update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,212 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- wmt16
|
| 7 |
+
model-index:
|
| 8 |
+
- name: t5-turkish-to-english
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# t5-turkish-to-english
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the wmt16 dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.0282
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-05
|
| 39 |
+
- train_batch_size: 8
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- lr_scheduler_warmup_steps: 500
|
| 45 |
+
- num_epochs: 3
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 51 |
+
| 0.6168 | 0.02 | 500 | 0.0497 |
|
| 52 |
+
| 0.0832 | 0.04 | 1000 | 0.0448 |
|
| 53 |
+
| 0.0791 | 0.06 | 1500 | 0.0424 |
|
| 54 |
+
| 0.0718 | 0.08 | 2000 | 0.0413 |
|
| 55 |
+
| 0.0661 | 0.1 | 2500 | 0.0406 |
|
| 56 |
+
| 0.0669 | 0.12 | 3000 | 0.0399 |
|
| 57 |
+
| 0.065 | 0.14 | 3500 | 0.0389 |
|
| 58 |
+
| 0.0627 | 0.16 | 4000 | 0.0389 |
|
| 59 |
+
| 0.0637 | 0.17 | 4500 | 0.0396 |
|
| 60 |
+
| 0.0599 | 0.19 | 5000 | 0.0376 |
|
| 61 |
+
| 0.0601 | 0.21 | 5500 | 0.0368 |
|
| 62 |
+
| 0.0594 | 0.23 | 6000 | 0.0379 |
|
| 63 |
+
| 0.0578 | 0.25 | 6500 | 0.0371 |
|
| 64 |
+
| 0.0577 | 0.27 | 7000 | 0.0383 |
|
| 65 |
+
| 0.0566 | 0.29 | 7500 | 0.0377 |
|
| 66 |
+
| 0.0554 | 0.31 | 8000 | 0.0351 |
|
| 67 |
+
| 0.0554 | 0.33 | 8500 | 0.0347 |
|
| 68 |
+
| 0.0546 | 0.35 | 9000 | 0.0351 |
|
| 69 |
+
| 0.0564 | 0.37 | 9500 | 0.0356 |
|
| 70 |
+
| 0.0533 | 0.39 | 10000 | 0.0340 |
|
| 71 |
+
| 0.0515 | 0.41 | 10500 | 0.0339 |
|
| 72 |
+
| 0.0523 | 0.43 | 11000 | 0.0337 |
|
| 73 |
+
| 0.0528 | 0.45 | 11500 | 0.0337 |
|
| 74 |
+
| 0.0536 | 0.47 | 12000 | 0.0332 |
|
| 75 |
+
| 0.0501 | 0.49 | 12500 | 0.0334 |
|
| 76 |
+
| 0.0493 | 0.51 | 13000 | 0.0332 |
|
| 77 |
+
| 0.0504 | 0.52 | 13500 | 0.0331 |
|
| 78 |
+
| 0.0484 | 0.54 | 14000 | 0.0328 |
|
| 79 |
+
| 0.0496 | 0.56 | 14500 | 0.0327 |
|
| 80 |
+
| 0.0469 | 0.58 | 15000 | 0.0331 |
|
| 81 |
+
| 0.0483 | 0.6 | 15500 | 0.0329 |
|
| 82 |
+
| 0.0477 | 0.62 | 16000 | 0.0326 |
|
| 83 |
+
| 0.0492 | 0.64 | 16500 | 0.0326 |
|
| 84 |
+
| 0.0482 | 0.66 | 17000 | 0.0322 |
|
| 85 |
+
| 0.0468 | 0.68 | 17500 | 0.0323 |
|
| 86 |
+
| 0.0474 | 0.7 | 18000 | 0.0320 |
|
| 87 |
+
| 0.0463 | 0.72 | 18500 | 0.0321 |
|
| 88 |
+
| 0.048 | 0.74 | 19000 | 0.0319 |
|
| 89 |
+
| 0.0463 | 0.76 | 19500 | 0.0319 |
|
| 90 |
+
| 0.0467 | 0.78 | 20000 | 0.0316 |
|
| 91 |
+
| 0.0457 | 0.8 | 20500 | 0.0319 |
|
| 92 |
+
| 0.0463 | 0.82 | 21000 | 0.0320 |
|
| 93 |
+
| 0.045 | 0.84 | 21500 | 0.0317 |
|
| 94 |
+
| 0.0442 | 0.86 | 22000 | 0.0314 |
|
| 95 |
+
| 0.0462 | 0.87 | 22500 | 0.0313 |
|
| 96 |
+
| 0.0453 | 0.89 | 23000 | 0.0313 |
|
| 97 |
+
| 0.0455 | 0.91 | 23500 | 0.0316 |
|
| 98 |
+
| 0.0459 | 0.93 | 24000 | 0.0311 |
|
| 99 |
+
| 0.0435 | 0.95 | 24500 | 0.0312 |
|
| 100 |
+
| 0.0451 | 0.97 | 25000 | 0.0310 |
|
| 101 |
+
| 0.043 | 0.99 | 25500 | 0.0310 |
|
| 102 |
+
| 0.0429 | 1.01 | 26000 | 0.0306 |
|
| 103 |
+
| 0.0423 | 1.03 | 26500 | 0.0309 |
|
| 104 |
+
| 0.0418 | 1.05 | 27000 | 0.0309 |
|
| 105 |
+
| 0.0418 | 1.07 | 27500 | 0.0308 |
|
| 106 |
+
| 0.0414 | 1.09 | 28000 | 0.0307 |
|
| 107 |
+
| 0.0426 | 1.11 | 28500 | 0.0308 |
|
| 108 |
+
| 0.0411 | 1.13 | 29000 | 0.0306 |
|
| 109 |
+
| 0.0414 | 1.15 | 29500 | 0.0310 |
|
| 110 |
+
| 0.0411 | 1.17 | 30000 | 0.0305 |
|
| 111 |
+
| 0.0424 | 1.19 | 30500 | 0.0305 |
|
| 112 |
+
| 0.0419 | 1.21 | 31000 | 0.0307 |
|
| 113 |
+
| 0.0415 | 1.22 | 31500 | 0.0304 |
|
| 114 |
+
| 0.0403 | 1.24 | 32000 | 0.0303 |
|
| 115 |
+
| 0.0411 | 1.26 | 32500 | 0.0302 |
|
| 116 |
+
| 0.0414 | 1.28 | 33000 | 0.0304 |
|
| 117 |
+
| 0.0412 | 1.3 | 33500 | 0.0301 |
|
| 118 |
+
| 0.0404 | 1.32 | 34000 | 0.0304 |
|
| 119 |
+
| 0.0403 | 1.34 | 34500 | 0.0304 |
|
| 120 |
+
| 0.0415 | 1.36 | 35000 | 0.0302 |
|
| 121 |
+
| 0.0389 | 1.38 | 35500 | 0.0303 |
|
| 122 |
+
| 0.0401 | 1.4 | 36000 | 0.0300 |
|
| 123 |
+
| 0.0393 | 1.42 | 36500 | 0.0301 |
|
| 124 |
+
| 0.0399 | 1.44 | 37000 | 0.0297 |
|
| 125 |
+
| 0.0404 | 1.46 | 37500 | 0.0297 |
|
| 126 |
+
| 0.0404 | 1.48 | 38000 | 0.0298 |
|
| 127 |
+
| 0.04 | 1.5 | 38500 | 0.0296 |
|
| 128 |
+
| 0.0403 | 1.52 | 39000 | 0.0296 |
|
| 129 |
+
| 0.04 | 1.54 | 39500 | 0.0294 |
|
| 130 |
+
| 0.0392 | 1.56 | 40000 | 0.0295 |
|
| 131 |
+
| 0.0392 | 1.57 | 40500 | 0.0295 |
|
| 132 |
+
| 0.0388 | 1.59 | 41000 | 0.0296 |
|
| 133 |
+
| 0.0398 | 1.61 | 41500 | 0.0297 |
|
| 134 |
+
| 0.0388 | 1.63 | 42000 | 0.0293 |
|
| 135 |
+
| 0.0385 | 1.65 | 42500 | 0.0294 |
|
| 136 |
+
| 0.0392 | 1.67 | 43000 | 0.0291 |
|
| 137 |
+
| 0.0384 | 1.69 | 43500 | 0.0293 |
|
| 138 |
+
| 0.0384 | 1.71 | 44000 | 0.0294 |
|
| 139 |
+
| 0.0395 | 1.73 | 44500 | 0.0291 |
|
| 140 |
+
| 0.0391 | 1.75 | 45000 | 0.0293 |
|
| 141 |
+
| 0.0375 | 1.77 | 45500 | 0.0293 |
|
| 142 |
+
| 0.0375 | 1.79 | 46000 | 0.0294 |
|
| 143 |
+
| 0.0388 | 1.81 | 46500 | 0.0292 |
|
| 144 |
+
| 0.0392 | 1.83 | 47000 | 0.0293 |
|
| 145 |
+
| 0.0382 | 1.85 | 47500 | 0.0294 |
|
| 146 |
+
| 0.038 | 1.87 | 48000 | 0.0293 |
|
| 147 |
+
| 0.0388 | 1.89 | 48500 | 0.0292 |
|
| 148 |
+
| 0.0383 | 1.91 | 49000 | 0.0290 |
|
| 149 |
+
| 0.0381 | 1.92 | 49500 | 0.0292 |
|
| 150 |
+
| 0.0388 | 1.94 | 50000 | 0.0290 |
|
| 151 |
+
| 0.0378 | 1.96 | 50500 | 0.0289 |
|
| 152 |
+
| 0.0391 | 1.98 | 51000 | 0.0290 |
|
| 153 |
+
| 0.0379 | 2.0 | 51500 | 0.0289 |
|
| 154 |
+
| 0.0364 | 2.02 | 52000 | 0.0289 |
|
| 155 |
+
| 0.0366 | 2.04 | 52500 | 0.0291 |
|
| 156 |
+
| 0.0362 | 2.06 | 53000 | 0.0291 |
|
| 157 |
+
| 0.0359 | 2.08 | 53500 | 0.0289 |
|
| 158 |
+
| 0.0367 | 2.1 | 54000 | 0.0291 |
|
| 159 |
+
| 0.0368 | 2.12 | 54500 | 0.0290 |
|
| 160 |
+
| 0.0359 | 2.14 | 55000 | 0.0288 |
|
| 161 |
+
| 0.0359 | 2.16 | 55500 | 0.0289 |
|
| 162 |
+
| 0.036 | 2.18 | 56000 | 0.0289 |
|
| 163 |
+
| 0.0362 | 2.2 | 56500 | 0.0288 |
|
| 164 |
+
| 0.0359 | 2.22 | 57000 | 0.0287 |
|
| 165 |
+
| 0.0374 | 2.24 | 57500 | 0.0287 |
|
| 166 |
+
| 0.0353 | 2.26 | 58000 | 0.0286 |
|
| 167 |
+
| 0.0351 | 2.27 | 58500 | 0.0287 |
|
| 168 |
+
| 0.0348 | 2.29 | 59000 | 0.0286 |
|
| 169 |
+
| 0.0355 | 2.31 | 59500 | 0.0286 |
|
| 170 |
+
| 0.0362 | 2.33 | 60000 | 0.0287 |
|
| 171 |
+
| 0.0361 | 2.35 | 60500 | 0.0287 |
|
| 172 |
+
| 0.0354 | 2.37 | 61000 | 0.0286 |
|
| 173 |
+
| 0.036 | 2.39 | 61500 | 0.0284 |
|
| 174 |
+
| 0.0341 | 2.41 | 62000 | 0.0285 |
|
| 175 |
+
| 0.0348 | 2.43 | 62500 | 0.0284 |
|
| 176 |
+
| 0.036 | 2.45 | 63000 | 0.0285 |
|
| 177 |
+
| 0.0351 | 2.47 | 63500 | 0.0284 |
|
| 178 |
+
| 0.0354 | 2.49 | 64000 | 0.0284 |
|
| 179 |
+
| 0.0372 | 2.51 | 64500 | 0.0285 |
|
| 180 |
+
| 0.035 | 2.53 | 65000 | 0.0285 |
|
| 181 |
+
| 0.0348 | 2.55 | 65500 | 0.0284 |
|
| 182 |
+
| 0.0353 | 2.57 | 66000 | 0.0283 |
|
| 183 |
+
| 0.0353 | 2.59 | 66500 | 0.0283 |
|
| 184 |
+
| 0.0352 | 2.6 | 67000 | 0.0283 |
|
| 185 |
+
| 0.0357 | 2.62 | 67500 | 0.0283 |
|
| 186 |
+
| 0.035 | 2.64 | 68000 | 0.0283 |
|
| 187 |
+
| 0.0352 | 2.66 | 68500 | 0.0283 |
|
| 188 |
+
| 0.035 | 2.68 | 69000 | 0.0282 |
|
| 189 |
+
| 0.0348 | 2.7 | 69500 | 0.0282 |
|
| 190 |
+
| 0.0344 | 2.72 | 70000 | 0.0281 |
|
| 191 |
+
| 0.0357 | 2.74 | 70500 | 0.0282 |
|
| 192 |
+
| 0.0348 | 2.76 | 71000 | 0.0282 |
|
| 193 |
+
| 0.0349 | 2.78 | 71500 | 0.0281 |
|
| 194 |
+
| 0.0365 | 2.8 | 72000 | 0.0282 |
|
| 195 |
+
| 0.0354 | 2.82 | 72500 | 0.0282 |
|
| 196 |
+
| 0.0359 | 2.84 | 73000 | 0.0281 |
|
| 197 |
+
| 0.0343 | 2.86 | 73500 | 0.0282 |
|
| 198 |
+
| 0.0343 | 2.88 | 74000 | 0.0281 |
|
| 199 |
+
| 0.0346 | 2.9 | 74500 | 0.0282 |
|
| 200 |
+
| 0.0357 | 2.92 | 75000 | 0.0282 |
|
| 201 |
+
| 0.0351 | 2.94 | 75500 | 0.0282 |
|
| 202 |
+
| 0.0355 | 2.95 | 76000 | 0.0282 |
|
| 203 |
+
| 0.0351 | 2.97 | 76500 | 0.0282 |
|
| 204 |
+
| 0.0359 | 2.99 | 77000 | 0.0282 |
|
| 205 |
+
|
| 206 |
+
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- Transformers 4.20.1
|
| 210 |
+
- Pytorch 1.11.0
|
| 211 |
+
- Datasets 2.1.0
|
| 212 |
+
- Tokenizers 0.12.1
|