<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilbert-base-uncased-finetuned-nitro
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3930
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 200
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.8306 | 1.0 | 5 | 3.2319 |
2.5782 | 2.0 | 10 | 2.4410 |
2.6843 | 3.0 | 15 | 2.2280 |
2.4366 | 4.0 | 20 | 1.9308 |
2.3116 | 5.0 | 25 | 2.3071 |
2.2877 | 6.0 | 30 | 2.5556 |
2.4158 | 7.0 | 35 | 2.6973 |
2.2463 | 8.0 | 40 | 1.9751 |
2.2046 | 9.0 | 45 | 2.2329 |
1.675 | 10.0 | 50 | 2.3977 |
2.398 | 11.0 | 55 | 2.1521 |
2.1949 | 12.0 | 60 | 2.5294 |
1.9113 | 13.0 | 65 | 2.1196 |
2.1362 | 14.0 | 70 | 2.3208 |
2.8067 | 15.0 | 75 | 3.0091 |
1.8936 | 16.0 | 80 | 2.3815 |
1.785 | 17.0 | 85 | 2.6941 |
2.0525 | 18.0 | 90 | 2.5582 |
2.2101 | 19.0 | 95 | 2.6840 |
1.8584 | 20.0 | 100 | 2.2681 |
1.7072 | 21.0 | 105 | 2.3054 |
1.603 | 22.0 | 110 | 2.7518 |
1.8076 | 23.0 | 115 | 2.3547 |
1.9246 | 24.0 | 120 | 2.1844 |
1.6282 | 25.0 | 125 | 1.5606 |
2.087 | 26.0 | 130 | 2.1277 |
1.7423 | 27.0 | 135 | 1.8514 |
1.8819 | 28.0 | 140 | 1.9988 |
2.2313 | 29.0 | 145 | 1.8946 |
2.108 | 30.0 | 150 | 2.3753 |
1.9609 | 31.0 | 155 | 2.5666 |
2.2095 | 32.0 | 160 | 1.8381 |
2.1499 | 33.0 | 165 | 2.4213 |
1.5674 | 34.0 | 170 | 2.2492 |
2.0289 | 35.0 | 175 | 2.1717 |
1.9795 | 36.0 | 180 | 2.3377 |
1.977 | 37.0 | 185 | 1.8292 |
1.6325 | 38.0 | 190 | 2.5112 |
1.8168 | 39.0 | 195 | 2.2321 |
1.4628 | 40.0 | 200 | 2.3930 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.9.0
- Tokenizers 0.13.2