Hugging Face's logo

adambiel22
/
calculator_model_test

Transformers
TensorBoard
Safetensors
encoder-decoder
text2text-generation
Generated from Trainer
Model card Files
xet
Metrics Community
adambiel22 commited on
Commit
2a4c5ff
·
verified ·
1 Parent(s): 0863e1b

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_14-41-47_7c339ad63e68/events.out.tfevents.1709563307.7c339ad63e68.836.2 +3 -0
  5. tokenizer.json +59 -35
  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: 0.0914
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
- | 2.9231 | 1.0 | 6 | 2.2571 |
48
- | 2.0141 | 2.0 | 12 | 1.6996 |
49
- | 1.5309 | 3.0 | 18 | 1.2998 |
50
- | 1.1976 | 4.0 | 24 | 1.0513 |
51
- | 1.0164 | 5.0 | 30 | 0.9962 |
52
- | 0.9314 | 6.0 | 36 | 0.8360 |
53
- | 0.8189 | 7.0 | 42 | 0.7625 |
54
- | 0.7377 | 8.0 | 48 | 0.6906 |
55
- | 0.6797 | 9.0 | 54 | 0.6286 |
56
- | 0.6326 | 10.0 | 60 | 0.6023 |
57
- | 0.6027 | 11.0 | 66 | 0.5696 |
58
- | 0.5668 | 12.0 | 72 | 0.5291 |
59
- | 0.5397 | 13.0 | 78 | 0.5183 |
60
- | 0.5151 | 14.0 | 84 | 0.4830 |
61
- | 0.4827 | 15.0 | 90 | 0.4806 |
62
- | 0.471 | 16.0 | 96 | 0.4802 |
63
- | 0.472 | 17.0 | 102 | 0.4500 |
64
- | 0.4374 | 18.0 | 108 | 0.4284 |
65
- | 0.4336 | 19.0 | 114 | 0.3807 |
66
- | 0.3985 | 20.0 | 120 | 0.3672 |
67
- | 0.38 | 21.0 | 126 | 0.3423 |
68
- | 0.3577 | 22.0 | 132 | 0.3290 |
69
- | 0.3397 | 23.0 | 138 | 0.2871 |
70
- | 0.3092 | 24.0 | 144 | 0.2936 |
71
- | 0.3086 | 25.0 | 150 | 0.2556 |
72
- | 0.2831 | 26.0 | 156 | 0.2386 |
73
- | 0.2589 | 27.0 | 162 | 0.2183 |
74
- | 0.2458 | 28.0 | 168 | 0.2022 |
75
- | 0.2312 | 29.0 | 174 | 0.1880 |
76
- | 0.2213 | 30.0 | 180 | 0.1704 |
77
- | 0.2023 | 31.0 | 186 | 0.1577 |
78
- | 0.1948 | 32.0 | 192 | 0.1401 |
79
- | 0.1776 | 33.0 | 198 | 0.1287 |
80
- | 0.1645 | 34.0 | 204 | 0.1158 |
81
- | 0.1569 | 35.0 | 210 | 0.1128 |
82
- | 0.1495 | 36.0 | 216 | 0.1032 |
83
- | 0.1435 | 37.0 | 222 | 0.0988 |
84
- | 0.1364 | 38.0 | 228 | 0.0972 |
85
- | 0.138 | 39.0 | 234 | 0.0930 |
86
- | 0.1294 | 40.0 | 240 | 0.0914 |
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: 0.0095
17
 
18
  ## Model description
19
 
 
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
+ | 2.4753 | 1.0 | 13 | 1.7336 |
48
+ | 1.3843 | 2.0 | 26 | 0.9380 |
49
+ | 0.8281 | 3.0 | 39 | 0.7141 |
50
+ | 0.6509 | 4.0 | 52 | 0.5507 |
51
+ | 0.5643 | 5.0 | 65 | 0.5065 |
52
+ | 0.5155 | 6.0 | 78 | 0.4642 |
53
+ | 0.445 | 7.0 | 91 | 0.3848 |
54
+ | 0.3912 | 8.0 | 104 | 0.3584 |
55
+ | 0.3564 | 9.0 | 117 | 0.3142 |
56
+ | 0.3175 | 10.0 | 130 | 0.2663 |
57
+ | 0.2765 | 11.0 | 143 | 0.2291 |
58
+ | 0.2436 | 12.0 | 156 | 0.1915 |
59
+ | 0.2186 | 13.0 | 169 | 0.1556 |
60
+ | 0.1646 | 14.0 | 182 | 0.1097 |
61
+ | 0.1504 | 15.0 | 195 | 0.0862 |
62
+ | 0.113 | 16.0 | 208 | 0.0725 |
63
+ | 0.0864 | 17.0 | 221 | 0.0500 |
64
+ | 0.0722 | 18.0 | 234 | 0.0425 |
65
+ | 0.0654 | 19.0 | 247 | 0.0389 |
66
+ | 0.0581 | 20.0 | 260 | 0.0312 |
67
+ | 0.052 | 21.0 | 273 | 0.0284 |
68
+ | 0.0459 | 22.0 | 286 | 0.0275 |
69
+ | 0.0426 | 23.0 | 299 | 0.0213 |
70
+ | 0.0381 | 24.0 | 312 | 0.0200 |
71
+ | 0.0374 | 25.0 | 325 | 0.0186 |
72
+ | 0.0334 | 26.0 | 338 | 0.0185 |
73
+ | 0.0307 | 27.0 | 351 | 0.0157 |
74
+ | 0.0292 | 28.0 | 364 | 0.0147 |
75
+ | 0.0269 | 29.0 | 377 | 0.0146 |
76
+ | 0.0261 | 30.0 | 390 | 0.0129 |
77
+ | 0.0248 | 31.0 | 403 | 0.0121 |
78
+ | 0.0237 | 32.0 | 416 | 0.0114 |
79
+ | 0.023 | 33.0 | 429 | 0.0115 |
80
+ | 0.0217 | 34.0 | 442 | 0.0109 |
81
+ | 0.0208 | 35.0 | 455 | 0.0101 |
82
+ | 0.0205 | 36.0 | 468 | 0.0102 |
83
+ | 0.0197 | 37.0 | 481 | 0.0098 |
84
+ | 0.0193 | 38.0 | 494 | 0.0096 |
85
+ | 0.019 | 39.0 | 507 | 0.0094 |
86
+ | 0.0188 | 40.0 | 520 | 0.0095 |
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": 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": 65
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": 65
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:bf444c542344de4bd3ed82e5f1b260d744fe2e6768426188c5c9199301fd7001
3
- size 31207604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee0f55fb90d9fd389a3b662334a8cbb4c01e631d10f9d6d5ea1f15d5829b53f3
3
+ size 31232228
runs/Mar04_14-41-47_7c339ad63e68/events.out.tfevents.1709563307.7c339ad63e68.836.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d1fb29e230fb7e056268a0bcaf839a9c640923c3e3a3a082568bdf4acdfb72e
3
+ size 28105
tokenizer.json CHANGED
@@ -113,80 +113,104 @@
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",
161
  "1 3",
162
  "9 5",
163
  "1 4",
164
- "9 4",
165
  "1 5",
166
- "9 3",
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
  ]
191
  }
192
  }
 
113
  "8": 14,
114
  "9": 15,
115
  "=": 16,
116
+ "99": 17,
117
+ "10": 18,
118
  "98": 19,
119
  "11": 20,
120
+ "12": 21,
121
+ "97": 22,
122
  "96": 23,
123
  "13": 24,
124
  "95": 25,
125
  "14": 26,
126
+ "15": 27,
127
+ "94": 28,
128
+ "16": 29,
129
+ "93": 30,
130
  "17": 31,
131
  "92": 32,
132
+ "91": 33,
133
+ "18": 34,
134
  "90": 35,
135
  "19": 36,
136
+ "89": 37,
137
+ "20": 38,
138
+ "88": 39,
139
+ "21": 40,
140
+ "22": 41,
141
+ "87": 42,
142
+ "86": 43,
143
+ "23": 44,
144
  "85": 45,
145
  "24": 46,
146
+ "84": 47,
147
+ "25": 48,
148
+ "26": 49,
149
+ "83": 50,
150
  "27": 51,
151
+ "81": 52,
152
+ "82": 53,
153
+ "28": 54,
154
+ "80": 55,
155
+ "30": 56,
156
+ "29": 57,
157
+ "31": 58,
158
+ "79": 59,
159
+ "78": 60,
160
+ "76": 61,
161
+ "34": 62,
162
+ "77": 63,
163
+ "33": 64
164
  },
165
  "merges": [
 
166
  "9 9",
167
+ "1 0",
168
  "9 8",
169
  "1 1",
 
170
  "1 2",
171
+ "9 7",
172
  "9 6",
173
  "1 3",
174
  "9 5",
175
  "1 4",
 
176
  "1 5",
177
+ "9 4",
178
  "1 6",
179
+ "9 3",
180
  "1 7",
181
  "9 2",
 
182
  "9 1",
183
+ "1 8",
184
  "9 0",
185
  "1 9",
 
186
  "8 9",
187
+ "2 0",
188
  "8 8",
189
+ "2 1",
190
  "2 2",
191
+ "8 7",
192
  "8 6",
193
+ "2 3",
194
  "8 5",
195
  "2 4",
 
196
  "8 4",
197
+ "2 5",
198
  "2 6",
199
+ "8 3",
200
  "2 7",
201
+ "8 1",
202
+ "8 2",
203
+ "2 8",
204
+ "8 0",
205
+ "3 0",
206
+ "2 9",
207
+ "3 1",
208
+ "7 9",
209
+ "7 8",
210
+ "7 6",
211
+ "3 4",
212
+ "7 7",
213
+ "3 3"
214
  ]
215
  }
216
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a8d5009d93cc0b28f0827c6753d8c862fb9c99bee9458d4004349b229359acd
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:540c8fd7baa2c13dbd0184f2ea00a0cd78a6ebf4642173f5ea5924130d2de23a
3
  size 5112