End of training
Browse files- README.md +102 -103
- config.json +0 -1
- model.safetensors +1 -1
- runs/Mar10_16-49-46_d0c17e360eb0/events.out.tfevents.1710089386.d0c17e360eb0.144.3 +3 -0
- tokenizer.json +18 -18
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: Marcin1304/calculator_model_test_second_version
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
model-index:
|
|
@@ -12,9 +11,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 12 |
|
| 13 |
# calculator_model_test_second_version
|
| 14 |
|
| 15 |
-
This model is a fine-tuned version of [
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Loss: 0.
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -45,106 +44,106 @@ The following hyperparameters were used during training:
|
|
| 45 |
|
| 46 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
-
|
|
| 49 |
-
|
|
| 50 |
-
| 1.
|
| 51 |
-
| 1.
|
| 52 |
-
|
|
| 53 |
-
|
|
| 54 |
-
|
|
| 55 |
-
|
|
| 56 |
-
|
|
| 57 |
-
|
|
| 58 |
-
|
|
| 59 |
-
|
|
| 60 |
-
|
|
| 61 |
-
|
|
| 62 |
-
|
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.
|
| 117 |
-
| 0.
|
| 118 |
-
| 0.
|
| 119 |
-
| 0.
|
| 120 |
-
| 0.
|
| 121 |
-
| 0.
|
| 122 |
-
| 0.
|
| 123 |
-
| 0.
|
| 124 |
-
| 0.
|
| 125 |
-
| 0.
|
| 126 |
-
| 0.
|
| 127 |
-
| 0.
|
| 128 |
-
| 0.
|
| 129 |
-
| 0.
|
| 130 |
-
| 0.
|
| 131 |
-
| 0.
|
| 132 |
-
| 0.
|
| 133 |
-
| 0.
|
| 134 |
-
| 0.
|
| 135 |
-
| 0.
|
| 136 |
-
| 0.
|
| 137 |
-
| 0.
|
| 138 |
-
| 0.
|
| 139 |
-
| 0.
|
| 140 |
-
| 0.
|
| 141 |
-
| 0.
|
| 142 |
-
| 0.
|
| 143 |
-
| 0.
|
| 144 |
-
| 0.
|
| 145 |
-
| 0.
|
| 146 |
-
| 0.
|
| 147 |
-
| 0.
|
| 148 |
|
| 149 |
|
| 150 |
### Framework versions
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
model-index:
|
|
|
|
| 11 |
|
| 12 |
# calculator_model_test_second_version
|
| 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: 0.1239
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 44 |
|
| 45 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 46 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 47 |
+
| 3.4193 | 1.0 | 6 | 2.7303 |
|
| 48 |
+
| 2.3495 | 2.0 | 12 | 1.9121 |
|
| 49 |
+
| 1.7677 | 3.0 | 18 | 1.6227 |
|
| 50 |
+
| 1.6093 | 4.0 | 24 | 1.5830 |
|
| 51 |
+
| 1.5528 | 5.0 | 30 | 1.5309 |
|
| 52 |
+
| 1.5114 | 6.0 | 36 | 1.4526 |
|
| 53 |
+
| 1.4513 | 7.0 | 42 | 1.3988 |
|
| 54 |
+
| 1.4022 | 8.0 | 48 | 1.3442 |
|
| 55 |
+
| 1.3473 | 9.0 | 54 | 1.2809 |
|
| 56 |
+
| 1.2985 | 10.0 | 60 | 1.2159 |
|
| 57 |
+
| 1.2173 | 11.0 | 66 | 1.1870 |
|
| 58 |
+
| 1.1373 | 12.0 | 72 | 1.0899 |
|
| 59 |
+
| 1.0855 | 13.0 | 78 | 1.0270 |
|
| 60 |
+
| 1.04 | 14.0 | 84 | 0.9607 |
|
| 61 |
+
| 1.0274 | 15.0 | 90 | 0.9749 |
|
| 62 |
+
| 0.9975 | 16.0 | 96 | 0.9045 |
|
| 63 |
+
| 0.9274 | 17.0 | 102 | 0.9247 |
|
| 64 |
+
| 0.8963 | 18.0 | 108 | 0.8161 |
|
| 65 |
+
| 0.8767 | 19.0 | 114 | 0.8131 |
|
| 66 |
+
| 0.8764 | 20.0 | 120 | 0.9056 |
|
| 67 |
+
| 0.8763 | 21.0 | 126 | 0.7668 |
|
| 68 |
+
| 0.8097 | 22.0 | 132 | 0.8305 |
|
| 69 |
+
| 0.8 | 23.0 | 138 | 0.7579 |
|
| 70 |
+
| 0.7483 | 24.0 | 144 | 0.7418 |
|
| 71 |
+
| 0.8242 | 25.0 | 150 | 0.7103 |
|
| 72 |
+
| 0.7375 | 26.0 | 156 | 0.6743 |
|
| 73 |
+
| 0.7078 | 27.0 | 162 | 0.6516 |
|
| 74 |
+
| 0.7112 | 28.0 | 168 | 0.7178 |
|
| 75 |
+
| 0.7518 | 29.0 | 174 | 0.7132 |
|
| 76 |
+
| 0.6874 | 30.0 | 180 | 0.6438 |
|
| 77 |
+
| 0.6671 | 31.0 | 186 | 0.6512 |
|
| 78 |
+
| 0.6595 | 32.0 | 192 | 0.6338 |
|
| 79 |
+
| 0.6375 | 33.0 | 198 | 0.5772 |
|
| 80 |
+
| 0.5933 | 34.0 | 204 | 0.5397 |
|
| 81 |
+
| 0.5938 | 35.0 | 210 | 0.5182 |
|
| 82 |
+
| 0.5818 | 36.0 | 216 | 0.5315 |
|
| 83 |
+
| 0.6946 | 37.0 | 222 | 0.9134 |
|
| 84 |
+
| 0.7946 | 38.0 | 228 | 0.7031 |
|
| 85 |
+
| 0.7079 | 39.0 | 234 | 0.6212 |
|
| 86 |
+
| 0.6055 | 40.0 | 240 | 0.5024 |
|
| 87 |
+
| 0.5524 | 41.0 | 246 | 0.5142 |
|
| 88 |
+
| 0.543 | 42.0 | 252 | 0.4946 |
|
| 89 |
+
| 0.5265 | 43.0 | 258 | 0.4820 |
|
| 90 |
+
| 0.5339 | 44.0 | 264 | 0.6029 |
|
| 91 |
+
| 0.5624 | 45.0 | 270 | 0.5800 |
|
| 92 |
+
| 0.5097 | 46.0 | 276 | 0.4858 |
|
| 93 |
+
| 0.5059 | 47.0 | 282 | 0.4554 |
|
| 94 |
+
| 0.4807 | 48.0 | 288 | 0.4538 |
|
| 95 |
+
| 0.4824 | 49.0 | 294 | 0.4248 |
|
| 96 |
+
| 0.4691 | 50.0 | 300 | 0.3919 |
|
| 97 |
+
| 0.5413 | 51.0 | 306 | 0.5179 |
|
| 98 |
+
| 0.5131 | 52.0 | 312 | 0.3809 |
|
| 99 |
+
| 0.4312 | 53.0 | 318 | 0.3955 |
|
| 100 |
+
| 0.4226 | 54.0 | 324 | 0.3597 |
|
| 101 |
+
| 0.4059 | 55.0 | 330 | 0.3501 |
|
| 102 |
+
| 0.3887 | 56.0 | 336 | 0.3281 |
|
| 103 |
+
| 0.3784 | 57.0 | 342 | 0.3294 |
|
| 104 |
+
| 0.3696 | 58.0 | 348 | 0.2937 |
|
| 105 |
+
| 0.3694 | 59.0 | 354 | 0.3153 |
|
| 106 |
+
| 0.3815 | 60.0 | 360 | 0.2878 |
|
| 107 |
+
| 0.3575 | 61.0 | 366 | 0.3236 |
|
| 108 |
+
| 0.3527 | 62.0 | 372 | 0.2940 |
|
| 109 |
+
| 0.3481 | 63.0 | 378 | 0.2703 |
|
| 110 |
+
| 0.3466 | 64.0 | 384 | 0.3331 |
|
| 111 |
+
| 0.4037 | 65.0 | 390 | 0.3615 |
|
| 112 |
+
| 0.363 | 66.0 | 396 | 0.3057 |
|
| 113 |
+
| 0.3374 | 67.0 | 402 | 0.2810 |
|
| 114 |
+
| 0.3256 | 68.0 | 408 | 0.2785 |
|
| 115 |
+
| 0.3206 | 69.0 | 414 | 0.2553 |
|
| 116 |
+
| 0.306 | 70.0 | 420 | 0.2336 |
|
| 117 |
+
| 0.2884 | 71.0 | 426 | 0.2361 |
|
| 118 |
+
| 0.2892 | 72.0 | 432 | 0.2257 |
|
| 119 |
+
| 0.275 | 73.0 | 438 | 0.2237 |
|
| 120 |
+
| 0.2968 | 74.0 | 444 | 0.2405 |
|
| 121 |
+
| 0.2879 | 75.0 | 450 | 0.2139 |
|
| 122 |
+
| 0.2832 | 76.0 | 456 | 0.2139 |
|
| 123 |
+
| 0.2726 | 77.0 | 462 | 0.2174 |
|
| 124 |
+
| 0.2687 | 78.0 | 468 | 0.2037 |
|
| 125 |
+
| 0.2609 | 79.0 | 474 | 0.1833 |
|
| 126 |
+
| 0.2518 | 80.0 | 480 | 0.1836 |
|
| 127 |
+
| 0.253 | 81.0 | 486 | 0.1861 |
|
| 128 |
+
| 0.2417 | 82.0 | 492 | 0.1650 |
|
| 129 |
+
| 0.2279 | 83.0 | 498 | 0.1706 |
|
| 130 |
+
| 0.2323 | 84.0 | 504 | 0.1785 |
|
| 131 |
+
| 0.225 | 85.0 | 510 | 0.1694 |
|
| 132 |
+
| 0.2194 | 86.0 | 516 | 0.1586 |
|
| 133 |
+
| 0.2217 | 87.0 | 522 | 0.1575 |
|
| 134 |
+
| 0.2093 | 88.0 | 528 | 0.1497 |
|
| 135 |
+
| 0.2109 | 89.0 | 534 | 0.1562 |
|
| 136 |
+
| 0.2081 | 90.0 | 540 | 0.1549 |
|
| 137 |
+
| 0.2027 | 91.0 | 546 | 0.1419 |
|
| 138 |
+
| 0.1982 | 92.0 | 552 | 0.1347 |
|
| 139 |
+
| 0.1951 | 93.0 | 558 | 0.1355 |
|
| 140 |
+
| 0.1893 | 94.0 | 564 | 0.1338 |
|
| 141 |
+
| 0.1881 | 95.0 | 570 | 0.1336 |
|
| 142 |
+
| 0.1911 | 96.0 | 576 | 0.1303 |
|
| 143 |
+
| 0.1862 | 97.0 | 582 | 0.1289 |
|
| 144 |
+
| 0.1882 | 98.0 | 588 | 0.1301 |
|
| 145 |
+
| 0.1792 | 99.0 | 594 | 0.1250 |
|
| 146 |
+
| 0.176 | 100.0 | 600 | 0.1239 |
|
| 147 |
|
| 148 |
|
| 149 |
### Framework versions
|
config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "Marcin1304/calculator_model_test_second_version",
|
| 3 |
"architectures": [
|
| 4 |
"EncoderDecoderModel"
|
| 5 |
],
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"EncoderDecoderModel"
|
| 4 |
],
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 31207604
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a905feeabc9c81f0b25326160ef494abc4e4a552b3464073d72745417f3b87b
|
| 3 |
size 31207604
|
runs/Mar10_16-49-46_d0c17e360eb0/events.out.tfevents.1710089386.d0c17e360eb0.144.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca2b4abe7646ffee89092aaac16cc99695d7fb22f2e6959ea92ce2447a040291
|
| 3 |
+
size 56963
|
tokenizer.json
CHANGED
|
@@ -115,34 +115,34 @@
|
|
| 115 |
"=": 16,
|
| 116 |
"10": 17,
|
| 117 |
"99": 18,
|
| 118 |
-
"
|
| 119 |
-
"
|
| 120 |
"12": 21,
|
| 121 |
"97": 22,
|
| 122 |
"13": 23,
|
| 123 |
"96": 24,
|
| 124 |
-
"
|
| 125 |
-
"
|
| 126 |
"15": 27,
|
| 127 |
"94": 28,
|
| 128 |
-
"
|
| 129 |
-
"
|
| 130 |
-
"
|
| 131 |
-
"
|
| 132 |
"18": 33,
|
| 133 |
"91": 34,
|
| 134 |
"19": 35,
|
| 135 |
"90": 36,
|
| 136 |
-
"
|
| 137 |
-
"
|
| 138 |
"21": 39,
|
| 139 |
"88": 40,
|
| 140 |
"22": 41,
|
| 141 |
"87": 42,
|
| 142 |
"23": 43,
|
| 143 |
"86": 44,
|
| 144 |
-
"
|
| 145 |
-
"
|
| 146 |
"25": 47,
|
| 147 |
"84": 48,
|
| 148 |
"26": 49,
|
|
@@ -153,34 +153,34 @@
|
|
| 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
|
| 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",
|
|
|
|
| 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 |
+
"14": 25,
|
| 125 |
+
"95": 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 |
"21": 39,
|
| 139 |
"88": 40,
|
| 140 |
"22": 41,
|
| 141 |
"87": 42,
|
| 142 |
"23": 43,
|
| 143 |
"86": 44,
|
| 144 |
+
"24": 45,
|
| 145 |
+
"85": 46,
|
| 146 |
"25": 47,
|
| 147 |
"84": 48,
|
| 148 |
"26": 49,
|
|
|
|
| 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 |
"1 4",
|
| 163 |
+
"9 5",
|
| 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 |
"2 1",
|
| 177 |
"8 8",
|
| 178 |
"2 2",
|
| 179 |
"8 7",
|
| 180 |
"2 3",
|
| 181 |
"8 6",
|
|
|
|
| 182 |
"2 4",
|
| 183 |
+
"8 5",
|
| 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:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a20c9478f127efcc47208f649d6556492aa8d0790902940f60b7e5ea7d0ce58
|
| 3 |
size 5112
|