End of training
Browse files- README.md +102 -117
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -13,8 +13,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
-
-
|
| 17 |
-
-
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -39,125 +39,110 @@ The following hyperparameters were used during training:
|
|
| 39 |
- seed: 42
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
-
-
|
| 43 |
- mixed_precision_training: Native AMP
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
-
| Training Loss | Epoch | Step
|
| 48 |
-
|
| 49 |
-
| 2.3833 | 0.36 | 1000
|
| 50 |
-
| 2.0754 | 0.71 | 2000
|
| 51 |
-
| 1.9838 | 1.07 | 3000
|
| 52 |
-
| 2.0476 | 1.42 | 4000
|
| 53 |
-
| 2.1071 | 1.78 | 5000
|
| 54 |
-
| 1.8743 | 2.13 | 6000
|
| 55 |
-
| 1.8685 | 2.49 | 7000
|
| 56 |
-
| 1.5893 | 2.84 | 8000
|
| 57 |
-
| 1.3116 | 3.2 | 9000
|
| 58 |
-
| 1.3257 | 3.55 | 10000
|
| 59 |
-
| 1.1866 | 3.91 | 11000
|
| 60 |
-
| 1.0506 | 4.27 | 12000
|
| 61 |
-
| 1.0177 | 4.62 | 13000
|
| 62 |
-
| 0.849 | 4.98 | 14000
|
| 63 |
-
| 0.9062 | 5.33 | 15000
|
| 64 |
-
| 0.9613 | 5.69 | 16000
|
| 65 |
-
| 0.698 | 6.04 | 17000
|
| 66 |
-
| 0.5992 | 6.4 | 18000
|
| 67 |
-
| 0.7429 | 6.75 | 19000
|
| 68 |
-
| 0.5958 | 7.11 | 20000
|
| 69 |
-
| 0.5933 | 7.47 | 21000
|
| 70 |
-
| 0.5802 | 7.82 | 22000
|
| 71 |
-
| 0.5026 | 8.18 | 23000
|
| 72 |
-
| 0.528 | 8.53 | 24000
|
| 73 |
-
| 0.5591 | 8.89 | 25000
|
| 74 |
-
| 0.5399 | 9.24 | 26000
|
| 75 |
-
| 0.5875 | 9.6 | 27000
|
| 76 |
-
| 0.5281 | 9.95 | 28000
|
| 77 |
-
| 0.4801 | 10.31 | 29000
|
| 78 |
-
| 0.4978 | 10.66 | 30000
|
| 79 |
-
| 0.2993 | 11.02 | 31000
|
| 80 |
-
| 0.3392 | 11.38 | 32000
|
| 81 |
-
| 0.4248 | 11.73 | 33000
|
| 82 |
-
| 0.2666 | 12.09 | 34000
|
| 83 |
-
| 0.3525 | 12.44 | 35000
|
| 84 |
-
| 0.259 | 12.8 | 36000
|
| 85 |
-
| 0.2105 | 13.15 | 37000
|
| 86 |
-
| 0.2125 | 13.51 | 38000
|
| 87 |
-
| 0.2744 | 13.86 | 39000
|
| 88 |
-
| 0.1858 | 14.22 | 40000
|
| 89 |
-
| 0.1762 | 14.58 | 41000
|
| 90 |
-
| 0.2107 | 14.93 | 42000
|
| 91 |
-
| 0.1403 | 15.29 | 43000
|
| 92 |
-
| 0.124 | 15.64 | 44000
|
| 93 |
-
| 0.1398 | 16.0 | 45000
|
| 94 |
-
| 0.1207 | 16.35 | 46000
|
| 95 |
-
| 0.1422 | 16.71 | 47000
|
| 96 |
-
| 0.0779 | 17.06 | 48000
|
| 97 |
-
| 0.1103 | 17.42 | 49000
|
| 98 |
-
| 0.1011 | 17.77 | 50000
|
| 99 |
-
| 0.0883 | 18.13 | 51000
|
| 100 |
-
| 0.0468 | 18.49 | 52000
|
| 101 |
-
| 0.0782 | 18.84 | 53000
|
| 102 |
-
| 0.0558 | 19.2 | 54000
|
| 103 |
-
| 0.0792 | 19.55 | 55000
|
| 104 |
-
| 0.063 | 19.91 | 56000
|
| 105 |
-
| 0.0464 | 20.26 | 57000
|
| 106 |
-
| 0.058 | 20.62 | 58000
|
| 107 |
-
| 0.062 | 20.97 | 59000
|
| 108 |
-
| 0.038 | 21.33 | 60000
|
| 109 |
-
| 0.0436 | 21.69 | 61000
|
| 110 |
-
| 0.0363 | 22.04 | 62000
|
| 111 |
-
| 0.0406 | 22.4 | 63000
|
| 112 |
-
| 0.0268 | 22.75 | 64000
|
| 113 |
-
| 0.0143 | 23.11 | 65000
|
| 114 |
-
| 0.0274 | 23.46 | 66000
|
| 115 |
-
| 0.0233 | 23.82 | 67000
|
| 116 |
-
| 0.0177 | 24.17 | 68000
|
| 117 |
-
| 0.0237 | 24.53 | 69000
|
| 118 |
-
| 0.0247 | 24.88 | 70000
|
| 119 |
-
| 0.0135 | 25.24 | 71000
|
| 120 |
-
| 0.0169 | 25.6 | 72000
|
| 121 |
-
| 0.0173 | 25.95 | 73000
|
| 122 |
-
| 0.0168 | 26.31 | 74000
|
| 123 |
-
| 0.0179 | 26.66 | 75000
|
| 124 |
-
| 0.0114 | 27.02 | 76000
|
| 125 |
-
| 0.0121 | 27.37 | 77000
|
| 126 |
-
| 0.0145 | 27.73 | 78000
|
| 127 |
-
| 0.0131 | 28.08 | 79000
|
| 128 |
-
| 0.0078 | 28.44 | 80000
|
| 129 |
-
| 0.0129 | 28.79 | 81000
|
| 130 |
-
| 0.0215 | 29.15 | 82000
|
| 131 |
-
| 0.0291 | 29.51 | 83000
|
| 132 |
-
| 0.0233 | 29.86 | 84000
|
| 133 |
-
| 0.0305 | 30.22 | 85000
|
| 134 |
-
| 0.0424 | 30.57 | 86000
|
| 135 |
-
| 0.0346 | 30.93 | 87000
|
| 136 |
-
| 0.0212 | 31.28 | 88000
|
| 137 |
-
| 0.0266 | 31.64 | 89000
|
| 138 |
-
| 0.0255 | 31.99 | 90000
|
| 139 |
-
| 0.019 | 32.35 | 91000
|
| 140 |
-
| 0.0151 | 32.71 | 92000
|
| 141 |
-
| 0.0243 | 33.06 | 93000
|
| 142 |
-
| 0.04 | 33.42 | 94000
|
| 143 |
-
| 0.0307 | 33.77 | 95000
|
| 144 |
-
| 0.0258 | 34.13 | 96000
|
| 145 |
-
| 0.0245 | 34.48 | 97000
|
| 146 |
-
| 0.0245 | 34.84 | 98000 | 0.2532 | 0.8798 |
|
| 147 |
-
| 0.0125 | 35.19 | 99000 | 0.2515 | 0.8305 |
|
| 148 |
-
| 0.0219 | 35.55 | 100000 | 0.2666 | 0.8567 |
|
| 149 |
-
| 0.0094 | 35.9 | 101000 | 0.2642 | 0.8269 |
|
| 150 |
-
| 0.0168 | 36.26 | 102000 | 0.2609 | 0.8392 |
|
| 151 |
-
| 0.0164 | 36.62 | 103000 | 0.2581 | 0.7637 |
|
| 152 |
-
| 0.009 | 36.97 | 104000 | 0.2611 | 0.9231 |
|
| 153 |
-
| 0.0139 | 37.33 | 105000 | 0.2640 | 0.8676 |
|
| 154 |
-
| 0.0145 | 37.68 | 106000 | 0.2537 | 0.8425 |
|
| 155 |
-
| 0.0091 | 38.04 | 107000 | 0.2737 | 0.7867 |
|
| 156 |
-
| 0.0079 | 38.39 | 108000 | 0.8245 | 0.2510 |
|
| 157 |
-
| 0.0029 | 38.75 | 109000 | 0.8862 | 0.2529 |
|
| 158 |
-
| 0.0053 | 39.1 | 110000 | 0.8612 | 0.2513 |
|
| 159 |
-
| 0.0056 | 39.46 | 111000 | 0.8624 | 0.2464 |
|
| 160 |
-
| 0.0046 | 39.82 | 112000 | 0.8902 | 0.2513 |
|
| 161 |
|
| 162 |
|
| 163 |
### Framework versions
|
|
|
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
+
- Cer: 0.2343
|
| 17 |
+
- Loss: 0.6859
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 39 |
- seed: 42
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
+
- training_steps: 97000
|
| 43 |
- mixed_precision_training: Native AMP
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
+
| Training Loss | Epoch | Step | Cer | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:-----:|:------:|:---------------:|
|
| 49 |
+
| 2.3833 | 0.36 | 1000 | 0.8052 | 2.3856 |
|
| 50 |
+
| 2.0754 | 0.71 | 2000 | 0.8113 | 2.2862 |
|
| 51 |
+
| 1.9838 | 1.07 | 3000 | 0.8163 | 2.3398 |
|
| 52 |
+
| 2.0476 | 1.42 | 4000 | 0.8057 | 2.1957 |
|
| 53 |
+
| 2.1071 | 1.78 | 5000 | 0.8085 | 2.2221 |
|
| 54 |
+
| 1.8743 | 2.13 | 6000 | 0.8142 | 2.3726 |
|
| 55 |
+
| 1.8685 | 2.49 | 7000 | 0.7860 | 2.2151 |
|
| 56 |
+
| 1.5893 | 2.84 | 8000 | 0.7558 | 1.9693 |
|
| 57 |
+
| 1.3116 | 3.2 | 9000 | 0.7187 | 1.9843 |
|
| 58 |
+
| 1.3257 | 3.55 | 10000 | 0.6980 | 1.9958 |
|
| 59 |
+
| 1.1866 | 3.91 | 11000 | 0.6662 | 1.7693 |
|
| 60 |
+
| 1.0506 | 4.27 | 12000 | 0.6439 | 1.7593 |
|
| 61 |
+
| 1.0177 | 4.62 | 13000 | 0.6157 | 1.6142 |
|
| 62 |
+
| 0.849 | 4.98 | 14000 | 0.5923 | 1.5052 |
|
| 63 |
+
| 0.9062 | 5.33 | 15000 | 0.5733 | 1.6439 |
|
| 64 |
+
| 0.9613 | 5.69 | 16000 | 0.5635 | 1.2713 |
|
| 65 |
+
| 0.698 | 6.04 | 17000 | 0.5348 | 1.3989 |
|
| 66 |
+
| 0.5992 | 6.4 | 18000 | 0.5197 | 1.5645 |
|
| 67 |
+
| 0.7429 | 6.75 | 19000 | 0.5132 | 1.3758 |
|
| 68 |
+
| 0.5958 | 7.11 | 20000 | 0.4961 | 1.4102 |
|
| 69 |
+
| 0.5933 | 7.47 | 21000 | 0.4845 | 1.2843 |
|
| 70 |
+
| 0.5802 | 7.82 | 22000 | 0.4760 | 1.2866 |
|
| 71 |
+
| 0.5026 | 8.18 | 23000 | 0.4733 | 1.3028 |
|
| 72 |
+
| 0.528 | 8.53 | 24000 | 0.4634 | 1.3796 |
|
| 73 |
+
| 0.5591 | 8.89 | 25000 | 0.4611 | 1.2754 |
|
| 74 |
+
| 0.5399 | 9.24 | 26000 | 0.4645 | 1.3143 |
|
| 75 |
+
| 0.5875 | 9.6 | 27000 | 0.4383 | 1.0949 |
|
| 76 |
+
| 0.5281 | 9.95 | 28000 | 0.4252 | 1.0851 |
|
| 77 |
+
| 0.4801 | 10.31 | 29000 | 0.4065 | 1.1674 |
|
| 78 |
+
| 0.4978 | 10.66 | 30000 | 0.3869 | 1.0382 |
|
| 79 |
+
| 0.2993 | 11.02 | 31000 | 0.3862 | 1.0100 |
|
| 80 |
+
| 0.3392 | 11.38 | 32000 | 0.3657 | 0.9267 |
|
| 81 |
+
| 0.4248 | 11.73 | 33000 | 0.3800 | 0.8588 |
|
| 82 |
+
| 0.2666 | 12.09 | 34000 | 0.3458 | 0.9895 |
|
| 83 |
+
| 0.3525 | 12.44 | 35000 | 0.3649 | 0.8927 |
|
| 84 |
+
| 0.259 | 12.8 | 36000 | 0.3272 | 0.9232 |
|
| 85 |
+
| 0.2105 | 13.15 | 37000 | 0.3358 | 0.7679 |
|
| 86 |
+
| 0.2125 | 13.51 | 38000 | 0.3291 | 0.8509 |
|
| 87 |
+
| 0.2744 | 13.86 | 39000 | 0.3367 | 0.7735 |
|
| 88 |
+
| 0.1858 | 14.22 | 40000 | 0.3005 | 0.7237 |
|
| 89 |
+
| 0.1762 | 14.58 | 41000 | 0.3238 | 0.7320 |
|
| 90 |
+
| 0.2107 | 14.93 | 42000 | 0.3035 | 0.8229 |
|
| 91 |
+
| 0.1403 | 15.29 | 43000 | 0.2981 | 0.8188 |
|
| 92 |
+
| 0.124 | 15.64 | 44000 | 0.3082 | 0.8104 |
|
| 93 |
+
| 0.1398 | 16.0 | 45000 | 0.2967 | 0.8586 |
|
| 94 |
+
| 0.1207 | 16.35 | 46000 | 0.2838 | 0.9125 |
|
| 95 |
+
| 0.1422 | 16.71 | 47000 | 0.3029 | 0.9329 |
|
| 96 |
+
| 0.0779 | 17.06 | 48000 | 0.3022 | 0.7960 |
|
| 97 |
+
| 0.1103 | 17.42 | 49000 | 0.2900 | 0.8678 |
|
| 98 |
+
| 0.1011 | 17.77 | 50000 | 0.2931 | 0.7747 |
|
| 99 |
+
| 0.0883 | 18.13 | 51000 | 0.2722 | 0.7624 |
|
| 100 |
+
| 0.0468 | 18.49 | 52000 | 0.2826 | 0.7573 |
|
| 101 |
+
| 0.0782 | 18.84 | 53000 | 0.2745 | 0.8906 |
|
| 102 |
+
| 0.0558 | 19.2 | 54000 | 0.2756 | 0.7796 |
|
| 103 |
+
| 0.0792 | 19.55 | 55000 | 0.2799 | 0.8554 |
|
| 104 |
+
| 0.063 | 19.91 | 56000 | 0.2916 | 0.8130 |
|
| 105 |
+
| 0.0464 | 20.26 | 57000 | 0.2889 | 0.9519 |
|
| 106 |
+
| 0.058 | 20.62 | 58000 | 0.2719 | 0.7782 |
|
| 107 |
+
| 0.062 | 20.97 | 59000 | 0.2697 | 0.8140 |
|
| 108 |
+
| 0.038 | 21.33 | 60000 | 0.2876 | 0.7488 |
|
| 109 |
+
| 0.0436 | 21.69 | 61000 | 0.2776 | 0.7391 |
|
| 110 |
+
| 0.0363 | 22.04 | 62000 | 0.2730 | 0.8416 |
|
| 111 |
+
| 0.0406 | 22.4 | 63000 | 0.2852 | 0.8974 |
|
| 112 |
+
| 0.0268 | 22.75 | 64000 | 0.2818 | 0.9051 |
|
| 113 |
+
| 0.0143 | 23.11 | 65000 | 0.2733 | 0.8073 |
|
| 114 |
+
| 0.0274 | 23.46 | 66000 | 0.2694 | 0.9573 |
|
| 115 |
+
| 0.0233 | 23.82 | 67000 | 0.2705 | 0.8856 |
|
| 116 |
+
| 0.0177 | 24.17 | 68000 | 0.2701 | 0.8605 |
|
| 117 |
+
| 0.0237 | 24.53 | 69000 | 0.2683 | 0.7962 |
|
| 118 |
+
| 0.0247 | 24.88 | 70000 | 0.2717 | 0.8272 |
|
| 119 |
+
| 0.0135 | 25.24 | 71000 | 0.2737 | 0.8667 |
|
| 120 |
+
| 0.0169 | 25.6 | 72000 | 0.2739 | 0.8405 |
|
| 121 |
+
| 0.0173 | 25.95 | 73000 | 0.2685 | 0.7505 |
|
| 122 |
+
| 0.0168 | 26.31 | 74000 | 0.2682 | 0.9736 |
|
| 123 |
+
| 0.0179 | 26.66 | 75000 | 0.2644 | 0.8753 |
|
| 124 |
+
| 0.0114 | 27.02 | 76000 | 0.2749 | 0.8917 |
|
| 125 |
+
| 0.0121 | 27.37 | 77000 | 0.2733 | 0.9144 |
|
| 126 |
+
| 0.0145 | 27.73 | 78000 | 0.2637 | 0.8889 |
|
| 127 |
+
| 0.0131 | 28.08 | 79000 | 0.2693 | 0.9278 |
|
| 128 |
+
| 0.0078 | 28.44 | 80000 | 0.2669 | 0.9077 |
|
| 129 |
+
| 0.0129 | 28.79 | 81000 | 0.2665 | 0.9218 |
|
| 130 |
+
| 0.0215 | 29.15 | 82000 | 0.2509 | 0.7342 |
|
| 131 |
+
| 0.0291 | 29.51 | 83000 | 0.2573 | 0.7706 |
|
| 132 |
+
| 0.0233 | 29.86 | 84000 | 0.2516 | 0.7602 |
|
| 133 |
+
| 0.0305 | 30.22 | 85000 | 0.2839 | 1.0254 |
|
| 134 |
+
| 0.0424 | 30.57 | 86000 | 0.2725 | 0.8747 |
|
| 135 |
+
| 0.0346 | 30.93 | 87000 | 0.2725 | 0.8864 |
|
| 136 |
+
| 0.0212 | 31.28 | 88000 | 0.2746 | 0.8550 |
|
| 137 |
+
| 0.0266 | 31.64 | 89000 | 0.2834 | 0.8797 |
|
| 138 |
+
| 0.0255 | 31.99 | 90000 | 0.2687 | 0.7178 |
|
| 139 |
+
| 0.019 | 32.35 | 91000 | 0.2744 | 0.8784 |
|
| 140 |
+
| 0.0151 | 32.71 | 92000 | 0.2494 | 0.6553 |
|
| 141 |
+
| 0.0243 | 33.06 | 93000 | 0.2531 | 0.7540 |
|
| 142 |
+
| 0.04 | 33.42 | 94000 | 0.2526 | 0.8605 |
|
| 143 |
+
| 0.0307 | 33.77 | 95000 | 0.2597 | 0.8507 |
|
| 144 |
+
| 0.0258 | 34.13 | 96000 | 0.2714 | 0.7760 |
|
| 145 |
+
| 0.0245 | 34.48 | 97000 | 0.2343 | 0.6859 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 146 |
|
| 147 |
|
| 148 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 963217272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f44f233d120effa729fc1001311411e659cf113f1af6ea727a2fa8a5bdb5cd0
|
| 3 |
size 963217272
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a46184b5fd59043f047ce1d53a383470deb4105acdc55926f6534d871c598109
|
| 3 |
size 4728
|