ConvertedEmojiT5-fintuned_AppReviews_32ep_32batch

This model is a fine-tuned version of maram00ali/CONVERTEDEmojiApp_Review_pretrained_T5_base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 4.0273

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 32

Training results

Training Loss	Epoch	Step	Validation Loss
7.4502	1.0	25	6.3007
5.5964	2.0	50	5.4523
4.8087	3.0	75	4.8659
4.3828	4.0	100	4.6815
4.102	5.0	125	4.3381
3.8679	6.0	150	4.2251
3.6813	7.0	175	4.0646
3.5024	8.0	200	4.0713
3.3388	9.0	225	4.0704
3.2091	10.0	250	3.9759
3.0804	11.0	275	4.0273
2.9532	12.0	300	4.0427
2.847	13.0	325	4.0273

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2