Hugging Face's logo

ciebson
/
calculator_model_test

Text2Text Generation
Transformers
TensorBoard
Safetensors
encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ciebson commited on
Commit
ce6a01a
·
verified ·
1 Parent(s): e68e058

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_14-00-51_d8c8da50ec4e/events.out.tfevents.1709560851.d8c8da50ec4e.409.2 +3 -0
  5. tokenizer.json +146 -54
  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: 0.2014
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
- | 2.947 | 1.0 | 6 | 2.2690 |
48
- | 2.0301 | 2.0 | 12 | 1.7402 |
49
- | 1.5419 | 3.0 | 18 | 1.2929 |
50
- | 1.2143 | 4.0 | 24 | 1.0901 |
51
- | 1.0259 | 5.0 | 30 | 0.9702 |
52
- | 0.9007 | 6.0 | 36 | 0.8471 |
53
- | 0.7925 | 7.0 | 42 | 0.8145 |
54
- | 0.7608 | 8.0 | 48 | 0.7531 |
55
- | 0.7152 | 9.0 | 54 | 0.6772 |
56
- | 0.6579 | 10.0 | 60 | 0.6378 |
57
- | 0.6218 | 11.0 | 66 | 0.5797 |
58
- | 0.5697 | 12.0 | 72 | 0.5534 |
59
- | 0.5604 | 13.0 | 78 | 0.5225 |
60
- | 0.5172 | 14.0 | 84 | 0.4961 |
61
- | 0.4936 | 15.0 | 90 | 0.4773 |
62
- | 0.4897 | 16.0 | 96 | 0.5122 |
63
- | 0.499 | 17.0 | 102 | 0.4710 |
64
- | 0.4578 | 18.0 | 108 | 0.4763 |
65
- | 0.4455 | 19.0 | 114 | 0.4437 |
66
- | 0.4382 | 20.0 | 120 | 0.4259 |
67
- | 0.407 | 21.0 | 126 | 0.4043 |
68
- | 0.3937 | 22.0 | 132 | 0.3824 |
69
- | 0.3753 | 23.0 | 138 | 0.3754 |
70
- | 0.3795 | 24.0 | 144 | 0.3496 |
71
- | 0.3553 | 25.0 | 150 | 0.3459 |
72
- | 0.3454 | 26.0 | 156 | 0.3359 |
73
- | 0.3391 | 27.0 | 162 | 0.3221 |
74
- | 0.3182 | 28.0 | 168 | 0.3027 |
75
- | 0.3087 | 29.0 | 174 | 0.2958 |
76
- | 0.288 | 30.0 | 180 | 0.2732 |
77
- | 0.288 | 31.0 | 186 | 0.2607 |
78
- | 0.2705 | 32.0 | 192 | 0.2444 |
79
- | 0.2637 | 33.0 | 198 | 0.2393 |
80
- | 0.2507 | 34.0 | 204 | 0.2264 |
81
- | 0.2331 | 35.0 | 210 | 0.2193 |
82
- | 0.2292 | 36.0 | 216 | 0.2118 |
83
- | 0.2238 | 37.0 | 222 | 0.2089 |
84
- | 0.2252 | 38.0 | 228 | 0.2051 |
85
- | 0.2131 | 39.0 | 234 | 0.2043 |
86
- | 0.2168 | 40.0 | 240 | 0.2014 |
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: 0.0943
17
 
18
  ## Model description
19
 
 
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
+ | 3.0793 | 1.0 | 12 | 2.2430 |
48
+ | 1.9376 | 2.0 | 24 | 1.5349 |
49
+ | 1.3941 | 3.0 | 36 | 1.2003 |
50
+ | 1.1127 | 4.0 | 48 | 1.0107 |
51
+ | 0.9531 | 5.0 | 60 | 0.8533 |
52
+ | 0.84 | 6.0 | 72 | 0.7840 |
53
+ | 0.7753 | 7.0 | 84 | 0.7185 |
54
+ | 0.7678 | 8.0 | 96 | 0.7171 |
55
+ | 0.724 | 9.0 | 108 | 0.6569 |
56
+ | 0.6601 | 10.0 | 120 | 0.6202 |
57
+ | 0.6235 | 11.0 | 132 | 0.5901 |
58
+ | 0.5875 | 12.0 | 144 | 0.5537 |
59
+ | 0.5707 | 13.0 | 156 | 0.5714 |
60
+ | 0.5528 | 14.0 | 168 | 0.5239 |
61
+ | 0.5327 | 15.0 | 180 | 0.5050 |
62
+ | 0.5042 | 16.0 | 192 | 0.4515 |
63
+ | 0.4587 | 17.0 | 204 | 0.4170 |
64
+ | 0.4317 | 18.0 | 216 | 0.3874 |
65
+ | 0.4012 | 19.0 | 228 | 0.3570 |
66
+ | 0.3729 | 20.0 | 240 | 0.3287 |
67
+ | 0.3486 | 21.0 | 252 | 0.3186 |
68
+ | 0.3391 | 22.0 | 264 | 0.2798 |
69
+ | 0.2975 | 23.0 | 276 | 0.2586 |
70
+ | 0.2832 | 24.0 | 288 | 0.2426 |
71
+ | 0.2641 | 25.0 | 300 | 0.2202 |
72
+ | 0.2427 | 26.0 | 312 | 0.2055 |
73
+ | 0.2315 | 27.0 | 324 | 0.1902 |
74
+ | 0.2149 | 28.0 | 336 | 0.1758 |
75
+ | 0.1983 | 29.0 | 348 | 0.1705 |
76
+ | 0.1865 | 30.0 | 360 | 0.1524 |
77
+ | 0.1732 | 31.0 | 372 | 0.1406 |
78
+ | 0.1611 | 32.0 | 384 | 0.1336 |
79
+ | 0.1514 | 33.0 | 396 | 0.1309 |
80
+ | 0.1443 | 34.0 | 408 | 0.1202 |
81
+ | 0.1374 | 35.0 | 420 | 0.1127 |
82
+ | 0.1302 | 36.0 | 432 | 0.1050 |
83
+ | 0.1247 | 37.0 | 444 | 0.1050 |
84
+ | 0.12 | 38.0 | 456 | 0.0985 |
85
+ | 0.1159 | 39.0 | 468 | 0.0960 |
86
+ | 0.1144 | 40.0 | 480 | 0.0943 |
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": 99
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": 99
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:f1718e7b86e2847840f6c60a23032d116ce48f66e5c61b46aed03617e0ddab03
3
- size 31207604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef070266d38568680a80d34762c0f65f401fce8618045f620bd8527c7fe04619
3
+ size 31301996
runs/Mar04_14-00-51_d8c8da50ec4e/events.out.tfevents.1709560851.d8c8da50ec4e.409.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9705e0a62d2ef54ca7f2fde513e665e3a3f3726b7922fb965147bc304319c0a
3
+ size 28096
tokenizer.json CHANGED
@@ -114,79 +114,171 @@
114
  "9": 15,
115
  "=": 16,
116
  "10": 17,
117
- "99": 18,
118
- "11": 19,
119
- "98": 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
- "16": 29,
129
- "93": 30,
130
- "17": 31,
131
- "92": 32,
132
- "18": 33,
133
- "91": 34,
134
- "19": 35,
135
- "90": 36,
136
- "20": 37,
137
- "89": 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
- "84": 47,
147
- "25": 48,
148
- "26": 49,
149
- "83": 50,
150
- "27": 51,
151
- "82": 52
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
152
  },
153
  "merges": [
154
  "1 0",
155
- "9 9",
156
  "1 1",
157
- "9 8",
 
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
- "1 6",
167
  "9 3",
168
- "1 7",
169
  "9 2",
170
- "1 8",
171
  "9 1",
172
- "1 9",
173
  "9 0",
174
- "2 0",
175
  "8 9",
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
- "8 4",
185
- "2 5",
186
- "2 6",
187
  "8 3",
188
- "2 7",
189
- "8 2"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
190
  ]
191
  }
192
  }
 
114
  "9": 15,
115
  "=": 16,
116
  "10": 17,
117
+ "11": 18,
118
+ "13": 19,
119
+ "19": 20,
120
  "12": 21,
121
+ "15": 22,
122
+ "14": 23,
123
+ "16": 24,
124
+ "17": 25,
125
+ "18": 26,
126
+ "20": 27,
127
+ "97": 28,
128
+ "99": 29,
129
+ "98": 30,
130
+ "21": 31,
131
+ "24": 32,
132
+ "22": 33,
133
+ "23": 34,
134
+ "95": 35,
135
+ "96": 36,
136
+ "25": 37,
137
+ "26": 38,
138
+ "94": 39,
139
+ "93": 40,
140
+ "27": 41,
141
+ "92": 42,
142
+ "91": 43,
143
+ "28": 44,
144
+ "90": 45,
145
+ "29": 46,
146
+ "89": 47,
147
+ "88": 48,
148
+ "32": 49,
149
+ "31": 50,
150
+ "30": 51,
151
+ "87": 52,
152
+ "33": 53,
153
+ "34": 54,
154
+ "86": 55,
155
+ "35": 56,
156
+ "85": 57,
157
+ "36": 58,
158
+ "83": 59,
159
+ "84": 60,
160
+ "37": 61,
161
+ "82": 62,
162
+ "81": 63,
163
+ "38": 64,
164
+ "39": 65,
165
+ "40": 66,
166
+ "80": 67,
167
+ "41": 68,
168
+ "79": 69,
169
+ "78": 70,
170
+ "43": 71,
171
+ "45": 72,
172
+ "76": 73,
173
+ "42": 74,
174
+ "77": 75,
175
+ "44": 76,
176
+ "75": 77,
177
+ "46": 78,
178
+ "47": 79,
179
+ "73": 80,
180
+ "71": 81,
181
+ "72": 82,
182
+ "74": 83,
183
+ "50": 84,
184
+ "49": 85,
185
+ "70": 86,
186
+ "48": 87,
187
+ "68": 88,
188
+ "51": 89,
189
+ "52": 90,
190
+ "69": 91,
191
+ "67": 92,
192
+ "65": 93,
193
+ "53": 94,
194
+ "54": 95,
195
+ "55": 96,
196
+ "66": 97,
197
+ "56": 98
198
  },
199
  "merges": [
200
  "1 0",
 
201
  "1 1",
202
+ "1 3",
203
+ "1 9",
204
  "1 2",
205
+ "1 5",
206
+ "1 4",
207
+ "1 6",
208
+ "1 7",
209
+ "1 8",
210
+ "2 0",
211
  "9 7",
212
+ "9 9",
213
+ "9 8",
214
+ "2 1",
215
+ "2 4",
216
+ "2 2",
217
+ "2 3",
218
  "9 5",
219
+ "9 6",
220
+ "2 5",
221
+ "2 6",
222
  "9 4",
 
223
  "9 3",
224
+ "2 7",
225
  "9 2",
 
226
  "9 1",
227
+ "2 8",
228
  "9 0",
229
+ "2 9",
230
  "8 9",
231
  "8 8",
232
+ "3 2",
233
+ "3 1",
234
+ "3 0",
235
  "8 7",
236
+ "3 3",
237
+ "3 4",
238
  "8 6",
239
+ "3 5",
240
  "8 5",
241
+ "3 6",
 
 
242
  "8 3",
243
+ "8 4",
244
+ "3 7",
245
+ "8 2",
246
+ "8 1",
247
+ "3 8",
248
+ "3 9",
249
+ "4 0",
250
+ "8 0",
251
+ "4 1",
252
+ "7 9",
253
+ "7 8",
254
+ "4 3",
255
+ "4 5",
256
+ "7 6",
257
+ "4 2",
258
+ "7 7",
259
+ "4 4",
260
+ "7 5",
261
+ "4 6",
262
+ "4 7",
263
+ "7 3",
264
+ "7 1",
265
+ "7 2",
266
+ "7 4",
267
+ "5 0",
268
+ "4 9",
269
+ "7 0",
270
+ "4 8",
271
+ "6 8",
272
+ "5 1",
273
+ "5 2",
274
+ "6 9",
275
+ "6 7",
276
+ "6 5",
277
+ "5 3",
278
+ "5 4",
279
+ "5 5",
280
+ "6 6",
281
+ "5 6"
282
  ]
283
  }
284
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac7ad0845eaad54b53a1cc4f9a14b90eecd2370ffb4954a8c0a67c31b5e464ae
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f60299a6ccf7de1e094eb15269b535f3bb4b8176d7eb4c126608ea557871b5d3
3
  size 5112