Upload 14 files
Browse files- README.md +193 -105
- all_results.json +10 -10
- eval_results.json +5 -5
- pytorch_model.bin +1 -1
- train_results.json +5 -5
- trainer_state.json +0 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -3,19 +3,17 @@ license: apache-2.0
|
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
model-index:
|
| 6 |
-
- name: bart-base-spelling-nl
|
| 7 |
results: []
|
| 8 |
---
|
| 9 |
|
| 10 |
-
# bart-base-spelling-nl
|
| 11 |
-
|
| 12 |
This model is a Dutch fine-tuned version of
|
| 13 |
[facebook/bart-base](https://huggingface.co/facebook/bart-base).
|
| 14 |
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
|
| 17 |
-
- Loss: 0.
|
| 18 |
-
- Cer: 0.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -23,8 +21,7 @@ This is a text-to-text fine-tuned version of
|
|
| 23 |
[facebook/bart-base](https://huggingface.co/facebook/bart-base)
|
| 24 |
trained on spelling correction. It leans on the excellent work by
|
| 25 |
Oliver Guhr ([github](https://github.com/oliverguhr/spelling),
|
| 26 |
-
[huggingface](https://huggingface.co/oliverguhr/spelling-correction-english-base)). Training
|
| 27 |
-
was performed on an AWS EC2 instance (g5.xlarge) on a single GPU.
|
| 28 |
|
| 29 |
## Intended uses & limitations
|
| 30 |
|
|
@@ -38,9 +35,9 @@ The model was trained on a Dutch dataset composed of 1,500,000 lines of
|
|
| 38 |
text from three public Dutch sources, downloaded from the [Opus
|
| 39 |
corpus](https://opus.nlpl.eu/):
|
| 40 |
|
| 41 |
-
- nl-europarlv7.100k.txt (
|
| 42 |
-
- nl-opensubtitles2016.100k.txt (
|
| 43 |
-
- nl-wikipedia.100k.txt (
|
| 44 |
|
| 45 |
## Training procedure
|
| 46 |
|
|
@@ -59,101 +56,192 @@ The following hyperparameters were used during training:
|
|
| 59 |
|
| 60 |
### Training results
|
| 61 |
|
| 62 |
-
| Training Loss | Epoch | Step
|
| 63 |
-
|
| 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 |
-
| 0.
|
| 149 |
-
| 0.
|
| 150 |
-
| 0.
|
| 151 |
-
| 0.
|
| 152 |
-
| 0.
|
| 153 |
-
| 0.
|
| 154 |
-
| 0.
|
| 155 |
-
| 0.
|
| 156 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 157 |
|
| 158 |
|
| 159 |
### Framework versions
|
|
|
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
model-index:
|
| 6 |
+
- name: bart-base-spelling-nl-1m
|
| 7 |
results: []
|
| 8 |
---
|
| 9 |
|
|
|
|
|
|
|
| 10 |
This model is a Dutch fine-tuned version of
|
| 11 |
[facebook/bart-base](https://huggingface.co/facebook/bart-base).
|
| 12 |
|
| 13 |
It achieves the following results on the evaluation set:
|
| 14 |
|
| 15 |
+
- Loss: 0.0221
|
| 16 |
+
- Cer: 0.0145
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 21 |
[facebook/bart-base](https://huggingface.co/facebook/bart-base)
|
| 22 |
trained on spelling correction. It leans on the excellent work by
|
| 23 |
Oliver Guhr ([github](https://github.com/oliverguhr/spelling),
|
| 24 |
+
[huggingface](https://huggingface.co/oliverguhr/spelling-correction-english-base)). Training was performed on an AWS EC2 instance (g5.xlarge) on a single GPU.
|
|
|
|
| 25 |
|
| 26 |
## Intended uses & limitations
|
| 27 |
|
|
|
|
| 35 |
text from three public Dutch sources, downloaded from the [Opus
|
| 36 |
corpus](https://opus.nlpl.eu/):
|
| 37 |
|
| 38 |
+
- nl-europarlv7.100k.txt (1,000,000 lines)
|
| 39 |
+
- nl-opensubtitles2016.100k.txt (1,000,000 lines)
|
| 40 |
+
- nl-wikipedia.100k.txt (964,203 lines)
|
| 41 |
|
| 42 |
## Training procedure
|
| 43 |
|
|
|
|
| 56 |
|
| 57 |
### Training results
|
| 58 |
|
| 59 |
+
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
| 60 |
+
|:-------------:|:-----:|:------:|:---------------:|:------:|
|
| 61 |
+
| 0.2824 | 0.01 | 1000 | 0.2129 | 0.9219 |
|
| 62 |
+
| 0.1971 | 0.02 | 2000 | 0.1600 | 0.9217 |
|
| 63 |
+
| 0.171 | 0.03 | 3000 | 0.1273 | 0.9217 |
|
| 64 |
+
| 0.1586 | 0.04 | 4000 | 0.1110 | 0.9216 |
|
| 65 |
+
| 0.1288 | 0.05 | 5000 | 0.0991 | 0.9214 |
|
| 66 |
+
| 0.1338 | 0.06 | 6000 | 0.0910 | 0.9215 |
|
| 67 |
+
| 0.1279 | 0.08 | 7000 | 0.0831 | 0.9215 |
|
| 68 |
+
| 0.1147 | 0.09 | 8000 | 0.0789 | 0.9215 |
|
| 69 |
+
| 0.1091 | 0.1 | 9000 | 0.0769 | 0.9216 |
|
| 70 |
+
| 0.0935 | 0.11 | 10000 | 0.0700 | 0.9214 |
|
| 71 |
+
| 0.0963 | 0.12 | 11000 | 0.0678 | 0.9215 |
|
| 72 |
+
| 0.0969 | 0.13 | 12000 | 0.0654 | 0.9214 |
|
| 73 |
+
| 0.0957 | 0.14 | 13000 | 0.0627 | 0.9215 |
|
| 74 |
+
| 0.0886 | 0.15 | 14000 | 0.0644 | 0.9215 |
|
| 75 |
+
| 0.0911 | 0.16 | 15000 | 0.0604 | 0.9215 |
|
| 76 |
+
| 0.0955 | 0.17 | 16000 | 0.0595 | 0.9215 |
|
| 77 |
+
| 0.0875 | 0.18 | 17000 | 0.0587 | 0.9213 |
|
| 78 |
+
| 0.0879 | 0.19 | 18000 | 0.0576 | 0.9214 |
|
| 79 |
+
| 0.079 | 0.21 | 19000 | 0.0550 | 0.9213 |
|
| 80 |
+
| 0.0808 | 0.22 | 20000 | 0.0536 | 0.9215 |
|
| 81 |
+
| 0.0684 | 0.23 | 21000 | 0.0536 | 0.9214 |
|
| 82 |
+
| 0.0789 | 0.24 | 22000 | 0.0530 | 0.9214 |
|
| 83 |
+
| 0.088 | 0.25 | 23000 | 0.0524 | 0.9215 |
|
| 84 |
+
| 0.076 | 0.26 | 24000 | 0.0519 | 0.9214 |
|
| 85 |
+
| 0.0714 | 0.27 | 25000 | 0.0506 | 0.9213 |
|
| 86 |
+
| 0.0664 | 0.28 | 26000 | 0.0495 | 0.9213 |
|
| 87 |
+
| 0.0791 | 0.29 | 27000 | 0.0492 | 0.9215 |
|
| 88 |
+
| 0.0702 | 0.3 | 28000 | 0.0485 | 0.9215 |
|
| 89 |
+
| 0.0709 | 0.31 | 29000 | 0.0493 | 0.9213 |
|
| 90 |
+
| 0.0676 | 0.32 | 30000 | 0.0480 | 0.9214 |
|
| 91 |
+
| 0.0692 | 0.34 | 31000 | 0.0468 | 0.9215 |
|
| 92 |
+
| 0.0633 | 0.35 | 32000 | 0.0473 | 0.9213 |
|
| 93 |
+
| 0.0732 | 0.36 | 33000 | 0.0455 | 0.9213 |
|
| 94 |
+
| 0.0809 | 0.37 | 34000 | 0.0455 | 0.9214 |
|
| 95 |
+
| 0.0562 | 0.38 | 35000 | 0.0451 | 0.9214 |
|
| 96 |
+
| 0.0715 | 0.39 | 36000 | 0.0440 | 0.9214 |
|
| 97 |
+
| 0.0596 | 0.4 | 37000 | 0.0441 | 0.9214 |
|
| 98 |
+
| 0.0534 | 0.41 | 38000 | 0.0430 | 0.9213 |
|
| 99 |
+
| 0.0657 | 0.42 | 39000 | 0.0427 | 0.9214 |
|
| 100 |
+
| 0.0643 | 0.43 | 40000 | 0.0441 | 0.9212 |
|
| 101 |
+
| 0.0579 | 0.44 | 41000 | 0.0414 | 0.9213 |
|
| 102 |
+
| 0.0695 | 0.45 | 42000 | 0.0430 | 0.9212 |
|
| 103 |
+
| 0.0566 | 0.47 | 43000 | 0.0413 | 0.9212 |
|
| 104 |
+
| 0.0646 | 0.48 | 44000 | 0.0415 | 0.9213 |
|
| 105 |
+
| 0.0573 | 0.49 | 45000 | 0.0410 | 0.9212 |
|
| 106 |
+
| 0.0568 | 0.5 | 46000 | 0.0406 | 0.9213 |
|
| 107 |
+
| 0.065 | 0.51 | 47000 | 0.0405 | 0.9213 |
|
| 108 |
+
| 0.063 | 0.52 | 48000 | 0.0396 | 0.9213 |
|
| 109 |
+
| 0.0654 | 0.53 | 49000 | 0.0397 | 0.9213 |
|
| 110 |
+
| 0.0506 | 0.54 | 50000 | 0.0391 | 0.9212 |
|
| 111 |
+
| 0.0573 | 0.55 | 51000 | 0.0382 | 0.9213 |
|
| 112 |
+
| 0.0569 | 0.56 | 52000 | 0.0381 | 0.9214 |
|
| 113 |
+
| 0.0597 | 0.57 | 53000 | 0.0381 | 0.9212 |
|
| 114 |
+
| 0.0543 | 0.58 | 54000 | 0.0374 | 0.9213 |
|
| 115 |
+
| 0.057 | 0.59 | 55000 | 0.0381 | 0.9213 |
|
| 116 |
+
| 0.058 | 0.61 | 56000 | 0.0380 | 0.9212 |
|
| 117 |
+
| 0.0481 | 0.62 | 57000 | 0.0366 | 0.9213 |
|
| 118 |
+
| 0.0581 | 0.63 | 58000 | 0.0367 | 0.9212 |
|
| 119 |
+
| 0.0521 | 0.64 | 59000 | 0.0363 | 0.9213 |
|
| 120 |
+
| 0.0543 | 0.65 | 60000 | 0.0358 | 0.9212 |
|
| 121 |
+
| 0.0594 | 0.66 | 61000 | 0.0359 | 0.9214 |
|
| 122 |
+
| 0.0479 | 0.67 | 62000 | 0.0354 | 0.9212 |
|
| 123 |
+
| 0.0512 | 0.68 | 63000 | 0.0357 | 0.9211 |
|
| 124 |
+
| 0.0488 | 0.69 | 64000 | 0.0341 | 0.9213 |
|
| 125 |
+
| 0.0485 | 0.7 | 65000 | 0.0346 | 0.9213 |
|
| 126 |
+
| 0.052 | 0.71 | 66000 | 0.0343 | 0.9213 |
|
| 127 |
+
| 0.0427 | 0.72 | 67000 | 0.0341 | 0.9212 |
|
| 128 |
+
| 0.0502 | 0.74 | 68000 | 0.0343 | 0.9211 |
|
| 129 |
+
| 0.0434 | 0.75 | 69000 | 0.0337 | 0.9213 |
|
| 130 |
+
| 0.0579 | 0.76 | 70000 | 0.0337 | 0.9213 |
|
| 131 |
+
| 0.0534 | 0.77 | 71000 | 0.0330 | 0.9212 |
|
| 132 |
+
| 0.0437 | 0.78 | 72000 | 0.0334 | 0.9212 |
|
| 133 |
+
| 0.05 | 0.79 | 73000 | 0.0332 | 0.9213 |
|
| 134 |
+
| 0.043 | 0.8 | 74000 | 0.0329 | 0.9212 |
|
| 135 |
+
| 0.0554 | 0.81 | 75000 | 0.0323 | 0.9212 |
|
| 136 |
+
| 0.0418 | 0.82 | 76000 | 0.0326 | 0.9212 |
|
| 137 |
+
| 0.0461 | 0.83 | 77000 | 0.0326 | 0.9212 |
|
| 138 |
+
| 0.0435 | 0.84 | 78000 | 0.0319 | 0.9212 |
|
| 139 |
+
| 0.0453 | 0.85 | 79000 | 0.0317 | 0.9212 |
|
| 140 |
+
| 0.0434 | 0.87 | 80000 | 0.0318 | 0.9212 |
|
| 141 |
+
| 0.0466 | 0.88 | 81000 | 0.0321 | 0.9212 |
|
| 142 |
+
| 0.0461 | 0.89 | 82000 | 0.0316 | 0.9212 |
|
| 143 |
+
| 0.0381 | 0.9 | 83000 | 0.0311 | 0.9213 |
|
| 144 |
+
| 0.0455 | 0.91 | 84000 | 0.0306 | 0.9212 |
|
| 145 |
+
| 0.0446 | 0.92 | 85000 | 0.0315 | 0.9212 |
|
| 146 |
+
| 0.0532 | 0.93 | 86000 | 0.0305 | 0.9212 |
|
| 147 |
+
| 0.052 | 0.94 | 87000 | 0.0305 | 0.9212 |
|
| 148 |
+
| 0.0353 | 0.95 | 88000 | 0.0305 | 0.9211 |
|
| 149 |
+
| 0.0469 | 0.96 | 89000 | 0.0304 | 0.9212 |
|
| 150 |
+
| 0.0387 | 0.97 | 90000 | 0.0303 | 0.9212 |
|
| 151 |
+
| 0.0478 | 0.98 | 91000 | 0.0302 | 0.9212 |
|
| 152 |
+
| 0.0395 | 1.0 | 92000 | 0.0299 | 0.9212 |
|
| 153 |
+
| 0.0387 | 1.01 | 93000 | 0.0290 | 0.9212 |
|
| 154 |
+
| 0.0356 | 1.02 | 94000 | 0.0287 | 0.9212 |
|
| 155 |
+
| 0.0381 | 1.03 | 95000 | 0.0295 | 0.9212 |
|
| 156 |
+
| 0.0386 | 1.04 | 96000 | 0.0284 | 0.9213 |
|
| 157 |
+
| 0.038 | 1.05 | 97000 | 0.0293 | 0.9212 |
|
| 158 |
+
| 0.0346 | 1.06 | 98000 | 0.0284 | 0.9212 |
|
| 159 |
+
| 0.0357 | 1.07 | 99000 | 0.0285 | 0.9212 |
|
| 160 |
+
| 0.0446 | 1.08 | 100000 | 0.0287 | 0.9211 |
|
| 161 |
+
| 0.0424 | 1.09 | 101000 | 0.0284 | 0.9213 |
|
| 162 |
+
| 0.0357 | 1.1 | 102000 | 0.0282 | 0.9211 |
|
| 163 |
+
| 0.0413 | 1.11 | 103000 | 0.0282 | 0.9211 |
|
| 164 |
+
| 0.0348 | 1.12 | 104000 | 0.0279 | 0.9212 |
|
| 165 |
+
| 0.0363 | 1.14 | 105000 | 0.0279 | 0.9212 |
|
| 166 |
+
| 0.0329 | 1.15 | 106000 | 0.0282 | 0.9211 |
|
| 167 |
+
| 0.0438 | 1.16 | 107000 | 0.0279 | 0.9212 |
|
| 168 |
+
| 0.037 | 1.17 | 108000 | 0.0274 | 0.9212 |
|
| 169 |
+
| 0.0311 | 1.18 | 109000 | 0.0278 | 0.9212 |
|
| 170 |
+
| 0.0297 | 1.19 | 110000 | 0.0275 | 0.9212 |
|
| 171 |
+
| 0.0323 | 1.2 | 111000 | 0.0271 | 0.9212 |
|
| 172 |
+
| 0.0387 | 1.21 | 112000 | 0.0275 | 0.9212 |
|
| 173 |
+
| 0.0366 | 1.22 | 113000 | 0.0269 | 0.9211 |
|
| 174 |
+
| 0.0345 | 1.23 | 114000 | 0.0269 | 0.9211 |
|
| 175 |
+
| 0.0389 | 1.24 | 115000 | 0.0261 | 0.9211 |
|
| 176 |
+
| 0.0381 | 1.25 | 116000 | 0.0265 | 0.9211 |
|
| 177 |
+
| 0.0324 | 1.27 | 117000 | 0.0265 | 0.9211 |
|
| 178 |
+
| 0.0345 | 1.28 | 118000 | 0.0260 | 0.9212 |
|
| 179 |
+
| 0.032 | 1.29 | 119000 | 0.0260 | 0.9211 |
|
| 180 |
+
| 0.0359 | 1.3 | 120000 | 0.0259 | 0.9211 |
|
| 181 |
+
| 0.0347 | 1.31 | 121000 | 0.0259 | 0.9212 |
|
| 182 |
+
| 0.0334 | 1.32 | 122000 | 0.0253 | 0.9211 |
|
| 183 |
+
| 0.0297 | 1.33 | 123000 | 0.0260 | 0.9210 |
|
| 184 |
+
| 0.0333 | 1.34 | 124000 | 0.0251 | 0.9212 |
|
| 185 |
+
| 0.0303 | 1.35 | 125000 | 0.0254 | 0.9211 |
|
| 186 |
+
| 0.0292 | 1.36 | 126000 | 0.0250 | 0.9211 |
|
| 187 |
+
| 0.0318 | 1.37 | 127000 | 0.0250 | 0.9212 |
|
| 188 |
+
| 0.0284 | 1.38 | 128000 | 0.0250 | 0.9211 |
|
| 189 |
+
| 0.0311 | 1.4 | 129000 | 0.0248 | 0.9211 |
|
| 190 |
+
| 0.0323 | 1.41 | 130000 | 0.0248 | 0.9211 |
|
| 191 |
+
| 0.0253 | 1.42 | 131000 | 0.0244 | 0.9211 |
|
| 192 |
+
| 0.0287 | 1.43 | 132000 | 0.0246 | 0.9211 |
|
| 193 |
+
| 0.0351 | 1.44 | 133000 | 0.0240 | 0.9212 |
|
| 194 |
+
| 0.0363 | 1.45 | 134000 | 0.0238 | 0.9211 |
|
| 195 |
+
| 0.0264 | 1.46 | 135000 | 0.0240 | 0.9211 |
|
| 196 |
+
| 0.0304 | 1.47 | 136000 | 0.0242 | 0.9211 |
|
| 197 |
+
| 0.0325 | 1.48 | 137000 | 0.0236 | 0.9212 |
|
| 198 |
+
| 0.033 | 1.49 | 138000 | 0.0239 | 0.9211 |
|
| 199 |
+
| 0.03 | 1.5 | 139000 | 0.0236 | 0.9211 |
|
| 200 |
+
| 0.0256 | 1.51 | 140000 | 0.0235 | 0.9211 |
|
| 201 |
+
| 0.0312 | 1.53 | 141000 | 0.0237 | 0.9211 |
|
| 202 |
+
| 0.0302 | 1.54 | 142000 | 0.0237 | 0.9211 |
|
| 203 |
+
| 0.0227 | 1.55 | 143000 | 0.0232 | 0.9212 |
|
| 204 |
+
| 0.0261 | 1.56 | 144000 | 0.0232 | 0.9211 |
|
| 205 |
+
| 0.0269 | 1.57 | 145000 | 0.0227 | 0.9211 |
|
| 206 |
+
| 0.0312 | 1.58 | 146000 | 0.0228 | 0.9211 |
|
| 207 |
+
| 0.0298 | 1.59 | 147000 | 0.0231 | 0.9211 |
|
| 208 |
+
| 0.0281 | 1.6 | 148000 | 0.0226 | 0.9212 |
|
| 209 |
+
| 0.029 | 1.61 | 149000 | 0.0227 | 0.9211 |
|
| 210 |
+
| 0.0324 | 1.62 | 150000 | 0.0225 | 0.9211 |
|
| 211 |
+
| 0.0251 | 1.63 | 151000 | 0.0223 | 0.9212 |
|
| 212 |
+
| 0.0278 | 1.64 | 152000 | 0.0223 | 0.9211 |
|
| 213 |
+
| 0.0284 | 1.65 | 153000 | 0.0224 | 0.9210 |
|
| 214 |
+
| 0.0254 | 1.67 | 154000 | 0.0220 | 0.9211 |
|
| 215 |
+
| 0.028 | 1.68 | 155000 | 0.0221 | 0.9210 |
|
| 216 |
+
| 0.0247 | 1.69 | 156000 | 0.0222 | 0.9211 |
|
| 217 |
+
| 0.0295 | 1.7 | 157000 | 0.0218 | 0.9211 |
|
| 218 |
+
| 0.0283 | 1.71 | 158000 | 0.0216 | 0.9211 |
|
| 219 |
+
| 0.0245 | 1.72 | 159000 | 0.0218 | 0.9211 |
|
| 220 |
+
| 0.0249 | 1.73 | 160000 | 0.0216 | 0.9211 |
|
| 221 |
+
| 0.0264 | 1.74 | 161000 | 0.0215 | 0.9211 |
|
| 222 |
+
| 0.0264 | 1.75 | 162000 | 0.0213 | 0.9211 |
|
| 223 |
+
| 0.0306 | 1.76 | 163000 | 0.0212 | 0.9211 |
|
| 224 |
+
| 0.0242 | 1.77 | 164000 | 0.0212 | 0.9212 |
|
| 225 |
+
| 0.0247 | 1.78 | 165000 | 0.0211 | 0.9211 |
|
| 226 |
+
| 0.0227 | 1.8 | 166000 | 0.0211 | 0.9210 |
|
| 227 |
+
| 0.0252 | 1.81 | 167000 | 0.0211 | 0.9211 |
|
| 228 |
+
| 0.0269 | 1.82 | 168000 | 0.0208 | 0.9211 |
|
| 229 |
+
| 0.0256 | 1.83 | 169000 | 0.0209 | 0.9211 |
|
| 230 |
+
| 0.0234 | 1.84 | 170000 | 0.0207 | 0.9211 |
|
| 231 |
+
| 0.0258 | 1.85 | 171000 | 0.0207 | 0.9211 |
|
| 232 |
+
| 0.0282 | 1.86 | 172000 | 0.0205 | 0.9210 |
|
| 233 |
+
| 0.0282 | 1.87 | 173000 | 0.0206 | 0.9210 |
|
| 234 |
+
| 0.0234 | 1.88 | 174000 | 0.0205 | 0.9211 |
|
| 235 |
+
| 0.0222 | 1.89 | 175000 | 0.0204 | 0.9211 |
|
| 236 |
+
| 0.0237 | 1.9 | 176000 | 0.0203 | 0.9211 |
|
| 237 |
+
| 0.0299 | 1.91 | 177000 | 0.0203 | 0.9211 |
|
| 238 |
+
| 0.0246 | 1.93 | 178000 | 0.0203 | 0.9211 |
|
| 239 |
+
| 0.0227 | 1.94 | 179000 | 0.0204 | 0.9211 |
|
| 240 |
+
| 0.0253 | 1.95 | 180000 | 0.0202 | 0.9211 |
|
| 241 |
+
| 0.0197 | 1.96 | 181000 | 0.0202 | 0.9211 |
|
| 242 |
+
| 0.0231 | 1.97 | 182000 | 0.0200 | 0.9211 |
|
| 243 |
+
| 0.0244 | 1.98 | 183000 | 0.0201 | 0.9211 |
|
| 244 |
+
| 0.0259 | 1.99 | 184000 | 0.0200 | 0.9211 |
|
| 245 |
|
| 246 |
|
| 247 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
-
"eval_cer": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
"eval_samples": 2000,
|
| 7 |
-
"eval_samples_per_second": 1.
|
| 8 |
-
"eval_steps_per_second": 0.
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples":
|
| 12 |
-
"train_samples_per_second": 28.
|
| 13 |
-
"train_steps_per_second": 0.
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
+
"eval_cer": 0.014513880422164147,
|
| 4 |
+
"eval_loss": 0.02208337001502514,
|
| 5 |
+
"eval_runtime": 1920.0198,
|
| 6 |
"eval_samples": 2000,
|
| 7 |
+
"eval_samples_per_second": 1.042,
|
| 8 |
+
"eval_steps_per_second": 0.26,
|
| 9 |
+
"train_loss": 0.05150384478483596,
|
| 10 |
+
"train_runtime": 204639.736,
|
| 11 |
+
"train_samples": 2958558,
|
| 12 |
+
"train_samples_per_second": 28.915,
|
| 13 |
+
"train_steps_per_second": 0.904
|
| 14 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
-
"eval_cer": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
"eval_samples": 2000,
|
| 7 |
-
"eval_samples_per_second": 1.
|
| 8 |
-
"eval_steps_per_second": 0.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
+
"eval_cer": 0.014513880422164147,
|
| 4 |
+
"eval_loss": 0.02208337001502514,
|
| 5 |
+
"eval_runtime": 1920.0198,
|
| 6 |
"eval_samples": 2000,
|
| 7 |
+
"eval_samples_per_second": 1.042,
|
| 8 |
+
"eval_steps_per_second": 0.26
|
| 9 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 557971229
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb2eb6470de7d689abff2f06ce460c17539f1dcffe05da3ff6a91b4cf6c353dd
|
| 3 |
size 557971229
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second": 28.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.05150384478483596,
|
| 4 |
+
"train_runtime": 204639.736,
|
| 5 |
+
"train_samples": 2958558,
|
| 6 |
+
"train_samples_per_second": 28.915,
|
| 7 |
+
"train_steps_per_second": 0.904
|
| 8 |
}
|
trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3707
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcaa8fb3e6403c3f1d958c15d97817380cca47833d439484dd2f38a0a53f4340
|
| 3 |
size 3707
|