XMLRobertaLexical-finetuned_70KURL_new
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5617
- Accuracy: 0.9141
- F1: 0.9143
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
No log | 0.2326 | 200 | 0.4085 | 0.8043 | 0.7840 |
No log | 0.4651 | 400 | 0.3684 | 0.8347 | 0.8303 |
No log | 0.6977 | 600 | 0.2978 | 0.8719 | 0.8700 |
No log | 0.9302 | 800 | 0.2840 | 0.8690 | 0.8724 |
0.3962 | 1.1628 | 1000 | 0.2713 | 0.8852 | 0.8860 |
0.3962 | 1.3953 | 1200 | 0.2466 | 0.8955 | 0.8956 |
0.3962 | 1.6279 | 1400 | 0.2378 | 0.8941 | 0.8957 |
0.3962 | 1.8605 | 1600 | 0.2499 | 0.8908 | 0.8931 |
0.2614 | 2.0930 | 1800 | 0.2351 | 0.9040 | 0.9037 |
0.2614 | 2.3256 | 2000 | 0.2290 | 0.9035 | 0.9048 |
0.2614 | 2.5581 | 2200 | 0.2413 | 0.9036 | 0.9041 |
0.2614 | 2.7907 | 2400 | 0.2292 | 0.9055 | 0.9064 |
0.2152 | 3.0233 | 2600 | 0.2289 | 0.9077 | 0.9086 |
0.2152 | 3.2558 | 2800 | 0.2379 | 0.9030 | 0.9022 |
0.2152 | 3.4884 | 3000 | 0.2382 | 0.9067 | 0.9060 |
0.2152 | 3.7209 | 3200 | 0.2212 | 0.9109 | 0.9120 |
0.2152 | 3.9535 | 3400 | 0.2378 | 0.9072 | 0.9089 |
0.1838 | 4.1860 | 3600 | 0.2234 | 0.9110 | 0.9119 |
0.1838 | 4.4186 | 3800 | 0.2306 | 0.9129 | 0.9128 |
0.1838 | 4.6512 | 4000 | 0.2288 | 0.9158 | 0.9154 |
0.1838 | 4.8837 | 4200 | 0.2524 | 0.9121 | 0.9121 |
0.1599 | 5.1163 | 4400 | 0.2393 | 0.9108 | 0.9116 |
0.1599 | 5.3488 | 4600 | 0.2503 | 0.9133 | 0.9128 |
0.1599 | 5.5814 | 4800 | 0.2498 | 0.9143 | 0.9150 |
0.1599 | 5.8140 | 5000 | 0.2561 | 0.9135 | 0.9142 |
0.1359 | 6.0465 | 5200 | 0.2679 | 0.9138 | 0.9141 |
0.1359 | 6.2791 | 5400 | 0.2900 | 0.9145 | 0.9148 |
0.1359 | 6.5116 | 5600 | 0.2727 | 0.9133 | 0.9135 |
0.1359 | 6.7442 | 5800 | 0.2678 | 0.9133 | 0.9132 |
0.1359 | 6.9767 | 6000 | 0.2674 | 0.9150 | 0.9150 |
0.1156 | 7.2093 | 6200 | 0.2951 | 0.9120 | 0.9118 |
0.1156 | 7.4419 | 6400 | 0.3056 | 0.9117 | 0.9126 |
0.1156 | 7.6744 | 6600 | 0.2621 | 0.9143 | 0.9148 |
0.1156 | 7.9070 | 6800 | 0.2925 | 0.9141 | 0.9142 |
0.1014 | 8.1395 | 7000 | 0.3045 | 0.9132 | 0.9139 |
0.1014 | 8.3721 | 7200 | 0.3095 | 0.9126 | 0.9133 |
0.1014 | 8.6047 | 7400 | 0.3183 | 0.9124 | 0.9119 |
0.1014 | 8.8372 | 7600 | 0.3007 | 0.9150 | 0.9146 |
0.0884 | 9.0698 | 7800 | 0.4062 | 0.9130 | 0.9136 |
0.0884 | 9.3023 | 8000 | 0.3673 | 0.9147 | 0.9150 |
0.0884 | 9.5349 | 8200 | 0.3815 | 0.9146 | 0.9147 |
0.0884 | 9.7674 | 8400 | 0.3336 | 0.9149 | 0.9158 |
0.0758 | 10.0 | 8600 | 0.3665 | 0.9137 | 0.9146 |
0.0758 | 10.2326 | 8800 | 0.3845 | 0.9106 | 0.9107 |
0.0758 | 10.4651 | 9000 | 0.3670 | 0.9132 | 0.9130 |
0.0758 | 10.6977 | 9200 | 0.3672 | 0.9124 | 0.9118 |
0.0758 | 10.9302 | 9400 | 0.3840 | 0.9140 | 0.9144 |
0.0661 | 11.1628 | 9600 | 0.4447 | 0.9127 | 0.9131 |
0.0661 | 11.3953 | 9800 | 0.4561 | 0.9137 | 0.9139 |
0.0661 | 11.6279 | 10000 | 0.4257 | 0.9118 | 0.9120 |
0.0661 | 11.8605 | 10200 | 0.3767 | 0.9118 | 0.9125 |
0.0585 | 12.0930 | 10400 | 0.4985 | 0.9127 | 0.9123 |
0.0585 | 12.3256 | 10600 | 0.4604 | 0.9110 | 0.9117 |
0.0585 | 12.5581 | 10800 | 0.4190 | 0.9131 | 0.9137 |
0.0585 | 12.7907 | 11000 | 0.4423 | 0.9147 | 0.9149 |
0.052 | 13.0233 | 11200 | 0.4110 | 0.9160 | 0.9164 |
0.052 | 13.2558 | 11400 | 0.4618 | 0.9120 | 0.9118 |
0.052 | 13.4884 | 11600 | 0.4913 | 0.9133 | 0.9140 |
0.052 | 13.7209 | 11800 | 0.4718 | 0.9141 | 0.9141 |
0.052 | 13.9535 | 12000 | 0.4985 | 0.9127 | 0.9117 |
0.0462 | 14.1860 | 12200 | 0.4876 | 0.9128 | 0.9129 |
0.0462 | 14.4186 | 12400 | 0.4797 | 0.9106 | 0.9108 |
0.0462 | 14.6512 | 12600 | 0.5125 | 0.9140 | 0.9143 |
0.0462 | 14.8837 | 12800 | 0.4633 | 0.9130 | 0.9129 |
0.0441 | 15.1163 | 13000 | 0.5142 | 0.9133 | 0.9134 |
0.0441 | 15.3488 | 13200 | 0.5444 | 0.9124 | 0.9124 |
0.0441 | 15.5814 | 13400 | 0.4726 | 0.9126 | 0.9125 |
0.0441 | 15.8140 | 13600 | 0.4834 | 0.9126 | 0.9129 |
0.0391 | 16.0465 | 13800 | 0.5001 | 0.9138 | 0.9143 |
0.0391 | 16.2791 | 14000 | 0.5298 | 0.9138 | 0.9138 |
0.0391 | 16.5116 | 14200 | 0.5190 | 0.9147 | 0.9149 |
0.0391 | 16.7442 | 14400 | 0.5098 | 0.9159 | 0.9160 |
0.0391 | 16.9767 | 14600 | 0.5018 | 0.9151 | 0.9150 |
0.0369 | 17.2093 | 14800 | 0.5342 | 0.9128 | 0.9128 |
0.0369 | 17.4419 | 15000 | 0.5672 | 0.9140 | 0.9141 |
0.0369 | 17.6744 | 15200 | 0.5524 | 0.9144 | 0.9142 |
0.0369 | 17.9070 | 15400 | 0.5385 | 0.9140 | 0.9135 |
0.0328 | 18.1395 | 15600 | 0.5498 | 0.9137 | 0.9139 |
0.0328 | 18.3721 | 15800 | 0.5581 | 0.9153 | 0.9155 |
0.0328 | 18.6047 | 16000 | 0.5486 | 0.9135 | 0.9138 |
0.0328 | 18.8372 | 16200 | 0.5416 | 0.9142 | 0.9142 |
0.0312 | 19.0698 | 16400 | 0.5535 | 0.9151 | 0.9149 |
0.0312 | 19.3023 | 16600 | 0.5622 | 0.9139 | 0.9140 |
0.0312 | 19.5349 | 16800 | 0.5681 | 0.9142 | 0.9143 |
0.0312 | 19.7674 | 17000 | 0.5612 | 0.9145 | 0.9146 |
0.0284 | 20.0 | 17200 | 0.5617 | 0.9141 | 0.9143 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.19.1
- Downloads last month
- 0
Model tree for phunganhsang/XMLRobertaLexical-finetuned_70KURL_new
Base model
FacebookAI/xlm-roberta-base