<!-- 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. -->
neuroscience-to-dev-bio-5
This model is a fine-tuned version of facebook/bart-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0170
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: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 128
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5000
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
19.0123 | 0.98 | 8 | 17.3893 |
16.2978 | 1.98 | 16 | 14.4660 |
13.2877 | 2.98 | 24 | 11.8149 |
12.016 | 3.98 | 32 | 10.7524 |
10.9473 | 4.98 | 40 | 9.3172 |
9.5556 | 5.98 | 48 | 7.3381 |
7.6993 | 6.98 | 56 | 5.8158 |
6.5798 | 7.98 | 64 | 5.1533 |
5.8632 | 8.98 | 72 | 4.6010 |
5.2411 | 9.98 | 80 | 4.0297 |
4.5648 | 10.98 | 88 | 3.3842 |
3.7885 | 11.98 | 96 | 2.6418 |
2.9055 | 12.98 | 104 | 1.8169 |
1.9604 | 13.98 | 112 | 1.0384 |
1.1051 | 14.98 | 120 | 0.4906 |
0.5087 | 15.98 | 128 | 0.2180 |
0.2096 | 16.98 | 136 | 0.1062 |
0.0906 | 17.98 | 144 | 0.0560 |
0.0417 | 18.98 | 152 | 0.0277 |
0.0223 | 19.98 | 160 | 0.0210 |
0.0158 | 20.98 | 168 | 0.0186 |
0.0121 | 21.98 | 176 | 0.0222 |
0.0091 | 22.98 | 184 | 0.0176 |
0.0077 | 23.98 | 192 | 0.0159 |
0.0071 | 24.98 | 200 | 0.0160 |
0.0062 | 25.98 | 208 | 0.0143 |
0.006 | 26.98 | 216 | 0.0138 |
0.005 | 27.98 | 224 | 0.0152 |
0.0045 | 28.98 | 232 | 0.0152 |
0.0224 | 29.98 | 240 | 0.0143 |
0.0065 | 30.98 | 248 | 0.0187 |
0.0095 | 31.98 | 256 | 0.0181 |
0.0126 | 32.98 | 264 | 0.0167 |
0.0789 | 33.98 | 272 | 0.0373 |
0.5145 | 34.98 | 280 | 0.0170 |
Framework versions
- Transformers 4.22.1
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1