |
78
- | 1.0181 | 32.0 | 192 | 0.9862 |
79
- | 1.0028 | 33.0 | 198 | 0.9744 |
80
- | 0.9996 | 34.0 | 204 | 0.9485 |
81
- | 0.9772 | 35.0 | 210 | 0.9270 |
82
- | 0.9558 | 36.0 | 216 | 0.9156 |
83
- | 0.9753 | 37.0 | 222 | 0.9040 |
84
- | 0.9376 | 38.0 | 228 | 0.8955 |
85
- | 0.9316 | 39.0 | 234 | 0.8908 |
86
- | 0.9245 | 40.0 | 240 | 0.8874 |
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: 0.7222
17
 
18
  ## Model description
19
 
 
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
+ | 3.4163 | 1.0 | 6 | 2.8253 |
48
+ | 2.463 | 2.0 | 12 | 2.0984 |
49
+ | 1.8832 | 3.0 | 18 | 1.7286 |
50
+ | 1.6613 | 4.0 | 24 | 1.6379 |
51
+ | 1.5863 | 5.0 | 30 | 1.5767 |
52
+ | 1.5021 | 6.0 | 36 | 1.5366 |
53
+ | 1.4813 | 7.0 | 42 | 1.5000 |
54
+ | 1.4805 | 8.0 | 48 | 1.4118 |
55
+ | 1.4184 | 9.0 | 54 | 1.4590 |
56
+ | 1.3594 | 10.0 | 60 | 1.3815 |
57
+ | 1.3154 | 11.0 | 66 | 1.3336 |
58
+ | 1.3036 | 12.0 | 72 | 1.3426 |
59
+ | 1.2467 | 13.0 | 78 | 1.2566 |
60
+ | 1.1995 | 14.0 | 84 | 1.1788 |
61
+ | 1.1292 | 15.0 | 90 | 1.1819 |
62
+ | 1.1157 | 16.0 | 96 | 1.1389 |
63
+ | 1.1397 | 17.0 | 102 | 1.0924 |
64
+ | 1.1128 | 18.0 | 108 | 1.0831 |
65
+ | 1.0476 | 19.0 | 114 | 1.0312 |
66
+ | 1.0193 | 20.0 | 120 | 0.9820 |
67
+ | 1.0701 | 21.0 | 126 | 0.9712 |
68
+ | 0.9618 | 22.0 | 132 | 0.9326 |
69
+ | 0.9227 | 23.0 | 138 | 0.9335 |
70
+ | 0.9399 | 24.0 | 144 | 0.9046 |
71
+ | 0.9318 | 25.0 | 150 | 0.8951 |
72
+ | 0.9068 | 26.0 | 156 | 0.8831 |
73
+ | 0.8687 | 27.0 | 162 | 0.8611 |
74
+ | 0.848 | 28.0 | 168 | 0.8884 |
75
+ | 0.8559 | 29.0 | 174 | 0.8844 |
76
+ | 0.8439 | 30.0 | 180 | 0.8729 |
77
+ | 0.8453 | 31.0 | 186 | 0.8323 |
78
+ | 0.8154 | 32.0 | 192 | 0.8130 |
79
+ | 0.788 | 33.0 | 198 | 0.8038 |
80
+ | 0.7912 | 34.0 | 204 | 0.7717 |
81
+ | 0.7823 | 35.0 | 210 | 0.7539 |
82
+ | 0.7658 | 36.0 | 216 | 0.7556 |
83
+ | 0.7617 | 37.0 | 222 | 0.7427 |
84
+ | 0.7396 | 38.0 | 228 | 0.7340 |
85
+ | 0.7621 | 39.0 | 234 | 0.7243 |
86
+ | 0.7324 | 40.0 | 240 | 0.7222 |
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 sha256:1c9cbe57dec03a2cdebb1dfd92343bc89e7f8de32f9c29fa852c65e6c2158af3
3
- size 31205552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc57d279b06577aa2908f9dd05e1c0a37e545c42dfedfbfe914fbce02ba8d9a0
3
+ size 31207604
runs/Mar10_16-27-55_d0c17e360eb0/events.out.tfevents.1710088076.d0c17e360eb0.144.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e2fe3cf1f9f4e21e904a0032a462fcc4b12a6a4d85c4d6de997054ffa092ca5
3
+ size 27997
tokenizer.json CHANGED
@@ -112,74 +112,75 @@
112
  "7": 13,
113
  "8": 14,
114
  "9": 15,
115
- "99": 16,
116
  "10": 17,
117
- "11": 18,
118
  "98": 19,
119
- "12": 20,
120
- "97": 21,
121
- "96": 22,
122
  "13": 23,
123
- "95": 24,
124
- "14": 25,
125
- "15": 26,
126
- "94": 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
- "9 9",
154
  "1 0",
155
- "1 1",
156
  "9 8",
 
157
  "1 2",
158
  "9 7",
159
- "9 6",
160
  "1 3",
 
161
  "9 5",
162
  "1 4",
163
  "1 5",
164
  "9 4",
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",
184
  "8 4",
185
  "2 6",
 
112
  "7": 13,
113
  "8": 14,
114
  "9": 15,
115
+ "=": 16,
116
  "10": 17,
117
+ "99": 18,
118
  "98": 19,
119
+ "11": 20,
120
+ "12": 21,
121
+ "97": 22,
122
  "13": 23,
123
+ "96": 24,
124
+ "95": 25,
125
+ "14": 26,
126
+ "15": 27,
127
+ "94": 28,
128
  "93": 29,
129
+ "16": 30,
130
  "92": 31,
131
+ "17": 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
  "22": 41,
141
+ "87": 42,
142
  "23": 43,
143
+ "86": 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
  "9 8",
157
+ "1 1",
158
  "1 2",
159
  "9 7",
 
160
  "1 3",
161
+ "9 6",
162
  "9 5",
163
  "1 4",
164
  "1 5",
165
  "9 4",
 
166
  "9 3",
167
+ "1 6",
168
  "9 2",
169
+ "1 7",
170
  "1 8",
171
+ "9 1",
172
  "1 9",
173
  "9 0",
 
174
  "8 9",
175
+ "2 0",
176
  "2 1",
177
  "8 8",
 
178
  "2 2",
179
+ "8 7",
180
  "2 3",
181
+ "8 6",
182
  "8 5",
183
+ "2 4",
184
  "2 5",
185
  "8 4",
186
  "2 6",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:602ea3edb6ceefe1ca334d445fc0878db980705f84b80cf789f2af12cf5fe19b
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c1cce945c5e65e2211dc0e5e08cf478ae72fd3da7322dd5486bca7af05174f
3
  size 5112