--- base_model: csebuetnlp/banglat5 tags: - generated_from_trainer model-index: - name: banglat5-bcoqa results: [] --- # banglat5-bcoqa This model is a fine-tuned version of [csebuetnlp/banglat5](https://huggingface.co/csebuetnlp/banglat5) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.4135 ## 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: 6 - eval_batch_size: 6 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 6.2253 | 0.03 | 700 | 2.8997 | | 3.5361 | 0.06 | 1400 | 2.5143 | | 2.8585 | 0.09 | 2100 | 2.3899 | | 2.7763 | 0.12 | 2800 | 2.3435 | | 2.6044 | 0.15 | 3500 | 2.3001 | | 2.6166 | 0.18 | 4200 | 2.2498 | | 2.5002 | 0.21 | 4900 | 2.1958 | | 2.4498 | 0.24 | 5600 | 2.1454 | | 2.4349 | 0.27 | 6300 | 2.1049 | | 2.3176 | 0.3 | 7000 | 2.0382 | | 2.2667 | 0.33 | 7700 | 1.9124 | | 2.2382 | 0.36 | 8400 | 1.7847 | | 2.1296 | 0.39 | 9100 | 1.6963 | | 2.0856 | 0.42 | 9800 | 1.6489 | | 2.0527 | 0.45 | 10500 | 1.6299 | | 2.0363 | 0.48 | 11200 | 1.6085 | | 1.9999 | 0.51 | 11900 | 1.5947 | | 1.9888 | 0.54 | 12600 | 1.5661 | | 1.9438 | 0.58 | 13300 | 1.5666 | | 1.9365 | 0.61 | 14000 | 1.5636 | | 1.9311 | 0.64 | 14700 | 1.5502 | | 1.9649 | 0.67 | 15400 | 1.5419 | | 1.9782 | 0.7 | 16100 | 1.5309 | | 1.8764 | 0.73 | 16800 | 1.5147 | | 1.9236 | 0.76 | 17500 | 1.5066 | | 1.8818 | 0.79 | 18200 | 1.4963 | | 1.9031 | 0.82 | 18900 | 1.4939 | | 1.8583 | 0.85 | 19600 | 1.4923 | | 1.8436 | 0.88 | 20300 | 1.4948 | | 1.8258 | 0.91 | 21000 | 1.4784 | | 1.8701 | 0.94 | 21700 | 1.4642 | | 1.8413 | 0.97 | 22400 | 1.4807 | | 1.8417 | 1.0 | 23100 | 1.4654 | | 1.7898 | 1.03 | 23800 | 1.4711 | | 1.7661 | 1.06 | 24500 | 1.4632 | | 1.7223 | 1.09 | 25200 | 1.4514 | | 1.7461 | 1.12 | 25900 | 1.4568 | | 1.7457 | 1.15 | 26600 | 1.4492 | | 1.7588 | 1.18 | 27300 | 1.4500 | | 1.6475 | 1.21 | 28000 | 1.4515 | | 1.7428 | 1.24 | 28700 | 1.4377 | | 1.782 | 1.27 | 29400 | 1.4456 | | 1.6906 | 1.3 | 30100 | 1.4435 | | 1.6865 | 1.33 | 30800 | 1.4378 | | 1.7806 | 1.36 | 31500 | 1.4327 | | 1.7444 | 1.39 | 32200 | 1.4372 | | 1.7136 | 1.42 | 32900 | 1.4293 | | 1.7252 | 1.45 | 33600 | 1.4246 | | 1.7209 | 1.48 | 34300 | 1.4218 | | 1.7523 | 1.51 | 35000 | 1.4283 | | 1.6808 | 1.54 | 35700 | 1.4216 | | 1.7167 | 1.57 | 36400 | 1.4246 | | 1.7246 | 1.6 | 37100 | 1.4171 | | 1.7614 | 1.63 | 37800 | 1.4204 | | 1.6704 | 1.66 | 38500 | 1.4116 | | 1.6823 | 1.7 | 39200 | 1.4213 | | 1.6744 | 1.73 | 39900 | 1.4236 | | 1.7086 | 1.76 | 40600 | 1.4197 | | 1.7179 | 1.79 | 41300 | 1.4156 | | 1.6223 | 1.82 | 42000 | 1.4205 | | 1.6817 | 1.85 | 42700 | 1.4159 | | 1.6786 | 1.88 | 43400 | 1.4131 | | 1.7163 | 1.91 | 44100 | 1.4147 | | 1.6381 | 1.94 | 44800 | 1.4131 | | 1.6961 | 1.97 | 45500 | 1.4134 | | 1.6247 | 2.0 | 46200 | 1.4135 | ### Framework versions - Transformers 4.39.0.dev0 - Pytorch 2.2.1+cu121 - Datasets 2.16.1 - Tokenizers 0.15.1